diff options
Diffstat (limited to 'tools/lib')
218 files changed, 70849 insertions, 0 deletions
diff --git a/tools/lib/api/Build b/tools/lib/api/Build new file mode 100644 index 000000000..6e2373db5 --- /dev/null +++ b/tools/lib/api/Build @@ -0,0 +1,9 @@ +libapi-y += fd/ +libapi-y += fs/ +libapi-y += cpu.o +libapi-y += debug.o +libapi-y += str_error_r.o + +$(OUTPUT)str_error_r.o: ../str_error_r.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile new file mode 100644 index 000000000..e21e1b40b --- /dev/null +++ b/tools/lib/api/Makefile @@ -0,0 +1,67 @@ +# SPDX-License-Identifier: GPL-2.0 +include ../../scripts/Makefile.include +include ../../scripts/utilities.mak # QUIET_CLEAN + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +CC ?= $(CROSS_COMPILE)gcc +AR ?= $(CROSS_COMPILE)ar +LD ?= $(CROSS_COMPILE)ld + +MAKEFLAGS += --no-print-directory + +LIBFILE = $(OUTPUT)libapi.a + +CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -fPIC + +ifeq ($(DEBUG),0) +ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -O3 +else + CFLAGS += -O6 +endif +endif + +ifeq ($(DEBUG),0) + CFLAGS += -D_FORTIFY_SOURCE +endif + +# Treat warnings as errors unless directed not to +ifneq ($(WERROR),0) + CFLAGS += -Werror +endif + +CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 +CFLAGS += -I$(srctree)/tools/lib/api +CFLAGS += -I$(srctree)/tools/include + +RM = rm -f + +API_IN := $(OUTPUT)libapi-in.o + +all: + +export srctree OUTPUT CC LD CFLAGS V +include $(srctree)/tools/build/Makefile.include + +all: fixdep $(LIBFILE) + +$(API_IN): FORCE + @$(MAKE) $(build)=libapi + +$(LIBFILE): $(API_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(API_IN) + +clean: + $(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \ + find $(or $(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) + +FORCE: + +.PHONY: clean FORCE diff --git a/tools/lib/api/cpu.c b/tools/lib/api/cpu.c new file mode 100644 index 000000000..4af6d4b7a --- /dev/null +++ b/tools/lib/api/cpu.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> + +#include "cpu.h" +#include "fs/fs.h" + +int cpu__get_max_freq(unsigned long long *freq) +{ + char entry[PATH_MAX]; + int cpu; + + if (sysfs__read_int("devices/system/cpu/online", &cpu) < 0) + return -1; + + snprintf(entry, sizeof(entry), + "devices/system/cpu/cpu%d/cpufreq/cpuinfo_max_freq", cpu); + + return sysfs__read_ull(entry, freq); +} diff --git a/tools/lib/api/cpu.h b/tools/lib/api/cpu.h new file mode 100644 index 000000000..90a102fb2 --- /dev/null +++ b/tools/lib/api/cpu.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __API_CPU__ +#define __API_CPU__ + +int cpu__get_max_freq(unsigned long long *freq); + +#endif /* __API_CPU__ */ diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h new file mode 100644 index 000000000..5a5820c11 --- /dev/null +++ b/tools/lib/api/debug-internal.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __API_DEBUG_INTERNAL_H__ +#define __API_DEBUG_INTERNAL_H__ + +#include "debug.h" + +#define __pr(func, fmt, ...) \ +do { \ + if ((func)) \ + (func)("libapi: " fmt, ##__VA_ARGS__); \ +} while (0) + +extern libapi_print_fn_t __pr_warn; +extern libapi_print_fn_t __pr_info; +extern libapi_print_fn_t __pr_debug; + +#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__) + +#endif /* __API_DEBUG_INTERNAL_H__ */ diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c new file mode 100644 index 000000000..7708f0558 --- /dev/null +++ b/tools/lib/api/debug.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdarg.h> +#include "debug.h" +#include "debug-internal.h" + +static int __base_pr(const char *format, ...) +{ + va_list args; + int err; + + va_start(args, format); + err = vfprintf(stderr, format, args); + va_end(args); + return err; +} + +libapi_print_fn_t __pr_warn = __base_pr; +libapi_print_fn_t __pr_info = __base_pr; +libapi_print_fn_t __pr_debug; + +void libapi_set_print(libapi_print_fn_t warn, + libapi_print_fn_t info, + libapi_print_fn_t debug) +{ + __pr_warn = warn; + __pr_info = info; + __pr_debug = debug; +} diff --git a/tools/lib/api/debug.h b/tools/lib/api/debug.h new file mode 100644 index 000000000..3684dd6e0 --- /dev/null +++ b/tools/lib/api/debug.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __API_DEBUG_H__ +#define __API_DEBUG_H__ + +typedef int (*libapi_print_fn_t)(const char *, ...); + +void libapi_set_print(libapi_print_fn_t warn, + libapi_print_fn_t info, + libapi_print_fn_t debug); + +#endif /* __API_DEBUG_H__ */ diff --git a/tools/lib/api/fd/Build b/tools/lib/api/fd/Build new file mode 100644 index 000000000..605d99f6d --- /dev/null +++ b/tools/lib/api/fd/Build @@ -0,0 +1 @@ +libapi-y += array.o diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c new file mode 100644 index 000000000..f0f195207 --- /dev/null +++ b/tools/lib/api/fd/array.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2014, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + */ +#include "array.h" +#include <errno.h> +#include <fcntl.h> +#include <poll.h> +#include <stdlib.h> +#include <unistd.h> +#include <string.h> + +void fdarray__init(struct fdarray *fda, int nr_autogrow) +{ + fda->entries = NULL; + fda->priv = NULL; + fda->nr = fda->nr_alloc = 0; + fda->nr_autogrow = nr_autogrow; +} + +int fdarray__grow(struct fdarray *fda, int nr) +{ + struct priv *priv; + int nr_alloc = fda->nr_alloc + nr; + size_t psize = sizeof(fda->priv[0]) * nr_alloc; + size_t size = sizeof(struct pollfd) * nr_alloc; + struct pollfd *entries = realloc(fda->entries, size); + + if (entries == NULL) + return -ENOMEM; + + priv = realloc(fda->priv, psize); + if (priv == NULL) { + free(entries); + return -ENOMEM; + } + + memset(&entries[fda->nr_alloc], 0, sizeof(struct pollfd) * nr); + memset(&priv[fda->nr_alloc], 0, sizeof(fda->priv[0]) * nr); + + fda->nr_alloc = nr_alloc; + fda->entries = entries; + fda->priv = priv; + return 0; +} + +struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow) +{ + struct fdarray *fda = calloc(1, sizeof(*fda)); + + if (fda != NULL) { + if (fdarray__grow(fda, nr_alloc)) { + free(fda); + fda = NULL; + } else { + fda->nr_autogrow = nr_autogrow; + } + } + + return fda; +} + +void fdarray__exit(struct fdarray *fda) +{ + free(fda->entries); + free(fda->priv); + fdarray__init(fda, 0); +} + +void fdarray__delete(struct fdarray *fda) +{ + fdarray__exit(fda); + free(fda); +} + +int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags) +{ + int pos = fda->nr; + + if (fda->nr == fda->nr_alloc && + fdarray__grow(fda, fda->nr_autogrow) < 0) + return -ENOMEM; + + fda->entries[fda->nr].fd = fd; + fda->entries[fda->nr].events = revents; + fda->priv[fda->nr].flags = flags; + fda->nr++; + return pos; +} + +int fdarray__dup_entry_from(struct fdarray *fda, int pos, struct fdarray *from) +{ + struct pollfd *entry; + int npos; + + if (pos >= from->nr) + return -EINVAL; + + entry = &from->entries[pos]; + + npos = fdarray__add(fda, entry->fd, entry->events, from->priv[pos].flags); + if (npos >= 0) + fda->priv[npos] = from->priv[pos]; + + return npos; +} + +int fdarray__filter(struct fdarray *fda, short revents, + void (*entry_destructor)(struct fdarray *fda, int fd, void *arg), + void *arg) +{ + int fd, nr = 0; + + if (fda->nr == 0) + return 0; + + for (fd = 0; fd < fda->nr; ++fd) { + if (!fda->entries[fd].events) + continue; + + if (fda->entries[fd].revents & revents) { + if (entry_destructor) + entry_destructor(fda, fd, arg); + + fda->entries[fd].revents = fda->entries[fd].events = 0; + continue; + } + + if (!(fda->priv[fd].flags & fdarray_flag__nonfilterable)) + ++nr; + } + + return nr; +} + +int fdarray__poll(struct fdarray *fda, int timeout) +{ + return poll(fda->entries, fda->nr, timeout); +} + +int fdarray__fprintf(struct fdarray *fda, FILE *fp) +{ + int fd, printed = fprintf(fp, "%d [ ", fda->nr); + + for (fd = 0; fd < fda->nr; ++fd) + printed += fprintf(fp, "%s%d", fd ? ", " : "", fda->entries[fd].fd); + + return printed + fprintf(fp, " ]"); +} diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h new file mode 100644 index 000000000..5c01f7b05 --- /dev/null +++ b/tools/lib/api/fd/array.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __API_FD_ARRAY__ +#define __API_FD_ARRAY__ + +#include <stdio.h> + +struct pollfd; + +/** + * struct fdarray: Array of file descriptors + * + * @priv: Per array entry priv area, users should access just its contents, + * not set it to anything, as it is kept in synch with @entries, being + * realloc'ed, * for instance, in fdarray__{grow,filter}. + * + * I.e. using 'fda->priv[N].idx = * value' where N < fda->nr is ok, + * but doing 'fda->priv = malloc(M)' is not allowed. + */ +struct fdarray { + int nr; + int nr_alloc; + int nr_autogrow; + struct pollfd *entries; + struct priv { + union { + int idx; + void *ptr; + }; + unsigned int flags; + } *priv; +}; + +enum fdarray_flags { + fdarray_flag__default = 0x00000000, + fdarray_flag__nonfilterable = 0x00000001, + fdarray_flag__non_perf_event = 0x00000002, +}; + +void fdarray__init(struct fdarray *fda, int nr_autogrow); +void fdarray__exit(struct fdarray *fda); + +struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow); +void fdarray__delete(struct fdarray *fda); + +int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags); +int fdarray__dup_entry_from(struct fdarray *fda, int pos, struct fdarray *from); +int fdarray__poll(struct fdarray *fda, int timeout); +int fdarray__filter(struct fdarray *fda, short revents, + void (*entry_destructor)(struct fdarray *fda, int fd, void *arg), + void *arg); +int fdarray__grow(struct fdarray *fda, int extra); +int fdarray__fprintf(struct fdarray *fda, FILE *fp); + +static inline int fdarray__available_entries(struct fdarray *fda) +{ + return fda->nr_alloc - fda->nr; +} + +#endif /* __API_FD_ARRAY__ */ diff --git a/tools/lib/api/fs/Build b/tools/lib/api/fs/Build new file mode 100644 index 000000000..0f75b2865 --- /dev/null +++ b/tools/lib/api/fs/Build @@ -0,0 +1,3 @@ +libapi-y += fs.o +libapi-y += tracing_path.o +libapi-y += cgroup.o diff --git a/tools/lib/api/fs/cgroup.c b/tools/lib/api/fs/cgroup.c new file mode 100644 index 000000000..1573dae42 --- /dev/null +++ b/tools/lib/api/fs/cgroup.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/stringify.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include "fs.h" + +struct cgroupfs_cache_entry { + char subsys[32]; + char mountpoint[PATH_MAX]; +}; + +/* just cache last used one */ +static struct cgroupfs_cache_entry cached; + +int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys) +{ + FILE *fp; + char *line = NULL; + size_t len = 0; + char *p, *path; + char mountpoint[PATH_MAX]; + + if (!strcmp(cached.subsys, subsys)) { + if (strlen(cached.mountpoint) < maxlen) { + strcpy(buf, cached.mountpoint); + return 0; + } + return -1; + } + + fp = fopen("/proc/mounts", "r"); + if (!fp) + return -1; + + /* + * in order to handle split hierarchy, we need to scan /proc/mounts + * and inspect every cgroupfs mount point to find one that has + * the given subsystem. If we found v1, just use it. If not we can + * use v2 path as a fallback. + */ + mountpoint[0] = '\0'; + + /* + * The /proc/mounts has the follow format: + * + * <devname> <mount point> <fs type> <options> ... + * + */ + while (getline(&line, &len, fp) != -1) { + /* skip devname */ + p = strchr(line, ' '); + if (p == NULL) + continue; + + /* save the mount point */ + path = ++p; + p = strchr(p, ' '); + if (p == NULL) + continue; + + *p++ = '\0'; + + /* check filesystem type */ + if (strncmp(p, "cgroup", 6)) + continue; + + if (p[6] == '2') { + /* save cgroup v2 path */ + strcpy(mountpoint, path); + continue; + } + + /* now we have cgroup v1, check the options for subsystem */ + p += 7; + + p = strstr(p, subsys); + if (p == NULL) + continue; + + /* sanity check: it should be separated by a space or a comma */ + if (!strchr(" ,", p[-1]) || !strchr(" ,", p[strlen(subsys)])) + continue; + + strcpy(mountpoint, path); + break; + } + free(line); + fclose(fp); + + strncpy(cached.subsys, subsys, sizeof(cached.subsys) - 1); + strcpy(cached.mountpoint, mountpoint); + + if (mountpoint[0] && strlen(mountpoint) < maxlen) { + strcpy(buf, mountpoint); + return 0; + } + return -1; +} diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c new file mode 100644 index 000000000..82f53d81a --- /dev/null +++ b/tools/lib/api/fs/fs.c @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <ctype.h> +#include <errno.h> +#include <limits.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/vfs.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> +#include <sys/mount.h> + +#include "fs.h" +#include "debug-internal.h" + +#define _STR(x) #x +#define STR(x) _STR(x) + +#ifndef SYSFS_MAGIC +#define SYSFS_MAGIC 0x62656572 +#endif + +#ifndef PROC_SUPER_MAGIC +#define PROC_SUPER_MAGIC 0x9fa0 +#endif + +#ifndef DEBUGFS_MAGIC +#define DEBUGFS_MAGIC 0x64626720 +#endif + +#ifndef TRACEFS_MAGIC +#define TRACEFS_MAGIC 0x74726163 +#endif + +#ifndef HUGETLBFS_MAGIC +#define HUGETLBFS_MAGIC 0x958458f6 +#endif + +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + +static const char * const sysfs__fs_known_mountpoints[] = { + "/sys", + 0, +}; + +static const char * const procfs__known_mountpoints[] = { + "/proc", + 0, +}; + +#ifndef DEBUGFS_DEFAULT_PATH +#define DEBUGFS_DEFAULT_PATH "/sys/kernel/debug" +#endif + +static const char * const debugfs__known_mountpoints[] = { + DEBUGFS_DEFAULT_PATH, + "/debug", + 0, +}; + + +#ifndef TRACEFS_DEFAULT_PATH +#define TRACEFS_DEFAULT_PATH "/sys/kernel/tracing" +#endif + +static const char * const tracefs__known_mountpoints[] = { + TRACEFS_DEFAULT_PATH, + "/sys/kernel/debug/tracing", + "/tracing", + "/trace", + 0, +}; + +static const char * const hugetlbfs__known_mountpoints[] = { + 0, +}; + +static const char * const bpf_fs__known_mountpoints[] = { + "/sys/fs/bpf", + 0, +}; + +struct fs { + const char *name; + const char * const *mounts; + char path[PATH_MAX]; + bool found; + bool checked; + long magic; +}; + +enum { + FS__SYSFS = 0, + FS__PROCFS = 1, + FS__DEBUGFS = 2, + FS__TRACEFS = 3, + FS__HUGETLBFS = 4, + FS__BPF_FS = 5, +}; + +#ifndef TRACEFS_MAGIC +#define TRACEFS_MAGIC 0x74726163 +#endif + +static struct fs fs__entries[] = { + [FS__SYSFS] = { + .name = "sysfs", + .mounts = sysfs__fs_known_mountpoints, + .magic = SYSFS_MAGIC, + .checked = false, + }, + [FS__PROCFS] = { + .name = "proc", + .mounts = procfs__known_mountpoints, + .magic = PROC_SUPER_MAGIC, + .checked = false, + }, + [FS__DEBUGFS] = { + .name = "debugfs", + .mounts = debugfs__known_mountpoints, + .magic = DEBUGFS_MAGIC, + .checked = false, + }, + [FS__TRACEFS] = { + .name = "tracefs", + .mounts = tracefs__known_mountpoints, + .magic = TRACEFS_MAGIC, + .checked = false, + }, + [FS__HUGETLBFS] = { + .name = "hugetlbfs", + .mounts = hugetlbfs__known_mountpoints, + .magic = HUGETLBFS_MAGIC, + .checked = false, + }, + [FS__BPF_FS] = { + .name = "bpf", + .mounts = bpf_fs__known_mountpoints, + .magic = BPF_FS_MAGIC, + .checked = false, + }, +}; + +static bool fs__read_mounts(struct fs *fs) +{ + bool found = false; + char type[100]; + FILE *fp; + + fp = fopen("/proc/mounts", "r"); + if (fp == NULL) + return NULL; + + while (!found && + fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", + fs->path, type) == 2) { + + if (strcmp(type, fs->name) == 0) + found = true; + } + + fclose(fp); + fs->checked = true; + return fs->found = found; +} + +static int fs__valid_mount(const char *fs, long magic) +{ + struct statfs st_fs; + + if (statfs(fs, &st_fs) < 0) + return -ENOENT; + else if ((long)st_fs.f_type != magic) + return -ENOENT; + + return 0; +} + +static bool fs__check_mounts(struct fs *fs) +{ + const char * const *ptr; + + ptr = fs->mounts; + while (*ptr) { + if (fs__valid_mount(*ptr, fs->magic) == 0) { + fs->found = true; + strcpy(fs->path, *ptr); + return true; + } + ptr++; + } + + return false; +} + +static void mem_toupper(char *f, size_t len) +{ + while (len) { + *f = toupper(*f); + f++; + len--; + } +} + +/* + * Check for "NAME_PATH" environment variable to override fs location (for + * testing). This matches the recommendation in Documentation/admin-guide/sysfs-rules.rst + * for SYSFS_PATH. + */ +static bool fs__env_override(struct fs *fs) +{ + char *override_path; + 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"); + + override_path = getenv(upper_name); + if (!override_path) + return false; + + fs->found = true; + fs->checked = true; + strncpy(fs->path, override_path, sizeof(fs->path) - 1); + fs->path[sizeof(fs->path) - 1] = '\0'; + return true; +} + +static const char *fs__get_mountpoint(struct fs *fs) +{ + if (fs__env_override(fs)) + return fs->path; + + if (fs__check_mounts(fs)) + return fs->path; + + if (fs__read_mounts(fs)) + return fs->path; + + return NULL; +} + +static const char *fs__mountpoint(int idx) +{ + struct fs *fs = &fs__entries[idx]; + + if (fs->found) + return (const char *)fs->path; + + /* the mount point was already checked for the mount point + * but and did not exist, so return NULL to avoid scanning again. + * This makes the found and not found paths cost equivalent + * in case of multiple calls. + */ + if (fs->checked) + return NULL; + + return fs__get_mountpoint(fs); +} + +static const char *mount_overload(struct fs *fs) +{ + size_t name_len = strlen(fs->name); + /* "PERF_" + name + "_ENVIRONMENT" + '\0' */ + char upper_name[5 + name_len + 12 + 1]; + + snprintf(upper_name, name_len, "PERF_%s_ENVIRONMENT", fs->name); + mem_toupper(upper_name, name_len); + + return getenv(upper_name) ?: *fs->mounts; +} + +static const char *fs__mount(int idx) +{ + struct fs *fs = &fs__entries[idx]; + const char *mountpoint; + + if (fs__mountpoint(idx)) + return (const char *)fs->path; + + mountpoint = mount_overload(fs); + + if (mount(NULL, mountpoint, fs->name, 0, NULL) < 0) + return NULL; + + return fs__check_mounts(fs) ? fs->path : NULL; +} + +#define FS(name, idx) \ +const char *name##__mountpoint(void) \ +{ \ + return fs__mountpoint(idx); \ +} \ + \ +const char *name##__mount(void) \ +{ \ + return fs__mount(idx); \ +} \ + \ +bool name##__configured(void) \ +{ \ + return name##__mountpoint() != NULL; \ +} + +FS(sysfs, FS__SYSFS); +FS(procfs, FS__PROCFS); +FS(debugfs, FS__DEBUGFS); +FS(tracefs, FS__TRACEFS); +FS(hugetlbfs, FS__HUGETLBFS); +FS(bpf_fs, FS__BPF_FS); + +int filename__read_int(const char *filename, int *value) +{ + char line[64]; + int fd = open(filename, O_RDONLY), err = -1; + + if (fd < 0) + return -1; + + if (read(fd, line, sizeof(line)) > 0) { + *value = atoi(line); + err = 0; + } + + close(fd); + return err; +} + +static int filename__read_ull_base(const char *filename, + unsigned long long *value, int base) +{ + char line[64]; + int fd = open(filename, O_RDONLY), err = -1; + + if (fd < 0) + return -1; + + if (read(fd, line, sizeof(line)) > 0) { + *value = strtoull(line, NULL, base); + if (*value != ULLONG_MAX) + err = 0; + } + + close(fd); + return err; +} + +/* + * Parses @value out of @filename with strtoull. + * By using 16 for base to treat the number as hex. + */ +int filename__read_xll(const char *filename, unsigned long long *value) +{ + return filename__read_ull_base(filename, value, 16); +} + +/* + * Parses @value out of @filename with strtoull. + * By using 0 for base, the strtoull detects the + * base automatically (see man strtoull). + */ +int filename__read_ull(const char *filename, unsigned long long *value) +{ + return filename__read_ull_base(filename, value, 0); +} + +#define STRERR_BUFSIZE 128 /* For the buffer size of strerror_r */ + +int filename__read_str(const char *filename, char **buf, size_t *sizep) +{ + size_t size = 0, alloc_size = 0; + void *bf = NULL, *nbf; + int fd, n, err = 0; + char sbuf[STRERR_BUFSIZE]; + + fd = open(filename, O_RDONLY); + if (fd < 0) + return -errno; + + do { + if (size == alloc_size) { + alloc_size += BUFSIZ; + nbf = realloc(bf, alloc_size); + if (!nbf) { + err = -ENOMEM; + break; + } + + bf = nbf; + } + + n = read(fd, bf + size, alloc_size - size); + if (n < 0) { + if (size) { + pr_warn("read failed %d: %s\n", errno, + strerror_r(errno, sbuf, sizeof(sbuf))); + err = 0; + } else + err = -errno; + + break; + } + + size += n; + } while (n > 0); + + if (!err) { + *sizep = size; + *buf = bf; + } else + free(bf); + + close(fd); + return err; +} + +int filename__write_int(const char *filename, int value) +{ + int fd = open(filename, O_WRONLY), err = -1; + char buf[64]; + + if (fd < 0) + return err; + + sprintf(buf, "%d", value); + if (write(fd, buf, sizeof(buf)) == sizeof(buf)) + err = 0; + + close(fd); + return err; +} + +int procfs__read_str(const char *entry, char **buf, size_t *sizep) +{ + char path[PATH_MAX]; + const char *procfs = procfs__mountpoint(); + + if (!procfs) + return -1; + + snprintf(path, sizeof(path), "%s/%s", procfs, entry); + + return filename__read_str(path, buf, sizep); +} + +static int sysfs__read_ull_base(const char *entry, + unsigned long long *value, int base) +{ + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + snprintf(path, sizeof(path), "%s/%s", sysfs, entry); + + return filename__read_ull_base(path, value, base); +} + +int sysfs__read_xll(const char *entry, unsigned long long *value) +{ + return sysfs__read_ull_base(entry, value, 16); +} + +int sysfs__read_ull(const char *entry, unsigned long long *value) +{ + return sysfs__read_ull_base(entry, value, 0); +} + +int sysfs__read_int(const char *entry, int *value) +{ + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + snprintf(path, sizeof(path), "%s/%s", sysfs, entry); + + return filename__read_int(path, value); +} + +int sysfs__read_str(const char *entry, char **buf, size_t *sizep) +{ + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + snprintf(path, sizeof(path), "%s/%s", sysfs, entry); + + return filename__read_str(path, buf, sizep); +} + +int sysfs__read_bool(const char *entry, bool *value) +{ + char *buf; + size_t size; + int ret; + + ret = sysfs__read_str(entry, &buf, &size); + if (ret < 0) + return ret; + + switch (buf[0]) { + case '1': + case 'y': + case 'Y': + *value = true; + break; + case '0': + case 'n': + case 'N': + *value = false; + break; + default: + ret = -1; + } + + free(buf); + + return ret; +} +int sysctl__read_int(const char *sysctl, int *value) +{ + char path[PATH_MAX]; + const char *procfs = procfs__mountpoint(); + + if (!procfs) + return -1; + + snprintf(path, sizeof(path), "%s/sys/%s", procfs, sysctl); + + return filename__read_int(path, value); +} + +int sysfs__write_int(const char *entry, int value) +{ + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + if (snprintf(path, sizeof(path), "%s/%s", sysfs, entry) >= PATH_MAX) + return -1; + + return filename__write_int(path, value); +} diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h new file mode 100644 index 000000000..aa222ca30 --- /dev/null +++ b/tools/lib/api/fs/fs.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __API_FS__ +#define __API_FS__ + +#include <stdbool.h> +#include <unistd.h> + +/* + * On most systems <limits.h> would have given us this, but not on some systems + * (e.g. GNU/Hurd). + */ +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +#define FS(name) \ + const char *name##__mountpoint(void); \ + const char *name##__mount(void); \ + bool name##__configured(void); \ + +/* + * The xxxx__mountpoint() entry points find the first match mount point for each + * filesystems listed below, where xxxx is the filesystem type. + * + * The interface is as follows: + * + * - If a mount point is found on first call, it is cached and used for all + * subsequent calls. + * + * - If a mount point is not found, NULL is returned on first call and all + * subsequent calls. + */ +FS(sysfs) +FS(procfs) +FS(debugfs) +FS(tracefs) +FS(hugetlbfs) +FS(bpf_fs) + +#undef FS + + +int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys); + +int filename__read_int(const char *filename, int *value); +int filename__read_ull(const char *filename, unsigned long long *value); +int filename__read_xll(const char *filename, unsigned long long *value); +int filename__read_str(const char *filename, char **buf, size_t *sizep); + +int filename__write_int(const char *filename, int value); + +int procfs__read_str(const char *entry, char **buf, size_t *sizep); + +int sysctl__read_int(const char *sysctl, int *value); +int sysfs__read_int(const char *entry, int *value); +int sysfs__read_ull(const char *entry, unsigned long long *value); +int sysfs__read_xll(const char *entry, unsigned long long *value); +int sysfs__read_str(const char *entry, char **buf, size_t *sizep); +int sysfs__read_bool(const char *entry, bool *value); + +int sysfs__write_int(const char *entry, int value); +#endif /* __API_FS__ */ diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c new file mode 100644 index 000000000..5afb11b30 --- /dev/null +++ b/tools/lib/api/fs/tracing_path.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _GNU_SOURCE +# define _GNU_SOURCE +#endif + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <linux/string.h> +#include <errno.h> +#include <unistd.h> +#include "fs.h" + +#include "tracing_path.h" + +static char tracing_mnt[PATH_MAX] = "/sys/kernel/debug"; +static char tracing_path[PATH_MAX] = "/sys/kernel/debug/tracing"; +static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events"; + +static void __tracing_path_set(const char *tracing, const char *mountpoint) +{ + snprintf(tracing_mnt, sizeof(tracing_mnt), "%s", mountpoint); + snprintf(tracing_path, sizeof(tracing_path), "%s/%s", + mountpoint, tracing); + snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s%s", + mountpoint, tracing, "events"); +} + +static const char *tracing_path_tracefs_mount(void) +{ + const char *mnt; + + mnt = tracefs__mount(); + if (!mnt) + return NULL; + + __tracing_path_set("", mnt); + + return tracing_path; +} + +static const char *tracing_path_debugfs_mount(void) +{ + const char *mnt; + + mnt = debugfs__mount(); + if (!mnt) + return NULL; + + __tracing_path_set("tracing/", mnt); + + return tracing_path; +} + +const char *tracing_path_mount(void) +{ + const char *mnt; + + mnt = tracing_path_tracefs_mount(); + if (mnt) + return mnt; + + mnt = tracing_path_debugfs_mount(); + + return mnt; +} + +void tracing_path_set(const char *mntpt) +{ + __tracing_path_set("tracing/", mntpt); +} + +char *get_tracing_file(const char *name) +{ + char *file; + + if (asprintf(&file, "%s/%s", tracing_path_mount(), name) < 0) + return NULL; + + return file; +} + +void put_tracing_file(char *file) +{ + free(file); +} + +char *get_events_file(const char *name) +{ + char *file; + + if (asprintf(&file, "%s/events/%s", tracing_path_mount(), name) < 0) + return NULL; + + return file; +} + +void put_events_file(char *file) +{ + free(file); +} + +DIR *tracing_events__opendir(void) +{ + DIR *dir = NULL; + char *path = get_tracing_file("events"); + + if (path) { + dir = opendir(path); + put_events_file(path); + } + + return dir; +} + +int tracing_path__strerror_open_tp(int err, char *buf, size_t size, + const char *sys, const char *name) +{ + char sbuf[128]; + char filename[PATH_MAX]; + + snprintf(filename, PATH_MAX, "%s/%s", sys, name ?: "*"); + + switch (err) { + case ENOENT: + /* + * We will get here if we can't find the tracepoint, but one of + * debugfs or tracefs is configured, which means you probably + * want some tracepoint which wasn't compiled in your kernel. + * - jirka + */ + if (debugfs__configured() || tracefs__configured()) { + /* sdt markers */ + if (!strncmp(filename, "sdt_", 4)) { + snprintf(buf, size, + "Error:\tFile %s/%s not found.\n" + "Hint:\tSDT event cannot be directly recorded on.\n" + "\tPlease first use 'perf probe %s:%s' before recording it.\n", + tracing_events_path, filename, sys, name); + } else { + snprintf(buf, size, + "Error:\tFile %s/%s not found.\n" + "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n", + tracing_events_path, filename); + } + break; + } + snprintf(buf, size, "%s", + "Error:\tUnable to find debugfs/tracefs\n" + "Hint:\tWas your kernel compiled with debugfs/tracefs support?\n" + "Hint:\tIs the debugfs/tracefs filesystem mounted?\n" + "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'"); + break; + case EACCES: { + snprintf(buf, size, + "Error:\tNo permissions to read %s/%s\n" + "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", + tracing_events_path, filename, tracing_path_mount()); + } + break; + default: + snprintf(buf, size, "%s", str_error_r(err, sbuf, sizeof(sbuf))); + break; + } + + return 0; +} diff --git a/tools/lib/api/fs/tracing_path.h b/tools/lib/api/fs/tracing_path.h new file mode 100644 index 000000000..a19136b08 --- /dev/null +++ b/tools/lib/api/fs/tracing_path.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __API_FS_TRACING_PATH_H +#define __API_FS_TRACING_PATH_H + +#include <linux/types.h> +#include <dirent.h> + +DIR *tracing_events__opendir(void); + +void tracing_path_set(const char *mountpoint); +const char *tracing_path_mount(void); + +char *get_tracing_file(const char *name); +void put_tracing_file(char *file); + +char *get_events_file(const char *name); +void put_events_file(char *file); + +#define zput_events_file(ptr) ({ free(*ptr); *ptr = NULL; }) + +int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name); +#endif /* __API_FS_TRACING_PATH_H */ diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h new file mode 100644 index 000000000..458acd294 --- /dev/null +++ b/tools/lib/api/io.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Lightweight buffered reading library. + * + * Copyright 2019 Google LLC. + */ +#ifndef __API_IO__ +#define __API_IO__ + +#include <stdlib.h> +#include <unistd.h> +#include <linux/types.h> + +struct io { + /* File descriptor being read/ */ + int fd; + /* Size of the read buffer. */ + unsigned int buf_len; + /* Pointer to storage for buffering read. */ + char *buf; + /* End of the storage. */ + char *end; + /* Currently accessed data pointer. */ + char *data; + /* Set true on when the end of file on read error. */ + bool eof; +}; + +static inline void io__init(struct io *io, int fd, + char *buf, unsigned int buf_len) +{ + io->fd = fd; + io->buf_len = buf_len; + io->buf = buf; + io->end = buf; + io->data = buf; + io->eof = false; +} + +/* Reads one character from the "io" file with similar semantics to fgetc. */ +static inline int io__get_char(struct io *io) +{ + char *ptr = io->data; + + if (io->eof) + return -1; + + if (ptr == io->end) { + ssize_t n = read(io->fd, io->buf, io->buf_len); + + if (n <= 0) { + io->eof = true; + return -1; + } + ptr = &io->buf[0]; + io->end = &io->buf[n]; + } + io->data = ptr + 1; + return *ptr; +} + +/* Read a hexadecimal value with no 0x prefix into the out argument hex. If the + * first character isn't hexadecimal returns -2, io->eof returns -1, otherwise + * returns the character after the hexadecimal value which may be -1 for eof. + * If the read value is larger than a u64 the high-order bits will be dropped. + */ +static inline int io__get_hex(struct io *io, __u64 *hex) +{ + bool first_read = true; + + *hex = 0; + while (true) { + int ch = io__get_char(io); + + if (ch < 0) + return ch; + if (ch >= '0' && ch <= '9') + *hex = (*hex << 4) | (ch - '0'); + else if (ch >= 'a' && ch <= 'f') + *hex = (*hex << 4) | (ch - 'a' + 10); + else if (ch >= 'A' && ch <= 'F') + *hex = (*hex << 4) | (ch - 'A' + 10); + else if (first_read) + return -2; + else + return ch; + first_read = false; + } +} + +/* Read a positive decimal value with out argument dec. If the first character + * isn't a decimal returns -2, io->eof returns -1, otherwise returns the + * character after the decimal value which may be -1 for eof. If the read value + * is larger than a u64 the high-order bits will be dropped. + */ +static inline int io__get_dec(struct io *io, __u64 *dec) +{ + bool first_read = true; + + *dec = 0; + while (true) { + int ch = io__get_char(io); + + if (ch < 0) + return ch; + if (ch >= '0' && ch <= '9') + *dec = (*dec * 10) + ch - '0'; + else if (first_read) + return -2; + else + return ch; + first_read = false; + } +} + +#endif /* __API_IO__ */ diff --git a/tools/lib/argv_split.c b/tools/lib/argv_split.c new file mode 100644 index 000000000..0a58ccf3f --- /dev/null +++ b/tools/lib/argv_split.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Helper function for splitting a string into an argv-like array. + */ + +#include <stdlib.h> +#include <linux/kernel.h> +#include <linux/ctype.h> +#include <linux/string.h> + +static const char *skip_arg(const char *cp) +{ + while (*cp && !isspace(*cp)) + cp++; + + return cp; +} + +static int count_argc(const char *str) +{ + int count = 0; + + while (*str) { + str = skip_spaces(str); + if (*str) { + count++; + str = skip_arg(str); + } + } + + return count; +} + +/** + * argv_free - free an argv + * @argv - the argument vector to be freed + * + * Frees an argv and the strings it points to. + */ +void argv_free(char **argv) +{ + char **p; + for (p = argv; *p; p++) { + free(*p); + *p = NULL; + } + + free(argv); +} + +/** + * argv_split - split a string at whitespace, returning an argv + * @str: the string to be split + * @argcp: returned argument count + * + * Returns an array of pointers to strings which are split out from + * @str. This is performed by strictly splitting on white-space; no + * quote processing is performed. Multiple whitespace characters are + * considered to be a single argument separator. The returned array + * is always NULL-terminated. Returns NULL on memory allocation + * failure. + */ +char **argv_split(const char *str, int *argcp) +{ + int argc = count_argc(str); + char **argv = calloc(argc + 1, sizeof(*argv)); + char **argvp; + + if (argv == NULL) + goto out; + + if (argcp) + *argcp = argc; + + argvp = argv; + + while (*str) { + str = skip_spaces(str); + + if (*str) { + const char *p = str; + char *t; + + str = skip_arg(str); + + t = strndup(p, str-p); + if (t == NULL) + goto fail; + *argvp++ = t; + } + } + *argvp = NULL; + +out: + return argv; + +fail: + argv_free(argv); + return NULL; +} diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c new file mode 100644 index 000000000..c3e487196 --- /dev/null +++ b/tools/lib/bitmap.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * From lib/bitmap.c + * Helper functions for bitmap.h. + */ +#include <linux/bitmap.h> + +unsigned int __bitmap_weight(const unsigned long *bitmap, int bits) +{ + unsigned int k, w = 0, lim = bits/BITS_PER_LONG; + + for (k = 0; k < lim; k++) + w += hweight_long(bitmap[k]); + + if (bits % BITS_PER_LONG) + w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits)); + + return w; +} + +void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k; + int nr = BITS_TO_LONGS(bits); + + for (k = 0; k < nr; k++) + dst[k] = bitmap1[k] | bitmap2[k]; +} + +size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits, + char *buf, size_t size) +{ + /* current bit is 'cur', most recently seen range is [rbot, rtop] */ + unsigned int cur, rbot, rtop; + bool first = true; + size_t ret = 0; + + rbot = cur = find_first_bit(bitmap, nbits); + while (cur < nbits) { + rtop = cur; + cur = find_next_bit(bitmap, nbits, cur + 1); + if (cur < nbits && cur <= rtop + 1) + continue; + + if (!first) + ret += scnprintf(buf + ret, size - ret, ","); + + first = false; + + ret += scnprintf(buf + ret, size - ret, "%d", rbot); + if (rbot < rtop) + ret += scnprintf(buf + ret, size - ret, "-%d", rtop); + + rbot = cur; + } + return ret; +} + +bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + unsigned int k; + unsigned int lim = bits/BITS_PER_LONG; + unsigned long result = 0; + + for (k = 0; k < lim; k++) + result |= (dst[k] = bitmap1[k] & bitmap2[k]); + if (bits % BITS_PER_LONG) + result |= (dst[k] = bitmap1[k] & bitmap2[k] & + BITMAP_LAST_WORD_MASK(bits)); + return result != 0; +} + +bool __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + unsigned int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap1[k] != bitmap2[k]) + return false; + + if (bits % BITS_PER_LONG) + if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) + return false; + + return true; +} + +bool __bitmap_intersects(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + unsigned int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap1[k] & bitmap2[k]) + return true; + + if (bits % BITS_PER_LONG) + if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) + return true; + return false; +} diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore new file mode 100644 index 000000000..0da84cb9e --- /dev/null +++ b/tools/lib/bpf/.gitignore @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +libbpf.pc +libbpf.so.* +TAGS +tags +cscope.* +/bpf_helper_defs.h diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build new file mode 100644 index 000000000..5a3dfb56d --- /dev/null +++ b/tools/lib/bpf/Build @@ -0,0 +1,4 @@ +libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ + netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ + btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ + usdt.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile new file mode 100644 index 000000000..4c904ef0b --- /dev/null +++ b/tools/lib/bpf/Makefile @@ -0,0 +1,288 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/lib/traceevent/Makefile + +RM ?= rm +srctree = $(abs_srctree) + +VERSION_SCRIPT := libbpf.map +LIBBPF_VERSION := $(shell \ + grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \ + sort -rV | head -n1 | cut -d'_' -f2) +LIBBPF_MAJOR_VERSION := $(word 1,$(subst ., ,$(LIBBPF_VERSION))) +LIBBPF_MINOR_VERSION := $(word 2,$(subst ., ,$(LIBBPF_VERSION))) + +MAKEFLAGS += --no-print-directory + +# 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 $(srctree))) +#$(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 $(srctree)/tools/scripts/Makefile.arch + +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= /usr/local +libdir = $(prefix)/$(libdir_relative) +man_dir = $(prefix)/share/man +man_dir_SQ = '$(subst ','\'',$(man_dir))' + +export man_dir man_dir_SQ INSTALL +export DESTDIR DESTDIR_SQ + +include $(srctree)/tools/scripts/Makefile.include + +# copy a bit from Linux kbuild + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +INCLUDES = -I$(or $(OUTPUT),.) \ + -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi + +export prefix libdir src obj + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) +libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) + +OBJ = $@ +N = + +LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION) +LIB_FILE = libbpf.a libbpf.so* +PC_FILE = libbpf.pc + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -O2 +endif + +# Append required CFLAGS +override CFLAGS += -std=gnu89 +override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum +override CFLAGS += -Werror -Wall +override CFLAGS += $(INCLUDES) +override CFLAGS += -fvisibility=hidden +override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 +override CFLAGS += $(CLANG_CROSS_FLAGS) + +# flags specific for shared library +SHLIB_FLAGS := -DSHARED -fPIC + +ifeq ($(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= + +all: + +export srctree OUTPUT CC LD CFLAGS V +include $(srctree)/tools/build/Makefile.include + +SHARED_OBJDIR := $(OUTPUT)sharedobjs/ +STATIC_OBJDIR := $(OUTPUT)staticobjs/ +BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o +BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o +BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h +BPF_GENERATED := $(BPF_HELPER_DEFS) + +LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) +LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) +PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE)) + +TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags) + +GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ + cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \ + sort -u | wc -l) +VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \ + grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) + +CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) + +all: fixdep + $(Q)$(MAKE) all_cmd + +all_cmd: $(CMD_TARGETS) check + +$(BPF_IN_SHARED): force $(BPF_GENERATED) + @(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 + @(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \ + (diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \ + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true + @(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) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" + +$(BPF_IN_STATIC): force $(BPF_GENERATED) + $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) + +$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h + $(QUIET_GEN)$(srctree)/scripts/bpf_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_SHARED) $(VERSION_SCRIPT) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \ + --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ + -Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@ + @ln -sf $(@F) $(OUTPUT)libbpf.so + @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) + +$(OUTPUT)libbpf.a: $(BPF_IN_STATIC) + $(QUIET_LINK)$(RM) -f $@; $(AR) rcs $@ $^ + +$(OUTPUT)libbpf.pc: + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(LIBBPF_VERSION)|" \ + < libbpf.pc.template > $@ + +check: check_abi check_version + +check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) + @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \ + 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 $(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 --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}'| \ + grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ + sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ + diff -u $(OUTPUT)libbpf_global_syms.tmp \ + $(OUTPUT)libbpf_versioned_syms.tmp; \ + rm $(OUTPUT)libbpf_global_syms.tmp \ + $(OUTPUT)libbpf_versioned_syms.tmp; \ + exit 1; \ + fi + +HDR_MAJ_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3) +HDR_MIN_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3) + +check_version: $(VERSION_SCRIPT) libbpf_version.h + @if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then \ + echo "Error: libbpf major version mismatch detected: " \ + "'$(HDR_MAJ_VERSION)' != '$(LIBBPF_MAJOR_VERSION)'" >&2; \ + exit 1; \ + fi + @if [ "$(HDR_MIN_VERSION)" != "$(LIBBPF_MINOR_VERSION)" ]; then \ + echo "Error: libbpf minor version mismatch detected: " \ + "'$(HDR_MIN_VERSION)' != '$(LIBBPF_MINOR_VERSION)'" >&2; \ + exit 1; \ + fi + +define do_install_mkdir + if [ ! -d '$(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) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' +endef + +install_lib: all_cmd + $(call QUIET_INSTALL, $(LIB_TARGET)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) + +SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h \ + bpf_helpers.h bpf_tracing.h bpf_endian.h bpf_core_read.h \ + skel_internal.h libbpf_version.h usdt.bpf.h +GEN_HDRS := $(BPF_GENERATED) + +INSTALL_PFX := $(DESTDIR)$(prefix)/include/bpf +INSTALL_SRC_HDRS := $(addprefix $(INSTALL_PFX)/, $(SRC_HDRS)) +INSTALL_GEN_HDRS := $(addprefix $(INSTALL_PFX)/, $(notdir $(GEN_HDRS))) + +$(INSTALL_SRC_HDRS): $(INSTALL_PFX)/%.h: %.h + $(call QUIET_INSTALL, $@) \ + $(call do_install,$<,$(prefix)/include/bpf,644) + +$(INSTALL_GEN_HDRS): $(INSTALL_PFX)/%.h: $(OUTPUT)%.h + $(call QUIET_INSTALL, $@) \ + $(call do_install,$<,$(prefix)/include/bpf,644) + +install_headers: $(BPF_GENERATED) $(INSTALL_SRC_HDRS) $(INSTALL_GEN_HDRS) + +install_pkgconfig: $(PC_FILE) + $(call QUIET_INSTALL, $(PC_FILE)) \ + $(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644) + +install: install_lib install_pkgconfig install_headers + +clean: + $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ + *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED) \ + $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ + $(addprefix $(OUTPUT), \ + *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc) + +PHONY += force cscope tags check check_abi check_version +force: + +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 new file mode 100644 index 000000000..1d49a0352 --- /dev/null +++ b/tools/lib/bpf/bpf.c @@ -0,0 +1,1125 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * common eBPF ELF operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see <http://www.gnu.org/licenses> + */ + +#include <stdlib.h> +#include <string.h> +#include <memory.h> +#include <unistd.h> +#include <asm/unistd.h> +#include <errno.h> +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/kernel.h> +#include <limits.h> +#include <sys/resource.h> +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +/* + * When building perf, unistd.h is overridden. __NR_bpf is + * required to be defined explicitly. + */ +#ifndef __NR_bpf +# if defined(__i386__) +# define __NR_bpf 357 +# elif defined(__x86_64__) +# define __NR_bpf 321 +# elif defined(__aarch64__) +# define __NR_bpf 280 +# elif defined(__sparc__) +# define __NR_bpf 349 +# elif defined(__s390__) +# define __NR_bpf 351 +# elif defined(__arc__) +# define __NR_bpf 280 +# elif defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 +# else +# error __NR_bpf not defined. libbpf does not support your arch. +# endif +#endif + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) +{ + return syscall(__NR_bpf, cmd, attr, size); +} + +static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) +{ + int fd; + + fd = sys_bpf(cmd, attr, size); + return ensure_good_fd(fd); +} + +int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) +{ + int fd; + + do { + fd = sys_bpf_fd(BPF_PROG_LOAD, attr, size); + } while (fd < 0 && errno == EAGAIN && --attempts > 0); + + return fd; +} + +/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to + * memcg-based memory accounting for BPF maps and progs. This was done in [0]. + * We use the support for bpf_ktime_get_coarse_ns() helper, which was added in + * the same 5.11 Linux release ([1]), to detect memcg-based accounting for BPF. + * + * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/ + * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") + */ +int probe_memcg_account(void) +{ + const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); + struct bpf_insn insns[] = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + union bpf_attr attr; + int prog_fd; + + /* attempt loading freplace trying to use custom BTF */ + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = insn_cnt; + attr.license = ptr_to_u64("GPL"); + + prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz); + if (prog_fd >= 0) { + close(prog_fd); + return 1; + } + return 0; +} + +static bool memlock_bumped; +static rlim_t memlock_rlim = RLIM_INFINITY; + +int libbpf_set_memlock_rlim(size_t memlock_bytes) +{ + if (memlock_bumped) + return libbpf_err(-EBUSY); + + memlock_rlim = memlock_bytes; + return 0; +} + +int bump_rlimit_memlock(void) +{ + struct rlimit rlim; + + /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ + if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) + return 0; + + memlock_bumped = true; + + /* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */ + if (memlock_rlim == 0) + return 0; + + rlim.rlim_cur = rlim.rlim_max = memlock_rlim; + if (setrlimit(RLIMIT_MEMLOCK, &rlim)) + return -errno; + + return 0; +} + +int bpf_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + union bpf_attr attr; + int fd; + + bump_rlimit_memlock(); + + memset(&attr, 0, attr_sz); + + if (!OPTS_VALID(opts, bpf_map_create_opts)) + return libbpf_err(-EINVAL); + + attr.map_type = map_type; + if (map_name && kernel_supports(NULL, FEAT_PROG_NAME)) + libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; + + attr.btf_fd = OPTS_GET(opts, btf_fd, 0); + attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0); + attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0); + attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0); + + attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0); + attr.map_flags = OPTS_GET(opts, map_flags, 0); + attr.map_extra = OPTS_GET(opts, map_extra, 0); + attr.numa_node = OPTS_GET(opts, numa_node, 0); + attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +static void * +alloc_zero_tailing_info(const void *orecord, __u32 cnt, + __u32 actual_rec_size, __u32 expected_rec_size) +{ + __u64 info_len = (__u64)actual_rec_size * cnt; + void *info, *nrecord; + int i; + + info = malloc(info_len); + if (!info) + return NULL; + + /* zero out bytes kernel does not understand */ + nrecord = info; + for (i = 0; i < cnt; i++) { + memcpy(nrecord, orecord, expected_rec_size); + memset(nrecord + expected_rec_size, 0, + actual_rec_size - expected_rec_size); + orecord += actual_rec_size; + nrecord += actual_rec_size; + } + + return info; +} + +int bpf_prog_load(enum bpf_prog_type prog_type, + const char *prog_name, const char *license, + const struct bpf_insn *insns, size_t insn_cnt, + const struct bpf_prog_load_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, fd_array); + void *finfo = NULL, *linfo = NULL; + const char *func_info, *line_info; + __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; + __u32 func_info_rec_size, line_info_rec_size; + int fd, attempts; + union bpf_attr attr; + char *log_buf; + + bump_rlimit_memlock(); + + if (!OPTS_VALID(opts, bpf_prog_load_opts)) + return libbpf_err(-EINVAL); + + attempts = OPTS_GET(opts, attempts, 0); + if (attempts < 0) + return libbpf_err(-EINVAL); + if (attempts == 0) + attempts = PROG_LOAD_ATTEMPTS; + + memset(&attr, 0, attr_sz); + + attr.prog_type = prog_type; + attr.expected_attach_type = OPTS_GET(opts, expected_attach_type, 0); + + attr.prog_btf_fd = OPTS_GET(opts, prog_btf_fd, 0); + attr.prog_flags = OPTS_GET(opts, prog_flags, 0); + attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); + attr.kern_version = OPTS_GET(opts, kern_version, 0); + + if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) + libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); + attr.license = ptr_to_u64(license); + + if (insn_cnt > UINT_MAX) + return libbpf_err(-E2BIG); + + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)insn_cnt; + + attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); + attach_btf_obj_fd = OPTS_GET(opts, attach_btf_obj_fd, 0); + + if (attach_prog_fd && attach_btf_obj_fd) + return libbpf_err(-EINVAL); + + attr.attach_btf_id = OPTS_GET(opts, attach_btf_id, 0); + if (attach_prog_fd) + attr.attach_prog_fd = attach_prog_fd; + else + attr.attach_btf_obj_fd = attach_btf_obj_fd; + + log_buf = OPTS_GET(opts, log_buf, NULL); + log_size = OPTS_GET(opts, log_size, 0); + log_level = OPTS_GET(opts, log_level, 0); + + if (!!log_buf != !!log_size) + return libbpf_err(-EINVAL); + if (log_level > (4 | 2 | 1)) + return libbpf_err(-EINVAL); + if (log_level && !log_buf) + return libbpf_err(-EINVAL); + + func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0); + func_info = OPTS_GET(opts, func_info, NULL); + attr.func_info_rec_size = func_info_rec_size; + attr.func_info = ptr_to_u64(func_info); + attr.func_info_cnt = OPTS_GET(opts, func_info_cnt, 0); + + line_info_rec_size = OPTS_GET(opts, line_info_rec_size, 0); + line_info = OPTS_GET(opts, line_info, NULL); + attr.line_info_rec_size = line_info_rec_size; + attr.line_info = ptr_to_u64(line_info); + attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0); + + attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL)); + + if (log_level) { + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_size; + attr.log_level = log_level; + } + + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + if (fd >= 0) + return fd; + + /* After bpf_prog_load, the kernel may modify certain attributes + * to give user space a hint how to deal with loading failure. + * Check to see whether we can make some changes and load again. + */ + while (errno == E2BIG && (!finfo || !linfo)) { + if (!finfo && attr.func_info_cnt && + attr.func_info_rec_size < func_info_rec_size) { + /* try with corrected func info records */ + finfo = alloc_zero_tailing_info(func_info, + attr.func_info_cnt, + func_info_rec_size, + attr.func_info_rec_size); + if (!finfo) { + errno = E2BIG; + goto done; + } + + attr.func_info = ptr_to_u64(finfo); + attr.func_info_rec_size = func_info_rec_size; + } else if (!linfo && attr.line_info_cnt && + attr.line_info_rec_size < line_info_rec_size) { + linfo = alloc_zero_tailing_info(line_info, + attr.line_info_cnt, + line_info_rec_size, + attr.line_info_rec_size); + if (!linfo) { + errno = E2BIG; + goto done; + } + + attr.line_info = ptr_to_u64(linfo); + attr.line_info_rec_size = line_info_rec_size; + } else { + break; + } + + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + if (fd >= 0) + goto done; + } + + if (log_level == 0 && log_buf) { + /* log_level == 0 with non-NULL log_buf requires retrying on error + * with log_level == 1 and log_buf/log_buf_size set, to get details of + * failure + */ + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_size; + attr.log_level = 1; + + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + } +done: + /* free() doesn't affect errno, so we don't need to restore it */ + free(finfo); + free(linfo); + return libbpf_err_errno(fd); +} + +int bpf_map_update_elem(int fd, const void *key, const void *value, + __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_lookup_elem(int fd, const void *key, void *value) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + + ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + + ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_delete_elem(int fd, const void *key) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + + ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.flags = flags; + + ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_get_next_key(int fd, const void *key, void *next_key) +{ + const size_t attr_sz = offsetofend(union bpf_attr, next_key); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.next_key = ptr_to_u64(next_key); + + ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_freeze(int fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_fd); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + + ret = sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +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) +{ + const size_t attr_sz = offsetofend(union bpf_attr, batch); + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_map_batch_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.batch.map_fd = fd; + attr.batch.in_batch = ptr_to_u64(in_batch); + attr.batch.out_batch = ptr_to_u64(out_batch); + 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, attr_sz); + *count = attr.batch.count; + + return libbpf_err_errno(ret); +} + +int bpf_map_delete_batch(int fd, const void *keys, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL, + NULL, (void *)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, const void *keys, const void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL, + (void *)keys, (void *)values, count, opts); +} + +int bpf_obj_pin(int fd, const char *pathname) +{ + const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.pathname = ptr_to_u64((void *)pathname); + attr.bpf_fd = fd; + + ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_obj_get(const char *pathname) +{ + return bpf_obj_get_opts(pathname, NULL); +} + +int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + union bpf_attr attr; + int fd; + + if (!OPTS_VALID(opts, bpf_obj_get_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.pathname = ptr_to_u64((void *)pathname); + attr.file_flags = OPTS_GET(opts, file_flags, 0); + + fd = sys_bpf_fd(BPF_OBJ_GET, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +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_opts(prog_fd, target_fd, type, &opts); +} + +int bpf_prog_attach_opts(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_prog_attach_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.target_fd = target_fd; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + attr.attach_flags = OPTS_GET(opts, flags, 0); + attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); + + ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_prog_detach(int target_fd, enum bpf_attach_type type) +{ + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.target_fd = target_fd; + attr.attach_type = type; + + ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +{ + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.target_fd = target_fd; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + + ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_link_create(int prog_fd, int target_fd, + enum bpf_attach_type attach_type, + const struct bpf_link_create_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, link_create); + __u32 target_btf_id, iter_info_len; + union bpf_attr attr; + int fd, err; + + if (!OPTS_VALID(opts, bpf_link_create_opts)) + return libbpf_err(-EINVAL); + + iter_info_len = OPTS_GET(opts, iter_info_len, 0); + target_btf_id = OPTS_GET(opts, target_btf_id, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (iter_info_len || target_btf_id) { + if (iter_info_len && target_btf_id) + return libbpf_err(-EINVAL); + if (!OPTS_ZEROED(opts, target_btf_id)) + return libbpf_err(-EINVAL); + } + + memset(&attr, 0, attr_sz); + attr.link_create.prog_fd = prog_fd; + attr.link_create.target_fd = target_fd; + attr.link_create.attach_type = attach_type; + attr.link_create.flags = OPTS_GET(opts, flags, 0); + + if (target_btf_id) { + attr.link_create.target_btf_id = target_btf_id; + goto proceed; + } + + switch (attach_type) { + case BPF_TRACE_ITER: + attr.link_create.iter_info = ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0)); + attr.link_create.iter_info_len = iter_info_len; + break; + case BPF_PERF_EVENT: + attr.link_create.perf_event.bpf_cookie = OPTS_GET(opts, perf_event.bpf_cookie, 0); + if (!OPTS_ZEROED(opts, perf_event)) + return libbpf_err(-EINVAL); + break; + case BPF_TRACE_KPROBE_MULTI: + attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0); + attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0); + attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0)); + attr.link_create.kprobe_multi.addrs = ptr_to_u64(OPTS_GET(opts, kprobe_multi.addrs, 0)); + attr.link_create.kprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, kprobe_multi.cookies, 0)); + if (!OPTS_ZEROED(opts, kprobe_multi)) + return libbpf_err(-EINVAL); + break; + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + case BPF_LSM_MAC: + attr.link_create.tracing.cookie = OPTS_GET(opts, tracing.cookie, 0); + if (!OPTS_ZEROED(opts, tracing)) + return libbpf_err(-EINVAL); + break; + default: + if (!OPTS_ZEROED(opts, flags)) + return libbpf_err(-EINVAL); + break; + } +proceed: + fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, attr_sz); + if (fd >= 0) + return fd; + /* we'll get EINVAL if LINK_CREATE doesn't support attaching fentry + * and other similar programs + */ + err = -errno; + if (err != -EINVAL) + return libbpf_err(err); + + /* if user used features not supported by + * BPF_RAW_TRACEPOINT_OPEN command, then just give up immediately + */ + if (attr.link_create.target_fd || attr.link_create.target_btf_id) + return libbpf_err(err); + if (!OPTS_ZEROED(opts, sz)) + return libbpf_err(err); + + /* otherwise, for few select kinds of programs that can be + * attached using BPF_RAW_TRACEPOINT_OPEN command, try that as + * a fallback for older kernels + */ + switch (attach_type) { + case BPF_TRACE_RAW_TP: + case BPF_LSM_MAC: + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + return bpf_raw_tracepoint_open(NULL, prog_fd); + default: + return libbpf_err(err); + } +} + +int bpf_link_detach(int link_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, link_detach); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.link_detach.link_fd = link_fd; + + ret = sys_bpf(BPF_LINK_DETACH, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_link_update(int link_fd, int new_prog_fd, + const struct bpf_link_update_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, link_update); + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_link_update_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.link_update.link_fd = link_fd; + attr.link_update.new_prog_fd = new_prog_fd; + attr.link_update.flags = OPTS_GET(opts, flags, 0); + attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + + ret = sys_bpf(BPF_LINK_UPDATE, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_iter_create(int link_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, iter_create); + union bpf_attr attr; + int fd; + + memset(&attr, 0, attr_sz); + attr.iter_create.link_fd = link_fd; + + fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +int bpf_prog_query_opts(int target_fd, + enum bpf_attach_type type, + struct bpf_prog_query_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, query); + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_prog_query_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + + attr.query.target_fd = target_fd; + attr.query.attach_type = type; + attr.query.query_flags = OPTS_GET(opts, query_flags, 0); + attr.query.prog_cnt = OPTS_GET(opts, prog_cnt, 0); + attr.query.prog_ids = ptr_to_u64(OPTS_GET(opts, prog_ids, NULL)); + attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL)); + + ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz); + + OPTS_SET(opts, attach_flags, attr.query.attach_flags); + OPTS_SET(opts, prog_cnt, attr.query.prog_cnt); + + return libbpf_err_errno(ret); +} + +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) +{ + LIBBPF_OPTS(bpf_prog_query_opts, opts); + int ret; + + opts.query_flags = query_flags; + opts.prog_ids = prog_ids; + opts.prog_cnt = *prog_cnt; + + ret = bpf_prog_query_opts(target_fd, type, &opts); + + if (attach_flags) + *attach_flags = opts.attach_flags; + *prog_cnt = opts.prog_cnt; + + return libbpf_err_errno(ret); +} + +int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, test); + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_test_run_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.test.prog_fd = prog_fd; + attr.test.batch_size = OPTS_GET(opts, batch_size, 0); + attr.test.cpu = OPTS_GET(opts, cpu, 0); + attr.test.flags = OPTS_GET(opts, flags, 0); + attr.test.repeat = OPTS_GET(opts, repeat, 0); + attr.test.duration = OPTS_GET(opts, duration, 0); + attr.test.ctx_size_in = OPTS_GET(opts, ctx_size_in, 0); + attr.test.ctx_size_out = OPTS_GET(opts, ctx_size_out, 0); + attr.test.data_size_in = OPTS_GET(opts, data_size_in, 0); + attr.test.data_size_out = OPTS_GET(opts, data_size_out, 0); + attr.test.ctx_in = ptr_to_u64(OPTS_GET(opts, ctx_in, NULL)); + attr.test.ctx_out = ptr_to_u64(OPTS_GET(opts, ctx_out, NULL)); + attr.test.data_in = ptr_to_u64(OPTS_GET(opts, data_in, NULL)); + attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL)); + + ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, attr_sz); + + OPTS_SET(opts, data_size_out, attr.test.data_size_out); + OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out); + OPTS_SET(opts, duration, attr.test.duration); + OPTS_SET(opts, retval, attr.test.retval); + + return libbpf_err_errno(ret); +} + +static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); + union bpf_attr attr; + int err; + + memset(&attr, 0, attr_sz); + attr.start_id = start_id; + + err = sys_bpf(cmd, &attr, attr_sz); + if (!err) + *next_id = attr.next_id; + + return libbpf_err_errno(err); +} + +int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_PROG_GET_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); +} + +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_link_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_LINK_GET_NEXT_ID); +} + +int bpf_prog_get_fd_by_id(__u32 id) +{ + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); + union bpf_attr attr; + int fd; + + memset(&attr, 0, attr_sz); + attr.prog_id = id; + + fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +int bpf_map_get_fd_by_id(__u32 id) +{ + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); + union bpf_attr attr; + int fd; + + memset(&attr, 0, attr_sz); + attr.map_id = id; + + fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +int bpf_btf_get_fd_by_id(__u32 id) +{ + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); + union bpf_attr attr; + int fd; + + memset(&attr, 0, attr_sz); + attr.btf_id = id; + + fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +int bpf_link_get_fd_by_id(__u32 id) +{ + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); + union bpf_attr attr; + int fd; + + memset(&attr, 0, attr_sz); + attr.link_id = id; + + fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) +{ + const size_t attr_sz = offsetofend(union bpf_attr, info); + union bpf_attr attr; + int err; + + memset(&attr, 0, attr_sz); + attr.info.bpf_fd = bpf_fd; + attr.info.info_len = *info_len; + attr.info.info = ptr_to_u64(info); + + err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz); + if (!err) + *info_len = attr.info.info_len; + return libbpf_err_errno(err); +} + +int bpf_raw_tracepoint_open(const char *name, int prog_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint); + union bpf_attr attr; + int fd; + + memset(&attr, 0, attr_sz); + attr.raw_tracepoint.name = ptr_to_u64(name); + attr.raw_tracepoint.prog_fd = prog_fd; + + fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level); + union bpf_attr attr; + char *log_buf; + size_t log_size; + __u32 log_level; + int fd; + + bump_rlimit_memlock(); + + memset(&attr, 0, attr_sz); + + if (!OPTS_VALID(opts, bpf_btf_load_opts)) + return libbpf_err(-EINVAL); + + log_buf = OPTS_GET(opts, log_buf, NULL); + log_size = OPTS_GET(opts, log_size, 0); + log_level = OPTS_GET(opts, log_level, 0); + + if (log_size > UINT_MAX) + return libbpf_err(-EINVAL); + if (log_size && !log_buf) + return libbpf_err(-EINVAL); + + attr.btf = ptr_to_u64(btf_data); + attr.btf_size = btf_size; + /* log_level == 0 and log_buf != NULL means "try loading without + * log_buf, but retry with log_buf and log_level=1 on error", which is + * consistent across low-level and high-level BTF and program loading + * APIs within libbpf and provides a sensible behavior in practice + */ + if (log_level) { + attr.btf_log_buf = ptr_to_u64(log_buf); + attr.btf_log_size = (__u32)log_size; + attr.btf_log_level = log_level; + } + + fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); + if (fd < 0 && log_buf && log_level == 0) { + attr.btf_log_buf = ptr_to_u64(log_buf); + attr.btf_log_size = (__u32)log_size; + attr.btf_log_level = 1; + fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); + } + return libbpf_err_errno(fd); +} + +int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, + __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, + __u64 *probe_addr) +{ + const size_t attr_sz = offsetofend(union bpf_attr, task_fd_query); + union bpf_attr attr; + int err; + + memset(&attr, 0, attr_sz); + attr.task_fd_query.pid = pid; + attr.task_fd_query.fd = fd; + attr.task_fd_query.flags = flags; + attr.task_fd_query.buf = ptr_to_u64(buf); + attr.task_fd_query.buf_len = *buf_len; + + err = sys_bpf(BPF_TASK_FD_QUERY, &attr, attr_sz); + + *buf_len = attr.task_fd_query.buf_len; + *prog_id = attr.task_fd_query.prog_id; + *fd_type = attr.task_fd_query.fd_type; + *probe_offset = attr.task_fd_query.probe_offset; + *probe_addr = attr.task_fd_query.probe_addr; + + return libbpf_err_errno(err); +} + +int bpf_enable_stats(enum bpf_stats_type type) +{ + const size_t attr_sz = offsetofend(union bpf_attr, enable_stats); + union bpf_attr attr; + int fd; + + memset(&attr, 0, attr_sz); + attr.enable_stats.type = type; + + fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +int bpf_prog_bind_map(int prog_fd, int map_fd, + const struct bpf_prog_bind_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_bind_map); + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_prog_bind_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.prog_bind_map.prog_fd = prog_fd; + attr.prog_bind_map.map_fd = map_fd; + attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0); + + ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); + return libbpf_err_errno(ret); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h new file mode 100644 index 000000000..fddc05c66 --- /dev/null +++ b/tools/lib/bpf/bpf.h @@ -0,0 +1,445 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * common eBPF ELF operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see <http://www.gnu.org/licenses> + */ +#ifndef __LIBBPF_BPF_H +#define __LIBBPF_BPF_H + +#include <linux/bpf.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> + +#include "libbpf_common.h" +#include "libbpf_legacy.h" + +#ifdef __cplusplus +extern "C" { +#endif + +int libbpf_set_memlock_rlim(size_t memlock_bytes); + +struct bpf_map_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + __u32 btf_fd; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 btf_vmlinux_value_type_id; + + __u32 inner_map_fd; + __u32 map_flags; + __u64 map_extra; + + __u32 numa_node; + __u32 map_ifindex; +}; +#define bpf_map_create_opts__last_field map_ifindex + +LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts); + +struct bpf_prog_load_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + /* libbpf can retry BPF_PROG_LOAD command if bpf() syscall returns + * -EAGAIN. This field determines how many attempts libbpf has to + * make. If not specified, libbpf will use default value of 5. + */ + int attempts; + + enum bpf_attach_type expected_attach_type; + __u32 prog_btf_fd; + __u32 prog_flags; + __u32 prog_ifindex; + __u32 kern_version; + + __u32 attach_btf_id; + __u32 attach_prog_fd; + __u32 attach_btf_obj_fd; + + const int *fd_array; + + /* .BTF.ext func info data */ + const void *func_info; + __u32 func_info_cnt; + __u32 func_info_rec_size; + + /* .BTF.ext line info data */ + const void *line_info; + __u32 line_info_cnt; + __u32 line_info_rec_size; + + /* verifier log options */ + __u32 log_level; + __u32 log_size; + char *log_buf; +}; +#define bpf_prog_load_opts__last_field log_buf + +LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, + const char *prog_name, const char *license, + const struct bpf_insn *insns, size_t insn_cnt, + const struct bpf_prog_load_opts *opts); + +/* Flags to direct loading requirements */ +#define MAPS_RELAX_COMPAT 0x01 + +/* Recommended log buffer size */ +#define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ + +struct bpf_btf_load_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + /* kernel log options */ + char *log_buf; + __u32 log_level; + __u32 log_size; +}; +#define bpf_btf_load_opts__last_field log_size + +LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, + const struct bpf_btf_load_opts *opts); + +LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, + __u64 flags); + +LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value); +LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, + __u64 flags); +LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, + void *value); +LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, + void *value, __u64 flags); +LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); +LIBBPF_API int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags); +LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); +LIBBPF_API int bpf_map_freeze(int fd); + +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 + + +/** + * @brief **bpf_map_delete_batch()** allows for batch deletion of multiple + * elements in a BPF map. + * + * @param fd BPF map file descriptor + * @param keys pointer to an array of *count* keys + * @param count input and output parameter; on input **count** represents the + * number of elements in the map to delete in batch; + * on output if a non-EFAULT error is returned, **count** represents the number of deleted + * elements if the output **count** value is not equal to the input **count** value + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch deletion works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys, + __u32 *count, + const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements. + * + * The parameter *in_batch* is the address of the first element in the batch to read. + * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent + * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate + * that the batched lookup starts from the beginning of the map. + * + * The *keys* and *values* are output parameters which must point to memory large enough to + * hold *count* items based on the key and value size of the map *map_fd*. The *keys* + * buffer must be of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * @param fd BPF map file descriptor + * @param in_batch address of the first element in batch to read, can pass NULL to + * indicate that the batched lookup starts from the beginning of the map. + * @param out_batch output parameter that should be passed to next call as *in_batch* + * @param keys pointer to an array large enough for *count* keys + * @param values pointer to an array large enough for *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to read in batch; on output it's the number of elements that were + * successfully read. + * If a non-EFAULT error is returned, count will be set as the number of elements + * that were read before the error occurred. + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch lookup works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion + * of BPF map elements where each element is deleted after being retrieved. + * + * @param fd BPF map file descriptor + * @param in_batch address of the first element in batch to read, can pass NULL to + * get address of the first element in *out_batch* + * @param out_batch output parameter that should be passed to next call as *in_batch* + * @param keys pointer to an array of *count* keys + * @param values pointer to an array large enough for *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to read and delete in batch; on output it represents the number of + * elements that were successfully read and deleted + * If a non-**EFAULT** error code is returned and if the output **count** value + * is not equal to the input **count** value, up to **count** elements may + * have been deleted. + * if **EFAULT** is returned up to *count* elements may have been deleted without + * being returned via the *keys* and *values* output parameters. + * @param opts options for configuring the way the batch lookup and delete works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, + void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_update_batch()** updates multiple elements in a map + * by specifying keys and their corresponding values. + * + * The *keys* and *values* parameters must point to memory large enough + * to hold *count* items based on the key and value size of the map. + * + * The *opts* parameter can be used to control how *bpf_map_update_batch()* + * should handle keys that either do or do not already exist in the map. + * In particular the *flags* parameter of *bpf_map_batch_opts* can be + * one of the following: + * + * Note that *count* is an input and output parameter, where on output it + * represents how many elements were successfully updated. Also note that if + * **EFAULT** then *count* should not be trusted to be correct. + * + * **BPF_ANY** + * Create new elements or update existing. + * + * **BPF_NOEXIST** + * Create new elements only if they do not exist. + * + * **BPF_EXIST** + * Update existing elements. + * + * **BPF_F_LOCK** + * Update spin_lock-ed map elements. This must be + * specified if the map value contains a spinlock. + * + * @param fd BPF map file descriptor + * @param keys pointer to an array of *count* keys + * @param values pointer to an array of *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to update in batch; on output if a non-EFAULT error is returned, + * **count** represents the number of updated elements if the output **count** + * value is not equal to the input **count** value. + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch update works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts); + +struct bpf_obj_get_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + __u32 file_flags; + + size_t :0; +}; +#define bpf_obj_get_opts__last_field file_flags + +LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); +LIBBPF_API int bpf_obj_get(const char *pathname); +LIBBPF_API int bpf_obj_get_opts(const char *pathname, + const struct bpf_obj_get_opts *opts); + +struct bpf_prog_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + 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_opts(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); +LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); +LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, + enum bpf_attach_type type); + +union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */ +struct bpf_link_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + union bpf_iter_link_info *iter_info; + __u32 iter_info_len; + __u32 target_btf_id; + union { + struct { + __u64 bpf_cookie; + } perf_event; + struct { + __u32 flags; + __u32 cnt; + const char **syms; + const unsigned long *addrs; + const __u64 *cookies; + } kprobe_multi; + struct { + __u64 cookie; + } tracing; + }; + size_t :0; +}; +#define bpf_link_create_opts__last_field kprobe_multi.cookies + +LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, + enum bpf_attach_type attach_type, + const struct bpf_link_create_opts *opts); + +LIBBPF_API int bpf_link_detach(int link_fd); + +struct bpf_link_update_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; /* extra flags */ + __u32 old_prog_fd; /* expected old program FD */ +}; +#define bpf_link_update_opts__last_field old_prog_fd + +LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd, + const struct bpf_link_update_opts *opts); + +LIBBPF_API int bpf_iter_create(int link_fd); + +struct bpf_prog_test_run_attr { + int prog_fd; + int repeat; + const void *data_in; + __u32 data_size_in; + void *data_out; /* optional */ + __u32 data_size_out; /* in: max length of data_out + * out: length of data_out */ + __u32 retval; /* out: return code of the BPF program */ + __u32 duration; /* out: average per repetition in ns */ + const void *ctx_in; /* optional */ + __u32 ctx_size_in; + void *ctx_out; /* optional */ + __u32 ctx_size_out; /* in: max length of ctx_out + * out: length of cxt_out */ +}; + +LIBBPF_API int bpf_prog_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_link_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); +LIBBPF_API int bpf_link_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len); + +struct bpf_prog_query_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 query_flags; + __u32 attach_flags; /* output argument */ + __u32 *prog_ids; + __u32 prog_cnt; /* input+output argument */ + __u32 *prog_attach_flags; +}; +#define bpf_prog_query_opts__last_field prog_attach_flags + +LIBBPF_API int bpf_prog_query_opts(int target_fd, + enum bpf_attach_type type, + struct bpf_prog_query_opts *opts); +LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, + __u32 query_flags, __u32 *attach_flags, + __u32 *prog_ids, __u32 *prog_cnt); + +LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); +LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, + __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, + __u64 *probe_offset, __u64 *probe_addr); + +#ifdef __cplusplus +/* forward-declaring enums in C++ isn't compatible with pure C enums, so + * instead define bpf_enable_stats() as accepting int as an input + */ +LIBBPF_API int bpf_enable_stats(int type); +#else +enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */ +LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type); +#endif + +struct bpf_prog_bind_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; +}; +#define bpf_prog_bind_opts__last_field flags + +LIBBPF_API int bpf_prog_bind_map(int prog_fd, int map_fd, + const struct bpf_prog_bind_opts *opts); + +struct bpf_test_run_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + const void *data_in; /* optional */ + void *data_out; /* optional */ + __u32 data_size_in; + __u32 data_size_out; /* in: max length of data_out + * out: length of data_out + */ + const void *ctx_in; /* optional */ + void *ctx_out; /* optional */ + __u32 ctx_size_in; + __u32 ctx_size_out; /* in: max length of ctx_out + * out: length of cxt_out + */ + __u32 retval; /* out: return code of the BPF program */ + int repeat; + __u32 duration; /* out: average per repetition in ns */ + __u32 flags; + __u32 cpu; + __u32 batch_size; +}; +#define bpf_test_run_opts__last_field batch_size + +LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, + struct bpf_test_run_opts *opts); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_BPF_H */ diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h new file mode 100644 index 000000000..496e6a8ee --- /dev/null +++ b/tools/lib/bpf/bpf_core_read.h @@ -0,0 +1,484 @@ +/* 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, +}; + +/* second argument to __builtin_btf_type_id() built-in */ +enum bpf_type_id_kind { + BPF_TYPE_ID_LOCAL = 0, /* BTF type ID in local program */ + BPF_TYPE_ID_TARGET = 1, /* BTF type ID in target kernel */ +}; + +/* second argument to __builtin_preserve_type_info() built-in */ +enum bpf_type_info_kind { + BPF_TYPE_EXISTS = 0, /* type existence in target kernel */ + BPF_TYPE_SIZE = 1, /* type size in target kernel */ + BPF_TYPE_MATCHES = 2, /* type match in target kernel */ +}; + +/* second argument to __builtin_preserve_enum_value() built-in */ +enum bpf_enum_value_kind { + BPF_ENUMVAL_EXISTS = 0, /* enum value existence in kernel */ + BPF_ENUMVAL_VALUE = 1, /* enum value value relocation */ +}; + +#define __CORE_RELO(src, field, info) \ + __builtin_preserve_field_info((src)->field, BPF_FIELD_##info) + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ + bpf_probe_read_kernel( \ + (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_kernel( \ + (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_kernel() to read underlying + * integer storage. Macro functions as an expression and its return type is + * bpf_probe_read_kernel()'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; \ + \ + /* This is a so-called barrier_var() operation that makes specified \ + * variable "a black box" for optimizing compiler. \ + * It forces compiler to perform BYTE_OFFSET relocation on p and use \ + * its calculated value in the switch below, instead of applying \ + * the same relocation 4 times for each individual memory load. \ + */ \ + asm volatile("" : "=r"(p) : "0"(p)); \ + \ + switch (__CORE_RELO(s, field, BYTE_SIZE)) { \ + case 1: val = *(const unsigned char *)p; break; \ + case 2: val = *(const unsigned short *)p; break; \ + case 4: val = *(const unsigned int *)p; break; \ + case 8: val = *(const unsigned long long *)p; break; \ + } \ + 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; \ +}) + +#define ___bpf_field_ref1(field) (field) +#define ___bpf_field_ref2(type, field) (((typeof(type) *)0)->field) +#define ___bpf_field_ref(args...) \ + ___bpf_apply(___bpf_field_ref, ___bpf_narg(args))(args) + +/* + * Convenience macro to check that field actually exists in target kernel's. + * Returns: + * 1, if matching field is present in target kernel; + * 0, if no matching field found. + * + * Supports two forms: + * - field reference through variable access: + * bpf_core_field_exists(p->my_field); + * - field reference through type and field names: + * bpf_core_field_exists(struct my_type, my_field). + */ +#define bpf_core_field_exists(field...) \ + __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_EXISTS) + +/* + * Convenience macro to get the byte size of a field. Works for integers, + * struct/unions, pointers, arrays, and enums. + * + * Supports two forms: + * - field reference through variable access: + * bpf_core_field_size(p->my_field); + * - field reference through type and field names: + * bpf_core_field_size(struct my_type, my_field). + */ +#define bpf_core_field_size(field...) \ + __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_SIZE) + +/* + * Convenience macro to get field's byte offset. + * + * Supports two forms: + * - field reference through variable access: + * bpf_core_field_offset(p->my_field); + * - field reference through type and field names: + * bpf_core_field_offset(struct my_type, my_field). + */ +#define bpf_core_field_offset(field...) \ + __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_OFFSET) + +/* + * Convenience macro to get BTF type ID of a specified type, using a local BTF + * information. Return 32-bit unsigned integer with type ID from program's own + * BTF. Always succeeds. + */ +#define bpf_core_type_id_local(type) \ + __builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_LOCAL) + +/* + * Convenience macro to get BTF type ID of a target kernel's type that matches + * specified local type. + * Returns: + * - valid 32-bit unsigned type ID in kernel BTF; + * - 0, if no matching type was found in a target kernel BTF. + */ +#define bpf_core_type_id_kernel(type) \ + __builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_TARGET) + +/* + * Convenience macro to check that provided named type + * (struct/union/enum/typedef) exists in a target kernel. + * Returns: + * 1, if such type is present in target kernel's BTF; + * 0, if no matching type is found. + */ +#define bpf_core_type_exists(type) \ + __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS) + +/* + * Convenience macro to check that provided named type + * (struct/union/enum/typedef) "matches" that in a target kernel. + * Returns: + * 1, if the type matches in the target kernel's BTF; + * 0, if the type does not match any in the target kernel + */ +#define bpf_core_type_matches(type) \ + __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_MATCHES) + +/* + * Convenience macro to get the byte size of a provided named type + * (struct/union/enum/typedef) in a target kernel. + * Returns: + * >= 0 size (in bytes), if type is present in target kernel's BTF; + * 0, if no matching type is found. + */ +#define bpf_core_type_size(type) \ + __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_SIZE) + +/* + * Convenience macro to check that provided enumerator value is defined in + * a target kernel. + * Returns: + * 1, if specified enum type and its enumerator value are present in target + * kernel's BTF; + * 0, if no matching enum and/or enum value within that enum is found. + */ +#define bpf_core_enum_value_exists(enum_type, enum_value) \ + __builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_EXISTS) + +/* + * Convenience macro to get the integer value of an enumerator value in + * a target kernel. + * Returns: + * 64-bit value, if specified enum type and its enumerator value are + * present in target kernel's BTF; + * 0, if no matching enum and/or enum value within that enum is found. + */ +#define bpf_core_enum_value(enum_type, enum_value) \ + __builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_VALUE) + +/* + * bpf_core_read() abstracts away bpf_probe_read_kernel() 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_kernel(dst, sz, (const void *)__builtin_preserve_access_index(src)) + +/* NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. */ +#define bpf_core_read_user(dst, sz, src) \ + bpf_probe_read_user(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_kernel_str(dst, sz, (const void *)__builtin_preserve_access_index(src)) + +/* NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. */ +#define bpf_core_read_user_str(dst, sz, src) \ + bpf_probe_read_user_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(fn, src, a) ___read(fn, &__t, ___type(src), src, a); +#define ___rd_last(fn, ...) \ + ___read(fn, &__t, ___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__)); +#define ___rd_p1(fn, ...) const void *__t; ___rd_first(fn, __VA_ARGS__) +#define ___rd_p2(fn, ...) ___rd_p1(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) +#define ___rd_p3(fn, ...) ___rd_p2(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) +#define ___rd_p4(fn, ...) ___rd_p3(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) +#define ___rd_p5(fn, ...) ___rd_p4(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) +#define ___rd_p6(fn, ...) ___rd_p5(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) +#define ___rd_p7(fn, ...) ___rd_p6(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) +#define ___rd_p8(fn, ...) ___rd_p7(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) +#define ___rd_p9(fn, ...) ___rd_p8(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) +#define ___read_ptrs(fn, src, ...) \ + ___apply(___rd_p, ___narg(__VA_ARGS__))(fn, src, __VA_ARGS__) + +#define ___core_read0(fn, fn_ptr, dst, src, a) \ + ___read(fn, dst, ___type(src), src, a); +#define ___core_readN(fn, fn_ptr, dst, src, ...) \ + ___read_ptrs(fn_ptr, src, ___nolast(__VA_ARGS__)) \ + ___read(fn, dst, ___type(src, ___nolast(__VA_ARGS__)), __t, \ + ___last(__VA_ARGS__)); +#define ___core_read(fn, fn_ptr, dst, src, a, ...) \ + ___apply(___core_read, ___empty(__VA_ARGS__))(fn, fn_ptr, 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, bpf_core_read, \ + dst, (src), a, ##__VA_ARGS__) \ +}) + +/* + * Variant of BPF_CORE_READ_INTO() for reading from user-space memory. + * + * NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. + */ +#define BPF_CORE_READ_USER_INTO(dst, src, a, ...) ({ \ + ___core_read(bpf_core_read_user, bpf_core_read_user, \ + dst, (src), a, ##__VA_ARGS__) \ +}) + +/* Non-CO-RE variant of BPF_CORE_READ_INTO() */ +#define BPF_PROBE_READ_INTO(dst, src, a, ...) ({ \ + ___core_read(bpf_probe_read, bpf_probe_read, \ + dst, (src), a, ##__VA_ARGS__) \ +}) + +/* Non-CO-RE variant of BPF_CORE_READ_USER_INTO(). + * + * As no CO-RE relocations are emitted, source types can be arbitrary and are + * not restricted to kernel types only. + */ +#define BPF_PROBE_READ_USER_INTO(dst, src, a, ...) ({ \ + ___core_read(bpf_probe_read_user, bpf_probe_read_user, \ + 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, bpf_core_read, \ + dst, (src), a, ##__VA_ARGS__) \ +}) + +/* + * Variant of BPF_CORE_READ_STR_INTO() for reading from user-space memory. + * + * NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. + */ +#define BPF_CORE_READ_USER_STR_INTO(dst, src, a, ...) ({ \ + ___core_read(bpf_core_read_user_str, bpf_core_read_user, \ + dst, (src), a, ##__VA_ARGS__) \ +}) + +/* Non-CO-RE variant of BPF_CORE_READ_STR_INTO() */ +#define BPF_PROBE_READ_STR_INTO(dst, src, a, ...) ({ \ + ___core_read(bpf_probe_read_str, bpf_probe_read, \ + dst, (src), a, ##__VA_ARGS__) \ +}) + +/* + * Non-CO-RE variant of BPF_CORE_READ_USER_STR_INTO(). + * + * As no CO-RE relocations are emitted, source types can be arbitrary and are + * not restricted to kernel types only. + */ +#define BPF_PROBE_READ_USER_STR_INTO(dst, src, a, ...) ({ \ + ___core_read(bpf_probe_read_user_str, bpf_probe_read_user, \ + 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_kernel() 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_kernel() 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; \ +}) + +/* + * Variant of BPF_CORE_READ() for reading from user-space memory. + * + * NOTE: all the source types involved are still *kernel types* and need to + * exist in kernel (or kernel module) BTF, otherwise CO-RE relocation will + * fail. Custom user types are not relocatable with CO-RE. + * The typical situation in which BPF_CORE_READ_USER() might be used is to + * read kernel UAPI types from the user-space memory passed in as a syscall + * input argument. + */ +#define BPF_CORE_READ_USER(src, a, ...) ({ \ + ___type((src), a, ##__VA_ARGS__) __r; \ + BPF_CORE_READ_USER_INTO(&__r, (src), a, ##__VA_ARGS__); \ + __r; \ +}) + +/* Non-CO-RE variant of BPF_CORE_READ() */ +#define BPF_PROBE_READ(src, a, ...) ({ \ + ___type((src), a, ##__VA_ARGS__) __r; \ + BPF_PROBE_READ_INTO(&__r, (src), a, ##__VA_ARGS__); \ + __r; \ +}) + +/* + * Non-CO-RE variant of BPF_CORE_READ_USER(). + * + * As no CO-RE relocations are emitted, source types can be arbitrary and are + * not restricted to kernel types only. + */ +#define BPF_PROBE_READ_USER(src, a, ...) ({ \ + ___type((src), a, ##__VA_ARGS__) __r; \ + BPF_PROBE_READ_USER_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 000000000..ec9db4fec --- /dev/null +++ b/tools/lib/bpf/bpf_endian.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_ENDIAN__ +#define __BPF_ENDIAN__ + +/* + * Isolate byte #n and put it into byte #m, for __u##b type. + * E.g., moving byte #6 (nnnnnnnn) into byte #1 (mmmmmmmm) for __u64: + * 1) xxxxxxxx nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx + * 2) nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx 00000000 + * 3) 00000000 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn + * 4) 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn 00000000 + */ +#define ___bpf_mvb(x, b, n, m) ((__u##b)(x) << (b-(n+1)*8) >> (b-8) << (m*8)) + +#define ___bpf_swab16(x) ((__u16)( \ + ___bpf_mvb(x, 16, 0, 1) | \ + ___bpf_mvb(x, 16, 1, 0))) + +#define ___bpf_swab32(x) ((__u32)( \ + ___bpf_mvb(x, 32, 0, 3) | \ + ___bpf_mvb(x, 32, 1, 2) | \ + ___bpf_mvb(x, 32, 2, 1) | \ + ___bpf_mvb(x, 32, 3, 0))) + +#define ___bpf_swab64(x) ((__u64)( \ + ___bpf_mvb(x, 64, 0, 7) | \ + ___bpf_mvb(x, 64, 1, 6) | \ + ___bpf_mvb(x, 64, 2, 5) | \ + ___bpf_mvb(x, 64, 3, 4) | \ + ___bpf_mvb(x, 64, 4, 3) | \ + ___bpf_mvb(x, 64, 5, 2) | \ + ___bpf_mvb(x, 64, 6, 1) | \ + ___bpf_mvb(x, 64, 7, 0))) + +/* 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) ___bpf_swab16(x) +# define __bpf_constant_htons(x) ___bpf_swab16(x) +# define __bpf_ntohl(x) __builtin_bswap32(x) +# define __bpf_htonl(x) __builtin_bswap32(x) +# define __bpf_constant_ntohl(x) ___bpf_swab32(x) +# define __bpf_constant_htonl(x) ___bpf_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) ___bpf_swab64(x) +# define __bpf_constant_cpu_to_be64(x) ___bpf_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_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h new file mode 100644 index 000000000..223308931 --- /dev/null +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2021 Facebook */ +#ifndef __BPF_GEN_INTERNAL_H +#define __BPF_GEN_INTERNAL_H + +#include "bpf.h" + +struct ksym_relo_desc { + const char *name; + int kind; + int insn_idx; + bool is_weak; + bool is_typeless; +}; + +struct ksym_desc { + const char *name; + int ref; + int kind; + union { + /* used for kfunc */ + int off; + /* used for typeless ksym */ + bool typeless; + }; + int insn; +}; + +struct bpf_gen { + struct gen_loader_opts *opts; + void *data_start; + void *data_cur; + void *insn_start; + void *insn_cur; + ssize_t cleanup_label; + __u32 nr_progs; + __u32 nr_maps; + int log_level; + int error; + struct ksym_relo_desc *relos; + int relo_cnt; + struct bpf_core_relo *core_relos; + int core_relo_cnt; + char attach_target[128]; + int attach_kind; + struct ksym_desc *ksyms; + __u32 nr_ksyms; + int fd_array; + int nr_fd_array; +}; + +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps); +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps); +void bpf_gen__free(struct bpf_gen *gen); +void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); +void bpf_gen__map_create(struct bpf_gen *gen, + enum bpf_map_type map_type, const char *map_name, + __u32 key_size, __u32 value_size, __u32 max_entries, + struct bpf_map_create_opts *map_attr, int map_idx); +void bpf_gen__prog_load(struct bpf_gen *gen, + enum bpf_prog_type prog_type, const char *prog_name, + const char *license, struct bpf_insn *insns, size_t insn_cnt, + struct bpf_prog_load_opts *load_attr, int prog_idx); +void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size); +void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx); +void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type); +void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, + bool is_typeless, int kind, int insn_idx); +void bpf_gen__record_relo_core(struct bpf_gen *gen, const struct bpf_core_relo *core_relo); +void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int key, int inner_map_idx); + +#endif diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h new file mode 100644 index 000000000..2b3b300bf --- /dev/null +++ b/tools/lib/bpf/bpf_helpers.h @@ -0,0 +1,294 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_HELPERS__ +#define __BPF_HELPERS__ + +/* + * Note that bpf programs need to include either + * vmlinux.h (auto-generated from BTF) or linux/types.h + * in advance since bpf_helper_defs.h uses such types + * as __u64. + */ +#include "bpf_helper_defs.h" + +#define __uint(name, val) int (*name)[val] +#define __type(name, val) typeof(val) *name +#define __array(name, val) typeof(val) *name[] + +/* + * Helper macro to place programs, maps, license in + * different sections in elf_bpf file. Section names + * are interpreted by libbpf depending on the context (BPF programs, BPF maps, + * extern variables, etc). + * To allow use of SEC() with externs (e.g., for extern .maps declarations), + * make sure __attribute__((unused)) doesn't trigger compilation warning. + */ +#if __GNUC__ && !__clang__ + +/* + * Pragma macros are broken on GCC + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55578 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90400 + */ +#define SEC(name) __attribute__((section(name), used)) + +#else + +#define SEC(name) \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wignored-attributes\"") \ + __attribute__((section(name), used)) \ + _Pragma("GCC diagnostic pop") \ + +#endif + +/* Avoid 'linux/stddef.h' definition of '__always_inline'. */ +#undef __always_inline +#define __always_inline inline __attribute__((always_inline)) + +#ifndef __noinline +#define __noinline __attribute__((noinline)) +#endif +#ifndef __weak +#define __weak __attribute__((weak)) +#endif + +/* + * Use __hidden attribute to mark a non-static BPF subprogram effectively + * static for BPF verifier's verification algorithm purposes, allowing more + * extensive and permissive BPF verification process, taking into account + * subprogram's caller context. + */ +#define __hidden __attribute__((visibility("hidden"))) + +/* When utilizing vmlinux.h with BPF CO-RE, user BPF programs can't include + * any system-level headers (such as stddef.h, linux/version.h, etc), and + * commonly-used macros like NULL and KERNEL_VERSION aren't available through + * vmlinux.h. This just adds unnecessary hurdles and forces users to re-define + * them on their own. So as a convenience, provide such definitions here. + */ +#ifndef NULL +#define NULL ((void *)0) +#endif + +#ifndef KERNEL_VERSION +#define KERNEL_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c))) +#endif + +/* + * Helper macros to manipulate data structures + */ + +/* offsetof() definition that uses __builtin_offset() might not preserve field + * offset CO-RE relocation properly, so force-redefine offsetof() using + * old-school approach which works with CO-RE correctly + */ +#undef offsetof +#define offsetof(type, member) ((unsigned long)&((type *)0)->member) + +/* redefined container_of() to ensure we use the above offsetof() macro */ +#undef container_of +#define container_of(ptr, type, member) \ + ({ \ + void *__mptr = (void *)(ptr); \ + ((type *)(__mptr - offsetof(type, member))); \ + }) + +/* + * Compiler (optimization) barrier. + */ +#ifndef barrier +#define barrier() asm volatile("" ::: "memory") +#endif + +/* Variable-specific compiler (optimization) barrier. It's a no-op which makes + * compiler believe that there is some black box modification of a given + * variable and thus prevents compiler from making extra assumption about its + * value and potential simplifications and optimizations on this variable. + * + * E.g., compiler might often delay or even omit 32-bit to 64-bit casting of + * a variable, making some code patterns unverifiable. Putting barrier_var() + * in place will ensure that cast is performed before the barrier_var() + * invocation, because compiler has to pessimistically assume that embedded + * asm section might perform some extra operations on that variable. + * + * This is a variable-specific variant of more global barrier(). + */ +#ifndef barrier_var +#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) +#endif + +/* + * Helper macro to throw a compilation error if __bpf_unreachable() gets + * built into the resulting code. This works given BPF back end does not + * implement __builtin_trap(). This is useful to assert that certain paths + * of the program code are never used and hence eliminated by the compiler. + * + * For example, consider a switch statement that covers known cases used by + * the program. __bpf_unreachable() can then reside in the default case. If + * the program gets extended such that a case is not covered in the switch + * statement, then it will throw a build error due to the default case not + * being compiled out. + */ +#ifndef __bpf_unreachable +# define __bpf_unreachable() __builtin_trap() +#endif + +/* + * Helper function to perform a tail call with a constant/immediate map slot. + */ +#if __clang_major__ >= 8 && defined(__bpf__) +static __always_inline void +bpf_tail_call_static(void *ctx, const void *map, const __u32 slot) +{ + if (!__builtin_constant_p(slot)) + __bpf_unreachable(); + + /* + * Provide a hard guarantee that LLVM won't optimize setting r2 (map + * pointer) and r3 (constant map index) from _different paths_ ending + * up at the _same_ call insn as otherwise we won't be able to use the + * jmpq/nopl retpoline-free patching by the x86-64 JIT in the kernel + * given they mismatch. See also d2e4c1e6c294 ("bpf: Constant map key + * tracking for prog array pokes") for details on verifier tracking. + * + * Note on clobber list: we need to stay in-line with BPF calling + * convention, so even if we don't end up using r0, r4, r5, we need + * to mark them as clobber so that LLVM doesn't end up using them + * before / after the call. + */ + asm volatile("r1 = %[ctx]\n\t" + "r2 = %[map]\n\t" + "r3 = %[slot]\n\t" + "call 12" + :: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot) + : "r0", "r1", "r2", "r3", "r4", "r5"); +} +#endif + +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"))) +#define __ksym __attribute__((section(".ksyms"))) +#define __kptr __attribute__((btf_type_tag("kptr"))) +#define __kptr_ref __attribute__((btf_type_tag("kptr_ref"))) + +#ifndef ___bpf_concat +#define ___bpf_concat(a, b) a ## b +#endif +#ifndef ___bpf_apply +#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#endif +#ifndef ___bpf_nth +#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#endif +#ifndef ___bpf_narg +#define ___bpf_narg(...) \ + ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#endif + +#define ___bpf_fill0(arr, p, x) do {} while (0) +#define ___bpf_fill1(arr, p, x) arr[p] = x +#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args) +#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args) +#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args) +#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args) +#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args) +#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args) +#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args) +#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args) +#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args) +#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args) +#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args) +#define ___bpf_fill(arr, args...) \ + ___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args) + +/* + * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values + * in a structure. + */ +#define BPF_SEQ_PRINTF(seq, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* + * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of + * an array of u64. + */ +#define BPF_SNPRINTF(out, out_size, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_snprintf(out, out_size, ___fmt, \ + ___param, sizeof(___param)); \ +}) + +#ifdef BPF_NO_GLOBAL_DATA +#define BPF_PRINTK_FMT_MOD +#else +#define BPF_PRINTK_FMT_MOD static const +#endif + +#define __bpf_printk(fmt, ...) \ +({ \ + BPF_PRINTK_FMT_MOD char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* + * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments + * instead of an array of u64. + */ +#define __bpf_vprintk(fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_trace_vprintk(___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args + * Otherwise use __bpf_vprintk + */ +#define ___bpf_pick_printk(...) \ + ___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\ + __bpf_printk /*1*/, __bpf_printk /*0*/) + +/* Helper macro to print out debug messages */ +#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args) + +#endif diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c new file mode 100644 index 000000000..5c503096e --- /dev/null +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include <string.h> +#include <stdlib.h> +#include <linux/err.h> +#include <linux/bpf.h> +#include "libbpf.h" +#include "libbpf_internal.h" + +struct bpf_prog_linfo { + void *raw_linfo; + void *raw_jited_linfo; + __u32 *nr_jited_linfo_per_func; + __u32 *jited_linfo_func_idx; + __u32 nr_linfo; + __u32 nr_jited_func; + __u32 rec_size; + __u32 jited_rec_size; +}; + +static int dissect_jited_func(struct bpf_prog_linfo *prog_linfo, + const __u64 *ksym_func, const __u32 *ksym_len) +{ + __u32 nr_jited_func, nr_linfo; + const void *raw_jited_linfo; + const __u64 *jited_linfo; + __u64 last_jited_linfo; + /* + * Index to raw_jited_linfo: + * i: Index for searching the next ksym_func + * prev_i: Index to the last found ksym_func + */ + __u32 i, prev_i; + __u32 f; /* Index to ksym_func */ + + raw_jited_linfo = prog_linfo->raw_jited_linfo; + jited_linfo = raw_jited_linfo; + if (ksym_func[0] != *jited_linfo) + goto errout; + + prog_linfo->jited_linfo_func_idx[0] = 0; + nr_jited_func = prog_linfo->nr_jited_func; + nr_linfo = prog_linfo->nr_linfo; + + for (prev_i = 0, i = 1, f = 1; + i < nr_linfo && f < nr_jited_func; + i++) { + raw_jited_linfo += prog_linfo->jited_rec_size; + last_jited_linfo = *jited_linfo; + jited_linfo = raw_jited_linfo; + + if (ksym_func[f] == *jited_linfo) { + prog_linfo->jited_linfo_func_idx[f] = i; + + /* Sanity check */ + if (last_jited_linfo - ksym_func[f - 1] + 1 > + ksym_len[f - 1]) + goto errout; + + prog_linfo->nr_jited_linfo_per_func[f - 1] = + i - prev_i; + prev_i = i; + + /* + * The ksym_func[f] is found in jited_linfo. + * Look for the next one. + */ + f++; + } else if (*jited_linfo <= last_jited_linfo) { + /* Ensure the addr is increasing _within_ a func */ + goto errout; + } + } + + if (f != nr_jited_func) + goto errout; + + prog_linfo->nr_jited_linfo_per_func[nr_jited_func - 1] = + nr_linfo - prev_i; + + return 0; + +errout: + return -EINVAL; +} + +void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo) +{ + if (!prog_linfo) + return; + + free(prog_linfo->raw_linfo); + free(prog_linfo->raw_jited_linfo); + free(prog_linfo->nr_jited_linfo_per_func); + free(prog_linfo->jited_linfo_func_idx); + free(prog_linfo); +} + +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; + + if (!nr_linfo) + return errno = EINVAL, NULL; + + /* + * The min size that bpf_prog_linfo has to access for + * searching purpose. + */ + if (info->line_info_rec_size < + offsetof(struct bpf_line_info, file_name_off)) + return errno = EINVAL, NULL; + + prog_linfo = calloc(1, sizeof(*prog_linfo)); + if (!prog_linfo) + return errno = ENOMEM, NULL; + + /* Copy xlated line_info */ + prog_linfo->nr_linfo = nr_linfo; + prog_linfo->rec_size = info->line_info_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, data_sz); + + nr_jited_func = info->nr_jited_ksyms; + if (!nr_jited_func || + !info->jited_line_info || + info->nr_jited_line_info != nr_linfo || + info->jited_line_info_rec_size < sizeof(__u64) || + info->nr_jited_func_lens != nr_jited_func || + !info->jited_ksyms || + !info->jited_func_lens) + /* Not enough info to provide jited_line_info */ + return prog_linfo; + + /* Copy jited_line_info */ + prog_linfo->nr_jited_func = nr_jited_func; + prog_linfo->jited_rec_size = info->jited_line_info_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, data_sz); + + /* Number of jited_line_info per jited func */ + prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func * + sizeof(__u32)); + if (!prog_linfo->nr_jited_linfo_per_func) + goto err_free; + + /* + * For each jited func, + * the start idx to the "linfo" and "jited_linfo" array, + */ + prog_linfo->jited_linfo_func_idx = malloc(nr_jited_func * + sizeof(__u32)); + if (!prog_linfo->jited_linfo_func_idx) + goto err_free; + + if (dissect_jited_func(prog_linfo, + (__u64 *)(long)info->jited_ksyms, + (__u32 *)(long)info->jited_func_lens)) + goto err_free; + + return prog_linfo; + +err_free: + bpf_prog_linfo__free(prog_linfo); + return errno = EINVAL, NULL; +} + +const struct bpf_line_info * +bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo, + __u64 addr, __u32 func_idx, __u32 nr_skip) +{ + __u32 jited_rec_size, rec_size, nr_linfo, start, i; + const void *raw_jited_linfo, *raw_linfo; + const __u64 *jited_linfo; + + if (func_idx >= prog_linfo->nr_jited_func) + return errno = ENOENT, NULL; + + nr_linfo = prog_linfo->nr_jited_linfo_per_func[func_idx]; + if (nr_skip >= nr_linfo) + return errno = ENOENT, NULL; + + start = prog_linfo->jited_linfo_func_idx[func_idx] + nr_skip; + jited_rec_size = prog_linfo->jited_rec_size; + raw_jited_linfo = prog_linfo->raw_jited_linfo + + (start * jited_rec_size); + jited_linfo = raw_jited_linfo; + if (addr < *jited_linfo) + return errno = ENOENT, NULL; + + nr_linfo -= nr_skip; + rec_size = prog_linfo->rec_size; + raw_linfo = prog_linfo->raw_linfo + (start * rec_size); + for (i = 0; i < nr_linfo; i++) { + if (addr < *jited_linfo) + break; + + raw_linfo += rec_size; + raw_jited_linfo += jited_rec_size; + jited_linfo = raw_jited_linfo; + } + + return raw_linfo - rec_size; +} + +const struct bpf_line_info * +bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo, + __u32 insn_off, __u32 nr_skip) +{ + const struct bpf_line_info *linfo; + __u32 rec_size, nr_linfo, i; + const void *raw_linfo; + + nr_linfo = prog_linfo->nr_linfo; + if (nr_skip >= nr_linfo) + return errno = ENOENT, NULL; + + rec_size = prog_linfo->rec_size; + raw_linfo = prog_linfo->raw_linfo + (nr_skip * rec_size); + linfo = raw_linfo; + if (insn_off < linfo->insn_off) + return errno = ENOENT, NULL; + + nr_linfo -= nr_skip; + for (i = 0; i < nr_linfo; i++) { + if (insn_off < linfo->insn_off) + break; + + raw_linfo += rec_size; + linfo = raw_linfo; + } + + return raw_linfo - rec_size; +} diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h new file mode 100644 index 000000000..9c1b16890 --- /dev/null +++ b/tools/lib/bpf/bpf_tracing.h @@ -0,0 +1,670 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_TRACING_H__ +#define __BPF_TRACING_H__ + +#include <bpf/bpf_helpers.h> + +/* Scan the ARCH passed in from ARCH env variable (see Makefile) */ +#if defined(__TARGET_ARCH_x86) + #define bpf_target_x86 + #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 +#elif defined(__TARGET_ARCH_riscv) + #define bpf_target_riscv + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arc) + #define bpf_target_arc + #define bpf_target_defined +#else + +/* Fall back to what the compiler says */ +#if defined(__x86_64__) + #define bpf_target_x86 + #define bpf_target_defined +#elif defined(__s390__) + #define bpf_target_s390 + #define bpf_target_defined +#elif defined(__arm__) + #define bpf_target_arm + #define bpf_target_defined +#elif defined(__aarch64__) + #define bpf_target_arm64 + #define bpf_target_defined +#elif defined(__mips__) + #define bpf_target_mips + #define bpf_target_defined +#elif defined(__powerpc__) + #define bpf_target_powerpc + #define bpf_target_defined +#elif defined(__sparc__) + #define bpf_target_sparc + #define bpf_target_defined +#elif defined(__riscv) && __riscv_xlen == 64 + #define bpf_target_riscv + #define bpf_target_defined +#elif defined(__arc__) + #define bpf_target_arc + #define bpf_target_defined +#endif /* no compiler target */ + +#endif + +#ifndef __BPF_TARGET_MISSING +#define __BPF_TARGET_MISSING "GCC error \"Must specify a BPF target arch via __TARGET_ARCH_xxx\"" +#endif + +#if defined(bpf_target_x86) + +#if defined(__KERNEL__) || defined(__VMLINUX_H__) + +#define __PT_PARM1_REG di +#define __PT_PARM2_REG si +#define __PT_PARM3_REG dx +#define __PT_PARM4_REG cx +#define __PT_PARM5_REG r8 +#define __PT_RET_REG sp +#define __PT_FP_REG bp +#define __PT_RC_REG ax +#define __PT_SP_REG sp +#define __PT_IP_REG ip +/* syscall uses r10 for PARM4 */ +#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) + +#else + +#ifdef __i386__ + +#define __PT_PARM1_REG eax +#define __PT_PARM2_REG edx +#define __PT_PARM3_REG ecx +/* i386 kernel is built with -mregparm=3 */ +#define __PT_PARM4_REG __unsupported__ +#define __PT_PARM5_REG __unsupported__ +#define __PT_RET_REG esp +#define __PT_FP_REG ebp +#define __PT_RC_REG eax +#define __PT_SP_REG esp +#define __PT_IP_REG eip + +#else /* __i386__ */ + +#define __PT_PARM1_REG rdi +#define __PT_PARM2_REG rsi +#define __PT_PARM3_REG rdx +#define __PT_PARM4_REG rcx +#define __PT_PARM5_REG r8 +#define __PT_RET_REG rsp +#define __PT_FP_REG rbp +#define __PT_RC_REG rax +#define __PT_SP_REG rsp +#define __PT_IP_REG rip +/* syscall uses r10 for PARM4 */ +#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) + +#endif /* __i386__ */ + +#endif /* __KERNEL__ || __VMLINUX_H__ */ + +#elif defined(bpf_target_s390) + +struct pt_regs___s390 { + unsigned long orig_gpr2; +}; + +/* s390 provides user_pt_regs instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) +#define __PT_PARM1_REG gprs[2] +#define __PT_PARM2_REG gprs[3] +#define __PT_PARM3_REG gprs[4] +#define __PT_PARM4_REG gprs[5] +#define __PT_PARM5_REG gprs[6] +#define __PT_RET_REG gprs[14] +#define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG gprs[2] +#define __PT_SP_REG gprs[15] +#define __PT_IP_REG psw.addr +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2) + +#elif defined(bpf_target_arm) + +#define __PT_PARM1_REG uregs[0] +#define __PT_PARM2_REG uregs[1] +#define __PT_PARM3_REG uregs[2] +#define __PT_PARM4_REG uregs[3] +#define __PT_PARM5_REG uregs[4] +#define __PT_RET_REG uregs[14] +#define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG uregs[0] +#define __PT_SP_REG uregs[13] +#define __PT_IP_REG uregs[12] + +#elif defined(bpf_target_arm64) + +struct pt_regs___arm64 { + unsigned long orig_x0; +}; + +/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) +#define __PT_PARM1_REG regs[0] +#define __PT_PARM2_REG regs[1] +#define __PT_PARM3_REG regs[2] +#define __PT_PARM4_REG regs[3] +#define __PT_PARM5_REG regs[4] +#define __PT_RET_REG regs[30] +#define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG regs[0] +#define __PT_SP_REG sp +#define __PT_IP_REG pc +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0) + +#elif defined(bpf_target_mips) + +#define __PT_PARM1_REG regs[4] +#define __PT_PARM2_REG regs[5] +#define __PT_PARM3_REG regs[6] +#define __PT_PARM4_REG regs[7] +#define __PT_PARM5_REG regs[8] +#define __PT_RET_REG regs[31] +#define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG regs[2] +#define __PT_SP_REG regs[29] +#define __PT_IP_REG cp0_epc + +#elif defined(bpf_target_powerpc) + +#define __PT_PARM1_REG gpr[3] +#define __PT_PARM2_REG gpr[4] +#define __PT_PARM3_REG gpr[5] +#define __PT_PARM4_REG gpr[6] +#define __PT_PARM5_REG gpr[7] +#define __PT_RET_REG regs[31] +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG gpr[3] +#define __PT_SP_REG sp +#define __PT_IP_REG nip +/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx + +#elif defined(bpf_target_sparc) + +#define __PT_PARM1_REG u_regs[UREG_I0] +#define __PT_PARM2_REG u_regs[UREG_I1] +#define __PT_PARM3_REG u_regs[UREG_I2] +#define __PT_PARM4_REG u_regs[UREG_I3] +#define __PT_PARM5_REG u_regs[UREG_I4] +#define __PT_RET_REG u_regs[UREG_I7] +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG u_regs[UREG_I0] +#define __PT_SP_REG u_regs[UREG_FP] +/* Should this also be a bpf_target check for the sparc case? */ +#if defined(__arch64__) +#define __PT_IP_REG tpc +#else +#define __PT_IP_REG pc +#endif + +#elif defined(bpf_target_riscv) + +#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) +#define __PT_PARM1_REG a0 +#define __PT_PARM2_REG a1 +#define __PT_PARM3_REG a2 +#define __PT_PARM4_REG a3 +#define __PT_PARM5_REG a4 +#define __PT_RET_REG ra +#define __PT_FP_REG s0 +#define __PT_RC_REG a0 +#define __PT_SP_REG sp +#define __PT_IP_REG pc +/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx + +#elif defined(bpf_target_arc) + +/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) +#define __PT_PARM1_REG scratch.r0 +#define __PT_PARM2_REG scratch.r1 +#define __PT_PARM3_REG scratch.r2 +#define __PT_PARM4_REG scratch.r3 +#define __PT_PARM5_REG scratch.r4 +#define __PT_RET_REG scratch.blink +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG scratch.r0 +#define __PT_SP_REG scratch.sp +#define __PT_IP_REG scratch.ret +/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx + +#endif + +#if defined(bpf_target_defined) + +struct pt_regs; + +/* allow some architecutres to override `struct pt_regs` */ +#ifndef __PT_REGS_CAST +#define __PT_REGS_CAST(x) (x) +#endif + +#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG) +#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG) +#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG) +#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG) +#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG) +#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG) +#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG) +#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG) +#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG) +#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG) + +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG) + +#if defined(bpf_target_powerpc) + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP + +#elif defined(bpf_target_sparc) + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP + +#else + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) \ + ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ + ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) + +#endif + +#ifndef PT_REGS_PARM1_SYSCALL +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x) +#endif +#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x) +#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x) +#ifndef PT_REGS_PARM4_SYSCALL +#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x) +#endif +#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x) + +#ifndef PT_REGS_PARM1_CORE_SYSCALL +#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x) +#endif +#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x) +#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x) +#ifndef PT_REGS_PARM4_CORE_SYSCALL +#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x) +#endif +#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x) + +#else /* defined(bpf_target_defined) */ + +#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_SP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_IP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_SP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_IP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#endif /* defined(bpf_target_defined) */ + +/* + * When invoked from a syscall handler kprobe, returns a pointer to a + * struct pt_regs containing syscall arguments and suitable for passing to + * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL(). + */ +#ifndef PT_REGS_SYSCALL_REGS +/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx)) +#endif + +#ifndef ___bpf_concat +#define ___bpf_concat(a, b) a ## b +#endif +#ifndef ___bpf_apply +#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#endif +#ifndef ___bpf_nth +#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#endif +#ifndef ___bpf_narg +#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#endif + +#define ___bpf_ctx_cast0() ctx +#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] +#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] +#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] +#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] +#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] +#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] +#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] +#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] +#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] +#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9] +#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10] +#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11] +#define ___bpf_ctx_cast(args...) ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) + +/* + * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and + * similar kinds of BPF programs, that accept input arguments as a single + * pointer to untyped u64 array, where each u64 can actually be a typed + * pointer or integer of different size. Instead of requring user to write + * manual casts and work with array elements by index, BPF_PROG macro + * allows user to declare a list of named and typed input arguments in the + * same syntax as for normal C function. All the casting is hidden and + * performed transparently, while user code can just assume working with + * function arguments of specified type and name. + * + * Original raw context argument is preserved as well as 'ctx' argument. + * This is useful when using BPF helpers that expect original context + * as one of the parameters (e.g., for bpf_perf_event_output()). + */ +#define BPF_PROG(name, args...) \ +name(unsigned long long *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_ctx_cast(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args) + +#ifndef ___bpf_nth2 +#define ___bpf_nth2(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, \ + _14, _15, _16, _17, _18, _19, _20, _21, _22, _23, _24, N, ...) N +#endif +#ifndef ___bpf_narg2 +#define ___bpf_narg2(...) \ + ___bpf_nth2(_, ##__VA_ARGS__, 12, 12, 11, 11, 10, 10, 9, 9, 8, 8, 7, 7, \ + 6, 6, 5, 5, 4, 4, 3, 3, 2, 2, 1, 1, 0) +#endif + +#define ___bpf_treg_cnt(t) \ + __builtin_choose_expr(sizeof(t) == 1, 1, \ + __builtin_choose_expr(sizeof(t) == 2, 1, \ + __builtin_choose_expr(sizeof(t) == 4, 1, \ + __builtin_choose_expr(sizeof(t) == 8, 1, \ + __builtin_choose_expr(sizeof(t) == 16, 2, \ + (void)0))))) + +#define ___bpf_reg_cnt0() (0) +#define ___bpf_reg_cnt1(t, x) (___bpf_reg_cnt0() + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt2(t, x, args...) (___bpf_reg_cnt1(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt3(t, x, args...) (___bpf_reg_cnt2(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt4(t, x, args...) (___bpf_reg_cnt3(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt5(t, x, args...) (___bpf_reg_cnt4(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt6(t, x, args...) (___bpf_reg_cnt5(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt7(t, x, args...) (___bpf_reg_cnt6(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt8(t, x, args...) (___bpf_reg_cnt7(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt9(t, x, args...) (___bpf_reg_cnt8(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt10(t, x, args...) (___bpf_reg_cnt9(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt11(t, x, args...) (___bpf_reg_cnt10(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt12(t, x, args...) (___bpf_reg_cnt11(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt(args...) ___bpf_apply(___bpf_reg_cnt, ___bpf_narg2(args))(args) + +#define ___bpf_union_arg(t, x, n) \ + __builtin_choose_expr(sizeof(t) == 1, ({ union { __u8 z[1]; t x; } ___t = { .z = {ctx[n]}}; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 2, ({ union { __u16 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 4, ({ union { __u32 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 8, ({ union { __u64 z[1]; t x; } ___t = {.z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 16, ({ union { __u64 z[2]; t x; } ___t = {.z = {ctx[n], ctx[n + 1]} }; ___t.x; }), \ + (void)0))))) + +#define ___bpf_ctx_arg0(n, args...) +#define ___bpf_ctx_arg1(n, t, x) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt1(t, x)) +#define ___bpf_ctx_arg2(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt2(t, x, args)) ___bpf_ctx_arg1(n, args) +#define ___bpf_ctx_arg3(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt3(t, x, args)) ___bpf_ctx_arg2(n, args) +#define ___bpf_ctx_arg4(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt4(t, x, args)) ___bpf_ctx_arg3(n, args) +#define ___bpf_ctx_arg5(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt5(t, x, args)) ___bpf_ctx_arg4(n, args) +#define ___bpf_ctx_arg6(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt6(t, x, args)) ___bpf_ctx_arg5(n, args) +#define ___bpf_ctx_arg7(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt7(t, x, args)) ___bpf_ctx_arg6(n, args) +#define ___bpf_ctx_arg8(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt8(t, x, args)) ___bpf_ctx_arg7(n, args) +#define ___bpf_ctx_arg9(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt9(t, x, args)) ___bpf_ctx_arg8(n, args) +#define ___bpf_ctx_arg10(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt10(t, x, args)) ___bpf_ctx_arg9(n, args) +#define ___bpf_ctx_arg11(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt11(t, x, args)) ___bpf_ctx_arg10(n, args) +#define ___bpf_ctx_arg12(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt12(t, x, args)) ___bpf_ctx_arg11(n, args) +#define ___bpf_ctx_arg(args...) ___bpf_apply(___bpf_ctx_arg, ___bpf_narg2(args))(___bpf_reg_cnt(args), args) + +#define ___bpf_ctx_decl0() +#define ___bpf_ctx_decl1(t, x) , t x +#define ___bpf_ctx_decl2(t, x, args...) , t x ___bpf_ctx_decl1(args) +#define ___bpf_ctx_decl3(t, x, args...) , t x ___bpf_ctx_decl2(args) +#define ___bpf_ctx_decl4(t, x, args...) , t x ___bpf_ctx_decl3(args) +#define ___bpf_ctx_decl5(t, x, args...) , t x ___bpf_ctx_decl4(args) +#define ___bpf_ctx_decl6(t, x, args...) , t x ___bpf_ctx_decl5(args) +#define ___bpf_ctx_decl7(t, x, args...) , t x ___bpf_ctx_decl6(args) +#define ___bpf_ctx_decl8(t, x, args...) , t x ___bpf_ctx_decl7(args) +#define ___bpf_ctx_decl9(t, x, args...) , t x ___bpf_ctx_decl8(args) +#define ___bpf_ctx_decl10(t, x, args...) , t x ___bpf_ctx_decl9(args) +#define ___bpf_ctx_decl11(t, x, args...) , t x ___bpf_ctx_decl10(args) +#define ___bpf_ctx_decl12(t, x, args...) , t x ___bpf_ctx_decl11(args) +#define ___bpf_ctx_decl(args...) ___bpf_apply(___bpf_ctx_decl, ___bpf_narg2(args))(args) + +/* + * BPF_PROG2 is an enhanced version of BPF_PROG in order to handle struct + * arguments. Since each struct argument might take one or two u64 values + * in the trampoline stack, argument type size is needed to place proper number + * of u64 values for each argument. Therefore, BPF_PROG2 has different + * syntax from BPF_PROG. For example, for the following BPF_PROG syntax: + * + * int BPF_PROG(test2, int a, int b) { ... } + * + * the corresponding BPF_PROG2 syntax is: + * + * int BPF_PROG2(test2, int, a, int, b) { ... } + * + * where type and the corresponding argument name are separated by comma. + * + * Use BPF_PROG2 macro if one of the arguments might be a struct/union larger + * than 8 bytes: + * + * int BPF_PROG2(test_struct_arg, struct bpf_testmod_struct_arg_1, a, int, b, + * int, c, int, d, struct bpf_testmod_struct_arg_2, e, int, ret) + * { + * // access a, b, c, d, e, and ret directly + * ... + * } + */ +#define BPF_PROG2(name, args...) \ +name(unsigned long long *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx ___bpf_ctx_decl(args)); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + return ____##name(ctx ___bpf_ctx_arg(args)); \ +} \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx ___bpf_ctx_decl(args)) + +struct pt_regs; + +#define ___bpf_kprobe_args0() ctx +#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) +#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) +#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) +#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) +#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) + +/* + * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for + * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific + * low-level way of getting kprobe input arguments from struct pt_regs, and + * provides a familiar typed and named function arguments syntax and + * semantics of accessing kprobe input paremeters. + * + * Original struct pt_regs* context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + */ +#define BPF_KPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + +#define ___bpf_kretprobe_args0() ctx +#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) +#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) + +/* + * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional + * return value (in addition to `struct pt_regs *ctx`), but no input + * arguments, because they will be clobbered by the time probed function + * returns. + */ +#define BPF_KRETPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kretprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) + +/* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */ +#define ___bpf_syscall_args0() ctx +#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs) +#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs) +#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs) +#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs) +#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs) +#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) + +/* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */ +#define ___bpf_syswrap_args0() ctx +#define ___bpf_syswrap_args1(x) ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args(args...) ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args) + +/* + * BPF_KSYSCALL is a variant of BPF_KPROBE, which is intended for + * tracing syscall functions, like __x64_sys_close. It hides the underlying + * platform-specific low-level way of getting syscall input arguments from + * struct pt_regs, and provides a familiar typed and named function arguments + * syntax and semantics of accessing syscall input parameters. + * + * Original struct pt_regs * context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + * + * At the moment BPF_KSYSCALL does not transparently handle all the calling + * convention quirks for the following syscalls: + * + * - mmap(): __ARCH_WANT_SYS_OLD_MMAP. + * - clone(): CONFIG_CLONE_BACKWARDS, CONFIG_CLONE_BACKWARDS2 and + * CONFIG_CLONE_BACKWARDS3. + * - socket-related syscalls: __ARCH_WANT_SYS_SOCKETCALL. + * - compat syscalls. + * + * This may or may not change in the future. User needs to take extra measures + * to handle such quirks explicitly, if necessary. + * + * This macro relies on BPF CO-RE support and virtual __kconfig externs. + */ +#define BPF_KSYSCALL(name, args...) \ +name(struct pt_regs *ctx); \ +extern _Bool LINUX_HAS_SYSCALL_WRAPPER __kconfig; \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + struct pt_regs *regs = LINUX_HAS_SYSCALL_WRAPPER \ + ? (struct pt_regs *)PT_REGS_PARM1(ctx) \ + : ctx; \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + if (LINUX_HAS_SYSCALL_WRAPPER) \ + return ____##name(___bpf_syswrap_args(args)); \ + else \ + return ____##name(___bpf_syscall_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + +#define BPF_KPROBE_SYSCALL BPF_KSYSCALL + +#endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c new file mode 100644 index 000000000..8224a797c --- /dev/null +++ b/tools/lib/bpf/btf.c @@ -0,0 +1,4916 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include <byteswap.h> +#include <endian.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#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> +#include "btf.h" +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" +#include "hashmap.h" +#include "strset.h" + +#define BTF_MAX_NR_TYPES 0x7fffffffU +#define BTF_MAX_STR_OFFSET 0x7fffffffU + +static struct btf_type btf_void; + +struct btf { + /* raw BTF data in native endianness */ + void *raw_data; + /* raw BTF data in non-native endianness */ + void *raw_data_swapped; + __u32 raw_size; + /* whether target endianness differs from the native one */ + bool swapped_endian; + + /* + * When BTF is loaded from an ELF or raw memory it is stored + * in a contiguous memory block. The hdr, type_data, and, strs_data + * point inside that memory region to their respective parts of BTF + * representation: + * + * +--------------------------------+ + * | Header | Types | Strings | + * +--------------------------------+ + * ^ ^ ^ + * | | | + * hdr | | + * types_data-+ | + * strs_data------------+ + * + * If BTF data is later modified, e.g., due to types added or + * removed, BTF deduplication performed, etc, this contiguous + * representation is broken up into three independently allocated + * memory regions to be able to modify them independently. + * raw_data is nulled out at that point, but can be later allocated + * and cached again if user calls btf__raw_data(), at which point + * raw_data will contain a contiguous copy of header, types, and + * strings: + * + * +----------+ +---------+ +-----------+ + * | Header | | Types | | Strings | + * +----------+ +---------+ +-----------+ + * ^ ^ ^ + * | | | + * hdr | | + * types_data----+ | + * strset__data(strs_set)-----+ + * + * +----------+---------+-----------+ + * | Header | Types | Strings | + * raw_data----->+----------+---------+-----------+ + */ + struct btf_header *hdr; + + void *types_data; + size_t types_data_cap; /* used size stored in hdr->type_len */ + + /* type ID to `struct btf_type *` lookup index + * type_offs[0] corresponds to the first non-VOID type: + * - for base BTF it's type [1]; + * - for split BTF it's the first non-base BTF type. + */ + __u32 *type_offs; + size_t type_offs_cap; + /* number of types in this BTF instance: + * - doesn't include special [0] void type; + * - for split BTF counts number of types added on top of base BTF. + */ + __u32 nr_types; + /* if not NULL, points to the base BTF on top of which the current + * split BTF is based + */ + struct btf *base_btf; + /* BTF type ID of the first type in this BTF instance: + * - for base BTF it's equal to 1; + * - for split BTF it's equal to biggest type ID of base BTF plus 1. + */ + int start_id; + /* logical string offset of this BTF instance: + * - for base BTF it's equal to 0; + * - for split BTF it's equal to total size of base BTF's string section size. + */ + int start_str_off; + + /* only one of strs_data or strs_set can be non-NULL, depending on + * whether BTF is in a modifiable state (strs_set is used) or not + * (strs_data points inside raw_data) + */ + void *strs_data; + /* a set of unique strings */ + struct strset *strs_set; + /* whether strings are already deduplicated */ + bool strs_deduped; + + /* BTF object FD, if loaded into kernel */ + int fd; + + /* Pointer size (in bytes) for a target architecture of this BTF */ + int ptr_sz; +}; + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +/* Ensure given dynamically allocated memory region pointed to by *data* with + * capacity of *cap_cnt* elements each taking *elem_sz* bytes has enough + * memory to accommodate *add_cnt* new elements, assuming *cur_cnt* elements + * are already used. At most *max_cnt* elements can be ever allocated. + * If necessary, memory is reallocated and all existing data is copied over, + * new pointer to the memory region is stored at *data, new memory region + * capacity (in number of elements) is stored in *cap. + * On success, memory pointer to the beginning of unused memory is returned. + * On error, NULL is returned. + */ +void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz, + size_t cur_cnt, size_t max_cnt, size_t add_cnt) +{ + size_t new_cnt; + void *new_data; + + if (cur_cnt + add_cnt <= *cap_cnt) + return *data + cur_cnt * elem_sz; + + /* requested more than the set limit */ + if (cur_cnt + add_cnt > max_cnt) + return NULL; + + new_cnt = *cap_cnt; + new_cnt += new_cnt / 4; /* expand by 25% */ + if (new_cnt < 16) /* but at least 16 elements */ + new_cnt = 16; + if (new_cnt > max_cnt) /* but not exceeding a set limit */ + new_cnt = max_cnt; + if (new_cnt < cur_cnt + add_cnt) /* also ensure we have enough memory */ + new_cnt = cur_cnt + add_cnt; + + new_data = libbpf_reallocarray(*data, new_cnt, elem_sz); + if (!new_data) + return NULL; + + /* zero out newly allocated portion of memory */ + memset(new_data + (*cap_cnt) * elem_sz, 0, (new_cnt - *cap_cnt) * elem_sz); + + *data = new_data; + *cap_cnt = new_cnt; + return new_data + cur_cnt * elem_sz; +} + +/* Ensure given dynamically allocated memory region has enough allocated space + * to accommodate *need_cnt* elements of size *elem_sz* bytes each + */ +int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt) +{ + void *p; + + if (need_cnt <= *cap_cnt) + return 0; + + p = libbpf_add_mem(data, cap_cnt, elem_sz, *cap_cnt, SIZE_MAX, need_cnt - *cap_cnt); + if (!p) + return -ENOMEM; + + return 0; +} + +static void *btf_add_type_offs_mem(struct btf *btf, size_t add_cnt) +{ + return libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32), + btf->nr_types, BTF_MAX_NR_TYPES, add_cnt); +} + +static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off) +{ + __u32 *p; + + p = btf_add_type_offs_mem(btf, 1); + if (!p) + return -ENOMEM; + + *p = type_off; + return 0; +} + +static void btf_bswap_hdr(struct btf_header *h) +{ + h->magic = bswap_16(h->magic); + h->hdr_len = bswap_32(h->hdr_len); + h->type_off = bswap_32(h->type_off); + h->type_len = bswap_32(h->type_len); + h->str_off = bswap_32(h->str_off); + h->str_len = bswap_32(h->str_len); +} + +static int btf_parse_hdr(struct btf *btf) +{ + struct btf_header *hdr = btf->hdr; + __u32 meta_left; + + if (btf->raw_size < sizeof(struct btf_header)) { + pr_debug("BTF header not found\n"); + return -EINVAL; + } + + if (hdr->magic == bswap_16(BTF_MAGIC)) { + btf->swapped_endian = true; + if (bswap_32(hdr->hdr_len) != sizeof(struct btf_header)) { + pr_warn("Can't load BTF with non-native endianness due to unsupported header length %u\n", + bswap_32(hdr->hdr_len)); + return -ENOTSUP; + } + btf_bswap_hdr(hdr); + } else if (hdr->magic != BTF_MAGIC) { + pr_debug("Invalid BTF magic: %x\n", hdr->magic); + return -EINVAL; + } + + if (btf->raw_size < hdr->hdr_len) { + pr_debug("BTF header len %u larger than data size %u\n", + hdr->hdr_len, btf->raw_size); + return -EINVAL; + } + + meta_left = btf->raw_size - hdr->hdr_len; + if (meta_left < (long long)hdr->str_off + hdr->str_len) { + pr_debug("Invalid BTF total size: %u\n", btf->raw_size); + return -EINVAL; + } + + if ((long long)hdr->type_off + hdr->type_len > hdr->str_off) { + pr_debug("Invalid BTF data sections layout: type data at %u + %u, strings data at %u + %u\n", + hdr->type_off, hdr->type_len, hdr->str_off, hdr->str_len); + return -EINVAL; + } + + if (hdr->type_off % 4) { + pr_debug("BTF type section is not aligned to 4 bytes\n"); + return -EINVAL; + } + + return 0; +} + +static int btf_parse_str_sec(struct btf *btf) +{ + const struct btf_header *hdr = btf->hdr; + const char *start = btf->strs_data; + const char *end = start + btf->hdr->str_len; + + if (btf->base_btf && hdr->str_len == 0) + return 0; + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET || end[-1]) { + pr_debug("Invalid BTF string section\n"); + return -EINVAL; + } + if (!btf->base_btf && start[0]) { + pr_debug("Invalid BTF string section\n"); + return -EINVAL; + } + return 0; +} + +static int btf_type_size(const struct btf_type *t) +{ + const int base_size = sizeof(struct btf_type); + __u16 vlen = btf_vlen(t); + + switch (btf_kind(t)) { + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: + return base_size; + case BTF_KIND_INT: + return base_size + sizeof(__u32); + case BTF_KIND_ENUM: + return base_size + vlen * sizeof(struct btf_enum); + case BTF_KIND_ENUM64: + return base_size + vlen * sizeof(struct btf_enum64); + case BTF_KIND_ARRAY: + return base_size + sizeof(struct btf_array); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return base_size + vlen * sizeof(struct btf_member); + case BTF_KIND_FUNC_PROTO: + return base_size + vlen * sizeof(struct btf_param); + case BTF_KIND_VAR: + return base_size + sizeof(struct btf_var); + case BTF_KIND_DATASEC: + return base_size + vlen * sizeof(struct btf_var_secinfo); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); + default: + pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); + return -EINVAL; + } +} + +static void btf_bswap_type_base(struct btf_type *t) +{ + t->name_off = bswap_32(t->name_off); + t->info = bswap_32(t->info); + t->type = bswap_32(t->type); +} + +static int btf_bswap_type_rest(struct btf_type *t) +{ + struct btf_var_secinfo *v; + struct btf_enum64 *e64; + struct btf_member *m; + struct btf_array *a; + struct btf_param *p; + struct btf_enum *e; + __u16 vlen = btf_vlen(t); + int i; + + switch (btf_kind(t)) { + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: + return 0; + case BTF_KIND_INT: + *(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1)); + return 0; + case BTF_KIND_ENUM: + for (i = 0, e = btf_enum(t); i < vlen; i++, e++) { + e->name_off = bswap_32(e->name_off); + e->val = bswap_32(e->val); + } + return 0; + case BTF_KIND_ENUM64: + for (i = 0, e64 = btf_enum64(t); i < vlen; i++, e64++) { + e64->name_off = bswap_32(e64->name_off); + e64->val_lo32 = bswap_32(e64->val_lo32); + e64->val_hi32 = bswap_32(e64->val_hi32); + } + return 0; + case BTF_KIND_ARRAY: + a = btf_array(t); + a->type = bswap_32(a->type); + a->index_type = bswap_32(a->index_type); + a->nelems = bswap_32(a->nelems); + return 0; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + for (i = 0, m = btf_members(t); i < vlen; i++, m++) { + m->name_off = bswap_32(m->name_off); + m->type = bswap_32(m->type); + m->offset = bswap_32(m->offset); + } + return 0; + case BTF_KIND_FUNC_PROTO: + for (i = 0, p = btf_params(t); i < vlen; i++, p++) { + p->name_off = bswap_32(p->name_off); + p->type = bswap_32(p->type); + } + return 0; + case BTF_KIND_VAR: + btf_var(t)->linkage = bswap_32(btf_var(t)->linkage); + return 0; + case BTF_KIND_DATASEC: + for (i = 0, v = btf_var_secinfos(t); i < vlen; i++, v++) { + v->type = bswap_32(v->type); + v->offset = bswap_32(v->offset); + v->size = bswap_32(v->size); + } + return 0; + case BTF_KIND_DECL_TAG: + btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx); + return 0; + default: + pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); + return -EINVAL; + } +} + +static int btf_parse_type_sec(struct btf *btf) +{ + struct btf_header *hdr = btf->hdr; + void *next_type = btf->types_data; + void *end_type = next_type + hdr->type_len; + int err, type_size; + + while (next_type + sizeof(struct btf_type) <= end_type) { + if (btf->swapped_endian) + btf_bswap_type_base(next_type); + + type_size = btf_type_size(next_type); + if (type_size < 0) + return type_size; + if (next_type + type_size > end_type) { + pr_warn("BTF type [%d] is malformed\n", btf->start_id + btf->nr_types); + return -EINVAL; + } + + if (btf->swapped_endian && btf_bswap_type_rest(next_type)) + return -EINVAL; + + err = btf_add_type_idx_entry(btf, next_type - btf->types_data); + if (err) + return err; + + next_type += type_size; + btf->nr_types++; + } + + if (next_type != end_type) { + pr_warn("BTF types data is malformed\n"); + return -EINVAL; + } + + return 0; +} + +__u32 btf__type_cnt(const struct btf *btf) +{ + return btf->start_id + btf->nr_types; +} + +const struct btf *btf__base_btf(const struct btf *btf) +{ + return btf->base_btf; +} + +/* internal helper returning non-const pointer to a type */ +struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id) +{ + if (type_id == 0) + return &btf_void; + if (type_id < btf->start_id) + return btf_type_by_id(btf->base_btf, type_id); + return btf->types_data + btf->type_offs[type_id - btf->start_id]; +} + +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) +{ + if (type_id >= btf->start_id + btf->nr_types) + return errno = EINVAL, NULL; + return btf_type_by_id((struct btf *)btf, type_id); +} + +static int determine_ptr_size(const struct btf *btf) +{ + static const char * const long_aliases[] = { + "long", + "long int", + "int long", + "unsigned long", + "long unsigned", + "unsigned long int", + "unsigned int long", + "long unsigned int", + "long int unsigned", + "int unsigned long", + "int long unsigned", + }; + const struct btf_type *t; + const char *name; + int i, j, n; + + if (btf->base_btf && btf->base_btf->ptr_sz > 0) + return btf->base_btf->ptr_sz; + + n = btf__type_cnt(btf); + for (i = 1; i < n; i++) { + t = btf__type_by_id(btf, i); + if (!btf_is_int(t)) + continue; + + if (t->size != 4 && t->size != 8) + continue; + + name = btf__name_by_offset(btf, t->name_off); + if (!name) + continue; + + for (j = 0; j < ARRAY_SIZE(long_aliases); j++) { + if (strcmp(name, long_aliases[j]) == 0) + return t->size; + } + } + + return -1; +} + +static size_t btf_ptr_sz(const struct btf *btf) +{ + if (!btf->ptr_sz) + ((struct btf *)btf)->ptr_sz = determine_ptr_size(btf); + return btf->ptr_sz < 0 ? sizeof(void *) : btf->ptr_sz; +} + +/* Return pointer size this BTF instance assumes. The size is heuristically + * determined by looking for 'long' or 'unsigned long' integer type and + * recording its size in bytes. If BTF type information doesn't have any such + * type, this function returns 0. In the latter case, native architecture's + * pointer size is assumed, so will be either 4 or 8, depending on + * architecture that libbpf was compiled for. It's possible to override + * guessed value by using btf__set_pointer_size() API. + */ +size_t btf__pointer_size(const struct btf *btf) +{ + if (!btf->ptr_sz) + ((struct btf *)btf)->ptr_sz = determine_ptr_size(btf); + + if (btf->ptr_sz < 0) + /* not enough BTF type info to guess */ + return 0; + + return btf->ptr_sz; +} + +/* Override or set pointer size in bytes. Only values of 4 and 8 are + * supported. + */ +int btf__set_pointer_size(struct btf *btf, size_t ptr_sz) +{ + if (ptr_sz != 4 && ptr_sz != 8) + return libbpf_err(-EINVAL); + btf->ptr_sz = ptr_sz; + return 0; +} + +static bool is_host_big_endian(void) +{ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + return false; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + return true; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif +} + +enum btf_endianness btf__endianness(const struct btf *btf) +{ + if (is_host_big_endian()) + return btf->swapped_endian ? BTF_LITTLE_ENDIAN : BTF_BIG_ENDIAN; + else + return btf->swapped_endian ? BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN; +} + +int btf__set_endianness(struct btf *btf, enum btf_endianness endian) +{ + if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN) + return libbpf_err(-EINVAL); + + btf->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN); + if (!btf->swapped_endian) { + free(btf->raw_data_swapped); + btf->raw_data_swapped = NULL; + } + return 0; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + return t == &btf_void || btf_is_fwd(t); +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +#define MAX_RESOLVE_DEPTH 32 + +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id) +{ + const struct btf_array *array; + const struct btf_type *t; + __u32 nelems = 1; + __s64 size = -1; + int i; + + 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_kind(t)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_DATASEC: + case BTF_KIND_FLOAT: + size = t->size; + goto done; + case BTF_KIND_PTR: + size = btf_ptr_sz(btf); + goto done; + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + type_id = t->type; + break; + case BTF_KIND_ARRAY: + array = btf_array(t); + if (nelems && array->nelems > UINT32_MAX / nelems) + return libbpf_err(-E2BIG); + nelems *= array->nelems; + type_id = array->type; + break; + default: + return libbpf_err(-EINVAL); + } + + t = btf__type_by_id(btf, type_id); + } + +done: + if (size < 0) + return libbpf_err(-EINVAL); + if (nelems && size > UINT32_MAX / nelems) + return libbpf_err(-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: + case BTF_KIND_ENUM64: + case BTF_KIND_FLOAT: + return min(btf_ptr_sz(btf), (size_t)t->size); + case BTF_KIND_PTR: + return btf_ptr_sz(btf); + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: + return btf__align_of(btf, t->type); + case BTF_KIND_ARRAY: + return btf__align_of(btf, btf_array(t)->type); + 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 libbpf_err(align); + max_align = max(max_align, align); + + /* if field offset isn't aligned according to field + * type's alignment, then struct must be packed + */ + if (btf_member_bitfield_size(t, i) == 0 && + (m->offset % (8 * align)) != 0) + return 1; + } + + /* if struct/union size isn't a multiple of its alignment, + * then struct must be packed + */ + if ((t->size % max_align) != 0) + return 1; + + return max_align; + } + default: + pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); + return errno = EINVAL, 0; + } +} + +int btf__resolve_type(const struct btf *btf, __u32 type_id) +{ + const struct btf_type *t; + int depth = 0; + + t = btf__type_by_id(btf, type_id); + while (depth < MAX_RESOLVE_DEPTH && + !btf_type_is_void_or_null(t) && + (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++; + } + + if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t)) + return libbpf_err(-EINVAL); + + return type_id; +} + +__s32 btf__find_by_name(const struct btf *btf, const char *type_name) +{ + __u32 i, nr_types = btf__type_cnt(btf); + + if (!strcmp(type_name, "void")) + return 0; + + for (i = 1; i < nr_types; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + const char *name = btf__name_by_offset(btf, t->name_off); + + if (name && !strcmp(type_name, name)) + return i; + } + + return libbpf_err(-ENOENT); +} + +static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id, + const char *type_name, __u32 kind) +{ + __u32 i, nr_types = btf__type_cnt(btf); + + if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void")) + return 0; + + for (i = start_id; i < nr_types; i++) { + const struct btf_type *t = btf__type_by_id(btf, 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 libbpf_err(-ENOENT); +} + +__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, + __u32 kind) +{ + return btf_find_by_name_kind(btf, btf->start_id, type_name, kind); +} + +__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, + __u32 kind) +{ + return btf_find_by_name_kind(btf, 1, type_name, kind); +} + +static bool btf_is_modifiable(const struct btf *btf) +{ + return (void *)btf->hdr != btf->raw_data; +} + +void btf__free(struct btf *btf) +{ + if (IS_ERR_OR_NULL(btf)) + return; + + if (btf->fd >= 0) + close(btf->fd); + + if (btf_is_modifiable(btf)) { + /* if BTF was modified after loading, it will have a split + * in-memory representation for header, types, and strings + * sections, so we need to free all of them individually. It + * might still have a cached contiguous raw data present, + * which will be unconditionally freed below. + */ + free(btf->hdr); + free(btf->types_data); + strset__free(btf->strs_set); + } + free(btf->raw_data); + free(btf->raw_data_swapped); + free(btf->type_offs); + free(btf); +} + +static struct btf *btf_new_empty(struct btf *base_btf) +{ + struct btf *btf; + + btf = calloc(1, sizeof(*btf)); + if (!btf) + return ERR_PTR(-ENOMEM); + + btf->nr_types = 0; + btf->start_id = 1; + btf->start_str_off = 0; + btf->fd = -1; + btf->ptr_sz = sizeof(void *); + btf->swapped_endian = false; + + if (base_btf) { + btf->base_btf = base_btf; + btf->start_id = btf__type_cnt(base_btf); + btf->start_str_off = base_btf->hdr->str_len; + } + + /* +1 for empty string at offset 0 */ + btf->raw_size = sizeof(struct btf_header) + (base_btf ? 0 : 1); + btf->raw_data = calloc(1, btf->raw_size); + if (!btf->raw_data) { + free(btf); + return ERR_PTR(-ENOMEM); + } + + btf->hdr = btf->raw_data; + btf->hdr->hdr_len = sizeof(struct btf_header); + btf->hdr->magic = BTF_MAGIC; + btf->hdr->version = BTF_VERSION; + + btf->types_data = btf->raw_data + btf->hdr->hdr_len; + btf->strs_data = btf->raw_data + btf->hdr->hdr_len; + btf->hdr->str_len = base_btf ? 0 : 1; /* empty string at offset 0 */ + + return btf; +} + +struct btf *btf__new_empty(void) +{ + return libbpf_ptr(btf_new_empty(NULL)); +} + +struct btf *btf__new_empty_split(struct btf *base_btf) +{ + return libbpf_ptr(btf_new_empty(base_btf)); +} + +static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) +{ + struct btf *btf; + int err; + + btf = calloc(1, sizeof(struct btf)); + if (!btf) + return ERR_PTR(-ENOMEM); + + btf->nr_types = 0; + btf->start_id = 1; + btf->start_str_off = 0; + btf->fd = -1; + + if (base_btf) { + btf->base_btf = base_btf; + btf->start_id = btf__type_cnt(base_btf); + btf->start_str_off = base_btf->hdr->str_len; + } + + btf->raw_data = malloc(size); + if (!btf->raw_data) { + err = -ENOMEM; + goto done; + } + memcpy(btf->raw_data, data, size); + btf->raw_size = size; + + btf->hdr = btf->raw_data; + err = btf_parse_hdr(btf); + if (err) + goto done; + + btf->strs_data = btf->raw_data + btf->hdr->hdr_len + btf->hdr->str_off; + btf->types_data = btf->raw_data + btf->hdr->hdr_len + btf->hdr->type_off; + + err = btf_parse_str_sec(btf); + err = err ?: btf_parse_type_sec(btf); + if (err) + goto done; + +done: + if (err) { + btf__free(btf); + return ERR_PTR(err); + } + + return btf; +} + +struct btf *btf__new(const void *data, __u32 size) +{ + return libbpf_ptr(btf_new(data, size, NULL)); +} + +static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, + struct btf_ext **btf_ext) +{ + Elf_Data *btf_data = NULL, *btf_ext_data = NULL; + int err = 0, fd = -1, idx = 0; + struct btf *btf = NULL; + Elf_Scn *scn = NULL; + Elf *elf = NULL; + GElf_Ehdr ehdr; + size_t shstrndx; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn("failed to init libelf for %s\n", path); + return ERR_PTR(-LIBBPF_ERRNO__LIBELF); + } + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + err = -errno; + pr_warn("failed to open %s: %s\n", path, strerror(errno)); + return ERR_PTR(err); + } + + err = -LIBBPF_ERRNO__FORMAT; + + elf = elf_begin(fd, ELF_C_READ, NULL); + if (!elf) { + pr_warn("failed to open %s as ELF file\n", path); + goto done; + } + if (!gelf_getehdr(elf, &ehdr)) { + pr_warn("failed to get EHDR from %s\n", path); + goto done; + } + + if (elf_getshdrstrndx(elf, &shstrndx)) { + pr_warn("failed to get section names section index for %s\n", + path); + goto done; + } + + if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) { + pr_warn("failed to get e_shstrndx from %s\n", path); + goto done; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + char *name; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warn("failed to get section(%d) header from %s\n", + idx, path); + goto done; + } + name = elf_strptr(elf, shstrndx, sh.sh_name); + if (!name) { + pr_warn("failed to get section(%d) name from %s\n", + idx, path); + goto done; + } + if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = elf_getdata(scn, 0); + if (!btf_data) { + pr_warn("failed to get section(%d, %s) data from %s\n", + idx, name, path); + goto done; + } + continue; + } else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) { + btf_ext_data = elf_getdata(scn, 0); + if (!btf_ext_data) { + pr_warn("failed to get section(%d, %s) data from %s\n", + idx, name, path); + goto done; + } + continue; + } + } + + err = 0; + + if (!btf_data) { + err = -ENOENT; + goto done; + } + btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf); + err = libbpf_get_error(btf); + if (err) + goto done; + + switch (gelf_getclass(elf)) { + case ELFCLASS32: + btf__set_pointer_size(btf, 4); + break; + case ELFCLASS64: + btf__set_pointer_size(btf, 8); + break; + default: + pr_warn("failed to get ELF class (bitness) for %s\n", path); + break; + } + + if (btf_ext && btf_ext_data) { + *btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); + err = libbpf_get_error(*btf_ext); + if (err) + goto done; + } else if (btf_ext) { + *btf_ext = NULL; + } +done: + if (elf) + elf_end(elf); + close(fd); + + if (!err) + return btf; + + if (btf_ext) + btf_ext__free(*btf_ext); + btf__free(btf); + + return ERR_PTR(err); +} + +struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) +{ + return libbpf_ptr(btf_parse_elf(path, NULL, btf_ext)); +} + +struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf) +{ + return libbpf_ptr(btf_parse_elf(path, base_btf, NULL)); +} + +static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) +{ + struct btf *btf = NULL; + void *data = NULL; + FILE *f = NULL; + __u16 magic; + int err = 0; + long sz; + + f = fopen(path, "rb"); + if (!f) { + err = -errno; + goto err_out; + } + + /* check BTF magic */ + if (fread(&magic, 1, sizeof(magic), f) < sizeof(magic)) { + err = -EIO; + goto err_out; + } + if (magic != BTF_MAGIC && magic != bswap_16(BTF_MAGIC)) { + /* definitely not a raw BTF */ + err = -EPROTO; + goto err_out; + } + + /* get file size */ + if (fseek(f, 0, SEEK_END)) { + err = -errno; + goto err_out; + } + sz = ftell(f); + if (sz < 0) { + err = -errno; + goto err_out; + } + /* rewind to the start */ + if (fseek(f, 0, SEEK_SET)) { + err = -errno; + goto err_out; + } + + /* pre-alloc memory and read all of BTF data */ + data = malloc(sz); + if (!data) { + err = -ENOMEM; + goto err_out; + } + if (fread(data, 1, sz, f) < sz) { + err = -EIO; + goto err_out; + } + + /* finally parse BTF data */ + btf = btf_new(data, sz, base_btf); + +err_out: + free(data); + if (f) + fclose(f); + return err ? ERR_PTR(err) : btf; +} + +struct btf *btf__parse_raw(const char *path) +{ + return libbpf_ptr(btf_parse_raw(path, NULL)); +} + +struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf) +{ + return libbpf_ptr(btf_parse_raw(path, base_btf)); +} + +static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext) +{ + struct btf *btf; + int err; + + if (btf_ext) + *btf_ext = NULL; + + btf = btf_parse_raw(path, base_btf); + err = libbpf_get_error(btf); + if (!err) + return btf; + if (err != -EPROTO) + return ERR_PTR(err); + return btf_parse_elf(path, base_btf, btf_ext); +} + +struct btf *btf__parse(const char *path, struct btf_ext **btf_ext) +{ + return libbpf_ptr(btf_parse(path, NULL, btf_ext)); +} + +struct btf *btf__parse_split(const char *path, struct btf *base_btf) +{ + return libbpf_ptr(btf_parse(path, base_btf, NULL)); +} + +static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); + +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level) +{ + LIBBPF_OPTS(bpf_btf_load_opts, opts); + __u32 buf_sz = 0, raw_size; + char *buf = NULL, *tmp; + void *raw_data; + int err = 0; + + if (btf->fd >= 0) + return libbpf_err(-EEXIST); + if (log_sz && !log_buf) + return libbpf_err(-EINVAL); + + /* cache native raw data representation */ + raw_data = btf_get_raw_data(btf, &raw_size, false); + if (!raw_data) { + err = -ENOMEM; + goto done; + } + btf->raw_size = raw_size; + btf->raw_data = raw_data; + +retry_load: + /* if log_level is 0, we won't provide log_buf/log_size to the kernel, + * initially. Only if BTF loading fails, we bump log_level to 1 and + * retry, using either auto-allocated or custom log_buf. This way + * non-NULL custom log_buf provides a buffer just in case, but hopes + * for successful load and no need for log_buf. + */ + if (log_level) { + /* if caller didn't provide custom log_buf, we'll keep + * allocating our own progressively bigger buffers for BTF + * verification log + */ + if (!log_buf) { + buf_sz = max((__u32)BPF_LOG_BUF_SIZE, buf_sz * 2); + tmp = realloc(buf, buf_sz); + if (!tmp) { + err = -ENOMEM; + goto done; + } + buf = tmp; + buf[0] = '\0'; + } + + opts.log_buf = log_buf ? log_buf : buf; + opts.log_size = log_buf ? log_sz : buf_sz; + opts.log_level = log_level; + } + + btf->fd = bpf_btf_load(raw_data, raw_size, &opts); + if (btf->fd < 0) { + /* time to turn on verbose mode and try again */ + if (log_level == 0) { + log_level = 1; + goto retry_load; + } + /* only retry if caller didn't provide custom log_buf, but + * make sure we can never overflow buf_sz + */ + if (!log_buf && errno == ENOSPC && buf_sz <= UINT_MAX / 2) + goto retry_load; + + err = -errno; + pr_warn("BTF loading error: %d\n", err); + /* don't print out contents of custom log_buf */ + if (!log_buf && buf[0]) + pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf); + } + +done: + free(buf); + return libbpf_err(err); +} + +int btf__load_into_kernel(struct btf *btf) +{ + return btf_load_into_kernel(btf, NULL, 0, 0); +} + +int btf__fd(const struct btf *btf) +{ + return btf->fd; +} + +void btf__set_fd(struct btf *btf, int fd) +{ + btf->fd = fd; +} + +static const void *btf_strs_data(const struct btf *btf) +{ + return btf->strs_data ? btf->strs_data : strset__data(btf->strs_set); +} + +static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian) +{ + struct btf_header *hdr = btf->hdr; + struct btf_type *t; + void *data, *p; + __u32 data_sz; + int i; + + data = swap_endian ? btf->raw_data_swapped : btf->raw_data; + if (data) { + *size = btf->raw_size; + return data; + } + + data_sz = hdr->hdr_len + hdr->type_len + hdr->str_len; + data = calloc(1, data_sz); + if (!data) + return NULL; + p = data; + + memcpy(p, hdr, hdr->hdr_len); + if (swap_endian) + btf_bswap_hdr(p); + p += hdr->hdr_len; + + memcpy(p, btf->types_data, hdr->type_len); + if (swap_endian) { + for (i = 0; i < btf->nr_types; i++) { + t = p + btf->type_offs[i]; + /* btf_bswap_type_rest() relies on native t->info, so + * we swap base type info after we swapped all the + * additional information + */ + if (btf_bswap_type_rest(t)) + goto err_out; + btf_bswap_type_base(t); + } + } + p += hdr->type_len; + + memcpy(p, btf_strs_data(btf), hdr->str_len); + p += hdr->str_len; + + *size = data_sz; + return data; +err_out: + free(data); + return NULL; +} + +const void *btf__raw_data(const struct btf *btf_ro, __u32 *size) +{ + struct btf *btf = (struct btf *)btf_ro; + __u32 data_sz; + void *data; + + data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian); + if (!data) + return errno = ENOMEM, NULL; + + btf->raw_size = data_sz; + if (btf->swapped_endian) + btf->raw_data_swapped = data; + else + btf->raw_data = data; + *size = data_sz; + return data; +} + +__attribute__((alias("btf__raw_data"))) +const void *btf__get_raw_data(const struct btf *btf, __u32 *size); + +const char *btf__str_by_offset(const struct btf *btf, __u32 offset) +{ + if (offset < btf->start_str_off) + return btf__str_by_offset(btf->base_btf, offset); + else if (offset - btf->start_str_off < btf->hdr->str_len) + return btf_strs_data(btf) + (offset - btf->start_str_off); + else + return errno = EINVAL, NULL; +} + +const char *btf__name_by_offset(const struct btf *btf, __u32 offset) +{ + return btf__str_by_offset(btf, offset); +} + +struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) +{ + struct bpf_btf_info btf_info; + __u32 len = sizeof(btf_info); + __u32 last_size; + struct btf *btf; + void *ptr; + int err; + + /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so + * let's start with a sane default - 4KiB here - and resize it only if + * bpf_obj_get_info_by_fd() needs a bigger buffer. + */ + last_size = 4096; + ptr = malloc(last_size); + if (!ptr) + return ERR_PTR(-ENOMEM); + + memset(&btf_info, 0, sizeof(btf_info)); + btf_info.btf = ptr_to_u64(ptr); + btf_info.btf_size = last_size; + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + + if (!err && btf_info.btf_size > last_size) { + void *temp_ptr; + + last_size = btf_info.btf_size; + temp_ptr = realloc(ptr, last_size); + if (!temp_ptr) { + btf = ERR_PTR(-ENOMEM); + goto exit_free; + } + ptr = temp_ptr; + + len = sizeof(btf_info); + memset(&btf_info, 0, sizeof(btf_info)); + btf_info.btf = ptr_to_u64(ptr); + btf_info.btf_size = last_size; + + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + } + + if (err || btf_info.btf_size > last_size) { + btf = err ? ERR_PTR(-errno) : ERR_PTR(-E2BIG); + goto exit_free; + } + + btf = btf_new(ptr, btf_info.btf_size, base_btf); + +exit_free: + free(ptr); + return btf; +} + +struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) +{ + struct btf *btf; + int btf_fd; + + btf_fd = bpf_btf_get_fd_by_id(id); + if (btf_fd < 0) + return libbpf_err_ptr(-errno); + + btf = btf_get_from_fd(btf_fd, base_btf); + close(btf_fd); + + return libbpf_ptr(btf); +} + +struct btf *btf__load_from_kernel_by_id(__u32 id) +{ + return btf__load_from_kernel_by_id_split(id, NULL); +} + +static void btf_invalidate_raw_data(struct btf *btf) +{ + if (btf->raw_data) { + free(btf->raw_data); + btf->raw_data = NULL; + } + if (btf->raw_data_swapped) { + free(btf->raw_data_swapped); + btf->raw_data_swapped = NULL; + } +} + +/* Ensure BTF is ready to be modified (by splitting into a three memory + * regions for header, types, and strings). Also invalidate cached + * raw_data, if any. + */ +static int btf_ensure_modifiable(struct btf *btf) +{ + void *hdr, *types; + struct strset *set = NULL; + int err = -ENOMEM; + + if (btf_is_modifiable(btf)) { + /* any BTF modification invalidates raw_data */ + btf_invalidate_raw_data(btf); + return 0; + } + + /* split raw data into three memory regions */ + hdr = malloc(btf->hdr->hdr_len); + types = malloc(btf->hdr->type_len); + if (!hdr || !types) + goto err_out; + + memcpy(hdr, btf->hdr, btf->hdr->hdr_len); + memcpy(types, btf->types_data, btf->hdr->type_len); + + /* build lookup index for all strings */ + set = strset__new(BTF_MAX_STR_OFFSET, btf->strs_data, btf->hdr->str_len); + if (IS_ERR(set)) { + err = PTR_ERR(set); + goto err_out; + } + + /* only when everything was successful, update internal state */ + btf->hdr = hdr; + btf->types_data = types; + btf->types_data_cap = btf->hdr->type_len; + btf->strs_data = NULL; + btf->strs_set = set; + /* if BTF was created from scratch, all strings are guaranteed to be + * unique and deduplicated + */ + if (btf->hdr->str_len == 0) + btf->strs_deduped = true; + if (!btf->base_btf && btf->hdr->str_len == 1) + btf->strs_deduped = true; + + /* invalidate raw_data representation */ + btf_invalidate_raw_data(btf); + + return 0; + +err_out: + strset__free(set); + free(hdr); + free(types); + return err; +} + +/* Find an offset in BTF string section that corresponds to a given string *s*. + * Returns: + * - >0 offset into string section, if string is found; + * - -ENOENT, if string is not in the string section; + * - <0, on any other error. + */ +int btf__find_str(struct btf *btf, const char *s) +{ + int off; + + if (btf->base_btf) { + off = btf__find_str(btf->base_btf, s); + if (off != -ENOENT) + return off; + } + + /* BTF needs to be in a modifiable state to build string lookup index */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + off = strset__find_str(btf->strs_set, s); + if (off < 0) + return libbpf_err(off); + + return btf->start_str_off + off; +} + +/* Add a string s to the BTF string section. + * Returns: + * - > 0 offset into string section, on success; + * - < 0, on error. + */ +int btf__add_str(struct btf *btf, const char *s) +{ + int off; + + if (btf->base_btf) { + off = btf__find_str(btf->base_btf, s); + if (off != -ENOENT) + return off; + } + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + off = strset__add_str(btf->strs_set, s); + if (off < 0) + return libbpf_err(off); + + btf->hdr->str_len = strset__data_size(btf->strs_set); + + return btf->start_str_off + off; +} + +static void *btf_add_type_mem(struct btf *btf, size_t add_sz) +{ + return libbpf_add_mem(&btf->types_data, &btf->types_data_cap, 1, + btf->hdr->type_len, UINT_MAX, add_sz); +} + +static void btf_type_inc_vlen(struct btf_type *t) +{ + t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, btf_kflag(t)); +} + +static int btf_commit_type(struct btf *btf, int data_sz) +{ + int err; + + err = btf_add_type_idx_entry(btf, btf->hdr->type_len); + if (err) + return libbpf_err(err); + + btf->hdr->type_len += data_sz; + btf->hdr->str_off += data_sz; + btf->nr_types++; + return btf->start_id + btf->nr_types - 1; +} + +struct btf_pipe { + const struct btf *src; + struct btf *dst; + struct hashmap *str_off_map; /* map string offsets from src to dst */ +}; + +static int btf_rewrite_str(__u32 *str_off, void *ctx) +{ + struct btf_pipe *p = ctx; + void *mapped_off; + int off, err; + + if (!*str_off) /* nothing to do for empty strings */ + return 0; + + if (p->str_off_map && + hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) { + *str_off = (__u32)(long)mapped_off; + return 0; + } + + off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off)); + if (off < 0) + return off; + + /* Remember string mapping from src to dst. It avoids + * performing expensive string comparisons. + */ + if (p->str_off_map) { + err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off); + if (err) + return err; + } + + *str_off = off; + return 0; +} + +int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type) +{ + struct btf_pipe p = { .src = src_btf, .dst = btf }; + struct btf_type *t; + int sz, err; + + sz = btf_type_size(src_type); + if (sz < 0) + return libbpf_err(sz); + + /* deconstruct BTF, if necessary, and invalidate raw_data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + memcpy(t, src_type, sz); + + err = btf_type_visit_str_offs(t, btf_rewrite_str, &p); + if (err) + return libbpf_err(err); + + return btf_commit_type(btf, sz); +} + +static int btf_rewrite_type_ids(__u32 *type_id, void *ctx) +{ + struct btf *btf = ctx; + + if (!*type_id) /* nothing to do for VOID references */ + return 0; + + /* we haven't updated btf's type count yet, so + * btf->start_id + btf->nr_types - 1 is the type ID offset we should + * add to all newly added BTF types + */ + *type_id += btf->start_id + btf->nr_types - 1; + return 0; +} + +static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx); +static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx); + +int btf__add_btf(struct btf *btf, const struct btf *src_btf) +{ + struct btf_pipe p = { .src = src_btf, .dst = btf }; + int data_sz, sz, cnt, i, err, old_strs_len; + __u32 *off; + void *t; + + /* appending split BTF isn't supported yet */ + if (src_btf->base_btf) + return libbpf_err(-ENOTSUP); + + /* deconstruct BTF, if necessary, and invalidate raw_data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + /* remember original strings section size if we have to roll back + * partial strings section changes + */ + old_strs_len = btf->hdr->str_len; + + data_sz = src_btf->hdr->type_len; + cnt = btf__type_cnt(src_btf) - 1; + + /* pre-allocate enough memory for new types */ + t = btf_add_type_mem(btf, data_sz); + if (!t) + return libbpf_err(-ENOMEM); + + /* pre-allocate enough memory for type offset index for new types */ + off = btf_add_type_offs_mem(btf, cnt); + if (!off) + return libbpf_err(-ENOMEM); + + /* Map the string offsets from src_btf to the offsets from btf to improve performance */ + p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(p.str_off_map)) + return libbpf_err(-ENOMEM); + + /* bulk copy types data for all types from src_btf */ + memcpy(t, src_btf->types_data, data_sz); + + for (i = 0; i < cnt; i++) { + sz = btf_type_size(t); + if (sz < 0) { + /* unlikely, has to be corrupted src_btf */ + err = sz; + goto err_out; + } + + /* fill out type ID to type offset mapping for lookups by type ID */ + *off = t - btf->types_data; + + /* add, dedup, and remap strings referenced by this BTF type */ + err = btf_type_visit_str_offs(t, btf_rewrite_str, &p); + if (err) + goto err_out; + + /* remap all type IDs referenced from this BTF type */ + err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf); + if (err) + goto err_out; + + /* go to next type data and type offset index entry */ + t += sz; + off++; + } + + /* Up until now any of the copied type data was effectively invisible, + * so if we exited early before this point due to error, BTF would be + * effectively unmodified. There would be extra internal memory + * pre-allocated, but it would not be available for querying. But now + * that we've copied and rewritten all the data successfully, we can + * update type count and various internal offsets and sizes to + * "commit" the changes and made them visible to the outside world. + */ + btf->hdr->type_len += data_sz; + btf->hdr->str_off += data_sz; + btf->nr_types += cnt; + + hashmap__free(p.str_off_map); + + /* return type ID of the first added BTF type */ + return btf->start_id + btf->nr_types - cnt; +err_out: + /* zero out preallocated memory as if it was just allocated with + * libbpf_add_mem() + */ + memset(btf->types_data + btf->hdr->type_len, 0, data_sz); + memset(btf->strs_data + old_strs_len, 0, btf->hdr->str_len - old_strs_len); + + /* and now restore original strings section size; types data size + * wasn't modified, so doesn't need restoring, see big comment above */ + btf->hdr->str_len = old_strs_len; + + hashmap__free(p.str_off_map); + + return libbpf_err(err); +} + +/* + * Append new BTF_KIND_INT type with: + * - *name* - non-empty, non-NULL type name; + * - *sz* - power-of-2 (1, 2, 4, ..) size of the type, in bytes; + * - encoding is a combination of BTF_INT_SIGNED, BTF_INT_CHAR, BTF_INT_BOOL. + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding) +{ + struct btf_type *t; + int sz, name_off; + + /* non-empty name */ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + /* byte_sz must be power of 2 */ + if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 16) + return libbpf_err(-EINVAL); + if (encoding & ~(BTF_INT_SIGNED | BTF_INT_CHAR | BTF_INT_BOOL)) + return libbpf_err(-EINVAL); + + /* deconstruct BTF, if necessary, and invalidate raw_data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type) + sizeof(int); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + /* if something goes wrong later, we might end up with an extra string, + * but that shouldn't be a problem, because BTF can't be constructed + * completely anyway and will most probably be just discarded + */ + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + t->name_off = name_off; + t->info = btf_type_info(BTF_KIND_INT, 0, 0); + t->size = byte_sz; + /* set INT info, we don't allow setting legacy bit offset/size */ + *(__u32 *)(t + 1) = (encoding << 24) | (byte_sz * 8); + + return btf_commit_type(btf, sz); +} + +/* + * Append new BTF_KIND_FLOAT type with: + * - *name* - non-empty, non-NULL type name; + * - *sz* - size of the type, in bytes; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_float(struct btf *btf, const char *name, size_t byte_sz) +{ + struct btf_type *t; + int sz, name_off; + + /* non-empty name */ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + + /* byte_sz must be one of the explicitly allowed values */ + if (byte_sz != 2 && byte_sz != 4 && byte_sz != 8 && byte_sz != 12 && + byte_sz != 16) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + t->name_off = name_off; + t->info = btf_type_info(BTF_KIND_FLOAT, 0, 0); + t->size = byte_sz; + + return btf_commit_type(btf, sz); +} + +/* it's completely legal to append BTF types with type IDs pointing forward to + * types that haven't been appended yet, so we only make sure that id looks + * sane, we can't guarantee that ID will always be valid + */ +static int validate_type_id(int id) +{ + if (id < 0 || id > BTF_MAX_NR_TYPES) + return -EINVAL; + return 0; +} + +/* generic append function for PTR, TYPEDEF, CONST/VOLATILE/RESTRICT */ +static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id) +{ + struct btf_type *t; + int sz, name_off = 0; + + if (validate_type_id(ref_type_id)) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + t->name_off = name_off; + t->info = btf_type_info(kind, 0, 0); + t->type = ref_type_id; + + return btf_commit_type(btf, sz); +} + +/* + * Append new BTF_KIND_PTR type with: + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_ptr(struct btf *btf, int ref_type_id) +{ + return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id); +} + +/* + * Append new BTF_KIND_ARRAY type with: + * - *index_type_id* - type ID of the type describing array index; + * - *elem_type_id* - type ID of the type describing array element; + * - *nr_elems* - the size of the array; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 nr_elems) +{ + struct btf_type *t; + struct btf_array *a; + int sz; + + if (validate_type_id(index_type_id) || validate_type_id(elem_type_id)) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type) + sizeof(struct btf_array); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + t->name_off = 0; + t->info = btf_type_info(BTF_KIND_ARRAY, 0, 0); + t->size = 0; + + a = btf_array(t); + a->type = elem_type_id; + a->index_type = index_type_id; + a->nelems = nr_elems; + + return btf_commit_type(btf, sz); +} + +/* generic STRUCT/UNION append function */ +static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32 bytes_sz) +{ + struct btf_type *t; + int sz, name_off = 0; + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + /* start out with vlen=0 and no kflag; this will be adjusted when + * adding each member + */ + t->name_off = name_off; + t->info = btf_type_info(kind, 0, 0); + t->size = bytes_sz; + + return btf_commit_type(btf, sz); +} + +/* + * Append new BTF_KIND_STRUCT type with: + * - *name* - name of the struct, can be NULL or empty for anonymous structs; + * - *byte_sz* - size of the struct, in bytes; + * + * Struct initially has no fields in it. Fields can be added by + * btf__add_field() right after btf__add_struct() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_struct(struct btf *btf, const char *name, __u32 byte_sz) +{ + return btf_add_composite(btf, BTF_KIND_STRUCT, name, byte_sz); +} + +/* + * Append new BTF_KIND_UNION type with: + * - *name* - name of the union, can be NULL or empty for anonymous union; + * - *byte_sz* - size of the union, in bytes; + * + * Union initially has no fields in it. Fields can be added by + * btf__add_field() right after btf__add_union() succeeds. All fields + * should have *bit_offset* of 0. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz) +{ + return btf_add_composite(btf, BTF_KIND_UNION, name, byte_sz); +} + +static struct btf_type *btf_last_type(struct btf *btf) +{ + return btf_type_by_id(btf, btf__type_cnt(btf) - 1); +} + +/* + * Append new field for the current STRUCT/UNION type with: + * - *name* - name of the field, can be NULL or empty for anonymous field; + * - *type_id* - type ID for the type describing field type; + * - *bit_offset* - bit offset of the start of the field within struct/union; + * - *bit_size* - bit size of a bitfield, 0 for non-bitfield fields; + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_field(struct btf *btf, const char *name, int type_id, + __u32 bit_offset, __u32 bit_size) +{ + struct btf_type *t; + struct btf_member *m; + bool is_bitfield; + int sz, name_off = 0; + + /* last type should be union/struct */ + if (btf->nr_types == 0) + return libbpf_err(-EINVAL); + t = btf_last_type(btf); + if (!btf_is_composite(t)) + return libbpf_err(-EINVAL); + + if (validate_type_id(type_id)) + return libbpf_err(-EINVAL); + /* best-effort bit field offset/size enforcement */ + is_bitfield = bit_size || (bit_offset % 8 != 0); + if (is_bitfield && (bit_size == 0 || bit_size > 255 || bit_offset > 0xffffff)) + return libbpf_err(-EINVAL); + + /* only offset 0 is allowed for unions */ + if (btf_is_union(t) && bit_offset) + return libbpf_err(-EINVAL); + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_member); + m = btf_add_type_mem(btf, sz); + if (!m) + return libbpf_err(-ENOMEM); + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + m->name_off = name_off; + m->type = type_id; + m->offset = bit_offset | (bit_size << 24); + + /* btf_add_type_mem can invalidate t pointer */ + t = btf_last_type(btf); + /* update parent type's vlen and kflag */ + t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, is_bitfield || btf_kflag(t)); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +static int btf_add_enum_common(struct btf *btf, const char *name, __u32 byte_sz, + bool is_signed, __u8 kind) +{ + struct btf_type *t; + int sz, name_off = 0; + + /* byte_sz must be power of 2 */ + if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + /* start out with vlen=0; it will be adjusted when adding enum values */ + t->name_off = name_off; + t->info = btf_type_info(kind, 0, is_signed); + t->size = byte_sz; + + return btf_commit_type(btf, sz); +} + +/* + * Append new BTF_KIND_ENUM type with: + * - *name* - name of the enum, can be NULL or empty for anonymous enums; + * - *byte_sz* - size of the enum, in bytes. + * + * Enum initially has no enum values in it (and corresponds to enum forward + * declaration). Enumerator values can be added by btf__add_enum_value() + * immediately after btf__add_enum() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) +{ + /* + * set the signedness to be unsigned, it will change to signed + * if any later enumerator is negative. + */ + return btf_add_enum_common(btf, name, byte_sz, false, BTF_KIND_ENUM); +} + +/* + * Append new enum value for the current ENUM type with: + * - *name* - name of the enumerator value, can't be NULL or empty; + * - *value* - integer value corresponding to enum value *name*; + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_enum_value(struct btf *btf, const char *name, __s64 value) +{ + struct btf_type *t; + struct btf_enum *v; + int sz, name_off; + + /* last type should be BTF_KIND_ENUM */ + if (btf->nr_types == 0) + return libbpf_err(-EINVAL); + t = btf_last_type(btf); + if (!btf_is_enum(t)) + return libbpf_err(-EINVAL); + + /* non-empty name */ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + if (value < INT_MIN || value > UINT_MAX) + return libbpf_err(-E2BIG); + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_enum); + v = btf_add_type_mem(btf, sz); + if (!v) + return libbpf_err(-ENOMEM); + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + v->name_off = name_off; + v->val = value; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + + /* if negative value, set signedness to signed */ + if (value < 0) + t->info = btf_type_info(btf_kind(t), btf_vlen(t), true); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_ENUM64 type with: + * - *name* - name of the enum, can be NULL or empty for anonymous enums; + * - *byte_sz* - size of the enum, in bytes. + * - *is_signed* - whether the enum values are signed or not; + * + * Enum initially has no enum values in it (and corresponds to enum forward + * declaration). Enumerator values can be added by btf__add_enum64_value() + * immediately after btf__add_enum64() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_enum64(struct btf *btf, const char *name, __u32 byte_sz, + bool is_signed) +{ + return btf_add_enum_common(btf, name, byte_sz, is_signed, + BTF_KIND_ENUM64); +} + +/* + * Append new enum value for the current ENUM64 type with: + * - *name* - name of the enumerator value, can't be NULL or empty; + * - *value* - integer value corresponding to enum value *name*; + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value) +{ + struct btf_enum64 *v; + struct btf_type *t; + int sz, name_off; + + /* last type should be BTF_KIND_ENUM64 */ + if (btf->nr_types == 0) + return libbpf_err(-EINVAL); + t = btf_last_type(btf); + if (!btf_is_enum64(t)) + return libbpf_err(-EINVAL); + + /* non-empty name */ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_enum64); + v = btf_add_type_mem(btf, sz); + if (!v) + return libbpf_err(-ENOMEM); + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + v->name_off = name_off; + v->val_lo32 = (__u32)value; + v->val_hi32 = value >> 32; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_FWD type with: + * - *name*, non-empty/non-NULL name; + * - *fwd_kind*, kind of forward declaration, one of BTF_FWD_STRUCT, + * BTF_FWD_UNION, or BTF_FWD_ENUM; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind) +{ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + + switch (fwd_kind) { + case BTF_FWD_STRUCT: + case BTF_FWD_UNION: { + struct btf_type *t; + int id; + + id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0); + if (id <= 0) + return id; + t = btf_type_by_id(btf, id); + t->info = btf_type_info(BTF_KIND_FWD, 0, fwd_kind == BTF_FWD_UNION); + return id; + } + case BTF_FWD_ENUM: + /* enum forward in BTF currently is just an enum with no enum + * values; we also assume a standard 4-byte size for it + */ + return btf__add_enum(btf, name, sizeof(int)); + default: + return libbpf_err(-EINVAL); + } +} + +/* + * Append new BTF_KING_TYPEDEF type with: + * - *name*, non-empty/non-NULL name; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) +{ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + + return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id); +} + +/* + * Append new BTF_KIND_VOLATILE type with: + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_volatile(struct btf *btf, int ref_type_id) +{ + return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id); +} + +/* + * Append new BTF_KIND_CONST type with: + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_const(struct btf *btf, int ref_type_id) +{ + return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id); +} + +/* + * Append new BTF_KIND_RESTRICT type with: + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_restrict(struct btf *btf, int ref_type_id) +{ + return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id); +} + +/* + * Append new BTF_KIND_TYPE_TAG type with: + * - *value*, non-empty/non-NULL tag value; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id) +{ + if (!value|| !value[0]) + return libbpf_err(-EINVAL); + + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id); +} + +/* + * Append new BTF_KIND_FUNC type with: + * - *name*, non-empty/non-NULL name; + * - *proto_type_id* - FUNC_PROTO's type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_func(struct btf *btf, const char *name, + enum btf_func_linkage linkage, int proto_type_id) +{ + int id; + + if (!name || !name[0]) + return libbpf_err(-EINVAL); + if (linkage != BTF_FUNC_STATIC && linkage != BTF_FUNC_GLOBAL && + linkage != BTF_FUNC_EXTERN) + return libbpf_err(-EINVAL); + + id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id); + if (id > 0) { + struct btf_type *t = btf_type_by_id(btf, id); + + t->info = btf_type_info(BTF_KIND_FUNC, linkage, 0); + } + return libbpf_err(id); +} + +/* + * Append new BTF_KIND_FUNC_PROTO with: + * - *ret_type_id* - type ID for return result of a function. + * + * Function prototype initially has no arguments, but they can be added by + * btf__add_func_param() one by one, immediately after + * btf__add_func_proto() succeeded. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_func_proto(struct btf *btf, int ret_type_id) +{ + struct btf_type *t; + int sz; + + if (validate_type_id(ret_type_id)) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + /* start out with vlen=0; this will be adjusted when adding enum + * values, if necessary + */ + t->name_off = 0; + t->info = btf_type_info(BTF_KIND_FUNC_PROTO, 0, 0); + t->type = ret_type_id; + + return btf_commit_type(btf, sz); +} + +/* + * Append new function parameter for current FUNC_PROTO type with: + * - *name* - parameter name, can be NULL or empty; + * - *type_id* - type ID describing the type of the parameter. + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_func_param(struct btf *btf, const char *name, int type_id) +{ + struct btf_type *t; + struct btf_param *p; + int sz, name_off = 0; + + if (validate_type_id(type_id)) + return libbpf_err(-EINVAL); + + /* last type should be BTF_KIND_FUNC_PROTO */ + if (btf->nr_types == 0) + return libbpf_err(-EINVAL); + t = btf_last_type(btf); + if (!btf_is_func_proto(t)) + return libbpf_err(-EINVAL); + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_param); + p = btf_add_type_mem(btf, sz); + if (!p) + return libbpf_err(-ENOMEM); + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + p->name_off = name_off; + p->type = type_id; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_VAR type with: + * - *name* - non-empty/non-NULL name; + * - *linkage* - variable linkage, one of BTF_VAR_STATIC, + * BTF_VAR_GLOBAL_ALLOCATED, or BTF_VAR_GLOBAL_EXTERN; + * - *type_id* - type ID of the type describing the type of the variable. + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id) +{ + struct btf_type *t; + struct btf_var *v; + int sz, name_off; + + /* non-empty name */ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + if (linkage != BTF_VAR_STATIC && linkage != BTF_VAR_GLOBAL_ALLOCATED && + linkage != BTF_VAR_GLOBAL_EXTERN) + return libbpf_err(-EINVAL); + if (validate_type_id(type_id)) + return libbpf_err(-EINVAL); + + /* deconstruct BTF, if necessary, and invalidate raw_data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type) + sizeof(struct btf_var); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + t->name_off = name_off; + t->info = btf_type_info(BTF_KIND_VAR, 0, 0); + t->type = type_id; + + v = btf_var(t); + v->linkage = linkage; + + return btf_commit_type(btf, sz); +} + +/* + * Append new BTF_KIND_DATASEC type with: + * - *name* - non-empty/non-NULL name; + * - *byte_sz* - data section size, in bytes. + * + * Data section is initially empty. Variables info can be added with + * btf__add_datasec_var_info() calls, after btf__add_datasec() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz) +{ + struct btf_type *t; + int sz, name_off; + + /* non-empty name */ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + /* start with vlen=0, which will be update as var_secinfos are added */ + t->name_off = name_off; + t->info = btf_type_info(BTF_KIND_DATASEC, 0, 0); + t->size = byte_sz; + + return btf_commit_type(btf, sz); +} + +/* + * Append new data section variable information entry for current DATASEC type: + * - *var_type_id* - type ID, describing type of the variable; + * - *offset* - variable offset within data section, in bytes; + * - *byte_sz* - variable size, in bytes. + * + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz) +{ + struct btf_type *t; + struct btf_var_secinfo *v; + int sz; + + /* last type should be BTF_KIND_DATASEC */ + if (btf->nr_types == 0) + return libbpf_err(-EINVAL); + t = btf_last_type(btf); + if (!btf_is_datasec(t)) + return libbpf_err(-EINVAL); + + if (validate_type_id(var_type_id)) + return libbpf_err(-EINVAL); + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_var_secinfo); + v = btf_add_type_mem(btf, sz); + if (!v) + return libbpf_err(-ENOMEM); + + v->type = var_type_id; + v->offset = offset; + v->size = byte_sz; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_DECL_TAG type with: + * - *value* - non-empty/non-NULL string; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * - *component_idx* - -1 for tagging reference type, otherwise struct/union + * member or function argument index; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + struct btf_type *t; + int sz, value_off; + + if (!value || !value[0] || component_idx < -1) + return libbpf_err(-EINVAL); + + if (validate_type_id(ref_type_id)) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + value_off = btf__add_str(btf, value); + if (value_off < 0) + return value_off; + + t->name_off = value_off; + t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false); + t->type = ref_type_id; + btf_decl_tag(t)->component_idx = component_idx; + + return btf_commit_type(btf, sz); +} + +struct btf_ext_sec_setup_param { + __u32 off; + __u32 len; + __u32 min_rec_size; + struct btf_ext_info *ext_info; + const char *desc; +}; + +static int btf_ext_setup_info(struct btf_ext *btf_ext, + struct btf_ext_sec_setup_param *ext_sec) +{ + const struct btf_ext_info_sec *sinfo; + struct btf_ext_info *ext_info; + __u32 info_left, record_size; + size_t sec_cnt = 0; + /* The start of the info sec (including the __u32 record_size). */ + void *info; + + if (ext_sec->len == 0) + return 0; + + if (ext_sec->off & 0x03) { + pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n", + ext_sec->desc); + return -EINVAL; + } + + info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off; + info_left = ext_sec->len; + + if (btf_ext->data + btf_ext->data_size < info + ext_sec->len) { + pr_debug("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n", + ext_sec->desc, ext_sec->off, ext_sec->len); + return -EINVAL; + } + + /* At least a record size */ + if (info_left < sizeof(__u32)) { + pr_debug(".BTF.ext %s record size not found\n", ext_sec->desc); + return -EINVAL; + } + + /* The record size needs to meet the minimum standard */ + record_size = *(__u32 *)info; + if (record_size < ext_sec->min_rec_size || + record_size & 0x03) { + pr_debug("%s section in .BTF.ext has invalid record size %u\n", + ext_sec->desc, record_size); + return -EINVAL; + } + + sinfo = info + sizeof(__u32); + info_left -= sizeof(__u32); + + /* If no records, return failure now so .BTF.ext won't be used. */ + if (!info_left) { + pr_debug("%s section in .BTF.ext has no records", ext_sec->desc); + return -EINVAL; + } + + while (info_left) { + unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec); + __u64 total_record_size; + __u32 num_records; + + if (info_left < sec_hdrlen) { + pr_debug("%s section header is not found in .BTF.ext\n", + ext_sec->desc); + return -EINVAL; + } + + num_records = sinfo->num_info; + if (num_records == 0) { + pr_debug("%s section has incorrect num_records in .BTF.ext\n", + ext_sec->desc); + return -EINVAL; + } + + total_record_size = sec_hdrlen + (__u64)num_records * record_size; + if (info_left < total_record_size) { + pr_debug("%s section has incorrect num_records in .BTF.ext\n", + ext_sec->desc); + return -EINVAL; + } + + info_left -= total_record_size; + sinfo = (void *)sinfo + total_record_size; + sec_cnt++; + } + + ext_info = ext_sec->ext_info; + ext_info->len = ext_sec->len - sizeof(__u32); + ext_info->rec_size = record_size; + ext_info->info = info + sizeof(__u32); + ext_info->sec_cnt = sec_cnt; + + return 0; +} + +static int btf_ext_setup_func_info(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->func_info_off, + .len = btf_ext->hdr->func_info_len, + .min_rec_size = sizeof(struct bpf_func_info_min), + .ext_info = &btf_ext->func_info, + .desc = "func_info" + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + +static int btf_ext_setup_line_info(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->line_info_off, + .len = btf_ext->hdr->line_info_len, + .min_rec_size = sizeof(struct bpf_line_info_min), + .ext_info = &btf_ext->line_info, + .desc = "line_info", + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + +static int btf_ext_setup_core_relos(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->core_relo_off, + .len = btf_ext->hdr->core_relo_len, + .min_rec_size = sizeof(struct bpf_core_relo), + .ext_info = &btf_ext->core_relo_info, + .desc = "core_relo", + }; + + 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 < offsetofend(struct btf_ext_header, hdr_len) || + data_size < hdr->hdr_len) { + pr_debug("BTF.ext header not found"); + return -EINVAL; + } + + if (hdr->magic == bswap_16(BTF_MAGIC)) { + pr_warn("BTF.ext in non-native endianness is not supported\n"); + return -ENOTSUP; + } else if (hdr->magic != BTF_MAGIC) { + pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + pr_debug("Unsupported BTF.ext version:%u\n", hdr->version); + return -ENOTSUP; + } + + if (hdr->flags) { + pr_debug("Unsupported BTF.ext flags:%x\n", hdr->flags); + return -ENOTSUP; + } + + if (data_size == hdr->hdr_len) { + pr_debug("BTF.ext has no data\n"); + return -EINVAL; + } + + return 0; +} + +void btf_ext__free(struct btf_ext *btf_ext) +{ + if (IS_ERR_OR_NULL(btf_ext)) + return; + free(btf_ext->func_info.sec_idxs); + free(btf_ext->line_info.sec_idxs); + free(btf_ext->core_relo_info.sec_idxs); + free(btf_ext->data); + free(btf_ext); +} + +struct btf_ext *btf_ext__new(const __u8 *data, __u32 size) +{ + struct btf_ext *btf_ext; + int err; + + btf_ext = calloc(1, sizeof(struct btf_ext)); + if (!btf_ext) + return libbpf_err_ptr(-ENOMEM); + + btf_ext->data_size = size; + btf_ext->data = malloc(size); + if (!btf_ext->data) { + err = -ENOMEM; + goto done; + } + memcpy(btf_ext->data, data, size); + + err = btf_ext_parse_hdr(btf_ext->data, size); + if (err) + goto done; + + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { + err = -EINVAL; + goto done; + } + + err = btf_ext_setup_func_info(btf_ext); + if (err) + goto done; + + err = btf_ext_setup_line_info(btf_ext); + if (err) + goto done; + + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + goto done; /* skip core relos parsing */ + + err = btf_ext_setup_core_relos(btf_ext); + if (err) + goto done; + +done: + if (err) { + btf_ext__free(btf_ext); + return libbpf_err_ptr(err); + } + + return btf_ext; +} + +const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size) +{ + *size = btf_ext->data_size; + return btf_ext->data; +} + +struct btf_dedup; + +static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts); +static void btf_dedup_free(struct btf_dedup *d); +static int btf_dedup_prep(struct btf_dedup *d); +static int btf_dedup_strings(struct btf_dedup *d); +static int btf_dedup_prim_types(struct btf_dedup *d); +static int btf_dedup_struct_types(struct btf_dedup *d); +static int btf_dedup_ref_types(struct btf_dedup *d); +static int btf_dedup_compact_types(struct btf_dedup *d); +static int btf_dedup_remap_types(struct btf_dedup *d); + +/* + * Deduplicate BTF types and strings. + * + * BTF dedup algorithm takes as an input `struct btf` representing `.BTF` ELF + * section with all BTF type descriptors and string data. It overwrites that + * memory in-place with deduplicated types and strings without any loss of + * information. If optional `struct btf_ext` representing '.BTF.ext' ELF section + * is provided, all the strings referenced from .BTF.ext section are honored + * and updated to point to the right offsets after deduplication. + * + * If function returns with error, type/string data might be garbled and should + * be discarded. + * + * More verbose and detailed description of both problem btf_dedup is solving, + * as well as solution could be found at: + * https://facebookmicrosites.github.io/bpf/blog/2018/11/14/btf-enhancement.html + * + * Problem description and justification + * ===================================== + * + * BTF type information is typically emitted either as a result of conversion + * from DWARF to BTF or directly by compiler. In both cases, each compilation + * unit contains information about a subset of all the types that are used + * in an application. These subsets are frequently overlapping and contain a lot + * of duplicated information when later concatenated together into a single + * binary. This algorithm ensures that each unique type is represented by single + * BTF type descriptor, greatly reducing resulting size of BTF data. + * + * Compilation unit isolation and subsequent duplication of data is not the only + * problem. The same type hierarchy (e.g., struct and all the type that struct + * references) in different compilation units can be represented in BTF to + * various degrees of completeness (or, rather, incompleteness) due to + * struct/union forward declarations. + * + * Let's take a look at an example, that we'll use to better understand the + * problem (and solution). Suppose we have two compilation units, each using + * same `struct S`, but each of them having incomplete type information about + * struct's fields: + * + * // CU #1: + * struct S; + * struct A { + * int a; + * struct A* self; + * struct S* parent; + * }; + * struct B; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * // CU #2: + * struct S; + * struct A; + * struct B { + * int b; + * struct B* self; + * struct S* parent; + * }; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * In case of CU #1, BTF data will know only that `struct B` exist (but no + * more), but will know the complete type information about `struct A`. While + * for CU #2, it will know full type information about `struct B`, but will + * only know about forward declaration of `struct A` (in BTF terms, it will + * have `BTF_KIND_FWD` type descriptor with name `B`). + * + * This compilation unit isolation means that it's possible that there is no + * single CU with complete type information describing structs `S`, `A`, and + * `B`. Also, we might get tons of duplicated and redundant type information. + * + * Additional complication we need to keep in mind comes from the fact that + * types, in general, can form graphs containing cycles, not just DAGs. + * + * While algorithm does deduplication, it also merges and resolves type + * information (unless disabled throught `struct btf_opts`), whenever possible. + * E.g., in the example above with two compilation units having partial type + * information for structs `A` and `B`, the output of algorithm will emit + * a single copy of each BTF type that describes structs `A`, `B`, and `S` + * (as well as type information for `int` and pointers), as if they were defined + * in a single compilation unit as: + * + * struct A { + * int a; + * struct A* self; + * struct S* parent; + * }; + * struct B { + * int b; + * struct B* self; + * struct S* parent; + * }; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * Algorithm summary + * ================= + * + * Algorithm completes its work in 6 separate passes: + * + * 1. Strings deduplication. + * 2. Primitive types deduplication (int, enum, fwd). + * 3. Struct/union types deduplication. + * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func + * protos, and const/volatile/restrict modifiers). + * 5. Types compaction. + * 6. Types remapping. + * + * Algorithm determines canonical type descriptor, which is a single + * representative type for each truly unique type. This canonical type is the + * one that will go into final deduplicated BTF type information. For + * struct/unions, it is also the type that algorithm will merge additional type + * information into (while resolving FWDs), as it discovers it from data in + * other CUs. Each input BTF type eventually gets either mapped to itself, if + * that type is canonical, or to some other type, if that type is equivalent + * and was chosen as canonical representative. This mapping is stored in + * `btf_dedup->map` array. This map is also used to record STRUCT/UNION that + * FWD type got resolved to. + * + * To facilitate fast discovery of canonical types, we also maintain canonical + * index (`btf_dedup->dedup_table`), which maps type descriptor's signature hash + * (i.e., hashed kind, name, size, fields, etc) into a list of canonical types + * that match that signature. With sufficiently good choice of type signature + * hashing function, we can limit number of canonical types for each unique type + * signature to a very small number, allowing to find canonical type for any + * duplicated type very quickly. + * + * Struct/union deduplication is the most critical part and algorithm for + * deduplicating structs/unions is described in greater details in comments for + * `btf_dedup_is_equiv` function. + */ +int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts) +{ + struct btf_dedup *d; + int err; + + if (!OPTS_VALID(opts, btf_dedup_opts)) + return libbpf_err(-EINVAL); + + d = btf_dedup_new(btf, opts); + if (IS_ERR(d)) { + pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); + return libbpf_err(-EINVAL); + } + + if (btf_ensure_modifiable(btf)) { + err = -ENOMEM; + goto done; + } + + err = btf_dedup_prep(d); + if (err) { + pr_debug("btf_dedup_prep failed:%d\n", err); + goto done; + } + err = btf_dedup_strings(d); + if (err < 0) { + pr_debug("btf_dedup_strings failed:%d\n", err); + goto done; + } + err = btf_dedup_prim_types(d); + if (err < 0) { + pr_debug("btf_dedup_prim_types failed:%d\n", err); + goto done; + } + err = btf_dedup_struct_types(d); + if (err < 0) { + pr_debug("btf_dedup_struct_types failed:%d\n", err); + goto done; + } + err = btf_dedup_ref_types(d); + if (err < 0) { + pr_debug("btf_dedup_ref_types failed:%d\n", err); + goto done; + } + err = btf_dedup_compact_types(d); + if (err < 0) { + pr_debug("btf_dedup_compact_types failed:%d\n", err); + goto done; + } + err = btf_dedup_remap_types(d); + if (err < 0) { + pr_debug("btf_dedup_remap_types failed:%d\n", err); + goto done; + } + +done: + btf_dedup_free(d); + return libbpf_err(err); +} + +#define BTF_UNPROCESSED_ID ((__u32)-1) +#define BTF_IN_PROGRESS_ID ((__u32)-2) + +struct btf_dedup { + /* .BTF section to be deduped in-place */ + struct btf *btf; + /* + * Optional .BTF.ext section. When provided, any strings referenced + * from it will be taken into account when deduping strings + */ + struct btf_ext *btf_ext; + /* + * This is a map from any type's signature hash to a list of possible + * canonical representative type candidates. Hash collisions are + * ignored, so even types of various kinds can share same list of + * candidates, which is fine because we rely on subsequent + * btf_xxx_equal() checks to authoritatively verify type equality. + */ + struct hashmap *dedup_table; + /* Canonical types map */ + __u32 *map; + /* Hypothetical mapping, used during type graph equivalence checks */ + __u32 *hypot_map; + __u32 *hypot_list; + size_t hypot_cnt; + size_t hypot_cap; + /* Whether hypothetical mapping, if successful, would need to adjust + * already canonicalized types (due to a new forward declaration to + * concrete type resolution). In such case, during split BTF dedup + * candidate type would still be considered as different, because base + * BTF is considered to be immutable. + */ + bool hypot_adjust_canon; + /* Various option modifying behavior of algorithm */ + struct btf_dedup_opts opts; + /* temporary strings deduplication state */ + struct strset *strs_set; +}; + +static long hash_combine(long h, long value) +{ + return h * 31 + value; +} + +#define for_each_dedup_cand(d, node, hash) \ + hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash) + +static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id) +{ + return hashmap__append(d->dedup_table, + (void *)hash, (void *)(long)type_id); +} + +static int btf_dedup_hypot_map_add(struct btf_dedup *d, + __u32 from_id, __u32 to_id) +{ + if (d->hypot_cnt == d->hypot_cap) { + __u32 *new_list; + + d->hypot_cap += max((size_t)16, d->hypot_cap / 2); + new_list = libbpf_reallocarray(d->hypot_list, d->hypot_cap, sizeof(__u32)); + if (!new_list) + return -ENOMEM; + d->hypot_list = new_list; + } + d->hypot_list[d->hypot_cnt++] = from_id; + d->hypot_map[from_id] = to_id; + return 0; +} + +static void btf_dedup_clear_hypot_map(struct btf_dedup *d) +{ + int i; + + for (i = 0; i < d->hypot_cnt; i++) + d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID; + d->hypot_cnt = 0; + d->hypot_adjust_canon = false; +} + +static void btf_dedup_free(struct btf_dedup *d) +{ + hashmap__free(d->dedup_table); + d->dedup_table = NULL; + + free(d->map); + d->map = NULL; + + free(d->hypot_map); + d->hypot_map = NULL; + + free(d->hypot_list); + d->hypot_list = NULL; + + free(d); +} + +static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx) +{ + return 0; +} + +static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts) +{ + struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup)); + hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn; + int i, err = 0, type_cnt; + + if (!d) + return ERR_PTR(-ENOMEM); + + if (OPTS_GET(opts, force_collisions, false)) + hash_fn = btf_dedup_collision_hash_fn; + + d->btf = btf; + d->btf_ext = OPTS_GET(opts, btf_ext, NULL); + + d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(d->dedup_table)) { + err = PTR_ERR(d->dedup_table); + d->dedup_table = NULL; + goto done; + } + + type_cnt = btf__type_cnt(btf); + d->map = malloc(sizeof(__u32) * type_cnt); + if (!d->map) { + err = -ENOMEM; + goto done; + } + /* special BTF "void" type is made canonical immediately */ + d->map[0] = 0; + for (i = 1; i < type_cnt; i++) { + struct btf_type *t = btf_type_by_id(d->btf, i); + + /* VAR and DATASEC are never deduped and are self-canonical */ + if (btf_is_var(t) || btf_is_datasec(t)) + d->map[i] = i; + else + d->map[i] = BTF_UNPROCESSED_ID; + } + + d->hypot_map = malloc(sizeof(__u32) * type_cnt); + if (!d->hypot_map) { + err = -ENOMEM; + goto done; + } + for (i = 0; i < type_cnt; i++) + d->hypot_map[i] = BTF_UNPROCESSED_ID; + +done: + if (err) { + btf_dedup_free(d); + return ERR_PTR(err); + } + + return d; +} + +/* + * Iterate over all possible places in .BTF and .BTF.ext that can reference + * string and pass pointer to it to a provided callback `fn`. + */ +static int btf_for_each_str_off(struct btf_dedup *d, str_off_visit_fn fn, void *ctx) +{ + int i, r; + + for (i = 0; i < d->btf->nr_types; i++) { + struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i); + + r = btf_type_visit_str_offs(t, fn, ctx); + if (r) + return r; + } + + if (!d->btf_ext) + return 0; + + r = btf_ext_visit_str_offs(d->btf_ext, fn, ctx); + if (r) + return r; + + return 0; +} + +static int strs_dedup_remap_str_off(__u32 *str_off_ptr, void *ctx) +{ + struct btf_dedup *d = ctx; + __u32 str_off = *str_off_ptr; + const char *s; + int off, err; + + /* don't touch empty string or string in main BTF */ + if (str_off == 0 || str_off < d->btf->start_str_off) + return 0; + + s = btf__str_by_offset(d->btf, str_off); + if (d->btf->base_btf) { + err = btf__find_str(d->btf->base_btf, s); + if (err >= 0) { + *str_off_ptr = err; + return 0; + } + if (err != -ENOENT) + return err; + } + + off = strset__add_str(d->strs_set, s); + if (off < 0) + return off; + + *str_off_ptr = d->btf->start_str_off + off; + return 0; +} + +/* + * Dedup string and filter out those that are not referenced from either .BTF + * or .BTF.ext (if provided) sections. + * + * This is done by building index of all strings in BTF's string section, + * then iterating over all entities that can reference strings (e.g., type + * names, struct field names, .BTF.ext line info, etc) and marking corresponding + * strings as used. After that all used strings are deduped and compacted into + * sequential blob of memory and new offsets are calculated. Then all the string + * references are iterated again and rewritten using new offsets. + */ +static int btf_dedup_strings(struct btf_dedup *d) +{ + int err; + + if (d->btf->strs_deduped) + return 0; + + d->strs_set = strset__new(BTF_MAX_STR_OFFSET, NULL, 0); + if (IS_ERR(d->strs_set)) { + err = PTR_ERR(d->strs_set); + goto err_out; + } + + if (!d->btf->base_btf) { + /* insert empty string; we won't be looking it up during strings + * dedup, but it's good to have it for generic BTF string lookups + */ + err = strset__add_str(d->strs_set, ""); + if (err < 0) + goto err_out; + } + + /* remap string offsets */ + err = btf_for_each_str_off(d, strs_dedup_remap_str_off, d); + if (err) + goto err_out; + + /* replace BTF string data and hash with deduped ones */ + strset__free(d->btf->strs_set); + d->btf->hdr->str_len = strset__data_size(d->strs_set); + d->btf->strs_set = d->strs_set; + d->strs_set = NULL; + d->btf->strs_deduped = true; + return 0; + +err_out: + strset__free(d->strs_set); + d->strs_set = NULL; + + return err; +} + +static long btf_hash_common(struct btf_type *t) +{ + long h; + + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info); + h = hash_combine(h, t->size); + return h; +} + +static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) +{ + return t1->name_off == t2->name_off && + t1->info == t2->info && + t1->size == t2->size; +} + +/* Calculate type signature hash of INT or TAG. */ +static long btf_hash_int_decl_tag(struct btf_type *t) +{ + __u32 info = *(__u32 *)(t + 1); + long h; + + h = btf_hash_common(t); + h = hash_combine(h, info); + return h; +} + +/* Check structural equality of two INTs or TAGs. */ +static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2) +{ + __u32 info1, info2; + + if (!btf_equal_common(t1, t2)) + return false; + info1 = *(__u32 *)(t1 + 1); + info2 = *(__u32 *)(t2 + 1); + return info1 == info2; +} + +/* Calculate type signature hash of ENUM/ENUM64. */ +static long btf_hash_enum(struct btf_type *t) +{ + long h; + + /* don't hash vlen and enum members to support enum fwd resolving */ + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info & ~0xffff); + h = hash_combine(h, t->size); + return h; +} + +/* Check structural equality of two ENUMs. */ +static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_enum *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + 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; + m1++; + m2++; + } + return true; +} + +static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_enum64 *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = btf_vlen(t1); + m1 = btf_enum64(t1); + m2 = btf_enum64(t2); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->val_lo32 != m2->val_lo32 || + m1->val_hi32 != m2->val_hi32) + return false; + m1++; + m2++; + } + return true; +} + +static inline bool btf_is_enum_fwd(struct btf_type *t) +{ + return btf_is_any_enum(t) && btf_vlen(t) == 0; +} + +static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2)) + return btf_equal_enum(t1, t2); + /* ignore vlen when comparing */ + return t1->name_off == t2->name_off && + (t1->info & ~0xffff) == (t2->info & ~0xffff) && + t1->size == t2->size; +} + +static bool btf_compat_enum64(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2)) + return btf_equal_enum64(t1, t2); + + /* ignore vlen when comparing */ + return t1->name_off == t2->name_off && + (t1->info & ~0xffff) == (t2->info & ~0xffff) && + t1->size == t2->size; +} + +/* + * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs, + * as referenced type IDs equivalence is established separately during type + * graph equivalence check algorithm. + */ +static long btf_hash_struct(struct btf_type *t) +{ + const struct btf_member *member = btf_members(t); + __u32 vlen = btf_vlen(t); + long h = btf_hash_common(t); + int i; + + for (i = 0; i < vlen; i++) { + h = hash_combine(h, member->name_off); + h = hash_combine(h, member->offset); + /* no hashing of referenced type ID, it can be unresolved yet */ + member++; + } + return h; +} + +/* + * Check structural compatibility of two STRUCTs/UNIONs, ignoring referenced + * type IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_member *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + 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; + m1++; + m2++; + } + return true; +} + +/* + * Calculate type signature hash of ARRAY, including referenced type IDs, + * under assumption that they were already resolved to canonical type IDs and + * are not going to change. + */ +static long btf_hash_array(struct btf_type *t) +{ + const struct btf_array *info = btf_array(t); + long h = btf_hash_common(t); + + h = hash_combine(h, info->type); + h = hash_combine(h, info->index_type); + h = hash_combine(h, info->nelems); + return h; +} + +/* + * Check exact equality of two ARRAYs, taking into account referenced + * type IDs, under assumption that they were already resolved to canonical + * type IDs and are not going to change. + * This function is called during reference types deduplication to compare + * ARRAY to potential canonical representative. + */ +static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_array *info1, *info2; + + if (!btf_equal_common(t1, t2)) + return false; + + info1 = btf_array(t1); + info2 = btf_array(t2); + return info1->type == info2->type && + info1->index_type == info2->index_type && + info1->nelems == info2->nelems; +} + +/* + * Check structural compatibility of two ARRAYs, ignoring referenced type + * IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_equal_common(t1, t2)) + return false; + + return btf_array(t1)->nelems == btf_array(t2)->nelems; +} + +/* + * Calculate type signature hash of FUNC_PROTO, including referenced type IDs, + * under assumption that they were already resolved to canonical type IDs and + * are not going to change. + */ +static long btf_hash_fnproto(struct btf_type *t) +{ + const struct btf_param *member = btf_params(t); + __u16 vlen = btf_vlen(t); + long h = btf_hash_common(t); + int i; + + for (i = 0; i < vlen; i++) { + h = hash_combine(h, member->name_off); + h = hash_combine(h, member->type); + member++; + } + return h; +} + +/* + * Check exact equality of two FUNC_PROTOs, taking into account referenced + * type IDs, under assumption that they were already resolved to canonical + * type IDs and are not going to change. + * This function is called during reference types deduplication to compare + * FUNC_PROTO to potential canonical representative. + */ +static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_param *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + 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; + m1++; + m2++; + } + return true; +} + +/* + * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type + * IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_param *m1, *m2; + __u16 vlen; + int i; + + /* skip return type ID */ + if (t1->name_off != t2->name_off || t1->info != t2->info) + return false; + + 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; + m1++; + m2++; + } + return true; +} + +/* Prepare split BTF for deduplication by calculating hashes of base BTF's + * types and initializing the rest of the state (canonical type mapping) for + * the fixed base BTF part. + */ +static int btf_dedup_prep(struct btf_dedup *d) +{ + struct btf_type *t; + int type_id; + long h; + + if (!d->btf->base_btf) + return 0; + + for (type_id = 1; type_id < d->btf->start_id; type_id++) { + t = btf_type_by_id(d->btf, type_id); + + /* all base BTF types are self-canonical by definition */ + d->map[type_id] = type_id; + + switch (btf_kind(t)) { + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: + /* VAR and DATASEC are never hash/deduplicated */ + continue; + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_FWD: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: + h = btf_hash_common(t); + break; + case BTF_KIND_INT: + case BTF_KIND_DECL_TAG: + h = btf_hash_int_decl_tag(t); + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + h = btf_hash_enum(t); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + h = btf_hash_struct(t); + break; + case BTF_KIND_ARRAY: + h = btf_hash_array(t); + break; + case BTF_KIND_FUNC_PROTO: + h = btf_hash_fnproto(t); + break; + default: + pr_debug("unknown kind %d for type [%d]\n", btf_kind(t), type_id); + return -EINVAL; + } + if (btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + } + + return 0; +} + +/* + * Deduplicate primitive types, that can't reference other types, by calculating + * their type signature hash and comparing them with any possible canonical + * candidate. If no canonical candidate matches, type itself is marked as + * canonical and is added into `btf_dedup->dedup_table` as another candidate. + */ +static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_type *t = btf_type_by_id(d->btf, type_id); + struct hashmap_entry *hash_entry; + struct btf_type *cand; + /* if we don't find equivalent type, then we are canonical */ + __u32 new_id = type_id; + __u32 cand_id; + long h; + + switch (btf_kind(t)) { + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_ARRAY: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_FUNC: + case BTF_KIND_FUNC_PROTO: + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + return 0; + + case BTF_KIND_INT: + h = btf_hash_int_decl_tag(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_int_tag(t, cand)) { + new_id = cand_id; + break; + } + } + break; + + case BTF_KIND_ENUM: + h = btf_hash_enum(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_enum(t, cand)) { + new_id = cand_id; + break; + } + if (btf_compat_enum(t, cand)) { + if (btf_is_enum_fwd(t)) { + /* resolve fwd to full enum */ + new_id = cand_id; + break; + } + /* resolve canonical enum fwd to full enum */ + d->map[cand_id] = type_id; + } + } + break; + + case BTF_KIND_ENUM64: + h = btf_hash_enum(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_enum64(t, cand)) { + new_id = cand_id; + break; + } + if (btf_compat_enum64(t, cand)) { + if (btf_is_enum_fwd(t)) { + /* resolve fwd to full enum */ + new_id = cand_id; + break; + } + /* resolve canonical enum fwd to full enum */ + d->map[cand_id] = type_id; + } + } + break; + + case BTF_KIND_FWD: + case BTF_KIND_FLOAT: + h = btf_hash_common(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_common(t, cand)) { + new_id = cand_id; + break; + } + } + break; + + default: + return -EINVAL; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return 0; +} + +static int btf_dedup_prim_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 0; i < d->btf->nr_types; i++) { + err = btf_dedup_prim_type(d, d->btf->start_id + i); + if (err) + return err; + } + return 0; +} + +/* + * Check whether type is already mapped into canonical one (could be to itself). + */ +static inline bool is_type_mapped(struct btf_dedup *d, uint32_t type_id) +{ + return d->map[type_id] <= BTF_MAX_NR_TYPES; +} + +/* + * Resolve type ID into its canonical type ID, if any; otherwise return original + * type ID. If type is FWD and is resolved into STRUCT/UNION already, follow + * STRUCT/UNION link and resolve it into canonical type ID as well. + */ +static inline __u32 resolve_type_id(struct btf_dedup *d, __u32 type_id) +{ + while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) + type_id = d->map[type_id]; + return type_id; +} + +/* + * Resolve FWD to underlying STRUCT/UNION, if any; otherwise return original + * type ID. + */ +static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) +{ + __u32 orig_type_id = type_id; + + if (!btf_is_fwd(btf__type_by_id(d->btf, 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_is_fwd(btf__type_by_id(d->btf, type_id))) + return type_id; + + return orig_type_id; +} + + +static inline __u16 btf_fwd_kind(struct btf_type *t) +{ + return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; +} + +/* Check if given two types are identical ARRAY definitions */ +static bool btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2) +{ + struct btf_type *t1, *t2; + + t1 = btf_type_by_id(d->btf, id1); + t2 = btf_type_by_id(d->btf, id2); + if (!btf_is_array(t1) || !btf_is_array(t2)) + return false; + + return btf_equal_array(t1, t2); +} + +/* Check if given two types are identical STRUCT/UNION definitions */ +static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id2) +{ + const struct btf_member *m1, *m2; + struct btf_type *t1, *t2; + int n, i; + + t1 = btf_type_by_id(d->btf, id1); + t2 = btf_type_by_id(d->btf, id2); + + if (!btf_is_composite(t1) || btf_kind(t1) != btf_kind(t2)) + return false; + + if (!btf_shallow_equal_struct(t1, t2)) + return false; + + m1 = btf_members(t1); + m2 = btf_members(t2); + for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) { + if (m1->type != m2->type && + !btf_dedup_identical_arrays(d, m1->type, m2->type) && + !btf_dedup_identical_structs(d, m1->type, m2->type)) + return false; + } + return true; +} + +/* + * Check equivalence of BTF type graph formed by candidate struct/union (we'll + * call it "candidate graph" in this description for brevity) to a type graph + * formed by (potential) canonical struct/union ("canonical graph" for brevity + * here, though keep in mind that not all types in canonical graph are + * necessarily canonical representatives themselves, some of them might be + * duplicates or its uniqueness might not have been established yet). + * Returns: + * - >0, if type graphs are equivalent; + * - 0, if not equivalent; + * - <0, on error. + * + * Algorithm performs side-by-side DFS traversal of both type graphs and checks + * equivalence of BTF types at each step. If at any point BTF types in candidate + * and canonical graphs are not compatible structurally, whole graphs are + * incompatible. If types are structurally equivalent (i.e., all information + * except referenced type IDs is exactly the same), a mapping from `canon_id` to + * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`). + * If a type references other types, then those referenced types are checked + * for equivalence recursively. + * + * During DFS traversal, if we find that for current `canon_id` type we + * already have some mapping in hypothetical map, we check for two possible + * situations: + * - `canon_id` is mapped to exactly the same type as `cand_id`. This will + * happen when type graphs have cycles. In this case we assume those two + * types are equivalent. + * - `canon_id` is mapped to different type. This is contradiction in our + * hypothetical mapping, because same graph in canonical graph corresponds + * to two different types in candidate graph, which for equivalent type + * graphs shouldn't happen. This condition terminates equivalence check + * with negative result. + * + * If type graphs traversal exhausts types to check and find no contradiction, + * then type graphs are equivalent. + * + * When checking types for equivalence, there is one special case: FWD types. + * If FWD type resolution is allowed and one of the types (either from canonical + * or candidate graph) is FWD and other is STRUCT/UNION (depending on FWD's kind + * flag) and their names match, hypothetical mapping is updated to point from + * FWD to STRUCT/UNION. If graphs will be determined as equivalent successfully, + * this mapping will be used to record FWD -> STRUCT/UNION mapping permanently. + * + * Technically, this could lead to incorrect FWD to STRUCT/UNION resolution, + * if there are two exactly named (or anonymous) structs/unions that are + * compatible structurally, one of which has FWD field, while other is concrete + * STRUCT/UNION, but according to C sources they are different structs/unions + * that are referencing different types with the same name. This is extremely + * unlikely to happen, but btf_dedup API allows to disable FWD resolution if + * this logic is causing problems. + * + * Doing FWD resolution means that both candidate and/or canonical graphs can + * consists of portions of the graph that come from multiple compilation units. + * This is due to the fact that types within single compilation unit are always + * deduplicated and FWDs are already resolved, if referenced struct/union + * definiton is available. So, if we had unresolved FWD and found corresponding + * STRUCT/UNION, they will be from different compilation units. This + * consequently means that when we "link" FWD to corresponding STRUCT/UNION, + * type graph will likely have at least two different BTF types that describe + * same type (e.g., most probably there will be two different BTF types for the + * same 'int' primitive type) and could even have "overlapping" parts of type + * graph that describe same subset of types. + * + * This in turn means that our assumption that each type in canonical graph + * must correspond to exactly one type in candidate graph might not hold + * anymore and will make it harder to detect contradictions using hypothetical + * map. To handle this problem, we allow to follow FWD -> STRUCT/UNION + * resolution only in canonical graph. FWDs in candidate graphs are never + * resolved. To see why it's OK, let's check all possible situations w.r.t. FWDs + * that can occur: + * - Both types in canonical and candidate graphs are FWDs. If they are + * structurally equivalent, then they can either be both resolved to the + * same STRUCT/UNION or not resolved at all. In both cases they are + * equivalent and there is no need to resolve FWD on candidate side. + * - Both types in canonical and candidate graphs are concrete STRUCT/UNION, + * so nothing to resolve as well, algorithm will check equivalence anyway. + * - Type in canonical graph is FWD, while type in candidate is concrete + * STRUCT/UNION. In this case candidate graph comes from single compilation + * unit, so there is exactly one BTF type for each unique C type. After + * resolving FWD into STRUCT/UNION, there might be more than one BTF type + * in canonical graph mapping to single BTF type in candidate graph, but + * because hypothetical mapping maps from canonical to candidate types, it's + * alright, and we still maintain the property of having single `canon_id` + * mapping to single `cand_id` (there could be two different `canon_id` + * mapped to the same `cand_id`, but it's not contradictory). + * - Type in canonical graph is concrete STRUCT/UNION, while type in candidate + * graph is FWD. In this case we are just going to check compatibility of + * STRUCT/UNION and corresponding FWD, and if they are compatible, we'll + * assume that whatever STRUCT/UNION FWD resolves to must be equivalent to + * a concrete STRUCT/UNION from canonical graph. If the rest of type graphs + * turn out equivalent, we'll re-resolve FWD to concrete STRUCT/UNION from + * canonical graph. + */ +static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, + __u32 canon_id) +{ + struct btf_type *cand_type; + struct btf_type *canon_type; + __u32 hypot_type_id; + __u16 cand_kind; + __u16 canon_kind; + int i, eq; + + /* if both resolve to the same canonical, they must be equivalent */ + if (resolve_type_id(d, cand_id) == resolve_type_id(d, canon_id)) + return 1; + + canon_id = resolve_fwd_id(d, canon_id); + + hypot_type_id = d->hypot_map[canon_id]; + if (hypot_type_id <= BTF_MAX_NR_TYPES) { + if (hypot_type_id == cand_id) + return 1; + /* In some cases compiler will generate different DWARF types + * for *identical* array type definitions and use them for + * different fields within the *same* struct. This breaks type + * equivalence check, which makes an assumption that candidate + * types sub-graph has a consistent and deduped-by-compiler + * types within a single CU. So work around that by explicitly + * allowing identical array types here. + */ + if (btf_dedup_identical_arrays(d, hypot_type_id, cand_id)) + return 1; + /* It turns out that similar situation can happen with + * struct/union sometimes, sigh... Handle the case where + * structs/unions are exactly the same, down to the referenced + * type IDs. Anything more complicated (e.g., if referenced + * types are different, but equivalent) is *way more* + * complicated and requires a many-to-many equivalence mapping. + */ + if (btf_dedup_identical_structs(d, hypot_type_id, cand_id)) + return 1; + return 0; + } + + if (btf_dedup_hypot_map_add(d, canon_id, cand_id)) + return -ENOMEM; + + cand_type = btf_type_by_id(d->btf, cand_id); + canon_type = btf_type_by_id(d->btf, canon_id); + cand_kind = btf_kind(cand_type); + canon_kind = btf_kind(canon_type); + + if (cand_type->name_off != canon_type->name_off) + return 0; + + /* FWD <--> STRUCT/UNION equivalence check, if enabled */ + if ((cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD) + && cand_kind != canon_kind) { + __u16 real_kind; + __u16 fwd_kind; + + if (cand_kind == BTF_KIND_FWD) { + real_kind = canon_kind; + fwd_kind = btf_fwd_kind(cand_type); + } else { + real_kind = cand_kind; + fwd_kind = btf_fwd_kind(canon_type); + /* we'd need to resolve base FWD to STRUCT/UNION */ + if (fwd_kind == real_kind && canon_id < d->btf->start_id) + d->hypot_adjust_canon = true; + } + return fwd_kind == real_kind; + } + + if (cand_kind != canon_kind) + return 0; + + switch (cand_kind) { + case BTF_KIND_INT: + return btf_equal_int_tag(cand_type, canon_type); + + case BTF_KIND_ENUM: + return btf_compat_enum(cand_type, canon_type); + + case BTF_KIND_ENUM64: + return btf_compat_enum64(cand_type, canon_type); + + case BTF_KIND_FWD: + case BTF_KIND_FLOAT: + return btf_equal_common(cand_type, canon_type); + + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: + if (cand_type->info != canon_type->info) + return 0; + return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); + + case BTF_KIND_ARRAY: { + const struct btf_array *cand_arr, *canon_arr; + + if (!btf_compat_array(cand_type, canon_type)) + return 0; + 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) + return eq; + return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type); + } + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *cand_m, *canon_m; + __u16 vlen; + + if (!btf_shallow_equal_struct(cand_type, canon_type)) + return 0; + 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) + return eq; + cand_m++; + canon_m++; + } + + return 1; + } + + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *cand_p, *canon_p; + __u16 vlen; + + if (!btf_compat_fnproto(cand_type, canon_type)) + return 0; + eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type); + if (eq <= 0) + return eq; + 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) + return eq; + cand_p++; + canon_p++; + } + return 1; + } + + default: + return -EINVAL; + } + return 0; +} + +/* + * Use hypothetical mapping, produced by successful type graph equivalence + * check, to augment existing struct/union canonical mapping, where possible. + * + * If BTF_KIND_FWD resolution is allowed, this mapping is also used to record + * FWD -> STRUCT/UNION correspondence as well. FWD resolution is bidirectional: + * it doesn't matter if FWD type was part of canonical graph or candidate one, + * we are recording the mapping anyway. As opposed to carefulness required + * for struct/union correspondence mapping (described below), for FWD resolution + * it's not important, as by the time that FWD type (reference type) will be + * deduplicated all structs/unions will be deduped already anyway. + * + * Recording STRUCT/UNION mapping is purely a performance optimization and is + * not required for correctness. It needs to be done carefully to ensure that + * struct/union from candidate's type graph is not mapped into corresponding + * struct/union from canonical type graph that itself hasn't been resolved into + * canonical representative. The only guarantee we have is that canonical + * struct/union was determined as canonical and that won't change. But any + * types referenced through that struct/union fields could have been not yet + * resolved, so in case like that it's too early to establish any kind of + * correspondence between structs/unions. + * + * No canonical correspondence is derived for primitive types (they are already + * deduplicated completely already anyway) or reference types (they rely on + * stability of struct/union canonical relationship for equivalence checks). + */ +static void btf_dedup_merge_hypot_map(struct btf_dedup *d) +{ + __u32 canon_type_id, targ_type_id; + __u16 t_kind, c_kind; + __u32 t_id, c_id; + int i; + + for (i = 0; i < d->hypot_cnt; i++) { + canon_type_id = d->hypot_list[i]; + targ_type_id = d->hypot_map[canon_type_id]; + t_id = resolve_type_id(d, targ_type_id); + c_id = resolve_type_id(d, canon_type_id); + t_kind = btf_kind(btf__type_by_id(d->btf, t_id)); + c_kind = btf_kind(btf__type_by_id(d->btf, c_id)); + /* + * Resolve FWD into STRUCT/UNION. + * It's ok to resolve FWD into STRUCT/UNION that's not yet + * mapped to canonical representative (as opposed to + * STRUCT/UNION <--> STRUCT/UNION mapping logic below), because + * eventually that struct is going to be mapped and all resolved + * FWDs will automatically resolve to correct canonical + * representative. This will happen before ref type deduping, + * which critically depends on stability of these mapping. This + * stability is not a requirement for STRUCT/UNION equivalence + * checks, though. + */ + + /* if it's the split BTF case, we still need to point base FWD + * to STRUCT/UNION in a split BTF, because FWDs from split BTF + * will be resolved against base FWD. If we don't point base + * canonical FWD to the resolved STRUCT/UNION, then all the + * FWDs in split BTF won't be correctly resolved to a proper + * STRUCT/UNION. + */ + if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD) + d->map[c_id] = t_id; + + /* if graph equivalence determined that we'd need to adjust + * base canonical types, then we need to only point base FWDs + * to STRUCTs/UNIONs and do no more modifications. For all + * other purposes the type graphs were not equivalent. + */ + if (d->hypot_adjust_canon) + continue; + + if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD) + d->map[t_id] = c_id; + + if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) && + c_kind != BTF_KIND_FWD && + is_type_mapped(d, c_id) && + !is_type_mapped(d, t_id)) { + /* + * as a perf optimization, we can map struct/union + * that's part of type graph we just verified for + * equivalence. We can do that for struct/union that has + * canonical representative only, though. + */ + d->map[t_id] = c_id; + } + } +} + +/* + * Deduplicate struct/union types. + * + * For each struct/union type its type signature hash is calculated, taking + * into account type's name, size, number, order and names of fields, but + * ignoring type ID's referenced from fields, because they might not be deduped + * completely until after reference types deduplication phase. This type hash + * is used to iterate over all potential canonical types, sharing same hash. + * For each canonical candidate we check whether type graphs that they form + * (through referenced types in fields and so on) are equivalent using algorithm + * implemented in `btf_dedup_is_equiv`. If such equivalence is found and + * BTF_KIND_FWD resolution is allowed, then hypothetical mapping + * (btf_dedup->hypot_map) produced by aforementioned type graph equivalence + * algorithm is used to record FWD -> STRUCT/UNION mapping. It's also used to + * potentially map other structs/unions to their canonical representatives, + * if such relationship hasn't yet been established. This speeds up algorithm + * by eliminating some of the duplicate work. + * + * If no matching canonical representative was found, struct/union is marked + * as canonical for itself and is added into btf_dedup->dedup_table hash map + * for further look ups. + */ +static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_type *cand_type, *t; + struct hashmap_entry *hash_entry; + /* if we don't find equivalent type, then we are canonical */ + __u32 new_id = type_id; + __u16 kind; + long h; + + /* already deduped or is in process of deduping (loop detected) */ + if (d->map[type_id] <= BTF_MAX_NR_TYPES) + return 0; + + t = btf_type_by_id(d->btf, type_id); + kind = btf_kind(t); + + if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) + return 0; + + h = btf_hash_struct(t); + for_each_dedup_cand(d, hash_entry, h) { + __u32 cand_id = (__u32)(long)hash_entry->value; + int eq; + + /* + * Even though btf_dedup_is_equiv() checks for + * btf_shallow_equal_struct() internally when checking two + * structs (unions) for equivalence, we need to guard here + * from picking matching FWD type as a dedup candidate. + * This can happen due to hash collision. In such case just + * relying on btf_dedup_is_equiv() would lead to potentially + * creating a loop (FWD -> STRUCT and STRUCT -> FWD), because + * FWD and compatible STRUCT/UNION are considered equivalent. + */ + cand_type = btf_type_by_id(d->btf, cand_id); + if (!btf_shallow_equal_struct(t, cand_type)) + continue; + + btf_dedup_clear_hypot_map(d); + eq = btf_dedup_is_equiv(d, type_id, cand_id); + if (eq < 0) + return eq; + if (!eq) + continue; + btf_dedup_merge_hypot_map(d); + if (d->hypot_adjust_canon) /* not really equivalent */ + continue; + new_id = cand_id; + break; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return 0; +} + +static int btf_dedup_struct_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 0; i < d->btf->nr_types; i++) { + err = btf_dedup_struct_type(d, d->btf->start_id + i); + if (err) + return err; + } + return 0; +} + +/* + * Deduplicate reference type. + * + * Once all primitive and struct/union types got deduplicated, we can easily + * deduplicate all other (reference) BTF types. This is done in two steps: + * + * 1. Resolve all referenced type IDs into their canonical type IDs. This + * resolution can be done either immediately for primitive or struct/union types + * (because they were deduped in previous two phases) or recursively for + * reference types. Recursion will always terminate at either primitive or + * struct/union type, at which point we can "unwind" chain of reference types + * one by one. There is no danger of encountering cycles because in C type + * system the only way to form type cycle is through struct/union, so any chain + * of reference types, even those taking part in a type cycle, will inevitably + * reach struct/union at some point. + * + * 2. Once all referenced type IDs are resolved into canonical ones, BTF type + * becomes "stable", in the sense that no further deduplication will cause + * any changes to it. With that, it's now possible to calculate type's signature + * hash (this time taking into account referenced type IDs) and loop over all + * potential canonical representatives. If no match was found, current type + * will become canonical representative of itself and will be added into + * btf_dedup->dedup_table as another possible canonical representative. + */ +static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) +{ + struct hashmap_entry *hash_entry; + __u32 new_id = type_id, cand_id; + struct btf_type *t, *cand; + /* if we don't find equivalent type, then we are representative type */ + int ref_type_id; + long h; + + if (d->map[type_id] == BTF_IN_PROGRESS_ID) + return -ELOOP; + if (d->map[type_id] <= BTF_MAX_NR_TYPES) + return resolve_type_id(d, type_id); + + t = btf_type_by_id(d->btf, type_id); + d->map[type_id] = BTF_IN_PROGRESS_ID; + + switch (btf_kind(t)) { + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + h = btf_hash_common(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_common(t, cand)) { + new_id = cand_id; + break; + } + } + break; + + case BTF_KIND_DECL_TAG: + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + h = btf_hash_int_decl_tag(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_int_tag(t, cand)) { + new_id = cand_id; + break; + } + } + break; + + case BTF_KIND_ARRAY: { + struct btf_array *info = btf_array(t); + + ref_type_id = btf_dedup_ref_type(d, info->type); + if (ref_type_id < 0) + return ref_type_id; + info->type = ref_type_id; + + ref_type_id = btf_dedup_ref_type(d, info->index_type); + if (ref_type_id < 0) + return ref_type_id; + info->index_type = ref_type_id; + + h = btf_hash_array(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_array(t, cand)) { + new_id = cand_id; + break; + } + } + break; + } + + case BTF_KIND_FUNC_PROTO: { + struct btf_param *param; + __u16 vlen; + int i; + + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + 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) + return ref_type_id; + param->type = ref_type_id; + param++; + } + + h = btf_hash_fnproto(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_fnproto(t, cand)) { + new_id = cand_id; + break; + } + } + break; + } + + default: + return -EINVAL; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return new_id; +} + +static int btf_dedup_ref_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 0; i < d->btf->nr_types; i++) { + err = btf_dedup_ref_type(d, d->btf->start_id + i); + if (err < 0) + return err; + } + /* we won't need d->dedup_table anymore */ + hashmap__free(d->dedup_table); + d->dedup_table = NULL; + return 0; +} + +/* + * Compact types. + * + * After we established for each type its corresponding canonical representative + * type, we now can eliminate types that are not canonical and leave only + * canonical ones layed out sequentially in memory by copying them over + * duplicates. During compaction btf_dedup->hypot_map array is reused to store + * a map from original type ID to a new compacted type ID, which will be used + * during next phase to "fix up" type IDs, referenced from struct/union and + * reference types. + */ +static int btf_dedup_compact_types(struct btf_dedup *d) +{ + __u32 *new_offs; + __u32 next_type_id = d->btf->start_id; + const struct btf_type *t; + void *p; + int i, id, len; + + /* we are going to reuse hypot_map to store compaction remapping */ + d->hypot_map[0] = 0; + /* base BTF types are not renumbered */ + for (id = 1; id < d->btf->start_id; id++) + d->hypot_map[id] = id; + for (i = 0, id = d->btf->start_id; i < d->btf->nr_types; i++, id++) + d->hypot_map[id] = BTF_UNPROCESSED_ID; + + p = d->btf->types_data; + + for (i = 0, id = d->btf->start_id; i < d->btf->nr_types; i++, id++) { + if (d->map[id] != id) + continue; + + t = btf__type_by_id(d->btf, id); + len = btf_type_size(t); + if (len < 0) + return len; + + memmove(p, t, len); + d->hypot_map[id] = next_type_id; + d->btf->type_offs[next_type_id - d->btf->start_id] = p - d->btf->types_data; + p += len; + next_type_id++; + } + + /* shrink struct btf's internal types index and update btf_header */ + d->btf->nr_types = next_type_id - d->btf->start_id; + d->btf->type_offs_cap = d->btf->nr_types; + d->btf->hdr->type_len = p - d->btf->types_data; + new_offs = libbpf_reallocarray(d->btf->type_offs, d->btf->type_offs_cap, + sizeof(*new_offs)); + if (d->btf->type_offs_cap && !new_offs) + return -ENOMEM; + d->btf->type_offs = new_offs; + d->btf->hdr->str_off = d->btf->hdr->type_len; + d->btf->raw_size = d->btf->hdr->hdr_len + d->btf->hdr->type_len + d->btf->hdr->str_len; + return 0; +} + +/* + * Figure out final (deduplicated and compacted) type ID for provided original + * `type_id` by first resolving it into corresponding canonical type ID and + * then mapping it to a deduplicated type ID, stored in btf_dedup->hypot_map, + * which is populated during compaction phase. + */ +static int btf_dedup_remap_type_id(__u32 *type_id, void *ctx) +{ + struct btf_dedup *d = ctx; + __u32 resolved_type_id, new_type_id; + + resolved_type_id = resolve_type_id(d, *type_id); + new_type_id = d->hypot_map[resolved_type_id]; + if (new_type_id > BTF_MAX_NR_TYPES) + return -EINVAL; + + *type_id = new_type_id; + return 0; +} + +/* + * Remap referenced type IDs into deduped type IDs. + * + * After BTF types are deduplicated and compacted, their final type IDs may + * differ from original ones. The map from original to a corresponding + * deduped type ID is stored in btf_dedup->hypot_map and is populated during + * compaction phase. During remapping phase we are rewriting all type IDs + * referenced from any BTF type (e.g., struct fields, func proto args, etc) to + * their final deduped type IDs. + */ +static int btf_dedup_remap_types(struct btf_dedup *d) +{ + int i, r; + + for (i = 0; i < d->btf->nr_types; i++) { + struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i); + + r = btf_type_visit_type_ids(t, btf_dedup_remap_type_id, d); + if (r) + return r; + } + + if (!d->btf_ext) + return 0; + + r = btf_ext_visit_type_ids(d->btf_ext, btf_dedup_remap_type_id, d); + if (r) + return r; + + return 0; +} + +/* + * 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 *btf__load_vmlinux_btf(void) +{ + const char *locations[] = { + /* try canonical vmlinux BTF through sysfs first */ + "/sys/kernel/btf/vmlinux", + /* fall back to trying to find vmlinux on disk otherwise */ + "/boot/vmlinux-%1$s", + "/lib/modules/%1$s/vmlinux-%1$s", + "/lib/modules/%1$s/build/vmlinux", + "/usr/lib/modules/%1$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, err; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i], buf.release); + + if (faccessat(AT_FDCWD, path, R_OK, AT_EACCESS)) + continue; + + btf = btf__parse(path, NULL); + err = libbpf_get_error(btf); + pr_debug("loading kernel BTF '%s': %d\n", path, err); + if (err) + continue; + + return btf; + } + + pr_warn("failed to find valid kernel BTF\n"); + return libbpf_err_ptr(-ESRCH); +} + +struct btf *libbpf_find_kernel_btf(void) __attribute__((alias("btf__load_vmlinux_btf"))); + +struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_btf) +{ + char path[80]; + + snprintf(path, sizeof(path), "/sys/kernel/btf/%s", module_name); + return btf__parse_split(path, vmlinux_btf); +} + +int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx) +{ + int i, n, err; + + switch (btf_kind(t)) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + return 0; + + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + return visit(&t->type, ctx); + + case BTF_KIND_ARRAY: { + struct btf_array *a = btf_array(t); + + err = visit(&a->type, ctx); + err = err ?: visit(&a->index_type, ctx); + return err; + } + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *m = btf_members(t); + + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->type, ctx); + if (err) + return err; + } + return 0; + } + + case BTF_KIND_FUNC_PROTO: { + struct btf_param *m = btf_params(t); + + err = visit(&t->type, ctx); + if (err) + return err; + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->type, ctx); + if (err) + return err; + } + return 0; + } + + case BTF_KIND_DATASEC: { + struct btf_var_secinfo *m = btf_var_secinfos(t); + + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->type, ctx); + if (err) + return err; + } + return 0; + } + + default: + return -EINVAL; + } +} + +int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx) +{ + int i, n, err; + + err = visit(&t->name_off, ctx); + if (err) + return err; + + switch (btf_kind(t)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *m = btf_members(t); + + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->name_off, ctx); + if (err) + return err; + } + break; + } + case BTF_KIND_ENUM: { + struct btf_enum *m = btf_enum(t); + + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->name_off, ctx); + if (err) + return err; + } + break; + } + case BTF_KIND_ENUM64: { + struct btf_enum64 *m = btf_enum64(t); + + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->name_off, ctx); + if (err) + return err; + } + break; + } + case BTF_KIND_FUNC_PROTO: { + struct btf_param *m = btf_params(t); + + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->name_off, ctx); + if (err) + return err; + } + break; + } + default: + break; + } + + return 0; +} + +int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx) +{ + const struct btf_ext_info *seg; + struct btf_ext_info_sec *sec; + int i, err; + + seg = &btf_ext->func_info; + for_each_btf_ext_sec(seg, sec) { + struct bpf_func_info_min *rec; + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = visit(&rec->type_id, ctx); + if (err < 0) + return err; + } + } + + seg = &btf_ext->core_relo_info; + for_each_btf_ext_sec(seg, sec) { + struct bpf_core_relo *rec; + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = visit(&rec->type_id, ctx); + if (err < 0) + return err; + } + } + + return 0; +} + +int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx) +{ + const struct btf_ext_info *seg; + struct btf_ext_info_sec *sec; + int i, err; + + seg = &btf_ext->func_info; + for_each_btf_ext_sec(seg, sec) { + err = visit(&sec->sec_name_off, ctx); + if (err) + return err; + } + + seg = &btf_ext->line_info; + for_each_btf_ext_sec(seg, sec) { + struct bpf_line_info_min *rec; + + err = visit(&sec->sec_name_off, ctx); + if (err) + return err; + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = visit(&rec->file_name_off, ctx); + if (err) + return err; + err = visit(&rec->line_off, ctx); + if (err) + return err; + } + } + + seg = &btf_ext->core_relo_info; + for_each_btf_ext_sec(seg, sec) { + struct bpf_core_relo *rec; + + err = visit(&sec->sec_name_off, ctx); + if (err) + return err; + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = visit(&rec->access_str_off, ctx); + if (err) + return err; + } + } + + return 0; +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h new file mode 100644 index 000000000..8e6880d91 --- /dev/null +++ b/tools/lib/bpf/btf.h @@ -0,0 +1,575 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2018 Facebook */ +/*! \file */ + +#ifndef __LIBBPF_BTF_H +#define __LIBBPF_BTF_H + +#include <stdarg.h> +#include <stdbool.h> +#include <linux/btf.h> +#include <linux/types.h> + +#include "libbpf_common.h" + +#ifdef __cplusplus +extern "C" { +#endif + +#define BTF_ELF_SEC ".BTF" +#define BTF_EXT_ELF_SEC ".BTF.ext" +#define MAPS_ELF_SEC ".maps" + +struct btf; +struct btf_ext; +struct btf_type; + +struct bpf_object; + +enum btf_endianness { + BTF_LITTLE_ENDIAN = 0, + BTF_BIG_ENDIAN = 1, +}; + +/** + * @brief **btf__free()** frees all data of a BTF object + * @param btf BTF object to free + */ +LIBBPF_API void btf__free(struct btf *btf); + +/** + * @brief **btf__new()** creates a new instance of a BTF object from the raw + * bytes of an ELF's BTF section + * @param data raw bytes + * @param size number of bytes passed in `data` + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ +LIBBPF_API struct btf *btf__new(const void *data, __u32 size); + +/** + * @brief **btf__new_split()** create a new instance of a BTF object from the + * provided raw data bytes. It takes another BTF instance, **base_btf**, which + * serves as a base BTF, which is extended by types in a newly created BTF + * instance + * @param data raw bytes + * @param size length of raw bytes + * @param base_btf the base BTF object + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and + * creates non-split BTF. + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ +LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf); + +/** + * @brief **btf__new_empty()** creates an empty BTF object. Use + * `btf__add_*()` to populate such BTF object. + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ +LIBBPF_API struct btf *btf__new_empty(void); + +/** + * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an + * ELF BTF section except with a base BTF on top of which split BTF should be + * based + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to + * `btf__new_empty()` and creates non-split BTF. + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ +LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); + +LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); +LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf); +LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext); +LIBBPF_API struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf); +LIBBPF_API struct btf *btf__parse_raw(const char *path); +LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf); + +LIBBPF_API struct btf *btf__load_vmlinux_btf(void); +LIBBPF_API struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_btf); + +LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id); +LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf); + +LIBBPF_API int btf__load_into_kernel(struct btf *btf); +LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, + const char *type_name); +LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, + const char *type_name, __u32 kind); +LIBBPF_API __u32 btf__type_cnt(const struct btf *btf); +LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf); +LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, + __u32 id); +LIBBPF_API size_t btf__pointer_size(const struct btf *btf); +LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz); +LIBBPF_API enum btf_endianness btf__endianness(const struct btf *btf); +LIBBPF_API int btf__set_endianness(struct btf *btf, enum btf_endianness endian); +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 void btf__set_fd(struct btf *btf, int fd); +LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size); +LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); +LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); + +LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); +LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); +LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); + +LIBBPF_API int btf__find_str(struct btf *btf, const char *s); +LIBBPF_API int btf__add_str(struct btf *btf, const char *s); +LIBBPF_API int btf__add_type(struct btf *btf, const struct btf *src_btf, + const struct btf_type *src_type); +/** + * @brief **btf__add_btf()** appends all the BTF types from *src_btf* into *btf* + * @param btf BTF object which all the BTF types and strings are added to + * @param src_btf BTF object which all BTF types and referenced strings are copied from + * @return BTF type ID of the first appended BTF type, or negative error code + * + * **btf__add_btf()** can be used to simply and efficiently append the entire + * contents of one BTF object to another one. All the BTF type data is copied + * over, all referenced type IDs are adjusted by adding a necessary ID offset. + * Only strings referenced from BTF types are copied over and deduplicated, so + * if there were some unused strings in *src_btf*, those won't be copied over, + * which is consistent with the general string deduplication semantics of BTF + * writing APIs. + * + * If any error is encountered during this process, the contents of *btf* is + * left intact, which means that **btf__add_btf()** follows the transactional + * semantics and the operation as a whole is all-or-nothing. + * + * *src_btf* has to be non-split BTF, as of now copying types from split BTF + * is not supported and will result in -ENOTSUP error code returned. + */ +LIBBPF_API int btf__add_btf(struct btf *btf, const struct btf *src_btf); + +LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding); +LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz); +LIBBPF_API int btf__add_ptr(struct btf *btf, int ref_type_id); +LIBBPF_API int btf__add_array(struct btf *btf, + int index_type_id, int elem_type_id, __u32 nr_elems); +/* struct/union construction APIs */ +LIBBPF_API int btf__add_struct(struct btf *btf, const char *name, __u32 sz); +LIBBPF_API int btf__add_union(struct btf *btf, const char *name, __u32 sz); +LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_id, + __u32 bit_offset, __u32 bit_size); + +/* enum construction APIs */ +LIBBPF_API int btf__add_enum(struct btf *btf, const char *name, __u32 bytes_sz); +LIBBPF_API int btf__add_enum_value(struct btf *btf, const char *name, __s64 value); +LIBBPF_API int btf__add_enum64(struct btf *btf, const char *name, __u32 bytes_sz, bool is_signed); +LIBBPF_API int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value); + +enum btf_fwd_kind { + BTF_FWD_STRUCT = 0, + BTF_FWD_UNION = 1, + BTF_FWD_ENUM = 2, +}; + +LIBBPF_API int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind); +LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id); +LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id); +LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id); +LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id); +LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id); + +/* func and func_proto construction APIs */ +LIBBPF_API int btf__add_func(struct btf *btf, const char *name, + enum btf_func_linkage linkage, int proto_type_id); +LIBBPF_API int btf__add_func_proto(struct btf *btf, int ret_type_id); +LIBBPF_API int btf__add_func_param(struct btf *btf, const char *name, int type_id); + +/* var & datasec construction APIs */ +LIBBPF_API int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id); +LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz); +LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, + __u32 offset, __u32 byte_sz); + +/* tag construction API */ +LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx); + +struct btf_dedup_opts { + size_t sz; + /* optional .BTF.ext info to dedup along the main BTF info */ + struct btf_ext *btf_ext; + /* force hash collisions (used for testing) */ + bool force_collisions; + size_t :0; +}; +#define btf_dedup_opts__last_field force_collisions + +LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts); + +struct btf_dump; + +struct btf_dump_opts { + size_t sz; +}; +#define btf_dump_opts__last_field sz + +typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args); + +LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf, + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts); + +LIBBPF_API void btf_dump__free(struct btf_dump *d); + +LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); + +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; + /* strip all the const/volatile/restrict mods */ + bool strip_mods; + size_t :0; +}; +#define btf_dump_emit_type_decl_opts__last_field strip_mods + +LIBBPF_API int +btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts); + + +struct btf_dump_type_data_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + const char *indent_str; + int indent_level; + /* below match "show" flags for bpf_show_snprintf() */ + bool compact; /* no newlines/indentation */ + bool skip_names; /* skip member/type names */ + bool emit_zeroes; /* show 0-valued fields */ + size_t :0; +}; +#define btf_dump_type_data_opts__last_field emit_zeroes + +LIBBPF_API int +btf_dump__dump_type_data(struct btf_dump *d, __u32 id, + const void *data, size_t data_sz, + const struct btf_dump_type_data_opts *opts); + +/* + * A set of helpers for easier BTF types handling. + * + * The inline functions below rely on constants from the kernel headers which + * may not be available for applications including this header file. To avoid + * compilation errors, we define all the constants here that were added after + * the initial introduction of the BTF_KIND* constants. + */ +#ifndef BTF_KIND_FUNC +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#endif +#ifndef BTF_KIND_VAR +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#endif +#ifndef BTF_KIND_FLOAT +#define BTF_KIND_FLOAT 16 /* Floating point */ +#endif +/* The kernel header switched to enums, so the following were never #defined */ +#define BTF_KIND_DECL_TAG 17 /* Decl Tag */ +#define BTF_KIND_TYPE_TAG 18 /* Type Tag */ +#define BTF_KIND_ENUM64 19 /* Enum for up-to 64bit values */ + +static inline __u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +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_void(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_UNKN; +} + +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_enum64(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM64; +} + +static inline bool btf_is_fwd(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FWD; +} + +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 || + kind == BTF_KIND_TYPE_TAG; +} + +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 bool btf_is_float(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FLOAT; +} + +static inline bool btf_is_decl_tag(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_DECL_TAG; +} + +static inline bool btf_is_type_tag(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TYPE_TAG; +} + +static inline bool btf_is_any_enum(const struct btf_type *t) +{ + return btf_is_enum(t) || btf_is_enum64(t); +} + +static inline bool btf_kind_core_compat(const struct btf_type *t1, + const struct btf_type *t2) +{ + return btf_kind(t1) == btf_kind(t2) || + (btf_is_any_enum(t1) && btf_is_any_enum(t2)); +} + +static inline __u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(__u32 *)(t + 1)); +} + +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); +} + +struct btf_enum64; + +static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) +{ + return (struct btf_enum64 *)(t + 1); +} + +static inline __u64 btf_enum64_value(const struct btf_enum64 *e) +{ + /* struct btf_enum64 is introduced in Linux 6.0, which is very + * bleeding-edge. Here we are avoiding relying on struct btf_enum64 + * definition coming from kernel UAPI headers to support wider range + * of system-wide kernel headers. + * + * Given this header can be also included from C++ applications, that + * further restricts C tricks we can use (like using compatible + * anonymous struct). So just treat struct btf_enum64 as + * a three-element array of u32 and access second (lo32) and third + * (hi32) elements directly. + * + * For reference, here is a struct btf_enum64 definition: + * + * const struct btf_enum64 { + * __u32 name_off; + * __u32 val_lo32; + * __u32 val_hi32; + * }; + */ + const __u32 *e64 = (const __u32 *)e; + + return ((__u64)e64[2] << 32) | e64[1]; +} + +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +/* 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); +} + +struct btf_decl_tag; +static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) +{ + return (struct btf_decl_tag *)(t + 1); +} + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_BTF_H */ diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c new file mode 100644 index 000000000..713264899 --- /dev/null +++ b/tools/lib/bpf/btf_dump.c @@ -0,0 +1,2505 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C type converter. + * + * Copyright (c) 2019 Facebook + */ + +#include <stdbool.h> +#include <stddef.h> +#include <stdlib.h> +#include <string.h> +#include <ctype.h> +#include <endian.h> +#include <errno.h> +#include <linux/err.h> +#include <linux/btf.h> +#include <linux/kernel.h> +#include "btf.h" +#include "hashmap.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t"; +static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1; + +static const char *pfx(int lvl) +{ + return lvl >= PREFIX_CNT ? PREFIXES : &PREFIXES[PREFIX_CNT - lvl]; +} + +enum btf_dump_type_order_state { + NOT_ORDERED, + ORDERING, + ORDERED, +}; + +enum btf_dump_type_emit_state { + NOT_EMITTED, + EMITTING, + EMITTED, +}; + +/* per-type auxiliary state */ +struct btf_dump_type_aux_state { + /* topological sorting state */ + enum btf_dump_type_order_state order_state: 2; + /* emitting state used to determine the need for forward declaration */ + enum btf_dump_type_emit_state emit_state: 2; + /* whether forward declaration was already emitted */ + __u8 fwd_emitted: 1; + /* whether unique non-duplicate name was already assigned */ + __u8 name_resolved: 1; + /* whether type is referenced from any other type */ + __u8 referenced: 1; +}; + +/* indent string length; one indent string is added for each indent level */ +#define BTF_DATA_INDENT_STR_LEN 32 + +/* + * Common internal data for BTF type data dump operations. + */ +struct btf_dump_data { + const void *data_end; /* end of valid data to show */ + bool compact; + bool skip_names; + bool emit_zeroes; + __u8 indent_lvl; /* base indent level */ + char indent_str[BTF_DATA_INDENT_STR_LEN]; + /* below are used during iteration */ + int depth; + bool is_array_member; + bool is_array_terminated; + bool is_array_char; +}; + +struct btf_dump { + const struct btf *btf; + btf_dump_printf_fn_t printf_fn; + void *cb_ctx; + int ptr_sz; + bool strip_mods; + bool skip_anon_defs; + int last_id; + + /* per-type auxiliary state */ + struct btf_dump_type_aux_state *type_states; + size_t type_states_cap; + /* per-type optional cached unique name, must be freed, if present */ + const char **cached_names; + size_t cached_names_cap; + + /* topo-sorted list of dependent type definitions */ + __u32 *emit_queue; + int emit_queue_cap; + int emit_queue_cnt; + + /* + * stack of type declarations (e.g., chain of modifiers, arrays, + * funcs, etc) + */ + __u32 *decl_stack; + int decl_stack_cap; + int decl_stack_cnt; + + /* maps struct/union/enum name to a number of name occurrences */ + struct hashmap *type_names; + /* + * maps typedef identifiers and enum value names to a number of such + * name occurrences + */ + struct hashmap *ident_names; + /* + * data for typed display; allocated if needed. + */ + struct btf_dump_data *typed_dump; +}; + +static size_t str_hash_fn(const void *key, void *ctx) +{ + return str_hash(key); +} + +static bool str_equal_fn(const void *a, const void *b, void *ctx) +{ + return strcmp(a, b) == 0; +} + +static const char *btf_name_of(const struct btf_dump *d, __u32 name_off) +{ + return btf__name_by_offset(d->btf, name_off); +} + +static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + d->printf_fn(d->cb_ctx, fmt, args); + va_end(args); +} + +static int btf_dump_mark_referenced(struct btf_dump *d); +static int btf_dump_resize(struct btf_dump *d); + +struct btf_dump *btf_dump__new(const struct btf *btf, + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts) +{ + struct btf_dump *d; + int err; + + if (!OPTS_VALID(opts, btf_dump_opts)) + return libbpf_err_ptr(-EINVAL); + + if (!printf_fn) + return libbpf_err_ptr(-EINVAL); + + d = calloc(1, sizeof(struct btf_dump)); + if (!d) + return libbpf_err_ptr(-ENOMEM); + + d->btf = btf; + d->printf_fn = printf_fn; + d->cb_ctx = ctx; + d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *); + + d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); + if (IS_ERR(d->type_names)) { + err = PTR_ERR(d->type_names); + d->type_names = NULL; + 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; + goto err; + } + + err = btf_dump_resize(d); + if (err) + goto err; + + return d; +err: + btf_dump__free(d); + return libbpf_err_ptr(err); +} + +static int btf_dump_resize(struct btf_dump *d) +{ + int err, last_id = btf__type_cnt(d->btf) - 1; + + if (last_id <= d->last_id) + return 0; + + if (libbpf_ensure_mem((void **)&d->type_states, &d->type_states_cap, + sizeof(*d->type_states), last_id + 1)) + return -ENOMEM; + if (libbpf_ensure_mem((void **)&d->cached_names, &d->cached_names_cap, + sizeof(*d->cached_names), last_id + 1)) + return -ENOMEM; + + if (d->last_id == 0) { + /* VOID is special */ + d->type_states[0].order_state = ORDERED; + d->type_states[0].emit_state = EMITTED; + } + + /* eagerly determine referenced types for anon enums */ + err = btf_dump_mark_referenced(d); + if (err) + return err; + + d->last_id = last_id; + return 0; +} + +static void btf_dump_free_names(struct hashmap *map) +{ + size_t bkt; + struct hashmap_entry *cur; + + hashmap__for_each_entry(map, cur, bkt) + free((void *)cur->key); + + hashmap__free(map); +} + +void btf_dump__free(struct btf_dump *d) +{ + int i; + + if (IS_ERR_OR_NULL(d)) + return; + + free(d->type_states); + if (d->cached_names) { + /* any set cached name is owned by us and should be freed */ + for (i = 0; i <= d->last_id; i++) { + if (d->cached_names[i]) + free((void *)d->cached_names[i]); + } + } + free(d->cached_names); + free(d->emit_queue); + free(d->decl_stack); + btf_dump_free_names(d->type_names); + btf_dump_free_names(d->ident_names); + + free(d); +} + +static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr); +static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id); + +/* + * Dump BTF type in a compilable C syntax, including all the necessary + * dependent types, necessary for compilation. If some of the dependent types + * were already emitted as part of previous btf_dump__dump_type() invocation + * for another type, they won't be emitted again. This API allows callers to + * filter out BTF types according to user-defined criterias and emitted only + * minimal subset of types, necessary to compile everything. Full struct/union + * definitions will still be emitted, even if the only usage is through + * pointer and could be satisfied with just a forward declaration. + * + * Dumping is done in two high-level passes: + * 1. Topologically sort type definitions to satisfy C rules of compilation. + * 2. Emit type definitions in C syntax. + * + * Returns 0 on success; <0, otherwise. + */ +int btf_dump__dump_type(struct btf_dump *d, __u32 id) +{ + int err, i; + + if (id >= btf__type_cnt(d->btf)) + return libbpf_err(-EINVAL); + + err = btf_dump_resize(d); + if (err) + return libbpf_err(err); + + d->emit_queue_cnt = 0; + err = btf_dump_order_type(d, id, false); + if (err < 0) + return libbpf_err(err); + + for (i = 0; i < d->emit_queue_cnt; i++) + btf_dump_emit_type(d, d->emit_queue[i], 0 /*top-level*/); + + return 0; +} + +/* + * Mark all types that are referenced from any other type. This is used to + * determine top-level anonymous enums that need to be emitted as an + * independent type declarations. + * Anonymous enums come in two flavors: either embedded in a struct's field + * definition, in which case they have to be declared inline as part of field + * type declaration; or as a top-level anonymous enum, typically used for + * declaring global constants. It's impossible to distinguish between two + * without knowning whether given enum type was referenced from other type: + * top-level anonymous enum won't be referenced by anything, while embedded + * one will. + */ +static int btf_dump_mark_referenced(struct btf_dump *d) +{ + int i, j, n = btf__type_cnt(d->btf); + const struct btf_type *t; + __u16 vlen; + + for (i = d->last_id + 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_ENUM64: + case BTF_KIND_FWD: + case BTF_KIND_FLOAT: + 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: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + d->type_states[t->type].referenced = 1; + break; + + case BTF_KIND_ARRAY: { + const struct btf_array *a = btf_array(t); + + d->type_states[a->index_type].referenced = 1; + d->type_states[a->type].referenced = 1; + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + + for (j = 0; j < vlen; j++, m++) + d->type_states[m->type].referenced = 1; + break; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + + for (j = 0; j < vlen; j++, p++) + d->type_states[p->type].referenced = 1; + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *v = btf_var_secinfos(t); + + for (j = 0; j < vlen; j++, v++) + d->type_states[v->type].referenced = 1; + break; + } + default: + return -EINVAL; + } + } + return 0; +} + +static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id) +{ + __u32 *new_queue; + size_t new_cap; + + if (d->emit_queue_cnt >= d->emit_queue_cap) { + new_cap = max(16, d->emit_queue_cap * 3 / 2); + new_queue = libbpf_reallocarray(d->emit_queue, new_cap, sizeof(new_queue[0])); + if (!new_queue) + return -ENOMEM; + d->emit_queue = new_queue; + d->emit_queue_cap = new_cap; + } + + d->emit_queue[d->emit_queue_cnt++] = id; + return 0; +} + +/* + * Determine order of emitting dependent types and specified type to satisfy + * C compilation rules. This is done through topological sorting with an + * additional complication which comes from C rules. The main idea for C is + * that if some type is "embedded" into a struct/union, it's size needs to be + * known at the time of definition of containing type. E.g., for: + * + * struct A {}; + * struct B { struct A x; } + * + * struct A *HAS* to be defined before struct B, because it's "embedded", + * i.e., it is part of struct B layout. But in the following case: + * + * struct A; + * struct B { struct A *x; } + * struct A {}; + * + * it's enough to just have a forward declaration of struct A at the time of + * struct B definition, as struct B has a pointer to struct A, so the size of + * field x is known without knowing struct A size: it's sizeof(void *). + * + * Unfortunately, there are some trickier cases we need to handle, e.g.: + * + * struct A {}; // if this was forward-declaration: compilation error + * struct B { + * struct { // anonymous struct + * struct A y; + * } *x; + * }; + * + * In this case, struct B's field x is a pointer, so it's size is known + * regardless of the size of (anonymous) struct it points to. But because this + * struct is anonymous and thus defined inline inside struct B, *and* it + * embeds struct A, compiler requires full definition of struct A to be known + * before struct B can be defined. This creates a transitive dependency + * between struct A and struct B. If struct A was forward-declared before + * struct B definition and fully defined after struct B definition, that would + * trigger compilation error. + * + * All this means that while we are doing topological sorting on BTF type + * graph, we need to determine relationships between different types (graph + * nodes): + * - weak link (relationship) between X and Y, if Y *CAN* be + * forward-declared at the point of X definition; + * - strong link, if Y *HAS* to be fully-defined before X can be defined. + * + * The rule is as follows. Given a chain of BTF types from X to Y, if there is + * BTF_KIND_PTR type in the chain and at least one non-anonymous type + * Z (excluding X, including Y), then link is weak. Otherwise, it's strong. + * Weak/strong relationship is determined recursively during DFS traversal and + * is returned as a result from btf_dump_order_type(). + * + * btf_dump_order_type() is trying to avoid unnecessary forward declarations, + * but it is not guaranteeing that no extraneous forward declarations will be + * emitted. + * + * To avoid extra work, algorithm marks some of BTF types as ORDERED, when + * it's done with them, but not for all (e.g., VOLATILE, CONST, RESTRICT, + * ARRAY, FUNC_PROTO), as weak/strong semantics for those depends on the + * entire graph path, so depending where from one came to that BTF type, it + * might cause weak or strong ordering. For types like STRUCT/UNION/INT/ENUM, + * once they are processed, there is no need to do it again, so they are + * marked as ORDERED. We can mark PTR as ORDERED as well, as it semi-forces + * weak link, unless subsequent referenced STRUCT/UNION/ENUM is anonymous. But + * in any case, once those are processed, no need to do it again, as the + * result won't change. + * + * Returns: + * - 1, if type is part of strong link (so there is strong topological + * ordering requirements); + * - 0, if type is part of weak link (so can be satisfied through forward + * declaration); + * - <0, on error (e.g., unsatisfiable type loop detected). + */ +static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) +{ + /* + * Order state is used to detect strong link cycles, but only for BTF + * kinds that are or could be an independent definition (i.e., + * stand-alone fwd decl, enum, typedef, struct, union). Ptrs, arrays, + * func_protos, modifiers are just means to get to these definitions. + * Int/void don't need definitions, they are assumed to be always + * properly defined. We also ignore datasec, var, and funcs for now. + * So for all non-defining kinds, we never even set ordering state, + * for defining kinds we set ORDERING and subsequently ORDERED if it + * forms a strong link. + */ + struct btf_dump_type_aux_state *tstate = &d->type_states[id]; + const struct btf_type *t; + __u16 vlen; + int err, i; + + /* return true, letting typedefs know that it's ok to be emitted */ + if (tstate->order_state == ORDERED) + return 1; + + t = btf__type_by_id(d->btf, id); + + if (tstate->order_state == ORDERING) { + /* type loop, but resolvable through fwd declaration */ + if (btf_is_composite(t) && through_ptr && t->name_off != 0) + return 0; + pr_warn("unsatisfiable type cycle, id:[%u]\n", id); + return -ELOOP; + } + + switch (btf_kind(t)) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + tstate->order_state = ORDERED; + return 0; + + case BTF_KIND_PTR: + err = btf_dump_order_type(d, t->type, true); + tstate->order_state = ORDERED; + return err; + + case BTF_KIND_ARRAY: + return btf_dump_order_type(d, btf_array(t)->type, false); + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + /* + * struct/union is part of strong link, only if it's embedded + * (so no ptr in a path) or it's anonymous (so has to be + * defined inline, even if declared through ptr) + */ + if (through_ptr && t->name_off != 0) + return 0; + + tstate->order_state = ORDERING; + + vlen = btf_vlen(t); + for (i = 0; i < vlen; i++, m++) { + err = btf_dump_order_type(d, m->type, false); + if (err < 0) + return err; + } + + if (t->name_off != 0) { + err = btf_dump_add_emit_queue_id(d, id); + if (err < 0) + return err; + } + + tstate->order_state = ORDERED; + return 1; + } + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_FWD: + /* + * non-anonymous or non-referenced enums are top-level + * declarations and should be emitted. Same logic can be + * applied to FWDs, it won't hurt anyways. + */ + if (t->name_off != 0 || !tstate->referenced) { + err = btf_dump_add_emit_queue_id(d, id); + if (err) + return err; + } + tstate->order_state = ORDERED; + return 1; + + case BTF_KIND_TYPEDEF: { + int is_strong; + + is_strong = btf_dump_order_type(d, t->type, through_ptr); + if (is_strong < 0) + return is_strong; + + /* typedef is similar to struct/union w.r.t. fwd-decls */ + if (through_ptr && !is_strong) + return 0; + + /* typedef is always a named definition */ + err = btf_dump_add_emit_queue_id(d, id); + if (err) + return err; + + d->type_states[id].order_state = ORDERED; + return 1; + } + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: + return btf_dump_order_type(d, t->type, through_ptr); + + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + bool is_strong; + + err = btf_dump_order_type(d, t->type, through_ptr); + if (err < 0) + return err; + is_strong = err > 0; + + vlen = btf_vlen(t); + for (i = 0; i < vlen; i++, p++) { + err = btf_dump_order_type(d, p->type, through_ptr); + if (err < 0) + return err; + if (err > 0) + is_strong = true; + } + return is_strong; + } + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: + case BTF_KIND_DECL_TAG: + d->type_states[id].order_state = ORDERED; + return 0; + + default: + return -EINVAL; + } +} + +static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id, + const struct btf_type *t); + +static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t); +static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t); +static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, + const struct btf_type *t); + +static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +/* a local view into a shared stack */ +struct id_stack { + const __u32 *ids; + int cnt; +}; + +static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, + const char *fname, int lvl); +static void btf_dump_emit_type_chain(struct btf_dump *d, + struct id_stack *decl_stack, + const char *fname, int lvl); + +static const char *btf_dump_type_name(struct btf_dump *d, __u32 id); +static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id); +static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map, + const char *orig_name); + +static bool btf_dump_is_blacklisted(struct btf_dump *d, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(d->btf, id); + + /* __builtin_va_list is a compiler built-in, which causes compilation + * errors, when compiling w/ different compiler, then used to compile + * original code (e.g., GCC to compile kernel, Clang to use generated + * C header from BTF). As it is built-in, it should be already defined + * properly internally in compiler. + */ + if (t->name_off == 0) + return false; + return strcmp(btf_name_of(d, t->name_off), "__builtin_va_list") == 0; +} + +/* + * Emit C-syntax definitions of types from chains of BTF types. + * + * High-level handling of determining necessary forward declarations are handled + * by btf_dump_emit_type() itself, but all nitty-gritty details of emitting type + * declarations/definitions in C syntax are handled by a combo of + * btf_dump_emit_type_decl()/btf_dump_emit_type_chain() w/ delegation to + * corresponding btf_dump_emit_*_{def,fwd}() functions. + * + * We also keep track of "containing struct/union type ID" to determine when + * we reference it from inside and thus can avoid emitting unnecessary forward + * declaration. + * + * This algorithm is designed in such a way, that even if some error occurs + * (either technical, e.g., out of memory, or logical, i.e., malformed BTF + * that doesn't comply to C rules completely), algorithm will try to proceed + * and produce as much meaningful output as possible. + */ +static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) +{ + struct btf_dump_type_aux_state *tstate = &d->type_states[id]; + bool top_level_def = cont_id == 0; + const struct btf_type *t; + __u16 kind; + + if (tstate->emit_state == EMITTED) + return; + + t = btf__type_by_id(d->btf, id); + kind = btf_kind(t); + + if (tstate->emit_state == EMITTING) { + if (tstate->fwd_emitted) + return; + + switch (kind) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* + * if we are referencing a struct/union that we are + * part of - then no need for fwd declaration + */ + if (id == cont_id) + return; + if (t->name_off == 0) { + pr_warn("anonymous struct/union loop, id:[%u]\n", + id); + return; + } + btf_dump_emit_struct_fwd(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->fwd_emitted = 1; + break; + case BTF_KIND_TYPEDEF: + /* + * for typedef fwd_emitted means typedef definition + * was emitted, but it can be used only for "weak" + * references through pointer only, not for embedding + */ + if (!btf_dump_is_blacklisted(d, id)) { + btf_dump_emit_typedef_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + } + tstate->fwd_emitted = 1; + break; + default: + break; + } + + return; + } + + switch (kind) { + case BTF_KIND_INT: + /* Emit type alias definitions if necessary */ + btf_dump_emit_missing_aliases(d, id, t); + + tstate->emit_state = EMITTED; + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + if (top_level_def) { + btf_dump_emit_enum_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + } + tstate->emit_state = EMITTED; + break; + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: + btf_dump_emit_type(d, t->type, cont_id); + break; + case BTF_KIND_ARRAY: + btf_dump_emit_type(d, btf_array(t)->type, cont_id); + break; + case BTF_KIND_FWD: + btf_dump_emit_fwd_def(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->emit_state = EMITTED; + break; + case BTF_KIND_TYPEDEF: + tstate->emit_state = EMITTING; + btf_dump_emit_type(d, t->type, id); + /* + * typedef can server as both definition and forward + * declaration; at this stage someone depends on + * typedef as a forward declaration (refers to it + * through pointer), so unless we already did it, + * emit typedef as a forward declaration + */ + if (!tstate->fwd_emitted && !btf_dump_is_blacklisted(d, id)) { + btf_dump_emit_typedef_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + } + tstate->emit_state = EMITTED; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + tstate->emit_state = EMITTING; + /* if it's a top-level struct/union definition or struct/union + * is anonymous, then in C we'll be emitting all fields and + * their types (as opposed to just `struct X`), so we need to + * make sure that all types, referenced from struct/union + * members have necessary forward-declarations, where + * applicable + */ + if (top_level_def || t->name_off == 0) { + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + int i, new_cont_id; + + new_cont_id = t->name_off == 0 ? cont_id : id; + for (i = 0; i < vlen; i++, m++) + btf_dump_emit_type(d, m->type, new_cont_id); + } else if (!tstate->fwd_emitted && id != cont_id) { + btf_dump_emit_struct_fwd(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->fwd_emitted = 1; + } + + if (top_level_def) { + btf_dump_emit_struct_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + tstate->emit_state = EMITTED; + } else { + tstate->emit_state = NOT_EMITTED; + } + break; + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + __u16 n = btf_vlen(t); + int i; + + btf_dump_emit_type(d, t->type, cont_id); + for (i = 0; i < n; i++, p++) + btf_dump_emit_type(d, p->type, cont_id); + + break; + } + default: + break; + } +} + +static bool btf_is_struct_packed(const struct btf *btf, __u32 id, + const struct btf_type *t) +{ + const struct btf_member *m; + int max_align = 1, align, i, bit_sz; + __u16 vlen; + + m = btf_members(t); + vlen = btf_vlen(t); + /* all non-bitfield fields have to be naturally aligned */ + for (i = 0; i < vlen; i++, m++) { + align = btf__align_of(btf, m->type); + bit_sz = btf_member_bitfield_size(t, i); + if (align && bit_sz == 0 && m->offset % (8 * align) != 0) + return true; + max_align = max(align, max_align); + } + /* size of a non-packed struct has to be a multiple of its alignment */ + if (t->size % max_align != 0) + return true; + /* + * if original struct was marked as packed, but its layout is + * naturally aligned, we'll detect that it's not packed + */ + return false; +} + +static void btf_dump_emit_bit_padding(const struct btf_dump *d, + int cur_off, int next_off, int next_align, + bool in_bitfield, int lvl) +{ + const struct { + const char *name; + int bits; + } pads[] = { + {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8} + }; + int new_off, pad_bits, bits, i; + const char *pad_type; + + if (cur_off >= next_off) + return; /* no gap */ + + /* For filling out padding we want to take advantage of + * natural alignment rules to minimize unnecessary explicit + * padding. First, we find the largest type (among long, int, + * short, or char) that can be used to force naturally aligned + * boundary. Once determined, we'll use such type to fill in + * the remaining padding gap. In some cases we can rely on + * compiler filling some gaps, but sometimes we need to force + * alignment to close natural alignment with markers like + * `long: 0` (this is always the case for bitfields). Note + * that even if struct itself has, let's say 4-byte alignment + * (i.e., it only uses up to int-aligned types), using `long: + * X;` explicit padding doesn't actually change struct's + * overall alignment requirements, but compiler does take into + * account that type's (long, in this example) natural + * alignment requirements when adding implicit padding. We use + * this fact heavily and don't worry about ruining correct + * struct alignment requirement. + */ + for (i = 0; i < ARRAY_SIZE(pads); i++) { + pad_bits = pads[i].bits; + pad_type = pads[i].name; + + new_off = roundup(cur_off, pad_bits); + if (new_off <= next_off) + break; + } + + if (new_off > cur_off && new_off <= next_off) { + /* We need explicit `<type>: 0` aligning mark if next + * field is right on alignment offset and its + * alignment requirement is less strict than <type>'s + * alignment (so compiler won't naturally align to the + * offset we expect), or if subsequent `<type>: X`, + * will actually completely fit in the remaining hole, + * making compiler basically ignore `<type>: X` + * completely. + */ + if (in_bitfield || + (new_off == next_off && roundup(cur_off, next_align * 8) != new_off) || + (new_off != next_off && next_off - new_off <= new_off - cur_off)) + /* but for bitfields we'll emit explicit bit count */ + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, + in_bitfield ? new_off - cur_off : 0); + cur_off = new_off; + } + + /* Now we know we start at naturally aligned offset for a chosen + * padding type (long, int, short, or char), and so the rest is just + * a straightforward filling of remaining padding gap with full + * `<type>: sizeof(<type>);` markers, except for the last one, which + * might need smaller than sizeof(<type>) padding. + */ + while (cur_off != next_off) { + bits = min(next_off - cur_off, pad_bits); + if (bits == pad_bits) { + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); + cur_off += bits; + continue; + } + /* For the remainder padding that doesn't cover entire + * pad_type bit length, we pick the smallest necessary type. + * This is pure aesthetics, we could have just used `long`, + * but having smallest necessary one communicates better the + * scale of the padding gap. + */ + for (i = ARRAY_SIZE(pads) - 1; i >= 0; i--) { + pad_type = pads[i].name; + pad_bits = pads[i].bits; + if (pad_bits < bits) + continue; + + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, bits); + cur_off += bits; + break; + } + } +} + +static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + btf_dump_printf(d, "%s%s%s", + btf_is_struct(t) ? "struct" : "union", + t->name_off ? " " : "", + btf_dump_type_name(d, id)); +} + +static void btf_dump_emit_struct_def(struct btf_dump *d, + __u32 id, + const struct btf_type *t, + int lvl) +{ + const struct btf_member *m = btf_members(t); + bool is_struct = btf_is_struct(t); + bool packed, prev_bitfield = false; + int align, i, off = 0; + __u16 vlen = btf_vlen(t); + + align = btf__align_of(d->btf, id); + packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; + + btf_dump_printf(d, "%s%s%s {", + is_struct ? "struct" : "union", + t->name_off ? " " : "", + btf_dump_type_name(d, id)); + + for (i = 0; i < vlen; i++, m++) { + const char *fname; + int m_off, m_sz, m_align; + bool in_bitfield; + + fname = btf_name_of(d, m->name_off); + m_sz = btf_member_bitfield_size(t, i); + m_off = btf_member_bit_offset(t, i); + m_align = packed ? 1 : btf__align_of(d->btf, m->type); + + in_bitfield = prev_bitfield && m_sz != 0; + + btf_dump_emit_bit_padding(d, off, m_off, m_align, in_bitfield, lvl + 1); + btf_dump_printf(d, "\n%s", pfx(lvl + 1)); + btf_dump_emit_type_decl(d, m->type, fname, lvl + 1); + + if (m_sz) { + btf_dump_printf(d, ": %d", m_sz); + off = m_off + m_sz; + prev_bitfield = true; + } else { + m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type)); + off = m_off + m_sz * 8; + prev_bitfield = false; + } + + btf_dump_printf(d, ";"); + } + + /* pad at the end, if necessary */ + if (is_struct) + btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1); + + /* + * Keep `struct empty {}` on a single line, + * only print newline when there are regular or padding fields. + */ + if (vlen || t->size) { + btf_dump_printf(d, "\n"); + btf_dump_printf(d, "%s}", pfx(lvl)); + } else { + btf_dump_printf(d, "}"); + } + if (packed) + btf_dump_printf(d, " __attribute__((packed))"); +} + +static const char *missing_base_types[][2] = { + /* + * GCC emits typedefs to its internal __PolyX_t types when compiling Arm + * SIMD intrinsics. Alias them to standard base types. + */ + { "__Poly8_t", "unsigned char" }, + { "__Poly16_t", "unsigned short" }, + { "__Poly64_t", "unsigned long long" }, + { "__Poly128_t", "unsigned __int128" }, +}; + +static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + const char *name = btf_dump_type_name(d, id); + int i; + + for (i = 0; i < ARRAY_SIZE(missing_base_types); i++) { + if (strcmp(name, missing_base_types[i][0]) == 0) { + btf_dump_printf(d, "typedef %s %s;\n\n", + missing_base_types[i][1], name); + break; + } + } +} + +static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + btf_dump_printf(d, "enum %s", btf_dump_type_name(d, id)); +} + +static void btf_dump_emit_enum32_val(struct btf_dump *d, + const struct btf_type *t, + int lvl, __u16 vlen) +{ + const struct btf_enum *v = btf_enum(t); + bool is_signed = btf_kflag(t); + const char *fmt_str; + const char *name; + size_t dup_cnt; + int i; + + for (i = 0; i < vlen; i++, v++) { + name = btf_name_of(d, v->name_off); + /* enumerators share namespace with typedef idents */ + dup_cnt = btf_dump_name_dups(d, d->ident_names, name); + if (dup_cnt > 1) { + fmt_str = is_signed ? "\n%s%s___%zd = %d," : "\n%s%s___%zd = %u,"; + btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, dup_cnt, v->val); + } else { + fmt_str = is_signed ? "\n%s%s = %d," : "\n%s%s = %u,"; + btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, v->val); + } + } +} + +static void btf_dump_emit_enum64_val(struct btf_dump *d, + const struct btf_type *t, + int lvl, __u16 vlen) +{ + const struct btf_enum64 *v = btf_enum64(t); + bool is_signed = btf_kflag(t); + const char *fmt_str; + const char *name; + size_t dup_cnt; + __u64 val; + int i; + + for (i = 0; i < vlen; i++, v++) { + name = btf_name_of(d, v->name_off); + dup_cnt = btf_dump_name_dups(d, d->ident_names, name); + val = btf_enum64_value(v); + if (dup_cnt > 1) { + fmt_str = is_signed ? "\n%s%s___%zd = %lldLL," + : "\n%s%s___%zd = %lluULL,"; + btf_dump_printf(d, fmt_str, + pfx(lvl + 1), name, dup_cnt, + (unsigned long long)val); + } else { + fmt_str = is_signed ? "\n%s%s = %lldLL," + : "\n%s%s = %lluULL,"; + btf_dump_printf(d, fmt_str, + pfx(lvl + 1), name, + (unsigned long long)val); + } + } +} +static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, + int lvl) +{ + __u16 vlen = btf_vlen(t); + + btf_dump_printf(d, "enum%s%s", + t->name_off ? " " : "", + btf_dump_type_name(d, id)); + + if (!vlen) + return; + + btf_dump_printf(d, " {"); + if (btf_is_enum(t)) + btf_dump_emit_enum32_val(d, t, lvl, vlen); + else + btf_dump_emit_enum64_val(d, t, lvl, vlen); + btf_dump_printf(d, "\n%s}", pfx(lvl)); +} + +static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + const char *name = btf_dump_type_name(d, id); + + if (btf_kflag(t)) + btf_dump_printf(d, "union %s", name); + else + btf_dump_printf(d, "struct %s", name); +} + +static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl) +{ + const char *name = btf_dump_ident_name(d, id); + + /* + * Old GCC versions are emitting invalid typedef for __gnuc_va_list + * pointing to VOID. This generates warnings from btf_dump() and + * results in uncompilable header file, so we are fixing it up here + * with valid typedef into __builtin_va_list. + */ + if (t->type == 0 && strcmp(name, "__gnuc_va_list") == 0) { + btf_dump_printf(d, "typedef __builtin_va_list __gnuc_va_list"); + return; + } + + btf_dump_printf(d, "typedef "); + btf_dump_emit_type_decl(d, t->type, name, lvl); +} + +static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id) +{ + __u32 *new_stack; + size_t new_cap; + + if (d->decl_stack_cnt >= d->decl_stack_cap) { + new_cap = max(16, d->decl_stack_cap * 3 / 2); + new_stack = libbpf_reallocarray(d->decl_stack, new_cap, sizeof(new_stack[0])); + if (!new_stack) + return -ENOMEM; + d->decl_stack = new_stack; + d->decl_stack_cap = new_cap; + } + + d->decl_stack[d->decl_stack_cnt++] = id; + + return 0; +} + +/* + * Emit type declaration (e.g., field type declaration in a struct or argument + * declaration in function prototype) in correct C syntax. + * + * For most types it's trivial, but there are few quirky type declaration + * cases worth mentioning: + * - function prototypes (especially nesting of function prototypes); + * - arrays; + * - const/volatile/restrict for pointers vs other types. + * + * For a good discussion of *PARSING* C syntax (as a human), see + * Peter van der Linden's "Expert C Programming: Deep C Secrets", + * Ch.3 "Unscrambling Declarations in C". + * + * It won't help with BTF to C conversion much, though, as it's an opposite + * problem. So we came up with this algorithm in reverse to van der Linden's + * parsing algorithm. It goes from structured BTF representation of type + * declaration to a valid compilable C syntax. + * + * For instance, consider this C typedef: + * typedef const int * const * arr[10] arr_t; + * It will be represented in BTF with this chain of BTF types: + * [typedef] -> [array] -> [ptr] -> [const] -> [ptr] -> [const] -> [int] + * + * Notice how [const] modifier always goes before type it modifies in BTF type + * graph, but in C syntax, const/volatile/restrict modifiers are written to + * the right of pointers, but to the left of other types. There are also other + * quirks, like function pointers, arrays of them, functions returning other + * functions, etc. + * + * We handle that by pushing all the types to a stack, until we hit "terminal" + * type (int/enum/struct/union/fwd). Then depending on the kind of a type on + * top of a stack, modifiers are handled differently. Array/function pointers + * have also wildly different syntax and how nesting of them are done. See + * code for authoritative definition. + * + * To avoid allocating new stack for each independent chain of BTF types, we + * share one bigger stack, with each chain working only on its own local view + * of a stack frame. Some care is required to "pop" stack frames after + * processing type declaration chain. + */ +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, err; + + if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts)) + return libbpf_err(-EINVAL); + + err = btf_dump_resize(d); + if (err) + return libbpf_err(err); + + fname = OPTS_GET(opts, field_name, ""); + lvl = OPTS_GET(opts, indent_level, 0); + d->strip_mods = OPTS_GET(opts, strip_mods, false); + btf_dump_emit_type_decl(d, id, fname, lvl); + d->strip_mods = false; + 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; + + stack_start = d->decl_stack_cnt; + for (;;) { + t = btf__type_by_id(d->btf, id); + if (d->strip_mods && btf_is_mod(t)) + goto skip_mod; + + err = btf_dump_push_decl_stack_id(d, id); + if (err < 0) { + /* + * if we don't have enough memory for entire type decl + * chain, restore stack, emit warning, and try to + * proceed nevertheless + */ + pr_warn("not enough memory for decl stack:%d", err); + d->decl_stack_cnt = stack_start; + return; + } +skip_mod: + /* VOID */ + if (id == 0) + break; + + switch (btf_kind(t)) { + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TYPE_TAG: + id = t->type; + break; + case BTF_KIND_ARRAY: + id = btf_array(t)->type; + break; + case BTF_KIND_INT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_FWD: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FLOAT: + goto done; + default: + pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n", + btf_kind(t), id); + goto done; + } + } +done: + /* + * We might be inside a chain of declarations (e.g., array of function + * pointers returning anonymous (so inlined) structs, having another + * array field). Each of those needs its own "stack frame" to handle + * emitting of declarations. Those stack frames are non-overlapping + * portions of shared btf_dump->decl_stack. To make it a bit nicer to + * handle this set of nested stacks, we create a view corresponding to + * our own "stack frame" and work with it as an independent stack. + * We'll need to clean up after emit_type_chain() returns, though. + */ + decl_stack.ids = d->decl_stack + stack_start; + decl_stack.cnt = d->decl_stack_cnt - stack_start; + btf_dump_emit_type_chain(d, &decl_stack, fname, lvl); + /* + * emit_type_chain() guarantees that it will pop its entire decl_stack + * frame before returning. But it works with a read-only view into + * decl_stack, so it doesn't actually pop anything from the + * perspective of shared btf_dump->decl_stack, per se. We need to + * reset decl_stack state to how it was before us to avoid it growing + * all the time. + */ + d->decl_stack_cnt = stack_start; +} + +static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) +{ + const struct btf_type *t; + __u32 id; + + while (decl_stack->cnt) { + id = decl_stack->ids[decl_stack->cnt - 1]; + t = btf__type_by_id(d->btf, id); + + switch (btf_kind(t)) { + case BTF_KIND_VOLATILE: + btf_dump_printf(d, "volatile "); + break; + case BTF_KIND_CONST: + btf_dump_printf(d, "const "); + break; + case BTF_KIND_RESTRICT: + btf_dump_printf(d, "restrict "); + break; + default: + return; + } + decl_stack->cnt--; + } +} + +static void btf_dump_drop_mods(struct btf_dump *d, struct id_stack *decl_stack) +{ + const struct btf_type *t; + __u32 id; + + while (decl_stack->cnt) { + id = decl_stack->ids[decl_stack->cnt - 1]; + t = btf__type_by_id(d->btf, id); + if (!btf_is_mod(t)) + return; + decl_stack->cnt--; + } +} + +static void btf_dump_emit_name(const struct btf_dump *d, + const char *name, bool last_was_ptr) +{ + bool separate = name[0] && !last_was_ptr; + + btf_dump_printf(d, "%s%s", separate ? " " : "", name); +} + +static void btf_dump_emit_type_chain(struct btf_dump *d, + struct id_stack *decls, + const char *fname, int lvl) +{ + /* + * last_was_ptr is used to determine if we need to separate pointer + * asterisk (*) from previous part of type signature with space, so + * that we get `int ***`, instead of `int * * *`. We default to true + * for cases where we have single pointer in a chain. E.g., in ptr -> + * func_proto case. func_proto will start a new emit_type_chain call + * with just ptr, which should be emitted as (*) or (*<fname>), so we + * don't want to prepend space for that last pointer. + */ + bool last_was_ptr = true; + const struct btf_type *t; + const char *name; + __u16 kind; + __u32 id; + + while (decls->cnt) { + id = decls->ids[--decls->cnt]; + if (id == 0) { + /* VOID is a special snowflake */ + btf_dump_emit_mods(d, decls); + btf_dump_printf(d, "void"); + last_was_ptr = false; + continue; + } + + t = btf__type_by_id(d->btf, id); + kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + btf_dump_emit_mods(d, decls); + name = btf_name_of(d, t->name_off); + btf_dump_printf(d, "%s", name); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + btf_dump_emit_mods(d, decls); + /* inline anonymous struct/union */ + if (t->name_off == 0 && !d->skip_anon_defs) + btf_dump_emit_struct_def(d, id, t, lvl); + else + btf_dump_emit_struct_fwd(d, id, t); + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + btf_dump_emit_mods(d, decls); + /* inline anonymous enum */ + if (t->name_off == 0 && !d->skip_anon_defs) + btf_dump_emit_enum_def(d, id, t, lvl); + else + btf_dump_emit_enum_fwd(d, id, t); + break; + case BTF_KIND_FWD: + btf_dump_emit_mods(d, decls); + btf_dump_emit_fwd_def(d, id, t); + break; + case BTF_KIND_TYPEDEF: + btf_dump_emit_mods(d, decls); + btf_dump_printf(d, "%s", btf_dump_ident_name(d, id)); + break; + case BTF_KIND_PTR: + btf_dump_printf(d, "%s", last_was_ptr ? "*" : " *"); + break; + case BTF_KIND_VOLATILE: + btf_dump_printf(d, " volatile"); + break; + case BTF_KIND_CONST: + btf_dump_printf(d, " const"); + break; + case BTF_KIND_RESTRICT: + btf_dump_printf(d, " restrict"); + break; + case BTF_KIND_TYPE_TAG: + btf_dump_emit_mods(d, decls); + name = btf_name_of(d, t->name_off); + btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); + break; + case BTF_KIND_ARRAY: { + const struct btf_array *a = btf_array(t); + const struct btf_type *next_t; + __u32 next_id; + bool multidim; + /* + * GCC has a bug + * (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=8354) + * which causes it to emit extra const/volatile + * modifiers for an array, if array's element type has + * const/volatile modifiers. Clang doesn't do that. + * In general, it doesn't seem very meaningful to have + * a const/volatile modifier for array, so we are + * going to silently skip them here. + */ + btf_dump_drop_mods(d, decls); + + if (decls->cnt == 0) { + btf_dump_emit_name(d, fname, last_was_ptr); + btf_dump_printf(d, "[%u]", a->nelems); + return; + } + + next_id = decls->ids[decls->cnt - 1]; + next_t = btf__type_by_id(d->btf, next_id); + multidim = btf_is_array(next_t); + /* we need space if we have named non-pointer */ + if (fname[0] && !last_was_ptr) + btf_dump_printf(d, " "); + /* no parentheses for multi-dimensional array */ + if (!multidim) + btf_dump_printf(d, "("); + btf_dump_emit_type_chain(d, decls, fname, lvl); + if (!multidim) + btf_dump_printf(d, ")"); + btf_dump_printf(d, "[%u]", a->nelems); + return; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); + int i; + + /* + * GCC emits extra volatile qualifier for + * __attribute__((noreturn)) function pointers. Clang + * doesn't do it. It's a GCC quirk for backwards + * compatibility with code written for GCC <2.5. So, + * similarly to extra qualifiers for array, just drop + * them, instead of handling them. + */ + btf_dump_drop_mods(d, decls); + if (decls->cnt) { + btf_dump_printf(d, " ("); + btf_dump_emit_type_chain(d, decls, fname, lvl); + btf_dump_printf(d, ")"); + } else { + btf_dump_emit_name(d, fname, last_was_ptr); + } + btf_dump_printf(d, "("); + /* + * Clang for BPF target generates func_proto with no + * args as a func_proto with a single void arg (e.g., + * `int (*f)(void)` vs just `int (*f)()`). We are + * going to pretend there are no args for such case. + */ + if (vlen == 1 && p->type == 0) { + btf_dump_printf(d, ")"); + return; + } + + for (i = 0; i < vlen; i++, p++) { + if (i > 0) + btf_dump_printf(d, ", "); + + /* last arg of type void is vararg */ + if (i == vlen - 1 && p->type == 0) { + btf_dump_printf(d, "..."); + break; + } + + name = btf_name_of(d, p->name_off); + btf_dump_emit_type_decl(d, p->type, name, lvl); + } + + btf_dump_printf(d, ")"); + return; + } + default: + pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n", + kind, id); + return; + } + + last_was_ptr = kind == BTF_KIND_PTR; + } + + btf_dump_emit_name(d, fname, last_was_ptr); +} + +/* show type name as (type_name) */ +static void btf_dump_emit_type_cast(struct btf_dump *d, __u32 id, + bool top_level) +{ + const struct btf_type *t; + + /* for array members, we don't bother emitting type name for each + * member to avoid the redundancy of + * .name = (char[4])[(char)'f',(char)'o',(char)'o',] + */ + if (d->typed_dump->is_array_member) + return; + + /* avoid type name specification for variable/section; it will be done + * for the associated variable value(s). + */ + t = btf__type_by_id(d->btf, id); + if (btf_is_var(t) || btf_is_datasec(t)) + return; + + if (top_level) + btf_dump_printf(d, "("); + + d->skip_anon_defs = true; + d->strip_mods = true; + btf_dump_emit_type_decl(d, id, "", 0); + d->strip_mods = false; + d->skip_anon_defs = false; + + if (top_level) + btf_dump_printf(d, ")"); +} + +/* return number of duplicates (occurrences) of a given name */ +static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map, + const char *orig_name) +{ + char *old_name, *new_name; + size_t dup_cnt = 0; + int err; + + new_name = strdup(orig_name); + if (!new_name) + return 1; + + hashmap__find(name_map, orig_name, (void **)&dup_cnt); + dup_cnt++; + + err = hashmap__set(name_map, new_name, (void *)dup_cnt, + (const void **)&old_name, NULL); + if (err) + free(new_name); + + free(old_name); + + return dup_cnt; +} + +static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id, + struct hashmap *name_map) +{ + struct btf_dump_type_aux_state *s = &d->type_states[id]; + const struct btf_type *t = btf__type_by_id(d->btf, id); + const char *orig_name = btf_name_of(d, t->name_off); + const char **cached_name = &d->cached_names[id]; + size_t dup_cnt; + + if (t->name_off == 0) + return ""; + + if (s->name_resolved) + return *cached_name ? *cached_name : orig_name; + + if (btf_is_fwd(t) || (btf_is_enum(t) && btf_vlen(t) == 0)) { + s->name_resolved = 1; + return orig_name; + } + + dup_cnt = btf_dump_name_dups(d, name_map, orig_name); + if (dup_cnt > 1) { + const size_t max_len = 256; + char new_name[max_len]; + + snprintf(new_name, max_len, "%s___%zu", orig_name, dup_cnt); + *cached_name = strdup(new_name); + } + + s->name_resolved = 1; + return *cached_name ? *cached_name : orig_name; +} + +static const char *btf_dump_type_name(struct btf_dump *d, __u32 id) +{ + return btf_dump_resolve_name(d, id, d->type_names); +} + +static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id) +{ + return btf_dump_resolve_name(d, id, d->ident_names); +} + +static int btf_dump_dump_type_data(struct btf_dump *d, + const char *fname, + const struct btf_type *t, + __u32 id, + const void *data, + __u8 bits_offset, + __u8 bit_sz); + +static const char *btf_dump_data_newline(struct btf_dump *d) +{ + return d->typed_dump->compact || d->typed_dump->depth == 0 ? "" : "\n"; +} + +static const char *btf_dump_data_delim(struct btf_dump *d) +{ + return d->typed_dump->depth == 0 ? "" : ","; +} + +static void btf_dump_data_pfx(struct btf_dump *d) +{ + int i, lvl = d->typed_dump->indent_lvl + d->typed_dump->depth; + + if (d->typed_dump->compact) + return; + + for (i = 0; i < lvl; i++) + btf_dump_printf(d, "%s", d->typed_dump->indent_str); +} + +/* A macro is used here as btf_type_value[s]() appends format specifiers + * to the format specifier passed in; these do the work of appending + * delimiters etc while the caller simply has to specify the type values + * in the format specifier + value(s). + */ +#define btf_dump_type_values(d, fmt, ...) \ + btf_dump_printf(d, fmt "%s%s", \ + ##__VA_ARGS__, \ + btf_dump_data_delim(d), \ + btf_dump_data_newline(d)) + +static int btf_dump_unsupported_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id) +{ + btf_dump_printf(d, "<unsupported kind:%u>", btf_kind(t)); + return -ENOTSUP; +} + +static int btf_dump_get_bitfield_value(struct btf_dump *d, + const struct btf_type *t, + const void *data, + __u8 bits_offset, + __u8 bit_sz, + __u64 *value) +{ + __u16 left_shift_bits, right_shift_bits; + const __u8 *bytes = data; + __u8 nr_copy_bits; + __u64 num = 0; + int i; + + /* Maximum supported bitfield size is 64 bits */ + if (t->size > 8) { + pr_warn("unexpected bitfield size %d\n", t->size); + return -EINVAL; + } + + /* Bitfield value retrieval is done in two steps; first relevant bytes are + * stored in num, then we left/right shift num to eliminate irrelevant bits. + */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + for (i = t->size - 1; i >= 0; i--) + num = num * 256 + bytes[i]; + nr_copy_bits = bit_sz + bits_offset; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + for (i = 0; i < t->size; i++) + num = num * 256 + bytes[i]; + nr_copy_bits = t->size * 8 - bits_offset; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + left_shift_bits = 64 - nr_copy_bits; + right_shift_bits = 64 - bit_sz; + + *value = (num << left_shift_bits) >> right_shift_bits; + + return 0; +} + +static int btf_dump_bitfield_check_zero(struct btf_dump *d, + const struct btf_type *t, + const void *data, + __u8 bits_offset, + __u8 bit_sz) +{ + __u64 check_num; + int err; + + err = btf_dump_get_bitfield_value(d, t, data, bits_offset, bit_sz, &check_num); + if (err) + return err; + if (check_num == 0) + return -ENODATA; + return 0; +} + +static int btf_dump_bitfield_data(struct btf_dump *d, + const struct btf_type *t, + const void *data, + __u8 bits_offset, + __u8 bit_sz) +{ + __u64 print_num; + int err; + + err = btf_dump_get_bitfield_value(d, t, data, bits_offset, bit_sz, &print_num); + if (err) + return err; + + btf_dump_type_values(d, "0x%llx", (unsigned long long)print_num); + + return 0; +} + +/* ints, floats and ptrs */ +static int btf_dump_base_type_check_zero(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + static __u8 bytecmp[16] = {}; + int nr_bytes; + + /* For pointer types, pointer size is not defined on a per-type basis. + * On dump creation however, we store the pointer size. + */ + if (btf_kind(t) == BTF_KIND_PTR) + nr_bytes = d->ptr_sz; + else + nr_bytes = t->size; + + if (nr_bytes < 1 || nr_bytes > 16) { + pr_warn("unexpected size %d for id [%u]\n", nr_bytes, id); + return -EINVAL; + } + + if (memcmp(data, bytecmp, nr_bytes) == 0) + return -ENODATA; + return 0; +} + +static bool ptr_is_aligned(const struct btf *btf, __u32 type_id, + const void *data) +{ + int alignment = btf__align_of(btf, type_id); + + if (alignment == 0) + return false; + + return ((uintptr_t)data) % alignment == 0; +} + +static int btf_dump_int_data(struct btf_dump *d, + const struct btf_type *t, + __u32 type_id, + const void *data, + __u8 bits_offset) +{ + __u8 encoding = btf_int_encoding(t); + bool sign = encoding & BTF_INT_SIGNED; + char buf[16] __attribute__((aligned(16))); + int sz = t->size; + + if (sz == 0 || sz > sizeof(buf)) { + pr_warn("unexpected size %d for id [%u]\n", sz, type_id); + return -EINVAL; + } + + /* handle packed int data - accesses of integers not aligned on + * int boundaries can cause problems on some platforms. + */ + if (!ptr_is_aligned(d->btf, type_id, data)) { + memcpy(buf, data, sz); + data = buf; + } + + switch (sz) { + case 16: { + const __u64 *ints = data; + __u64 lsi, msi; + + /* avoid use of __int128 as some 32-bit platforms do not + * support it. + */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + lsi = ints[0]; + msi = ints[1]; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + lsi = ints[1]; + msi = ints[0]; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + if (msi == 0) + btf_dump_type_values(d, "0x%llx", (unsigned long long)lsi); + else + btf_dump_type_values(d, "0x%llx%016llx", (unsigned long long)msi, + (unsigned long long)lsi); + break; + } + case 8: + if (sign) + btf_dump_type_values(d, "%lld", *(long long *)data); + else + btf_dump_type_values(d, "%llu", *(unsigned long long *)data); + break; + case 4: + if (sign) + btf_dump_type_values(d, "%d", *(__s32 *)data); + else + btf_dump_type_values(d, "%u", *(__u32 *)data); + break; + case 2: + if (sign) + btf_dump_type_values(d, "%d", *(__s16 *)data); + else + btf_dump_type_values(d, "%u", *(__u16 *)data); + break; + case 1: + if (d->typed_dump->is_array_char) { + /* check for null terminator */ + if (d->typed_dump->is_array_terminated) + break; + if (*(char *)data == '\0') { + d->typed_dump->is_array_terminated = true; + break; + } + if (isprint(*(char *)data)) { + btf_dump_type_values(d, "'%c'", *(char *)data); + break; + } + } + if (sign) + btf_dump_type_values(d, "%d", *(__s8 *)data); + else + btf_dump_type_values(d, "%u", *(__u8 *)data); + break; + default: + pr_warn("unexpected sz %d for id [%u]\n", sz, type_id); + return -EINVAL; + } + return 0; +} + +union float_data { + long double ld; + double d; + float f; +}; + +static int btf_dump_float_data(struct btf_dump *d, + const struct btf_type *t, + __u32 type_id, + const void *data) +{ + const union float_data *flp = data; + union float_data fl; + int sz = t->size; + + /* handle unaligned data; copy to local union */ + if (!ptr_is_aligned(d->btf, type_id, data)) { + memcpy(&fl, data, sz); + flp = &fl; + } + + switch (sz) { + case 16: + btf_dump_type_values(d, "%Lf", flp->ld); + break; + case 8: + btf_dump_type_values(d, "%lf", flp->d); + break; + case 4: + btf_dump_type_values(d, "%f", flp->f); + break; + default: + pr_warn("unexpected size %d for id [%u]\n", sz, type_id); + return -EINVAL; + } + return 0; +} + +static int btf_dump_var_data(struct btf_dump *d, + const struct btf_type *v, + __u32 id, + const void *data) +{ + enum btf_func_linkage linkage = btf_var(v)->linkage; + const struct btf_type *t; + const char *l; + __u32 type_id; + + switch (linkage) { + case BTF_FUNC_STATIC: + l = "static "; + break; + case BTF_FUNC_EXTERN: + l = "extern "; + break; + case BTF_FUNC_GLOBAL: + default: + l = ""; + break; + } + + /* format of output here is [linkage] [type] [varname] = (type)value, + * for example "static int cpu_profile_flip = (int)1" + */ + btf_dump_printf(d, "%s", l); + type_id = v->type; + t = btf__type_by_id(d->btf, type_id); + btf_dump_emit_type_cast(d, type_id, false); + btf_dump_printf(d, " %s = ", btf_name_of(d, v->name_off)); + return btf_dump_dump_type_data(d, NULL, t, type_id, data, 0, 0); +} + +static int btf_dump_array_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + const struct btf_array *array = btf_array(t); + const struct btf_type *elem_type; + __u32 i, elem_type_id; + __s64 elem_size; + bool is_array_member; + + elem_type_id = array->type; + elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL); + elem_size = btf__resolve_size(d->btf, elem_type_id); + if (elem_size <= 0) { + pr_warn("unexpected elem size %zd for array type [%u]\n", + (ssize_t)elem_size, id); + return -EINVAL; + } + + if (btf_is_int(elem_type)) { + /* + * BTF_INT_CHAR encoding never seems to be set for + * char arrays, so if size is 1 and element is + * printable as a char, we'll do that. + */ + if (elem_size == 1) + d->typed_dump->is_array_char = true; + } + + /* note that we increment depth before calling btf_dump_print() below; + * this is intentional. btf_dump_data_newline() will not print a + * newline for depth 0 (since this leaves us with trailing newlines + * at the end of typed display), so depth is incremented first. + * For similar reasons, we decrement depth before showing the closing + * parenthesis. + */ + d->typed_dump->depth++; + btf_dump_printf(d, "[%s", btf_dump_data_newline(d)); + + /* may be a multidimensional array, so store current "is array member" + * status so we can restore it correctly later. + */ + is_array_member = d->typed_dump->is_array_member; + d->typed_dump->is_array_member = true; + for (i = 0; i < array->nelems; i++, data += elem_size) { + if (d->typed_dump->is_array_terminated) + break; + btf_dump_dump_type_data(d, NULL, elem_type, elem_type_id, data, 0, 0); + } + d->typed_dump->is_array_member = is_array_member; + d->typed_dump->depth--; + btf_dump_data_pfx(d); + btf_dump_type_values(d, "]"); + + return 0; +} + +static int btf_dump_struct_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + const struct btf_member *m = btf_members(t); + __u16 n = btf_vlen(t); + int i, err = 0; + + /* note that we increment depth before calling btf_dump_print() below; + * this is intentional. btf_dump_data_newline() will not print a + * newline for depth 0 (since this leaves us with trailing newlines + * at the end of typed display), so depth is incremented first. + * For similar reasons, we decrement depth before showing the closing + * parenthesis. + */ + d->typed_dump->depth++; + btf_dump_printf(d, "{%s", btf_dump_data_newline(d)); + + for (i = 0; i < n; i++, m++) { + const struct btf_type *mtype; + const char *mname; + __u32 moffset; + __u8 bit_sz; + + mtype = btf__type_by_id(d->btf, m->type); + mname = btf_name_of(d, m->name_off); + moffset = btf_member_bit_offset(t, i); + + bit_sz = btf_member_bitfield_size(t, i); + err = btf_dump_dump_type_data(d, mname, mtype, m->type, data + moffset / 8, + moffset % 8, bit_sz); + if (err < 0) + return err; + } + d->typed_dump->depth--; + btf_dump_data_pfx(d); + btf_dump_type_values(d, "}"); + return err; +} + +union ptr_data { + unsigned int p; + unsigned long long lp; +}; + +static int btf_dump_ptr_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + if (ptr_is_aligned(d->btf, id, data) && d->ptr_sz == sizeof(void *)) { + btf_dump_type_values(d, "%p", *(void **)data); + } else { + union ptr_data pt; + + memcpy(&pt, data, d->ptr_sz); + if (d->ptr_sz == 4) + btf_dump_type_values(d, "0x%x", pt.p); + else + btf_dump_type_values(d, "0x%llx", pt.lp); + } + return 0; +} + +static int btf_dump_get_enum_value(struct btf_dump *d, + const struct btf_type *t, + const void *data, + __u32 id, + __s64 *value) +{ + bool is_signed = btf_kflag(t); + + if (!ptr_is_aligned(d->btf, id, data)) { + __u64 val; + int err; + + err = btf_dump_get_bitfield_value(d, t, data, 0, 0, &val); + if (err) + return err; + *value = (__s64)val; + return 0; + } + + switch (t->size) { + case 8: + *value = *(__s64 *)data; + return 0; + case 4: + *value = is_signed ? (__s64)*(__s32 *)data : *(__u32 *)data; + return 0; + case 2: + *value = is_signed ? *(__s16 *)data : *(__u16 *)data; + return 0; + case 1: + *value = is_signed ? *(__s8 *)data : *(__u8 *)data; + return 0; + default: + pr_warn("unexpected size %d for enum, id:[%u]\n", t->size, id); + return -EINVAL; + } +} + +static int btf_dump_enum_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + bool is_signed; + __s64 value; + int i, err; + + err = btf_dump_get_enum_value(d, t, data, id, &value); + if (err) + return err; + + is_signed = btf_kflag(t); + if (btf_is_enum(t)) { + const struct btf_enum *e; + + for (i = 0, e = btf_enum(t); i < btf_vlen(t); i++, e++) { + if (value != e->val) + continue; + btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off)); + return 0; + } + + btf_dump_type_values(d, is_signed ? "%d" : "%u", value); + } else { + const struct btf_enum64 *e; + + for (i = 0, e = btf_enum64(t); i < btf_vlen(t); i++, e++) { + if (value != btf_enum64_value(e)) + continue; + btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off)); + return 0; + } + + btf_dump_type_values(d, is_signed ? "%lldLL" : "%lluULL", + (unsigned long long)value); + } + return 0; +} + +static int btf_dump_datasec_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + const struct btf_var_secinfo *vsi; + const struct btf_type *var; + __u32 i; + int err; + + btf_dump_type_values(d, "SEC(\"%s\") ", btf_name_of(d, t->name_off)); + + for (i = 0, vsi = btf_var_secinfos(t); i < btf_vlen(t); i++, vsi++) { + var = btf__type_by_id(d->btf, vsi->type); + err = btf_dump_dump_type_data(d, NULL, var, vsi->type, data + vsi->offset, 0, 0); + if (err < 0) + return err; + btf_dump_printf(d, ";"); + } + return 0; +} + +/* return size of type, or if base type overflows, return -E2BIG. */ +static int btf_dump_type_data_check_overflow(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data, + __u8 bits_offset, + __u8 bit_sz) +{ + __s64 size; + + if (bit_sz) { + /* bits_offset is at most 7. bit_sz is at most 128. */ + __u8 nr_bytes = (bits_offset + bit_sz + 7) / 8; + + /* When bit_sz is non zero, it is called from + * btf_dump_struct_data() where it only cares about + * negative error value. + * Return nr_bytes in success case to make it + * consistent as the regular integer case below. + */ + return data + nr_bytes > d->typed_dump->data_end ? -E2BIG : nr_bytes; + } + + size = btf__resolve_size(d->btf, id); + + if (size < 0 || size >= INT_MAX) { + pr_warn("unexpected size [%zu] for id [%u]\n", + (size_t)size, id); + return -EINVAL; + } + + /* Only do overflow checking for base types; we do not want to + * avoid showing part of a struct, union or array, even if we + * do not have enough data to show the full object. By + * restricting overflow checking to base types we can ensure + * that partial display succeeds, while avoiding overflowing + * and using bogus data for display. + */ + t = skip_mods_and_typedefs(d->btf, id, NULL); + if (!t) { + pr_warn("unexpected error skipping mods/typedefs for id [%u]\n", + id); + return -EINVAL; + } + + switch (btf_kind(t)) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_PTR: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + if (data + bits_offset / 8 + size > d->typed_dump->data_end) + return -E2BIG; + break; + default: + break; + } + return (int)size; +} + +static int btf_dump_type_data_check_zero(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data, + __u8 bits_offset, + __u8 bit_sz) +{ + __s64 value; + int i, err; + + /* toplevel exceptions; we show zero values if + * - we ask for them (emit_zeros) + * - if we are at top-level so we see "struct empty { }" + * - or if we are an array member and the array is non-empty and + * not a char array; we don't want to be in a situation where we + * have an integer array 0, 1, 0, 1 and only show non-zero values. + * If the array contains zeroes only, or is a char array starting + * with a '\0', the array-level check_zero() will prevent showing it; + * we are concerned with determining zero value at the array member + * level here. + */ + if (d->typed_dump->emit_zeroes || d->typed_dump->depth == 0 || + (d->typed_dump->is_array_member && + !d->typed_dump->is_array_char)) + return 0; + + t = skip_mods_and_typedefs(d->btf, id, NULL); + + switch (btf_kind(t)) { + case BTF_KIND_INT: + if (bit_sz) + return btf_dump_bitfield_check_zero(d, t, data, bits_offset, bit_sz); + return btf_dump_base_type_check_zero(d, t, id, data); + case BTF_KIND_FLOAT: + case BTF_KIND_PTR: + return btf_dump_base_type_check_zero(d, t, id, data); + case BTF_KIND_ARRAY: { + const struct btf_array *array = btf_array(t); + const struct btf_type *elem_type; + __u32 elem_type_id, elem_size; + bool ischar; + + elem_type_id = array->type; + elem_size = btf__resolve_size(d->btf, elem_type_id); + elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL); + + ischar = btf_is_int(elem_type) && elem_size == 1; + + /* check all elements; if _any_ element is nonzero, all + * of array is displayed. We make an exception however + * for char arrays where the first element is 0; these + * are considered zeroed also, even if later elements are + * non-zero because the string is terminated. + */ + for (i = 0; i < array->nelems; i++) { + if (i == 0 && ischar && *(char *)data == 0) + return -ENODATA; + err = btf_dump_type_data_check_zero(d, elem_type, + elem_type_id, + data + + (i * elem_size), + bits_offset, 0); + if (err != -ENODATA) + return err; + } + return -ENODATA; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + __u16 n = btf_vlen(t); + + /* if any struct/union member is non-zero, the struct/union + * is considered non-zero and dumped. + */ + for (i = 0; i < n; i++, m++) { + const struct btf_type *mtype; + __u32 moffset; + + mtype = btf__type_by_id(d->btf, m->type); + moffset = btf_member_bit_offset(t, i); + + /* btf_int_bits() does not store member bitfield size; + * bitfield size needs to be stored here so int display + * of member can retrieve it. + */ + bit_sz = btf_member_bitfield_size(t, i); + err = btf_dump_type_data_check_zero(d, mtype, m->type, data + moffset / 8, + moffset % 8, bit_sz); + if (err != ENODATA) + return err; + } + return -ENODATA; + } + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + err = btf_dump_get_enum_value(d, t, data, id, &value); + if (err) + return err; + if (value == 0) + return -ENODATA; + return 0; + default: + return 0; + } +} + +/* returns size of data dumped, or error. */ +static int btf_dump_dump_type_data(struct btf_dump *d, + const char *fname, + const struct btf_type *t, + __u32 id, + const void *data, + __u8 bits_offset, + __u8 bit_sz) +{ + int size, err = 0; + + size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset, bit_sz); + if (size < 0) + return size; + err = btf_dump_type_data_check_zero(d, t, id, data, bits_offset, bit_sz); + if (err) { + /* zeroed data is expected and not an error, so simply skip + * dumping such data. Record other errors however. + */ + if (err == -ENODATA) + return size; + return err; + } + btf_dump_data_pfx(d); + + if (!d->typed_dump->skip_names) { + if (fname && strlen(fname) > 0) + btf_dump_printf(d, ".%s = ", fname); + btf_dump_emit_type_cast(d, id, true); + } + + t = skip_mods_and_typedefs(d->btf, id, NULL); + + switch (btf_kind(t)) { + case BTF_KIND_UNKN: + case BTF_KIND_FWD: + case BTF_KIND_FUNC: + case BTF_KIND_FUNC_PROTO: + case BTF_KIND_DECL_TAG: + err = btf_dump_unsupported_data(d, t, id); + break; + case BTF_KIND_INT: + if (bit_sz) + err = btf_dump_bitfield_data(d, t, data, bits_offset, bit_sz); + else + err = btf_dump_int_data(d, t, id, data, bits_offset); + break; + case BTF_KIND_FLOAT: + err = btf_dump_float_data(d, t, id, data); + break; + case BTF_KIND_PTR: + err = btf_dump_ptr_data(d, t, id, data); + break; + case BTF_KIND_ARRAY: + err = btf_dump_array_data(d, t, id, data); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + err = btf_dump_struct_data(d, t, id, data); + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + /* handle bitfield and int enum values */ + if (bit_sz) { + __u64 print_num; + __s64 enum_val; + + err = btf_dump_get_bitfield_value(d, t, data, bits_offset, bit_sz, + &print_num); + if (err) + break; + enum_val = (__s64)print_num; + err = btf_dump_enum_data(d, t, id, &enum_val); + } else + err = btf_dump_enum_data(d, t, id, data); + break; + case BTF_KIND_VAR: + err = btf_dump_var_data(d, t, id, data); + break; + case BTF_KIND_DATASEC: + err = btf_dump_datasec_data(d, t, id, data); + break; + default: + pr_warn("unexpected kind [%u] for id [%u]\n", + BTF_INFO_KIND(t->info), id); + return -EINVAL; + } + if (err < 0) + return err; + return size; +} + +int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, + const void *data, size_t data_sz, + const struct btf_dump_type_data_opts *opts) +{ + struct btf_dump_data typed_dump = {}; + const struct btf_type *t; + int ret; + + if (!OPTS_VALID(opts, btf_dump_type_data_opts)) + return libbpf_err(-EINVAL); + + t = btf__type_by_id(d->btf, id); + if (!t) + return libbpf_err(-ENOENT); + + d->typed_dump = &typed_dump; + d->typed_dump->data_end = data + data_sz; + d->typed_dump->indent_lvl = OPTS_GET(opts, indent_level, 0); + + /* default indent string is a tab */ + if (!OPTS_GET(opts, indent_str, NULL)) + d->typed_dump->indent_str[0] = '\t'; + else + libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str, + sizeof(d->typed_dump->indent_str)); + + d->typed_dump->compact = OPTS_GET(opts, compact, false); + d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false); + d->typed_dump->emit_zeroes = OPTS_GET(opts, emit_zeroes, false); + + ret = btf_dump_dump_type_data(d, NULL, t, id, data, 0, 0); + + d->typed_dump = NULL; + + return libbpf_err(ret); +} diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c new file mode 100644 index 000000000..b74c82bb8 --- /dev/null +++ b/tools/lib/bpf/gen_loader.c @@ -0,0 +1,1123 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2021 Facebook */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <linux/filter.h> +#include <sys/param.h> +#include "btf.h" +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" +#include "hashmap.h" +#include "bpf_gen_internal.h" +#include "skel_internal.h" +#include <asm/byteorder.h> + +#define MAX_USED_MAPS 64 +#define MAX_USED_PROGS 32 +#define MAX_KFUNC_DESCS 256 +#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS) + +/* The following structure describes the stack layout of the loader program. + * In addition R6 contains the pointer to context. + * R7 contains the result of the last sys_bpf command (typically error or FD). + * R9 contains the result of the last sys_close command. + * + * Naming convention: + * ctx - bpf program context + * stack - bpf program stack + * blob - bpf_attr-s, strings, insns, map data. + * All the bytes that loader prog will use for read/write. + */ +struct loader_stack { + __u32 btf_fd; + __u32 inner_map_fd; + __u32 prog_fd[MAX_USED_PROGS]; +}; + +#define stack_off(field) \ + (__s16)(-sizeof(struct loader_stack) + offsetof(struct loader_stack, field)) + +#define attr_field(attr, field) (attr + offsetof(union bpf_attr, field)) + +static int blob_fd_array_off(struct bpf_gen *gen, int index) +{ + return gen->fd_array + index * sizeof(int); +} + +static int realloc_insn_buf(struct bpf_gen *gen, __u32 size) +{ + size_t off = gen->insn_cur - gen->insn_start; + void *insn_start; + + if (gen->error) + return gen->error; + if (size > INT32_MAX || off + size > INT32_MAX) { + gen->error = -ERANGE; + return -ERANGE; + } + insn_start = realloc(gen->insn_start, off + size); + if (!insn_start) { + gen->error = -ENOMEM; + free(gen->insn_start); + gen->insn_start = NULL; + return -ENOMEM; + } + gen->insn_start = insn_start; + gen->insn_cur = insn_start + off; + return 0; +} + +static int realloc_data_buf(struct bpf_gen *gen, __u32 size) +{ + size_t off = gen->data_cur - gen->data_start; + void *data_start; + + if (gen->error) + return gen->error; + if (size > INT32_MAX || off + size > INT32_MAX) { + gen->error = -ERANGE; + return -ERANGE; + } + data_start = realloc(gen->data_start, off + size); + if (!data_start) { + gen->error = -ENOMEM; + free(gen->data_start); + gen->data_start = NULL; + return -ENOMEM; + } + gen->data_start = data_start; + gen->data_cur = data_start + off; + return 0; +} + +static void emit(struct bpf_gen *gen, struct bpf_insn insn) +{ + if (realloc_insn_buf(gen, sizeof(insn))) + return; + memcpy(gen->insn_cur, &insn, sizeof(insn)); + gen->insn_cur += sizeof(insn); +} + +static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn insn2) +{ + emit(gen, insn1); + emit(gen, insn2); +} + +static int add_data(struct bpf_gen *gen, const void *data, __u32 size); +static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off); + +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps) +{ + size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz; + int i; + + gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); + gen->log_level = log_level; + /* save ctx pointer into R6 */ + emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1)); + + /* bzero stack */ + emit(gen, BPF_MOV64_REG(BPF_REG_1, BPF_REG_10)); + emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -stack_sz)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, stack_sz)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); + + /* amount of stack actually used, only used to calculate iterations, not stack offset */ + nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]); + /* jump over cleanup code */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, + /* size of cleanup code below (including map fd cleanup) */ + (nr_progs_sz / 4) * 3 + 2 + + /* 6 insns for emit_sys_close_blob, + * 6 insns for debug_regs in emit_sys_close_blob + */ + nr_maps * (6 + (gen->log_level ? 6 : 0)))); + + /* remember the label where all error branches will jump to */ + gen->cleanup_label = gen->insn_cur - gen->insn_start; + /* emit cleanup code: close all temp FDs */ + for (i = 0; i < nr_progs_sz; i += 4) { + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i)); + emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); + } + for (i = 0; i < nr_maps; i++) + emit_sys_close_blob(gen, blob_fd_array_off(gen, i)); + /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ + emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); + emit(gen, BPF_EXIT_INSN()); +} + +static int add_data(struct bpf_gen *gen, const void *data, __u32 size) +{ + __u32 size8 = roundup(size, 8); + __u64 zero = 0; + void *prev; + + if (realloc_data_buf(gen, size8)) + return 0; + prev = gen->data_cur; + if (data) { + memcpy(gen->data_cur, data, size); + memcpy(gen->data_cur + size, &zero, size8 - size); + } else { + memset(gen->data_cur, 0, size8); + } + gen->data_cur += size8; + return prev - gen->data_start; +} + +/* Get index for map_fd/btf_fd slot in reserved fd_array, or in data relative + * to start of fd_array. Caller can decide if it is usable or not. + */ +static int add_map_fd(struct bpf_gen *gen) +{ + if (gen->nr_maps == MAX_USED_MAPS) { + pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS); + gen->error = -E2BIG; + return 0; + } + return gen->nr_maps++; +} + +static int add_kfunc_btf_fd(struct bpf_gen *gen) +{ + int cur; + + if (gen->nr_fd_array == MAX_KFUNC_DESCS) { + cur = add_data(gen, NULL, sizeof(int)); + return (cur - gen->fd_array) / sizeof(int); + } + return MAX_USED_MAPS + gen->nr_fd_array++; +} + +static int insn_bytes_to_bpf_size(__u32 sz) +{ + switch (sz) { + case 8: return BPF_DW; + case 4: return BPF_W; + case 2: return BPF_H; + case 1: return BPF_B; + default: return -1; + } +} + +/* *(u64 *)(blob + off) = (u64)(void *)(blob + data) */ +static void emit_rel_store(struct bpf_gen *gen, int off, int data) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, data)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_blob2blob(struct bpf_gen *gen, int off, int size, int blob_off) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_off)); + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_2, 0)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_blob2ctx(struct bpf_gen *gen, int ctx_off, int size, int blob_off) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_off)); + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_1, 0)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off)); +} + +static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off, + bool check_non_zero) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_6, ctx_off)); + if (check_non_zero) + /* If value in ctx is zero don't update the blob. + * For example: when ctx->map.max_entries == 0, keep default max_entries from bpf.c + */ + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_stack2blob(struct bpf_gen *gen, int off, int size, int stack_off) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_stack2ctx(struct bpf_gen *gen, int ctx_off, int size, int stack_off) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off)); +} + +static void emit_sys_bpf(struct bpf_gen *gen, int cmd, int attr, int attr_size) +{ + emit(gen, BPF_MOV64_IMM(BPF_REG_1, cmd)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, attr)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, attr_size)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_bpf)); + /* remember the result in R7 */ + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); +} + +static bool is_simm16(__s64 value) +{ + return value == (__s64)(__s16)value; +} + +static void emit_check_err(struct bpf_gen *gen) +{ + __s64 off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1; + + /* R7 contains result of last sys_bpf command. + * if (R7 < 0) goto cleanup; + */ + if (is_simm16(off)) { + emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, off)); + } else { + gen->error = -ERANGE; + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1)); + } +} + +/* reg1 and reg2 should not be R1 - R5. They can be R0, R6 - R10 */ +static void emit_debug(struct bpf_gen *gen, int reg1, int reg2, + const char *fmt, va_list args) +{ + char buf[1024]; + int addr, len, ret; + + if (!gen->log_level) + return; + ret = vsnprintf(buf, sizeof(buf), fmt, args); + if (ret < 1024 - 7 && reg1 >= 0 && reg2 < 0) + /* The special case to accommodate common debug_ret(): + * to avoid specifying BPF_REG_7 and adding " r=%%d" to + * prints explicitly. + */ + strcat(buf, " r=%d"); + len = strlen(buf) + 1; + addr = add_data(gen, buf, len); + + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, addr)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + if (reg1 >= 0) + emit(gen, BPF_MOV64_REG(BPF_REG_3, reg1)); + if (reg2 >= 0) + emit(gen, BPF_MOV64_REG(BPF_REG_4, reg2)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_trace_printk)); +} + +static void debug_regs(struct bpf_gen *gen, int reg1, int reg2, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + emit_debug(gen, reg1, reg2, fmt, args); + va_end(args); +} + +static void debug_ret(struct bpf_gen *gen, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + emit_debug(gen, BPF_REG_7, -1, fmt, args); + va_end(args); +} + +static void __emit_sys_close(struct bpf_gen *gen) +{ + emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, + /* 2 is the number of the following insns + * * 6 is additional insns in debug_regs + */ + 2 + (gen->log_level ? 6 : 0))); + emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); + debug_regs(gen, BPF_REG_9, BPF_REG_0, "close(%%d) = %%d"); +} + +static void emit_sys_close_stack(struct bpf_gen *gen, int stack_off) +{ + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, stack_off)); + __emit_sys_close(gen); +} + +static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_off)); + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0)); + __emit_sys_close(gen); +} + +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) +{ + int i; + + if (nr_progs < gen->nr_progs || nr_maps != gen->nr_maps) { + pr_warn("nr_progs %d/%d nr_maps %d/%d mismatch\n", + nr_progs, gen->nr_progs, nr_maps, gen->nr_maps); + gen->error = -EFAULT; + return gen->error; + } + emit_sys_close_stack(gen, stack_off(btf_fd)); + for (i = 0; i < gen->nr_progs; i++) + move_stack2ctx(gen, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * gen->nr_maps + + sizeof(struct bpf_prog_desc) * i + + offsetof(struct bpf_prog_desc, prog_fd), 4, + stack_off(prog_fd[i])); + for (i = 0; i < gen->nr_maps; i++) + move_blob2ctx(gen, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * i + + offsetof(struct bpf_map_desc, map_fd), 4, + blob_fd_array_off(gen, i)); + emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0)); + emit(gen, BPF_EXIT_INSN()); + pr_debug("gen: finish %d\n", gen->error); + if (!gen->error) { + struct gen_loader_opts *opts = gen->opts; + + opts->insns = gen->insn_start; + opts->insns_sz = gen->insn_cur - gen->insn_start; + opts->data = gen->data_start; + opts->data_sz = gen->data_cur - gen->data_start; + } + return gen->error; +} + +void bpf_gen__free(struct bpf_gen *gen) +{ + if (!gen) + return; + free(gen->data_start); + free(gen->insn_start); + free(gen); +} + +void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, + __u32 btf_raw_size) +{ + int attr_size = offsetofend(union bpf_attr, btf_log_level); + int btf_data, btf_load_attr; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: load_btf: size %d\n", btf_raw_size); + btf_data = add_data(gen, btf_raw_data, btf_raw_size); + + attr.btf_size = btf_raw_size; + btf_load_attr = add_data(gen, &attr, attr_size); + + /* populate union bpf_attr with user provided log details */ + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4, + offsetof(struct bpf_loader_ctx, log_level), false); + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_size), 4, + offsetof(struct bpf_loader_ctx, log_size), false); + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_buf), 8, + offsetof(struct bpf_loader_ctx, log_buf), false); + /* populate union bpf_attr with a pointer to the BTF data */ + emit_rel_store(gen, attr_field(btf_load_attr, btf), btf_data); + /* emit BTF_LOAD command */ + emit_sys_bpf(gen, BPF_BTF_LOAD, btf_load_attr, attr_size); + debug_ret(gen, "btf_load size %d", btf_raw_size); + emit_check_err(gen); + /* remember btf_fd in the stack, if successful */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, stack_off(btf_fd))); +} + +void bpf_gen__map_create(struct bpf_gen *gen, + enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, __u32 value_size, __u32 max_entries, + struct bpf_map_create_opts *map_attr, int map_idx) +{ + int attr_size = offsetofend(union bpf_attr, map_extra); + bool close_inner_map_fd = false; + int map_create_attr, idx; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + attr.map_type = map_type; + attr.key_size = key_size; + attr.value_size = value_size; + attr.map_flags = map_attr->map_flags; + attr.map_extra = map_attr->map_extra; + if (map_name) + libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); + attr.numa_node = map_attr->numa_node; + attr.map_ifindex = map_attr->map_ifindex; + attr.max_entries = max_entries; + attr.btf_key_type_id = map_attr->btf_key_type_id; + attr.btf_value_type_id = map_attr->btf_value_type_id; + + pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", + attr.map_name, map_idx, map_type, attr.btf_value_type_id); + + map_create_attr = add_data(gen, &attr, attr_size); + if (attr.btf_value_type_id) + /* populate union bpf_attr with btf_fd saved in the stack earlier */ + move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4, + stack_off(btf_fd)); + switch (attr.map_type) { + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4, + stack_off(inner_map_fd)); + close_inner_map_fd = true; + break; + default: + break; + } + /* conditionally update max_entries */ + if (map_idx >= 0) + move_ctx2blob(gen, attr_field(map_create_attr, max_entries), 4, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * map_idx + + offsetof(struct bpf_map_desc, max_entries), + true /* check that max_entries != 0 */); + /* emit MAP_CREATE command */ + emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); + debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", + attr.map_name, map_idx, map_type, value_size, + attr.btf_value_type_id); + emit_check_err(gen); + /* remember map_fd in the stack, if successful */ + if (map_idx < 0) { + /* This bpf_gen__map_create() function is called with map_idx >= 0 + * for all maps that libbpf loading logic tracks. + * It's called with -1 to create an inner map. + */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, + stack_off(inner_map_fd))); + } else if (map_idx != gen->nr_maps) { + gen->error = -EDOM; /* internal bug */ + return; + } else { + /* add_map_fd does gen->nr_maps++ */ + idx = add_map_fd(gen); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_fd_array_off(gen, idx))); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7, 0)); + } + if (close_inner_map_fd) + emit_sys_close_stack(gen, stack_off(inner_map_fd)); +} + +void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name, + enum bpf_attach_type type) +{ + const char *prefix; + int kind, ret; + + btf_get_kernel_prefix_kind(type, &prefix, &kind); + gen->attach_kind = kind; + ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s", + prefix, attach_name); + if (ret >= sizeof(gen->attach_target)) + gen->error = -ENOSPC; +} + +static void emit_find_attach_target(struct bpf_gen *gen) +{ + int name, len = strlen(gen->attach_target) + 1; + + pr_debug("gen: find_attach_tgt %s %d\n", gen->attach_target, gen->attach_kind); + name = add_data(gen, gen->attach_target, len); + + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, name)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, gen->attach_kind)); + emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + debug_ret(gen, "find_by_name_kind(%s,%d)", + gen->attach_target, gen->attach_kind); + emit_check_err(gen); + /* if successful, btf_id is in lower 32-bit of R7 and + * btf_obj_fd is in upper 32-bit + */ +} + +void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, + bool is_typeless, int kind, int insn_idx) +{ + struct ksym_relo_desc *relo; + + relo = libbpf_reallocarray(gen->relos, gen->relo_cnt + 1, sizeof(*relo)); + if (!relo) { + gen->error = -ENOMEM; + return; + } + gen->relos = relo; + relo += gen->relo_cnt; + relo->name = name; + relo->is_weak = is_weak; + relo->is_typeless = is_typeless; + relo->kind = kind; + relo->insn_idx = insn_idx; + gen->relo_cnt++; +} + +/* returns existing ksym_desc with ref incremented, or inserts a new one */ +static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_desc *relo) +{ + struct ksym_desc *kdesc; + int i; + + for (i = 0; i < gen->nr_ksyms; i++) { + if (!strcmp(gen->ksyms[i].name, relo->name)) { + gen->ksyms[i].ref++; + return &gen->ksyms[i]; + } + } + kdesc = libbpf_reallocarray(gen->ksyms, gen->nr_ksyms + 1, sizeof(*kdesc)); + if (!kdesc) { + gen->error = -ENOMEM; + return NULL; + } + gen->ksyms = kdesc; + kdesc = &gen->ksyms[gen->nr_ksyms++]; + kdesc->name = relo->name; + kdesc->kind = relo->kind; + kdesc->ref = 1; + kdesc->off = 0; + kdesc->insn = 0; + return kdesc; +} + +/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7} + * Returns result in BPF_REG_7 + */ +static void emit_bpf_find_by_name_kind(struct bpf_gen *gen, struct ksym_relo_desc *relo) +{ + int name_off, len = strlen(relo->name) + 1; + + name_off = add_data(gen, relo->name, len); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, name_off)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind)); + emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind); +} + +/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7} + * Returns result in BPF_REG_7 + * Returns u64 symbol addr in BPF_REG_9 + */ +static void emit_bpf_kallsyms_lookup_name(struct bpf_gen *gen, struct ksym_relo_desc *relo) +{ + int name_off, len = strlen(relo->name) + 1, res_off; + + name_off = add_data(gen, relo->name, len); + res_off = add_data(gen, NULL, 8); /* res is u64 */ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, name_off)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_4, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, res_off)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_4)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_kallsyms_lookup_name)); + emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + debug_ret(gen, "kallsyms_lookup_name(%s,%d)", relo->name, relo->kind); +} + +/* Expects: + * BPF_REG_8 - pointer to instruction + * + * We need to reuse BTF fd for same symbol otherwise each relocation takes a new + * index, while kernel limits total kfunc BTFs to 256. For duplicate symbols, + * this would mean a new BTF fd index for each entry. By pairing symbol name + * with index, we get the insn->imm, insn->off pairing that kernel uses for + * kfunc_tab, which becomes the effective limit even though all of them may + * share same index in fd_array (such that kfunc_btf_tab has 1 element). + */ +static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn) +{ + struct ksym_desc *kdesc; + int btf_fd_idx; + + kdesc = get_ksym_desc(gen, relo); + if (!kdesc) + return; + /* try to copy from existing bpf_insn */ + if (kdesc->ref > 1) { + move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + offsetof(struct bpf_insn, imm)); + move_blob2blob(gen, insn + offsetof(struct bpf_insn, off), 2, + kdesc->insn + offsetof(struct bpf_insn, off)); + goto log; + } + /* remember insn offset, so we can copy BTF ID and FD later */ + kdesc->insn = insn; + emit_bpf_find_by_name_kind(gen, relo); + if (!relo->is_weak) + emit_check_err(gen); + /* get index in fd_array to store BTF FD at */ + btf_fd_idx = add_kfunc_btf_fd(gen); + if (btf_fd_idx > INT16_MAX) { + pr_warn("BTF fd off %d for kfunc %s exceeds INT16_MAX, cannot process relocation\n", + btf_fd_idx, relo->name); + gen->error = -E2BIG; + return; + } + kdesc->off = btf_fd_idx; + /* jump to success case */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + /* set value for imm, off as 0 */ + emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0)); + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip success case for ret < 0 */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 10)); + /* store btf_id into insn[insn_idx].imm */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm))); + /* obtain fd in BPF_REG_9 */ + emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); + /* jump to fd_array store if fd denotes module BTF */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); + /* set the default value for off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip BTF fd store for vmlinux BTF */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); + /* load fd_array slot pointer */ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx))); + /* store BTF fd in slot */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0)); + /* store index into insn[insn_idx].off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx)); +log: + if (!gen->log_level) + return; + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8, + offsetof(struct bpf_insn, imm))); + emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, + offsetof(struct bpf_insn, off))); + debug_regs(gen, BPF_REG_7, BPF_REG_9, " func (%s:count=%d): imm: %%d, off: %%d", + relo->name, kdesc->ref); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_fd_array_off(gen, kdesc->off))); + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_0, 0)); + debug_regs(gen, BPF_REG_9, -1, " func (%s:count=%d): btf_fd", + relo->name, kdesc->ref); +} + +static void emit_ksym_relo_log(struct bpf_gen *gen, struct ksym_relo_desc *relo, + int ref) +{ + if (!gen->log_level) + return; + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8, + offsetof(struct bpf_insn, imm))); + emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, sizeof(struct bpf_insn) + + offsetof(struct bpf_insn, imm))); + debug_regs(gen, BPF_REG_7, BPF_REG_9, " var t=%d w=%d (%s:count=%d): imm[0]: %%d, imm[1]: %%d", + relo->is_typeless, relo->is_weak, relo->name, ref); + emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code))); + debug_regs(gen, BPF_REG_9, -1, " var t=%d w=%d (%s:count=%d): insn.reg", + relo->is_typeless, relo->is_weak, relo->name, ref); +} + +/* Expects: + * BPF_REG_8 - pointer to instruction + */ +static void emit_relo_ksym_typeless(struct bpf_gen *gen, + struct ksym_relo_desc *relo, int insn) +{ + struct ksym_desc *kdesc; + + kdesc = get_ksym_desc(gen, relo); + if (!kdesc) + return; + /* try to copy from existing ldimm64 insn */ + if (kdesc->ref > 1) { + move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + offsetof(struct bpf_insn, imm)); + move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)); + goto log; + } + /* remember insn offset, so we can copy ksym addr later */ + kdesc->insn = insn; + /* skip typeless ksym_desc in fd closing loop in cleanup_relos */ + kdesc->typeless = true; + emit_bpf_kallsyms_lookup_name(gen, relo); + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_7, -ENOENT, 1)); + emit_check_err(gen); + /* store lower half of addr into insn[insn_idx].imm */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9, offsetof(struct bpf_insn, imm))); + /* store upper half of addr into insn[insn_idx + 1].imm */ + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9, + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm))); +log: + emit_ksym_relo_log(gen, relo, kdesc->ref); +} + +static __u32 src_reg_mask(void) +{ +#if defined(__LITTLE_ENDIAN_BITFIELD) + return 0x0f; /* src_reg,dst_reg,... */ +#elif defined(__BIG_ENDIAN_BITFIELD) + return 0xf0; /* dst_reg,src_reg,... */ +#else +#error "Unsupported bit endianness, cannot proceed" +#endif +} + +/* Expects: + * BPF_REG_8 - pointer to instruction + */ +static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn) +{ + struct ksym_desc *kdesc; + __u32 reg_mask; + + kdesc = get_ksym_desc(gen, relo); + if (!kdesc) + return; + /* try to copy from existing ldimm64 insn */ + if (kdesc->ref > 1) { + move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)); + move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + offsetof(struct bpf_insn, imm)); + /* jump over src_reg adjustment if imm (btf_id) is not 0, reuse BPF_REG_0 from move_blob2blob + * If btf_id is zero, clear BPF_PSEUDO_BTF_ID flag in src_reg of ld_imm64 insn + */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3)); + goto clear_src_reg; + } + /* remember insn offset, so we can copy BTF ID and FD later */ + kdesc->insn = insn; + emit_bpf_find_by_name_kind(gen, relo); + if (!relo->is_weak) + emit_check_err(gen); + /* jump to success case */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + /* set values for insn[insn_idx].imm, insn[insn_idx + 1].imm as 0 */ + emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0)); + emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0)); + /* skip success case for ret < 0 */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); + /* store btf_id into insn[insn_idx].imm */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm))); + /* store btf_obj_fd into insn[insn_idx + 1].imm */ + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm))); + /* skip src_reg adjustment */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 3)); +clear_src_reg: + /* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */ + reg_mask = src_reg_mask(); + emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code))); + emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask)); + emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code))); + + emit_ksym_relo_log(gen, relo, kdesc->ref); +} + +void bpf_gen__record_relo_core(struct bpf_gen *gen, + const struct bpf_core_relo *core_relo) +{ + struct bpf_core_relo *relos; + + relos = libbpf_reallocarray(gen->core_relos, gen->core_relo_cnt + 1, sizeof(*relos)); + if (!relos) { + gen->error = -ENOMEM; + return; + } + gen->core_relos = relos; + relos += gen->core_relo_cnt; + memcpy(relos, core_relo, sizeof(*relos)); + gen->core_relo_cnt++; +} + +static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns) +{ + int insn; + + pr_debug("gen: emit_relo (%d): %s at %d\n", relo->kind, relo->name, relo->insn_idx); + insn = insns + sizeof(struct bpf_insn) * relo->insn_idx; + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn)); + switch (relo->kind) { + case BTF_KIND_VAR: + if (relo->is_typeless) + emit_relo_ksym_typeless(gen, relo, insn); + else + emit_relo_ksym_btf(gen, relo, insn); + break; + case BTF_KIND_FUNC: + emit_relo_kfunc_btf(gen, relo, insn); + break; + default: + pr_warn("Unknown relocation kind '%d'\n", relo->kind); + gen->error = -EDOM; + return; + } +} + +static void emit_relos(struct bpf_gen *gen, int insns) +{ + int i; + + for (i = 0; i < gen->relo_cnt; i++) + emit_relo(gen, gen->relos + i, insns); +} + +static void cleanup_core_relo(struct bpf_gen *gen) +{ + if (!gen->core_relo_cnt) + return; + free(gen->core_relos); + gen->core_relo_cnt = 0; + gen->core_relos = NULL; +} + +static void cleanup_relos(struct bpf_gen *gen, int insns) +{ + int i, insn; + + for (i = 0; i < gen->nr_ksyms; i++) { + /* only close fds for typed ksyms and kfuncs */ + if (gen->ksyms[i].kind == BTF_KIND_VAR && !gen->ksyms[i].typeless) { + /* close fd recorded in insn[insn_idx + 1].imm */ + insn = gen->ksyms[i].insn; + insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm); + emit_sys_close_blob(gen, insn); + } else if (gen->ksyms[i].kind == BTF_KIND_FUNC) { + emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off)); + if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ) + gen->nr_fd_array--; + } + } + if (gen->nr_ksyms) { + free(gen->ksyms); + gen->nr_ksyms = 0; + gen->ksyms = NULL; + } + if (gen->relo_cnt) { + free(gen->relos); + gen->relo_cnt = 0; + gen->relos = NULL; + } + cleanup_core_relo(gen); +} + +void bpf_gen__prog_load(struct bpf_gen *gen, + enum bpf_prog_type prog_type, const char *prog_name, + const char *license, struct bpf_insn *insns, size_t insn_cnt, + struct bpf_prog_load_opts *load_attr, int prog_idx) +{ + int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos; + int attr_size = offsetofend(union bpf_attr, core_relo_rec_size); + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n", + prog_type, insn_cnt, prog_idx); + /* add license string to blob of bytes */ + license_off = add_data(gen, license, strlen(license) + 1); + /* add insns to blob of bytes */ + insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn)); + + attr.prog_type = prog_type; + attr.expected_attach_type = load_attr->expected_attach_type; + attr.attach_btf_id = load_attr->attach_btf_id; + attr.prog_ifindex = load_attr->prog_ifindex; + attr.kern_version = 0; + attr.insn_cnt = (__u32)insn_cnt; + attr.prog_flags = load_attr->prog_flags; + + attr.func_info_rec_size = load_attr->func_info_rec_size; + attr.func_info_cnt = load_attr->func_info_cnt; + func_info = add_data(gen, load_attr->func_info, + attr.func_info_cnt * attr.func_info_rec_size); + + attr.line_info_rec_size = load_attr->line_info_rec_size; + attr.line_info_cnt = load_attr->line_info_cnt; + line_info = add_data(gen, load_attr->line_info, + attr.line_info_cnt * attr.line_info_rec_size); + + attr.core_relo_rec_size = sizeof(struct bpf_core_relo); + attr.core_relo_cnt = gen->core_relo_cnt; + core_relos = add_data(gen, gen->core_relos, + attr.core_relo_cnt * attr.core_relo_rec_size); + + libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); + prog_load_attr = add_data(gen, &attr, attr_size); + + /* populate union bpf_attr with a pointer to license */ + emit_rel_store(gen, attr_field(prog_load_attr, license), license_off); + + /* populate union bpf_attr with a pointer to instructions */ + emit_rel_store(gen, attr_field(prog_load_attr, insns), insns_off); + + /* populate union bpf_attr with a pointer to func_info */ + emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info); + + /* populate union bpf_attr with a pointer to line_info */ + emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info); + + /* populate union bpf_attr with a pointer to core_relos */ + emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos); + + /* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */ + emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array); + + /* populate union bpf_attr with user provided log details */ + move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4, + offsetof(struct bpf_loader_ctx, log_level), false); + move_ctx2blob(gen, attr_field(prog_load_attr, log_size), 4, + offsetof(struct bpf_loader_ctx, log_size), false); + move_ctx2blob(gen, attr_field(prog_load_attr, log_buf), 8, + offsetof(struct bpf_loader_ctx, log_buf), false); + /* populate union bpf_attr with btf_fd saved in the stack earlier */ + move_stack2blob(gen, attr_field(prog_load_attr, prog_btf_fd), 4, + stack_off(btf_fd)); + if (gen->attach_kind) { + emit_find_attach_target(gen); + /* populate union bpf_attr with btf_id and btf_obj_fd found by helper */ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, prog_load_attr)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, + offsetof(union bpf_attr, attach_btf_id))); + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, + offsetof(union bpf_attr, attach_btf_obj_fd))); + } + emit_relos(gen, insns_off); + /* emit PROG_LOAD command */ + emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size); + debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt); + /* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */ + cleanup_relos(gen, insns_off); + if (gen->attach_kind) { + emit_sys_close_blob(gen, + attr_field(prog_load_attr, attach_btf_obj_fd)); + gen->attach_kind = 0; + } + emit_check_err(gen); + /* remember prog_fd in the stack, if successful */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, + stack_off(prog_fd[gen->nr_progs]))); + gen->nr_progs++; +} + +void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, + __u32 value_size) +{ + int attr_size = offsetofend(union bpf_attr, flags); + int map_update_attr, value, key; + union bpf_attr attr; + int zero = 0; + + memset(&attr, 0, attr_size); + pr_debug("gen: map_update_elem: idx %d\n", map_idx); + + value = add_data(gen, pvalue, value_size); + key = add_data(gen, &zero, sizeof(zero)); + + /* if (map_desc[map_idx].initial_value) { + * if (ctx->flags & BPF_SKEL_KERNEL) + * bpf_probe_read_kernel(value, value_size, initial_value); + * else + * bpf_copy_from_user(value, value_size, initial_value); + * } + */ + emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * map_idx + + offsetof(struct bpf_map_desc, initial_value))); + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 8)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, value)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size)); + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, + offsetof(struct bpf_loader_ctx, flags))); + emit(gen, BPF_JMP_IMM(BPF_JSET, BPF_REG_0, BPF_SKEL_KERNEL, 2)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user)); + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); + + map_update_attr = add_data(gen, &attr, attr_size); + move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, + blob_fd_array_off(gen, map_idx)); + emit_rel_store(gen, attr_field(map_update_attr, key), key); + emit_rel_store(gen, attr_field(map_update_attr, value), value); + /* emit MAP_UPDATE_ELEM command */ + emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size); + debug_ret(gen, "update_elem idx %d value_size %d", map_idx, value_size); + emit_check_err(gen); +} + +void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slot, + int inner_map_idx) +{ + int attr_size = offsetofend(union bpf_attr, flags); + int map_update_attr, key; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n", + outer_map_idx, slot, inner_map_idx); + + key = add_data(gen, &slot, sizeof(slot)); + + map_update_attr = add_data(gen, &attr, attr_size); + move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, + blob_fd_array_off(gen, outer_map_idx)); + emit_rel_store(gen, attr_field(map_update_attr, key), key); + emit_rel_store(gen, attr_field(map_update_attr, value), + blob_fd_array_off(gen, inner_map_idx)); + + /* emit MAP_UPDATE_ELEM command */ + emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size); + debug_ret(gen, "populate_outer_map outer %d key %d inner %d", + outer_map_idx, slot, inner_map_idx); + emit_check_err(gen); +} + +void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) +{ + int attr_size = offsetofend(union bpf_attr, map_fd); + int map_freeze_attr; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: map_freeze: idx %d\n", map_idx); + map_freeze_attr = add_data(gen, &attr, attr_size); + move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4, + blob_fd_array_off(gen, map_idx)); + /* emit MAP_FREEZE command */ + emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size); + debug_ret(gen, "map_freeze"); + emit_check_err(gen); +} diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c new file mode 100644 index 000000000..aeb09c288 --- /dev/null +++ b/tools/lib/bpf/hashmap.c @@ -0,0 +1,240 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Generic non-thread safe hash map implementation. + * + * Copyright (c) 2019 Facebook + */ +#include <stdint.h> +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <linux/err.h> +#include "hashmap.h" + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +/* prevent accidental re-addition of reallocarray() */ +#pragma GCC poison reallocarray + +/* start with 4 buckets */ +#define HASHMAP_MIN_CAP_BITS 2 + +static void hashmap_add_entry(struct hashmap_entry **pprev, + struct hashmap_entry *entry) +{ + entry->next = *pprev; + *pprev = entry; +} + +static void hashmap_del_entry(struct hashmap_entry **pprev, + struct hashmap_entry *entry) +{ + *pprev = entry->next; + entry->next = NULL; +} + +void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, void *ctx) +{ + map->hash_fn = hash_fn; + map->equal_fn = equal_fn; + map->ctx = ctx; + + map->buckets = NULL; + map->cap = 0; + map->cap_bits = 0; + map->sz = 0; +} + +struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, + void *ctx) +{ + struct hashmap *map = malloc(sizeof(struct hashmap)); + + if (!map) + return ERR_PTR(-ENOMEM); + hashmap__init(map, hash_fn, equal_fn, ctx); + return map; +} + +void hashmap__clear(struct hashmap *map) +{ + struct hashmap_entry *cur, *tmp; + size_t bkt; + + hashmap__for_each_entry_safe(map, cur, tmp, bkt) { + free(cur); + } + free(map->buckets); + map->buckets = NULL; + map->cap = map->cap_bits = map->sz = 0; +} + +void hashmap__free(struct hashmap *map) +{ + if (IS_ERR_OR_NULL(map)) + return; + + hashmap__clear(map); + free(map); +} + +size_t hashmap__size(const struct hashmap *map) +{ + return map->sz; +} + +size_t hashmap__capacity(const struct hashmap *map) +{ + return map->cap; +} + +static bool hashmap_needs_to_grow(struct hashmap *map) +{ + /* grow if empty or more than 75% filled */ + return (map->cap == 0) || ((map->sz + 1) * 4 / 3 > map->cap); +} + +static int hashmap_grow(struct hashmap *map) +{ + struct hashmap_entry **new_buckets; + struct hashmap_entry *cur, *tmp; + size_t new_cap_bits, new_cap; + size_t h, bkt; + + new_cap_bits = map->cap_bits + 1; + if (new_cap_bits < HASHMAP_MIN_CAP_BITS) + new_cap_bits = HASHMAP_MIN_CAP_BITS; + + new_cap = 1UL << new_cap_bits; + new_buckets = calloc(new_cap, sizeof(new_buckets[0])); + if (!new_buckets) + return -ENOMEM; + + hashmap__for_each_entry_safe(map, cur, tmp, bkt) { + h = hash_bits(map->hash_fn(cur->key, map->ctx), new_cap_bits); + hashmap_add_entry(&new_buckets[h], cur); + } + + map->cap = new_cap; + map->cap_bits = new_cap_bits; + free(map->buckets); + map->buckets = new_buckets; + + return 0; +} + +static bool hashmap_find_entry(const struct hashmap *map, + const void *key, size_t hash, + struct hashmap_entry ***pprev, + struct hashmap_entry **entry) +{ + struct hashmap_entry *cur, **prev_ptr; + + if (!map->buckets) + return false; + + for (prev_ptr = &map->buckets[hash], cur = *prev_ptr; + cur; + prev_ptr = &cur->next, cur = cur->next) { + if (map->equal_fn(cur->key, key, map->ctx)) { + if (pprev) + *pprev = prev_ptr; + *entry = cur; + return true; + } + } + + return false; +} + +int hashmap__insert(struct hashmap *map, const void *key, void *value, + enum hashmap_insert_strategy strategy, + const void **old_key, void **old_value) +{ + struct hashmap_entry *entry; + size_t h; + int err; + + if (old_key) + *old_key = NULL; + if (old_value) + *old_value = NULL; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (strategy != HASHMAP_APPEND && + hashmap_find_entry(map, key, h, NULL, &entry)) { + if (old_key) + *old_key = entry->key; + if (old_value) + *old_value = entry->value; + + if (strategy == HASHMAP_SET || strategy == HASHMAP_UPDATE) { + entry->key = key; + entry->value = value; + return 0; + } else if (strategy == HASHMAP_ADD) { + return -EEXIST; + } + } + + if (strategy == HASHMAP_UPDATE) + return -ENOENT; + + if (hashmap_needs_to_grow(map)) { + err = hashmap_grow(map); + if (err) + return err; + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + } + + entry = malloc(sizeof(struct hashmap_entry)); + if (!entry) + return -ENOMEM; + + entry->key = key; + entry->value = value; + hashmap_add_entry(&map->buckets[h], entry); + map->sz++; + + return 0; +} + +bool hashmap__find(const struct hashmap *map, const void *key, void **value) +{ + struct hashmap_entry *entry; + size_t h; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (!hashmap_find_entry(map, key, h, NULL, &entry)) + return false; + + if (value) + *value = entry->value; + return true; +} + +bool hashmap__delete(struct hashmap *map, const void *key, + const void **old_key, void **old_value) +{ + struct hashmap_entry **pprev, *entry; + size_t h; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (!hashmap_find_entry(map, key, h, &pprev, &entry)) + return false; + + if (old_key) + *old_key = entry->key; + if (old_value) + *old_value = entry->value; + + hashmap_del_entry(pprev, entry); + free(entry); + map->sz--; + + return true; +} diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h new file mode 100644 index 000000000..10a4c4cd1 --- /dev/null +++ b/tools/lib/bpf/hashmap.h @@ -0,0 +1,195 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Generic non-thread safe hash map implementation. + * + * Copyright (c) 2019 Facebook + */ +#ifndef __LIBBPF_HASHMAP_H +#define __LIBBPF_HASHMAP_H + +#include <stdbool.h> +#include <stddef.h> +#include <limits.h> + +static inline size_t hash_bits(size_t h, int bits) +{ + /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + +#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) + /* LP64 case */ + return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); +#elif (__SIZEOF_SIZE_T__ <= __SIZEOF_LONG__) + return (h * 2654435769lu) >> (__SIZEOF_LONG__ * 8 - bits); +#else +# error "Unsupported size_t size" +#endif +} + +/* generic C-string hashing function */ +static inline size_t str_hash(const char *s) +{ + size_t h = 0; + + while (*s) { + h = h * 31 + *s; + s++; + } + return h; +} + +typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); +typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx); + +struct hashmap_entry { + const void *key; + void *value; + struct hashmap_entry *next; +}; + +struct hashmap { + hashmap_hash_fn hash_fn; + hashmap_equal_fn equal_fn; + void *ctx; + + struct hashmap_entry **buckets; + size_t cap; + size_t cap_bits; + size_t sz; +}; + +#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \ + .hash_fn = (hash_fn), \ + .equal_fn = (equal_fn), \ + .ctx = (ctx), \ + .buckets = NULL, \ + .cap = 0, \ + .cap_bits = 0, \ + .sz = 0, \ +} + +void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, void *ctx); +struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, + void *ctx); +void hashmap__clear(struct hashmap *map); +void hashmap__free(struct hashmap *map); + +size_t hashmap__size(const struct hashmap *map); +size_t hashmap__capacity(const struct hashmap *map); + +/* + * Hashmap insertion strategy: + * - HASHMAP_ADD - only add key/value if key doesn't exist yet; + * - HASHMAP_SET - add key/value pair if key doesn't exist yet; otherwise, + * update value; + * - HASHMAP_UPDATE - update value, if key already exists; otherwise, do + * nothing and return -ENOENT; + * - HASHMAP_APPEND - always add key/value pair, even if key already exists. + * This turns hashmap into a multimap by allowing multiple values to be + * associated with the same key. Most useful read API for such hashmap is + * hashmap__for_each_key_entry() iteration. If hashmap__find() is still + * used, it will return last inserted key/value entry (first in a bucket + * chain). + */ +enum hashmap_insert_strategy { + HASHMAP_ADD, + HASHMAP_SET, + HASHMAP_UPDATE, + HASHMAP_APPEND, +}; + +/* + * hashmap__insert() adds key/value entry w/ various semantics, depending on + * provided strategy value. If a given key/value pair replaced already + * existing key/value pair, both old key and old value will be returned + * through old_key and old_value to allow calling code do proper memory + * management. + */ +int hashmap__insert(struct hashmap *map, const void *key, void *value, + enum hashmap_insert_strategy strategy, + const void **old_key, void **old_value); + +static inline int hashmap__add(struct hashmap *map, + const void *key, void *value) +{ + return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL); +} + +static inline int hashmap__set(struct hashmap *map, + const void *key, void *value, + const void **old_key, void **old_value) +{ + return hashmap__insert(map, key, value, HASHMAP_SET, + old_key, old_value); +} + +static inline int hashmap__update(struct hashmap *map, + const void *key, void *value, + const void **old_key, void **old_value) +{ + return hashmap__insert(map, key, value, HASHMAP_UPDATE, + old_key, old_value); +} + +static inline int hashmap__append(struct hashmap *map, + const void *key, void *value) +{ + return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL); +} + +bool hashmap__delete(struct hashmap *map, const void *key, + const void **old_key, void **old_value); + +bool hashmap__find(const struct hashmap *map, const void *key, void **value); + +/* + * hashmap__for_each_entry - iterate over all entries in hashmap + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @bkt: integer used as a bucket loop cursor + */ +#define hashmap__for_each_entry(map, cur, bkt) \ + for (bkt = 0; bkt < map->cap; bkt++) \ + for (cur = map->buckets[bkt]; cur; cur = cur->next) + +/* + * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe + * against removals + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @tmp: struct hashmap_entry * used as a temporary next cursor storage + * @bkt: integer used as a bucket loop cursor + */ +#define hashmap__for_each_entry_safe(map, cur, tmp, bkt) \ + for (bkt = 0; bkt < map->cap; bkt++) \ + for (cur = map->buckets[bkt]; \ + cur && ({tmp = cur->next; true; }); \ + cur = tmp) + +/* + * hashmap__for_each_key_entry - iterate over entries associated with given key + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @key: key to iterate entries for + */ +#define hashmap__for_each_key_entry(map, cur, _key) \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ + cur; \ + cur = cur->next) \ + if (map->equal_fn(cur->key, (_key), map->ctx)) + +#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ + cur && ({ tmp = cur->next; true; }); \ + cur = tmp) \ + if (map->equal_fn(cur->key, (_key), map->ctx)) + +#endif /* __LIBBPF_HASHMAP_H */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c new file mode 100644 index 000000000..10f15a3e3 --- /dev/null +++ b/tools/lib/bpf/libbpf.c @@ -0,0 +1,12446 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Common eBPF ELF object loading operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. + * Copyright (C) 2019 Isovalent, Inc. + */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <stdlib.h> +#include <stdio.h> +#include <stdarg.h> +#include <libgen.h> +#include <inttypes.h> +#include <limits.h> +#include <string.h> +#include <unistd.h> +#include <endian.h> +#include <fcntl.h> +#include <errno.h> +#include <ctype.h> +#include <asm/unistd.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/filter.h> +#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 <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" +#include "bpf_gen_internal.h" + +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + +#define BPF_INSN_SZ (sizeof(struct bpf_insn)) + +/* vsprintf() in __base_pr() uses nonliteral format string. It may break + * compilation if user enables corresponding warning. Disable it explicitly. + */ +#pragma GCC diagnostic ignored "-Wformat-nonliteral" + +#define __printf(a, b) __attribute__((format(printf, a, b))) + +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); +static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); + +static const char * const attach_type_name[] = { + [BPF_CGROUP_INET_INGRESS] = "cgroup_inet_ingress", + [BPF_CGROUP_INET_EGRESS] = "cgroup_inet_egress", + [BPF_CGROUP_INET_SOCK_CREATE] = "cgroup_inet_sock_create", + [BPF_CGROUP_INET_SOCK_RELEASE] = "cgroup_inet_sock_release", + [BPF_CGROUP_SOCK_OPS] = "cgroup_sock_ops", + [BPF_CGROUP_DEVICE] = "cgroup_device", + [BPF_CGROUP_INET4_BIND] = "cgroup_inet4_bind", + [BPF_CGROUP_INET6_BIND] = "cgroup_inet6_bind", + [BPF_CGROUP_INET4_CONNECT] = "cgroup_inet4_connect", + [BPF_CGROUP_INET6_CONNECT] = "cgroup_inet6_connect", + [BPF_CGROUP_INET4_POST_BIND] = "cgroup_inet4_post_bind", + [BPF_CGROUP_INET6_POST_BIND] = "cgroup_inet6_post_bind", + [BPF_CGROUP_INET4_GETPEERNAME] = "cgroup_inet4_getpeername", + [BPF_CGROUP_INET6_GETPEERNAME] = "cgroup_inet6_getpeername", + [BPF_CGROUP_INET4_GETSOCKNAME] = "cgroup_inet4_getsockname", + [BPF_CGROUP_INET6_GETSOCKNAME] = "cgroup_inet6_getsockname", + [BPF_CGROUP_UDP4_SENDMSG] = "cgroup_udp4_sendmsg", + [BPF_CGROUP_UDP6_SENDMSG] = "cgroup_udp6_sendmsg", + [BPF_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_CGROUP_UDP4_RECVMSG] = "cgroup_udp4_recvmsg", + [BPF_CGROUP_UDP6_RECVMSG] = "cgroup_udp6_recvmsg", + [BPF_CGROUP_GETSOCKOPT] = "cgroup_getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "cgroup_setsockopt", + [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", + [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", + [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", + [BPF_LIRC_MODE2] = "lirc_mode2", + [BPF_FLOW_DISSECTOR] = "flow_dissector", + [BPF_TRACE_RAW_TP] = "trace_raw_tp", + [BPF_TRACE_FENTRY] = "trace_fentry", + [BPF_TRACE_FEXIT] = "trace_fexit", + [BPF_MODIFY_RETURN] = "modify_return", + [BPF_LSM_MAC] = "lsm_mac", + [BPF_LSM_CGROUP] = "lsm_cgroup", + [BPF_SK_LOOKUP] = "sk_lookup", + [BPF_TRACE_ITER] = "trace_iter", + [BPF_XDP_DEVMAP] = "xdp_devmap", + [BPF_XDP_CPUMAP] = "xdp_cpumap", + [BPF_XDP] = "xdp", + [BPF_SK_REUSEPORT_SELECT] = "sk_reuseport_select", + [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_reuseport_select_or_migrate", + [BPF_PERF_EVENT] = "perf_event", + [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", +}; + +static const char * const link_type_name[] = { + [BPF_LINK_TYPE_UNSPEC] = "unspec", + [BPF_LINK_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_LINK_TYPE_TRACING] = "tracing", + [BPF_LINK_TYPE_CGROUP] = "cgroup", + [BPF_LINK_TYPE_ITER] = "iter", + [BPF_LINK_TYPE_NETNS] = "netns", + [BPF_LINK_TYPE_XDP] = "xdp", + [BPF_LINK_TYPE_PERF_EVENT] = "perf_event", + [BPF_LINK_TYPE_KPROBE_MULTI] = "kprobe_multi", + [BPF_LINK_TYPE_STRUCT_OPS] = "struct_ops", +}; + +static const char * const map_type_name[] = { + [BPF_MAP_TYPE_UNSPEC] = "unspec", + [BPF_MAP_TYPE_HASH] = "hash", + [BPF_MAP_TYPE_ARRAY] = "array", + [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", + [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", + [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", + [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", + [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", + [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", + [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", + [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", + [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", + [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", + [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", + [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", + [BPF_MAP_TYPE_SOCKMAP] = "sockmap", + [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_XSKMAP] = "xskmap", + [BPF_MAP_TYPE_SOCKHASH] = "sockhash", + [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", + [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", + [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", + [BPF_MAP_TYPE_QUEUE] = "queue", + [BPF_MAP_TYPE_STACK] = "stack", + [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", + [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_MAP_TYPE_RINGBUF] = "ringbuf", + [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage", + [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage", + [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", + [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf", +}; + +static const char * const prog_type_name[] = { + [BPF_PROG_TYPE_UNSPEC] = "unspec", + [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", + [BPF_PROG_TYPE_KPROBE] = "kprobe", + [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", + [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", + [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", + [BPF_PROG_TYPE_XDP] = "xdp", + [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", + [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", + [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", + [BPF_PROG_TYPE_LWT_IN] = "lwt_in", + [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", + [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", + [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", + [BPF_PROG_TYPE_SK_SKB] = "sk_skb", + [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", + [BPF_PROG_TYPE_SK_MSG] = "sk_msg", + [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", + [BPF_PROG_TYPE_LWT_SEG6LOCAL] = "lwt_seg6local", + [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", + [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", + [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", + [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", + [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", + [BPF_PROG_TYPE_TRACING] = "tracing", + [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_PROG_TYPE_EXT] = "ext", + [BPF_PROG_TYPE_LSM] = "lsm", + [BPF_PROG_TYPE_SK_LOOKUP] = "sk_lookup", + [BPF_PROG_TYPE_SYSCALL] = "syscall", +}; + +static int __base_pr(enum libbpf_print_level level, const char *format, + va_list args) +{ + if (level == LIBBPF_DEBUG) + return 0; + + return vfprintf(stderr, format, args); +} + +static libbpf_print_fn_t __libbpf_pr = __base_pr; + +libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) +{ + libbpf_print_fn_t old_print_fn = __libbpf_pr; + + __libbpf_pr = fn; + return old_print_fn; +} + +__printf(2, 3) +void libbpf_print(enum libbpf_print_level level, const char *format, ...) +{ + va_list args; + int old_errno; + + if (!__libbpf_pr) + return; + + old_errno = errno; + + va_start(args, format); + __libbpf_pr(level, format, args); + va_end(args); + + errno = old_errno; +} + +static void pr_perm_msg(int err) +{ + 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)); + + 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 +# define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) +#endif + +#ifndef zclose +# define zclose(fd) ({ \ + int ___err = 0; \ + if ((fd) >= 0) \ + ___err = close((fd)); \ + fd = -1; \ + ___err; }) +#endif + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +int libbpf_set_strict_mode(enum libbpf_strict_mode mode) +{ + /* as of v1.0 libbpf_set_strict_mode() is a no-op */ + return 0; +} + +__u32 libbpf_major_version(void) +{ + return LIBBPF_MAJOR_VERSION; +} + +__u32 libbpf_minor_version(void) +{ + return LIBBPF_MINOR_VERSION; +} + +const char *libbpf_version_string(void) +{ +#define __S(X) #X +#define _S(X) __S(X) + return "v" _S(LIBBPF_MAJOR_VERSION) "." _S(LIBBPF_MINOR_VERSION); +#undef _S +#undef __S +} + +enum reloc_type { + RELO_LD64, + RELO_CALL, + RELO_DATA, + RELO_EXTERN_VAR, + RELO_EXTERN_FUNC, + RELO_SUBPROG_ADDR, + RELO_CORE, +}; + +struct reloc_desc { + enum reloc_type type; + int insn_idx; + union { + const struct bpf_core_relo *core_relo; /* used when type == RELO_CORE */ + struct { + int map_idx; + int sym_off; + }; + }; +}; + +/* stored as sec_def->cookie for all libbpf-supported SEC()s */ +enum sec_def_flags { + SEC_NONE = 0, + /* expected_attach_type is optional, if kernel doesn't support that */ + SEC_EXP_ATTACH_OPT = 1, + /* legacy, only used by libbpf_get_type_names() and + * libbpf_attach_type_by_name(), not used by libbpf itself at all. + * This used to be associated with cgroup (and few other) BPF programs + * that were attachable through BPF_PROG_ATTACH command. Pretty + * meaningless nowadays, though. + */ + SEC_ATTACHABLE = 2, + SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT, + /* attachment target is specified through BTF ID in either kernel or + * other BPF program's BTF object */ + SEC_ATTACH_BTF = 4, + /* BPF program type allows sleeping/blocking in kernel */ + SEC_SLEEPABLE = 8, + /* BPF program support non-linear XDP buffer */ + SEC_XDP_FRAGS = 16, +}; + +struct bpf_sec_def { + char *sec; + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + long cookie; + int handler_id; + + libbpf_prog_setup_fn_t prog_setup_fn; + libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; + libbpf_prog_attach_fn_t prog_attach_fn; +}; + +/* + * bpf_prog should be a better name but it has been used in + * linux/filter.h. + */ +struct bpf_program { + char *name; + char *sec_name; + size_t sec_idx; + const struct bpf_sec_def *sec_def; + /* this program's instruction offset (in number of instructions) + * within its containing ELF section + */ + size_t sec_insn_off; + /* number of original instructions in ELF section belonging to this + * program, not taking into account subprogram instructions possible + * appended later during relocation + */ + size_t sec_insn_cnt; + /* Offset (in number of instructions) of the start of instruction + * belonging to this BPF program within its containing main BPF + * program. For the entry-point (main) BPF program, this is always + * zero. For a sub-program, this gets reset before each of main BPF + * programs are processed and relocated and is used to determined + * whether sub-program was already appended to the main program, and + * if yes, at which instruction offset. + */ + size_t sub_insn_off; + + /* instructions that belong to BPF program; insns[0] is located at + * sec_insn_off instruction within its ELF section in ELF file, so + * when mapping ELF file instruction index to the local instruction, + * one needs to subtract sec_insn_off; and vice versa. + */ + struct bpf_insn *insns; + /* actual number of instruction in this BPF program's image; for + * entry-point BPF programs this includes the size of main program + * itself plus all the used sub-programs, appended at the end + */ + size_t insns_cnt; + + struct reloc_desc *reloc_desc; + int nr_reloc; + + /* BPF verifier log settings */ + char *log_buf; + size_t log_size; + __u32 log_level; + + struct bpf_object *obj; + + int fd; + bool autoload; + bool autoattach; + bool mark_btf_static; + enum bpf_prog_type type; + enum bpf_attach_type expected_attach_type; + + int prog_ifindex; + __u32 attach_btf_obj_fd; + __u32 attach_btf_id; + __u32 attach_prog_fd; + + void *func_info; + __u32 func_info_rec_size; + __u32 func_info_cnt; + + void *line_info; + __u32 line_info_rec_size; + __u32 line_info_cnt; + __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 KSYMS_SEC ".ksyms" +#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, +}; + +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; +}; + +struct bpf_map { + struct bpf_object *obj; + char *name; + /* real_name is defined for special internal maps (.rodata*, + * .data*, .bss, .kconfig) and preserves their original ELF section + * name. This is important to be be able to find corresponding BTF + * DATASEC information. + */ + char *real_name; + int fd; + int sec_idx; + size_t sec_offset; + int map_ifindex; + int inner_map_fd; + struct bpf_map_def def; + __u32 numa_node; + __u32 btf_var_idx; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 btf_vmlinux_value_type_id; + enum libbpf_map_type libbpf_type; + void *mmaped; + struct bpf_struct_ops *st_ops; + struct bpf_map *inner_map; + void **init_slots; + int init_slots_sz; + char *pin_path; + bool pinned; + bool reused; + bool autocreate; + __u64 map_extra; +}; + +enum extern_type { + EXT_UNKNOWN, + EXT_KCFG, + EXT_KSYM, +}; + +enum kcfg_type { + KCFG_UNKNOWN, + KCFG_CHAR, + KCFG_BOOL, + KCFG_INT, + KCFG_TRISTATE, + KCFG_CHAR_ARR, +}; + +struct extern_desc { + enum extern_type type; + int sym_idx; + int btf_id; + int sec_btf_id; + const char *name; + bool is_set; + bool is_weak; + union { + struct { + enum kcfg_type type; + int sz; + int align; + int data_off; + bool is_signed; + } kcfg; + struct { + unsigned long long addr; + + /* target btf_id of the corresponding kernel var. */ + int kernel_btf_obj_fd; + int kernel_btf_id; + + /* local btf_id of the ksym extern's type. */ + __u32 type_id; + /* BTF fd index to be patched in for insn->off, this is + * 0 for vmlinux BTF, index in obj->fd_array for module + * BTF + */ + __s16 btf_fd_idx; + } ksym; + }; +}; + +struct module_btf { + struct btf *btf; + char *name; + __u32 id; + int fd; + int fd_array_idx; +}; + +enum sec_type { + SEC_UNUSED = 0, + SEC_RELO, + SEC_BSS, + SEC_DATA, + SEC_RODATA, +}; + +struct elf_sec_desc { + enum sec_type sec_type; + Elf64_Shdr *shdr; + Elf_Data *data; +}; + +struct elf_state { + int fd; + const void *obj_buf; + size_t obj_buf_sz; + Elf *elf; + Elf64_Ehdr *ehdr; + Elf_Data *symbols; + Elf_Data *st_ops_data; + size_t shstrndx; /* section index for section name strings */ + size_t strtabidx; + struct elf_sec_desc *secs; + size_t sec_cnt; + int btf_maps_shndx; + __u32 btf_maps_sec_btf_id; + int text_shndx; + int symbols_shndx; + int st_ops_shndx; +}; + +struct usdt_manager; + +struct bpf_object { + char name[BPF_OBJ_NAME_LEN]; + char license[64]; + __u32 kern_version; + + struct bpf_program *programs; + size_t nr_programs; + struct bpf_map *maps; + size_t nr_maps; + size_t maps_cap; + + char *kconfig; + struct extern_desc *externs; + int nr_extern; + int kconfig_map_idx; + + bool loaded; + bool has_subcalls; + bool has_rodata; + + struct bpf_gen *gen_loader; + + /* Information when doing ELF related work. Only valid if efile.elf is not NULL */ + struct elf_state efile; + + struct btf *btf; + struct btf_ext *btf_ext; + + /* Parse and load BTF vmlinux if any of the programs in the object need + * it at load time. + */ + struct btf *btf_vmlinux; + /* Path to the custom BTF to be used for BPF CO-RE relocations as an + * override for vmlinux BTF. + */ + char *btf_custom_path; + /* vmlinux BTF override for CO-RE relocations */ + struct btf *btf_vmlinux_override; + /* Lazily initialized kernel module BTFs */ + struct module_btf *btf_modules; + bool btf_modules_loaded; + size_t btf_module_cnt; + size_t btf_module_cap; + + /* optional log settings passed to BPF_BTF_LOAD and BPF_PROG_LOAD commands */ + char *log_buf; + size_t log_size; + __u32 log_level; + + int *fd_array; + size_t fd_array_cap; + size_t fd_array_cnt; + + struct usdt_manager *usdt_man; + + char path[]; +}; + +static const char *elf_sym_str(const struct bpf_object *obj, size_t off); +static const char *elf_sec_str(const struct bpf_object *obj, size_t off); +static Elf_Scn *elf_sec_by_idx(const struct bpf_object *obj, size_t idx); +static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name); +static Elf64_Shdr *elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn); +static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn); +static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn); +static Elf64_Sym *elf_sym_by_idx(const struct bpf_object *obj, size_t idx); +static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx); + +void bpf_program__unload(struct bpf_program *prog) +{ + if (!prog) + return; + + zclose(prog->fd); + + zfree(&prog->func_info); + zfree(&prog->line_info); +} + +static void bpf_program__exit(struct bpf_program *prog) +{ + if (!prog) + return; + + bpf_program__unload(prog); + zfree(&prog->name); + zfree(&prog->sec_name); + zfree(&prog->insns); + zfree(&prog->reloc_desc); + + prog->nr_reloc = 0; + prog->insns_cnt = 0; + prog->sec_idx = -1; +} + +static bool insn_is_subprog_call(const struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_JMP && + BPF_OP(insn->code) == BPF_CALL && + BPF_SRC(insn->code) == BPF_K && + insn->src_reg == BPF_PSEUDO_CALL && + insn->dst_reg == 0 && + insn->off == 0; +} + +static bool is_call_insn(const struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_CALL); +} + +static bool insn_is_pseudo_func(struct bpf_insn *insn) +{ + return is_ldimm64_insn(insn) && insn->src_reg == BPF_PSEUDO_FUNC; +} + +static int +bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, + const char *name, size_t sec_idx, const char *sec_name, + size_t sec_off, void *insn_data, size_t insn_data_sz) +{ + if (insn_data_sz == 0 || insn_data_sz % BPF_INSN_SZ || sec_off % BPF_INSN_SZ) { + pr_warn("sec '%s': corrupted program '%s', offset %zu, size %zu\n", + sec_name, name, sec_off, insn_data_sz); + return -EINVAL; + } + + memset(prog, 0, sizeof(*prog)); + prog->obj = obj; + + prog->sec_idx = sec_idx; + prog->sec_insn_off = sec_off / BPF_INSN_SZ; + prog->sec_insn_cnt = insn_data_sz / BPF_INSN_SZ; + /* insns_cnt can later be increased by appending used subprograms */ + prog->insns_cnt = prog->sec_insn_cnt; + + prog->type = BPF_PROG_TYPE_UNSPEC; + prog->fd = -1; + + /* libbpf's convention for SEC("?abc...") is that it's just like + * SEC("abc...") but the corresponding bpf_program starts out with + * autoload set to false. + */ + if (sec_name[0] == '?') { + prog->autoload = false; + /* from now on forget there was ? in section name */ + sec_name++; + } else { + prog->autoload = true; + } + + prog->autoattach = true; + + /* inherit object's log_level */ + prog->log_level = obj->log_level; + + prog->sec_name = strdup(sec_name); + if (!prog->sec_name) + goto errout; + + prog->name = strdup(name); + if (!prog->name) + goto errout; + + prog->insns = malloc(insn_data_sz); + if (!prog->insns) + goto errout; + memcpy(prog->insns, insn_data, insn_data_sz); + + return 0; +errout: + pr_warn("sec '%s': failed to allocate memory for prog '%s'\n", sec_name, name); + bpf_program__exit(prog); + return -ENOMEM; +} + +static int +bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, + const char *sec_name, int sec_idx) +{ + Elf_Data *symbols = obj->efile.symbols; + struct bpf_program *prog, *progs; + void *data = sec_data->d_buf; + size_t sec_sz = sec_data->d_size, sec_off, prog_sz, nr_syms; + int nr_progs, err, i; + const char *name; + Elf64_Sym *sym; + + progs = obj->programs; + nr_progs = obj->nr_programs; + nr_syms = symbols->d_size / sizeof(Elf64_Sym); + sec_off = 0; + + for (i = 0; i < nr_syms; i++) { + sym = elf_sym_by_idx(obj, i); + + if (sym->st_shndx != sec_idx) + continue; + if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) + continue; + + prog_sz = sym->st_size; + sec_off = sym->st_value; + + name = elf_sym_str(obj, sym->st_name); + if (!name) { + pr_warn("sec '%s': failed to get symbol name for offset %zu\n", + sec_name, sec_off); + return -LIBBPF_ERRNO__FORMAT; + } + + if (sec_off + prog_sz > sec_sz) { + pr_warn("sec '%s': program at offset %zu crosses section boundary\n", + sec_name, sec_off); + return -LIBBPF_ERRNO__FORMAT; + } + + if (sec_idx != obj->efile.text_shndx && ELF64_ST_BIND(sym->st_info) == STB_LOCAL) { + pr_warn("sec '%s': program '%s' is static and not supported\n", sec_name, name); + return -ENOTSUP; + } + + pr_debug("sec '%s': found program '%s' at insn offset %zu (%zu bytes), code size %zu insns (%zu bytes)\n", + sec_name, name, sec_off / BPF_INSN_SZ, sec_off, prog_sz / BPF_INSN_SZ, prog_sz); + + progs = libbpf_reallocarray(progs, nr_progs + 1, sizeof(*progs)); + if (!progs) { + /* + * In this case the original obj->programs + * is still valid, so don't need special treat for + * bpf_close_object(). + */ + pr_warn("sec '%s': failed to alloc memory for new program '%s'\n", + sec_name, name); + return -ENOMEM; + } + obj->programs = progs; + + prog = &progs[nr_progs]; + + err = bpf_object__init_prog(obj, prog, name, sec_idx, sec_name, + sec_off, data + sec_off, prog_sz); + if (err) + return err; + + /* if function is a global/weak symbol, but has restricted + * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC + * as static to enable more permissive BPF verification mode + * with more outside context available to BPF verifier + */ + if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL + && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN + || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)) + prog->mark_btf_static = true; + + nr_progs++; + obj->nr_programs = nr_progs; + } + + return 0; +} + +__u32 get_kernel_version(void) +{ + /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, + * but Ubuntu provides /proc/version_signature file, as described at + * https://ubuntu.com/kernel, with an example contents below, which we + * can use to get a proper LINUX_VERSION_CODE. + * + * Ubuntu 5.4.0-12.15-generic 5.4.8 + * + * In the above, 5.4.8 is what kernel is actually expecting, while + * uname() call will return 5.4.0 in info.release. + */ + const char *ubuntu_kver_file = "/proc/version_signature"; + __u32 major, minor, patch; + struct utsname info; + + if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) { + FILE *f; + + f = fopen(ubuntu_kver_file, "r"); + if (f) { + if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) { + fclose(f); + return KERNEL_VERSION(major, minor, patch); + } + fclose(f); + } + /* something went wrong, fall back to uname() approach */ + } + + uname(&info); + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + 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; + + prog = st_ops->progs[i]; + if (!prog) + continue; + + kern_mtype = skip_mods_and_typedefs(kern_btf, + kern_mtype->type, + &kern_mtype_id); + + /* mtype->type must be a func_proto which was + * guaranteed in bpf_object__collect_st_ops_relos(), + * so only check kern_mtype for func_proto here. + */ + if (!btf_is_func_proto(kern_mtype)) { + pr_warn("struct_ops init_kern %s: kernel member %s is not a func ptr\n", + map->name, mname); + return -ENOTSUP; + } + + 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, + 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_warn("alloc memory failed for %s\n", path); + return ERR_PTR(-ENOMEM); + } + + strcpy(obj->path, path); + if (obj_name) { + libbpf_strlcpy(obj->name, obj_name, sizeof(obj->name)); + } else { + /* Using basename() GNU version which doesn't modify arg. */ + libbpf_strlcpy(obj->name, basename((void *)path), sizeof(obj->name)); + end = strchr(obj->name, '.'); + if (end) + *end = 0; + } + + obj->efile.fd = -1; + /* + * Caller of this function should also call + * bpf_object__elf_finish() after data collection to return + * obj_buf to user. If not, we should duplicate the buffer to + * avoid user freeing them before elf finish. + */ + obj->efile.obj_buf = obj_buf; + obj->efile.obj_buf_sz = obj_buf_sz; + obj->efile.btf_maps_shndx = -1; + obj->efile.st_ops_shndx = -1; + obj->kconfig_map_idx = -1; + + obj->kern_version = get_kernel_version(); + obj->loaded = false; + + return obj; +} + +static void bpf_object__elf_finish(struct bpf_object *obj) +{ + if (!obj->efile.elf) + return; + + elf_end(obj->efile.elf); + obj->efile.elf = NULL; + obj->efile.symbols = NULL; + obj->efile.st_ops_data = NULL; + + zfree(&obj->efile.secs); + obj->efile.sec_cnt = 0; + zclose(obj->efile.fd); + obj->efile.obj_buf = NULL; + obj->efile.obj_buf_sz = 0; +} + +static int bpf_object__elf_init(struct bpf_object *obj) +{ + Elf64_Ehdr *ehdr; + int err = 0; + Elf *elf; + + if (obj->efile.elf) { + pr_warn("elf: init internal error\n"); + return -LIBBPF_ERRNO__LIBELF; + } + + if (obj->efile.obj_buf_sz > 0) { + /* obj_buf should have been validated by bpf_object__open_mem(). */ + elf = elf_memory((char *)obj->efile.obj_buf, obj->efile.obj_buf_sz); + } else { + obj->efile.fd = open(obj->path, O_RDONLY | O_CLOEXEC); + if (obj->efile.fd < 0) { + char errmsg[STRERR_BUFSIZE], *cp; + + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("elf: failed to open %s: %s\n", obj->path, cp); + return err; + } + + elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL); + } + + if (!elf) { + pr_warn("elf: failed to open %s as ELF file: %s\n", obj->path, elf_errmsg(-1)); + err = -LIBBPF_ERRNO__LIBELF; + goto errout; + } + + obj->efile.elf = elf; + + if (elf_kind(elf) != ELF_K_ELF) { + err = -LIBBPF_ERRNO__FORMAT; + pr_warn("elf: '%s' is not a proper ELF object\n", obj->path); + goto errout; + } + + if (gelf_getclass(elf) != ELFCLASS64) { + err = -LIBBPF_ERRNO__FORMAT; + pr_warn("elf: '%s' is not a 64-bit ELF object\n", obj->path); + goto errout; + } + + obj->efile.ehdr = ehdr = elf64_getehdr(elf); + if (!obj->efile.ehdr) { + pr_warn("elf: failed to get ELF header from %s: %s\n", obj->path, elf_errmsg(-1)); + err = -LIBBPF_ERRNO__FORMAT; + goto errout; + } + + if (elf_getshdrstrndx(elf, &obj->efile.shstrndx)) { + pr_warn("elf: failed to get section names section index for %s: %s\n", + obj->path, elf_errmsg(-1)); + err = -LIBBPF_ERRNO__FORMAT; + goto errout; + } + + /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + if (!elf_rawdata(elf_getscn(elf, obj->efile.shstrndx), NULL)) { + pr_warn("elf: failed to get section names strings from %s: %s\n", + obj->path, elf_errmsg(-1)); + err = -LIBBPF_ERRNO__FORMAT; + goto errout; + } + + /* Old LLVM set e_machine to EM_NONE */ + if (ehdr->e_type != ET_REL || (ehdr->e_machine && ehdr->e_machine != EM_BPF)) { + pr_warn("elf: %s is not a valid eBPF object file\n", obj->path); + err = -LIBBPF_ERRNO__FORMAT; + goto errout; + } + + return 0; +errout: + bpf_object__elf_finish(obj); + return err; +} + +static int bpf_object__check_endianness(struct bpf_object *obj) +{ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + return 0; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + return 0; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + pr_warn("elf: endianness mismatch in %s.\n", obj->path); + return -LIBBPF_ERRNO__ENDIAN; +} + +static int +bpf_object__init_license(struct bpf_object *obj, void *data, size_t size) +{ + if (!data) { + pr_warn("invalid license section in %s\n", obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + /* libbpf_strlcpy() only copies first N - 1 bytes, so size + 1 won't + * go over allowed ELF data section buffer + */ + libbpf_strlcpy(obj->license, data, min(size + 1, sizeof(obj->license))); + pr_debug("license of %s is %s\n", obj->path, obj->license); + return 0; +} + +static int +bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size) +{ + __u32 kver; + + if (!data || size != sizeof(kver)) { + pr_warn("invalid kver section in %s\n", obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + memcpy(&kver, data, sizeof(kver)); + obj->kern_version = kver; + pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version); + return 0; +} + +static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) +{ + if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS || + type == BPF_MAP_TYPE_HASH_OF_MAPS) + return true; + return false; +} + +static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32 *size) +{ + Elf_Data *data; + Elf_Scn *scn; + + if (!name) + return -EINVAL; + + scn = elf_sec_by_name(obj, name); + data = elf_sec_data(obj, scn); + if (data) { + *size = data->d_size; + return 0; /* found it */ + } + + return -ENOENT; +} + +static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off) +{ + Elf_Data *symbols = obj->efile.symbols; + const char *sname; + size_t si; + + if (!name || !off) + return -EINVAL; + + for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) { + Elf64_Sym *sym = elf_sym_by_idx(obj, si); + + if (ELF64_ST_TYPE(sym->st_info) != STT_OBJECT) + continue; + + if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && + ELF64_ST_BIND(sym->st_info) != STB_WEAK) + continue; + + sname = elf_sym_str(obj, sym->st_name); + if (!sname) { + pr_warn("failed to get sym name string for var %s\n", name); + return -EIO; + } + if (strcmp(name, sname) == 0) { + *off = sym->st_value; + return 0; + } + } + + return -ENOENT; +} + +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) +{ + struct bpf_map *map; + int err; + + err = libbpf_ensure_mem((void **)&obj->maps, &obj->maps_cap, + sizeof(*obj->maps), obj->nr_maps + 1); + if (err) + return ERR_PTR(err); + + map = &obj->maps[obj->nr_maps++]; + map->obj = obj; + map->fd = -1; + map->inner_map_fd = -1; + map->autocreate = true; + + return map; +} + +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, const char *real_name) +{ + char map_name[BPF_OBJ_NAME_LEN], *p; + int pfx_len, sfx_len = max((size_t)7, strlen(real_name)); + + /* This is one of the more confusing parts of libbpf for various + * reasons, some of which are historical. The original idea for naming + * internal names was to include as much of BPF object name prefix as + * possible, so that it can be distinguished from similar internal + * maps of a different BPF object. + * As an example, let's say we have bpf_object named 'my_object_name' + * and internal map corresponding to '.rodata' ELF section. The final + * map name advertised to user and to the kernel will be + * 'my_objec.rodata', taking first 8 characters of object name and + * entire 7 characters of '.rodata'. + * Somewhat confusingly, if internal map ELF section name is shorter + * than 7 characters, e.g., '.bss', we still reserve 7 characters + * for the suffix, even though we only have 4 actual characters, and + * resulting map will be called 'my_objec.bss', not even using all 15 + * characters allowed by the kernel. Oh well, at least the truncated + * object name is somewhat consistent in this case. But if the map + * name is '.kconfig', we'll still have entirety of '.kconfig' added + * (8 chars) and thus will be left with only first 7 characters of the + * object name ('my_obje'). Happy guessing, user, that the final map + * name will be "my_obje.kconfig". + * Now, with libbpf starting to support arbitrarily named .rodata.* + * and .data.* data sections, it's possible that ELF section name is + * longer than allowed 15 chars, so we now need to be careful to take + * only up to 15 first characters of ELF name, taking no BPF object + * name characters at all. So '.rodata.abracadabra' will result in + * '.rodata.abracad' kernel and user-visible name. + * We need to keep this convoluted logic intact for .data, .bss and + * .rodata maps, but for new custom .data.custom and .rodata.custom + * maps we use their ELF names as is, not prepending bpf_object name + * in front. We still need to truncate them to 15 characters for the + * kernel. Full name can be recovered for such maps by using DATASEC + * BTF type associated with such map's value type, though. + */ + if (sfx_len >= BPF_OBJ_NAME_LEN) + sfx_len = BPF_OBJ_NAME_LEN - 1; + + /* if there are two or more dots in map name, it's a custom dot map */ + if (strchr(real_name + 1, '.') != NULL) + pfx_len = 0; + else + 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, real_name); + + /* sanitise map name to characters allowed by kernel */ + for (p = map_name; *p && p < map_name + sizeof(map_name); p++) + if (!isalnum(*p) && *p != '_' && *p != '.') + *p = '_'; + + return strdup(map_name); +} + +static int +bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map); + +static int +bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, + const char *real_name, int sec_idx, void *data, size_t data_sz) +{ + struct bpf_map_def *def; + struct bpf_map *map; + int err; + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map->libbpf_type = type; + map->sec_idx = sec_idx; + map->sec_offset = 0; + map->real_name = strdup(real_name); + map->name = internal_map_name(obj, real_name); + if (!map->real_name || !map->name) { + zfree(&map->real_name); + zfree(&map->name); + return -ENOMEM; + } + + def = &map->def; + def->type = BPF_MAP_TYPE_ARRAY; + def->key_size = sizeof(int); + def->value_size = data_sz; + def->max_entries = 1; + def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG + ? BPF_F_RDONLY_PROG : 0; + 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->real_name); + zfree(&map->name); + return err; + } + + /* failures are fine because of maps like .rodata.str1.1 */ + (void) bpf_map_find_btf_info(obj, map); + + if (data) + memcpy(map->mmaped, data, data_sz); + + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); + return 0; +} + +static int bpf_object__init_global_data_maps(struct bpf_object *obj) +{ + struct elf_sec_desc *sec_desc; + const char *sec_name; + int err = 0, sec_idx; + + /* + * Populate obj->maps with libbpf internal maps. + */ + for (sec_idx = 1; sec_idx < obj->efile.sec_cnt; sec_idx++) { + sec_desc = &obj->efile.secs[sec_idx]; + + /* Skip recognized sections with size 0. */ + if (!sec_desc->data || sec_desc->data->d_size == 0) + continue; + + switch (sec_desc->sec_type) { + case SEC_DATA: + sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, + sec_name, sec_idx, + sec_desc->data->d_buf, + sec_desc->data->d_size); + break; + case SEC_RODATA: + obj->has_rodata = true; + sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, + sec_name, sec_idx, + sec_desc->data->d_buf, + sec_desc->data->d_size); + break; + case SEC_BSS: + sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, + sec_name, sec_idx, + NULL, + sec_desc->data->d_size); + break; + default: + /* skip */ + break; + } + 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_kcfg_value_tri(struct extern_desc *ext, void *ext_val, + char value) +{ + switch (ext->kcfg.type) { + case KCFG_BOOL: + if (value == 'm') { + pr_warn("extern (kcfg) '%s': value '%c' implies tristate or char type\n", + ext->name, value); + return -EINVAL; + } + *(bool *)ext_val = value == 'y' ? true : false; + break; + case KCFG_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 KCFG_CHAR: + *(char *)ext_val = value; + break; + case KCFG_UNKNOWN: + case KCFG_INT: + case KCFG_CHAR_ARR: + default: + pr_warn("extern (kcfg) '%s': value '%c' implies bool, tristate, or char type\n", + ext->name, value); + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val, + const char *value) +{ + size_t len; + + if (ext->kcfg.type != KCFG_CHAR_ARR) { + pr_warn("extern (kcfg) '%s': value '%s' implies char array type\n", + ext->name, value); + return -EINVAL; + } + + len = strlen(value); + if (value[len - 1] != '"') { + pr_warn("extern (kcfg) '%s': invalid string config '%s'\n", + ext->name, value); + return -EINVAL; + } + + /* strip quotes */ + len -= 2; + if (len >= ext->kcfg.sz) { + pr_warn("extern (kcfg) '%s': long string '%s' of (%zu bytes) truncated to %d bytes\n", + ext->name, value, len, ext->kcfg.sz - 1); + len = ext->kcfg.sz - 1; + } + 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_kcfg_value_in_range(const struct extern_desc *ext, __u64 v) +{ + int bit_sz = ext->kcfg.sz * 8; + + if (ext->kcfg.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->kcfg.is_signed) + return v + (1ULL << (bit_sz - 1)) < (1ULL << bit_sz); + else + return (v >> bit_sz) == 0; +} + +static int set_kcfg_value_num(struct extern_desc *ext, void *ext_val, + __u64 value) +{ + if (ext->kcfg.type != KCFG_INT && ext->kcfg.type != KCFG_CHAR && + ext->kcfg.type != KCFG_BOOL) { + pr_warn("extern (kcfg) '%s': value '%llu' implies integer, char, or boolean type\n", + ext->name, (unsigned long long)value); + return -EINVAL; + } + if (ext->kcfg.type == KCFG_BOOL && value > 1) { + pr_warn("extern (kcfg) '%s': value '%llu' isn't boolean compatible\n", + ext->name, (unsigned long long)value); + return -EINVAL; + + } + if (!is_kcfg_value_in_range(ext, value)) { + pr_warn("extern (kcfg) '%s': value '%llu' doesn't fit in %d bytes\n", + ext->name, (unsigned long long)value, ext->kcfg.sz); + return -ERANGE; + } + switch (ext->kcfg.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 (!str_has_pfx(buf, "CONFIG_")) + 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->kcfg.data_off; + value = sep + 1; + + switch (*value) { + case 'y': case 'n': case 'm': + err = set_kcfg_value_tri(ext, ext_val, *value); + break; + case '"': + err = set_kcfg_value_str(ext, ext_val, value); + break; + default: + /* assume integer */ + err = parse_u64(value, &num); + if (err) { + pr_warn("extern (kcfg) '%s': value '%s' isn't a valid integer\n", ext->name, value); + return err; + } + if (ext->kcfg.type != KCFG_INT && ext->kcfg.type != KCFG_CHAR) { + pr_warn("extern (kcfg) '%s': value '%s' implies integer type\n", ext->name, value); + return -EINVAL; + } + err = set_kcfg_value_num(ext, ext_val, num); + break; + } + if (err) + return err; + pr_debug("extern (kcfg) '%s': set to %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 = NULL, *ext; + size_t map_sz; + int i, err; + + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (ext->type == EXT_KCFG) + last_ext = ext; + } + + if (!last_ext) + return 0; + + map_sz = last_ext->kcfg.data_off + last_ext->kcfg.sz; + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG, + ".kconfig", obj->efile.symbols_shndx, + NULL, map_sz); + if (err) + return err; + + obj->kconfig_map_idx = obj->nr_maps - 1; + + return 0; +} + +const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + + if (res_id) + *res_id = id; + + while (btf_is_mod(t) || btf_is_typedef(t)) { + if (res_id) + *res_id = t->type; + t = btf__type_by_id(btf, t->type); + } + + return t; +} + +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; +} + +static const char *__btf_kind_str(__u16 kind) +{ + switch (kind) { + case BTF_KIND_UNKN: return "void"; + case BTF_KIND_INT: return "int"; + case BTF_KIND_PTR: return "ptr"; + case BTF_KIND_ARRAY: return "array"; + case BTF_KIND_STRUCT: return "struct"; + case BTF_KIND_UNION: return "union"; + case BTF_KIND_ENUM: return "enum"; + case BTF_KIND_FWD: return "fwd"; + case BTF_KIND_TYPEDEF: return "typedef"; + case BTF_KIND_VOLATILE: return "volatile"; + case BTF_KIND_CONST: return "const"; + case BTF_KIND_RESTRICT: return "restrict"; + case BTF_KIND_FUNC: return "func"; + case BTF_KIND_FUNC_PROTO: return "func_proto"; + case BTF_KIND_VAR: return "var"; + case BTF_KIND_DATASEC: return "datasec"; + case BTF_KIND_FLOAT: return "float"; + case BTF_KIND_DECL_TAG: return "decl_tag"; + case BTF_KIND_TYPE_TAG: return "type_tag"; + case BTF_KIND_ENUM64: return "enum64"; + default: return "unknown"; + } +} + +const char *btf_kind_str(const struct btf_type *t) +{ + return __btf_kind_str(btf_kind(t)); +} + +/* + * Fetch integer attribute of BTF map definition. Such attributes are + * represented using a pointer to an array, in which dimensionality of array + * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY]; + * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF + * type definition, while using only sizeof(void *) space in ELF data section. + */ +static bool get_map_field_int(const char *map_name, const struct btf *btf, + const struct btf_member *m, __u32 *res) +{ + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL); + const char *name = btf__name_by_offset(btf, m->name_off); + const struct btf_array *arr_info; + const struct btf_type *arr_t; + + if (!btf_is_ptr(t)) { + pr_warn("map '%s': attr '%s': expected PTR, got %s.\n", + map_name, name, btf_kind_str(t)); + return false; + } + + arr_t = btf__type_by_id(btf, t->type); + if (!arr_t) { + pr_warn("map '%s': attr '%s': type [%u] not found.\n", + map_name, name, t->type); + return false; + } + if (!btf_is_array(arr_t)) { + pr_warn("map '%s': attr '%s': expected ARRAY, got %s.\n", + map_name, name, btf_kind_str(arr_t)); + return false; + } + arr_info = btf_array(arr_t); + *res = arr_info->nelems; + return true; +} + +static int pathname_concat(char *buf, size_t buf_sz, const char *path, const char *name) +{ + int len; + + len = snprintf(buf, buf_sz, "%s/%s", path, name); + if (len < 0) + return -EINVAL; + if (len >= buf_sz) + return -ENAMETOOLONG; + + return 0; +} + +static int build_map_pin_path(struct bpf_map *map, const char *path) +{ + char buf[PATH_MAX]; + int err; + + if (!path) + path = "/sys/fs/bpf"; + + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) + return err; + + return bpf_map__set_pin_path(map, buf); +} + +/* should match definition in bpf_helpers.h */ +enum libbpf_pin_type { + LIBBPF_PIN_NONE, + /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ + LIBBPF_PIN_BY_NAME, +}; + +int parse_btf_map_def(const char *map_name, struct btf *btf, + const struct btf_type *def_t, bool strict, + struct btf_map_def *map_def, struct btf_map_def *inner_def) +{ + const struct btf_type *t; + const struct btf_member *m; + bool is_inner = inner_def == NULL; + int vlen, i; + + vlen = btf_vlen(def_t); + m = btf_members(def_t); + for (i = 0; i < vlen; i++, m++) { + const char *name = btf__name_by_offset(btf, m->name_off); + + if (!name) { + pr_warn("map '%s': invalid field #%d.\n", map_name, i); + return -EINVAL; + } + if (strcmp(name, "type") == 0) { + if (!get_map_field_int(map_name, btf, m, &map_def->map_type)) + return -EINVAL; + map_def->parts |= MAP_DEF_MAP_TYPE; + } else if (strcmp(name, "max_entries") == 0) { + if (!get_map_field_int(map_name, btf, m, &map_def->max_entries)) + return -EINVAL; + map_def->parts |= MAP_DEF_MAX_ENTRIES; + } else if (strcmp(name, "map_flags") == 0) { + if (!get_map_field_int(map_name, btf, m, &map_def->map_flags)) + return -EINVAL; + map_def->parts |= MAP_DEF_MAP_FLAGS; + } else if (strcmp(name, "numa_node") == 0) { + if (!get_map_field_int(map_name, btf, m, &map_def->numa_node)) + return -EINVAL; + map_def->parts |= MAP_DEF_NUMA_NODE; + } else if (strcmp(name, "key_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, btf, m, &sz)) + return -EINVAL; + if (map_def->key_size && map_def->key_size != sz) { + pr_warn("map '%s': conflicting key size %u != %u.\n", + map_name, map_def->key_size, sz); + return -EINVAL; + } + map_def->key_size = sz; + map_def->parts |= MAP_DEF_KEY_SIZE; + } else if (strcmp(name, "key") == 0) { + __s64 sz; + + t = btf__type_by_id(btf, m->type); + if (!t) { + pr_warn("map '%s': key type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (!btf_is_ptr(t)) { + pr_warn("map '%s': key spec is not PTR: %s.\n", + map_name, btf_kind_str(t)); + return -EINVAL; + } + sz = btf__resolve_size(btf, t->type); + if (sz < 0) { + pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); + return sz; + } + if (map_def->key_size && 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; + map_def->key_type_id = t->type; + map_def->parts |= MAP_DEF_KEY_SIZE | MAP_DEF_KEY_TYPE; + } else if (strcmp(name, "value_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, btf, m, &sz)) + return -EINVAL; + if (map_def->value_size && map_def->value_size != sz) { + pr_warn("map '%s': conflicting value size %u != %u.\n", + map_name, map_def->value_size, sz); + return -EINVAL; + } + map_def->value_size = sz; + map_def->parts |= MAP_DEF_VALUE_SIZE; + } else if (strcmp(name, "value") == 0) { + __s64 sz; + + t = btf__type_by_id(btf, m->type); + if (!t) { + pr_warn("map '%s': value type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (!btf_is_ptr(t)) { + pr_warn("map '%s': value spec is not PTR: %s.\n", + map_name, btf_kind_str(t)); + return -EINVAL; + } + sz = btf__resolve_size(btf, t->type); + if (sz < 0) { + pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); + return sz; + } + if (map_def->value_size && 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_def->value_type_id = t->type; + map_def->parts |= MAP_DEF_VALUE_SIZE | MAP_DEF_VALUE_TYPE; + } + else if (strcmp(name, "values") == 0) { + bool is_map_in_map = bpf_map_type__is_map_in_map(map_def->map_type); + bool is_prog_array = map_def->map_type == BPF_MAP_TYPE_PROG_ARRAY; + const char *desc = is_map_in_map ? "map-in-map inner" : "prog-array value"; + char inner_map_name[128]; + int err; + + if (is_inner) { + pr_warn("map '%s': multi-level inner maps not supported.\n", + map_name); + return -ENOTSUP; + } + if (i != vlen - 1) { + pr_warn("map '%s': '%s' member should be last.\n", + map_name, name); + return -EINVAL; + } + if (!is_map_in_map && !is_prog_array) { + pr_warn("map '%s': should be map-in-map or prog-array.\n", + map_name); + return -ENOTSUP; + } + if (map_def->value_size && map_def->value_size != 4) { + pr_warn("map '%s': conflicting value size %u != 4.\n", + map_name, map_def->value_size); + return -EINVAL; + } + map_def->value_size = 4; + t = btf__type_by_id(btf, m->type); + if (!t) { + pr_warn("map '%s': %s type [%d] not found.\n", + map_name, desc, m->type); + return -EINVAL; + } + if (!btf_is_array(t) || btf_array(t)->nelems) { + pr_warn("map '%s': %s spec is not a zero-sized array.\n", + map_name, desc); + return -EINVAL; + } + t = skip_mods_and_typedefs(btf, btf_array(t)->type, NULL); + if (!btf_is_ptr(t)) { + pr_warn("map '%s': %s def is of unexpected kind %s.\n", + map_name, desc, btf_kind_str(t)); + return -EINVAL; + } + t = skip_mods_and_typedefs(btf, t->type, NULL); + if (is_prog_array) { + if (!btf_is_func_proto(t)) { + pr_warn("map '%s': prog-array value def is of unexpected kind %s.\n", + map_name, btf_kind_str(t)); + return -EINVAL; + } + continue; + } + if (!btf_is_struct(t)) { + pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", + map_name, btf_kind_str(t)); + return -EINVAL; + } + + snprintf(inner_map_name, sizeof(inner_map_name), "%s.inner", map_name); + err = parse_btf_map_def(inner_map_name, btf, t, strict, inner_def, NULL); + if (err) + return err; + + map_def->parts |= MAP_DEF_INNER_MAP; + } else if (strcmp(name, "pinning") == 0) { + __u32 val; + + if (is_inner) { + pr_warn("map '%s': inner def can't be pinned.\n", map_name); + return -EINVAL; + } + if (!get_map_field_int(map_name, btf, m, &val)) + return -EINVAL; + if (val != LIBBPF_PIN_NONE && val != LIBBPF_PIN_BY_NAME) { + pr_warn("map '%s': invalid pinning value %u.\n", + map_name, val); + return -EINVAL; + } + map_def->pinning = val; + map_def->parts |= MAP_DEF_PINNING; + } else if (strcmp(name, "map_extra") == 0) { + __u32 map_extra; + + if (!get_map_field_int(map_name, btf, m, &map_extra)) + return -EINVAL; + map_def->map_extra = map_extra; + map_def->parts |= MAP_DEF_MAP_EXTRA; + } else { + if (strict) { + pr_warn("map '%s': unknown field '%s'.\n", map_name, name); + return -ENOTSUP; + } + pr_debug("map '%s': ignoring unknown field '%s'.\n", map_name, name); + } + } + + if (map_def->map_type == BPF_MAP_TYPE_UNSPEC) { + pr_warn("map '%s': map type isn't specified.\n", map_name); + return -EINVAL; + } + + return 0; +} + +static size_t adjust_ringbuf_sz(size_t sz) +{ + __u32 page_sz = sysconf(_SC_PAGE_SIZE); + __u32 mul; + + /* if user forgot to set any size, make sure they see error */ + if (sz == 0) + return 0; + /* Kernel expects BPF_MAP_TYPE_RINGBUF's max_entries to be + * a power-of-2 multiple of kernel's page size. If user diligently + * satisified these conditions, pass the size through. + */ + if ((sz % page_sz) == 0 && is_pow_of_2(sz / page_sz)) + return sz; + + /* Otherwise find closest (page_sz * power_of_2) product bigger than + * user-set size to satisfy both user size request and kernel + * requirements and substitute correct max_entries for map creation. + */ + for (mul = 1; mul <= UINT_MAX / page_sz; mul <<= 1) { + if (mul * page_sz > sz) + return mul * page_sz; + } + + /* if it's impossible to satisfy the conditions (i.e., user size is + * very close to UINT_MAX but is not a power-of-2 multiple of + * page_size) then just return original size and let kernel reject it + */ + return sz; +} + +static bool map_is_ringbuf(const struct bpf_map *map) +{ + return map->def.type == BPF_MAP_TYPE_RINGBUF || + map->def.type == BPF_MAP_TYPE_USER_RINGBUF; +} + +static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def) +{ + map->def.type = def->map_type; + map->def.key_size = def->key_size; + map->def.value_size = def->value_size; + map->def.max_entries = def->max_entries; + map->def.map_flags = def->map_flags; + map->map_extra = def->map_extra; + + map->numa_node = def->numa_node; + map->btf_key_type_id = def->key_type_id; + map->btf_value_type_id = def->value_type_id; + + /* auto-adjust BPF ringbuf map max_entries to be a multiple of page size */ + if (map_is_ringbuf(map)) + map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries); + + if (def->parts & MAP_DEF_MAP_TYPE) + pr_debug("map '%s': found type = %u.\n", map->name, def->map_type); + + if (def->parts & MAP_DEF_KEY_TYPE) + pr_debug("map '%s': found key [%u], sz = %u.\n", + map->name, def->key_type_id, def->key_size); + else if (def->parts & MAP_DEF_KEY_SIZE) + pr_debug("map '%s': found key_size = %u.\n", map->name, def->key_size); + + if (def->parts & MAP_DEF_VALUE_TYPE) + pr_debug("map '%s': found value [%u], sz = %u.\n", + map->name, def->value_type_id, def->value_size); + else if (def->parts & MAP_DEF_VALUE_SIZE) + pr_debug("map '%s': found value_size = %u.\n", map->name, def->value_size); + + if (def->parts & MAP_DEF_MAX_ENTRIES) + pr_debug("map '%s': found max_entries = %u.\n", map->name, def->max_entries); + if (def->parts & MAP_DEF_MAP_FLAGS) + pr_debug("map '%s': found map_flags = 0x%x.\n", map->name, def->map_flags); + if (def->parts & MAP_DEF_MAP_EXTRA) + pr_debug("map '%s': found map_extra = 0x%llx.\n", map->name, + (unsigned long long)def->map_extra); + if (def->parts & MAP_DEF_PINNING) + pr_debug("map '%s': found pinning = %u.\n", map->name, def->pinning); + if (def->parts & MAP_DEF_NUMA_NODE) + pr_debug("map '%s': found numa_node = %u.\n", map->name, def->numa_node); + + if (def->parts & MAP_DEF_INNER_MAP) + pr_debug("map '%s': found inner map definition.\n", map->name); +} + +static const char *btf_var_linkage_str(__u32 linkage) +{ + switch (linkage) { + case BTF_VAR_STATIC: return "static"; + case BTF_VAR_GLOBAL_ALLOCATED: return "global"; + case BTF_VAR_GLOBAL_EXTERN: return "extern"; + default: return "unknown"; + } +} + +static int bpf_object__init_user_btf_map(struct bpf_object *obj, + const struct btf_type *sec, + int var_idx, int sec_idx, + const Elf_Data *data, bool strict, + const char *pin_root_path) +{ + struct btf_map_def map_def = {}, inner_def = {}; + const struct btf_type *var, *def; + const struct btf_var_secinfo *vi; + const struct btf_var *var_extra; + const char *map_name; + struct bpf_map *map; + int err; + + vi = btf_var_secinfos(sec) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = btf_var(var); + map_name = btf__name_by_offset(obj->btf, var->name_off); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warn("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warn("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (!btf_is_var(var)) { + pr_warn("map '%s': unexpected var kind %s.\n", + map_name, btf_kind_str(var)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED) { + pr_warn("map '%s': unsupported map linkage %s.\n", + map_name, btf_var_linkage_str(var_extra->linkage)); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { + pr_warn("map '%s': unexpected def kind %s.\n", + map_name, btf_kind_str(var)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warn("map '%s': invalid def size.\n", map_name); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("map '%s': failed to alloc map name.\n", map_name); + return -ENOMEM; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->def.type = BPF_MAP_TYPE_UNSPEC; + map->sec_idx = sec_idx; + map->sec_offset = vi->offset; + map->btf_var_idx = var_idx; + pr_debug("map '%s': at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + + err = parse_btf_map_def(map->name, obj->btf, def, strict, &map_def, &inner_def); + if (err) + return err; + + fill_map_from_def(map, &map_def); + + if (map_def.pinning == 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; + } + } + + if (map_def.parts & MAP_DEF_INNER_MAP) { + map->inner_map = calloc(1, sizeof(*map->inner_map)); + if (!map->inner_map) + return -ENOMEM; + map->inner_map->fd = -1; + map->inner_map->sec_idx = sec_idx; + map->inner_map->name = malloc(strlen(map_name) + sizeof(".inner") + 1); + if (!map->inner_map->name) + return -ENOMEM; + sprintf(map->inner_map->name, "%s.inner", map_name); + + fill_map_from_def(map->inner_map, &inner_def); + } + + err = bpf_map_find_btf_info(obj, map); + if (err) + return err; + + return 0; +} + +static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, + const char *pin_root_path) +{ + const struct btf_type *sec = NULL; + int nr_types, i, vlen, err; + const struct btf_type *t; + const char *name; + Elf_Data *data; + Elf_Scn *scn; + + if (obj->efile.btf_maps_shndx < 0) + return 0; + + scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx); + data = elf_sec_data(obj, scn); + if (!scn || !data) { + pr_warn("elf: failed to get %s map definitions for %s\n", + MAPS_ELF_SEC, obj->path); + return -EINVAL; + } + + nr_types = btf__type_cnt(obj->btf); + for (i = 1; i < nr_types; i++) { + t = btf__type_by_id(obj->btf, i); + if (!btf_is_datasec(t)) + continue; + name = btf__name_by_offset(obj->btf, t->name_off); + if (strcmp(name, MAPS_ELF_SEC) == 0) { + sec = t; + obj->efile.btf_maps_sec_btf_id = i; + break; + } + } + + if (!sec) { + pr_warn("DATASEC '%s' not found.\n", MAPS_ELF_SEC); + return -ENOENT; + } + + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++) { + err = bpf_object__init_user_btf_map(obj, sec, i, + obj->efile.btf_maps_shndx, + data, strict, + pin_root_path); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_maps(struct bpf_object *obj, + const struct bpf_object_open_opts *opts) +{ + const char *pin_root_path; + bool strict; + int err = 0; + + strict = !OPTS_GET(opts, relaxed_maps, false); + pin_root_path = OPTS_GET(opts, pin_root_path, NULL); + + err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + err = 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); + + return err; +} + +static bool section_have_execinstr(struct bpf_object *obj, int idx) +{ + Elf64_Shdr *sh; + + sh = elf_sec_hdr(obj, elf_sec_by_idx(obj, idx)); + if (!sh) + return false; + + return sh->sh_flags & SHF_EXECINSTR; +} + +static bool btf_needs_sanitization(struct bpf_object *obj) +{ + bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); + bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); + bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); + bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); + bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); + bool has_enum64 = kernel_supports(obj, FEAT_BTF_ENUM64); + + return !has_func || !has_datasec || !has_func_global || !has_float || + !has_decl_tag || !has_type_tag || !has_enum64; +} + +static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) +{ + bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); + bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); + bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); + bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); + bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); + bool has_enum64 = kernel_supports(obj, FEAT_BTF_ENUM64); + int enum64_placeholder_id = 0; + struct btf_type *t; + int i, j, vlen; + + for (i = 1; i < btf__type_cnt(btf); i++) { + t = (struct btf_type *)btf__type_by_id(btf, i); + + if ((!has_datasec && btf_is_var(t)) || (!has_decl_tag && btf_is_decl_tag(t))) { + /* replace VAR/DECL_TAG with INT */ + t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); + /* + * using size = 1 is the safest choice, 4 will be too + * big and cause kernel BTF validation failure if + * original variable took less than 4 bytes + */ + t->size = 1; + *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8); + } else if (!has_datasec && btf_is_datasec(t)) { + /* replace DATASEC with STRUCT */ + const struct btf_var_secinfo *v = btf_var_secinfos(t); + struct btf_member *m = btf_members(t); + struct btf_type *vt; + char *name; + + name = (char *)btf__name_by_offset(btf, t->name_off); + while (*name) { + if (*name == '.') + *name = '_'; + name++; + } + + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen); + for (j = 0; j < vlen; j++, v++, m++) { + /* order of field assignments is important */ + m->offset = v->offset * 8; + m->type = v->type; + /* preserve variable name as member name */ + vt = (void *)btf__type_by_id(btf, v->type); + m->name_off = vt->name_off; + } + } else if (!has_func && btf_is_func_proto(t)) { + /* replace FUNC_PROTO with ENUM */ + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); + t->size = sizeof(__u32); /* kernel enforced */ + } else if (!has_func && btf_is_func(t)) { + /* replace FUNC with TYPEDEF */ + t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); + } 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); + } else if (!has_float && btf_is_float(t)) { + /* replace FLOAT with an equally-sized empty STRUCT; + * since C compilers do not accept e.g. "float" as a + * valid struct name, make it anonymous + */ + t->name_off = 0; + t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0); + } else if (!has_type_tag && btf_is_type_tag(t)) { + /* replace TYPE_TAG with a CONST */ + t->name_off = 0; + t->info = BTF_INFO_ENC(BTF_KIND_CONST, 0, 0); + } else if (!has_enum64 && btf_is_enum(t)) { + /* clear the kflag */ + t->info = btf_type_info(btf_kind(t), btf_vlen(t), false); + } else if (!has_enum64 && btf_is_enum64(t)) { + /* replace ENUM64 with a union */ + struct btf_member *m; + + if (enum64_placeholder_id == 0) { + enum64_placeholder_id = btf__add_int(btf, "enum64_placeholder", 1, 0); + if (enum64_placeholder_id < 0) + return enum64_placeholder_id; + + t = (struct btf_type *)btf__type_by_id(btf, i); + } + + m = btf_members(t); + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_UNION, 0, vlen); + for (j = 0; j < vlen; j++, m++) { + m->type = enum64_placeholder_id; + m->offset = 0; + } + } + } + + return 0; +} + +static bool libbpf_needs_btf(const struct bpf_object *obj) +{ + return obj->efile.btf_maps_shndx >= 0 || + obj->efile.st_ops_shndx >= 0 || + obj->nr_extern > 0; +} + +static bool kernel_needs_btf(const struct bpf_object *obj) +{ + return obj->efile.st_ops_shndx >= 0; +} + +static int bpf_object__init_btf(struct bpf_object *obj, + Elf_Data *btf_data, + Elf_Data *btf_ext_data) +{ + int err = -ENOENT; + + if (btf_data) { + obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); + err = libbpf_get_error(obj->btf); + if (err) { + obj->btf = NULL; + pr_warn("Error loading ELF section %s: %d.\n", BTF_ELF_SEC, err); + goto out; + } + /* enforce 8-byte pointers for BPF-targeted BTFs */ + btf__set_pointer_size(obj->btf, 8); + } + if (btf_ext_data) { + struct btf_ext_info *ext_segs[3]; + int seg_num, sec_num; + + if (!obj->btf) { + pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", + BTF_EXT_ELF_SEC, BTF_ELF_SEC); + goto out; + } + obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); + err = libbpf_get_error(obj->btf_ext); + if (err) { + pr_warn("Error loading ELF section %s: %d. Ignored and continue.\n", + BTF_EXT_ELF_SEC, err); + obj->btf_ext = NULL; + goto out; + } + + /* setup .BTF.ext to ELF section mapping */ + ext_segs[0] = &obj->btf_ext->func_info; + ext_segs[1] = &obj->btf_ext->line_info; + ext_segs[2] = &obj->btf_ext->core_relo_info; + for (seg_num = 0; seg_num < ARRAY_SIZE(ext_segs); seg_num++) { + struct btf_ext_info *seg = ext_segs[seg_num]; + const struct btf_ext_info_sec *sec; + const char *sec_name; + Elf_Scn *scn; + + if (seg->sec_cnt == 0) + continue; + + seg->sec_idxs = calloc(seg->sec_cnt, sizeof(*seg->sec_idxs)); + if (!seg->sec_idxs) { + err = -ENOMEM; + goto out; + } + + sec_num = 0; + for_each_btf_ext_sec(seg, sec) { + /* preventively increment index to avoid doing + * this before every continue below + */ + sec_num++; + + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) + continue; + scn = elf_sec_by_name(obj, sec_name); + if (!scn) + continue; + + seg->sec_idxs[sec_num - 1] = elf_ndxscn(scn); + } + } + } +out: + if (err && libbpf_needs_btf(obj)) { + pr_warn("BTF is required, but is missing or corrupted.\n"); + return err; + } + return 0; +} + +static int compare_vsi_off(const void *_a, const void *_b) +{ + const struct btf_var_secinfo *a = _a; + const struct btf_var_secinfo *b = _b; + + return a->offset - b->offset; +} + +static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, + struct btf_type *t) +{ + __u32 size = 0, off = 0, i, vars = btf_vlen(t); + const char *name = btf__name_by_offset(btf, t->name_off); + const struct btf_type *t_var; + struct btf_var_secinfo *vsi; + const struct btf_var *var; + int ret; + + if (!name) { + pr_debug("No name found in string section for DATASEC kind.\n"); + return -ENOENT; + } + + /* .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 = find_elf_sec_sz(obj, name, &size); + if (ret || !size) { + pr_debug("Invalid size for section %s: %u bytes\n", name, size); + return -ENOENT; + } + + t->size = size; + + for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + if (!t_var || !btf_is_var(t_var)) { + pr_debug("Non-VAR type seen in section %s\n", name); + return -EINVAL; + } + + var = btf_var(t_var); + if (var->linkage == BTF_VAR_STATIC) + continue; + + name = btf__name_by_offset(btf, t_var->name_off); + if (!name) { + pr_debug("No name found in string section for VAR kind\n"); + return -ENOENT; + } + + ret = find_elf_var_offset(obj, name, &off); + if (ret) { + pr_debug("No offset found in symbol table for VAR %s\n", + name); + return -ENOENT; + } + + vsi->offset = off; + } + +sort_vars: + qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off); + return 0; +} + +static int btf_finalize_data(struct bpf_object *obj, struct btf *btf) +{ + int err = 0; + __u32 i, n = btf__type_cnt(btf); + + for (i = 1; i < n; i++) { + struct btf_type *t = btf_type_by_id(btf, i); + + /* Loader needs to fix up some of the things compiler + * couldn't get its hands on while emitting BTF. This + * is section size and global variable offset. We use + * the info from the ELF itself for this purpose. + */ + if (btf_is_datasec(t)) { + err = btf_fixup_datasec(obj, btf, t); + if (err) + break; + } + } + + return libbpf_err(err); +} + +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) { + pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); + return err; + } + + return 0; +} + +static bool prog_needs_vmlinux_btf(struct bpf_program *prog) +{ + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS || + prog->type == BPF_PROG_TYPE_LSM) + 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 bool obj_needs_vmlinux_btf(const struct bpf_object *obj) +{ + struct bpf_program *prog; + int i; + + /* CO-RE relocations need kernel BTF, only when btf_custom_path + * is not specified + */ + if (obj->btf_ext && obj->btf_ext->core_relo_info.len && !obj->btf_custom_path) + return true; + + /* Support for typed ksyms needs kernel BTF */ + for (i = 0; i < obj->nr_extern; i++) { + const struct extern_desc *ext; + + ext = &obj->externs[i]; + if (ext->type == EXT_KSYM && ext->ksym.type_id) + return true; + } + + bpf_object__for_each_program(prog, obj) { + if (!prog->autoload) + continue; + if (prog_needs_vmlinux_btf(prog)) + return true; + } + + return false; +} + +static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force) +{ + int err; + + /* btf_vmlinux could be loaded earlier */ + if (obj->btf_vmlinux || obj->gen_loader) + return 0; + + if (!force && !obj_needs_vmlinux_btf(obj)) + return 0; + + obj->btf_vmlinux = btf__load_vmlinux_btf(); + err = libbpf_get_error(obj->btf_vmlinux); + if (err) { + pr_warn("Error loading vmlinux BTF: %d\n", err); + obj->btf_vmlinux = NULL; + return err; + } + return 0; +} + +static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) +{ + struct btf *kern_btf = obj->btf; + bool btf_mandatory, sanitize; + int i, err = 0; + + if (!obj->btf) + return 0; + + if (!kernel_supports(obj, FEAT_BTF)) { + if (kernel_needs_btf(obj)) { + err = -EOPNOTSUPP; + goto report; + } + pr_debug("Kernel doesn't support BTF, skipping uploading it.\n"); + return 0; + } + + /* Even though some subprogs are global/weak, user might prefer more + * permissive BPF verification process that BPF verifier performs for + * static functions, taking into account more context from the caller + * functions. In such case, they need to mark such subprogs with + * __attribute__((visibility("hidden"))) and libbpf will adjust + * corresponding FUNC BTF type to be marked as static and trigger more + * involved BPF verification process. + */ + for (i = 0; i < obj->nr_programs; i++) { + struct bpf_program *prog = &obj->programs[i]; + struct btf_type *t; + const char *name; + int j, n; + + if (!prog->mark_btf_static || !prog_is_subprog(obj, prog)) + continue; + + n = btf__type_cnt(obj->btf); + for (j = 1; j < n; j++) { + t = btf_type_by_id(obj->btf, j); + if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) + continue; + + name = btf__str_by_offset(obj->btf, t->name_off); + if (strcmp(name, prog->name) != 0) + continue; + + t->info = btf_type_info(BTF_KIND_FUNC, BTF_FUNC_STATIC, 0); + break; + } + } + + sanitize = btf_needs_sanitization(obj); + if (sanitize) { + const void *raw_data; + __u32 sz; + + /* clone BTF to sanitize a copy and leave the original intact */ + raw_data = btf__raw_data(obj->btf, &sz); + kern_btf = btf__new(raw_data, sz); + err = libbpf_get_error(kern_btf); + if (err) + return err; + + /* enforce 8-byte pointers for BPF-targeted BTFs */ + btf__set_pointer_size(obj->btf, 8); + err = bpf_object__sanitize_btf(obj, kern_btf); + if (err) + return err; + } + + if (obj->gen_loader) { + __u32 raw_size = 0; + const void *raw_data = btf__raw_data(kern_btf, &raw_size); + + if (!raw_data) + return -ENOMEM; + bpf_gen__load_btf(obj->gen_loader, raw_data, raw_size); + /* Pretend to have valid FD to pass various fd >= 0 checks. + * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. + */ + btf__set_fd(kern_btf, 0); + } else { + /* currently BPF_BTF_LOAD only supports log_level 1 */ + err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size, + obj->log_level ? 1 : 0); + } + if (sanitize) { + if (!err) { + /* move fd to libbpf's BTF */ + btf__set_fd(obj->btf, btf__fd(kern_btf)); + btf__set_fd(kern_btf, -1); + } + btf__free(kern_btf); + } +report: + if (err) { + btf_mandatory = kernel_needs_btf(obj); + pr_warn("Error loading .BTF into kernel: %d. %s\n", err, + btf_mandatory ? "BTF is mandatory, can't proceed." + : "BTF is optional, ignoring."); + if (!btf_mandatory) + err = 0; + } + return err; +} + +static const char *elf_sym_str(const struct bpf_object *obj, size_t off) +{ + const char *name; + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, off); + if (!name) { + pr_warn("elf: failed to get section name string at offset %zu from %s: %s\n", + off, obj->path, elf_errmsg(-1)); + return NULL; + } + + return name; +} + +static const char *elf_sec_str(const struct bpf_object *obj, size_t off) +{ + const char *name; + + name = elf_strptr(obj->efile.elf, obj->efile.shstrndx, off); + if (!name) { + pr_warn("elf: failed to get section name string at offset %zu from %s: %s\n", + off, obj->path, elf_errmsg(-1)); + return NULL; + } + + return name; +} + +static Elf_Scn *elf_sec_by_idx(const struct bpf_object *obj, size_t idx) +{ + Elf_Scn *scn; + + scn = elf_getscn(obj->efile.elf, idx); + if (!scn) { + pr_warn("elf: failed to get section(%zu) from %s: %s\n", + idx, obj->path, elf_errmsg(-1)); + return NULL; + } + return scn; +} + +static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name) +{ + Elf_Scn *scn = NULL; + Elf *elf = obj->efile.elf; + const char *sec_name; + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + sec_name = elf_sec_name(obj, scn); + if (!sec_name) + return NULL; + + if (strcmp(sec_name, name) != 0) + continue; + + return scn; + } + return NULL; +} + +static Elf64_Shdr *elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn) +{ + Elf64_Shdr *shdr; + + if (!scn) + return NULL; + + shdr = elf64_getshdr(scn); + if (!shdr) { + pr_warn("elf: failed to get section(%zu) header from %s: %s\n", + elf_ndxscn(scn), obj->path, elf_errmsg(-1)); + return NULL; + } + + return shdr; +} + +static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn) +{ + const char *name; + Elf64_Shdr *sh; + + if (!scn) + return NULL; + + sh = elf_sec_hdr(obj, scn); + if (!sh) + return NULL; + + name = elf_sec_str(obj, sh->sh_name); + if (!name) { + pr_warn("elf: failed to get section(%zu) name from %s: %s\n", + elf_ndxscn(scn), obj->path, elf_errmsg(-1)); + return NULL; + } + + return name; +} + +static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn) +{ + Elf_Data *data; + + if (!scn) + return NULL; + + data = elf_getdata(scn, 0); + if (!data) { + pr_warn("elf: failed to get section(%zu) %s data from %s: %s\n", + elf_ndxscn(scn), elf_sec_name(obj, scn) ?: "<?>", + obj->path, elf_errmsg(-1)); + return NULL; + } + + return data; +} + +static Elf64_Sym *elf_sym_by_idx(const struct bpf_object *obj, size_t idx) +{ + if (idx >= obj->efile.symbols->d_size / sizeof(Elf64_Sym)) + return NULL; + + return (Elf64_Sym *)obj->efile.symbols->d_buf + idx; +} + +static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx) +{ + if (idx >= data->d_size / sizeof(Elf64_Rel)) + return NULL; + + return (Elf64_Rel *)data->d_buf + idx; +} + +static bool is_sec_name_dwarf(const char *name) +{ + /* approximation, but the actual list is too long */ + return str_has_pfx(name, ".debug_"); +} + +static bool ignore_elf_section(Elf64_Shdr *hdr, const char *name) +{ + /* no special handling of .strtab */ + if (hdr->sh_type == SHT_STRTAB) + return true; + + /* ignore .llvm_addrsig section as well */ + if (hdr->sh_type == SHT_LLVM_ADDRSIG) + return true; + + /* no subprograms will lead to an empty .text section, ignore it */ + if (hdr->sh_type == SHT_PROGBITS && hdr->sh_size == 0 && + strcmp(name, ".text") == 0) + return true; + + /* DWARF sections */ + if (is_sec_name_dwarf(name)) + return true; + + if (str_has_pfx(name, ".rel")) { + name += sizeof(".rel") - 1; + /* DWARF section relocations */ + if (is_sec_name_dwarf(name)) + return true; + + /* .BTF and .BTF.ext don't need relocations */ + if (strcmp(name, BTF_ELF_SEC) == 0 || + strcmp(name, BTF_EXT_ELF_SEC) == 0) + return true; + } + + return false; +} + +static int cmp_progs(const void *_a, const void *_b) +{ + const struct bpf_program *a = _a; + const struct bpf_program *b = _b; + + if (a->sec_idx != b->sec_idx) + return a->sec_idx < b->sec_idx ? -1 : 1; + + /* sec_insn_off can't be the same within the section */ + return a->sec_insn_off < b->sec_insn_off ? -1 : 1; +} + +static int bpf_object__elf_collect(struct bpf_object *obj) +{ + struct elf_sec_desc *sec_desc; + Elf *elf = obj->efile.elf; + Elf_Data *btf_ext_data = NULL; + Elf_Data *btf_data = NULL; + int idx = 0, err = 0; + const char *name; + Elf_Data *data; + Elf_Scn *scn; + Elf64_Shdr *sh; + + /* ELF section indices are 0-based, but sec #0 is special "invalid" + * section. Since section count retrieved by elf_getshdrnum() does + * include sec #0, it is already the necessary size of an array to keep + * all the sections. + */ + if (elf_getshdrnum(obj->efile.elf, &obj->efile.sec_cnt)) { + pr_warn("elf: failed to get the number of sections for %s: %s\n", + obj->path, elf_errmsg(-1)); + return -LIBBPF_ERRNO__FORMAT; + } + obj->efile.secs = calloc(obj->efile.sec_cnt, sizeof(*obj->efile.secs)); + if (!obj->efile.secs) + return -ENOMEM; + + /* a bunch of ELF parsing functionality depends on processing symbols, + * so do the first pass and find the symbol table + */ + scn = NULL; + while ((scn = elf_nextscn(elf, scn)) != NULL) { + sh = elf_sec_hdr(obj, scn); + if (!sh) + return -LIBBPF_ERRNO__FORMAT; + + if (sh->sh_type == SHT_SYMTAB) { + if (obj->efile.symbols) { + pr_warn("elf: multiple symbol tables in %s\n", obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + data = elf_sec_data(obj, scn); + if (!data) + return -LIBBPF_ERRNO__FORMAT; + + idx = elf_ndxscn(scn); + + obj->efile.symbols = data; + obj->efile.symbols_shndx = idx; + obj->efile.strtabidx = sh->sh_link; + } + } + + if (!obj->efile.symbols) { + pr_warn("elf: couldn't find symbol table in %s, stripped object file?\n", + obj->path); + return -ENOENT; + } + + scn = NULL; + while ((scn = elf_nextscn(elf, scn)) != NULL) { + idx = elf_ndxscn(scn); + sec_desc = &obj->efile.secs[idx]; + + sh = elf_sec_hdr(obj, scn); + if (!sh) + return -LIBBPF_ERRNO__FORMAT; + + name = elf_sec_str(obj, sh->sh_name); + if (!name) + return -LIBBPF_ERRNO__FORMAT; + + if (ignore_elf_section(sh, name)) + continue; + + data = elf_sec_data(obj, scn); + if (!data) + return -LIBBPF_ERRNO__FORMAT; + + pr_debug("elf: section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", + idx, name, (unsigned long)data->d_size, + (int)sh->sh_link, (unsigned long)sh->sh_flags, + (int)sh->sh_type); + + if (strcmp(name, "license") == 0) { + err = bpf_object__init_license(obj, data->d_buf, data->d_size); + if (err) + return err; + } else if (strcmp(name, "version") == 0) { + err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); + if (err) + return err; + } else if (strcmp(name, "maps") == 0) { + pr_warn("elf: legacy map definitions in 'maps' section are not supported by libbpf v1.0+\n"); + return -ENOTSUP; + } else if (strcmp(name, MAPS_ELF_SEC) == 0) { + obj->efile.btf_maps_shndx = idx; + } else if (strcmp(name, BTF_ELF_SEC) == 0) { + if (sh->sh_type != SHT_PROGBITS) + return -LIBBPF_ERRNO__FORMAT; + btf_data = data; + } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { + if (sh->sh_type != SHT_PROGBITS) + return -LIBBPF_ERRNO__FORMAT; + btf_ext_data = data; + } else if (sh->sh_type == SHT_SYMTAB) { + /* already processed during the first pass above */ + } 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_programs(obj, data, name, idx); + if (err) + return err; + } else if (strcmp(name, DATA_SEC) == 0 || + str_has_pfx(name, DATA_SEC ".")) { + sec_desc->sec_type = SEC_DATA; + sec_desc->shdr = sh; + sec_desc->data = data; + } else if (strcmp(name, RODATA_SEC) == 0 || + str_has_pfx(name, RODATA_SEC ".")) { + sec_desc->sec_type = SEC_RODATA; + sec_desc->shdr = sh; + sec_desc->data = data; + } else if (strcmp(name, STRUCT_OPS_SEC) == 0) { + obj->efile.st_ops_data = data; + obj->efile.st_ops_shndx = idx; + } else { + pr_info("elf: skipping unrecognized data section(%d) %s\n", + idx, name); + } + } else if (sh->sh_type == SHT_REL) { + int targ_sec_idx = sh->sh_info; /* points to other section */ + + if (sh->sh_entsize != sizeof(Elf64_Rel) || + targ_sec_idx >= obj->efile.sec_cnt) + return -LIBBPF_ERRNO__FORMAT; + + /* Only do relo for section with exec instructions */ + if (!section_have_execinstr(obj, targ_sec_idx) && + strcmp(name, ".rel" STRUCT_OPS_SEC) && + strcmp(name, ".rel" MAPS_ELF_SEC)) { + pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n", + idx, name, targ_sec_idx, + elf_sec_name(obj, elf_sec_by_idx(obj, targ_sec_idx)) ?: "<?>"); + continue; + } + + sec_desc->sec_type = SEC_RELO; + sec_desc->shdr = sh; + sec_desc->data = data; + } else if (sh->sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) { + sec_desc->sec_type = SEC_BSS; + sec_desc->shdr = sh; + sec_desc->data = data; + } else { + pr_info("elf: skipping section(%d) %s (size %zu)\n", idx, name, + (size_t)sh->sh_size); + } + } + + if (!obj->efile.strtabidx || obj->efile.strtabidx > idx) { + pr_warn("elf: symbol strings section missing or invalid in %s\n", obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + /* sort BPF programs by section name and in-section instruction offset + * for faster search */ + if (obj->nr_programs) + qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs); + + return bpf_object__init_btf(obj, btf_data, btf_ext_data); +} + +static bool sym_is_extern(const Elf64_Sym *sym) +{ + int bind = ELF64_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) && + ELF64_ST_TYPE(sym->st_info) == STT_NOTYPE; +} + +static bool sym_is_subprog(const Elf64_Sym *sym, int text_shndx) +{ + int bind = ELF64_ST_BIND(sym->st_info); + int type = ELF64_ST_TYPE(sym->st_info); + + /* in .text section */ + if (sym->st_shndx != text_shndx) + return false; + + /* local function */ + if (bind == STB_LOCAL && type == STT_SECTION) + return true; + + /* global function */ + return bind == STB_GLOBAL && type == STT_FUNC; +} + +static int find_extern_btf_id(const struct btf *btf, const char *ext_name) +{ + const struct btf_type *t; + const char *tname; + int i, n; + + if (!btf) + return -ESRCH; + + n = btf__type_cnt(btf); + for (i = 1; i < n; i++) { + t = btf__type_by_id(btf, i); + + if (!btf_is_var(t) && !btf_is_func(t)) + continue; + + tname = btf__name_by_offset(btf, t->name_off); + if (strcmp(tname, ext_name)) + continue; + + if (btf_is_var(t) && + btf_var(t)->linkage != BTF_VAR_GLOBAL_EXTERN) + return -EINVAL; + + if (btf_is_func(t) && btf_func_linkage(t) != BTF_FUNC_EXTERN) + return -EINVAL; + + return i; + } + + return -ENOENT; +} + +static int find_extern_sec_btf_id(struct btf *btf, int ext_btf_id) { + const struct btf_var_secinfo *vs; + const struct btf_type *t; + int i, j, n; + + if (!btf) + return -ESRCH; + + n = btf__type_cnt(btf); + for (i = 1; i < n; i++) { + t = btf__type_by_id(btf, i); + + if (!btf_is_datasec(t)) + continue; + + vs = btf_var_secinfos(t); + for (j = 0; j < btf_vlen(t); j++, vs++) { + if (vs->type == ext_btf_id) + return i; + } + } + + return -ENOENT; +} + +static enum kcfg_type find_kcfg_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 ? KCFG_BOOL : KCFG_UNKNOWN; + if (is_signed) + *is_signed = enc & BTF_INT_SIGNED; + if (t->size == 1) + return KCFG_CHAR; + if (t->size < 1 || t->size > 8 || (t->size & (t->size - 1))) + return KCFG_UNKNOWN; + return KCFG_INT; + } + case BTF_KIND_ENUM: + if (t->size != 4) + return KCFG_UNKNOWN; + if (strcmp(name, "libbpf_tristate")) + return KCFG_UNKNOWN; + return KCFG_TRISTATE; + case BTF_KIND_ENUM64: + if (strcmp(name, "libbpf_tristate")) + return KCFG_UNKNOWN; + return KCFG_TRISTATE; + case BTF_KIND_ARRAY: + if (btf_array(t)->nelems == 0) + return KCFG_UNKNOWN; + if (find_kcfg_type(btf, btf_array(t)->type, NULL) != KCFG_CHAR) + return KCFG_UNKNOWN; + return KCFG_CHAR_ARR; + default: + return KCFG_UNKNOWN; + } +} + +static int cmp_externs(const void *_a, const void *_b) +{ + const struct extern_desc *a = _a; + const struct extern_desc *b = _b; + + if (a->type != b->type) + return a->type < b->type ? -1 : 1; + + if (a->type == EXT_KCFG) { + /* descending order by alignment requirements */ + if (a->kcfg.align != b->kcfg.align) + return a->kcfg.align > b->kcfg.align ? -1 : 1; + /* ascending order by size, within same alignment class */ + if (a->kcfg.sz != b->kcfg.sz) + return a->kcfg.sz < b->kcfg.sz ? -1 : 1; + } + + /* resolve ties by name */ + return strcmp(a->name, b->name); +} + +static int find_int_btf_id(const struct btf *btf) +{ + const struct btf_type *t; + int i, n; + + n = btf__type_cnt(btf); + for (i = 1; i < n; i++) { + t = btf__type_by_id(btf, i); + + if (btf_is_int(t) && btf_int_bits(t) == 32) + return i; + } + + return 0; +} + +static int add_dummy_ksym_var(struct btf *btf) +{ + int i, int_btf_id, sec_btf_id, dummy_var_btf_id; + const struct btf_var_secinfo *vs; + const struct btf_type *sec; + + if (!btf) + return 0; + + sec_btf_id = btf__find_by_name_kind(btf, KSYMS_SEC, + BTF_KIND_DATASEC); + if (sec_btf_id < 0) + return 0; + + sec = btf__type_by_id(btf, sec_btf_id); + vs = btf_var_secinfos(sec); + for (i = 0; i < btf_vlen(sec); i++, vs++) { + const struct btf_type *vt; + + vt = btf__type_by_id(btf, vs->type); + if (btf_is_func(vt)) + break; + } + + /* No func in ksyms sec. No need to add dummy var. */ + if (i == btf_vlen(sec)) + return 0; + + int_btf_id = find_int_btf_id(btf); + dummy_var_btf_id = btf__add_var(btf, + "dummy_ksym", + BTF_VAR_GLOBAL_ALLOCATED, + int_btf_id); + if (dummy_var_btf_id < 0) + pr_warn("cannot create a dummy_ksym var\n"); + + return dummy_var_btf_id; +} + +static int bpf_object__collect_externs(struct bpf_object *obj) +{ + struct btf_type *sec, *kcfg_sec = NULL, *ksym_sec = NULL; + const struct btf_type *t; + struct extern_desc *ext; + int i, n, off, dummy_var_btf_id; + const char *ext_name, *sec_name; + Elf_Scn *scn; + Elf64_Shdr *sh; + + if (!obj->efile.symbols) + return 0; + + scn = elf_sec_by_idx(obj, obj->efile.symbols_shndx); + sh = elf_sec_hdr(obj, scn); + if (!sh || sh->sh_entsize != sizeof(Elf64_Sym)) + return -LIBBPF_ERRNO__FORMAT; + + dummy_var_btf_id = add_dummy_ksym_var(obj->btf); + if (dummy_var_btf_id < 0) + return dummy_var_btf_id; + + n = sh->sh_size / sh->sh_entsize; + pr_debug("looking for externs among %d symbols...\n", n); + + for (i = 0; i < n; i++) { + Elf64_Sym *sym = elf_sym_by_idx(obj, i); + + if (!sym) + return -LIBBPF_ERRNO__FORMAT; + if (!sym_is_extern(sym)) + continue; + ext_name = elf_sym_str(obj, sym->st_name); + if (!ext_name || !ext_name[0]) + continue; + + ext = obj->externs; + ext = libbpf_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 = ELF64_ST_BIND(sym->st_info) == STB_WEAK; + + ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id); + if (ext->sec_btf_id <= 0) { + pr_warn("failed to find BTF for extern '%s' [%d] section: %d\n", + ext_name, ext->btf_id, ext->sec_btf_id); + return ext->sec_btf_id; + } + sec = (void *)btf__type_by_id(obj->btf, ext->sec_btf_id); + sec_name = btf__name_by_offset(obj->btf, sec->name_off); + + if (strcmp(sec_name, KCONFIG_SEC) == 0) { + if (btf_is_func(t)) { + pr_warn("extern function %s is unsupported under %s section\n", + ext->name, KCONFIG_SEC); + return -ENOTSUP; + } + kcfg_sec = sec; + ext->type = EXT_KCFG; + ext->kcfg.sz = btf__resolve_size(obj->btf, t->type); + if (ext->kcfg.sz <= 0) { + pr_warn("failed to resolve size of extern (kcfg) '%s': %d\n", + ext_name, ext->kcfg.sz); + return ext->kcfg.sz; + } + ext->kcfg.align = btf__align_of(obj->btf, t->type); + if (ext->kcfg.align <= 0) { + pr_warn("failed to determine alignment of extern (kcfg) '%s': %d\n", + ext_name, ext->kcfg.align); + return -EINVAL; + } + ext->kcfg.type = find_kcfg_type(obj->btf, t->type, + &ext->kcfg.is_signed); + if (ext->kcfg.type == KCFG_UNKNOWN) { + pr_warn("extern (kcfg) '%s': type is unsupported\n", ext_name); + return -ENOTSUP; + } + } else if (strcmp(sec_name, KSYMS_SEC) == 0) { + ksym_sec = sec; + ext->type = EXT_KSYM; + skip_mods_and_typedefs(obj->btf, t->type, + &ext->ksym.type_id); + } else { + pr_warn("unrecognized extern section '%s'\n", sec_name); + return -ENOTSUP; + } + } + pr_debug("collected %d externs total\n", obj->nr_extern); + + if (!obj->nr_extern) + return 0; + + /* sort externs by type, for kcfg ones also by (align, size, name) */ + qsort(obj->externs, obj->nr_extern, sizeof(*ext), cmp_externs); + + /* for .ksyms section, we need to turn all externs into allocated + * variables in BTF to pass kernel verification; we do this by + * pretending that each extern is a 8-byte variable + */ + if (ksym_sec) { + /* find existing 4-byte integer type in BTF to use for fake + * extern variables in DATASEC + */ + int int_btf_id = find_int_btf_id(obj->btf); + /* For extern function, a dummy_var added earlier + * will be used to replace the vs->type and + * its name string will be used to refill + * the missing param's name. + */ + const struct btf_type *dummy_var; + + dummy_var = btf__type_by_id(obj->btf, dummy_var_btf_id); + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (ext->type != EXT_KSYM) + continue; + pr_debug("extern (ksym) #%d: symbol %d, name %s\n", + i, ext->sym_idx, ext->name); + } + + sec = ksym_sec; + n = btf_vlen(sec); + for (i = 0, off = 0; i < n; i++, off += sizeof(int)) { + struct btf_var_secinfo *vs = btf_var_secinfos(sec) + i; + struct btf_type *vt; + + vt = (void *)btf__type_by_id(obj->btf, vs->type); + ext_name = btf__name_by_offset(obj->btf, vt->name_off); + ext = find_extern_by_name(obj, ext_name); + if (!ext) { + pr_warn("failed to find extern definition for BTF %s '%s'\n", + btf_kind_str(vt), ext_name); + return -ESRCH; + } + if (btf_is_func(vt)) { + const struct btf_type *func_proto; + struct btf_param *param; + int j; + + func_proto = btf__type_by_id(obj->btf, + vt->type); + param = btf_params(func_proto); + /* Reuse the dummy_var string if the + * func proto does not have param name. + */ + for (j = 0; j < btf_vlen(func_proto); j++) + if (param[j].type && !param[j].name_off) + param[j].name_off = + dummy_var->name_off; + vs->type = dummy_var_btf_id; + vt->info &= ~0xffff; + vt->info |= BTF_FUNC_GLOBAL; + } else { + btf_var(vt)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + vt->type = int_btf_id; + } + vs->offset = off; + vs->size = sizeof(int); + } + sec->size = off; + } + + if (kcfg_sec) { + sec = kcfg_sec; + /* for kcfg externs calculate their offsets within a .kconfig map */ + off = 0; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (ext->type != EXT_KCFG) + continue; + + ext->kcfg.data_off = roundup(off, ext->kcfg.align); + off = ext->kcfg.data_off + ext->kcfg.sz; + pr_debug("extern (kcfg) #%d: symbol %d, off %u, name %s\n", + i, ext->sym_idx, ext->kcfg.data_off, ext->name); + } + 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; + } + btf_var(t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + vs->offset = ext->kcfg.data_off; + } + } + return 0; +} + +static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) +{ + return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; +} + +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 (prog_is_subprog(obj, prog)) + continue; + if (!strcmp(prog->name, name)) + return prog; + } + return errno = ENOENT, NULL; +} + +static bool bpf_object__shndx_is_data(const struct bpf_object *obj, + int shndx) +{ + switch (obj->efile.secs[shndx].sec_type) { + case SEC_BSS: + case SEC_DATA: + case SEC_RODATA: + return true; + default: + return false; + } +} + +static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.btf_maps_shndx; +} + +static enum libbpf_map_type +bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) +{ + if (shndx == obj->efile.symbols_shndx) + return LIBBPF_MAP_KCONFIG; + + switch (obj->efile.secs[shndx].sec_type) { + case SEC_BSS: + return LIBBPF_MAP_BSS; + case SEC_DATA: + return LIBBPF_MAP_DATA; + case SEC_RODATA: + return LIBBPF_MAP_RODATA; + default: + return LIBBPF_MAP_UNSPEC; + } +} + +static int bpf_program__record_reloc(struct bpf_program *prog, + struct reloc_desc *reloc_desc, + __u32 insn_idx, const char *sym_name, + const Elf64_Sym *sym, const Elf64_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; + const char *sym_sec_name; + struct bpf_map *map; + + if (!is_call_insn(insn) && !is_ldimm64_insn(insn)) { + pr_warn("prog '%s': invalid relo against '%s' for insns[%d].code 0x%x\n", + prog->name, sym_name, insn_idx, insn->code); + return -LIBBPF_ERRNO__RELOC; + } + + if (sym_is_extern(sym)) { + int sym_idx = ELF64_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("prog '%s': extern relo failed to find extern for '%s' (%d)\n", + prog->name, sym_name, sym_idx); + return -LIBBPF_ERRNO__RELOC; + } + pr_debug("prog '%s': found extern #%d '%s' (sym %d) for insn #%u\n", + prog->name, i, ext->name, ext->sym_idx, insn_idx); + if (insn->code == (BPF_JMP | BPF_CALL)) + reloc_desc->type = RELO_EXTERN_FUNC; + else + reloc_desc->type = RELO_EXTERN_VAR; + reloc_desc->insn_idx = insn_idx; + reloc_desc->sym_off = i; /* sym_off stores extern index */ + return 0; + } + + /* sub-program call relocation */ + if (is_call_insn(insn)) { + if (insn->src_reg != BPF_PSEUDO_CALL) { + pr_warn("prog '%s': incorrect bpf_call opcode\n", prog->name); + return -LIBBPF_ERRNO__RELOC; + } + /* text_shndx can be 0, if no default "main" program exists */ + if (!shdr_idx || shdr_idx != obj->efile.text_shndx) { + sym_sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, shdr_idx)); + pr_warn("prog '%s': bad call relo against '%s' in section '%s'\n", + prog->name, sym_name, sym_sec_name); + return -LIBBPF_ERRNO__RELOC; + } + if (sym->st_value % BPF_INSN_SZ) { + pr_warn("prog '%s': bad call relo against '%s' at offset %zu\n", + prog->name, sym_name, (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; + return 0; + } + + if (!shdr_idx || shdr_idx >= SHN_LORESERVE) { + pr_warn("prog '%s': invalid relo against '%s' in special section 0x%x; forgot to initialize global var?..\n", + prog->name, sym_name, shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + /* loading subprog addresses */ + if (sym_is_subprog(sym, obj->efile.text_shndx)) { + /* global_func: sym->st_value = offset in the section, insn->imm = 0. + * local_func: sym->st_value = 0, insn->imm = offset in the section. + */ + if ((sym->st_value % BPF_INSN_SZ) || (insn->imm % BPF_INSN_SZ)) { + pr_warn("prog '%s': bad subprog addr relo against '%s' at offset %zu+%d\n", + prog->name, sym_name, (size_t)sym->st_value, insn->imm); + return -LIBBPF_ERRNO__RELOC; + } + + reloc_desc->type = RELO_SUBPROG_ADDR; + reloc_desc->insn_idx = insn_idx; + reloc_desc->sym_off = sym->st_value; + return 0; + } + + type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); + sym_sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, shdr_idx)); + + /* generic map reference relocation */ + if (type == LIBBPF_MAP_UNSPEC) { + if (!bpf_object__shndx_is_maps(obj, shdr_idx)) { + pr_warn("prog '%s': bad map relo against '%s' in section '%s'\n", + prog->name, sym_name, sym_sec_name); + 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("prog '%s': found map %zd (%s, sec %d, off %zu) for insn #%u\n", + prog->name, map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); + break; + } + if (map_idx >= nr_maps) { + pr_warn("prog '%s': map relo failed to find map for section '%s', off %zu\n", + prog->name, sym_sec_name, (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("prog '%s': bad data relo against section '%s'\n", + prog->name, sym_sec_name); + 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) + continue; + pr_debug("prog '%s': found data map %zd (%s, sec %d, off %zu) for insn %u\n", + prog->name, map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); + break; + } + if (map_idx >= nr_maps) { + pr_warn("prog '%s': data relo failed to find map for section '%s'\n", + prog->name, sym_sec_name); + 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 bool prog_contains_insn(const struct bpf_program *prog, size_t insn_idx) +{ + return insn_idx >= prog->sec_insn_off && + insn_idx < prog->sec_insn_off + prog->sec_insn_cnt; +} + +static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj, + size_t sec_idx, size_t insn_idx) +{ + int l = 0, r = obj->nr_programs - 1, m; + struct bpf_program *prog; + + if (!obj->nr_programs) + return NULL; + + while (l < r) { + m = l + (r - l + 1) / 2; + prog = &obj->programs[m]; + + if (prog->sec_idx < sec_idx || + (prog->sec_idx == sec_idx && prog->sec_insn_off <= insn_idx)) + l = m; + else + r = m - 1; + } + /* matching program could be at index l, but it still might be the + * wrong one, so we need to double check conditions for the last time + */ + prog = &obj->programs[l]; + if (prog->sec_idx == sec_idx && prog_contains_insn(prog, insn_idx)) + return prog; + return NULL; +} + +static int +bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data) +{ + const char *relo_sec_name, *sec_name; + size_t sec_idx = shdr->sh_info, sym_idx; + struct bpf_program *prog; + struct reloc_desc *relos; + int err, i, nrels; + const char *sym_name; + __u32 insn_idx; + Elf_Scn *scn; + Elf_Data *scn_data; + Elf64_Sym *sym; + Elf64_Rel *rel; + + if (sec_idx >= obj->efile.sec_cnt) + return -EINVAL; + + scn = elf_sec_by_idx(obj, sec_idx); + scn_data = elf_sec_data(obj, scn); + + relo_sec_name = elf_sec_str(obj, shdr->sh_name); + sec_name = elf_sec_name(obj, scn); + if (!relo_sec_name || !sec_name) + return -EINVAL; + + pr_debug("sec '%s': collecting relocation for section(%zu) '%s'\n", + relo_sec_name, sec_idx, sec_name); + nrels = shdr->sh_size / shdr->sh_entsize; + + for (i = 0; i < nrels; i++) { + rel = elf_rel_by_idx(data, i); + if (!rel) { + pr_warn("sec '%s': failed to get relo #%d\n", relo_sec_name, i); + return -LIBBPF_ERRNO__FORMAT; + } + + sym_idx = ELF64_R_SYM(rel->r_info); + sym = elf_sym_by_idx(obj, sym_idx); + if (!sym) { + pr_warn("sec '%s': symbol #%zu not found for relo #%d\n", + relo_sec_name, sym_idx, i); + return -LIBBPF_ERRNO__FORMAT; + } + + if (sym->st_shndx >= obj->efile.sec_cnt) { + pr_warn("sec '%s': corrupted symbol #%zu pointing to invalid section #%zu for relo #%d\n", + relo_sec_name, sym_idx, (size_t)sym->st_shndx, i); + return -LIBBPF_ERRNO__FORMAT; + } + + if (rel->r_offset % BPF_INSN_SZ || rel->r_offset >= scn_data->d_size) { + pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n", + relo_sec_name, (size_t)rel->r_offset, i); + return -LIBBPF_ERRNO__FORMAT; + } + + insn_idx = rel->r_offset / BPF_INSN_SZ; + /* relocations against static functions are recorded as + * relocations against the section that contains a function; + * in such case, symbol will be STT_SECTION and sym.st_name + * will point to empty string (0), so fetch section name + * instead + */ + if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && sym->st_name == 0) + sym_name = elf_sec_name(obj, elf_sec_by_idx(obj, sym->st_shndx)); + else + sym_name = elf_sym_str(obj, sym->st_name); + sym_name = sym_name ?: "<?"; + + pr_debug("sec '%s': relo #%d: insn #%u against '%s'\n", + relo_sec_name, i, insn_idx, sym_name); + + prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx); + if (!prog) { + pr_debug("sec '%s': relo #%d: couldn't find program in section '%s' for insn #%u, probably overridden weak function, skipping...\n", + relo_sec_name, i, sec_name, insn_idx); + continue; + } + + relos = libbpf_reallocarray(prog->reloc_desc, + prog->nr_reloc + 1, sizeof(*relos)); + if (!relos) + return -ENOMEM; + prog->reloc_desc = relos; + + /* adjust insn_idx to local BPF program frame of reference */ + insn_idx -= prog->sec_insn_off; + err = bpf_program__record_reloc(prog, &relos[prog->nr_reloc], + insn_idx, sym_name, sym, rel); + if (err) + return err; + + prog->nr_reloc++; + } + return 0; +} + +static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) +{ + int id; + + if (!obj->btf) + return -ENOENT; + + /* if it's BTF-defined map, we don't need to search for type IDs. + * For struct_ops map, it does not need btf_key_type_id and + * btf_value_type_id. + */ + if (map->sec_idx == obj->efile.btf_maps_shndx || bpf_map__is_struct_ops(map)) + return 0; + + /* + * LLVM annotates global data differently in BTF, that is, + * only as '.data', '.bss' or '.rodata'. + */ + if (!bpf_map__is_internal(map)) + return -ENOENT; + + id = btf__find_by_name(obj->btf, map->real_name); + if (id < 0) + return id; + + map->btf_key_type_id = 0; + map->btf_value_type_id = id; + return 0; +} + +static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) +{ + char file[PATH_MAX], buff[4096]; + FILE *fp; + __u32 val; + int err; + + snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd); + memset(info, 0, sizeof(*info)); + + fp = fopen(file, "r"); + if (!fp) { + err = -errno; + pr_warn("failed to open %s: %d. No procfs support?\n", file, + err); + return err; + } + + while (fgets(buff, sizeof(buff), fp)) { + if (sscanf(buff, "map_type:\t%u", &val) == 1) + info->type = val; + else if (sscanf(buff, "key_size:\t%u", &val) == 1) + info->key_size = val; + else if (sscanf(buff, "value_size:\t%u", &val) == 1) + info->value_size = val; + else if (sscanf(buff, "max_entries:\t%u", &val) == 1) + info->max_entries = val; + else if (sscanf(buff, "map_flags:\t%i", &val) == 1) + info->map_flags = val; + } + + fclose(fp); + + return 0; +} + +bool bpf_map__autocreate(const struct bpf_map *map) +{ + return map->autocreate; +} + +int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate) +{ + if (map->obj->loaded) + return libbpf_err(-EBUSY); + + map->autocreate = autocreate; + return 0; +} + +int bpf_map__reuse_fd(struct bpf_map *map, int fd) +{ + struct bpf_map_info info; + __u32 len = sizeof(info), name_len; + int new_fd, err; + char *new_name; + + memset(&info, 0, len); + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err && errno == EINVAL) + err = bpf_get_map_info_from_fdinfo(fd, &info); + if (err) + return libbpf_err(err); + + name_len = strlen(info.name); + if (name_len == BPF_OBJ_NAME_LEN - 1 && strncmp(map->name, info.name, name_len) == 0) + new_name = strdup(map->name); + else + new_name = strdup(info.name); + + if (!new_name) + return libbpf_err(-errno); + + new_fd = open("/", O_RDONLY | O_CLOEXEC); + if (new_fd < 0) { + err = -errno; + goto err_free_new_name; + } + + new_fd = dup3(fd, new_fd, O_CLOEXEC); + if (new_fd < 0) { + err = -errno; + goto err_close_new_fd; + } + + err = zclose(map->fd); + if (err) { + err = -errno; + goto err_close_new_fd; + } + free(map->name); + + map->fd = new_fd; + map->name = new_name; + map->def.type = info.type; + map->def.key_size = info.key_size; + map->def.value_size = info.value_size; + map->def.max_entries = info.max_entries; + 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; + map->map_extra = info.map_extra; + + return 0; + +err_close_new_fd: + close(new_fd); +err_free_new_name: + free(new_name); + return libbpf_err(err); +} + +__u32 bpf_map__max_entries(const struct bpf_map *map) +{ + return map->def.max_entries; +} + +struct bpf_map *bpf_map__inner_map(struct bpf_map *map) +{ + if (!bpf_map_type__is_map_in_map(map->def.type)) + return errno = EINVAL, NULL; + + return map->inner_map; +} + +int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) +{ + if (map->obj->loaded) + return libbpf_err(-EBUSY); + + map->def.max_entries = max_entries; + + /* auto-adjust BPF ringbuf map max_entries to be a multiple of page size */ + if (map_is_ringbuf(map)) + map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries); + + return 0; +} + +static int +bpf_object__probe_loading(struct bpf_object *obj) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, insn_cnt = ARRAY_SIZE(insns); + + if (obj->gen_loader) + return 0; + + ret = bump_rlimit_memlock(); + if (ret) + pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret); + + /* make sure basic loading works */ + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + if (ret < 0) + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); + if (ret < 0) { + ret = errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't load trivial BPF " + "program. Make sure your kernel supports BPF " + "(CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is " + "set to big enough value.\n", __func__, cp, ret); + return -ret; + } + close(ret); + + return 0; +} + +static int probe_fd(int fd) +{ + if (fd >= 0) + close(fd); + return fd >= 0; +} + +static int probe_kern_prog_name(void) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_name); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.license = ptr_to_u64("GPL"); + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); + + /* make sure loading with name works */ + ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); + return probe_fd(ret); +} + +static int probe_kern_global_data(void) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + insns[0].imm = map; + + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + close(map); + return probe_fd(ret); +} + +static int probe_kern_btf(void) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_func(void) +{ + static const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_func_global(void) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_datasec(void) +{ + static const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_float(void) +{ + static const char strs[] = "\0float"; + __u32 types[] = { + /* float */ + BTF_TYPE_FLOAT_ENC(1, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_decl_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_type_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* attr */ + BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ + /* ptr */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_array_mmap(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); +} + +static int probe_kern_exp_attach_type(void) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + /* use any valid combination of program type and (optional) + * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) + * to see if kernel supports expected_attach_type field for + * BPF_PROG_LOAD command + */ + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); +} + +static int probe_kern_probe_read_kernel(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ + BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ + BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(fd); +} + +static int probe_prog_bind_map(void) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + if (prog < 0) { + close(map); + return 0; + } + + ret = bpf_prog_bind_map(prog, map, NULL); + + close(map); + close(prog); + + return ret >= 0; +} + +static int probe_module_btf(void) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[16]; + int fd, err; + + fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); + if (fd < 0) + return 0; /* BTF not supported at all */ + + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; + * kernel's module BTF support coincides with support for + * name/name_len fields in struct bpf_btf_info. + */ + err = bpf_obj_get_info_by_fd(fd, &info, &len); + close(fd); + return !err; +} + +static int probe_perf_link(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", + insns, ARRAY_SIZE(insns), NULL); + if (prog_fd < 0) + return -errno; + + /* use invalid perf_event FD to get EBADF, if link is supported; + * otherwise EINVAL should be returned + */ + link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_kern_bpf_cookie(void) +{ + struct bpf_insn insns[] = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), + BPF_EXIT_INSN(), + }; + int ret, insn_cnt = ARRAY_SIZE(insns); + + ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(ret); +} + +static int probe_kern_btf_enum64(void) +{ + static const char strs[] = "\0enum64"; + __u32 types[] = { + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_syscall_wrapper(void); + +enum kern_feature_result { + FEAT_UNKNOWN = 0, + FEAT_SUPPORTED = 1, + FEAT_MISSING = 2, +}; + +typedef int (*feature_probe_fn)(void); + +static struct kern_feature_desc { + const char *desc; + feature_probe_fn probe; + enum kern_feature_result res; +} feature_probes[__FEAT_CNT] = { + [FEAT_PROG_NAME] = { + "BPF program name", probe_kern_prog_name, + }, + [FEAT_GLOBAL_DATA] = { + "global variables", probe_kern_global_data, + }, + [FEAT_BTF] = { + "minimal BTF", probe_kern_btf, + }, + [FEAT_BTF_FUNC] = { + "BTF functions", probe_kern_btf_func, + }, + [FEAT_BTF_GLOBAL_FUNC] = { + "BTF global function", probe_kern_btf_func_global, + }, + [FEAT_BTF_DATASEC] = { + "BTF data section and variable", probe_kern_btf_datasec, + }, + [FEAT_ARRAY_MMAP] = { + "ARRAY map mmap()", probe_kern_array_mmap, + }, + [FEAT_EXP_ATTACH_TYPE] = { + "BPF_PROG_LOAD expected_attach_type attribute", + probe_kern_exp_attach_type, + }, + [FEAT_PROBE_READ_KERN] = { + "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, + }, + [FEAT_PROG_BIND_MAP] = { + "BPF_PROG_BIND_MAP support", probe_prog_bind_map, + }, + [FEAT_MODULE_BTF] = { + "module BTF support", probe_module_btf, + }, + [FEAT_BTF_FLOAT] = { + "BTF_KIND_FLOAT support", probe_kern_btf_float, + }, + [FEAT_PERF_LINK] = { + "BPF perf link support", probe_perf_link, + }, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, + }, + [FEAT_BTF_TYPE_TAG] = { + "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, + }, + [FEAT_MEMCG_ACCOUNT] = { + "memcg-based memory accounting", probe_memcg_account, + }, + [FEAT_BPF_COOKIE] = { + "BPF cookie support", probe_kern_bpf_cookie, + }, + [FEAT_BTF_ENUM64] = { + "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, + }, + [FEAT_SYSCALL_WRAPPER] = { + "Kernel using syscall wrapper", probe_kern_syscall_wrapper, + }, +}; + +bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) +{ + struct kern_feature_desc *feat = &feature_probes[feat_id]; + int ret; + + if (obj && obj->gen_loader) + /* To generate loader program assume the latest kernel + * to avoid doing extra prog_load, map_create syscalls. + */ + return true; + + if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { + ret = feat->probe(); + if (ret > 0) { + WRITE_ONCE(feat->res, FEAT_SUPPORTED); + } else if (ret == 0) { + WRITE_ONCE(feat->res, FEAT_MISSING); + } else { + pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); + WRITE_ONCE(feat->res, FEAT_MISSING); + } + } + + return READ_ONCE(feat->res) == FEAT_SUPPORTED; +} + +static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) +{ + struct bpf_map_info map_info; + char msg[STRERR_BUFSIZE]; + __u32 map_info_len = sizeof(map_info); + int err; + + memset(&map_info, 0, map_info_len); + err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len); + if (err && errno == EINVAL) + err = bpf_get_map_info_from_fdinfo(map_fd, &map_info); + if (err) { + pr_warn("failed to get map info for map FD %d: %s\n", map_fd, + libbpf_strerror_r(errno, msg, sizeof(msg))); + 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 && + map_info.map_extra == map->map_extra); +} + +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); + close(pin_fd); + if (err) { + 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; + + if (obj->gen_loader) { + bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps, + map->mmaped, map->def.value_size); + if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG) + bpf_gen__map_freeze(obj->gen_loader, map - obj->maps); + return 0; + } + err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0); + if (err) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error setting initial map(%s) contents: %s\n", + map->name, cp); + return err; + } + + /* 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) { + 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 0; +} + +static void bpf_map__destroy(struct bpf_map *map); + +static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) +{ + LIBBPF_OPTS(bpf_map_create_opts, create_attr); + struct bpf_map_def *def = &map->def; + const char *map_name = NULL; + int err = 0; + + if (kernel_supports(obj, FEAT_PROG_NAME)) + map_name = map->name; + create_attr.map_ifindex = map->map_ifindex; + create_attr.map_flags = def->map_flags; + create_attr.numa_node = map->numa_node; + create_attr.map_extra = map->map_extra; + + if (bpf_map__is_struct_ops(map)) + create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + + if (obj->btf && btf__fd(obj->btf) >= 0) { + create_attr.btf_fd = btf__fd(obj->btf); + create_attr.btf_key_type_id = map->btf_key_type_id; + create_attr.btf_value_type_id = map->btf_value_type_id; + } + + if (bpf_map_type__is_map_in_map(def->type)) { + if (map->inner_map) { + err = bpf_object__create_map(obj, map->inner_map, true); + if (err) { + pr_warn("map '%s': failed to create inner map: %d\n", + map->name, err); + return err; + } + map->inner_map_fd = bpf_map__fd(map->inner_map); + } + if (map->inner_map_fd >= 0) + create_attr.inner_map_fd = map->inner_map_fd; + } + + switch (def->type) { + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_STACK_TRACE: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + default: + break; + } + + if (obj->gen_loader) { + bpf_gen__map_create(obj->gen_loader, def->type, map_name, + def->key_size, def->value_size, def->max_entries, + &create_attr, is_inner ? -1 : map - obj->maps); + /* Pretend to have valid FD to pass various fd >= 0 checks. + * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. + */ + map->fd = 0; + } else { + map->fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + def->max_entries, &create_attr); + } + if (map->fd < 0 && (create_attr.btf_key_type_id || + create_attr.btf_value_type_id)) { + char *cp, errmsg[STRERR_BUFSIZE]; + + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, cp, err); + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + map->fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + def->max_entries, &create_attr); + } + + err = map->fd < 0 ? -errno : 0; + + if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) { + if (obj->gen_loader) + map->inner_map->fd = -1; + bpf_map__destroy(map->inner_map); + zfree(&map->inner_map); + } + + return err; +} + +static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map) +{ + const struct bpf_map *targ_map; + unsigned int i; + int fd, err = 0; + + for (i = 0; i < map->init_slots_sz; i++) { + if (!map->init_slots[i]) + continue; + + targ_map = map->init_slots[i]; + fd = bpf_map__fd(targ_map); + + if (obj->gen_loader) { + bpf_gen__populate_outer_map(obj->gen_loader, + map - obj->maps, i, + targ_map - obj->maps); + } else { + err = bpf_map_update_elem(map->fd, &i, &fd, 0); + } + if (err) { + err = -errno; + pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", + map->name, i, targ_map->name, fd, err); + return err; + } + pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", + map->name, i, targ_map->name, fd); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + return 0; +} + +static int init_prog_array_slots(struct bpf_object *obj, struct bpf_map *map) +{ + const struct bpf_program *targ_prog; + unsigned int i; + int fd, err; + + if (obj->gen_loader) + return -ENOTSUP; + + for (i = 0; i < map->init_slots_sz; i++) { + if (!map->init_slots[i]) + continue; + + targ_prog = map->init_slots[i]; + fd = bpf_program__fd(targ_prog); + + err = bpf_map_update_elem(map->fd, &i, &fd, 0); + if (err) { + err = -errno; + pr_warn("map '%s': failed to initialize slot [%d] to prog '%s' fd=%d: %d\n", + map->name, i, targ_prog->name, fd, err); + return err; + } + pr_debug("map '%s': slot [%d] set to prog '%s' fd=%d\n", + map->name, i, targ_prog->name, fd); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + return 0; +} + +static int bpf_object_init_prog_arrays(struct bpf_object *obj) +{ + struct bpf_map *map; + int i, err; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + + if (!map->init_slots_sz || map->def.type != BPF_MAP_TYPE_PROG_ARRAY) + continue; + + err = init_prog_array_slots(obj, map); + if (err < 0) { + zclose(map->fd); + return err; + } + } + return 0; +} + +static int map_set_def_max_entries(struct bpf_map *map) +{ + if (map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !map->def.max_entries) { + int nr_cpus; + + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warn("map '%s': failed to determine number of system CPUs: %d\n", + map->name, nr_cpus); + return nr_cpus; + } + pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); + map->def.max_entries = nr_cpus; + } + + return 0; +} + +static int +bpf_object__create_maps(struct bpf_object *obj) +{ + struct bpf_map *map; + char *cp, errmsg[STRERR_BUFSIZE]; + unsigned int i, j; + int err; + bool retried; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + + /* To support old kernels, we skip creating global data maps + * (.rodata, .data, .kconfig, etc); later on, during program + * loading, if we detect that at least one of the to-be-loaded + * programs is referencing any global data map, we'll error + * out with program name and relocation index logged. + * This approach allows to accommodate Clang emitting + * unnecessary .rodata.str1.1 sections for string literals, + * but also it allows to have CO-RE applications that use + * global variables in some of BPF programs, but not others. + * If those global variable-using programs are not loaded at + * runtime due to bpf_program__set_autoload(prog, false), + * bpf_object loading will succeed just fine even on old + * kernels. + */ + if (bpf_map__is_internal(map) && !kernel_supports(obj, FEAT_GLOBAL_DATA)) + map->autocreate = false; + + if (!map->autocreate) { + pr_debug("map '%s': skipped auto-creating...\n", map->name); + continue; + } + + err = map_set_def_max_entries(map); + if (err) + goto err_out; + + retried = false; +retry: + if (map->pin_path) { + err = bpf_object__reuse_map(map); + if (err) { + pr_warn("map '%s': error reusing pinned map\n", + map->name); + goto err_out; + } + if (retried && map->fd < 0) { + pr_warn("map '%s': cannot find pinned map\n", + map->name); + err = -ENOENT; + goto err_out; + } + } + + if (map->fd >= 0) { + pr_debug("map '%s': skipping creation (preset fd=%d)\n", + map->name, map->fd); + } else { + err = bpf_object__create_map(obj, map, false); + if (err) + goto err_out; + + pr_debug("map '%s': created successfully, fd=%d\n", + map->name, map->fd); + + if (bpf_map__is_internal(map)) { + err = bpf_object__populate_internal_map(obj, map); + if (err < 0) { + zclose(map->fd); + goto err_out; + } + } + + if (map->init_slots_sz && map->def.type != BPF_MAP_TYPE_PROG_ARRAY) { + err = init_map_in_map_slots(obj, map); + if (err < 0) { + zclose(map->fd); + goto err_out; + } + } + } + + if (map->pin_path && !map->pinned) { + err = bpf_map__pin(map, NULL); + if (err) { + zclose(map->fd); + if (!retried && err == -EEXIST) { + retried = true; + goto retry; + } + pr_warn("map '%s': failed to auto-pin at '%s': %d\n", + map->name, map->pin_path, err); + goto err_out; + } + } + } + + return 0; + +err_out: + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("map '%s': failed to create: %s(%d)\n", map->name, cp, err); + pr_perm_msg(err); + for (j = 0; j < i; j++) + zclose(obj->maps[j].fd); + return err; +} + +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. + */ +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; +} + +void bpf_core_free_cands(struct bpf_core_cand_list *cands) +{ + if (!cands) + return; + + free(cands->cands); + free(cands); +} + +int bpf_core_add_cands(struct bpf_core_cand *local_cand, + size_t local_essent_len, + const struct btf *targ_btf, + const char *targ_btf_name, + int targ_start_id, + struct bpf_core_cand_list *cands) +{ + struct bpf_core_cand *new_cands, *cand; + const struct btf_type *t, *local_t; + const char *targ_name, *local_name; + size_t targ_essent_len; + int n, i; + + local_t = btf__type_by_id(local_cand->btf, local_cand->id); + local_name = btf__str_by_offset(local_cand->btf, local_t->name_off); + + n = btf__type_cnt(targ_btf); + for (i = targ_start_id; i < n; i++) { + t = btf__type_by_id(targ_btf, i); + if (!btf_kind_core_compat(t, local_t)) + continue; + + 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) + continue; + + pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s in [%s]\n", + local_cand->id, btf_kind_str(local_t), + local_name, i, btf_kind_str(t), targ_name, + targ_btf_name); + new_cands = libbpf_reallocarray(cands->cands, cands->len + 1, + sizeof(*cands->cands)); + if (!new_cands) + return -ENOMEM; + + cand = &new_cands[cands->len]; + cand->btf = targ_btf; + cand->id = i; + + cands->cands = new_cands; + cands->len++; + } + return 0; +} + +static int load_module_btfs(struct bpf_object *obj) +{ + struct bpf_btf_info info; + struct module_btf *mod_btf; + struct btf *btf; + char name[64]; + __u32 id = 0, len; + int err, fd; + + if (obj->btf_modules_loaded) + return 0; + + if (obj->gen_loader) + return 0; + + /* don't do this again, even if we find no module BTFs */ + obj->btf_modules_loaded = true; + + /* kernel too old to support module BTFs */ + if (!kernel_supports(obj, FEAT_MODULE_BTF)) + return 0; + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err && errno == ENOENT) + return 0; + if (err) { + err = -errno; + pr_warn("failed to iterate BTF objects: %d\n", err); + return err; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; /* expected race: BTF was unloaded */ + err = -errno; + pr_warn("failed to get BTF object #%d FD: %d\n", id, err); + return err; + } + + len = sizeof(info); + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + err = -errno; + pr_warn("failed to get BTF object #%d info: %d\n", id, err); + goto err_out; + } + + /* ignore non-module BTFs */ + if (!info.kernel_btf || strcmp(name, "vmlinux") == 0) { + close(fd); + continue; + } + + btf = btf_get_from_fd(fd, obj->btf_vmlinux); + err = libbpf_get_error(btf); + if (err) { + pr_warn("failed to load module [%s]'s BTF object #%d: %d\n", + name, id, err); + goto err_out; + } + + err = libbpf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap, + sizeof(*obj->btf_modules), obj->btf_module_cnt + 1); + if (err) + goto err_out; + + mod_btf = &obj->btf_modules[obj->btf_module_cnt++]; + + mod_btf->btf = btf; + mod_btf->id = id; + mod_btf->fd = fd; + mod_btf->name = strdup(name); + if (!mod_btf->name) { + err = -ENOMEM; + goto err_out; + } + continue; + +err_out: + close(fd); + return err; + } + + return 0; +} + +static struct bpf_core_cand_list * +bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 local_type_id) +{ + struct bpf_core_cand local_cand = {}; + struct bpf_core_cand_list *cands; + const struct btf *main_btf; + const struct btf_type *local_t; + const char *local_name; + size_t local_essent_len; + int err, i; + + local_cand.btf = local_btf; + local_cand.id = local_type_id; + local_t = btf__type_by_id(local_btf, local_type_id); + if (!local_t) + return ERR_PTR(-EINVAL); + + local_name = btf__name_by_offset(local_btf, local_t->name_off); + if (str_is_empty(local_name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(local_name); + + cands = calloc(1, sizeof(*cands)); + if (!cands) + return ERR_PTR(-ENOMEM); + + /* Attempt to find target candidates in vmlinux BTF first */ + main_btf = obj->btf_vmlinux_override ?: obj->btf_vmlinux; + err = bpf_core_add_cands(&local_cand, local_essent_len, main_btf, "vmlinux", 1, cands); + if (err) + goto err_out; + + /* if vmlinux BTF has any candidate, don't got for module BTFs */ + if (cands->len) + return cands; + + /* if vmlinux BTF was overridden, don't attempt to load module BTFs */ + if (obj->btf_vmlinux_override) + return cands; + + /* now look through module BTFs, trying to still find candidates */ + err = load_module_btfs(obj); + if (err) + goto err_out; + + for (i = 0; i < obj->btf_module_cnt; i++) { + err = bpf_core_add_cands(&local_cand, local_essent_len, + obj->btf_modules[i].btf, + obj->btf_modules[i].name, + btf__type_cnt(obj->btf_vmlinux), + cands); + if (err) + goto err_out; + } + + return cands; +err_out: + bpf_core_free_cands(cands); + return ERR_PTR(err); +} + +/* Check local and target types for compatibility. This check is used for + * type-based CO-RE relocations and follow slightly different rules than + * field-based relocations. This function assumes that root types were already + * checked for name match. Beyond that initial root-level name check, names + * are completely ignored. Compatibility rules are as follows: + * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs are considered compatible, but + * kind should match for local and target types (i.e., STRUCT is not + * compatible with UNION); + * - for ENUMs, the size is ignored; + * - for INT, size and signedness are ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - CONST/VOLATILE/RESTRICT modifiers are ignored; + * - TYPEDEFs/PTRs are compatible if types they pointing to are compatible; + * - FUNC_PROTOs are compatible if they have compatible signature: same + * number of input args and compatible return and argument types. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id) +{ + return __bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id, 32); +} + +int bpf_core_types_match(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id) +{ + return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, 32); +} + +static size_t bpf_core_hash_fn(const void *key, void *ctx) +{ + 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; +} + +static int record_relo_core(struct bpf_program *prog, + const struct bpf_core_relo *core_relo, int insn_idx) +{ + struct reloc_desc *relos, *relo; + + relos = libbpf_reallocarray(prog->reloc_desc, + prog->nr_reloc + 1, sizeof(*relos)); + if (!relos) + return -ENOMEM; + relo = &relos[prog->nr_reloc]; + relo->type = RELO_CORE; + relo->insn_idx = insn_idx; + relo->core_relo = core_relo; + prog->reloc_desc = relos; + prog->nr_reloc++; + return 0; +} + +static const struct bpf_core_relo *find_relo_core(struct bpf_program *prog, int insn_idx) +{ + struct reloc_desc *relo; + int i; + + for (i = 0; i < prog->nr_reloc; i++) { + relo = &prog->reloc_desc[i]; + if (relo->type != RELO_CORE || relo->insn_idx != insn_idx) + continue; + + return relo->core_relo; + } + + return NULL; +} + +static int bpf_core_resolve_relo(struct bpf_program *prog, + const struct bpf_core_relo *relo, + int relo_idx, + const struct btf *local_btf, + struct hashmap *cand_cache, + struct bpf_core_relo_res *targ_res) +{ + struct bpf_core_spec specs_scratch[3] = {}; + const void *type_key = u32_as_hash_key(relo->type_id); + struct bpf_core_cand_list *cands = NULL; + const char *prog_name = prog->name; + const struct btf_type *local_type; + const char *local_name; + __u32 local_id = relo->type_id; + int err; + + 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 (!local_name) + return -EINVAL; + + if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && + !hashmap__find(cand_cache, type_key, (void **)&cands)) { + cands = bpf_core_find_cands(prog->obj, local_btf, local_id); + if (IS_ERR(cands)) { + pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld\n", + prog_name, relo_idx, local_id, btf_kind_str(local_type), + local_name, PTR_ERR(cands)); + return PTR_ERR(cands); + } + err = hashmap__set(cand_cache, type_key, cands, NULL, NULL); + if (err) { + bpf_core_free_cands(cands); + return err; + } + } + + return bpf_core_calc_relo_insn(prog_name, relo, relo_idx, local_btf, cands, specs_scratch, + targ_res); +} + +static int +bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) +{ + const struct btf_ext_info_sec *sec; + struct bpf_core_relo_res targ_res; + const struct bpf_core_relo *rec; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct bpf_program *prog; + struct bpf_insn *insn; + const char *sec_name; + int i, err = 0, insn_idx, sec_idx, sec_num; + + if (obj->btf_ext->core_relo_info.len == 0) + return 0; + + if (targ_btf_path) { + obj->btf_vmlinux_override = btf__parse(targ_btf_path, NULL); + err = libbpf_get_error(obj->btf_vmlinux_override); + if (err) { + pr_warn("failed to parse target BTF: %d\n", err); + return err; + } + } + + 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->core_relo_info; + sec_num = 0; + for_each_btf_ext_sec(seg, sec) { + sec_idx = seg->sec_idxs[sec_num]; + sec_num++; + + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) { + err = -EINVAL; + goto out; + } + + pr_debug("sec '%s': found %d CO-RE relocations\n", sec_name, sec->num_info); + + for_each_btf_ext_rec(seg, sec, i, rec) { + if (rec->insn_off % BPF_INSN_SZ) + return -EINVAL; + insn_idx = rec->insn_off / BPF_INSN_SZ; + prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx); + if (!prog) { + /* When __weak subprog is "overridden" by another instance + * of the subprog from a different object file, linker still + * appends all the .BTF.ext info that used to belong to that + * eliminated subprogram. + * This is similar to what x86-64 linker does for relocations. + * So just ignore such relocations just like we ignore + * subprog instructions when discovering subprograms. + */ + pr_debug("sec '%s': skipping CO-RE relocation #%d for insn #%d belonging to eliminated weak subprogram\n", + sec_name, i, insn_idx); + continue; + } + /* no need to apply CO-RE relocation if the program is + * not going to be loaded + */ + if (!prog->autoload) + continue; + + /* adjust insn_idx from section frame of reference to the local + * program's frame of reference; (sub-)program code is not yet + * relocated, so it's enough to just subtract in-section offset + */ + insn_idx = insn_idx - prog->sec_insn_off; + if (insn_idx >= prog->insns_cnt) + return -EINVAL; + insn = &prog->insns[insn_idx]; + + err = record_relo_core(prog, rec, insn_idx); + if (err) { + pr_warn("prog '%s': relo #%d: failed to record relocation: %d\n", + prog->name, i, err); + goto out; + } + + if (prog->obj->gen_loader) + continue; + + err = bpf_core_resolve_relo(prog, rec, i, obj->btf, cand_cache, &targ_res); + if (err) { + pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", + prog->name, i, err); + goto out; + } + + err = bpf_core_patch_insn(prog->name, insn, insn_idx, rec, i, &targ_res); + if (err) { + pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n", + prog->name, i, insn_idx, err); + goto out; + } + } + } + +out: + /* obj->btf_vmlinux and module BTFs are freed after object load */ + btf__free(obj->btf_vmlinux_override); + obj->btf_vmlinux_override = NULL; + + 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; +} + +/* base map load ldimm64 special constant, used also for log fixup logic */ +#define MAP_LDIMM64_POISON_BASE 2001000000 +#define MAP_LDIMM64_POISON_PFX "200100" + +static void poison_map_ldimm64(struct bpf_program *prog, int relo_idx, + int insn_idx, struct bpf_insn *insn, + int map_idx, const struct bpf_map *map) +{ + int i; + + pr_debug("prog '%s': relo #%d: poisoning insn #%d that loads map #%d '%s'\n", + prog->name, relo_idx, insn_idx, map_idx, map->name); + + /* we turn single ldimm64 into two identical invalid calls */ + for (i = 0; i < 2; i++) { + insn->code = BPF_JMP | BPF_CALL; + insn->dst_reg = 0; + insn->src_reg = 0; + insn->off = 0; + /* if this instruction is reachable (not a dead code), + * verifier will complain with something like: + * invalid func unknown#2001000123 + * where lower 123 is map index into obj->maps[] array + */ + insn->imm = MAP_LDIMM64_POISON_BASE + map_idx; + + insn++; + } +} + +/* Relocate data references within program code: + * - map references; + * - global variable references; + * - extern references. + */ +static int +bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) +{ + int i; + + for (i = 0; i < prog->nr_reloc; i++) { + struct reloc_desc *relo = &prog->reloc_desc[i]; + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; + const struct bpf_map *map; + struct extern_desc *ext; + + switch (relo->type) { + case RELO_LD64: + map = &obj->maps[relo->map_idx]; + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX; + insn[0].imm = relo->map_idx; + } else if (map->autocreate) { + insn[0].src_reg = BPF_PSEUDO_MAP_FD; + insn[0].imm = map->fd; + } else { + poison_map_ldimm64(prog, i, relo->insn_idx, insn, + relo->map_idx, map); + } + break; + case RELO_DATA: + map = &obj->maps[relo->map_idx]; + insn[1].imm = insn[0].imm + relo->sym_off; + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; + insn[0].imm = relo->map_idx; + } else if (map->autocreate) { + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = map->fd; + } else { + poison_map_ldimm64(prog, i, relo->insn_idx, insn, + relo->map_idx, map); + } + break; + case RELO_EXTERN_VAR: + ext = &obj->externs[relo->sym_off]; + if (ext->type == EXT_KCFG) { + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; + insn[0].imm = obj->kconfig_map_idx; + } else { + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + } + insn[1].imm = ext->kcfg.data_off; + } else /* EXT_KSYM */ { + if (ext->ksym.type_id && ext->is_set) { /* typed ksyms */ + insn[0].src_reg = BPF_PSEUDO_BTF_ID; + insn[0].imm = ext->ksym.kernel_btf_id; + insn[1].imm = ext->ksym.kernel_btf_obj_fd; + } else { /* typeless ksyms or unresolved typed ksyms */ + insn[0].imm = (__u32)ext->ksym.addr; + insn[1].imm = ext->ksym.addr >> 32; + } + } + break; + case RELO_EXTERN_FUNC: + ext = &obj->externs[relo->sym_off]; + insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL; + if (ext->is_set) { + insn[0].imm = ext->ksym.kernel_btf_id; + insn[0].off = ext->ksym.btf_fd_idx; + } else { /* unresolved weak kfunc */ + insn[0].imm = 0; + insn[0].off = 0; + } + break; + case RELO_SUBPROG_ADDR: + if (insn[0].src_reg != BPF_PSEUDO_FUNC) { + pr_warn("prog '%s': relo #%d: bad insn\n", + prog->name, i); + return -EINVAL; + } + /* handled already */ + break; + case RELO_CALL: + /* handled already */ + break; + case RELO_CORE: + /* will be handled by bpf_program_record_relos() */ + break; + default: + pr_warn("prog '%s': relo #%d: bad relo type %d\n", + prog->name, i, relo->type); + return -EINVAL; + } + } + + return 0; +} + +static int adjust_prog_btf_ext_info(const struct bpf_object *obj, + const struct bpf_program *prog, + const struct btf_ext_info *ext_info, + void **prog_info, __u32 *prog_rec_cnt, + __u32 *prog_rec_sz) +{ + void *copy_start = NULL, *copy_end = NULL; + void *rec, *rec_end, *new_prog_info; + const struct btf_ext_info_sec *sec; + size_t old_sz, new_sz; + int i, sec_num, sec_idx, off_adj; + + sec_num = 0; + for_each_btf_ext_sec(ext_info, sec) { + sec_idx = ext_info->sec_idxs[sec_num]; + sec_num++; + if (prog->sec_idx != sec_idx) + continue; + + for_each_btf_ext_rec(ext_info, sec, i, rec) { + __u32 insn_off = *(__u32 *)rec / BPF_INSN_SZ; + + if (insn_off < prog->sec_insn_off) + continue; + if (insn_off >= prog->sec_insn_off + prog->sec_insn_cnt) + break; + + if (!copy_start) + copy_start = rec; + copy_end = rec + ext_info->rec_size; + } + + if (!copy_start) + return -ENOENT; + + /* append func/line info of a given (sub-)program to the main + * program func/line info + */ + old_sz = (size_t)(*prog_rec_cnt) * ext_info->rec_size; + new_sz = old_sz + (copy_end - copy_start); + new_prog_info = realloc(*prog_info, new_sz); + if (!new_prog_info) + return -ENOMEM; + *prog_info = new_prog_info; + *prog_rec_cnt = new_sz / ext_info->rec_size; + memcpy(new_prog_info + old_sz, copy_start, copy_end - copy_start); + + /* Kernel instruction offsets are in units of 8-byte + * instructions, while .BTF.ext instruction offsets generated + * by Clang are in units of bytes. So convert Clang offsets + * into kernel offsets and adjust offset according to program + * relocated position. + */ + off_adj = prog->sub_insn_off - prog->sec_insn_off; + rec = new_prog_info + old_sz; + rec_end = new_prog_info + new_sz; + for (; rec < rec_end; rec += ext_info->rec_size) { + __u32 *insn_off = rec; + + *insn_off = *insn_off / BPF_INSN_SZ + off_adj; + } + *prog_rec_sz = ext_info->rec_size; + return 0; + } + + return -ENOENT; +} + +static int +reloc_prog_func_and_line_info(const struct bpf_object *obj, + struct bpf_program *main_prog, + const struct bpf_program *prog) +{ + int err; + + /* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't + * supprot func/line info + */ + if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC)) + return 0; + + /* only attempt func info relocation if main program's func_info + * relocation was successful + */ + if (main_prog != prog && !main_prog->func_info) + goto line_info; + + err = adjust_prog_btf_ext_info(obj, prog, &obj->btf_ext->func_info, + &main_prog->func_info, + &main_prog->func_info_cnt, + &main_prog->func_info_rec_size); + if (err) { + if (err != -ENOENT) { + pr_warn("prog '%s': error relocating .BTF.ext function info: %d\n", + prog->name, err); + return err; + } + if (main_prog->func_info) { + /* + * Some info has already been found but has problem + * in the last btf_ext reloc. Must have to error out. + */ + pr_warn("prog '%s': missing .BTF.ext function info.\n", prog->name); + return err; + } + /* Have problem loading the very first info. Ignore the rest. */ + pr_warn("prog '%s': missing .BTF.ext function info for the main program, skipping all of .BTF.ext func info.\n", + prog->name); + } + +line_info: + /* don't relocate line info if main program's relocation failed */ + if (main_prog != prog && !main_prog->line_info) + return 0; + + err = adjust_prog_btf_ext_info(obj, prog, &obj->btf_ext->line_info, + &main_prog->line_info, + &main_prog->line_info_cnt, + &main_prog->line_info_rec_size); + if (err) { + if (err != -ENOENT) { + pr_warn("prog '%s': error relocating .BTF.ext line info: %d\n", + prog->name, err); + return err; + } + if (main_prog->line_info) { + /* + * Some info has already been found but has problem + * in the last btf_ext reloc. Must have to error out. + */ + pr_warn("prog '%s': missing .BTF.ext line info.\n", prog->name); + return err; + } + /* Have problem loading the very first info. Ignore the rest. */ + pr_warn("prog '%s': missing .BTF.ext line info for the main program, skipping all of .BTF.ext line info.\n", + prog->name); + } + return 0; +} + +static int cmp_relo_by_insn_idx(const void *key, const void *elem) +{ + size_t insn_idx = *(const size_t *)key; + const struct reloc_desc *relo = elem; + + if (insn_idx == relo->insn_idx) + return 0; + return insn_idx < relo->insn_idx ? -1 : 1; +} + +static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, size_t insn_idx) +{ + if (!prog->nr_reloc) + return NULL; + return bsearch(&insn_idx, prog->reloc_desc, prog->nr_reloc, + sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx); +} + +static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_program *subprog) +{ + int new_cnt = main_prog->nr_reloc + subprog->nr_reloc; + struct reloc_desc *relos; + int i; + + if (main_prog == subprog) + return 0; + relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (!relos && new_cnt) + return -ENOMEM; + if (subprog->nr_reloc) + memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, + sizeof(*relos) * subprog->nr_reloc); + + for (i = main_prog->nr_reloc; i < new_cnt; i++) + relos[i].insn_idx += subprog->sub_insn_off; + /* After insn_idx adjustment the 'relos' array is still sorted + * by insn_idx and doesn't break bsearch. + */ + main_prog->reloc_desc = relos; + main_prog->nr_reloc = new_cnt; + return 0; +} + +static int +bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, + struct bpf_program *prog) +{ + size_t sub_insn_idx, insn_idx, new_cnt; + struct bpf_program *subprog; + struct bpf_insn *insns, *insn; + struct reloc_desc *relo; + int err; + + err = reloc_prog_func_and_line_info(obj, main_prog, prog); + if (err) + return err; + + for (insn_idx = 0; insn_idx < prog->sec_insn_cnt; insn_idx++) { + insn = &main_prog->insns[prog->sub_insn_off + insn_idx]; + if (!insn_is_subprog_call(insn) && !insn_is_pseudo_func(insn)) + continue; + + relo = find_prog_insn_relo(prog, insn_idx); + if (relo && relo->type == RELO_EXTERN_FUNC) + /* kfunc relocations will be handled later + * in bpf_object__relocate_data() + */ + continue; + if (relo && relo->type != RELO_CALL && relo->type != RELO_SUBPROG_ADDR) { + pr_warn("prog '%s': unexpected relo for insn #%zu, type %d\n", + prog->name, insn_idx, relo->type); + return -LIBBPF_ERRNO__RELOC; + } + if (relo) { + /* sub-program instruction index is a combination of + * an offset of a symbol pointed to by relocation and + * call instruction's imm field; for global functions, + * call always has imm = -1, but for static functions + * relocation is against STT_SECTION and insn->imm + * points to a start of a static function + * + * for subprog addr relocation, the relo->sym_off + insn->imm is + * the byte offset in the corresponding section. + */ + if (relo->type == RELO_CALL) + sub_insn_idx = relo->sym_off / BPF_INSN_SZ + insn->imm + 1; + else + sub_insn_idx = (relo->sym_off + insn->imm) / BPF_INSN_SZ; + } else if (insn_is_pseudo_func(insn)) { + /* + * RELO_SUBPROG_ADDR relo is always emitted even if both + * functions are in the same section, so it shouldn't reach here. + */ + pr_warn("prog '%s': missing subprog addr relo for insn #%zu\n", + prog->name, insn_idx); + return -LIBBPF_ERRNO__RELOC; + } else { + /* if subprogram call is to a static function within + * the same ELF section, there won't be any relocation + * emitted, but it also means there is no additional + * offset necessary, insns->imm is relative to + * instruction's original position within the section + */ + sub_insn_idx = prog->sec_insn_off + insn_idx + insn->imm + 1; + } + + /* we enforce that sub-programs should be in .text section */ + subprog = find_prog_by_sec_insn(obj, obj->efile.text_shndx, sub_insn_idx); + if (!subprog) { + pr_warn("prog '%s': no .text section found yet sub-program call exists\n", + prog->name); + return -LIBBPF_ERRNO__RELOC; + } + + /* if it's the first call instruction calling into this + * subprogram (meaning this subprog hasn't been processed + * yet) within the context of current main program: + * - append it at the end of main program's instructions blog; + * - process is recursively, while current program is put on hold; + * - if that subprogram calls some other not yet processes + * subprogram, same thing will happen recursively until + * there are no more unprocesses subprograms left to append + * and relocate. + */ + if (subprog->sub_insn_off == 0) { + subprog->sub_insn_off = main_prog->insns_cnt; + + new_cnt = main_prog->insns_cnt + subprog->insns_cnt; + insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); + if (!insns) { + pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); + return -ENOMEM; + } + main_prog->insns = insns; + main_prog->insns_cnt = new_cnt; + + memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, + subprog->insns_cnt * sizeof(*insns)); + + pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", + main_prog->name, subprog->insns_cnt, subprog->name); + + /* The subprog insns are now appended. Append its relos too. */ + err = append_subprog_relos(main_prog, subprog); + if (err) + return err; + err = bpf_object__reloc_code(obj, main_prog, subprog); + if (err) + return err; + } + + /* main_prog->insns memory could have been re-allocated, so + * calculate pointer again + */ + insn = &main_prog->insns[prog->sub_insn_off + insn_idx]; + /* calculate correct instruction position within current main + * prog; each main prog can have a different set of + * subprograms appended (potentially in different order as + * well), so position of any subprog can be different for + * different main programs */ + insn->imm = subprog->sub_insn_off - (prog->sub_insn_off + insn_idx) - 1; + + pr_debug("prog '%s': insn #%zu relocated, imm %d points to subprog '%s' (now at %zu offset)\n", + prog->name, insn_idx, insn->imm, subprog->name, subprog->sub_insn_off); + } + + return 0; +} + +/* + * Relocate sub-program calls. + * + * Algorithm operates as follows. Each entry-point BPF program (referred to as + * main prog) is processed separately. For each subprog (non-entry functions, + * that can be called from either entry progs or other subprogs) gets their + * sub_insn_off reset to zero. This serves as indicator that this subprogram + * hasn't been yet appended and relocated within current main prog. Once its + * relocated, sub_insn_off will point at the position within current main prog + * where given subprog was appended. This will further be used to relocate all + * the call instructions jumping into this subprog. + * + * We start with main program and process all call instructions. If the call + * is into a subprog that hasn't been processed (i.e., subprog->sub_insn_off + * is zero), subprog instructions are appended at the end of main program's + * instruction array. Then main program is "put on hold" while we recursively + * process newly appended subprogram. If that subprogram calls into another + * subprogram that hasn't been appended, new subprogram is appended again to + * the *main* prog's instructions (subprog's instructions are always left + * untouched, as they need to be in unmodified state for subsequent main progs + * and subprog instructions are always sent only as part of a main prog) and + * the process continues recursively. Once all the subprogs called from a main + * prog or any of its subprogs are appended (and relocated), all their + * positions within finalized instructions array are known, so it's easy to + * rewrite call instructions with correct relative offsets, corresponding to + * desired target subprog. + * + * Its important to realize that some subprogs might not be called from some + * main prog and any of its called/used subprogs. Those will keep their + * subprog->sub_insn_off as zero at all times and won't be appended to current + * main prog and won't be relocated within the context of current main prog. + * They might still be used from other main progs later. + * + * Visually this process can be shown as below. Suppose we have two main + * programs mainA and mainB and BPF object contains three subprogs: subA, + * subB, and subC. mainA calls only subA, mainB calls only subC, but subA and + * subC both call subB: + * + * +--------+ +-------+ + * | v v | + * +--+---+ +--+-+-+ +---+--+ + * | subA | | subB | | subC | + * +--+---+ +------+ +---+--+ + * ^ ^ + * | | + * +---+-------+ +------+----+ + * | mainA | | mainB | + * +-----------+ +-----------+ + * + * We'll start relocating mainA, will find subA, append it and start + * processing sub A recursively: + * + * +-----------+------+ + * | mainA | subA | + * +-----------+------+ + * + * At this point we notice that subB is used from subA, so we append it and + * relocate (there are no further subcalls from subB): + * + * +-----------+------+------+ + * | mainA | subA | subB | + * +-----------+------+------+ + * + * At this point, we relocate subA calls, then go one level up and finish with + * relocatin mainA calls. mainA is done. + * + * For mainB process is similar but results in different order. We start with + * mainB and skip subA and subB, as mainB never calls them (at least + * directly), but we see subC is needed, so we append and start processing it: + * + * +-----------+------+ + * | mainB | subC | + * +-----------+------+ + * Now we see subC needs subB, so we go back to it, append and relocate it: + * + * +-----------+------+------+ + * | mainB | subC | subB | + * +-----------+------+------+ + * + * At this point we unwind recursion, relocate calls in subC, then in mainB. + */ +static int +bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog) +{ + struct bpf_program *subprog; + int i, err; + + /* mark all subprogs as not relocated (yet) within the context of + * current main program + */ + for (i = 0; i < obj->nr_programs; i++) { + subprog = &obj->programs[i]; + if (!prog_is_subprog(obj, subprog)) + continue; + + subprog->sub_insn_off = 0; + } + + err = bpf_object__reloc_code(obj, prog, prog); + if (err) + return err; + + return 0; +} + +static void +bpf_object__free_relocs(struct bpf_object *obj) +{ + struct bpf_program *prog; + int i; + + /* free up relocation descriptors */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + zfree(&prog->reloc_desc); + prog->nr_reloc = 0; + } +} + +static int cmp_relocs(const void *_a, const void *_b) +{ + const struct reloc_desc *a = _a; + const struct reloc_desc *b = _b; + + if (a->insn_idx != b->insn_idx) + return a->insn_idx < b->insn_idx ? -1 : 1; + + /* no two relocations should have the same insn_idx, but ... */ + if (a->type != b->type) + return a->type < b->type ? -1 : 1; + + return 0; +} + +static void bpf_object__sort_relos(struct bpf_object *obj) +{ + int i; + + for (i = 0; i < obj->nr_programs; i++) { + struct bpf_program *p = &obj->programs[i]; + + if (!p->nr_reloc) + continue; + + qsort(p->reloc_desc, p->nr_reloc, sizeof(*p->reloc_desc), cmp_relocs); + } +} + +static int +bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) +{ + struct bpf_program *prog; + size_t i, j; + 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; + } + bpf_object__sort_relos(obj); + } + + /* Before relocating calls pre-process relocations and mark + * few ld_imm64 instructions that points to subprogs. + * Otherwise bpf_object__reloc_code() later would have to consider + * all ld_imm64 insns as relocation candidates. That would + * reduce relocation speed, since amount of find_prog_insn_relo() + * would increase and most of them will fail to find a relo. + */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + for (j = 0; j < prog->nr_reloc; j++) { + struct reloc_desc *relo = &prog->reloc_desc[j]; + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; + + /* mark the insn, so it's recognized by insn_is_pseudo_func() */ + if (relo->type == RELO_SUBPROG_ADDR) + insn[0].src_reg = BPF_PSEUDO_FUNC; + } + } + + /* relocate subprogram calls and append used subprograms to main + * programs; each copy of subprogram code needs to be relocated + * differently for each main program, because its code location might + * have changed. + * Append subprog relos to main programs to allow data relos to be + * processed after text is completely relocated. + */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + /* sub-program's sub-calls are relocated within the context of + * its main program only + */ + if (prog_is_subprog(obj, prog)) + continue; + if (!prog->autoload) + continue; + + err = bpf_object__relocate_calls(obj, prog); + if (err) { + pr_warn("prog '%s': failed to relocate calls: %d\n", + prog->name, err); + return err; + } + } + /* Process data relos for main programs */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + if (prog_is_subprog(obj, prog)) + continue; + if (!prog->autoload) + continue; + err = bpf_object__relocate_data(obj, prog); + if (err) { + pr_warn("prog '%s': failed to relocate data references: %d\n", + prog->name, err); + return err; + } + } + + return 0; +} + +static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, + Elf64_Shdr *shdr, Elf_Data *data); + +static int bpf_object__collect_map_relos(struct bpf_object *obj, + Elf64_Shdr *shdr, Elf_Data *data) +{ + const int bpf_ptr_sz = 8, host_ptr_sz = sizeof(void *); + int i, j, nrels, new_sz; + const struct btf_var_secinfo *vi = NULL; + const struct btf_type *sec, *var, *def; + struct bpf_map *map = NULL, *targ_map = NULL; + struct bpf_program *targ_prog = NULL; + bool is_prog_array, is_map_in_map; + const struct btf_member *member; + const char *name, *mname, *type; + unsigned int moff; + Elf64_Sym *sym; + Elf64_Rel *rel; + void *tmp; + + if (!obj->efile.btf_maps_sec_btf_id || !obj->btf) + return -EINVAL; + sec = btf__type_by_id(obj->btf, obj->efile.btf_maps_sec_btf_id); + if (!sec) + return -EINVAL; + + nrels = shdr->sh_size / shdr->sh_entsize; + for (i = 0; i < nrels; i++) { + rel = elf_rel_by_idx(data, i); + if (!rel) { + pr_warn(".maps relo #%d: failed to get ELF relo\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + + sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info)); + if (!sym) { + pr_warn(".maps relo #%d: symbol %zx not found\n", + i, (size_t)ELF64_R_SYM(rel->r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + name = elf_sym_str(obj, sym->st_name) ?: "<?>"; + + pr_debug(".maps relo #%d: for %zd value %zd rel->r_offset %zu name %d ('%s')\n", + i, (ssize_t)(rel->r_info >> 32), (size_t)sym->st_value, + (size_t)rel->r_offset, sym->st_name, name); + + for (j = 0; j < obj->nr_maps; j++) { + map = &obj->maps[j]; + if (map->sec_idx != obj->efile.btf_maps_shndx) + continue; + + vi = btf_var_secinfos(sec) + map->btf_var_idx; + if (vi->offset <= rel->r_offset && + rel->r_offset + bpf_ptr_sz <= vi->offset + vi->size) + break; + } + if (j == obj->nr_maps) { + pr_warn(".maps relo #%d: cannot find map '%s' at rel->r_offset %zu\n", + i, name, (size_t)rel->r_offset); + return -EINVAL; + } + + is_map_in_map = bpf_map_type__is_map_in_map(map->def.type); + is_prog_array = map->def.type == BPF_MAP_TYPE_PROG_ARRAY; + type = is_map_in_map ? "map" : "prog"; + if (is_map_in_map) { + if (sym->st_shndx != obj->efile.btf_maps_shndx) { + pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && + map->def.key_size != sizeof(int)) { + pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", + i, map->name, sizeof(int)); + return -EINVAL; + } + targ_map = bpf_object__find_map_by_name(obj, name); + if (!targ_map) { + pr_warn(".maps relo #%d: '%s' isn't a valid map reference\n", + i, name); + return -ESRCH; + } + } else if (is_prog_array) { + targ_prog = bpf_object__find_program_by_name(obj, name); + if (!targ_prog) { + pr_warn(".maps relo #%d: '%s' isn't a valid program reference\n", + i, name); + return -ESRCH; + } + if (targ_prog->sec_idx != sym->st_shndx || + targ_prog->sec_insn_off * 8 != sym->st_value || + prog_is_subprog(obj, targ_prog)) { + pr_warn(".maps relo #%d: '%s' isn't an entry-point program\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + } else { + return -EINVAL; + } + + var = btf__type_by_id(obj->btf, vi->type); + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (btf_vlen(def) == 0) + return -EINVAL; + member = btf_members(def) + btf_vlen(def) - 1; + mname = btf__name_by_offset(obj->btf, member->name_off); + if (strcmp(mname, "values")) + return -EINVAL; + + moff = btf_member_bit_offset(def, btf_vlen(def) - 1) / 8; + if (rel->r_offset - vi->offset < moff) + return -EINVAL; + + moff = rel->r_offset - vi->offset - moff; + /* here we use BPF pointer size, which is always 64 bit, as we + * are parsing ELF that was built for BPF target + */ + if (moff % bpf_ptr_sz) + return -EINVAL; + moff /= bpf_ptr_sz; + if (moff >= map->init_slots_sz) { + new_sz = moff + 1; + tmp = libbpf_reallocarray(map->init_slots, new_sz, host_ptr_sz); + if (!tmp) + return -ENOMEM; + map->init_slots = tmp; + memset(map->init_slots + map->init_slots_sz, 0, + (new_sz - map->init_slots_sz) * host_ptr_sz); + map->init_slots_sz = new_sz; + } + map->init_slots[moff] = is_map_in_map ? (void *)targ_map : (void *)targ_prog; + + pr_debug(".maps relo #%d: map '%s' slot [%d] points to %s '%s'\n", + i, map->name, moff, type, name); + } + + return 0; +} + +static int bpf_object__collect_relos(struct bpf_object *obj) +{ + int i, err; + + for (i = 0; i < obj->efile.sec_cnt; i++) { + struct elf_sec_desc *sec_desc = &obj->efile.secs[i]; + Elf64_Shdr *shdr; + Elf_Data *data; + int idx; + + if (sec_desc->sec_type != SEC_RELO) + continue; + + shdr = sec_desc->shdr; + data = sec_desc->data; + idx = shdr->sh_info; + + if (shdr->sh_type != SHT_REL) { + pr_warn("internal error at %d\n", __LINE__); + return -LIBBPF_ERRNO__INTERNAL; + } + + if (idx == obj->efile.st_ops_shndx) + err = bpf_object__collect_st_ops_relos(obj, shdr, data); + else if (idx == obj->efile.btf_maps_shndx) + err = bpf_object__collect_map_relos(obj, shdr, data); + else + err = bpf_object__collect_prog_relos(obj, shdr, data); + if (err) + return err; + } + + bpf_object__sort_relos(obj); + return 0; +} + +static bool insn_is_helper_call(struct bpf_insn *insn, enum bpf_func_id *func_id) +{ + if (BPF_CLASS(insn->code) == BPF_JMP && + BPF_OP(insn->code) == BPF_CALL && + BPF_SRC(insn->code) == BPF_K && + insn->src_reg == 0 && + insn->dst_reg == 0) { + *func_id = insn->imm; + return true; + } + return false; +} + +static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program *prog) +{ + struct bpf_insn *insn = prog->insns; + enum bpf_func_id func_id; + int i; + + if (obj->gen_loader) + return 0; + + for (i = 0; i < prog->insns_cnt; i++, insn++) { + if (!insn_is_helper_call(insn, &func_id)) + continue; + + /* on kernels that don't yet support + * bpf_probe_read_{kernel,user}[_str] helpers, fall back + * to bpf_probe_read() which works well for old kernels + */ + switch (func_id) { + case BPF_FUNC_probe_read_kernel: + case BPF_FUNC_probe_read_user: + if (!kernel_supports(obj, FEAT_PROBE_READ_KERN)) + insn->imm = BPF_FUNC_probe_read; + break; + case BPF_FUNC_probe_read_kernel_str: + case BPF_FUNC_probe_read_user_str: + if (!kernel_supports(obj, FEAT_PROBE_READ_KERN)) + insn->imm = BPF_FUNC_probe_read_str; + break; + default: + break; + } + } + return 0; +} + +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id); + +/* this is called as prog->sec_def->prog_prepare_load_fn for libbpf-supported sec_defs */ +static int libbpf_prepare_prog_load(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie) +{ + enum sec_def_flags def = cookie; + + /* old kernels might not support specifying expected_attach_type */ + if ((def & SEC_EXP_ATTACH_OPT) && !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE)) + opts->expected_attach_type = 0; + + if (def & SEC_SLEEPABLE) + opts->prog_flags |= BPF_F_SLEEPABLE; + + if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS)) + opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; + + if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) { + int btf_obj_fd = 0, btf_type_id = 0, err; + const char *attach_name; + + attach_name = strchr(prog->sec_name, '/'); + if (!attach_name) { + /* if BPF program is annotated with just SEC("fentry") + * (or similar) without declaratively specifying + * target, then it is expected that target will be + * specified with bpf_program__set_attach_target() at + * runtime before BPF object load step. If not, then + * there is nothing to load into the kernel as BPF + * verifier won't be able to validate BPF program + * correctness anyways. + */ + pr_warn("prog '%s': no BTF-based attach target is specified, use bpf_program__set_attach_target()\n", + prog->name); + return -EINVAL; + } + attach_name++; /* skip over / */ + + err = libbpf_find_attach_btf_id(prog, attach_name, &btf_obj_fd, &btf_type_id); + if (err) + return err; + + /* cache resolved BTF FD and BTF type ID in the prog */ + prog->attach_btf_obj_fd = btf_obj_fd; + prog->attach_btf_id = btf_type_id; + + /* but by now libbpf common logic is not utilizing + * prog->atach_btf_obj_fd/prog->attach_btf_id anymore because + * this callback is called after opts were populated by + * libbpf, so this callback has to update opts explicitly here + */ + opts->attach_btf_obj_fd = btf_obj_fd; + opts->attach_btf_id = btf_type_id; + } + return 0; +} + +static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_sz); + +static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog, + struct bpf_insn *insns, int insns_cnt, + const char *license, __u32 kern_version, int *prog_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_attr); + const char *prog_name = NULL; + char *cp, errmsg[STRERR_BUFSIZE]; + size_t log_buf_size = 0; + char *log_buf = NULL, *tmp; + int btf_fd, ret, err; + bool own_log_buf = true; + __u32 log_level = prog->log_level; + + if (prog->type == BPF_PROG_TYPE_UNSPEC) { + /* + * The program type must be set. Most likely we couldn't find a proper + * section definition at load time, and thus we didn't infer the type. + */ + pr_warn("prog '%s': missing BPF prog type, check ELF section name '%s'\n", + prog->name, prog->sec_name); + return -EINVAL; + } + + if (!insns || !insns_cnt) + return -EINVAL; + + load_attr.expected_attach_type = prog->expected_attach_type; + if (kernel_supports(obj, FEAT_PROG_NAME)) + prog_name = prog->name; + load_attr.attach_prog_fd = prog->attach_prog_fd; + load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; + load_attr.attach_btf_id = prog->attach_btf_id; + load_attr.kern_version = kern_version; + load_attr.prog_ifindex = prog->prog_ifindex; + + /* specify func_info/line_info only if kernel supports them */ + btf_fd = bpf_object__btf_fd(obj); + if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { + load_attr.prog_btf_fd = btf_fd; + load_attr.func_info = prog->func_info; + load_attr.func_info_rec_size = prog->func_info_rec_size; + load_attr.func_info_cnt = prog->func_info_cnt; + load_attr.line_info = prog->line_info; + load_attr.line_info_rec_size = prog->line_info_rec_size; + load_attr.line_info_cnt = prog->line_info_cnt; + } + load_attr.log_level = log_level; + load_attr.prog_flags = prog->prog_flags; + load_attr.fd_array = obj->fd_array; + + /* adjust load_attr if sec_def provides custom preload callback */ + if (prog->sec_def && prog->sec_def->prog_prepare_load_fn) { + err = prog->sec_def->prog_prepare_load_fn(prog, &load_attr, prog->sec_def->cookie); + if (err < 0) { + pr_warn("prog '%s': failed to prepare load attributes: %d\n", + prog->name, err); + return err; + } + insns = prog->insns; + insns_cnt = prog->insns_cnt; + } + + if (obj->gen_loader) { + bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name, + license, insns, insns_cnt, &load_attr, + prog - obj->programs); + *prog_fd = -1; + return 0; + } + +retry_load: + /* if log_level is zero, we don't request logs initially even if + * custom log_buf is specified; if the program load fails, then we'll + * bump log_level to 1 and use either custom log_buf or we'll allocate + * our own and retry the load to get details on what failed + */ + if (log_level) { + if (prog->log_buf) { + log_buf = prog->log_buf; + log_buf_size = prog->log_size; + own_log_buf = false; + } else if (obj->log_buf) { + log_buf = obj->log_buf; + log_buf_size = obj->log_size; + own_log_buf = false; + } else { + log_buf_size = max((size_t)BPF_LOG_BUF_SIZE, log_buf_size * 2); + tmp = realloc(log_buf, log_buf_size); + if (!tmp) { + ret = -ENOMEM; + goto out; + } + log_buf = tmp; + log_buf[0] = '\0'; + own_log_buf = true; + } + } + + load_attr.log_buf = log_buf; + load_attr.log_size = log_buf_size; + load_attr.log_level = log_level; + + ret = bpf_prog_load(prog->type, prog_name, license, insns, insns_cnt, &load_attr); + if (ret >= 0) { + if (log_level && own_log_buf) { + pr_debug("prog '%s': -- BEGIN PROG LOAD LOG --\n%s-- END PROG LOAD LOG --\n", + prog->name, log_buf); + } + + if (obj->has_rodata && kernel_supports(obj, FEAT_PROG_BIND_MAP)) { + struct bpf_map *map; + int i; + + for (i = 0; i < obj->nr_maps; i++) { + map = &prog->obj->maps[i]; + if (map->libbpf_type != LIBBPF_MAP_RODATA) + continue; + + if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("prog '%s': failed to bind map '%s': %s\n", + prog->name, map->real_name, cp); + /* Don't fail hard if can't bind rodata. */ + } + } + } + + *prog_fd = ret; + ret = 0; + goto out; + } + + if (log_level == 0) { + log_level = 1; + goto retry_load; + } + /* On ENOSPC, increase log buffer size and retry, unless custom + * log_buf is specified. + * Be careful to not overflow u32, though. Kernel's log buf size limit + * isn't part of UAPI so it can always be bumped to full 4GB. So don't + * multiply by 2 unless we are sure we'll fit within 32 bits. + * Currently, we'll get -EINVAL when we reach (UINT_MAX >> 2). + */ + if (own_log_buf && errno == ENOSPC && log_buf_size <= UINT_MAX / 2) + goto retry_load; + + ret = -errno; + + /* post-process verifier log to improve error descriptions */ + fixup_verifier_log(prog, log_buf, log_buf_size); + + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("prog '%s': BPF program load failed: %s\n", prog->name, cp); + pr_perm_msg(ret); + + if (own_log_buf && log_buf && log_buf[0] != '\0') { + pr_warn("prog '%s': -- BEGIN PROG LOAD LOG --\n%s-- END PROG LOAD LOG --\n", + prog->name, log_buf); + } + +out: + if (own_log_buf) + free(log_buf); + return ret; +} + +static char *find_prev_line(char *buf, char *cur) +{ + char *p; + + if (cur == buf) /* end of a log buf */ + return NULL; + + p = cur - 1; + while (p - 1 >= buf && *(p - 1) != '\n') + p--; + + return p; +} + +static void patch_log(char *buf, size_t buf_sz, size_t log_sz, + char *orig, size_t orig_sz, const char *patch) +{ + /* size of the remaining log content to the right from the to-be-replaced part */ + size_t rem_sz = (buf + log_sz) - (orig + orig_sz); + size_t patch_sz = strlen(patch); + + if (patch_sz != orig_sz) { + /* If patch line(s) are longer than original piece of verifier log, + * shift log contents by (patch_sz - orig_sz) bytes to the right + * starting from after to-be-replaced part of the log. + * + * If patch line(s) are shorter than original piece of verifier log, + * shift log contents by (orig_sz - patch_sz) bytes to the left + * starting from after to-be-replaced part of the log + * + * We need to be careful about not overflowing available + * buf_sz capacity. If that's the case, we'll truncate the end + * of the original log, as necessary. + */ + if (patch_sz > orig_sz) { + if (orig + patch_sz >= buf + buf_sz) { + /* patch is big enough to cover remaining space completely */ + patch_sz -= (orig + patch_sz) - (buf + buf_sz) + 1; + rem_sz = 0; + } else if (patch_sz - orig_sz > buf_sz - log_sz) { + /* patch causes part of remaining log to be truncated */ + rem_sz -= (patch_sz - orig_sz) - (buf_sz - log_sz); + } + } + /* shift remaining log to the right by calculated amount */ + memmove(orig + patch_sz, orig + orig_sz, rem_sz); + } + + memcpy(orig, patch, patch_sz); +} + +static void fixup_log_failed_core_relo(struct bpf_program *prog, + char *buf, size_t buf_sz, size_t log_sz, + char *line1, char *line2, char *line3) +{ + /* Expected log for failed and not properly guarded CO-RE relocation: + * line1 -> 123: (85) call unknown#195896080 + * line2 -> invalid func unknown#195896080 + * line3 -> <anything else or end of buffer> + * + * "123" is the index of the instruction that was poisoned. We extract + * instruction index to find corresponding CO-RE relocation and + * replace this part of the log with more relevant information about + * failed CO-RE relocation. + */ + const struct bpf_core_relo *relo; + struct bpf_core_spec spec; + char patch[512], spec_buf[256]; + int insn_idx, err, spec_len; + + if (sscanf(line1, "%d: (%*d) call unknown#195896080\n", &insn_idx) != 1) + return; + + relo = find_relo_core(prog, insn_idx); + if (!relo) + return; + + err = bpf_core_parse_spec(prog->name, prog->obj->btf, relo, &spec); + if (err) + return; + + spec_len = bpf_core_format_spec(spec_buf, sizeof(spec_buf), &spec); + snprintf(patch, sizeof(patch), + "%d: <invalid CO-RE relocation>\n" + "failed to resolve CO-RE relocation %s%s\n", + insn_idx, spec_buf, spec_len >= sizeof(spec_buf) ? "..." : ""); + + patch_log(buf, buf_sz, log_sz, line1, line3 - line1, patch); +} + +static void fixup_log_missing_map_load(struct bpf_program *prog, + char *buf, size_t buf_sz, size_t log_sz, + char *line1, char *line2, char *line3) +{ + /* Expected log for failed and not properly guarded CO-RE relocation: + * line1 -> 123: (85) call unknown#2001000345 + * line2 -> invalid func unknown#2001000345 + * line3 -> <anything else or end of buffer> + * + * "123" is the index of the instruction that was poisoned. + * "345" in "2001000345" are map index in obj->maps to fetch map name. + */ + struct bpf_object *obj = prog->obj; + const struct bpf_map *map; + int insn_idx, map_idx; + char patch[128]; + + if (sscanf(line1, "%d: (%*d) call unknown#%d\n", &insn_idx, &map_idx) != 2) + return; + + map_idx -= MAP_LDIMM64_POISON_BASE; + if (map_idx < 0 || map_idx >= obj->nr_maps) + return; + map = &obj->maps[map_idx]; + + snprintf(patch, sizeof(patch), + "%d: <invalid BPF map reference>\n" + "BPF map '%s' is referenced but wasn't created\n", + insn_idx, map->name); + + patch_log(buf, buf_sz, log_sz, line1, line3 - line1, patch); +} + +static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_sz) +{ + /* look for familiar error patterns in last N lines of the log */ + const size_t max_last_line_cnt = 10; + char *prev_line, *cur_line, *next_line; + size_t log_sz; + int i; + + if (!buf) + return; + + log_sz = strlen(buf) + 1; + next_line = buf + log_sz - 1; + + for (i = 0; i < max_last_line_cnt; i++, next_line = cur_line) { + cur_line = find_prev_line(buf, next_line); + if (!cur_line) + return; + + /* failed CO-RE relocation case */ + if (str_has_pfx(cur_line, "invalid func unknown#195896080\n")) { + prev_line = find_prev_line(buf, cur_line); + if (!prev_line) + continue; + + fixup_log_failed_core_relo(prog, buf, buf_sz, log_sz, + prev_line, cur_line, next_line); + return; + } else if (str_has_pfx(cur_line, "invalid func unknown#"MAP_LDIMM64_POISON_PFX)) { + prev_line = find_prev_line(buf, cur_line); + if (!prev_line) + continue; + + fixup_log_missing_map_load(prog, buf, buf_sz, log_sz, + prev_line, cur_line, next_line); + return; + } + } +} + +static int bpf_program_record_relos(struct bpf_program *prog) +{ + struct bpf_object *obj = prog->obj; + int i; + + for (i = 0; i < prog->nr_reloc; i++) { + struct reloc_desc *relo = &prog->reloc_desc[i]; + struct extern_desc *ext = &obj->externs[relo->sym_off]; + + switch (relo->type) { + case RELO_EXTERN_VAR: + if (ext->type != EXT_KSYM) + continue; + bpf_gen__record_extern(obj->gen_loader, ext->name, + ext->is_weak, !ext->ksym.type_id, + BTF_KIND_VAR, relo->insn_idx); + break; + case RELO_EXTERN_FUNC: + bpf_gen__record_extern(obj->gen_loader, ext->name, + ext->is_weak, false, BTF_KIND_FUNC, + relo->insn_idx); + break; + case RELO_CORE: { + struct bpf_core_relo cr = { + .insn_off = relo->insn_idx * 8, + .type_id = relo->core_relo->type_id, + .access_str_off = relo->core_relo->access_str_off, + .kind = relo->core_relo->kind, + }; + + bpf_gen__record_relo_core(obj->gen_loader, &cr); + break; + } + default: + continue; + } + } + return 0; +} + +static int +bpf_object__load_progs(struct bpf_object *obj, int log_level) +{ + struct bpf_program *prog; + size_t i; + int err; + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + err = bpf_object__sanitize_prog(obj, prog); + if (err) + return err; + } + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + if (prog_is_subprog(obj, prog)) + continue; + if (!prog->autoload) { + pr_debug("prog '%s': skipped loading\n", prog->name); + continue; + } + prog->log_level |= log_level; + + if (obj->gen_loader) + bpf_program_record_relos(prog); + + err = bpf_object_load_prog(obj, prog, prog->insns, prog->insns_cnt, + obj->license, obj->kern_version, &prog->fd); + if (err) { + pr_warn("prog '%s': failed to load: %d\n", prog->name, err); + return err; + } + } + + bpf_object__free_relocs(obj); + return 0; +} + +static const struct bpf_sec_def *find_sec_def(const char *sec_name); + +static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts) +{ + struct bpf_program *prog; + int err; + + bpf_object__for_each_program(prog, obj) { + prog->sec_def = find_sec_def(prog->sec_name); + if (!prog->sec_def) { + /* couldn't guess, but user might manually specify */ + pr_debug("prog '%s': unrecognized ELF section name '%s'\n", + prog->name, prog->sec_name); + continue; + } + + prog->type = prog->sec_def->prog_type; + prog->expected_attach_type = prog->sec_def->expected_attach_type; + + /* sec_def can have custom callback which should be called + * after bpf_program is initialized to adjust its properties + */ + if (prog->sec_def->prog_setup_fn) { + err = prog->sec_def->prog_setup_fn(prog, prog->sec_def->cookie); + if (err < 0) { + pr_warn("prog '%s': failed to initialize: %d\n", + prog->name, err); + return err; + } + } + } + + return 0; +} + +static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, + const struct bpf_object_open_opts *opts) +{ + const char *obj_name, *kconfig, *btf_tmp_path; + struct bpf_object *obj; + char tmp_name[64]; + int err; + char *log_buf; + size_t log_size; + __u32 log_level; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn("failed to init libelf for %s\n", + path ? : "(mem buf)"); + return ERR_PTR(-LIBBPF_ERRNO__LIBELF); + } + + 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); + } + + log_buf = OPTS_GET(opts, kernel_log_buf, NULL); + log_size = OPTS_GET(opts, kernel_log_size, 0); + log_level = OPTS_GET(opts, kernel_log_level, 0); + if (log_size > UINT_MAX) + return ERR_PTR(-EINVAL); + if (log_size && !log_buf) + return ERR_PTR(-EINVAL); + + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); + if (IS_ERR(obj)) + return obj; + + obj->log_buf = log_buf; + obj->log_size = log_size; + obj->log_level = log_level; + + btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL); + if (btf_tmp_path) { + if (strlen(btf_tmp_path) >= PATH_MAX) { + err = -ENAMETOOLONG; + goto out; + } + obj->btf_custom_path = strdup(btf_tmp_path); + if (!obj->btf_custom_path) { + err = -ENOMEM; + goto out; + } + } + + kconfig = OPTS_GET(opts, kconfig, NULL); + if (kconfig) { + obj->kconfig = strdup(kconfig); + if (!obj->kconfig) { + err = -ENOMEM; + goto out; + } + } + + 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_progs(obj, opts); + err = err ? : bpf_object__collect_relos(obj); + if (err) + goto out; + + bpf_object__elf_finish(obj); + + return obj; +out: + bpf_object__close(obj); + return ERR_PTR(err); +} + +struct bpf_object * +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) +{ + if (!path) + return libbpf_err_ptr(-EINVAL); + + pr_debug("loading %s\n", path); + + return libbpf_ptr(bpf_object_open(path, NULL, 0, opts)); +} + +struct bpf_object *bpf_object__open(const char *path) +{ + return bpf_object__open_file(path, NULL); +} + +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 libbpf_err_ptr(-EINVAL); + + return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts)); +} + +static int bpf_object_unload(struct bpf_object *obj) +{ + size_t i; + + if (!obj) + return libbpf_err(-EINVAL); + + 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]); + + 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 (!kernel_supports(obj, FEAT_ARRAY_MMAP)) + m->def.map_flags ^= BPF_F_MMAPABLE; + } + + return 0; +} + +int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) +{ + char sym_type, sym_name[500]; + unsigned long long sym_addr; + int ret, err = 0; + FILE *f; + + f = fopen("/proc/kallsyms", "r"); + if (!f) { + err = -errno; + pr_warn("failed to open /proc/kallsyms: %d\n", err); + return err; + } + + while (true) { + ret = fscanf(f, "%llx %c %499s%*[^\n]\n", + &sym_addr, &sym_type, sym_name); + if (ret == EOF && feof(f)) + break; + if (ret != 3) { + pr_warn("failed to read kallsyms entry: %d\n", ret); + err = -EINVAL; + break; + } + + err = cb(sym_addr, sym_type, sym_name, ctx); + if (err) + break; + } + + fclose(f); + return err; +} + +static int kallsyms_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct bpf_object *obj = ctx; + const struct btf_type *t; + struct extern_desc *ext; + + ext = find_extern_by_name(obj, sym_name); + if (!ext || ext->type != EXT_KSYM) + return 0; + + t = btf__type_by_id(obj->btf, ext->btf_id); + if (!btf_is_var(t)) + return 0; + + if (ext->is_set && ext->ksym.addr != sym_addr) { + pr_warn("extern (ksym) '%s': resolution is ambiguous: 0x%llx or 0x%llx\n", + sym_name, ext->ksym.addr, sym_addr); + return -EINVAL; + } + if (!ext->is_set) { + ext->is_set = true; + ext->ksym.addr = sym_addr; + pr_debug("extern (ksym) '%s': set to 0x%llx\n", sym_name, sym_addr); + } + return 0; +} + +static int bpf_object__read_kallsyms_file(struct bpf_object *obj) +{ + return libbpf_kallsyms_parse(kallsyms_cb, obj); +} + +static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, + __u16 kind, struct btf **res_btf, + struct module_btf **res_mod_btf) +{ + struct module_btf *mod_btf; + struct btf *btf; + int i, id, err; + + btf = obj->btf_vmlinux; + mod_btf = NULL; + id = btf__find_by_name_kind(btf, ksym_name, kind); + + if (id == -ENOENT) { + err = load_module_btfs(obj); + if (err) + return err; + + for (i = 0; i < obj->btf_module_cnt; i++) { + /* we assume module_btf's BTF FD is always >0 */ + mod_btf = &obj->btf_modules[i]; + btf = mod_btf->btf; + id = btf__find_by_name_kind_own(btf, ksym_name, kind); + if (id != -ENOENT) + break; + } + } + if (id <= 0) + return -ESRCH; + + *res_btf = btf; + *res_mod_btf = mod_btf; + return id; +} + +static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj, + struct extern_desc *ext) +{ + const struct btf_type *targ_var, *targ_type; + __u32 targ_type_id, local_type_id; + struct module_btf *mod_btf = NULL; + const char *targ_var_name; + struct btf *btf = NULL; + int id, err; + + id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &mod_btf); + if (id < 0) { + if (id == -ESRCH && ext->is_weak) + return 0; + pr_warn("extern (var ksym) '%s': not found in kernel BTF\n", + ext->name); + return id; + } + + /* find local type_id */ + local_type_id = ext->ksym.type_id; + + /* find target type_id */ + targ_var = btf__type_by_id(btf, id); + targ_var_name = btf__name_by_offset(btf, targ_var->name_off); + targ_type = skip_mods_and_typedefs(btf, targ_var->type, &targ_type_id); + + err = bpf_core_types_are_compat(obj->btf, local_type_id, + btf, targ_type_id); + if (err <= 0) { + const struct btf_type *local_type; + const char *targ_name, *local_name; + + local_type = btf__type_by_id(obj->btf, local_type_id); + local_name = btf__name_by_offset(obj->btf, local_type->name_off); + targ_name = btf__name_by_offset(btf, targ_type->name_off); + + pr_warn("extern (var ksym) '%s': incompatible types, expected [%d] %s %s, but kernel has [%d] %s %s\n", + ext->name, local_type_id, + btf_kind_str(local_type), local_name, targ_type_id, + btf_kind_str(targ_type), targ_name); + return -EINVAL; + } + + ext->is_set = true; + ext->ksym.kernel_btf_obj_fd = mod_btf ? mod_btf->fd : 0; + ext->ksym.kernel_btf_id = id; + pr_debug("extern (var ksym) '%s': resolved to [%d] %s %s\n", + ext->name, id, btf_kind_str(targ_var), targ_var_name); + + return 0; +} + +static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, + struct extern_desc *ext) +{ + int local_func_proto_id, kfunc_proto_id, kfunc_id; + struct module_btf *mod_btf = NULL; + const struct btf_type *kern_func; + struct btf *kern_btf = NULL; + int ret; + + local_func_proto_id = ext->ksym.type_id; + + kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf); + if (kfunc_id < 0) { + if (kfunc_id == -ESRCH && ext->is_weak) + return 0; + pr_warn("extern (func ksym) '%s': not found in kernel or module BTFs\n", + ext->name); + return kfunc_id; + } + + kern_func = btf__type_by_id(kern_btf, kfunc_id); + kfunc_proto_id = kern_func->type; + + ret = bpf_core_types_are_compat(obj->btf, local_func_proto_id, + kern_btf, kfunc_proto_id); + if (ret <= 0) { + pr_warn("extern (func ksym) '%s': func_proto [%d] incompatible with kernel [%d]\n", + ext->name, local_func_proto_id, kfunc_proto_id); + return -EINVAL; + } + + /* set index for module BTF fd in fd_array, if unset */ + if (mod_btf && !mod_btf->fd_array_idx) { + /* insn->off is s16 */ + if (obj->fd_array_cnt == INT16_MAX) { + pr_warn("extern (func ksym) '%s': module BTF fd index %d too big to fit in bpf_insn offset\n", + ext->name, mod_btf->fd_array_idx); + return -E2BIG; + } + /* Cannot use index 0 for module BTF fd */ + if (!obj->fd_array_cnt) + obj->fd_array_cnt = 1; + + ret = libbpf_ensure_mem((void **)&obj->fd_array, &obj->fd_array_cap, sizeof(int), + obj->fd_array_cnt + 1); + if (ret) + return ret; + mod_btf->fd_array_idx = obj->fd_array_cnt; + /* we assume module BTF FD is always >0 */ + obj->fd_array[obj->fd_array_cnt++] = mod_btf->fd; + } + + ext->is_set = true; + ext->ksym.kernel_btf_id = kfunc_id; + ext->ksym.btf_fd_idx = mod_btf ? mod_btf->fd_array_idx : 0; + pr_debug("extern (func ksym) '%s': resolved to kernel [%d]\n", + ext->name, kfunc_id); + + return 0; +} + +static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj) +{ + const struct btf_type *t; + struct extern_desc *ext; + int i, err; + + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (ext->type != EXT_KSYM || !ext->ksym.type_id) + continue; + + if (obj->gen_loader) { + ext->is_set = true; + ext->ksym.kernel_btf_obj_fd = 0; + ext->ksym.kernel_btf_id = 0; + continue; + } + t = btf__type_by_id(obj->btf, ext->btf_id); + if (btf_is_var(t)) + err = bpf_object__resolve_ksym_var_btf_id(obj, ext); + else + err = bpf_object__resolve_ksym_func_btf_id(obj, ext); + if (err) + return err; + } + return 0; +} + +static int bpf_object__resolve_externs(struct bpf_object *obj, + const char *extra_kconfig) +{ + bool need_config = false, need_kallsyms = false; + bool need_vmlinux_btf = false; + struct extern_desc *ext; + void *kcfg_data = NULL; + int err, i; + + if (obj->nr_extern == 0) + return 0; + + if (obj->kconfig_map_idx >= 0) + kcfg_data = obj->maps[obj->kconfig_map_idx].mmaped; + + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + + if (ext->type == EXT_KSYM) { + if (ext->ksym.type_id) + need_vmlinux_btf = true; + else + need_kallsyms = true; + continue; + } else if (ext->type == EXT_KCFG) { + void *ext_ptr = kcfg_data + ext->kcfg.data_off; + __u64 value = 0; + + /* Kconfig externs need actual /proc/config.gz */ + if (str_has_pfx(ext->name, "CONFIG_")) { + need_config = true; + continue; + } + + /* Virtual kcfg externs are customly handled by libbpf */ + if (strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) { + value = get_kernel_version(); + if (!value) { + pr_warn("extern (kcfg) '%s': failed to get kernel version\n", ext->name); + return -EINVAL; + } + } else if (strcmp(ext->name, "LINUX_HAS_BPF_COOKIE") == 0) { + value = kernel_supports(obj, FEAT_BPF_COOKIE); + } else if (strcmp(ext->name, "LINUX_HAS_SYSCALL_WRAPPER") == 0) { + value = kernel_supports(obj, FEAT_SYSCALL_WRAPPER); + } else if (!str_has_pfx(ext->name, "LINUX_") || !ext->is_weak) { + /* Currently libbpf supports only CONFIG_ and LINUX_ prefixed + * __kconfig externs, where LINUX_ ones are virtual and filled out + * customly by libbpf (their values don't come from Kconfig). + * If LINUX_xxx variable is not recognized by libbpf, but is marked + * __weak, it defaults to zero value, just like for CONFIG_xxx + * externs. + */ + pr_warn("extern (kcfg) '%s': unrecognized virtual extern\n", ext->name); + return -EINVAL; + } + + err = set_kcfg_value_num(ext, ext_ptr, value); + if (err) + return err; + pr_debug("extern (kcfg) '%s': set to 0x%llx\n", + ext->name, (long long)value); + } else { + pr_warn("extern '%s': unrecognized extern kind\n", ext->name); + return -EINVAL; + } + } + if (need_config && extra_kconfig) { + err = bpf_object__read_kconfig_mem(obj, extra_kconfig, kcfg_data); + if (err) + return -EINVAL; + need_config = false; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (ext->type == EXT_KCFG && !ext->is_set) { + need_config = true; + break; + } + } + } + if (need_config) { + err = bpf_object__read_kconfig_file(obj, kcfg_data); + if (err) + return -EINVAL; + } + if (need_kallsyms) { + err = bpf_object__read_kallsyms_file(obj); + if (err) + return -EINVAL; + } + if (need_vmlinux_btf) { + err = bpf_object__resolve_ksyms_btf_id(obj); + 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; +} + +static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) +{ + int err, i; + + if (!obj) + return libbpf_err(-EINVAL); + + if (obj->loaded) { + pr_warn("object '%s': load can't be attempted twice\n", obj->name); + return libbpf_err(-EINVAL); + } + + if (obj->gen_loader) + bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); + + err = bpf_object__probe_loading(obj); + err = err ? : bpf_object__load_vmlinux_btf(obj, false); + err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); + err = err ? : bpf_object__sanitize_and_load_btf(obj); + err = err ? : bpf_object__sanitize_maps(obj); + err = err ? : bpf_object__init_kern_struct_ops_maps(obj); + err = err ? : bpf_object__create_maps(obj); + err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); + err = err ? : bpf_object__load_progs(obj, extra_log_level); + err = err ? : bpf_object_init_prog_arrays(obj); + + if (obj->gen_loader) { + /* reset FDs */ + if (obj->btf) + btf__set_fd(obj->btf, -1); + for (i = 0; i < obj->nr_maps; i++) + obj->maps[i].fd = -1; + if (!err) + err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); + } + + /* clean up fd_array */ + zfree(&obj->fd_array); + + /* clean up module BTFs */ + for (i = 0; i < obj->btf_module_cnt; i++) { + close(obj->btf_modules[i].fd); + btf__free(obj->btf_modules[i].btf); + free(obj->btf_modules[i].name); + } + free(obj->btf_modules); + + /* clean up vmlinux BTF */ + btf__free(obj->btf_vmlinux); + obj->btf_vmlinux = NULL; + + obj->loaded = true; /* doesn't matter if successfully or not */ + + 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_warn("failed to load object '%s'\n", obj->path); + return libbpf_err(err); +} + +int bpf_object__load(struct bpf_object *obj) +{ + return bpf_object_load(obj, 0, NULL); +} + +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]; + struct statfs st_fs; + char *dname, *dir; + int err = 0; + + if (path == NULL) + return -EINVAL; + + dname = strdup(path); + if (dname == NULL) + return -ENOMEM; + + dir = dirname(dname); + if (statfs(dir, &st_fs)) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("failed to statfs %s: %s\n", dir, cp); + err = -errno; + } + free(dname); + + if (!err && st_fs.f_type != BPF_FS_MAGIC) { + pr_warn("specified path %s is not on BPF FS\n", path); + err = -EINVAL; + } + + return err; +} + +int bpf_program__pin(struct bpf_program *prog, const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err; + + if (prog->fd < 0) { + pr_warn("prog '%s': can't pin program that wasn't loaded\n", prog->name); + return libbpf_err(-EINVAL); + } + + err = make_parent_dir(path); + if (err) + return libbpf_err(err); + + err = check_path(path); + if (err) + return libbpf_err(err); + + if (bpf_obj_pin(prog->fd, path)) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("prog '%s': failed to pin at '%s': %s\n", prog->name, path, cp); + return libbpf_err(err); + } + + pr_debug("prog '%s': pinned at '%s'\n", prog->name, path); + return 0; +} + +int bpf_program__unpin(struct bpf_program *prog, const char *path) +{ + int err; + + if (prog->fd < 0) { + pr_warn("prog '%s': can't unpin program that wasn't loaded\n", prog->name); + return libbpf_err(-EINVAL); + } + + err = check_path(path); + if (err) + return libbpf_err(err); + + err = unlink(path); + if (err) + return libbpf_err(-errno); + + pr_debug("prog '%s': unpinned from '%s'\n", prog->name, path); + return 0; +} + +int bpf_map__pin(struct bpf_map *map, const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err; + + if (map == NULL) { + pr_warn("invalid map pointer\n"); + return libbpf_err(-EINVAL); + } + + if (map->pin_path) { + if (path && strcmp(path, map->pin_path)) { + pr_warn("map '%s' already has pin path '%s' different from '%s'\n", + bpf_map__name(map), map->pin_path, path); + return libbpf_err(-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 libbpf_err(-EINVAL); + } else if (map->pinned) { + pr_warn("map '%s' already pinned\n", bpf_map__name(map)); + return libbpf_err(-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 libbpf_err(err); + + err = check_path(map->pin_path); + if (err) + return libbpf_err(err); + + if (bpf_obj_pin(map->fd, map->pin_path)) { + err = -errno; + goto out_err; + } + + map->pinned = true; + pr_debug("pinned map '%s'\n", map->pin_path); + + return 0; + +out_err: + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("failed to pin map: %s\n", cp); + return libbpf_err(err); +} + +int bpf_map__unpin(struct bpf_map *map, const char *path) +{ + int err; + + if (map == NULL) { + pr_warn("invalid map pointer\n"); + return libbpf_err(-EINVAL); + } + + if (map->pin_path) { + if (path && strcmp(path, map->pin_path)) { + pr_warn("map '%s' already has pin path '%s' different from '%s'\n", + bpf_map__name(map), map->pin_path, path); + return libbpf_err(-EINVAL); + } + path = map->pin_path; + } else if (!path) { + pr_warn("no path to unpin map '%s' from\n", + bpf_map__name(map)); + return libbpf_err(-EINVAL); + } + + err = check_path(path); + if (err) + return libbpf_err(err); + + err = unlink(path); + if (err != 0) + return libbpf_err(-errno); + + 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 libbpf_err(-errno); + } + + free(map->pin_path); + map->pin_path = new; + return 0; +} + +__alias(bpf_map__pin_path) +const char *bpf_map__get_pin_path(const struct bpf_map *map); + +const char *bpf_map__pin_path(const struct bpf_map *map) +{ + return map->pin_path; +} + +bool bpf_map__is_pinned(const struct bpf_map *map) +{ + return map->pinned; +} + +static void sanitize_pin_path(char *s) +{ + /* bpffs disallows periods in path names */ + while (*s) { + if (*s == '.') + *s = '_'; + s++; + } +} + +int bpf_object__pin_maps(struct bpf_object *obj, const char *path) +{ + struct bpf_map *map; + int err; + + if (!obj) + return libbpf_err(-ENOENT); + + if (!obj->loaded) { + pr_warn("object not yet loaded; load it first\n"); + return libbpf_err(-ENOENT); + } + + bpf_object__for_each_map(map, obj) { + char *pin_path = NULL; + char buf[PATH_MAX]; + + if (!map->autocreate) + continue; + + if (path) { + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) + goto err_unpin_maps; + sanitize_pin_path(buf); + pin_path = buf; + } else if (!map->pin_path) { + continue; + } + + err = bpf_map__pin(map, pin_path); + if (err) + goto err_unpin_maps; + } + + return 0; + +err_unpin_maps: + while ((map = bpf_object__prev_map(obj, map))) { + if (!map->pin_path) + continue; + + bpf_map__unpin(map, NULL); + } + + return libbpf_err(err); +} + +int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) +{ + struct bpf_map *map; + int err; + + if (!obj) + return libbpf_err(-ENOENT); + + bpf_object__for_each_map(map, obj) { + char *pin_path = NULL; + char buf[PATH_MAX]; + + if (path) { + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) + return libbpf_err(err); + sanitize_pin_path(buf); + pin_path = buf; + } else if (!map->pin_path) { + continue; + } + + err = bpf_map__unpin(map, pin_path); + if (err) + return libbpf_err(err); + } + + return 0; +} + +int bpf_object__pin_programs(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + char buf[PATH_MAX]; + int err; + + if (!obj) + return libbpf_err(-ENOENT); + + if (!obj->loaded) { + pr_warn("object not yet loaded; load it first\n"); + return libbpf_err(-ENOENT); + } + + bpf_object__for_each_program(prog, obj) { + err = pathname_concat(buf, sizeof(buf), path, prog->name); + if (err) + goto err_unpin_programs; + + err = bpf_program__pin(prog, buf); + if (err) + goto err_unpin_programs; + } + + return 0; + +err_unpin_programs: + while ((prog = bpf_object__prev_program(obj, prog))) { + if (pathname_concat(buf, sizeof(buf), path, prog->name)) + continue; + + bpf_program__unpin(prog, buf); + } + + return libbpf_err(err); +} + +int bpf_object__unpin_programs(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + int err; + + if (!obj) + return libbpf_err(-ENOENT); + + bpf_object__for_each_program(prog, obj) { + char buf[PATH_MAX]; + + err = pathname_concat(buf, sizeof(buf), path, prog->name); + if (err) + return libbpf_err(err); + + err = bpf_program__unpin(prog, buf); + if (err) + return libbpf_err(err); + } + + return 0; +} + +int bpf_object__pin(struct bpf_object *obj, const char *path) +{ + int err; + + err = bpf_object__pin_maps(obj, path); + if (err) + return libbpf_err(err); + + err = bpf_object__pin_programs(obj, path); + if (err) { + bpf_object__unpin_maps(obj, path); + return libbpf_err(err); + } + + return 0; +} + +static void bpf_map__destroy(struct bpf_map *map) +{ + if (map->inner_map) { + bpf_map__destroy(map->inner_map); + zfree(&map->inner_map); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + 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->real_name); + zfree(&map->pin_path); + + if (map->fd >= 0) + zclose(map->fd); +} + +void bpf_object__close(struct bpf_object *obj) +{ + size_t i; + + if (IS_ERR_OR_NULL(obj)) + return; + + usdt_manager_free(obj->usdt_man); + obj->usdt_man = NULL; + + bpf_gen__free(obj->gen_loader); + bpf_object__elf_finish(obj); + bpf_object_unload(obj); + btf__free(obj->btf); + btf__free(obj->btf_vmlinux); + btf_ext__free(obj->btf_ext); + + for (i = 0; i < obj->nr_maps; i++) + bpf_map__destroy(&obj->maps[i]); + + zfree(&obj->btf_custom_path); + zfree(&obj->kconfig); + zfree(&obj->externs); + obj->nr_extern = 0; + + zfree(&obj->maps); + obj->nr_maps = 0; + + if (obj->programs && obj->nr_programs) { + for (i = 0; i < obj->nr_programs; i++) + bpf_program__exit(&obj->programs[i]); + } + zfree(&obj->programs); + + free(obj); +} + +const char *bpf_object__name(const struct bpf_object *obj) +{ + return obj ? obj->name : libbpf_err_ptr(-EINVAL); +} + +unsigned int bpf_object__kversion(const struct bpf_object *obj) +{ + return obj ? obj->kern_version : 0; +} + +struct btf *bpf_object__btf(const struct bpf_object *obj) +{ + return obj ? obj->btf : NULL; +} + +int bpf_object__btf_fd(const struct bpf_object *obj) +{ + return obj->btf ? btf__fd(obj->btf) : -1; +} + +int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version) +{ + if (obj->loaded) + return libbpf_err(-EINVAL); + + obj->kern_version = kern_version; + + return 0; +} + +int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts) +{ + struct bpf_gen *gen; + + if (!opts) + return -EFAULT; + if (!OPTS_VALID(opts, gen_loader_opts)) + return -EINVAL; + gen = calloc(sizeof(*gen), 1); + if (!gen) + return -ENOMEM; + gen->opts = opts; + obj->gen_loader = gen; + return 0; +} + +static struct bpf_program * +__bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, + bool forward) +{ + size_t nr_programs = obj->nr_programs; + ssize_t idx; + + if (!nr_programs) + return NULL; + + if (!p) + /* Iter from the beginning */ + return forward ? &obj->programs[0] : + &obj->programs[nr_programs - 1]; + + if (p->obj != obj) { + pr_warn("error: program handler doesn't match object\n"); + return errno = EINVAL, NULL; + } + + idx = (p - obj->programs) + (forward ? 1 : -1); + if (idx >= obj->nr_programs || idx < 0) + return NULL; + return &obj->programs[idx]; +} + +struct bpf_program * +bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev) +{ + struct bpf_program *prog = prev; + + do { + prog = __bpf_program__iter(prog, obj, true); + } while (prog && prog_is_subprog(obj, prog)); + + return prog; +} + +struct bpf_program * +bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *next) +{ + struct bpf_program *prog = next; + + do { + prog = __bpf_program__iter(prog, obj, false); + } while (prog && prog_is_subprog(obj, prog)); + + return prog; +} + +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__section_name(const struct bpf_program *prog) +{ + return prog->sec_name; +} + +bool bpf_program__autoload(const struct bpf_program *prog) +{ + return prog->autoload; +} + +int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) +{ + if (prog->obj->loaded) + return libbpf_err(-EINVAL); + + prog->autoload = autoload; + return 0; +} + +bool bpf_program__autoattach(const struct bpf_program *prog) +{ + return prog->autoattach; +} + +void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach) +{ + prog->autoattach = autoattach; +} + +const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog) +{ + return prog->insns; +} + +size_t bpf_program__insn_cnt(const struct bpf_program *prog) +{ + return prog->insns_cnt; +} + +int bpf_program__set_insns(struct bpf_program *prog, + struct bpf_insn *new_insns, size_t new_insn_cnt) +{ + struct bpf_insn *insns; + + if (prog->obj->loaded) + return -EBUSY; + + insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns)); + /* NULL is a valid return from reallocarray if the new count is zero */ + if (!insns && new_insn_cnt) { + pr_warn("prog '%s': failed to realloc prog code\n", prog->name); + return -ENOMEM; + } + memcpy(insns, new_insns, new_insn_cnt * sizeof(*insns)); + + prog->insns = insns; + prog->insns_cnt = new_insn_cnt; + return 0; +} + +int bpf_program__fd(const struct bpf_program *prog) +{ + if (!prog) + return libbpf_err(-EINVAL); + + if (prog->fd < 0) + return libbpf_err(-ENOENT); + + return prog->fd; +} + +__alias(bpf_program__type) +enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); + +enum bpf_prog_type bpf_program__type(const struct bpf_program *prog) +{ + return prog->type; +} + +int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + + prog->type = type; + return 0; +} + +__alias(bpf_program__expected_attach_type) +enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); + +enum bpf_attach_type bpf_program__expected_attach_type(const struct bpf_program *prog) +{ + return prog->expected_attach_type; +} + +int bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + + prog->expected_attach_type = type; + return 0; +} + +__u32 bpf_program__flags(const struct bpf_program *prog) +{ + return prog->prog_flags; +} + +int bpf_program__set_flags(struct bpf_program *prog, __u32 flags) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + + prog->prog_flags = flags; + return 0; +} + +__u32 bpf_program__log_level(const struct bpf_program *prog) +{ + return prog->log_level; +} + +int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + + prog->log_level = log_level; + return 0; +} + +const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size) +{ + *log_size = prog->log_size; + return prog->log_buf; +} + +int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size) +{ + if (log_size && !log_buf) + return -EINVAL; + if (prog->log_size > UINT_MAX) + return -EINVAL; + if (prog->obj->loaded) + return -EBUSY; + + prog->log_buf = log_buf; + prog->log_size = log_size; + return 0; +} + +#define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ + .sec = (char *)sec_pfx, \ + .prog_type = BPF_PROG_TYPE_##ptype, \ + .expected_attach_type = atype, \ + .cookie = (long)(flags), \ + .prog_prepare_load_fn = libbpf_prepare_prog_load, \ + __VA_ARGS__ \ +} + +static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_ksyscall(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_usdt(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link); + +static const struct bpf_sec_def section_defs[] = { + SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE), + SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE), + SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE), + SEC_DEF("kprobe+", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uprobe+", KPROBE, 0, SEC_NONE, attach_uprobe), + SEC_DEF("uprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), + SEC_DEF("kretprobe+", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uretprobe+", KPROBE, 0, SEC_NONE, attach_uprobe), + SEC_DEF("uretprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), + SEC_DEF("kprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("kretprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("ksyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), + SEC_DEF("kretsyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), + SEC_DEF("usdt+", KPROBE, 0, SEC_NONE, attach_usdt), + SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), + SEC_DEF("tracepoint+", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("tp+", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("raw_tracepoint+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tracepoint.w+", RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp.w+", RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("tp_btf+", TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry+", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fmod_ret+", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fexit+", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry.s+", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fmod_ret.s+", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fexit.s+", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("freplace+", EXT, 0, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("lsm+", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), + SEC_DEF("lsm.s+", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), + SEC_DEF("lsm_cgroup+", LSM, BPF_LSM_CGROUP, SEC_ATTACH_BTF), + SEC_DEF("iter+", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), + SEC_DEF("iter.s+", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_iter), + SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), + SEC_DEF("xdp.frags/devmap", XDP, BPF_XDP_DEVMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/devmap", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + SEC_DEF("xdp.frags/cpumap", XDP, BPF_XDP_CPUMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/cpumap", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp.frags", XDP, BPF_XDP, SEC_XDP_FRAGS), + SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT), + SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE), + SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE), + SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE), + SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE), + SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE), + SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE), + SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT), + SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT), + SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE), + SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE), + SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE), + SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE), + SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE), + SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE), + SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE), + SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT), + SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), + SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), +}; + +static size_t custom_sec_def_cnt; +static struct bpf_sec_def *custom_sec_defs; +static struct bpf_sec_def custom_fallback_def; +static bool has_custom_fallback_def; + +static int last_custom_sec_def_handler_id; + +int libbpf_register_prog_handler(const char *sec, + enum bpf_prog_type prog_type, + enum bpf_attach_type exp_attach_type, + const struct libbpf_prog_handler_opts *opts) +{ + struct bpf_sec_def *sec_def; + + if (!OPTS_VALID(opts, libbpf_prog_handler_opts)) + return libbpf_err(-EINVAL); + + if (last_custom_sec_def_handler_id == INT_MAX) /* prevent overflow */ + return libbpf_err(-E2BIG); + + if (sec) { + sec_def = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt + 1, + sizeof(*sec_def)); + if (!sec_def) + return libbpf_err(-ENOMEM); + + custom_sec_defs = sec_def; + sec_def = &custom_sec_defs[custom_sec_def_cnt]; + } else { + if (has_custom_fallback_def) + return libbpf_err(-EBUSY); + + sec_def = &custom_fallback_def; + } + + sec_def->sec = sec ? strdup(sec) : NULL; + if (sec && !sec_def->sec) + return libbpf_err(-ENOMEM); + + sec_def->prog_type = prog_type; + sec_def->expected_attach_type = exp_attach_type; + sec_def->cookie = OPTS_GET(opts, cookie, 0); + + sec_def->prog_setup_fn = OPTS_GET(opts, prog_setup_fn, NULL); + sec_def->prog_prepare_load_fn = OPTS_GET(opts, prog_prepare_load_fn, NULL); + sec_def->prog_attach_fn = OPTS_GET(opts, prog_attach_fn, NULL); + + sec_def->handler_id = ++last_custom_sec_def_handler_id; + + if (sec) + custom_sec_def_cnt++; + else + has_custom_fallback_def = true; + + return sec_def->handler_id; +} + +int libbpf_unregister_prog_handler(int handler_id) +{ + struct bpf_sec_def *sec_defs; + int i; + + if (handler_id <= 0) + return libbpf_err(-EINVAL); + + if (has_custom_fallback_def && custom_fallback_def.handler_id == handler_id) { + memset(&custom_fallback_def, 0, sizeof(custom_fallback_def)); + has_custom_fallback_def = false; + return 0; + } + + for (i = 0; i < custom_sec_def_cnt; i++) { + if (custom_sec_defs[i].handler_id == handler_id) + break; + } + + if (i == custom_sec_def_cnt) + return libbpf_err(-ENOENT); + + free(custom_sec_defs[i].sec); + for (i = i + 1; i < custom_sec_def_cnt; i++) + custom_sec_defs[i - 1] = custom_sec_defs[i]; + custom_sec_def_cnt--; + + /* try to shrink the array, but it's ok if we couldn't */ + sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs)); + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (sec_defs || custom_sec_def_cnt == 0) + custom_sec_defs = sec_defs; + + return 0; +} + +static bool sec_def_matches(const struct bpf_sec_def *sec_def, const char *sec_name) +{ + size_t len = strlen(sec_def->sec); + + /* "type/" always has to have proper SEC("type/extras") form */ + if (sec_def->sec[len - 1] == '/') { + if (str_has_pfx(sec_name, sec_def->sec)) + return true; + return false; + } + + /* "type+" means it can be either exact SEC("type") or + * well-formed SEC("type/extras") with proper '/' separator + */ + if (sec_def->sec[len - 1] == '+') { + len--; + /* not even a prefix */ + if (strncmp(sec_name, sec_def->sec, len) != 0) + return false; + /* exact match or has '/' separator */ + if (sec_name[len] == '\0' || sec_name[len] == '/') + return true; + return false; + } + + return strcmp(sec_name, sec_def->sec) == 0; +} + +static const struct bpf_sec_def *find_sec_def(const char *sec_name) +{ + const struct bpf_sec_def *sec_def; + int i, n; + + n = custom_sec_def_cnt; + for (i = 0; i < n; i++) { + sec_def = &custom_sec_defs[i]; + if (sec_def_matches(sec_def, sec_name)) + return sec_def; + } + + n = ARRAY_SIZE(section_defs); + for (i = 0; i < n; i++) { + sec_def = §ion_defs[i]; + if (sec_def_matches(sec_def, sec_name)) + return sec_def; + } + + if (has_custom_fallback_def) + return &custom_fallback_def; + + return NULL; +} + +#define MAX_TYPE_NAME_SIZE 32 + +static char *libbpf_get_type_names(bool attach_type) +{ + int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE; + char *buf; + + buf = malloc(len); + if (!buf) + return NULL; + + buf[0] = '\0'; + /* Forge string buf with all available names */ + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + const struct bpf_sec_def *sec_def = §ion_defs[i]; + + if (attach_type) { + if (sec_def->prog_prepare_load_fn != libbpf_prepare_prog_load) + continue; + + if (!(sec_def->cookie & SEC_ATTACHABLE)) + continue; + } + + if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { + free(buf); + return NULL; + } + strcat(buf, " "); + strcat(buf, section_defs[i].sec); + } + + return buf; +} + +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; + + if (!name) + return libbpf_err(-EINVAL); + + 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_debug("failed to guess program type from ELF section '%s'\n", name); + type_names = libbpf_get_type_names(false); + if (type_names != NULL) { + pr_debug("supported section(type) names are:%s\n", type_names); + free(type_names); + } + + return libbpf_err(-ESRCH); +} + +const char *libbpf_bpf_attach_type_str(enum bpf_attach_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(attach_type_name)) + return NULL; + + return attach_type_name[t]; +} + +const char *libbpf_bpf_link_type_str(enum bpf_link_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(link_type_name)) + return NULL; + + return link_type_name[t]; +} + +const char *libbpf_bpf_map_type_str(enum bpf_map_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(map_type_name)) + return NULL; + + return map_type_name[t]; +} + +const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(prog_type_name)) + return NULL; + + return prog_type_name[t]; +} + +static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, + size_t offset) +{ + 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_st_ops_relos(struct bpf_object *obj, + Elf64_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; + unsigned int moff, insn_idx; + const char *name; + __u32 member_idx; + Elf64_Sym *sym; + Elf64_Rel *rel; + int i, nrels; + + btf = obj->btf; + nrels = shdr->sh_size / shdr->sh_entsize; + for (i = 0; i < nrels; i++) { + rel = elf_rel_by_idx(data, i); + if (!rel) { + pr_warn("struct_ops reloc: failed to get %d reloc\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + + sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info)); + if (!sym) { + pr_warn("struct_ops reloc: symbol %zx not found\n", + (size_t)ELF64_R_SYM(rel->r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + + name = elf_sym_str(obj, 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; + } + if (sym->st_value % BPF_INSN_SZ) { + pr_warn("struct_ops reloc %s: invalid target program offset %llu\n", + map->name, (unsigned long long)sym->st_value); + return -LIBBPF_ERRNO__FORMAT; + } + insn_idx = sym->st_value / BPF_INSN_SZ; + + 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 = find_prog_by_sec_insn(obj, shdr_idx, insn_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; + } + + /* prevent the use of BPF prog with invalid type */ + if (prog->type != BPF_PROG_TYPE_STRUCT_OPS) { + pr_warn("struct_ops reloc %s: prog %s is not struct_ops BPF program\n", + map->name, prog->name); + return -EINVAL; + } + + /* if we haven't yet processed this BPF program, record proper + * attach_btf_id and member_idx + */ + if (!prog->attach_btf_id) { + prog->attach_btf_id = st_ops->type_id; + prog->expected_attach_type = member_idx; + } + + /* struct_ops BPF prog can be re-used between multiple + * .struct_ops as long as it's the same struct_ops struct + * definition and the same function pointer field + */ + if (prog->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != member_idx) { + pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", + map->name, prog->name, prog->sec_name, prog->type, + prog->attach_btf_id, prog->expected_attach_type, name); + return -EINVAL; + } + + st_ops->progs[member_idx] = prog; + } + + return 0; +} + +#define BTF_TRACE_PREFIX "btf_trace_" +#define BTF_LSM_PREFIX "bpf_lsm_" +#define BTF_ITER_PREFIX "bpf_iter_" +#define BTF_MAX_NAME_SIZE 128 + +void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, + const char **prefix, int *kind) +{ + switch (attach_type) { + case BPF_TRACE_RAW_TP: + *prefix = BTF_TRACE_PREFIX; + *kind = BTF_KIND_TYPEDEF; + break; + case BPF_LSM_MAC: + case BPF_LSM_CGROUP: + *prefix = BTF_LSM_PREFIX; + *kind = BTF_KIND_FUNC; + break; + case BPF_TRACE_ITER: + *prefix = BTF_ITER_PREFIX; + *kind = BTF_KIND_FUNC; + break; + default: + *prefix = ""; + *kind = BTF_KIND_FUNC; + } +} + +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 + * 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_attach_btf_id(struct btf *btf, const char *name, + enum bpf_attach_type attach_type) +{ + const char *prefix; + int kind; + + btf_get_kernel_prefix_kind(attach_type, &prefix, &kind); + return find_btf_by_prefix_kind(btf, prefix, name, kind); +} + +int libbpf_find_vmlinux_btf_id(const char *name, + enum bpf_attach_type attach_type) +{ + struct btf *btf; + int err; + + btf = btf__load_vmlinux_btf(); + err = libbpf_get_error(btf); + if (err) { + pr_warn("vmlinux BTF is not found\n"); + return libbpf_err(err); + } + + err = find_attach_btf_id(btf, name, attach_type); + if (err <= 0) + pr_warn("%s is not found in vmlinux BTF\n", name); + + btf__free(btf); + return libbpf_err(err); +} + +static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) +{ + struct bpf_prog_info info; + __u32 info_len = sizeof(info); + struct btf *btf; + int err; + + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len); + if (err) { + pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n", + attach_prog_fd, err); + return err; + } + + err = -EINVAL; + if (!info.btf_id) { + pr_warn("The target program doesn't have BTF\n"); + goto out; + } + btf = btf__load_from_kernel_by_id(info.btf_id); + err = libbpf_get_error(btf); + if (err) { + pr_warn("Failed to get BTF %d of the program: %d\n", info.btf_id, err); + 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: + return err; +} + +static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, + enum bpf_attach_type attach_type, + int *btf_obj_fd, int *btf_type_id) +{ + int ret, i; + + ret = find_attach_btf_id(obj->btf_vmlinux, attach_name, attach_type); + if (ret > 0) { + *btf_obj_fd = 0; /* vmlinux BTF */ + *btf_type_id = ret; + return 0; + } + if (ret != -ENOENT) + return ret; + + ret = load_module_btfs(obj); + if (ret) + return ret; + + for (i = 0; i < obj->btf_module_cnt; i++) { + const struct module_btf *mod = &obj->btf_modules[i]; + + ret = find_attach_btf_id(mod->btf, attach_name, attach_type); + if (ret > 0) { + *btf_obj_fd = mod->fd; + *btf_type_id = ret; + return 0; + } + if (ret == -ENOENT) + continue; + + return ret; + } + + return -ESRCH; +} + +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id) +{ + enum bpf_attach_type attach_type = prog->expected_attach_type; + __u32 attach_prog_fd = prog->attach_prog_fd; + int err = 0; + + /* BPF program's BTF ID */ + if (prog->type == BPF_PROG_TYPE_EXT || attach_prog_fd) { + if (!attach_prog_fd) { + pr_warn("prog '%s': attach program FD is not set\n", prog->name); + return -EINVAL; + } + err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); + if (err < 0) { + pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %d\n", + prog->name, attach_prog_fd, attach_name, err); + return err; + } + *btf_obj_fd = 0; + *btf_type_id = err; + return 0; + } + + /* kernel/module BTF ID */ + if (prog->obj->gen_loader) { + bpf_gen__record_attach_target(prog->obj->gen_loader, attach_name, attach_type); + *btf_obj_fd = 0; + *btf_type_id = 1; + } else { + err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + } + if (err) { + pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n", + prog->name, attach_name, err); + return err; + } + return 0; +} + +int libbpf_attach_type_by_name(const char *name, + enum bpf_attach_type *attach_type) +{ + char *type_names; + const struct bpf_sec_def *sec_def; + + if (!name) + return libbpf_err(-EINVAL); + + sec_def = find_sec_def(name); + if (!sec_def) { + 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_debug("attachable section(type) names are:%s\n", type_names); + free(type_names); + } + + return libbpf_err(-EINVAL); + } + + if (sec_def->prog_prepare_load_fn != libbpf_prepare_prog_load) + return libbpf_err(-EINVAL); + if (!(sec_def->cookie & SEC_ATTACHABLE)) + return libbpf_err(-EINVAL); + + *attach_type = sec_def->expected_attach_type; + return 0; +} + +int bpf_map__fd(const struct bpf_map *map) +{ + return map ? map->fd : libbpf_err(-EINVAL); +} + +static bool map_uses_real_name(const struct bpf_map *map) +{ + /* Since libbpf started to support custom .data.* and .rodata.* maps, + * their user-visible name differs from kernel-visible name. Users see + * such map's corresponding ELF section name as a map name. + * This check distinguishes .data/.rodata from .data.* and .rodata.* + * maps to know which name has to be returned to the user. + */ + if (map->libbpf_type == LIBBPF_MAP_DATA && strcmp(map->real_name, DATA_SEC) != 0) + return true; + if (map->libbpf_type == LIBBPF_MAP_RODATA && strcmp(map->real_name, RODATA_SEC) != 0) + return true; + return false; +} + +const char *bpf_map__name(const struct bpf_map *map) +{ + if (!map) + return NULL; + + if (map_uses_real_name(map)) + return map->real_name; + + return map->name; +} + +enum bpf_map_type bpf_map__type(const struct bpf_map *map) +{ + return map->def.type; +} + +int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->def.type = type; + return 0; +} + +__u32 bpf_map__map_flags(const struct bpf_map *map) +{ + return map->def.map_flags; +} + +int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->def.map_flags = flags; + return 0; +} + +__u64 bpf_map__map_extra(const struct bpf_map *map) +{ + return map->map_extra; +} + +int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->map_extra = map_extra; + return 0; +} + +__u32 bpf_map__numa_node(const struct bpf_map *map) +{ + return map->numa_node; +} + +int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->numa_node = numa_node; + return 0; +} + +__u32 bpf_map__key_size(const struct bpf_map *map) +{ + return map->def.key_size; +} + +int bpf_map__set_key_size(struct bpf_map *map, __u32 size) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->def.key_size = size; + return 0; +} + +__u32 bpf_map__value_size(const struct bpf_map *map) +{ + return map->def.value_size; +} + +int bpf_map__set_value_size(struct bpf_map *map, __u32 size) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->def.value_size = size; + return 0; +} + +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map) +{ + return map ? map->btf_key_type_id : 0; +} + +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map) +{ + return map ? map->btf_value_type_id : 0; +} + +int bpf_map__set_initial_value(struct bpf_map *map, + const void *data, size_t size) +{ + if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG || + size != map->def.value_size || map->fd >= 0) + return libbpf_err(-EINVAL); + + memcpy(map->mmaped, data, size); + return 0; +} + +const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) +{ + if (!map->mmaped) + return NULL; + *psize = map->def.value_size; + return map->mmaped; +} + +bool bpf_map__is_internal(const struct bpf_map *map) +{ + return map->libbpf_type != LIBBPF_MAP_UNSPEC; +} + +__u32 bpf_map__ifindex(const struct bpf_map *map) +{ + return map->map_ifindex; +} + +int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->map_ifindex = ifindex; + return 0; +} + +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_warn("error: unsupported map type\n"); + return libbpf_err(-EINVAL); + } + if (map->inner_map_fd != -1) { + pr_warn("error: inner_map_fd already specified\n"); + return libbpf_err(-EINVAL); + } + if (map->inner_map) { + bpf_map__destroy(map->inner_map); + zfree(&map->inner_map); + } + map->inner_map_fd = fd; + return 0; +} + +static struct bpf_map * +__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) +{ + ssize_t idx; + struct bpf_map *s, *e; + + if (!obj || !obj->maps) + return errno = EINVAL, NULL; + + s = obj->maps; + e = obj->maps + obj->nr_maps; + + if ((m < s) || (m >= e)) { + pr_warn("error in %s: map handler doesn't belong to object\n", + __func__); + return errno = EINVAL, NULL; + } + + idx = (m - obj->maps) + i; + if (idx >= obj->nr_maps || idx < 0) + return NULL; + return &obj->maps[idx]; +} + +struct bpf_map * +bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) +{ + if (prev == NULL) + return obj->maps; + + return __bpf_map__iter(prev, obj, 1); +} + +struct bpf_map * +bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next) +{ + if (next == NULL) { + if (!obj->nr_maps) + return NULL; + return obj->maps + obj->nr_maps - 1; + } + + return __bpf_map__iter(next, obj, -1); +} + +struct bpf_map * +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) +{ + struct bpf_map *pos; + + bpf_object__for_each_map(pos, obj) { + /* if it's a special internal map name (which always starts + * with dot) then check if that special name matches the + * real map name (ELF section name) + */ + if (name[0] == '.') { + if (pos->real_name && strcmp(pos->real_name, name) == 0) + return pos; + continue; + } + /* otherwise map name has to be an exact match */ + if (map_uses_real_name(pos)) { + if (strcmp(pos->real_name, name) == 0) + return pos; + continue; + } + if (strcmp(pos->name, name) == 0) + return pos; + } + return errno = ENOENT, NULL; +} + +int +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) +{ + return bpf_map__fd(bpf_object__find_map_by_name(obj, name)); +} + +static int validate_map_op(const struct bpf_map *map, size_t key_sz, + size_t value_sz, bool check_value_sz) +{ + if (map->fd <= 0) + return -ENOENT; + + if (map->def.key_size != key_sz) { + pr_warn("map '%s': unexpected key size %zu provided, expected %u\n", + map->name, key_sz, map->def.key_size); + return -EINVAL; + } + + if (!check_value_sz) + return 0; + + switch (map->def.type) { + case BPF_MAP_TYPE_PERCPU_ARRAY: + case BPF_MAP_TYPE_PERCPU_HASH: + case BPF_MAP_TYPE_LRU_PERCPU_HASH: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: { + int num_cpu = libbpf_num_possible_cpus(); + size_t elem_sz = roundup(map->def.value_size, 8); + + if (value_sz != num_cpu * elem_sz) { + pr_warn("map '%s': unexpected value size %zu provided for per-CPU map, expected %d * %zu = %zd\n", + map->name, value_sz, num_cpu, elem_sz, num_cpu * elem_sz); + return -EINVAL; + } + break; + } + default: + if (map->def.value_size != value_sz) { + pr_warn("map '%s': unexpected value size %zu provided, expected %u\n", + map->name, value_sz, map->def.value_size); + return -EINVAL; + } + break; + } + return 0; +} + +int bpf_map__lookup_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + void *value, size_t value_sz, __u64 flags) +{ + int err; + + err = validate_map_op(map, key_sz, value_sz, true); + if (err) + return libbpf_err(err); + + return bpf_map_lookup_elem_flags(map->fd, key, value, flags); +} + +int bpf_map__update_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + const void *value, size_t value_sz, __u64 flags) +{ + int err; + + err = validate_map_op(map, key_sz, value_sz, true); + if (err) + return libbpf_err(err); + + return bpf_map_update_elem(map->fd, key, value, flags); +} + +int bpf_map__delete_elem(const struct bpf_map *map, + const void *key, size_t key_sz, __u64 flags) +{ + int err; + + err = validate_map_op(map, key_sz, 0, false /* check_value_sz */); + if (err) + return libbpf_err(err); + + return bpf_map_delete_elem_flags(map->fd, key, flags); +} + +int bpf_map__lookup_and_delete_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + void *value, size_t value_sz, __u64 flags) +{ + int err; + + err = validate_map_op(map, key_sz, value_sz, true); + if (err) + return libbpf_err(err); + + return bpf_map_lookup_and_delete_elem_flags(map->fd, key, value, flags); +} + +int bpf_map__get_next_key(const struct bpf_map *map, + const void *cur_key, void *next_key, size_t key_sz) +{ + int err; + + err = validate_map_op(map, key_sz, 0, false /* check_value_sz */); + if (err) + return libbpf_err(err); + + return bpf_map_get_next_key(map->fd, cur_key, next_key); +} + +long libbpf_get_error(const void *ptr) +{ + if (!IS_ERR_OR_NULL(ptr)) + return 0; + + if (IS_ERR(ptr)) + errno = -PTR_ERR(ptr); + + /* If ptr == NULL, then errno should be already set by the failing + * API, because libbpf never returns NULL on success and it now always + * sets errno on error. So no extra errno handling for ptr == NULL + * case. + */ + return -errno; +} + +/* Replace link's underlying BPF program with the new one */ +int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog) +{ + int ret; + + ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL); + return libbpf_err_errno(ret); +} + +/* 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 = 0; + + if (IS_ERR_OR_NULL(link)) + return 0; + + if (!link->disconnected && link->detach) + err = link->detach(link); + if (link->pin_path) + free(link->pin_path); + if (link->dealloc) + link->dealloc(link); + else + free(link); + + return libbpf_err(err); +} + +int bpf_link__fd(const struct bpf_link *link) +{ + return link->fd; +} + +const char *bpf_link__pin_path(const struct bpf_link *link) +{ + return link->pin_path; +} + +static int bpf_link__detach_fd(struct bpf_link *link) +{ + return libbpf_err_errno(close(link->fd)); +} + +struct bpf_link *bpf_link__open(const char *path) +{ + struct bpf_link *link; + int fd; + + fd = bpf_obj_get(path); + if (fd < 0) { + fd = -errno; + pr_warn("failed to open link at %s: %d\n", path, fd); + return libbpf_err_ptr(fd); + } + + link = calloc(1, sizeof(*link)); + if (!link) { + close(fd); + return libbpf_err_ptr(-ENOMEM); + } + link->detach = &bpf_link__detach_fd; + link->fd = fd; + + link->pin_path = strdup(path); + if (!link->pin_path) { + bpf_link__destroy(link); + return libbpf_err_ptr(-ENOMEM); + } + + return link; +} + +int bpf_link__detach(struct bpf_link *link) +{ + return bpf_link_detach(link->fd) ? -errno : 0; +} + +int bpf_link__pin(struct bpf_link *link, const char *path) +{ + int err; + + if (link->pin_path) + return libbpf_err(-EBUSY); + err = make_parent_dir(path); + if (err) + return libbpf_err(err); + err = check_path(path); + if (err) + return libbpf_err(err); + + link->pin_path = strdup(path); + if (!link->pin_path) + return libbpf_err(-ENOMEM); + + if (bpf_obj_pin(link->fd, link->pin_path)) { + err = -errno; + zfree(&link->pin_path); + return libbpf_err(err); + } + + pr_debug("link fd=%d: pinned at %s\n", link->fd, link->pin_path); + return 0; +} + +int bpf_link__unpin(struct bpf_link *link) +{ + int err; + + if (!link->pin_path) + return libbpf_err(-EINVAL); + + err = unlink(link->pin_path); + if (err != 0) + return -errno; + + pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path); + zfree(&link->pin_path); + return 0; +} + +struct bpf_link_perf { + struct bpf_link link; + int perf_event_fd; + /* legacy kprobe support: keep track of probe identifier and type */ + char *legacy_probe_name; + bool legacy_is_kprobe; + bool legacy_is_retprobe; +}; + +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe); +static int remove_uprobe_event_legacy(const char *probe_name, bool retprobe); + +static int bpf_link_perf_detach(struct bpf_link *link) +{ + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + int err = 0; + + if (ioctl(perf_link->perf_event_fd, PERF_EVENT_IOC_DISABLE, 0) < 0) + err = -errno; + + if (perf_link->perf_event_fd != link->fd) + close(perf_link->perf_event_fd); + close(link->fd); + + /* legacy uprobe/kprobe needs to be removed after perf event fd closure */ + if (perf_link->legacy_probe_name) { + if (perf_link->legacy_is_kprobe) { + err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } else { + err = remove_uprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } + } + + return err; +} + +static void bpf_link_perf_dealloc(struct bpf_link *link) +{ + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + free(perf_link->legacy_probe_name); + free(perf_link); +} + +struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, + const struct bpf_perf_event_opts *opts) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_perf *link; + int prog_fd, link_fd = -1, err; + + if (!OPTS_VALID(opts, bpf_perf_event_opts)) + return libbpf_err_ptr(-EINVAL); + + if (pfd < 0) { + pr_warn("prog '%s': invalid perf event FD %d\n", + prog->name, pfd); + return libbpf_err_ptr(-EINVAL); + } + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-ENOMEM); + link->link.detach = &bpf_link_perf_detach; + link->link.dealloc = &bpf_link_perf_dealloc; + link->perf_event_fd = pfd; + + if (kernel_supports(prog->obj, FEAT_PERF_LINK)) { + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_opts, + .perf_event.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0)); + + link_fd = bpf_link_create(prog_fd, pfd, BPF_PERF_EVENT, &link_opts); + if (link_fd < 0) { + err = -errno; + pr_warn("prog '%s': failed to create BPF link for perf_event FD %d: %d (%s)\n", + prog->name, pfd, + err, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; + } + link->link.fd = link_fd; + } else { + if (OPTS_GET(opts, bpf_cookie, 0)) { + pr_warn("prog '%s': user context value is not supported\n", prog->name); + err = -EOPNOTSUPP; + goto err_out; + } + + if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { + err = -errno; + pr_warn("prog '%s': failed to attach to perf_event FD %d: %s\n", + prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + if (err == -EPROTO) + pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n", + prog->name, pfd); + goto err_out; + } + link->link.fd = pfd; + } + if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n", + prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; + } + + return &link->link; +err_out: + if (link_fd >= 0) + close(link_fd); + free(link); + return libbpf_err_ptr(err); +} + +struct bpf_link *bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd) +{ + return bpf_program__attach_perf_event_opts(prog, pfd, NULL); +} + +/* + * this function is expected to parse integer in the range of [0, 2^31-1] from + * given file using scanf format string fmt. If actual parsed value is + * negative, the result might be indistinguishable from error + */ +static int parse_uint_from_file(const char *file, const char *fmt) +{ + char buf[STRERR_BUFSIZE]; + int err, ret; + FILE *f; + + f = fopen(file, "r"); + if (!f) { + err = -errno; + pr_debug("failed to open '%s': %s\n", file, + libbpf_strerror_r(err, buf, sizeof(buf))); + return err; + } + err = fscanf(f, fmt, &ret); + if (err != 1) { + err = err == EOF ? -EIO : -errno; + pr_debug("failed to parse '%s': %s\n", file, + libbpf_strerror_r(err, buf, sizeof(buf))); + fclose(f); + return err; + } + fclose(f); + return ret; +} + +static int determine_kprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/kprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_uprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_kprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/kprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static int determine_uprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +#define PERF_UPROBE_REF_CTR_OFFSET_BITS 32 +#define PERF_UPROBE_REF_CTR_OFFSET_SHIFT 32 + +static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, + uint64_t offset, int pid, size_t ref_ctr_off) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; + char errmsg[STRERR_BUFSIZE]; + int type, pfd; + + if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS)) + return -EINVAL; + + memset(&attr, 0, attr_sz); + + type = uprobe ? determine_uprobe_perf_type() + : determine_kprobe_perf_type(); + if (type < 0) { + pr_warn("failed to determine %s perf type: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + return type; + } + if (retprobe) { + int bit = uprobe ? determine_uprobe_retprobe_bit() + : determine_kprobe_retprobe_bit(); + + if (bit < 0) { + pr_warn("failed to determine %s retprobe bit: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(bit, errmsg, sizeof(errmsg))); + return bit; + } + attr.config |= 1 << bit; + } + attr.size = attr_sz; + attr.type = type; + attr.config |= (__u64)ref_ctr_off << PERF_UPROBE_REF_CTR_OFFSET_SHIFT; + attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */ + attr.config2 = offset; /* kprobe_addr or probe_offset */ + + /* pid filter is meaningful only for uprobes */ + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid /* pid */, + pid == -1 ? 0 : -1 /* cpu */, + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + return pfd >= 0 ? pfd : -errno; +} + +static int append_to_file(const char *file, const char *fmt, ...) +{ + int fd, n, err = 0; + va_list ap; + + fd = open(file, O_WRONLY | O_APPEND | O_CLOEXEC, 0); + if (fd < 0) + return -errno; + + va_start(ap, fmt); + n = vdprintf(fd, fmt, ap); + va_end(ap); + + if (n < 0) + err = -errno; + + close(fd); + return err; +} + +#define DEBUGFS "/sys/kernel/debug/tracing" +#define TRACEFS "/sys/kernel/tracing" + +static bool use_debugfs(void) +{ + static int has_debugfs = -1; + + if (has_debugfs < 0) + has_debugfs = faccessat(AT_FDCWD, DEBUGFS, F_OK, AT_EACCESS) == 0; + + return has_debugfs == 1; +} + +static const char *tracefs_path(void) +{ + return use_debugfs() ? DEBUGFS : TRACEFS; +} + +static const char *tracefs_kprobe_events(void) +{ + return use_debugfs() ? DEBUGFS"/kprobe_events" : TRACEFS"/kprobe_events"; +} + +static const char *tracefs_uprobe_events(void) +{ + return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events"; +} + +static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *kfunc_name, size_t offset) +{ + static int index = 0; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset, + __sync_fetch_and_add(&index, 1)); +} + +static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset) +{ + return append_to_file(tracefs_kprobe_events(), "%c:%s/%s %s+0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "kretprobes" : "kprobes", + probe_name, kfunc_name, offset); +} + +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe) +{ + return append_to_file(tracefs_kprobe_events(), "-:%s/%s", + retprobe ? "kretprobes" : "kprobes", probe_name); +} + +static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[256]; + + snprintf(file, sizeof(file), "%s/events/%s/%s/id", + tracefs_path(), retprobe ? "kretprobes" : "kprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset, int pid) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; + char errmsg[STRERR_BUFSIZE]; + int type, pfd, err; + + err = add_kprobe_event_legacy(probe_name, retprobe, kfunc_name, offset); + if (err < 0) { + pr_warn("failed to add legacy kprobe event for '%s+0x%zx': %s\n", + kfunc_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + type = determine_kprobe_perf_type_legacy(probe_name, retprobe); + if (type < 0) { + err = type; + pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n", + kfunc_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_clean_legacy; + } + + memset(&attr, 0, attr_sz); + attr.size = attr_sz; + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy kprobe perf_event_open() failed: %s\n", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_clean_legacy; + } + return pfd; + +err_clean_legacy: + /* Clear the newly added legacy kprobe_event */ + remove_kprobe_event_legacy(probe_name, retprobe); + return err; +} + +static const char *arch_specific_syscall_pfx(void) +{ +#if defined(__x86_64__) + return "x64"; +#elif defined(__i386__) + return "ia32"; +#elif defined(__s390x__) + return "s390x"; +#elif defined(__s390__) + return "s390"; +#elif defined(__arm__) + return "arm"; +#elif defined(__aarch64__) + return "arm64"; +#elif defined(__mips__) + return "mips"; +#elif defined(__riscv) + return "riscv"; +#elif defined(__powerpc__) + return "powerpc"; +#elif defined(__powerpc64__) + return "powerpc64"; +#else + return NULL; +#endif +} + +static int probe_kern_syscall_wrapper(void) +{ + char syscall_name[64]; + const char *ksys_pfx; + + ksys_pfx = arch_specific_syscall_pfx(); + if (!ksys_pfx) + return 0; + + snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx); + + if (determine_kprobe_perf_type() >= 0) { + int pfd; + + pfd = perf_event_open_probe(false, false, syscall_name, 0, getpid(), 0); + if (pfd >= 0) + close(pfd); + + return pfd >= 0 ? 1 : 0; + } else { /* legacy mode */ + char probe_name[128]; + + gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0); + if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0) + return 0; + + (void)remove_kprobe_event_legacy(probe_name, false); + return 1; + } +} + +struct bpf_link * +bpf_program__attach_kprobe_opts(const struct bpf_program *prog, + const char *func_name, + const struct bpf_kprobe_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); + char errmsg[STRERR_BUFSIZE]; + char *legacy_probe = NULL; + struct bpf_link *link; + size_t offset; + bool retprobe, legacy; + int pfd, err; + + if (!OPTS_VALID(opts, bpf_kprobe_opts)) + return libbpf_err_ptr(-EINVAL); + + retprobe = OPTS_GET(opts, retprobe, false); + offset = OPTS_GET(opts, offset, 0); + pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); + + legacy = determine_kprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(false /* uprobe */, retprobe, + func_name, offset, + -1 /* pid */, 0 /* ref_ctr_off */); + } else { + char probe_name[256]; + + gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), + func_name, offset); + + legacy_probe = strdup(probe_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_kprobe_open_legacy(legacy_probe, retprobe, func_name, + offset, -1 /* pid */); + } + if (pfd < 0) { + err = -errno; + pr_warn("prog '%s': failed to create %s '%s+0x%zx' perf event: %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; + } + link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); + err = libbpf_get_error(link); + if (err) { + close(pfd); + pr_warn("prog '%s': failed to attach to %s '%s+0x%zx': %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_clean_legacy; + } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = true; + perf_link->legacy_is_retprobe = retprobe; + } + + return link; + +err_clean_legacy: + if (legacy) + remove_kprobe_event_legacy(legacy_probe, retprobe); +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); +} + +struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, + bool retprobe, + const char *func_name) +{ + DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts, + .retprobe = retprobe, + ); + + return bpf_program__attach_kprobe_opts(prog, func_name, &opts); +} + +struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog, + const char *syscall_name, + const struct bpf_ksyscall_opts *opts) +{ + LIBBPF_OPTS(bpf_kprobe_opts, kprobe_opts); + char func_name[128]; + + if (!OPTS_VALID(opts, bpf_ksyscall_opts)) + return libbpf_err_ptr(-EINVAL); + + if (kernel_supports(prog->obj, FEAT_SYSCALL_WRAPPER)) { + /* arch_specific_syscall_pfx() should never return NULL here + * because it is guarded by kernel_supports(). However, since + * compiler does not know that we have an explicit conditional + * as well. + */ + snprintf(func_name, sizeof(func_name), "__%s_sys_%s", + arch_specific_syscall_pfx() ? : "", syscall_name); + } else { + snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name); + } + + kprobe_opts.retprobe = OPTS_GET(opts, retprobe, false); + kprobe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); + + return bpf_program__attach_kprobe_opts(prog, func_name, &kprobe_opts); +} + +/* Adapted from perf/util/string.c */ +static bool glob_match(const char *str, const char *pat) +{ + while (*str && *pat && *pat != '*') { + if (*pat == '?') { /* Matches any single character */ + str++; + pat++; + continue; + } + if (*str != *pat) + return false; + str++; + pat++; + } + /* Check wild card */ + if (*pat == '*') { + while (*pat == '*') + pat++; + if (!*pat) /* Tail wild card matches all */ + return true; + while (*str) + if (glob_match(str++, pat)) + return true; + } + return !*str && !*pat; +} + +struct kprobe_multi_resolve { + const char *pattern; + unsigned long *addrs; + size_t cap; + size_t cnt; +}; + +static int +resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct kprobe_multi_resolve *res = ctx; + int err; + + if (!glob_match(sym_name, res->pattern)) + return 0; + + err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long), + res->cnt + 1); + if (err) + return err; + + res->addrs[res->cnt++] = (unsigned long) sym_addr; + return 0; +} + +struct bpf_link * +bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, + const char *pattern, + const struct bpf_kprobe_multi_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, lopts); + struct kprobe_multi_resolve res = { + .pattern = pattern, + }; + struct bpf_link *link = NULL; + char errmsg[STRERR_BUFSIZE]; + const unsigned long *addrs; + int err, link_fd, prog_fd; + const __u64 *cookies; + const char **syms; + bool retprobe; + size_t cnt; + + if (!OPTS_VALID(opts, bpf_kprobe_multi_opts)) + return libbpf_err_ptr(-EINVAL); + + syms = OPTS_GET(opts, syms, false); + addrs = OPTS_GET(opts, addrs, false); + cnt = OPTS_GET(opts, cnt, false); + cookies = OPTS_GET(opts, cookies, false); + + if (!pattern && !addrs && !syms) + return libbpf_err_ptr(-EINVAL); + if (pattern && (addrs || syms || cookies || cnt)) + return libbpf_err_ptr(-EINVAL); + if (!pattern && !cnt) + return libbpf_err_ptr(-EINVAL); + if (addrs && syms) + return libbpf_err_ptr(-EINVAL); + + if (pattern) { + err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res); + if (err) + goto error; + if (!res.cnt) { + err = -ENOENT; + goto error; + } + addrs = res.addrs; + cnt = res.cnt; + } + + retprobe = OPTS_GET(opts, retprobe, false); + + lopts.kprobe_multi.syms = syms; + lopts.kprobe_multi.addrs = addrs; + lopts.kprobe_multi.cookies = cookies; + lopts.kprobe_multi.cnt = cnt; + lopts.kprobe_multi.flags = retprobe ? BPF_F_KPROBE_MULTI_RETURN : 0; + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto error; + } + link->detach = &bpf_link__detach_fd; + + prog_fd = bpf_program__fd(prog); + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts); + if (link_fd < 0) { + err = -errno; + pr_warn("prog '%s': failed to attach: %s\n", + prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto error; + } + link->fd = link_fd; + free(res.addrs); + return link; + +error: + free(link); + free(res.addrs); + return libbpf_err_ptr(err); +} + +static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); + unsigned long offset = 0; + const char *func_name; + char *func; + int n; + + *link = NULL; + + /* no auto-attach for SEC("kprobe") and SEC("kretprobe") */ + if (strcmp(prog->sec_name, "kprobe") == 0 || strcmp(prog->sec_name, "kretprobe") == 0) + return 0; + + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); + if (opts.retprobe) + func_name = prog->sec_name + sizeof("kretprobe/") - 1; + else + func_name = prog->sec_name + sizeof("kprobe/") - 1; + + n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); + if (n < 1) { + pr_warn("kprobe name is invalid: %s\n", func_name); + return -EINVAL; + } + if (opts.retprobe && offset != 0) { + free(func); + pr_warn("kretprobes do not support offset specification\n"); + return -EINVAL; + } + + opts.offset = offset; + *link = bpf_program__attach_kprobe_opts(prog, func, &opts); + free(func); + return libbpf_get_error(*link); +} + +static int attach_ksyscall(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + LIBBPF_OPTS(bpf_ksyscall_opts, opts); + const char *syscall_name; + + *link = NULL; + + /* no auto-attach for SEC("ksyscall") and SEC("kretsyscall") */ + if (strcmp(prog->sec_name, "ksyscall") == 0 || strcmp(prog->sec_name, "kretsyscall") == 0) + return 0; + + opts.retprobe = str_has_pfx(prog->sec_name, "kretsyscall/"); + if (opts.retprobe) + syscall_name = prog->sec_name + sizeof("kretsyscall/") - 1; + else + syscall_name = prog->sec_name + sizeof("ksyscall/") - 1; + + *link = bpf_program__attach_ksyscall(prog, syscall_name, &opts); + return *link ? 0 : -errno; +} + +static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + const char *spec; + char *pattern; + int n; + + *link = NULL; + + /* no auto-attach for SEC("kprobe.multi") and SEC("kretprobe.multi") */ + if (strcmp(prog->sec_name, "kprobe.multi") == 0 || + strcmp(prog->sec_name, "kretprobe.multi") == 0) + return 0; + + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe.multi/"); + if (opts.retprobe) + spec = prog->sec_name + sizeof("kretprobe.multi/") - 1; + else + spec = prog->sec_name + sizeof("kprobe.multi/") - 1; + + n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); + if (n < 1) { + pr_warn("kprobe multi pattern is invalid: %s\n", pattern); + return -EINVAL; + } + + *link = bpf_program__attach_kprobe_multi_opts(prog, pattern, &opts); + free(pattern); + return libbpf_get_error(*link); +} + +static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *binary_path, uint64_t offset) +{ + int i; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), binary_path, (size_t)offset); + + /* sanitize binary_path in the probe name */ + for (i = 0; buf[i]; i++) { + if (!isalnum(buf[i])) + buf[i] = '_'; + } +} + +static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset) +{ + return append_to_file(tracefs_uprobe_events(), "%c:%s/%s %s:0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "uretprobes" : "uprobes", + probe_name, binary_path, offset); +} + +static inline int remove_uprobe_event_legacy(const char *probe_name, bool retprobe) +{ + return append_to_file(tracefs_uprobe_events(), "-:%s/%s", + retprobe ? "uretprobes" : "uprobes", probe_name); +} + +static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[512]; + + snprintf(file, sizeof(file), "%s/events/%s/%s/id", + tracefs_path(), retprobe ? "uretprobes" : "uprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset, int pid) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; + int type, pfd, err; + + err = add_uprobe_event_legacy(probe_name, retprobe, binary_path, offset); + if (err < 0) { + pr_warn("failed to add legacy uprobe event for %s:0x%zx: %d\n", + binary_path, (size_t)offset, err); + return err; + } + type = determine_uprobe_perf_type_legacy(probe_name, retprobe); + if (type < 0) { + err = type; + pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n", + binary_path, offset, err); + goto err_clean_legacy; + } + + memset(&attr, 0, attr_sz); + attr.size = attr_sz; + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy uprobe perf_event_open() failed: %d\n", err); + goto err_clean_legacy; + } + return pfd; + +err_clean_legacy: + /* Clear the newly added legacy uprobe_event */ + remove_uprobe_event_legacy(probe_name, retprobe); + return err; +} + +/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */ +static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn) +{ + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + + if (!gelf_getshdr(scn, &sh)) + continue; + if (sh.sh_type == sh_type) + return scn; + } + return NULL; +} + +/* Find offset of function name in object specified by path. "name" matches + * symbol name or name@@LIB for library functions. + */ +static long elf_find_func_offset(const char *binary_path, const char *name) +{ + int fd, i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; + bool is_shared_lib, is_name_qualified; + char errmsg[STRERR_BUFSIZE]; + long ret = -ENOENT; + size_t name_len; + GElf_Ehdr ehdr; + Elf *elf; + + fd = open(binary_path, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + ret = -errno; + pr_warn("failed to open %s: %s\n", binary_path, + libbpf_strerror_r(ret, errmsg, sizeof(errmsg))); + return ret; + } + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) { + pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1)); + close(fd); + return -LIBBPF_ERRNO__FORMAT; + } + if (!gelf_getehdr(elf, &ehdr)) { + pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } + /* for shared lib case, we do not need to calculate relative offset */ + is_shared_lib = ehdr.e_type == ET_DYN; + + name_len = strlen(name); + /* Does name specify "@@LIB"? */ + is_name_qualified = strstr(name, "@@") != NULL; + + /* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if + * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically + * linked binary may not have SHT_DYMSYM, so absence of a section should not be + * reported as a warning/error. + */ + for (i = 0; i < ARRAY_SIZE(sh_types); i++) { + size_t nr_syms, strtabidx, idx; + Elf_Data *symbols = NULL; + Elf_Scn *scn = NULL; + int last_bind = -1; + const char *sname; + GElf_Shdr sh; + + scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL); + if (!scn) { + pr_debug("elf: failed to find symbol table ELF sections in '%s'\n", + binary_path); + continue; + } + if (!gelf_getshdr(scn, &sh)) + continue; + strtabidx = sh.sh_link; + symbols = elf_getdata(scn, 0); + if (!symbols) { + pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n", + binary_path, elf_errmsg(-1)); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } + nr_syms = symbols->d_size / sh.sh_entsize; + + for (idx = 0; idx < nr_syms; idx++) { + int curr_bind; + GElf_Sym sym; + Elf_Scn *sym_scn; + GElf_Shdr sym_sh; + + if (!gelf_getsym(symbols, idx, &sym)) + continue; + + if (GELF_ST_TYPE(sym.st_info) != STT_FUNC) + continue; + + sname = elf_strptr(elf, strtabidx, sym.st_name); + if (!sname) + continue; + + curr_bind = GELF_ST_BIND(sym.st_info); + + /* User can specify func, func@@LIB or func@@LIB_VERSION. */ + if (strncmp(sname, name, name_len) != 0) + continue; + /* ...but we don't want a search for "foo" to match 'foo2" also, so any + * additional characters in sname should be of the form "@@LIB". + */ + if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@') + continue; + + if (ret >= 0) { + /* handle multiple matches */ + if (last_bind != STB_WEAK && curr_bind != STB_WEAK) { + /* Only accept one non-weak bind. */ + pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n", + sname, name, binary_path); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } else if (curr_bind == STB_WEAK) { + /* already have a non-weak bind, and + * this is a weak bind, so ignore. + */ + continue; + } + } + + /* Transform symbol's virtual address (absolute for + * binaries and relative for shared libs) into file + * offset, which is what kernel is expecting for + * uprobe/uretprobe attachment. + * See Documentation/trace/uprobetracer.rst for more + * details. + * This is done by looking up symbol's containing + * section's header and using it's virtual address + * (sh_addr) and corresponding file offset (sh_offset) + * to transform sym.st_value (virtual address) into + * desired final file offset. + */ + sym_scn = elf_getscn(elf, sym.st_shndx); + if (!sym_scn) + continue; + if (!gelf_getshdr(sym_scn, &sym_sh)) + continue; + + ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset; + last_bind = curr_bind; + } + if (ret > 0) + break; + } + + if (ret > 0) { + pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path, + ret); + } else { + if (ret == 0) { + pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path, + is_shared_lib ? "should not be 0 in a shared library" : + "try using shared library path instead"); + ret = -ENOENT; + } else { + pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path); + } + } +out: + elf_end(elf); + close(fd); + return ret; +} + +static const char *arch_specific_lib_paths(void) +{ + /* + * Based on https://packages.debian.org/sid/libc6. + * + * Assume that the traced program is built for the same architecture + * as libbpf, which should cover the vast majority of cases. + */ +#if defined(__x86_64__) + return "/lib/x86_64-linux-gnu"; +#elif defined(__i386__) + return "/lib/i386-linux-gnu"; +#elif defined(__s390x__) + return "/lib/s390x-linux-gnu"; +#elif defined(__s390__) + return "/lib/s390-linux-gnu"; +#elif defined(__arm__) && defined(__SOFTFP__) + return "/lib/arm-linux-gnueabi"; +#elif defined(__arm__) && !defined(__SOFTFP__) + return "/lib/arm-linux-gnueabihf"; +#elif defined(__aarch64__) + return "/lib/aarch64-linux-gnu"; +#elif defined(__mips__) && defined(__MIPSEL__) && _MIPS_SZLONG == 64 + return "/lib/mips64el-linux-gnuabi64"; +#elif defined(__mips__) && defined(__MIPSEL__) && _MIPS_SZLONG == 32 + return "/lib/mipsel-linux-gnu"; +#elif defined(__powerpc64__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + return "/lib/powerpc64le-linux-gnu"; +#elif defined(__sparc__) && defined(__arch64__) + return "/lib/sparc64-linux-gnu"; +#elif defined(__riscv) && __riscv_xlen == 64 + return "/lib/riscv64-linux-gnu"; +#else + return NULL; +#endif +} + +/* Get full path to program/shared library. */ +static int resolve_full_path(const char *file, char *result, size_t result_sz) +{ + const char *search_paths[3] = {}; + int i, perm; + + if (str_has_sfx(file, ".so") || strstr(file, ".so.")) { + search_paths[0] = getenv("LD_LIBRARY_PATH"); + search_paths[1] = "/usr/lib64:/usr/lib"; + search_paths[2] = arch_specific_lib_paths(); + perm = R_OK; + } else { + search_paths[0] = getenv("PATH"); + search_paths[1] = "/usr/bin:/usr/sbin"; + perm = R_OK | X_OK; + } + + for (i = 0; i < ARRAY_SIZE(search_paths); i++) { + const char *s; + + if (!search_paths[i]) + continue; + for (s = search_paths[i]; s != NULL; s = strchr(s, ':')) { + char *next_path; + int seg_len; + + if (s[0] == ':') + s++; + next_path = strchr(s, ':'); + seg_len = next_path ? next_path - s : strlen(s); + if (!seg_len) + continue; + snprintf(result, result_sz, "%.*s/%s", seg_len, s, file); + /* ensure it has required permissions */ + if (faccessat(AT_FDCWD, result, perm, AT_EACCESS) < 0) + continue; + pr_debug("resolved '%s' to '%s'\n", file, result); + return 0; + } + } + return -ENOENT; +} + +LIBBPF_API struct bpf_link * +bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, + const char *binary_path, size_t func_offset, + const struct bpf_uprobe_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); + char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL; + char full_binary_path[PATH_MAX]; + struct bpf_link *link; + size_t ref_ctr_off; + int pfd, err; + bool retprobe, legacy; + const char *func_name; + + if (!OPTS_VALID(opts, bpf_uprobe_opts)) + return libbpf_err_ptr(-EINVAL); + + retprobe = OPTS_GET(opts, retprobe, false); + ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0); + pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); + + if (!binary_path) + return libbpf_err_ptr(-EINVAL); + + if (!strchr(binary_path, '/')) { + err = resolve_full_path(binary_path, full_binary_path, + sizeof(full_binary_path)); + if (err) { + pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", + prog->name, binary_path, err); + return libbpf_err_ptr(err); + } + binary_path = full_binary_path; + } + func_name = OPTS_GET(opts, func_name, NULL); + if (func_name) { + long sym_off; + + sym_off = elf_find_func_offset(binary_path, func_name); + if (sym_off < 0) + return libbpf_err_ptr(sym_off); + func_offset += sym_off; + } + + legacy = determine_uprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, + func_offset, pid, ref_ctr_off); + } else { + char probe_name[PATH_MAX + 64]; + + if (ref_ctr_off) + return libbpf_err_ptr(-EINVAL); + + gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name), + binary_path, func_offset); + + legacy_probe = strdup(probe_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_uprobe_open_legacy(legacy_probe, retprobe, + binary_path, func_offset, pid); + } + if (pfd < 0) { + err = -errno; + pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n", + prog->name, retprobe ? "uretprobe" : "uprobe", + binary_path, func_offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; + } + + link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); + err = libbpf_get_error(link); + if (err) { + close(pfd); + pr_warn("prog '%s': failed to attach to %s '%s:0x%zx': %s\n", + prog->name, retprobe ? "uretprobe" : "uprobe", + binary_path, func_offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_clean_legacy; + } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = false; + perf_link->legacy_is_retprobe = retprobe; + } + return link; + +err_clean_legacy: + if (legacy) + remove_uprobe_event_legacy(legacy_probe, retprobe); +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); +} + +/* Format of u[ret]probe section definition supporting auto-attach: + * u[ret]probe/binary:function[+offset] + * + * binary can be an absolute/relative path or a filename; the latter is resolved to a + * full binary path via bpf_program__attach_uprobe_opts. + * + * Specifying uprobe+ ensures we carry out strict matching; either "uprobe" must be + * specified (and auto-attach is not possible) or the above format is specified for + * auto-attach. + */ +static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts); + char *probe_type = NULL, *binary_path = NULL, *func_name = NULL; + int n, ret = -EINVAL; + long offset = 0; + + *link = NULL; + + n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.]+%li", + &probe_type, &binary_path, &func_name, &offset); + switch (n) { + case 1: + /* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */ + ret = 0; + break; + case 2: + pr_warn("prog '%s': section '%s' missing ':function[+offset]' specification\n", + prog->name, prog->sec_name); + break; + case 3: + case 4: + opts.retprobe = strcmp(probe_type, "uretprobe") == 0 || + strcmp(probe_type, "uretprobe.s") == 0; + if (opts.retprobe && offset != 0) { + pr_warn("prog '%s': uretprobes do not support offset specification\n", + prog->name); + break; + } + opts.func_name = func_name; + *link = bpf_program__attach_uprobe_opts(prog, -1, binary_path, offset, &opts); + ret = libbpf_get_error(*link); + break; + default: + pr_warn("prog '%s': invalid format of section definition '%s'\n", prog->name, + prog->sec_name); + break; + } + free(probe_type); + free(binary_path); + free(func_name); + + return ret; +} + +struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog, + bool retprobe, pid_t pid, + const char *binary_path, + size_t func_offset) +{ + DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts, .retprobe = retprobe); + + return bpf_program__attach_uprobe_opts(prog, pid, binary_path, func_offset, &opts); +} + +struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog, + pid_t pid, const char *binary_path, + const char *usdt_provider, const char *usdt_name, + const struct bpf_usdt_opts *opts) +{ + char resolved_path[512]; + struct bpf_object *obj = prog->obj; + struct bpf_link *link; + __u64 usdt_cookie; + int err; + + if (!OPTS_VALID(opts, bpf_uprobe_opts)) + return libbpf_err_ptr(-EINVAL); + + if (bpf_program__fd(prog) < 0) { + pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + if (!binary_path) + return libbpf_err_ptr(-EINVAL); + + if (!strchr(binary_path, '/')) { + err = resolve_full_path(binary_path, resolved_path, sizeof(resolved_path)); + if (err) { + pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", + prog->name, binary_path, err); + return libbpf_err_ptr(err); + } + binary_path = resolved_path; + } + + /* USDT manager is instantiated lazily on first USDT attach. It will + * be destroyed together with BPF object in bpf_object__close(). + */ + if (IS_ERR(obj->usdt_man)) + return libbpf_ptr(obj->usdt_man); + if (!obj->usdt_man) { + obj->usdt_man = usdt_manager_new(obj); + if (IS_ERR(obj->usdt_man)) + return libbpf_ptr(obj->usdt_man); + } + + usdt_cookie = OPTS_GET(opts, usdt_cookie, 0); + link = usdt_manager_attach_usdt(obj->usdt_man, prog, pid, binary_path, + usdt_provider, usdt_name, usdt_cookie); + err = libbpf_get_error(link); + if (err) + return libbpf_err_ptr(err); + return link; +} + +static int attach_usdt(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + char *path = NULL, *provider = NULL, *name = NULL; + const char *sec_name; + int n, err; + + sec_name = bpf_program__section_name(prog); + if (strcmp(sec_name, "usdt") == 0) { + /* no auto-attach for just SEC("usdt") */ + *link = NULL; + return 0; + } + + n = sscanf(sec_name, "usdt/%m[^:]:%m[^:]:%m[^:]", &path, &provider, &name); + if (n != 3) { + pr_warn("invalid section '%s', expected SEC(\"usdt/<path>:<provider>:<name>\")\n", + sec_name); + err = -EINVAL; + } else { + *link = bpf_program__attach_usdt(prog, -1 /* any process */, path, + provider, name, NULL); + err = libbpf_get_error(*link); + } + free(path); + free(provider); + free(name); + return err; +} + +static int determine_tracepoint_id(const char *tp_category, + const char *tp_name) +{ + char file[PATH_MAX]; + int ret; + + ret = snprintf(file, sizeof(file), "%s/events/%s/%s/id", + tracefs_path(), tp_category, tp_name); + if (ret < 0) + return -errno; + if (ret >= sizeof(file)) { + pr_debug("tracepoint %s/%s path is too long\n", + tp_category, tp_name); + return -E2BIG; + } + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_open_tracepoint(const char *tp_category, + const char *tp_name) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; + char errmsg[STRERR_BUFSIZE]; + int tp_id, pfd, err; + + tp_id = determine_tracepoint_id(tp_category, tp_name); + if (tp_id < 0) { + pr_warn("failed to determine tracepoint '%s/%s' perf event ID: %s\n", + tp_category, tp_name, + libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg))); + return tp_id; + } + + memset(&attr, 0, attr_sz); + attr.type = PERF_TYPE_TRACEPOINT; + attr.size = attr_sz; + attr.config = tp_id; + + pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */, + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("tracepoint '%s/%s' perf_event_open() failed: %s\n", + tp_category, tp_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + +struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, + const char *tp_category, + const char *tp_name, + const struct bpf_tracepoint_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + if (!OPTS_VALID(opts, bpf_tracepoint_opts)) + return libbpf_err_ptr(-EINVAL); + + pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); + + pfd = perf_event_open_tracepoint(tp_category, tp_name); + if (pfd < 0) { + pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n", + prog->name, tp_category, tp_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return libbpf_err_ptr(pfd); + } + link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); + err = libbpf_get_error(link); + if (err) { + close(pfd); + pr_warn("prog '%s': failed to attach to tracepoint '%s/%s': %s\n", + prog->name, tp_category, tp_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return libbpf_err_ptr(err); + } + return link; +} + +struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, + const char *tp_category, + const char *tp_name) +{ + return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); +} + +static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + char *sec_name, *tp_cat, *tp_name; + + *link = NULL; + + /* no auto-attach for SEC("tp") or SEC("tracepoint") */ + if (strcmp(prog->sec_name, "tp") == 0 || strcmp(prog->sec_name, "tracepoint") == 0) + return 0; + + sec_name = strdup(prog->sec_name); + if (!sec_name) + return -ENOMEM; + + /* extract "tp/<category>/<name>" or "tracepoint/<category>/<name>" */ + if (str_has_pfx(prog->sec_name, "tp/")) + tp_cat = sec_name + sizeof("tp/") - 1; + else + tp_cat = sec_name + sizeof("tracepoint/") - 1; + tp_name = strchr(tp_cat, '/'); + if (!tp_name) { + free(sec_name); + return -EINVAL; + } + *tp_name = '\0'; + tp_name++; + + *link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); + free(sec_name); + return libbpf_get_error(*link); +} + +struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, + const char *tp_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int prog_fd, pfd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach before loaded\n", prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-ENOMEM); + link->detach = &bpf_link__detach_fd; + + pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); + if (pfd < 0) { + pfd = -errno; + free(link); + pr_warn("prog '%s': failed to attach to raw tracepoint '%s': %s\n", + prog->name, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return libbpf_err_ptr(pfd); + } + link->fd = pfd; + return link; +} + +static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + static const char *const prefixes[] = { + "raw_tp", + "raw_tracepoint", + "raw_tp.w", + "raw_tracepoint.w", + }; + size_t i; + const char *tp_name = NULL; + + *link = NULL; + + for (i = 0; i < ARRAY_SIZE(prefixes); i++) { + size_t pfx_len; + + if (!str_has_pfx(prog->sec_name, prefixes[i])) + continue; + + pfx_len = strlen(prefixes[i]); + /* no auto-attach case of, e.g., SEC("raw_tp") */ + if (prog->sec_name[pfx_len] == '\0') + return 0; + + if (prog->sec_name[pfx_len] != '/') + continue; + + tp_name = prog->sec_name + pfx_len + 1; + break; + } + + if (!tp_name) { + pr_warn("prog '%s': invalid section name '%s'\n", + prog->name, prog->sec_name); + return -EINVAL; + } + + *link = bpf_program__attach_raw_tracepoint(prog, tp_name); + return libbpf_get_error(*link); +} + +/* Common logic for all BPF program types that attach to a btf_id */ +static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *prog, + const struct bpf_trace_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int prog_fd, pfd; + + if (!OPTS_VALID(opts, bpf_trace_opts)) + return libbpf_err_ptr(-EINVAL); + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach before loaded\n", prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-ENOMEM); + link->detach = &bpf_link__detach_fd; + + /* libbpf is smart enough to redirect to BPF_RAW_TRACEPOINT_OPEN on old kernels */ + link_opts.tracing.cookie = OPTS_GET(opts, cookie, 0); + pfd = bpf_link_create(prog_fd, 0, bpf_program__expected_attach_type(prog), &link_opts); + if (pfd < 0) { + pfd = -errno; + free(link); + pr_warn("prog '%s': failed to attach: %s\n", + prog->name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return libbpf_err_ptr(pfd); + } + link->fd = pfd; + return link; +} + +struct bpf_link *bpf_program__attach_trace(const struct bpf_program *prog) +{ + return bpf_program__attach_btf_id(prog, NULL); +} + +struct bpf_link *bpf_program__attach_trace_opts(const struct bpf_program *prog, + const struct bpf_trace_opts *opts) +{ + return bpf_program__attach_btf_id(prog, opts); +} + +struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) +{ + return bpf_program__attach_btf_id(prog, NULL); +} + +static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + *link = bpf_program__attach_trace(prog); + return libbpf_get_error(*link); +} + +static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + *link = bpf_program__attach_lsm(prog); + return libbpf_get_error(*link); +} + +static struct bpf_link * +bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id, + const char *target_name) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, + .target_btf_id = btf_id); + enum bpf_attach_type attach_type; + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int prog_fd, link_fd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach before loaded\n", prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-ENOMEM); + link->detach = &bpf_link__detach_fd; + + attach_type = bpf_program__expected_attach_type(prog); + link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts); + if (link_fd < 0) { + link_fd = -errno; + free(link); + pr_warn("prog '%s': failed to attach to %s: %s\n", + prog->name, target_name, + libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + return libbpf_err_ptr(link_fd); + } + link->fd = link_fd; + return link; +} + +struct bpf_link * +bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd) +{ + return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup"); +} + +struct bpf_link * +bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd) +{ + return bpf_program__attach_fd(prog, netns_fd, 0, "netns"); +} + +struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex) +{ + /* target_fd/target_ifindex use the same field in LINK_CREATE */ + return bpf_program__attach_fd(prog, ifindex, 0, "xdp"); +} + +struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, + int target_fd, + const char *attach_func_name) +{ + int btf_id; + + if (!!target_fd != !!attach_func_name) { + pr_warn("prog '%s': supply none or both of target_fd and attach_func_name\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + if (prog->type != BPF_PROG_TYPE_EXT) { + pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + if (target_fd) { + btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd); + if (btf_id < 0) + return libbpf_err_ptr(btf_id); + + return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace"); + } else { + /* no target, so use raw_tracepoint_open for compatibility + * with old kernels + */ + return bpf_program__attach_trace(prog); + } +} + +struct bpf_link * +bpf_program__attach_iter(const struct bpf_program *prog, + const struct bpf_iter_attach_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int prog_fd, link_fd; + __u32 target_fd = 0; + + if (!OPTS_VALID(opts, bpf_iter_attach_opts)) + return libbpf_err_ptr(-EINVAL); + + link_create_opts.iter_info = OPTS_GET(opts, link_info, (void *)0); + link_create_opts.iter_info_len = OPTS_GET(opts, link_info_len, 0); + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach before loaded\n", prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-ENOMEM); + link->detach = &bpf_link__detach_fd; + + link_fd = bpf_link_create(prog_fd, target_fd, BPF_TRACE_ITER, + &link_create_opts); + if (link_fd < 0) { + link_fd = -errno; + free(link); + pr_warn("prog '%s': failed to attach to iterator: %s\n", + prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + return libbpf_err_ptr(link_fd); + } + link->fd = link_fd; + return link; +} + +static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + *link = bpf_program__attach_iter(prog, NULL); + return libbpf_get_error(*link); +} + +struct bpf_link *bpf_program__attach(const struct bpf_program *prog) +{ + struct bpf_link *link = NULL; + int err; + + if (!prog->sec_def || !prog->sec_def->prog_attach_fn) + return libbpf_err_ptr(-EOPNOTSUPP); + + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link); + if (err) + return libbpf_err_ptr(err); + + /* When calling bpf_program__attach() explicitly, auto-attach support + * is expected to work, so NULL returned link is considered an error. + * This is different for skeleton's attach, see comment in + * bpf_object__attach_skeleton(). + */ + if (!link) + return libbpf_err_ptr(-EOPNOTSUPP); + + return link; +} + +static int bpf_link__detach_struct_ops(struct bpf_link *link) +{ + __u32 zero = 0; + + if (bpf_map_delete_elem(link->fd, &zero)) + return -errno; + + return 0; +} + +struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) +{ + struct bpf_struct_ops *st_ops; + struct bpf_link *link; + __u32 i, zero = 0; + int err; + + if (!bpf_map__is_struct_ops(map) || map->fd == -1) + return libbpf_err_ptr(-EINVAL); + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-EINVAL); + + st_ops = map->st_ops; + for (i = 0; i < btf_vlen(st_ops->type); i++) { + struct bpf_program *prog = st_ops->progs[i]; + void *kern_data; + int prog_fd; + + 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 libbpf_err_ptr(err); + } + + link->detach = bpf_link__detach_struct_ops; + link->fd = map->fd; + + return link; +} + +typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, + void *private_data); + +static enum bpf_perf_event_ret +perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, + void **copy_mem, size_t *copy_size, + bpf_perf_event_print_t fn, void *private_data) +{ + struct perf_event_mmap_page *header = mmap_mem; + __u64 data_head = ring_buffer_read_head(header); + __u64 data_tail = header->data_tail; + void *base = ((__u8 *)header) + page_size; + int ret = LIBBPF_PERF_EVENT_CONT; + struct perf_event_header *ehdr; + size_t ehdr_size; + + while (data_head != data_tail) { + ehdr = base + (data_tail & (mmap_size - 1)); + ehdr_size = ehdr->size; + + if (((void *)ehdr) + ehdr_size > base + mmap_size) { + void *copy_start = ehdr; + size_t len_first = base + mmap_size - copy_start; + size_t len_secnd = ehdr_size - len_first; + + if (*copy_size < ehdr_size) { + free(*copy_mem); + *copy_mem = malloc(ehdr_size); + if (!*copy_mem) { + *copy_size = 0; + ret = LIBBPF_PERF_EVENT_ERROR; + break; + } + *copy_size = ehdr_size; + } + + memcpy(*copy_mem, copy_start, len_first); + memcpy(*copy_mem + len_first, base, len_secnd); + ehdr = *copy_mem; + } + + ret = fn(ehdr, private_data); + data_tail += ehdr_size; + if (ret != LIBBPF_PERF_EVENT_CONT) + break; + } + + ring_buffer_write_tail(header, data_tail); + return libbpf_err(ret); +} + +struct perf_buffer; + +struct perf_buffer_params { + struct perf_event_attr *attr; + /* if event_cb is specified, it takes precendence */ + perf_buffer_event_fn event_cb; + /* sample_cb and lost_cb are higher-level common-case callbacks */ + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; + int cpu_cnt; + int *cpus; + int *map_keys; +}; + +struct perf_cpu_buf { + struct perf_buffer *pb; + void *base; /* mmap()'ed memory */ + void *buf; /* for reconstructing segmented data */ + size_t buf_size; + int fd; + int cpu; + int map_key; +}; + +struct perf_buffer { + perf_buffer_event_fn event_cb; + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; /* passed into callbacks */ + + size_t page_size; + size_t mmap_size; + struct perf_cpu_buf **cpu_bufs; + struct epoll_event *events; + int cpu_cnt; /* number of allocated CPU buffers */ + int epoll_fd; /* perf event FD */ + int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ +}; + +static void perf_buffer__free_cpu_buf(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + if (!cpu_buf) + return; + if (cpu_buf->base && + munmap(cpu_buf->base, pb->mmap_size + pb->page_size)) + pr_warn("failed to munmap cpu_buf #%d\n", cpu_buf->cpu); + if (cpu_buf->fd >= 0) { + ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0); + close(cpu_buf->fd); + } + free(cpu_buf->buf); + free(cpu_buf); +} + +void perf_buffer__free(struct perf_buffer *pb) +{ + int i; + + if (IS_ERR_OR_NULL(pb)) + return; + if (pb->cpu_bufs) { + for (i = 0; i < pb->cpu_cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i]; + + if (!cpu_buf) + continue; + + bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key); + perf_buffer__free_cpu_buf(pb, cpu_buf); + } + free(pb->cpu_bufs); + } + if (pb->epoll_fd >= 0) + close(pb->epoll_fd); + free(pb->events); + free(pb); +} + +static struct perf_cpu_buf * +perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, + int cpu, int map_key) +{ + struct perf_cpu_buf *cpu_buf; + char msg[STRERR_BUFSIZE]; + int err; + + cpu_buf = calloc(1, sizeof(*cpu_buf)); + if (!cpu_buf) + return ERR_PTR(-ENOMEM); + + cpu_buf->pb = pb; + cpu_buf->cpu = cpu; + cpu_buf->map_key = map_key; + + cpu_buf->fd = syscall(__NR_perf_event_open, attr, -1 /* pid */, cpu, + -1, PERF_FLAG_FD_CLOEXEC); + if (cpu_buf->fd < 0) { + err = -errno; + pr_warn("failed to open perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + cpu_buf->base = mmap(NULL, pb->mmap_size + pb->page_size, + PROT_READ | PROT_WRITE, MAP_SHARED, + cpu_buf->fd, 0); + if (cpu_buf->base == MAP_FAILED) { + cpu_buf->base = NULL; + err = -errno; + pr_warn("failed to mmap perf buffer on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + pr_warn("failed to enable perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + return cpu_buf; + +error: + perf_buffer__free_cpu_buf(pb, cpu_buf); + return (struct perf_cpu_buf *)ERR_PTR(err); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p); + +struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, + perf_buffer_sample_fn sample_cb, + perf_buffer_lost_fn lost_cb, + void *ctx, + const struct perf_buffer_opts *opts) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_buffer_params p = {}; + struct perf_event_attr attr; + + if (!OPTS_VALID(opts, perf_buffer_opts)) + return libbpf_err_ptr(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.size = attr_sz; + attr.config = PERF_COUNT_SW_BPF_OUTPUT; + attr.type = PERF_TYPE_SOFTWARE; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; + + p.attr = &attr; + p.sample_cb = sample_cb; + p.lost_cb = lost_cb; + p.ctx = ctx; + + return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p)); +} + +struct perf_buffer *perf_buffer__new_raw(int map_fd, size_t page_cnt, + struct perf_event_attr *attr, + perf_buffer_event_fn event_cb, void *ctx, + const struct perf_buffer_raw_opts *opts) +{ + struct perf_buffer_params p = {}; + + if (!attr) + return libbpf_err_ptr(-EINVAL); + + if (!OPTS_VALID(opts, perf_buffer_raw_opts)) + return libbpf_err_ptr(-EINVAL); + + p.attr = attr; + p.event_cb = event_cb; + p.ctx = ctx; + p.cpu_cnt = OPTS_GET(opts, cpu_cnt, 0); + p.cpus = OPTS_GET(opts, cpus, NULL); + p.map_keys = OPTS_GET(opts, map_keys, NULL); + + return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p)); +} + +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, j, n; + + if (page_cnt == 0 || (page_cnt & (page_cnt - 1))) { + pr_warn("page count should be power of two, but is %zu\n", + page_cnt); + return ERR_PTR(-EINVAL); + } + + /* best-effort sanity checks */ + memset(&map, 0, sizeof(map)); + map_info_len = sizeof(map); + err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); + if (err) { + err = -errno; + /* if BPF_OBJ_GET_INFO_BY_FD is supported, will return + * -EBADFD, -EFAULT, or -E2BIG on real error + */ + if (err != -EINVAL) { + pr_warn("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + return ERR_PTR(err); + } + pr_debug("failed to get map info for FD %d; API not supported? Ignoring...\n", + map_fd); + } else { + if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + pr_warn("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", + map.name); + return ERR_PTR(-EINVAL); + } + } + + pb = calloc(1, sizeof(*pb)); + if (!pb) + return ERR_PTR(-ENOMEM); + + pb->event_cb = p->event_cb; + pb->sample_cb = p->sample_cb; + pb->lost_cb = p->lost_cb; + pb->ctx = p->ctx; + + pb->page_size = getpagesize(); + pb->mmap_size = pb->page_size * page_cnt; + pb->map_fd = map_fd; + + pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (pb->epoll_fd < 0) { + err = -errno; + pr_warn("failed to create epoll instance: %s\n", + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (p->cpu_cnt > 0) { + pb->cpu_cnt = p->cpu_cnt; + } else { + pb->cpu_cnt = libbpf_num_possible_cpus(); + if (pb->cpu_cnt < 0) { + err = pb->cpu_cnt; + goto error; + } + if (map.max_entries && map.max_entries < pb->cpu_cnt) + pb->cpu_cnt = map.max_entries; + } + + pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events)); + if (!pb->events) { + err = -ENOMEM; + pr_warn("failed to allocate events: out of memory\n"); + goto error; + } + pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs)); + if (!pb->cpu_bufs) { + err = -ENOMEM; + pr_warn("failed to allocate buffers: out of memory\n"); + goto error; + } + + 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[j] = cpu_buf; + + err = bpf_map_update_elem(pb->map_fd, &map_key, + &cpu_buf->fd, 0); + if (err) { + err = -errno; + pr_warn("failed to set cpu #%d, key %d -> perf FD %d: %s\n", + cpu, map_key, cpu_buf->fd, + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + pb->events[j].events = EPOLLIN; + pb->events[j].data.ptr = cpu_buf; + if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, + &pb->events[j]) < 0) { + err = -errno; + pr_warn("failed to epoll_ctl cpu #%d perf FD %d: %s\n", + cpu, cpu_buf->fd, + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + j++; + } + pb->cpu_cnt = j; + free(online); + + return pb; + +error: + free(online); + if (pb) + perf_buffer__free(pb); + return ERR_PTR(err); +} + +struct perf_sample_raw { + struct perf_event_header header; + uint32_t size; + char data[]; +}; + +struct perf_sample_lost { + struct perf_event_header header; + uint64_t id; + uint64_t lost; + uint64_t sample_id; +}; + +static enum bpf_perf_event_ret +perf_buffer__process_record(struct perf_event_header *e, void *ctx) +{ + struct perf_cpu_buf *cpu_buf = ctx; + struct perf_buffer *pb = cpu_buf->pb; + void *data = e; + + /* user wants full control over parsing perf event */ + if (pb->event_cb) + return pb->event_cb(pb->ctx, cpu_buf->cpu, e); + + switch (e->type) { + case PERF_RECORD_SAMPLE: { + struct perf_sample_raw *s = data; + + if (pb->sample_cb) + pb->sample_cb(pb->ctx, cpu_buf->cpu, s->data, s->size); + break; + } + case PERF_RECORD_LOST: { + struct perf_sample_lost *s = data; + + if (pb->lost_cb) + pb->lost_cb(pb->ctx, cpu_buf->cpu, s->lost); + break; + } + default: + pr_warn("unknown perf sample type %d\n", e->type); + return LIBBPF_PERF_EVENT_ERROR; + } + return LIBBPF_PERF_EVENT_CONT; +} + +static int perf_buffer__process_records(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + enum bpf_perf_event_ret ret; + + ret = perf_event_read_simple(cpu_buf->base, pb->mmap_size, + pb->page_size, &cpu_buf->buf, + &cpu_buf->buf_size, + perf_buffer__process_record, cpu_buf); + if (ret != LIBBPF_PERF_EVENT_CONT) + return ret; + return 0; +} + +int perf_buffer__epoll_fd(const struct perf_buffer *pb) +{ + return pb->epoll_fd; +} + +int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) +{ + int i, cnt, err; + + cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms); + if (cnt < 0) + return -errno; + + for (i = 0; i < cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr; + + err = perf_buffer__process_records(pb, cpu_buf); + if (err) { + pr_warn("error while processing records: %d\n", err); + return libbpf_err(err); + } + } + return cnt; +} + +/* Return number of PERF_EVENT_ARRAY map slots set up by this perf_buffer + * manager. + */ +size_t perf_buffer__buffer_cnt(const struct perf_buffer *pb) +{ + return pb->cpu_cnt; +} + +/* + * Return perf_event FD of a ring buffer in *buf_idx* slot of + * PERF_EVENT_ARRAY BPF map. This FD can be polled for new data using + * select()/poll()/epoll() Linux syscalls. + */ +int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx) +{ + struct perf_cpu_buf *cpu_buf; + + if (buf_idx >= pb->cpu_cnt) + return libbpf_err(-EINVAL); + + cpu_buf = pb->cpu_bufs[buf_idx]; + if (!cpu_buf) + return libbpf_err(-ENOENT); + + return cpu_buf->fd; +} + +int perf_buffer__buffer(struct perf_buffer *pb, int buf_idx, void **buf, size_t *buf_size) +{ + struct perf_cpu_buf *cpu_buf; + + if (buf_idx >= pb->cpu_cnt) + return libbpf_err(-EINVAL); + + cpu_buf = pb->cpu_bufs[buf_idx]; + if (!cpu_buf) + return libbpf_err(-ENOENT); + + *buf = cpu_buf->base; + *buf_size = pb->mmap_size; + return 0; +} + +/* + * Consume data from perf ring buffer corresponding to slot *buf_idx* in + * PERF_EVENT_ARRAY BPF map without waiting/polling. If there is no data to + * consume, do nothing and return success. + * Returns: + * - 0 on success; + * - <0 on failure. + */ +int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx) +{ + struct perf_cpu_buf *cpu_buf; + + if (buf_idx >= pb->cpu_cnt) + return libbpf_err(-EINVAL); + + cpu_buf = pb->cpu_bufs[buf_idx]; + if (!cpu_buf) + return libbpf_err(-ENOENT); + + return perf_buffer__process_records(pb, cpu_buf); +} + +int perf_buffer__consume(struct perf_buffer *pb) +{ + int i, err; + + for (i = 0; i < pb->cpu_cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i]; + + if (!cpu_buf) + continue; + + err = perf_buffer__process_records(pb, cpu_buf); + if (err) { + pr_warn("perf_buffer: failed to process records in buffer #%d: %d\n", i, err); + return libbpf_err(err); + } + } + return 0; +} + +int bpf_program__set_attach_target(struct bpf_program *prog, + int attach_prog_fd, + const char *attach_func_name) +{ + int btf_obj_fd = 0, btf_id = 0, err; + + if (!prog || attach_prog_fd < 0) + return libbpf_err(-EINVAL); + + if (prog->obj->loaded) + return libbpf_err(-EINVAL); + + if (attach_prog_fd && !attach_func_name) { + /* remember attach_prog_fd and let bpf_program__load() find + * BTF ID during the program load + */ + prog->attach_prog_fd = attach_prog_fd; + return 0; + } + + if (attach_prog_fd) { + btf_id = libbpf_find_prog_btf_id(attach_func_name, + attach_prog_fd); + if (btf_id < 0) + return libbpf_err(btf_id); + } else { + if (!attach_func_name) + return libbpf_err(-EINVAL); + + /* load btf_vmlinux, if not yet */ + err = bpf_object__load_vmlinux_btf(prog->obj, true); + if (err) + return libbpf_err(err); + err = find_kernel_btf_id(prog->obj, attach_func_name, + prog->expected_attach_type, + &btf_obj_fd, &btf_id); + if (err) + return libbpf_err(err); + } + + prog->attach_btf_id = btf_id; + prog->attach_btf_obj_fd = btf_obj_fd; + prog->attach_prog_fd = attach_prog_fd; + return 0; +} + +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz) +{ + int err = 0, n, len, start, end = -1; + bool *tmp; + + *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 | O_CLOEXEC); + if (fd < 0) { + 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) { + err = len ? -errno : -EINVAL; + pr_warn("Failed to read cpu mask from %s: %d\n", fcpu, err); + return err; + } + if (len >= sizeof(buf)) { + pr_warn("CPU mask is too big in file %s\n", fcpu); + return -E2BIG; + } + buf[len] = '\0'; + + 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 libbpf_err(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; +} + +static int populate_skeleton_maps(const struct bpf_object *obj, + struct bpf_map_skeleton *maps, + size_t map_cnt) +{ + int i; + + for (i = 0; i < map_cnt; i++) { + struct bpf_map **map = maps[i].map; + const char *name = maps[i].name; + void **mmaped = maps[i].mmaped; + + *map = bpf_object__find_map_by_name(obj, name); + if (!*map) { + pr_warn("failed to find skeleton map '%s'\n", name); + return -ESRCH; + } + + /* externs shouldn't be pre-setup from user code */ + if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) + *mmaped = (*map)->mmaped; + } + return 0; +} + +static int populate_skeleton_progs(const struct bpf_object *obj, + struct bpf_prog_skeleton *progs, + size_t prog_cnt) +{ + int i; + + for (i = 0; i < prog_cnt; i++) { + struct bpf_program **prog = progs[i].prog; + const char *name = progs[i].name; + + *prog = bpf_object__find_program_by_name(obj, name); + if (!*prog) { + pr_warn("failed to find skeleton program '%s'\n", name); + return -ESRCH; + } + } + return 0; +} + +int bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts, + .object_name = s->name, + ); + struct bpf_object *obj; + int err; + + /* Attempt to preserve opts->object_name, unless overriden by user + * explicitly. Overwriting object name for skeletons is discouraged, + * as it breaks global data maps, because they contain object name + * prefix as their own map name prefix. When skeleton is generated, + * bpftool is making an assumption that this name will stay the same. + */ + if (opts) { + memcpy(&skel_opts, opts, sizeof(*opts)); + if (!opts->object_name) + skel_opts.object_name = s->name; + } + + obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts); + err = libbpf_get_error(obj); + if (err) { + pr_warn("failed to initialize skeleton BPF object '%s': %d\n", + s->name, err); + return libbpf_err(err); + } + + *s->obj = obj; + err = populate_skeleton_maps(obj, s->maps, s->map_cnt); + if (err) { + pr_warn("failed to populate skeleton maps for '%s': %d\n", s->name, err); + return libbpf_err(err); + } + + err = populate_skeleton_progs(obj, s->progs, s->prog_cnt); + if (err) { + pr_warn("failed to populate skeleton progs for '%s': %d\n", s->name, err); + return libbpf_err(err); + } + + return 0; +} + +int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s) +{ + int err, len, var_idx, i; + const char *var_name; + const struct bpf_map *map; + struct btf *btf; + __u32 map_type_id; + const struct btf_type *map_type, *var_type; + const struct bpf_var_skeleton *var_skel; + struct btf_var_secinfo *var; + + if (!s->obj) + return libbpf_err(-EINVAL); + + btf = bpf_object__btf(s->obj); + if (!btf) { + pr_warn("subskeletons require BTF at runtime (object %s)\n", + bpf_object__name(s->obj)); + return libbpf_err(-errno); + } + + err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt); + if (err) { + pr_warn("failed to populate subskeleton maps: %d\n", err); + return libbpf_err(err); + } + + err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt); + if (err) { + pr_warn("failed to populate subskeleton maps: %d\n", err); + return libbpf_err(err); + } + + for (var_idx = 0; var_idx < s->var_cnt; var_idx++) { + var_skel = &s->vars[var_idx]; + map = *var_skel->map; + map_type_id = bpf_map__btf_value_type_id(map); + map_type = btf__type_by_id(btf, map_type_id); + + if (!btf_is_datasec(map_type)) { + pr_warn("type for map '%1$s' is not a datasec: %2$s", + bpf_map__name(map), + __btf_kind_str(btf_kind(map_type))); + return libbpf_err(-EINVAL); + } + + len = btf_vlen(map_type); + var = btf_var_secinfos(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + if (strcmp(var_name, var_skel->name) == 0) { + *var_skel->addr = map->mmaped + var->offset; + break; + } + } + } + return 0; +} + +void bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s) +{ + if (!s) + return; + free(s->maps); + free(s->progs); + free(s->vars); + free(s); +} + +int bpf_object__load_skeleton(struct bpf_object_skeleton *s) +{ + int i, err; + + err = bpf_object__load(*s->obj); + if (err) { + pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err); + return libbpf_err(err); + } + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map *map = *s->maps[i].map; + 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 libbpf_err(err); + } + } + + return 0; +} + +int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) +{ + int i, err; + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program *prog = *s->progs[i].prog; + struct bpf_link **link = s->progs[i].link; + + if (!prog->autoload || !prog->autoattach) + continue; + + /* auto-attaching not supported for this program */ + if (!prog->sec_def || !prog->sec_def->prog_attach_fn) + continue; + + /* if user already set the link manually, don't attempt auto-attach */ + if (*link) + continue; + + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, link); + if (err) { + pr_warn("prog '%s': failed to auto-attach: %d\n", + bpf_program__name(prog), err); + return libbpf_err(err); + } + + /* It's possible that for some SEC() definitions auto-attach + * is supported in some cases (e.g., if definition completely + * specifies target information), but is not in other cases. + * SEC("uprobe") is one such case. If user specified target + * binary and function name, such BPF program can be + * auto-attached. But if not, it shouldn't trigger skeleton's + * attach to fail. It should just be skipped. + * attach_fn signals such case with returning 0 (no error) and + * setting link to NULL. + */ + } + + return 0; +} + +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; + + bpf_link__destroy(*link); + *link = NULL; + } +} + +void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) +{ + if (!s) + return; + + 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 new file mode 100644 index 000000000..eee883f00 --- /dev/null +++ b/tools/lib/bpf/libbpf.h @@ -0,0 +1,1529 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Common eBPF ELF object loading operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + */ +#ifndef __LIBBPF_LIBBPF_H +#define __LIBBPF_LIBBPF_H + +#include <stdarg.h> +#include <stdio.h> +#include <stdint.h> +#include <stdbool.h> +#include <sys/types.h> // for size_t +#include <linux/bpf.h> + +#include "libbpf_common.h" +#include "libbpf_legacy.h" + +#ifdef __cplusplus +extern "C" { +#endif + +LIBBPF_API __u32 libbpf_major_version(void); +LIBBPF_API __u32 libbpf_minor_version(void); +LIBBPF_API const char *libbpf_version_string(void); + +enum libbpf_errno { + __LIBBPF_ERRNO__START = 4000, + + /* Something wrong in libelf */ + LIBBPF_ERRNO__LIBELF = __LIBBPF_ERRNO__START, + LIBBPF_ERRNO__FORMAT, /* BPF object format invalid */ + LIBBPF_ERRNO__KVERSION, /* Incorrect or no 'version' section */ + LIBBPF_ERRNO__ENDIAN, /* Endian mismatch */ + LIBBPF_ERRNO__INTERNAL, /* Internal error in libbpf */ + LIBBPF_ERRNO__RELOC, /* Relocation failed */ + LIBBPF_ERRNO__LOAD, /* Load program failure for unknown reason */ + LIBBPF_ERRNO__VERIFY, /* Kernel verifier blocks program loading */ + LIBBPF_ERRNO__PROG2BIG, /* Program too big */ + LIBBPF_ERRNO__KVER, /* Incorrect kernel version */ + LIBBPF_ERRNO__PROGTYPE, /* Kernel doesn't support this program type */ + LIBBPF_ERRNO__WRNGPID, /* Wrong pid in netlink message */ + LIBBPF_ERRNO__INVSEQ, /* Invalid netlink sequence */ + LIBBPF_ERRNO__NLPARSE, /* netlink parsing error */ + __LIBBPF_ERRNO__END, +}; + +LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); + +/** + * @brief **libbpf_bpf_attach_type_str()** converts the provided attach type + * value into a textual representation. + * @param t The attach type. + * @return Pointer to a static string identifying the attach type. NULL is + * returned for unknown **bpf_attach_type** values. + */ +LIBBPF_API const char *libbpf_bpf_attach_type_str(enum bpf_attach_type t); + +/** + * @brief **libbpf_bpf_link_type_str()** converts the provided link type value + * into a textual representation. + * @param t The link type. + * @return Pointer to a static string identifying the link type. NULL is + * returned for unknown **bpf_link_type** values. + */ +LIBBPF_API const char *libbpf_bpf_link_type_str(enum bpf_link_type t); + +/** + * @brief **libbpf_bpf_map_type_str()** converts the provided map type value + * into a textual representation. + * @param t The map type. + * @return Pointer to a static string identifying the map type. NULL is + * returned for unknown **bpf_map_type** values. + */ +LIBBPF_API const char *libbpf_bpf_map_type_str(enum bpf_map_type t); + +/** + * @brief **libbpf_bpf_prog_type_str()** converts the provided program type + * value into a textual representation. + * @param t The program type. + * @return Pointer to a static string identifying the program type. NULL is + * returned for unknown **bpf_prog_type** values. + */ +LIBBPF_API const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t); + +enum libbpf_print_level { + LIBBPF_WARN, + LIBBPF_INFO, + LIBBPF_DEBUG, +}; + +typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, + const char *, va_list ap); + +LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); + +/* Hide internal to user */ +struct bpf_object; + +struct bpf_object_open_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* object name override, if provided: + * - for object open from file, this will override setting object + * 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; + /* 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 :32; /* stub out now removed attach_prog_fd */ + + /* Additional kernel config content that augments and overrides + * system Kconfig for CONFIG_xxx externs. + */ + const char *kconfig; + /* Path to the custom BTF to be used for BPF CO-RE relocations. + * This custom BTF completely replaces the use of vmlinux BTF + * for the purpose of CO-RE relocations. + * NOTE: any other BPF feature (e.g., fentry/fexit programs, + * struct_ops, etc) will need actual kernel BTF at /sys/kernel/btf/vmlinux. + */ + const char *btf_custom_path; + /* Pointer to a buffer for storing kernel logs for applicable BPF + * commands. Valid kernel_log_size has to be specified as well and are + * passed-through to bpf() syscall. Keep in mind that kernel might + * fail operation with -ENOSPC error if provided buffer is too small + * to contain entire log output. + * See the comment below for kernel_log_level for interaction between + * log_buf and log_level settings. + * + * If specified, this log buffer will be passed for: + * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden + * with bpf_program__set_log() on per-program level, to get + * BPF verifier log output. + * - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get + * BTF sanity checking log. + * + * Each BPF command (BPF_BTF_LOAD or BPF_PROG_LOAD) will overwrite + * previous contents, so if you need more fine-grained control, set + * per-program buffer with bpf_program__set_log_buf() to preserve each + * individual program's verification log. Keep using kernel_log_buf + * for BTF verification log, if necessary. + */ + char *kernel_log_buf; + size_t kernel_log_size; + /* + * Log level can be set independently from log buffer. Log_level=0 + * means that libbpf will attempt loading BTF or program without any + * logging requested, but will retry with either its own or custom log + * buffer, if provided, and log_level=1 on any error. + * And vice versa, setting log_level>0 will request BTF or prog + * loading with verbose log from the first attempt (and as such also + * for successfully loaded BTF or program), and the actual log buffer + * could be either libbpf's own auto-allocated log buffer, if + * kernel_log_buffer is NULL, or user-provided custom kernel_log_buf. + * If user didn't provide custom log buffer, libbpf will emit captured + * logs through its print callback. + */ + __u32 kernel_log_level; + + size_t :0; +}; +#define bpf_object_open_opts__last_field kernel_log_level + +LIBBPF_API struct bpf_object *bpf_object__open(const char *path); + +/** + * @brief **bpf_object__open_file()** creates a bpf_object by opening + * the BPF ELF object file pointed to by the passed path and loading it + * into memory. + * @param path BPF object file path + * @param opts options for how to load the bpf object, this parameter is + * optional and can be set to NULL + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ +LIBBPF_API struct bpf_object * +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); + +/** + * @brief **bpf_object__open_mem()** creates a bpf_object by reading + * the BPF objects raw bytes from a memory buffer containing a valid + * BPF ELF object file. + * @param obj_buf pointer to the buffer containing ELF file bytes + * @param obj_buf_sz number of bytes in the buffer + * @param opts options for how to load the bpf object + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ +LIBBPF_API struct bpf_object * +bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, + const struct bpf_object_open_opts *opts); + +/* Load/unload object into/from kernel */ +LIBBPF_API int bpf_object__load(struct bpf_object *obj); + +LIBBPF_API void bpf_object__close(struct bpf_object *object); + +/* pin_maps and unpin_maps can both be called with a NULL path, in which case + * they will use the pin_path attribute of each map (and ignore all maps that + * 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); +LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, + const char *path); +LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj, + const char *path); +LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); + +LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); +LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); +LIBBPF_API int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version); + +struct btf; +LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); +LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); + +LIBBPF_API struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name); + +LIBBPF_API int +libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type); +LIBBPF_API int libbpf_attach_type_by_name(const char *name, + enum bpf_attach_type *attach_type); +LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name, + enum bpf_attach_type attach_type); + +/* Accessors of bpf_program */ +struct bpf_program; + +LIBBPF_API struct bpf_program * +bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prog); + +#define bpf_object__for_each_program(pos, obj) \ + for ((pos) = bpf_object__next_program((obj), NULL); \ + (pos) != NULL; \ + (pos) = bpf_object__next_program((obj), (pos))) + +LIBBPF_API struct bpf_program * +bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog); + +LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, + __u32 ifindex); + +LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog); +LIBBPF_API const char *bpf_program__section_name(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload); +LIBBPF_API bool bpf_program__autoattach(const struct bpf_program *prog); +LIBBPF_API void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach); + +struct bpf_insn; + +/** + * @brief **bpf_program__insns()** gives read-only access to BPF program's + * underlying BPF instructions. + * @param prog BPF program for which to return instructions + * @return a pointer to an array of BPF instructions that belong to the + * specified BPF program + * + * Returned pointer is always valid and not NULL. Number of `struct bpf_insn` + * pointed to can be fetched using **bpf_program__insn_cnt()** API. + * + * Keep in mind, libbpf can modify and append/delete BPF program's + * instructions as it processes BPF object file and prepares everything for + * uploading into the kernel. So depending on the point in BPF object + * lifetime, **bpf_program__insns()** can return different sets of + * instructions. As an example, during BPF object load phase BPF program + * instructions will be CO-RE-relocated, BPF subprograms instructions will be + * appended, ldimm64 instructions will have FDs embedded, etc. So instructions + * returned before **bpf_object__load()** and after it might be quite + * different. + */ +LIBBPF_API const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog); + +/** + * @brief **bpf_program__set_insns()** can set BPF program's underlying + * BPF instructions. + * + * WARNING: This is a very advanced libbpf API and users need to know + * what they are doing. This should be used from prog_prepare_load_fn + * callback only. + * + * @param prog BPF program for which to return instructions + * @param new_insns a pointer to an array of BPF instructions + * @param new_insn_cnt number of `struct bpf_insn`'s that form + * specified BPF program + * @return 0, on success; negative error code, otherwise + */ +LIBBPF_API int bpf_program__set_insns(struct bpf_program *prog, + struct bpf_insn *new_insns, size_t new_insn_cnt); + +/** + * @brief **bpf_program__insn_cnt()** returns number of `struct bpf_insn`'s + * that form specified BPF program. + * @param prog BPF program for which to return number of BPF instructions + * + * See **bpf_program__insns()** documentation for notes on how libbpf can + * change instructions and their count during different phases of + * **bpf_object** lifetime. + */ +LIBBPF_API size_t bpf_program__insn_cnt(const struct bpf_program *prog); + +LIBBPF_API int bpf_program__fd(const struct bpf_program *prog); + +/** + * @brief **bpf_program__pin()** pins the BPF program to a file + * in the BPF FS specified by a path. This increments the programs + * reference count, allowing it to stay loaded after the process + * which loaded it has exited. + * + * @param prog BPF program to pin, must already be loaded + * @param path file path in a BPF file system + * @return 0, on success; negative error code, otherwise + */ +LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); + +/** + * @brief **bpf_program__unpin()** unpins the BPF program from a file + * in the BPFFS specified by a path. This decrements the programs + * reference count. + * + * The file pinning the BPF program can also be unlinked by a different + * process in which case this function will return an error. + * + * @param prog BPF program to unpin + * @param path file path to the pin in a BPF file system + * @return 0, on success; negative error code, otherwise + */ +LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path); +LIBBPF_API void bpf_program__unload(struct bpf_program *prog); + +struct bpf_link; + +LIBBPF_API struct bpf_link *bpf_link__open(const char *path); +LIBBPF_API int bpf_link__fd(const struct bpf_link *link); +LIBBPF_API const char *bpf_link__pin_path(const struct bpf_link *link); +/** + * @brief **bpf_link__pin()** pins the BPF link to a file + * in the BPF FS specified by a path. This increments the links + * reference count, allowing it to stay loaded after the process + * which loaded it has exited. + * + * @param link BPF link to pin, must already be loaded + * @param path file path in a BPF file system + * @return 0, on success; negative error code, otherwise + */ + +LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path); + +/** + * @brief **bpf_link__unpin()** unpins the BPF link from a file + * in the BPFFS specified by a path. This decrements the links + * reference count. + * + * The file pinning the BPF link can also be unlinked by a different + * process in which case this function will return an error. + * + * @param prog BPF program to unpin + * @param path file path to the pin in a BPF file system + * @return 0, on success; negative error code, otherwise + */ +LIBBPF_API int bpf_link__unpin(struct bpf_link *link); +LIBBPF_API int bpf_link__update_program(struct bpf_link *link, + struct bpf_program *prog); +LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); +LIBBPF_API int bpf_link__detach(struct bpf_link *link); +LIBBPF_API int bpf_link__destroy(struct bpf_link *link); + +/** + * @brief **bpf_program__attach()** is a generic function for attaching + * a BPF program based on auto-detection of program type, attach type, + * and extra paremeters, where applicable. + * + * @param prog BPF program to attach + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + * + * This is supported for: + * - kprobe/kretprobe (depends on SEC() definition) + * - uprobe/uretprobe (depends on SEC() definition) + * - tracepoint + * - raw tracepoint + * - tracing programs (typed raw TP/fentry/fexit/fmod_ret) + */ +LIBBPF_API struct bpf_link * +bpf_program__attach(const struct bpf_program *prog); + +struct bpf_perf_event_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* custom user-provided value fetchable through bpf_get_attach_cookie() */ + __u64 bpf_cookie; +}; +#define bpf_perf_event_opts__last_field bpf_cookie + +LIBBPF_API struct bpf_link * +bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd); + +LIBBPF_API struct bpf_link * +bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, + const struct bpf_perf_event_opts *opts); + +struct bpf_kprobe_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* custom user-provided value fetchable through bpf_get_attach_cookie() */ + __u64 bpf_cookie; + /* function's offset to install kprobe to */ + size_t offset; + /* kprobe is return probe */ + bool retprobe; + size_t :0; +}; +#define bpf_kprobe_opts__last_field retprobe + +LIBBPF_API struct bpf_link * +bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, + const char *func_name); +LIBBPF_API struct bpf_link * +bpf_program__attach_kprobe_opts(const struct bpf_program *prog, + const char *func_name, + const struct bpf_kprobe_opts *opts); + +struct bpf_kprobe_multi_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* array of function symbols to attach */ + const char **syms; + /* array of function addresses to attach */ + const unsigned long *addrs; + /* array of user-provided values fetchable through bpf_get_attach_cookie */ + const __u64 *cookies; + /* number of elements in syms/addrs/cookies arrays */ + size_t cnt; + /* create return kprobes */ + bool retprobe; + size_t :0; +}; + +#define bpf_kprobe_multi_opts__last_field retprobe + +LIBBPF_API struct bpf_link * +bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, + const char *pattern, + const struct bpf_kprobe_multi_opts *opts); + +struct bpf_ksyscall_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* custom user-provided value fetchable through bpf_get_attach_cookie() */ + __u64 bpf_cookie; + /* attach as return probe? */ + bool retprobe; + size_t :0; +}; +#define bpf_ksyscall_opts__last_field retprobe + +/** + * @brief **bpf_program__attach_ksyscall()** attaches a BPF program + * to kernel syscall handler of a specified syscall. Optionally it's possible + * to request to install retprobe that will be triggered at syscall exit. It's + * also possible to associate BPF cookie (though options). + * + * Libbpf automatically will determine correct full kernel function name, + * which depending on system architecture and kernel version/configuration + * could be of the form __<arch>_sys_<syscall> or __se_sys_<syscall>, and will + * attach specified program using kprobe/kretprobe mechanism. + * + * **bpf_program__attach_ksyscall()** is an API counterpart of declarative + * **SEC("ksyscall/<syscall>")** annotation of BPF programs. + * + * At the moment **SEC("ksyscall")** and **bpf_program__attach_ksyscall()** do + * not handle all the calling convention quirks for mmap(), clone() and compat + * syscalls. It also only attaches to "native" syscall interfaces. If host + * system supports compat syscalls or defines 32-bit syscalls in 64-bit + * kernel, such syscall interfaces won't be attached to by libbpf. + * + * These limitations may or may not change in the future. Therefore it is + * recommended to use SEC("kprobe") for these syscalls or if working with + * compat and 32-bit interfaces is required. + * + * @param prog BPF program to attach + * @param syscall_name Symbolic name of the syscall (e.g., "bpf") + * @param opts Additional options (see **struct bpf_ksyscall_opts**) + * @return Reference to the newly created BPF link; or NULL is returned on + * error, error code is stored in errno + */ +LIBBPF_API struct bpf_link * +bpf_program__attach_ksyscall(const struct bpf_program *prog, + const char *syscall_name, + const struct bpf_ksyscall_opts *opts); + +struct bpf_uprobe_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* offset of kernel reference counted USDT semaphore, added in + * a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe") + */ + size_t ref_ctr_offset; + /* custom user-provided value fetchable through bpf_get_attach_cookie() */ + __u64 bpf_cookie; + /* uprobe is return probe, invoked at function return time */ + bool retprobe; + /* Function name to attach to. Could be an unqualified ("abc") or library-qualified + * "abc@LIBXYZ" name. To specify function entry, func_name should be set while + * func_offset argument to bpf_prog__attach_uprobe_opts() should be 0. To trace an + * offset within a function, specify func_name and use func_offset argument to specify + * offset within the function. Shared library functions must specify the shared library + * binary_path. + */ + const char *func_name; + size_t :0; +}; +#define bpf_uprobe_opts__last_field func_name + +/** + * @brief **bpf_program__attach_uprobe()** attaches a BPF program + * to the userspace function which is found by binary path and + * offset. You can optionally specify a particular proccess to attach + * to. You can also optionally attach the program to the function + * exit instead of entry. + * + * @param prog BPF program to attach + * @param retprobe Attach to function exit + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains the function symbol + * @param func_offset Offset within the binary of the function symbol + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ +LIBBPF_API struct bpf_link * +bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, + pid_t pid, const char *binary_path, + size_t func_offset); + +/** + * @brief **bpf_program__attach_uprobe_opts()** is just like + * bpf_program__attach_uprobe() except with a options struct + * for various configurations. + * + * @param prog BPF program to attach + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains the function symbol + * @param func_offset Offset within the binary of the function symbol + * @param opts Options for altering program attachment + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ +LIBBPF_API struct bpf_link * +bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, + const char *binary_path, size_t func_offset, + const struct bpf_uprobe_opts *opts); + +struct bpf_usdt_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* custom user-provided value accessible through usdt_cookie() */ + __u64 usdt_cookie; + size_t :0; +}; +#define bpf_usdt_opts__last_field usdt_cookie + +/** + * @brief **bpf_program__attach_usdt()** is just like + * bpf_program__attach_uprobe_opts() except it covers USDT (User-space + * Statically Defined Tracepoint) attachment, instead of attaching to + * user-space function entry or exit. + * + * @param prog BPF program to attach + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains provided USDT probe + * @param usdt_provider USDT provider name + * @param usdt_name USDT probe name + * @param opts Options for altering program attachment + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ +LIBBPF_API struct bpf_link * +bpf_program__attach_usdt(const struct bpf_program *prog, + pid_t pid, const char *binary_path, + const char *usdt_provider, const char *usdt_name, + const struct bpf_usdt_opts *opts); + +struct bpf_tracepoint_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* custom user-provided value fetchable through bpf_get_attach_cookie() */ + __u64 bpf_cookie; +}; +#define bpf_tracepoint_opts__last_field bpf_cookie + +LIBBPF_API struct bpf_link * +bpf_program__attach_tracepoint(const struct bpf_program *prog, + const char *tp_category, + const char *tp_name); +LIBBPF_API struct bpf_link * +bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, + const char *tp_category, + const char *tp_name, + const struct bpf_tracepoint_opts *opts); + +LIBBPF_API struct bpf_link * +bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, + const char *tp_name); + +struct bpf_trace_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* custom user-provided value fetchable through bpf_get_attach_cookie() */ + __u64 cookie; +}; +#define bpf_trace_opts__last_field cookie + +LIBBPF_API struct bpf_link * +bpf_program__attach_trace(const struct bpf_program *prog); +LIBBPF_API struct bpf_link * +bpf_program__attach_trace_opts(const struct bpf_program *prog, const struct bpf_trace_opts *opts); + +LIBBPF_API struct bpf_link * +bpf_program__attach_lsm(const struct bpf_program *prog); +LIBBPF_API struct bpf_link * +bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd); +LIBBPF_API struct bpf_link * +bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd); +LIBBPF_API struct bpf_link * +bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex); +LIBBPF_API struct bpf_link * +bpf_program__attach_freplace(const struct bpf_program *prog, + int target_fd, const char *attach_func_name); + +struct bpf_map; + +LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); + +struct bpf_iter_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + union bpf_iter_link_info *link_info; + __u32 link_info_len; +}; +#define bpf_iter_attach_opts__last_field link_info_len + +LIBBPF_API struct bpf_link * +bpf_program__attach_iter(const struct bpf_program *prog, + const struct bpf_iter_attach_opts *opts); + +LIBBPF_API enum bpf_prog_type bpf_program__type(const struct bpf_program *prog); + +/** + * @brief **bpf_program__set_type()** sets the program + * type of the passed BPF program. + * @param prog BPF program to set the program type for + * @param type program type to set the BPF map to have + * @return error code; or 0 if no error. An error occurs + * if the object is already loaded. + * + * This must be called before the BPF object is loaded, + * otherwise it has no effect and an error is returned. + */ +LIBBPF_API int bpf_program__set_type(struct bpf_program *prog, + enum bpf_prog_type type); + +LIBBPF_API enum bpf_attach_type +bpf_program__expected_attach_type(const struct bpf_program *prog); + +/** + * @brief **bpf_program__set_expected_attach_type()** sets the + * attach type of the passed BPF program. This is used for + * auto-detection of attachment when programs are loaded. + * @param prog BPF program to set the attach type for + * @param type attach type to set the BPF map to have + * @return error code; or 0 if no error. An error occurs + * if the object is already loaded. + * + * This must be called before the BPF object is loaded, + * otherwise it has no effect and an error is returned. + */ +LIBBPF_API int +bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); + +LIBBPF_API __u32 bpf_program__flags(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_flags(struct bpf_program *prog, __u32 flags); + +/* Per-program log level and log buffer getters/setters. + * See bpf_object_open_opts comments regarding log_level and log_buf + * interactions. + */ +LIBBPF_API __u32 bpf_program__log_level(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level); +LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size); +LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size); + +/** + * @brief **bpf_program__set_attach_target()** sets BTF-based attach target + * for supported BPF program types: + * - BTF-aware raw tracepoints (tp_btf); + * - fentry/fexit/fmod_ret; + * - lsm; + * - freplace. + * @param prog BPF program to set the attach type for + * @param type attach type to set the BPF map to have + * @return error code; or 0 if no error occurred. + */ +LIBBPF_API int +bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, + const char *attach_func_name); + +/** + * @brief **bpf_object__find_map_by_name()** returns BPF map of + * the given name, if it exists within the passed BPF object + * @param obj BPF object + * @param name name of the BPF map + * @return BPF map instance, if such map exists within the BPF object; + * or NULL otherwise. + */ +LIBBPF_API struct bpf_map * +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); + +LIBBPF_API int +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name); + +LIBBPF_API struct bpf_map * +bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *map); + +#define bpf_object__for_each_map(pos, obj) \ + for ((pos) = bpf_object__next_map((obj), NULL); \ + (pos) != NULL; \ + (pos) = bpf_object__next_map((obj), (pos))) +#define bpf_map__for_each bpf_object__for_each_map + +LIBBPF_API struct bpf_map * +bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map); + +/** + * @brief **bpf_map__set_autocreate()** sets whether libbpf has to auto-create + * BPF map during BPF object load phase. + * @param map the BPF map instance + * @param autocreate whether to create BPF map during BPF object load + * @return 0 on success; -EBUSY if BPF object was already loaded + * + * **bpf_map__set_autocreate()** allows to opt-out from libbpf auto-creating + * BPF map. By default, libbpf will attempt to create every single BPF map + * defined in BPF object file using BPF_MAP_CREATE command of bpf() syscall + * and fill in map FD in BPF instructions. + * + * This API allows to opt-out of this process for specific map instance. This + * can be useful if host kernel doesn't support such BPF map type or used + * combination of flags and user application wants to avoid creating such + * a map in the first place. User is still responsible to make sure that their + * BPF-side code that expects to use such missing BPF map is recognized by BPF + * verifier as dead code, otherwise BPF verifier will reject such BPF program. + */ +LIBBPF_API int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate); +LIBBPF_API bool bpf_map__autocreate(const struct bpf_map *map); + +/** + * @brief **bpf_map__fd()** gets the file descriptor of the passed + * BPF map + * @param map the BPF map instance + * @return the file descriptor; or -EINVAL in case of an error + */ +LIBBPF_API int bpf_map__fd(const struct bpf_map *map); +LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); +/* get map name */ +LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); +/* get/set map type */ +LIBBPF_API enum bpf_map_type bpf_map__type(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type); +/* get/set map size (max_entries) */ +LIBBPF_API __u32 bpf_map__max_entries(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries); +/* get/set map flags */ +LIBBPF_API __u32 bpf_map__map_flags(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags); +/* get/set map NUMA node */ +LIBBPF_API __u32 bpf_map__numa_node(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node); +/* get/set map key size */ +LIBBPF_API __u32 bpf_map__key_size(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_key_size(struct bpf_map *map, __u32 size); +/* get/set map value size */ +LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_value_size(struct bpf_map *map, __u32 size); +/* get map key/value BTF type IDs */ +LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); +LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); +/* get/set map if_index */ +LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); +/* get/set map map_extra flags */ +LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); + +LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, + const void *data, size_t size); +LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); + +/** + * @brief **bpf_map__is_internal()** tells the caller whether or not the + * passed map is a special map created by libbpf automatically for things like + * global variables, __ksym externs, Kconfig values, etc + * @param map the bpf_map + * @return true, if the map is an internal map; false, otherwise + */ +LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); +LIBBPF_API const char *bpf_map__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); + +LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); +LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); + +/** + * @brief **bpf_map__lookup_elem()** allows to lookup BPF map value + * corresponding to provided key. + * @param map BPF map to lookup element in + * @param key pointer to memory containing bytes of the key used for lookup + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @param value pointer to memory in which looked up value will be stored + * @param value_sz size in byte of value data memory; it has to match BPF map + * definition's **value_size**. For per-CPU BPF maps value size has to be + * a product of BPF map value size and number of possible CPUs in the system + * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for + * per-CPU values value size has to be aligned up to closest 8 bytes for + * alignment reasons, so expected size is: `round_up(value_size, 8) + * * libbpf_num_possible_cpus()`. + * @flags extra flags passed to kernel for this operation + * @return 0, on success; negative error, otherwise + * + * **bpf_map__lookup_elem()** is high-level equivalent of + * **bpf_map_lookup_elem()** API with added check for key and value size. + */ +LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + void *value, size_t value_sz, __u64 flags); + +/** + * @brief **bpf_map__update_elem()** allows to insert or update value in BPF + * map that corresponds to provided key. + * @param map BPF map to insert to or update element in + * @param key pointer to memory containing bytes of the key + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @param value pointer to memory containing bytes of the value + * @param value_sz size in byte of value data memory; it has to match BPF map + * definition's **value_size**. For per-CPU BPF maps value size has to be + * a product of BPF map value size and number of possible CPUs in the system + * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for + * per-CPU values value size has to be aligned up to closest 8 bytes for + * alignment reasons, so expected size is: `round_up(value_size, 8) + * * libbpf_num_possible_cpus()`. + * @flags extra flags passed to kernel for this operation + * @return 0, on success; negative error, otherwise + * + * **bpf_map__update_elem()** is high-level equivalent of + * **bpf_map_update_elem()** API with added check for key and value size. + */ +LIBBPF_API int bpf_map__update_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + const void *value, size_t value_sz, __u64 flags); + +/** + * @brief **bpf_map__delete_elem()** allows to delete element in BPF map that + * corresponds to provided key. + * @param map BPF map to delete element from + * @param key pointer to memory containing bytes of the key + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @flags extra flags passed to kernel for this operation + * @return 0, on success; negative error, otherwise + * + * **bpf_map__delete_elem()** is high-level equivalent of + * **bpf_map_delete_elem()** API with added check for key size. + */ +LIBBPF_API int bpf_map__delete_elem(const struct bpf_map *map, + const void *key, size_t key_sz, __u64 flags); + +/** + * @brief **bpf_map__lookup_and_delete_elem()** allows to lookup BPF map value + * corresponding to provided key and atomically delete it afterwards. + * @param map BPF map to lookup element in + * @param key pointer to memory containing bytes of the key used for lookup + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @param value pointer to memory in which looked up value will be stored + * @param value_sz size in byte of value data memory; it has to match BPF map + * definition's **value_size**. For per-CPU BPF maps value size has to be + * a product of BPF map value size and number of possible CPUs in the system + * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for + * per-CPU values value size has to be aligned up to closest 8 bytes for + * alignment reasons, so expected size is: `round_up(value_size, 8) + * * libbpf_num_possible_cpus()`. + * @flags extra flags passed to kernel for this operation + * @return 0, on success; negative error, otherwise + * + * **bpf_map__lookup_and_delete_elem()** is high-level equivalent of + * **bpf_map_lookup_and_delete_elem()** API with added check for key and value size. + */ +LIBBPF_API int bpf_map__lookup_and_delete_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + void *value, size_t value_sz, __u64 flags); + +/** + * @brief **bpf_map__get_next_key()** allows to iterate BPF map keys by + * fetching next key that follows current key. + * @param map BPF map to fetch next key from + * @param cur_key pointer to memory containing bytes of current key or NULL to + * fetch the first key + * @param next_key pointer to memory to write next key into + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @return 0, on success; -ENOENT if **cur_key** is the last key in BPF map; + * negative error, otherwise + * + * **bpf_map__get_next_key()** is high-level equivalent of + * **bpf_map_get_next_key()** API with added check for key size. + */ +LIBBPF_API int bpf_map__get_next_key(const struct bpf_map *map, + const void *cur_key, void *next_key, size_t key_sz); + +struct bpf_xdp_set_link_opts { + size_t sz; + int old_fd; + size_t :0; +}; +#define bpf_xdp_set_link_opts__last_field old_fd + +struct bpf_xdp_attach_opts { + size_t sz; + int old_prog_fd; + size_t :0; +}; +#define bpf_xdp_attach_opts__last_field old_prog_fd + +struct bpf_xdp_query_opts { + size_t sz; + __u32 prog_id; /* output */ + __u32 drv_prog_id; /* output */ + __u32 hw_prog_id; /* output */ + __u32 skb_prog_id; /* output */ + __u8 attach_mode; /* output */ + size_t :0; +}; +#define bpf_xdp_query_opts__last_field attach_mode + +LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_detach(int ifindex, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_query(int ifindex, int flags, struct bpf_xdp_query_opts *opts); +LIBBPF_API int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id); + +/* TC related API */ +enum bpf_tc_attach_point { + BPF_TC_INGRESS = 1 << 0, + BPF_TC_EGRESS = 1 << 1, + BPF_TC_CUSTOM = 1 << 2, +}; + +#define BPF_TC_PARENT(a, b) \ + ((((a) << 16) & 0xFFFF0000U) | ((b) & 0x0000FFFFU)) + +enum bpf_tc_flags { + BPF_TC_F_REPLACE = 1 << 0, +}; + +struct bpf_tc_hook { + size_t sz; + int ifindex; + enum bpf_tc_attach_point attach_point; + __u32 parent; + size_t :0; +}; +#define bpf_tc_hook__last_field parent + +struct bpf_tc_opts { + size_t sz; + int prog_fd; + __u32 flags; + __u32 prog_id; + __u32 handle; + __u32 priority; + size_t :0; +}; +#define bpf_tc_opts__last_field priority + +LIBBPF_API int bpf_tc_hook_create(struct bpf_tc_hook *hook); +LIBBPF_API int bpf_tc_hook_destroy(struct bpf_tc_hook *hook); +LIBBPF_API int bpf_tc_attach(const struct bpf_tc_hook *hook, + struct bpf_tc_opts *opts); +LIBBPF_API int bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts); +LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook, + struct bpf_tc_opts *opts); + +/* Ring buffer APIs */ +struct ring_buffer; +struct user_ring_buffer; + +typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size); + +struct ring_buffer_opts { + size_t sz; /* size of this struct, for forward/backward compatiblity */ +}; + +#define ring_buffer_opts__last_field sz + +LIBBPF_API struct ring_buffer * +ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, + const struct ring_buffer_opts *opts); +LIBBPF_API void ring_buffer__free(struct ring_buffer *rb); +LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd, + ring_buffer_sample_fn sample_cb, void *ctx); +LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms); +LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb); +LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb); + +struct user_ring_buffer_opts { + size_t sz; /* size of this struct, for forward/backward compatibility */ +}; + +#define user_ring_buffer_opts__last_field sz + +/* @brief **user_ring_buffer__new()** creates a new instance of a user ring + * buffer. + * + * @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map. + * @param opts Options for how the ring buffer should be created. + * @return A user ring buffer on success; NULL and errno being set on a + * failure. + */ +LIBBPF_API struct user_ring_buffer * +user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts); + +/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the + * user ring buffer. + * @param rb A pointer to a user ring buffer. + * @param size The size of the sample, in bytes. + * @return A pointer to an 8-byte aligned reserved region of the user ring + * buffer; NULL, and errno being set if a sample could not be reserved. + * + * This function is *not* thread safe, and callers must synchronize accessing + * this function if there are multiple producers. If a size is requested that + * is larger than the size of the entire ring buffer, errno will be set to + * E2BIG and NULL is returned. If the ring buffer could accommodate the size, + * but currently does not have enough space, errno is set to ENOSPC and NULL is + * returned. + * + * After initializing the sample, callers must invoke + * **user_ring_buffer__submit()** to post the sample to the kernel. Otherwise, + * the sample must be freed with **user_ring_buffer__discard()**. + */ +LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size); + +/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the + * ring buffer, possibly blocking for up to @timeout_ms until a sample becomes + * available. + * @param rb The user ring buffer. + * @param size The size of the sample, in bytes. + * @param timeout_ms The amount of time, in milliseconds, for which the caller + * should block when waiting for a sample. -1 causes the caller to block + * indefinitely. + * @return A pointer to an 8-byte aligned reserved region of the user ring + * buffer; NULL, and errno being set if a sample could not be reserved. + * + * This function is *not* thread safe, and callers must synchronize + * accessing this function if there are multiple producers + * + * If **timeout_ms** is -1, the function will block indefinitely until a sample + * becomes available. Otherwise, **timeout_ms** must be non-negative, or errno + * is set to EINVAL, and NULL is returned. If **timeout_ms** is 0, no blocking + * will occur and the function will return immediately after attempting to + * reserve a sample. + * + * If **size** is larger than the size of the entire ring buffer, errno is set + * to E2BIG and NULL is returned. If the ring buffer could accommodate + * **size**, but currently does not have enough space, the caller will block + * until at most **timeout_ms** has elapsed. If insufficient space is available + * at that time, errno is set to ENOSPC, and NULL is returned. + * + * The kernel guarantees that it will wake up this thread to check if + * sufficient space is available in the ring buffer at least once per + * invocation of the **bpf_ringbuf_drain()** helper function, provided that at + * least one sample is consumed, and the BPF program did not invoke the + * function with BPF_RB_NO_WAKEUP. A wakeup may occur sooner than that, but the + * kernel does not guarantee this. If the helper function is invoked with + * BPF_RB_FORCE_WAKEUP, a wakeup event will be sent even if no sample is + * consumed. + * + * When a sample of size **size** is found within **timeout_ms**, a pointer to + * the sample is returned. After initializing the sample, callers must invoke + * **user_ring_buffer__submit()** to post the sample to the ring buffer. + * Otherwise, the sample must be freed with **user_ring_buffer__discard()**. + */ +LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, + __u32 size, + int timeout_ms); + +/* @brief **user_ring_buffer__submit()** submits a previously reserved sample + * into the ring buffer. + * @param rb The user ring buffer. + * @param sample A reserved sample. + * + * It is not necessary to synchronize amongst multiple producers when invoking + * this function. + */ +LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample); + +/* @brief **user_ring_buffer__discard()** discards a previously reserved sample. + * @param rb The user ring buffer. + * @param sample A reserved sample. + * + * It is not necessary to synchronize amongst multiple producers when invoking + * this function. + */ +LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample); + +/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously + * created with **user_ring_buffer__new()**. + * @param rb The user ring buffer being freed. + */ +LIBBPF_API void user_ring_buffer__free(struct user_ring_buffer *rb); + +/* Perf buffer APIs */ +struct perf_buffer; + +typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu, + void *data, __u32 size); +typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); + +/* common use perf buffer options */ +struct perf_buffer_opts { + size_t sz; +}; +#define perf_buffer_opts__last_field sz + +/** + * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified + * BPF_PERF_EVENT_ARRAY map + * @param map_fd FD of BPF_PERF_EVENT_ARRAY BPF map that will be used by BPF + * code to send data over to user-space + * @param page_cnt number of memory pages allocated for each per-CPU buffer + * @param sample_cb function called on each received data record + * @param lost_cb function called when record loss has occurred + * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb* + * @return a new instance of struct perf_buffer on success, NULL on error with + * *errno* containing an error code + */ +LIBBPF_API struct perf_buffer * +perf_buffer__new(int map_fd, size_t page_cnt, + perf_buffer_sample_fn sample_cb, perf_buffer_lost_fn lost_cb, void *ctx, + const struct perf_buffer_opts *opts); + +enum bpf_perf_event_ret { + LIBBPF_PERF_EVENT_DONE = 0, + LIBBPF_PERF_EVENT_ERROR = -1, + LIBBPF_PERF_EVENT_CONT = -2, +}; + +struct perf_event_header; + +typedef enum bpf_perf_event_ret +(*perf_buffer_event_fn)(void *ctx, int cpu, struct perf_event_header *event); + +/* raw perf buffer options, giving most power and control */ +struct perf_buffer_raw_opts { + size_t sz; + long :0; + long :0; + /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of + * max_entries of given PERF_EVENT_ARRAY map) + */ + int cpu_cnt; + /* if cpu_cnt > 0, cpus is an array of CPUs to open ring buffers on */ + int *cpus; + /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */ + int *map_keys; +}; +#define perf_buffer_raw_opts__last_field map_keys + +struct perf_event_attr; + +LIBBPF_API struct perf_buffer * +perf_buffer__new_raw(int map_fd, size_t page_cnt, struct perf_event_attr *attr, + perf_buffer_event_fn event_cb, void *ctx, + const struct perf_buffer_raw_opts *opts); + +LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); +LIBBPF_API int perf_buffer__epoll_fd(const struct perf_buffer *pb); +LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); +LIBBPF_API int perf_buffer__consume(struct perf_buffer *pb); +LIBBPF_API int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx); +LIBBPF_API size_t perf_buffer__buffer_cnt(const struct perf_buffer *pb); +LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx); +/** + * @brief **perf_buffer__buffer()** returns the per-cpu raw mmap()'ed underlying + * memory region of the ring buffer. + * This ring buffer can be used to implement a custom events consumer. + * The ring buffer starts with the *struct perf_event_mmap_page*, which + * holds the ring buffer managment fields, when accessing the header + * structure it's important to be SMP aware. + * You can refer to *perf_event_read_simple* for a simple example. + * @param pb the perf buffer structure + * @param buf_idx the buffer index to retreive + * @param buf (out) gets the base pointer of the mmap()'ed memory + * @param buf_size (out) gets the size of the mmap()'ed region + * @return 0 on success, negative error code for failure + */ +LIBBPF_API int perf_buffer__buffer(struct perf_buffer *pb, int buf_idx, void **buf, + size_t *buf_size); + +struct bpf_prog_linfo; +struct bpf_prog_info; + +LIBBPF_API void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo); +LIBBPF_API struct bpf_prog_linfo * +bpf_prog_linfo__new(const struct bpf_prog_info *info); +LIBBPF_API const struct bpf_line_info * +bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo, + __u64 addr, __u32 func_idx, __u32 nr_skip); +LIBBPF_API const struct bpf_line_info * +bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo, + __u32 insn_off, __u32 nr_skip); + +/* + * Probe for supported system features + * + * Note that running many of these probes in a short amount of time can cause + * the kernel to reach the maximal size of lockable memory allowed for the + * user, causing subsequent probes to fail. In this case, the caller may want + * to adjust that limit with setrlimit(). + */ + +/** + * @brief **libbpf_probe_bpf_prog_type()** detects if host kernel supports + * BPF programs of a given type. + * @param prog_type BPF program type to detect kernel support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given program type is supported; 0, if given program type is + * not supported; negative error code if feature detection failed or can't be + * performed + * + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts); +/** + * @brief **libbpf_probe_bpf_map_type()** detects if host kernel supports + * BPF maps of a given type. + * @param map_type BPF map type to detect kernel support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given map type is supported; 0, if given map type is + * not supported; negative error code if feature detection failed or can't be + * performed + * + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts); +/** + * @brief **libbpf_probe_bpf_helper()** detects if host kernel supports the + * use of a given BPF helper from specified BPF program type. + * @param prog_type BPF program type used to check the support of BPF helper + * @param helper_id BPF helper ID (enum bpf_func_id) to check support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given combination of program type and helper is supported; 0, + * if the combination is not supported; negative error code if feature + * detection for provided input arguments failed or can't be performed + * + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, + enum bpf_func_id helper_id, const void *opts); + +/** + * @brief **libbpf_num_possible_cpus()** is a helper function to get the + * number of possible CPUs that the host kernel supports and expects. + * @return number of possible CPUs; or error code on failure + * + * Example usage: + * + * int ncpus = libbpf_num_possible_cpus(); + * if (ncpus < 0) { + * // error handling + * } + * long values[ncpus]; + * bpf_map_lookup_elem(per_cpu_map_fd, key, values); + */ +LIBBPF_API int libbpf_num_possible_cpus(void); + +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; + const void *data; + size_t data_sz; + + struct bpf_object **obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ + struct bpf_prog_skeleton *progs; +}; + +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); + +struct bpf_var_skeleton { + const char *name; + struct bpf_map **map; + void **addr; +}; + +struct bpf_object_subskeleton { + size_t sz; /* size of this struct, for forward/backward compatibility */ + + const struct bpf_object *obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ + struct bpf_prog_skeleton *progs; + + int var_cnt; + int var_skel_sz; /* sizeof(struct bpf_var_skeleton) */ + struct bpf_var_skeleton *vars; +}; + +LIBBPF_API int +bpf_object__open_subskeleton(struct bpf_object_subskeleton *s); +LIBBPF_API void +bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s); + +struct gen_loader_opts { + size_t sz; /* size of this struct, for forward/backward compatiblity */ + const char *data; + const char *insns; + __u32 data_sz; + __u32 insns_sz; +}; + +#define gen_loader_opts__last_field insns_sz +LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj, + struct gen_loader_opts *opts); + +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + +struct bpf_linker_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; +}; +#define bpf_linker_opts__last_field sz + +struct bpf_linker_file_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; +}; +#define bpf_linker_file_opts__last_field sz + +struct bpf_linker; + +LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts); +LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, + const char *filename, + const struct bpf_linker_file_opts *opts); +LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); +LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); + +/* + * Custom handling of BPF program's SEC() definitions + */ + +struct bpf_prog_load_opts; /* defined in bpf.h */ + +/* Called during bpf_object__open() for each recognized BPF program. Callback + * can use various bpf_program__set_*() setters to adjust whatever properties + * are necessary. + */ +typedef int (*libbpf_prog_setup_fn_t)(struct bpf_program *prog, long cookie); + +/* Called right before libbpf performs bpf_prog_load() to load BPF program + * into the kernel. Callback can adjust opts as necessary. + */ +typedef int (*libbpf_prog_prepare_load_fn_t)(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie); + +/* Called during skeleton attach or through bpf_program__attach(). If + * auto-attach is not supported, callback should return 0 and set link to + * NULL (it's not considered an error during skeleton attach, but it will be + * an error for bpf_program__attach() calls). On error, error should be + * returned directly and link set to NULL. On success, return 0 and set link + * to a valid struct bpf_link. + */ +typedef int (*libbpf_prog_attach_fn_t)(const struct bpf_program *prog, long cookie, + struct bpf_link **link); + +struct libbpf_prog_handler_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* User-provided value that is passed to prog_setup_fn, + * prog_prepare_load_fn, and prog_attach_fn callbacks. Allows user to + * register one set of callbacks for multiple SEC() definitions and + * still be able to distinguish them, if necessary. For example, + * libbpf itself is using this to pass necessary flags (e.g., + * sleepable flag) to a common internal SEC() handler. + */ + long cookie; + /* BPF program initialization callback (see libbpf_prog_setup_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_setup_fn_t prog_setup_fn; + /* BPF program loading callback (see libbpf_prog_prepare_load_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; + /* BPF program attach callback (see libbpf_prog_attach_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_attach_fn_t prog_attach_fn; +}; +#define libbpf_prog_handler_opts__last_field prog_attach_fn + +/** + * @brief **libbpf_register_prog_handler()** registers a custom BPF program + * SEC() handler. + * @param sec section prefix for which custom handler is registered + * @param prog_type BPF program type associated with specified section + * @param exp_attach_type Expected BPF attach type associated with specified section + * @param opts optional cookie, callbacks, and other extra options + * @return Non-negative handler ID is returned on success. This handler ID has + * to be passed to *libbpf_unregister_prog_handler()* to unregister such + * custom handler. Negative error code is returned on error. + * + * *sec* defines which SEC() definitions are handled by this custom handler + * registration. *sec* can have few different forms: + * - if *sec* is just a plain string (e.g., "abc"), it will match only + * SEC("abc"). If BPF program specifies SEC("abc/whatever") it will result + * in an error; + * - if *sec* is of the form "abc/", proper SEC() form is + * SEC("abc/something"), where acceptable "something" should be checked by + * *prog_init_fn* callback, if there are additional restrictions; + * - if *sec* is of the form "abc+", it will successfully match both + * SEC("abc") and SEC("abc/whatever") forms; + * - if *sec* is NULL, custom handler is registered for any BPF program that + * doesn't match any of the registered (custom or libbpf's own) SEC() + * handlers. There could be only one such generic custom handler registered + * at any given time. + * + * All custom handlers (except the one with *sec* == NULL) are processed + * before libbpf's own SEC() handlers. It is allowed to "override" libbpf's + * SEC() handlers by registering custom ones for the same section prefix + * (i.e., it's possible to have custom SEC("perf_event/LLC-load-misses") + * handler). + * + * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), + * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs + * to ensure synchronization if there is a risk of running this API from + * multiple threads simultaneously. + */ +LIBBPF_API int libbpf_register_prog_handler(const char *sec, + enum bpf_prog_type prog_type, + enum bpf_attach_type exp_attach_type, + const struct libbpf_prog_handler_opts *opts); +/** + * @brief *libbpf_unregister_prog_handler()* unregisters previously registered + * custom BPF program SEC() handler. + * @param handler_id handler ID returned by *libbpf_register_prog_handler()* + * after successful registration + * @return 0 on success, negative error code if handler isn't found + * + * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), + * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs + * to ensure synchronization if there is a risk of running this API from + * multiple threads simultaneously. + */ +LIBBPF_API int libbpf_unregister_prog_handler(int handler_id); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_LIBBPF_H */ diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map new file mode 100644 index 000000000..c1d6aa7c8 --- /dev/null +++ b/tools/lib/bpf/libbpf.map @@ -0,0 +1,380 @@ +LIBBPF_0.0.1 { + global: + bpf_btf_get_fd_by_id; + bpf_map__btf_key_type_id; + bpf_map__btf_value_type_id; + bpf_map__fd; + bpf_map__name; + bpf_map__pin; + bpf_map__reuse_fd; + bpf_map__set_ifindex; + bpf_map__set_inner_map_fd; + bpf_map__unpin; + bpf_map_delete_elem; + bpf_map_get_fd_by_id; + bpf_map_get_next_id; + bpf_map_get_next_key; + bpf_map_lookup_and_delete_elem; + bpf_map_lookup_elem; + bpf_map_update_elem; + bpf_obj_get; + bpf_obj_get_info_by_fd; + bpf_obj_pin; + bpf_object__btf_fd; + bpf_object__close; + bpf_object__find_map_by_name; + bpf_object__kversion; + bpf_object__load; + bpf_object__name; + bpf_object__open; + bpf_object__pin; + bpf_object__pin_maps; + bpf_object__pin_programs; + bpf_object__unpin_maps; + bpf_object__unpin_programs; + bpf_prog_attach; + bpf_prog_detach; + bpf_prog_detach2; + bpf_prog_get_fd_by_id; + bpf_prog_get_next_id; + bpf_prog_query; + bpf_program__fd; + bpf_program__pin; + bpf_program__set_expected_attach_type; + bpf_program__set_ifindex; + bpf_program__set_type; + bpf_program__unload; + bpf_program__unpin; + bpf_prog_linfo__free; + bpf_prog_linfo__new; + bpf_prog_linfo__lfind_addr_func; + bpf_prog_linfo__lfind; + bpf_raw_tracepoint_open; + bpf_task_fd_query; + btf__fd; + btf__find_by_name; + btf__free; + btf__name_by_offset; + btf__new; + btf__resolve_size; + btf__resolve_type; + btf__type_by_id; + libbpf_attach_type_by_name; + libbpf_get_error; + libbpf_prog_type_by_name; + libbpf_set_print; + libbpf_strerror; + local: + *; +}; + +LIBBPF_0.0.2 { + global: + bpf_map_lookup_elem_flags; + bpf_object__btf; + bpf_object__find_map_fd_by_name; + btf__get_raw_data; + btf_ext__free; + btf_ext__get_raw_data; + btf_ext__new; +} LIBBPF_0.0.1; + +LIBBPF_0.0.3 { + global: + bpf_map__is_internal; + bpf_map_freeze; +} LIBBPF_0.0.2; + +LIBBPF_0.0.4 { + global: + bpf_link__destroy; + bpf_program__attach_kprobe; + bpf_program__attach_perf_event; + bpf_program__attach_raw_tracepoint; + bpf_program__attach_tracepoint; + bpf_program__attach_uprobe; + btf_dump__dump_type; + btf_dump__free; + btf__parse_elf; + libbpf_num_possible_cpus; + perf_buffer__free; + perf_buffer__poll; +} LIBBPF_0.0.3; + +LIBBPF_0.0.5 { + global: + bpf_btf_get_next_id; +} LIBBPF_0.0.4; + +LIBBPF_0.0.6 { + global: + 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; + 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_program__attach; + bpf_program__name; + btf__align_of; + libbpf_find_kernel_btf; +} LIBBPF_0.0.6; + +LIBBPF_0.0.8 { + global: + bpf_link__fd; + bpf_link__open; + bpf_link__pin; + bpf_link__pin_path; + bpf_link__unpin; + bpf_link__update_program; + bpf_link_create; + bpf_link_update; + bpf_map__set_initial_value; + bpf_prog_attach_opts; + bpf_program__attach_cgroup; + bpf_program__attach_lsm; + bpf_program__set_attach_target; +} LIBBPF_0.0.7; + +LIBBPF_0.0.9 { + global: + bpf_enable_stats; + bpf_iter_create; + bpf_link_get_fd_by_id; + bpf_link_get_next_id; + bpf_program__attach_iter; + bpf_program__attach_netns; + perf_buffer__consume; + ring_buffer__add; + ring_buffer__consume; + ring_buffer__free; + ring_buffer__new; + ring_buffer__poll; +} LIBBPF_0.0.8; + +LIBBPF_0.1.0 { + global: + bpf_link__detach; + bpf_link_detach; + bpf_map__ifindex; + bpf_map__key_size; + bpf_map__map_flags; + bpf_map__max_entries; + bpf_map__numa_node; + bpf_map__set_key_size; + bpf_map__set_map_flags; + bpf_map__set_max_entries; + bpf_map__set_numa_node; + bpf_map__set_type; + bpf_map__set_value_size; + bpf_map__type; + bpf_map__value_size; + bpf_program__attach_xdp; + bpf_program__autoload; + bpf_program__set_autoload; + btf__parse; + btf__parse_raw; + btf__pointer_size; + btf__set_fd; + btf__set_pointer_size; +} LIBBPF_0.0.9; + +LIBBPF_0.2.0 { + global: + bpf_prog_bind_map; + bpf_prog_test_run_opts; + bpf_program__attach_freplace; + bpf_program__section_name; + btf__add_array; + btf__add_const; + btf__add_enum; + btf__add_enum_value; + btf__add_datasec; + btf__add_datasec_var_info; + btf__add_field; + btf__add_func; + btf__add_func_param; + btf__add_func_proto; + btf__add_fwd; + btf__add_int; + btf__add_ptr; + btf__add_restrict; + btf__add_str; + btf__add_struct; + btf__add_typedef; + btf__add_union; + btf__add_var; + btf__add_volatile; + btf__endianness; + btf__find_str; + btf__new_empty; + btf__set_endianness; + btf__str_by_offset; + perf_buffer__buffer_cnt; + perf_buffer__buffer_fd; + perf_buffer__epoll_fd; + perf_buffer__consume_buffer; +} LIBBPF_0.1.0; + +LIBBPF_0.3.0 { + global: + btf__base_btf; + btf__parse_elf_split; + btf__parse_raw_split; + btf__parse_split; + btf__new_empty_split; + btf__new_split; + ring_buffer__epoll_fd; +} LIBBPF_0.2.0; + +LIBBPF_0.4.0 { + global: + btf__add_float; + btf__add_type; + bpf_linker__add_file; + bpf_linker__finalize; + bpf_linker__free; + bpf_linker__new; + bpf_map__inner_map; + bpf_object__set_kversion; + bpf_tc_attach; + bpf_tc_detach; + bpf_tc_hook_create; + bpf_tc_hook_destroy; + bpf_tc_query; +} LIBBPF_0.3.0; + +LIBBPF_0.5.0 { + global: + bpf_map__initial_value; + bpf_map__pin_path; + bpf_map_lookup_and_delete_elem_flags; + bpf_program__attach_kprobe_opts; + bpf_program__attach_perf_event_opts; + bpf_program__attach_tracepoint_opts; + bpf_program__attach_uprobe_opts; + bpf_object__gen_loader; + btf__load_from_kernel_by_id; + btf__load_from_kernel_by_id_split; + btf__load_into_kernel; + btf__load_module_btf; + btf__load_vmlinux_btf; + btf_dump__dump_type_data; + libbpf_set_strict_mode; +} LIBBPF_0.4.0; + +LIBBPF_0.6.0 { + global: + bpf_map__map_extra; + bpf_map__set_map_extra; + bpf_map_create; + bpf_object__next_map; + bpf_object__next_program; + bpf_object__prev_map; + bpf_object__prev_program; + bpf_prog_load; + bpf_program__flags; + bpf_program__insn_cnt; + bpf_program__insns; + bpf_program__set_flags; + btf__add_btf; + btf__add_decl_tag; + btf__add_type_tag; + btf__dedup; + btf__raw_data; + btf__type_cnt; + btf_dump__new; + libbpf_major_version; + libbpf_minor_version; + libbpf_version_string; + perf_buffer__new; + perf_buffer__new_raw; +} LIBBPF_0.5.0; + +LIBBPF_0.7.0 { + global: + bpf_btf_load; + bpf_program__expected_attach_type; + bpf_program__log_buf; + bpf_program__log_level; + bpf_program__set_log_buf; + bpf_program__set_log_level; + bpf_program__type; + bpf_xdp_attach; + bpf_xdp_detach; + bpf_xdp_query; + bpf_xdp_query_id; + btf_ext__raw_data; + libbpf_probe_bpf_helper; + libbpf_probe_bpf_map_type; + libbpf_probe_bpf_prog_type; + libbpf_set_memlock_rlim; +} LIBBPF_0.6.0; + +LIBBPF_0.8.0 { + global: + bpf_map__autocreate; + bpf_map__get_next_key; + bpf_map__delete_elem; + bpf_map__lookup_and_delete_elem; + bpf_map__lookup_elem; + bpf_map__set_autocreate; + bpf_map__update_elem; + bpf_map_delete_elem_flags; + bpf_object__destroy_subskeleton; + bpf_object__open_subskeleton; + bpf_program__attach_kprobe_multi_opts; + bpf_program__attach_trace_opts; + bpf_program__attach_usdt; + bpf_program__set_insns; + libbpf_register_prog_handler; + libbpf_unregister_prog_handler; +} LIBBPF_0.7.0; + +LIBBPF_1.0.0 { + global: + bpf_obj_get_opts; + bpf_prog_query_opts; + bpf_program__attach_ksyscall; + bpf_program__autoattach; + bpf_program__set_autoattach; + btf__add_enum64; + btf__add_enum64_value; + libbpf_bpf_attach_type_str; + libbpf_bpf_link_type_str; + libbpf_bpf_map_type_str; + libbpf_bpf_prog_type_str; + perf_buffer__buffer; +}; + +LIBBPF_1.1.0 { + global: + user_ring_buffer__discard; + user_ring_buffer__free; + user_ring_buffer__new; + user_ring_buffer__reserve; + user_ring_buffer__reserve_blocking; + user_ring_buffer__submit; +} LIBBPF_1.0.0; diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template new file mode 100644 index 000000000..b45ed534b --- /dev/null +++ b/tools/lib/bpf/libbpf.pc.template @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libbpf +Description: BPF library +Version: @VERSION@ +Libs: -L${libdir} -lbpf +Requires.private: libelf zlib +Cflags: -I${includedir} diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h new file mode 100644 index 000000000..9a7937f33 --- /dev/null +++ b/tools/lib/bpf/libbpf_common.h @@ -0,0 +1,73 @@ +/* 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> +#include "libbpf_version.h" + +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + +#define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg))) + +/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */ +#define LIBBPF_DEPRECATED_SINCE(major, minor, msg) \ + __LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor \ + (LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg)) + +#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor) \ + (LIBBPF_MAJOR_VERSION > (major) || \ + (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor))) + +/* Add checks for other versions below when planning deprecation of API symbols + * with the LIBBPF_DEPRECATED_SINCE macro. + */ +#if __LIBBPF_CURRENT_VERSION_GEQ(1, 0) +#define __LIBBPF_MARK_DEPRECATED_1_0(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_1_0(X) +#endif + +/* This set of internal macros allows to do "function overloading" based on + * number of arguments provided by used in backwards-compatible way during the + * transition to libbpf 1.0 + * It's ugly but necessary evil that will be cleaned up when we get to 1.0. + * See bpf_prog_load() overload for example. + */ +#define ___libbpf_cat(A, B) A ## B +#define ___libbpf_select(NAME, NUM) ___libbpf_cat(NAME, NUM) +#define ___libbpf_nth(_1, _2, _3, _4, _5, _6, N, ...) N +#define ___libbpf_cnt(...) ___libbpf_nth(__VA_ARGS__, 6, 5, 4, 3, 2, 1) +#define ___libbpf_overload(NAME, ...) ___libbpf_select(NAME, ___libbpf_cnt(__VA_ARGS__))(__VA_ARGS__) + +/* Helper macro to declare and initialize libbpf options struct + * + * This dance with uninitialized declaration, followed by memset to zero, + * 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 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 new file mode 100644 index 000000000..96f67a772 --- /dev/null +++ b/tools/lib/bpf/libbpf_errno.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. + */ + +#undef _GNU_SOURCE +#include <stdio.h> +#include <string.h> + +#include "libbpf.h" +#include "libbpf_internal.h" + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) +#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) +#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) + +static const char *libbpf_strerror_table[NR_ERRNO] = { + [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf", + [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid", + [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost", + [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch", + [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf", + [ERRCODE_OFFSET(RELOC)] = "Relocation failed", + [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading", + [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", + [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", + [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", + [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", + [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", + [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing", +}; + +int libbpf_strerror(int err, char *buf, size_t size) +{ + if (!buf || !size) + return libbpf_err(-EINVAL); + + err = err > 0 ? err : -err; + + if (err < __LIBBPF_ERRNO__START) { + int ret; + + ret = strerror_r(err, buf, size); + buf[size - 1] = '\0'; + return libbpf_err_errno(ret); + } + + if (err < __LIBBPF_ERRNO__END) { + const char *msg; + + msg = libbpf_strerror_table[ERRNO_OFFSET(err)]; + snprintf(buf, size, "%s", msg); + buf[size - 1] = '\0'; + return 0; + } + + snprintf(buf, size, "Unknown libbpf error %d", err); + buf[size - 1] = '\0'; + return libbpf_err(-ENOENT); +} diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h new file mode 100644 index 000000000..377642ff5 --- /dev/null +++ b/tools/lib/bpf/libbpf_internal.h @@ -0,0 +1,579 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Internal libbpf helpers. + * + * Copyright (c) 2019 Facebook + */ + +#ifndef __LIBBPF_LIBBPF_INTERNAL_H +#define __LIBBPF_LIBBPF_INTERNAL_H + +#include <stdlib.h> +#include <limits.h> +#include <errno.h> +#include <linux/err.h> +#include <fcntl.h> +#include <unistd.h> +#include "relo_core.h" + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +/* prevent accidental re-addition of reallocarray() */ +#pragma GCC poison reallocarray + +#include "libbpf.h" +#include "btf.h" + +#ifndef EM_BPF +#define EM_BPF 247 +#endif + +#ifndef R_BPF_64_64 +#define R_BPF_64_64 1 +#endif +#ifndef R_BPF_64_ABS64 +#define R_BPF_64_ABS64 2 +#endif +#ifndef R_BPF_64_ABS32 +#define R_BPF_64_ABS32 3 +#endif +#ifndef R_BPF_64_32 +#define R_BPF_64_32 10 +#endif + +#ifndef SHT_LLVM_ADDRSIG +#define SHT_LLVM_ADDRSIG 0x6FFF4C03 +#endif + +/* if libelf is old and doesn't support mmap(), fall back to read() */ +#ifndef ELF_C_READ_MMAP +#define ELF_C_READ_MMAP ELF_C_READ +#endif + +/* Older libelf all end up in this expression, for both 32 and 64 bit */ +#ifndef ELF64_ST_VISIBILITY +#define ELF64_ST_VISIBILITY(o) ((o) & 0x03) +#endif + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) +#define BTF_MEMBER_ENC(name, type, bits_offset) (name), (type), (bits_offset) +#define BTF_PARAM_ENC(name, type) (name), (type) +#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) +#define BTF_TYPE_FLOAT_ENC(name, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) +#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) +#define BTF_TYPE_TYPE_TAG_ENC(value, type) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type) + +#ifndef likely +#define likely(x) __builtin_expect(!!(x), 1) +#endif +#ifndef unlikely +#define unlikely(x) __builtin_expect(!!(x), 0) +#endif +#ifndef min +# define min(x, y) ((x) < (y) ? (x) : (y)) +#endif +#ifndef max +# define max(x, y) ((x) < (y) ? (y) : (x)) +#endif +#ifndef offsetofend +# define offsetofend(TYPE, FIELD) \ + (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) +#endif +#ifndef __alias +#define __alias(symbol) __attribute__((alias(#symbol))) +#endif + +/* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is + * a string literal known at compilation time or char * pointer known only at + * runtime. + */ +#define str_has_pfx(str, pfx) \ + (strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0) + +/* suffix check */ +static inline bool str_has_sfx(const char *str, const char *sfx) +{ + size_t str_len = strlen(str); + size_t sfx_len = strlen(sfx); + + if (sfx_len > str_len) + return false; + return strcmp(str + str_len - sfx_len, sfx) == 0; +} + +/* Symbol versioning is different between static and shared library. + * Properly versioned symbols are needed for shared library, but + * only the symbol of the new version is needed for static library. + * Starting with GNU C 10, use symver attribute instead of .symver assembler + * directive, which works better with GCC LTO builds. + */ +#if defined(SHARED) && defined(__GNUC__) && __GNUC__ >= 10 + +#define DEFAULT_VERSION(internal_name, api_name, version) \ + __attribute__((symver(#api_name "@@" #version))) +#define COMPAT_VERSION(internal_name, api_name, version) \ + __attribute__((symver(#api_name "@" #version))) + +#elif defined(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 /* !SHARED */ + +#define COMPAT_VERSION(internal_name, api_name, version) +#define DEFAULT_VERSION(internal_name, api_name, version) \ + extern typeof(internal_name) api_name \ + __attribute__((alias(#internal_name))); + +#endif + +extern void libbpf_print(enum libbpf_print_level level, + const char *format, ...) + __attribute__((format(printf, 2, 3))); + +#define __pr(level, fmt, ...) \ +do { \ + libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \ +} while (0) + +#define pr_warn(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) + +#ifndef __has_builtin +#define __has_builtin(x) 0 +#endif + +struct bpf_link { + int (*detach)(struct bpf_link *link); + void (*dealloc)(struct bpf_link *link); + char *pin_path; /* NULL, if not pinned */ + int fd; /* hook FD, -1 if not applicable */ + bool disconnected; +}; + +/* + * Re-implement glibc's reallocarray() for libbpf internal-only use. + * reallocarray(), unfortunately, is not available in all versions of glibc, + * so requires extra feature detection and using reallocarray() stub from + * <tools/libc_compat.h> and COMPAT_NEED_REALLOCARRAY. All this complicates + * build of libbpf unnecessarily and is just a maintenance burden. Instead, + * it's trivial to implement libbpf-specific internal version and use it + * throughout libbpf. + */ +static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size) +{ + size_t total; + +#if __has_builtin(__builtin_mul_overflow) + if (unlikely(__builtin_mul_overflow(nmemb, size, &total))) + return NULL; +#else + if (size == 0 || nmemb > ULONG_MAX / size) + return NULL; + total = nmemb * size; +#endif + return realloc(ptr, total); +} + +/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst + * is zero-terminated string no matter what (unless sz == 0, in which case + * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs + * in what is returned. Given this is internal helper, it's trivial to extend + * this, when necessary. Use this instead of strncpy inside libbpf source code. + */ +static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz) +{ + size_t i; + + if (sz == 0) + return; + + sz--; + for (i = 0; i < sz && src[i]; i++) + dst[i] = src[i]; + dst[i] = '\0'; +} + +__u32 get_kernel_version(void); + +struct btf; +struct btf_type; + +struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id); +const char *btf_kind_str(const struct btf_type *t); +const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); + +static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t) +{ + return (enum btf_func_linkage)(int)btf_vlen(t); +} + +static inline __u32 btf_type_info(int kind, int vlen, int kflag) +{ + return (kflag << 31) | (kind << 24) | vlen; +} + +enum map_def_parts { + MAP_DEF_MAP_TYPE = 0x001, + MAP_DEF_KEY_TYPE = 0x002, + MAP_DEF_KEY_SIZE = 0x004, + MAP_DEF_VALUE_TYPE = 0x008, + MAP_DEF_VALUE_SIZE = 0x010, + MAP_DEF_MAX_ENTRIES = 0x020, + MAP_DEF_MAP_FLAGS = 0x040, + MAP_DEF_NUMA_NODE = 0x080, + MAP_DEF_PINNING = 0x100, + MAP_DEF_INNER_MAP = 0x200, + MAP_DEF_MAP_EXTRA = 0x400, + + MAP_DEF_ALL = 0x7ff, /* combination of all above */ +}; + +struct btf_map_def { + enum map_def_parts parts; + __u32 map_type; + __u32 key_type_id; + __u32 key_size; + __u32 value_type_id; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; + __u32 numa_node; + __u32 pinning; + __u64 map_extra; +}; + +int parse_btf_map_def(const char *map_name, struct btf *btf, + const struct btf_type *def_t, bool strict, + struct btf_map_def *map_def, struct btf_map_def *inner_def); + +void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz, + size_t cur_cnt, size_t max_cnt, size_t add_cnt); +int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt); + +static inline bool libbpf_is_mem_zeroed(const char *p, ssize_t len) +{ + while (len > 0) { + if (*p) + return false; + p++; + len--; + } + return true; +} + +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 (!libbpf_is_mem_zeroed(opts + opts_sz, (ssize_t)user_sz - opts_sz)) { + 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) +#define OPTS_SET(opts, field, value) \ + do { \ + if (OPTS_HAS(opts, field)) \ + (opts)->field = value; \ + } while (0) + +#define OPTS_ZEROED(opts, last_nonzero_field) \ +({ \ + ssize_t __off = offsetofend(typeof(*(opts)), last_nonzero_field); \ + !(opts) || libbpf_is_mem_zeroed((const void *)opts + __off, \ + (opts)->sz - __off); \ +}) + +enum kern_feature_id { + /* v4.14: kernel support for program & map names. */ + FEAT_PROG_NAME, + /* v5.2: kernel support for global data sections. */ + FEAT_GLOBAL_DATA, + /* BTF support */ + FEAT_BTF, + /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ + FEAT_BTF_FUNC, + /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ + FEAT_BTF_DATASEC, + /* BTF_FUNC_GLOBAL is supported */ + FEAT_BTF_GLOBAL_FUNC, + /* BPF_F_MMAPABLE is supported for arrays */ + FEAT_ARRAY_MMAP, + /* kernel support for expected_attach_type in BPF_PROG_LOAD */ + FEAT_EXP_ATTACH_TYPE, + /* bpf_probe_read_{kernel,user}[_str] helpers */ + FEAT_PROBE_READ_KERN, + /* BPF_PROG_BIND_MAP is supported */ + FEAT_PROG_BIND_MAP, + /* Kernel support for module BTFs */ + FEAT_MODULE_BTF, + /* BTF_KIND_FLOAT support */ + FEAT_BTF_FLOAT, + /* BPF perf link support */ + FEAT_PERF_LINK, + /* BTF_KIND_DECL_TAG support */ + FEAT_BTF_DECL_TAG, + /* BTF_KIND_TYPE_TAG support */ + FEAT_BTF_TYPE_TAG, + /* memcg-based accounting for BPF maps and progs */ + FEAT_MEMCG_ACCOUNT, + /* BPF cookie (bpf_get_attach_cookie() BPF helper) support */ + FEAT_BPF_COOKIE, + /* BTF_KIND_ENUM64 support and BTF_KIND_ENUM kflag support */ + FEAT_BTF_ENUM64, + /* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */ + FEAT_SYSCALL_WRAPPER, + __FEAT_CNT, +}; + +int probe_memcg_account(void); +bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); +int bump_rlimit_memlock(void); + +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); +int libbpf__load_raw_btf(const char *raw_types, size_t types_len, + const char *str_sec, size_t str_len); +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level); + +struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); +void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, + const char **prefix, int *kind); + +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; + /* optional (maintained internally by libbpf) mapping between .BTF.ext + * section and corresponding ELF section. This is used to join + * information like CO-RE relocation records with corresponding BPF + * programs defined in ELF sections + */ + __u32 *sec_idxs; + int sec_cnt; +}; + +#define for_each_btf_ext_sec(seg, sec) \ + 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) + +/* + * The .BTF.ext ELF section layout defined as + * struct btf_ext_header + * func_info subsection + * + * The func_info subsection layout: + * record size for struct bpf_func_info in the func_info subsection + * struct btf_sec_func_info for section #1 + * a list of bpf_func_info records for section #1 + * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h + * but may not be identical + * struct btf_sec_func_info for section #2 + * a list of bpf_func_info records for section #2 + * ...... + * + * Note that the bpf_func_info record size in .BTF.ext may not + * be the same as the one defined in include/uapi/linux/bpf.h. + * The loader should ensure that record_size meets minimum + * requirement and pass the record as is to the kernel. The + * kernel will handle the func_info properly based on its contents. + */ +struct btf_ext_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 func_info_off; + __u32 func_info_len; + __u32 line_info_off; + __u32 line_info_len; + + /* optional part of .BTF.ext header */ + __u32 core_relo_off; + __u32 core_relo_len; +}; + +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 core_relo_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[]; +}; + +/* 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; +}; + + +typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx); +typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx); +int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx); +int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx); +int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx); +int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx); +__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, + __u32 kind); + +typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx); + +int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *arg); + +/* handle direct returned errors */ +static inline int libbpf_err(int ret) +{ + if (ret < 0) + errno = -ret; + return ret; +} + +/* handle errno-based (e.g., syscall or libc) errors according to libbpf's + * strict mode settings + */ +static inline int libbpf_err_errno(int ret) +{ + /* errno is already assumed to be set on error */ + return ret < 0 ? -errno : ret; +} + +/* handle error for pointer-returning APIs, err is assumed to be < 0 always */ +static inline void *libbpf_err_ptr(int err) +{ + /* set errno on error, this doesn't break anything */ + errno = -err; + return NULL; +} + +/* handle pointer-returning APIs' error handling */ +static inline void *libbpf_ptr(void *ret) +{ + /* set errno on error, this doesn't break anything */ + if (IS_ERR(ret)) + errno = -PTR_ERR(ret); + + return IS_ERR(ret) ? NULL : ret; +} + +static inline bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +static inline bool is_ldimm64_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + +/* if fd is stdin, stdout, or stderr, dup to a fd greater than 2 + * Takes ownership of the fd passed in, and closes it if calling + * fcntl(fd, F_DUPFD_CLOEXEC, 3). + */ +static inline int ensure_good_fd(int fd) +{ + int old_fd = fd, saved_errno; + + if (fd < 0) + return fd; + if (fd < 3) { + fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); + saved_errno = errno; + close(old_fd); + if (fd < 0) { + pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno); + errno = saved_errno; + } + } + return fd; +} + +/* The following two functions are exposed to bpftool */ +int bpf_core_add_cands(struct bpf_core_cand *local_cand, + size_t local_essent_len, + const struct btf *targ_btf, + const char *targ_btf_name, + int targ_start_id, + struct bpf_core_cand_list *cands); +void bpf_core_free_cands(struct bpf_core_cand_list *cands); + +struct usdt_manager *usdt_manager_new(struct bpf_object *obj); +void usdt_manager_free(struct usdt_manager *man); +struct bpf_link * usdt_manager_attach_usdt(struct usdt_manager *man, + const struct bpf_program *prog, + pid_t pid, const char *path, + const char *usdt_provider, const char *usdt_name, + __u64 usdt_cookie); + +static inline bool is_pow_of_2(size_t x) +{ + return x && (x & (x - 1)) == 0; +} + +#define PROG_LOAD_ATTEMPTS 5 +int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts); + +#endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h new file mode 100644 index 000000000..1e1be467b --- /dev/null +++ b/tools/lib/bpf/libbpf_legacy.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Libbpf legacy APIs (either discouraged or deprecated, as mentioned in [0]) + * + * [0] https://docs.google.com/document/d/1UyjTZuPFWiPFyKk1tV5an11_iaRuec6U-ZESZ54nNTY + * + * Copyright (C) 2021 Facebook + */ +#ifndef __LIBBPF_LEGACY_BPF_H +#define __LIBBPF_LEGACY_BPF_H + +#include <linux/bpf.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include "libbpf_common.h" + +#ifdef __cplusplus +extern "C" { +#endif + +/* As of libbpf 1.0 libbpf_set_strict_mode() and enum libbpf_struct_mode have + * no effect. But they are left in libbpf_legacy.h so that applications that + * prepared for libbpf 1.0 before final release by using + * libbpf_set_strict_mode() still work with libbpf 1.0+ without any changes. + */ +enum libbpf_strict_mode { + /* Turn on all supported strict features of libbpf to simulate libbpf + * v1.0 behavior. + * This will be the default behavior in libbpf v1.0. + */ + LIBBPF_STRICT_ALL = 0xffffffff, + + /* + * Disable any libbpf 1.0 behaviors. This is the default before libbpf + * v1.0. It won't be supported anymore in v1.0, please update your + * code so that it handles LIBBPF_STRICT_ALL mode before libbpf v1.0. + */ + LIBBPF_STRICT_NONE = 0x00, + /* + * Return NULL pointers on error, not ERR_PTR(err). + * Additionally, libbpf also always sets errno to corresponding Exx + * (positive) error code. + */ + LIBBPF_STRICT_CLEAN_PTRS = 0x01, + /* + * Return actual error codes from low-level APIs directly, not just -1. + * Additionally, libbpf also always sets errno to corresponding Exx + * (positive) error code. + */ + LIBBPF_STRICT_DIRECT_ERRS = 0x02, + /* + * Enforce strict BPF program section (SEC()) names. + * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were + * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become + * unrecognized by libbpf and would have to be just SEC("xdp") and + * SEC("xdp") and SEC("perf_event"). + * + * Note, in this mode the program pin path will be based on the + * function name instead of section name. + * + * Additionally, routines in the .text section are always considered + * sub-programs. Legacy behavior allows for a single routine in .text + * to be a program. + */ + LIBBPF_STRICT_SEC_NAME = 0x04, + /* + * Disable the global 'bpf_objects_list'. Maintaining this list adds + * a race condition to bpf_object__open() and bpf_object__close(). + * Clients can maintain it on their own if it is valuable for them. + */ + LIBBPF_STRICT_NO_OBJECT_LIST = 0x08, + /* + * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the + * first BPF program or map creation operation. This is done only if + * kernel is too old to support memcg-based memory accounting for BPF + * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY, + * but it can be overriden with libbpf_set_memlock_rlim() API. + * Note that libbpf_set_memlock_rlim() needs to be called before + * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load() + * operation. + */ + LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10, + /* + * Error out on any SEC("maps") map definition, which are deprecated + * in favor of BTF-defined map definitions in SEC(".maps"). + */ + LIBBPF_STRICT_MAP_DEFINITIONS = 0x20, + + __LIBBPF_STRICT_LAST, +}; + +LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); + +/** + * @brief **libbpf_get_error()** extracts the error code from the passed + * pointer + * @param ptr pointer returned from libbpf API function + * @return error code; or 0 if no error occured + * + * Note, as of libbpf 1.0 this function is not necessary and not recommended + * to be used. Libbpf doesn't return error code embedded into the pointer + * itself. Instead, NULL is returned on error and error code is passed through + * thread-local errno variable. **libbpf_get_error()** is just returning -errno + * value if it receives NULL, which is correct only if errno hasn't been + * modified between libbpf API call and corresponding **libbpf_get_error()** + * call. Prefer to check return for NULL and use errno directly. + * + * This API is left in libbpf 1.0 to allow applications that were 1.0-ready + * before final libbpf 1.0 without needing to change them. + */ +LIBBPF_API long libbpf_get_error(const void *ptr); + +#define DECLARE_LIBBPF_OPTS LIBBPF_OPTS + +/* "Discouraged" APIs which don't follow consistent libbpf naming patterns. + * They are normally a trivial aliases or wrappers for proper APIs and are + * left to minimize unnecessary disruption for users of libbpf. But they + * shouldn't be used going forward. + */ + +struct bpf_program; +struct bpf_map; +struct btf; +struct btf_ext; + +LIBBPF_API struct btf *libbpf_find_kernel_btf(void); + +LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); +LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); +LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); +LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); +LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_LEGACY_BPF_H */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c new file mode 100644 index 000000000..d504d96ad --- /dev/null +++ b/tools/lib/bpf/libbpf_probes.c @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2019 Netronome Systems, Inc. */ + +#include <errno.h> +#include <fcntl.h> +#include <string.h> +#include <stdlib.h> +#include <unistd.h> +#include <net/if.h> +#include <sys/utsname.h> + +#include <linux/btf.h> +#include <linux/filter.h> +#include <linux/kernel.h> + +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +static int probe_prog_load(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + ); + int fd, err, exp_err = 0; + const char *exp_msg = NULL; + char buf[4096]; + + switch (prog_type) { + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + opts.expected_attach_type = BPF_CGROUP_INET4_CONNECT; + break; + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + opts.expected_attach_type = BPF_CGROUP_GETSOCKOPT; + break; + case BPF_PROG_TYPE_SK_LOOKUP: + opts.expected_attach_type = BPF_SK_LOOKUP; + break; + case BPF_PROG_TYPE_KPROBE: + opts.kern_version = get_kernel_version(); + break; + case BPF_PROG_TYPE_LIRC_MODE2: + opts.expected_attach_type = BPF_LIRC_MODE2; + break; + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + opts.log_buf = buf; + opts.log_size = sizeof(buf); + opts.log_level = 1; + if (prog_type == BPF_PROG_TYPE_TRACING) + opts.expected_attach_type = BPF_TRACE_FENTRY; + else + opts.expected_attach_type = BPF_MODIFY_RETURN; + opts.attach_btf_id = 1; + + exp_err = -EINVAL; + exp_msg = "attach_btf_id 1 is not a function"; + break; + case BPF_PROG_TYPE_EXT: + opts.log_buf = buf; + opts.log_size = sizeof(buf); + opts.log_level = 1; + opts.attach_btf_id = 1; + + exp_err = -EINVAL; + exp_msg = "Cannot replace kernel functions"; + break; + case BPF_PROG_TYPE_SYSCALL: + opts.prog_flags = BPF_F_SLEEPABLE; + break; + case BPF_PROG_TYPE_STRUCT_OPS: + exp_err = -524; /* -ENOTSUPP */ + break; + case BPF_PROG_TYPE_UNSPEC: + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_PERF_EVENT: + 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_SOCK_OPS: + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: + case BPF_PROG_TYPE_SK_REUSEPORT: + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + break; + default: + return -EOPNOTSUPP; + } + + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + err = -errno; + if (fd >= 0) + close(fd); + if (exp_err) { + if (fd >= 0 || err != exp_err) + return 0; + if (exp_msg && !strstr(buf, exp_msg)) + return 0; + return 1; + } + return fd >= 0 ? 1 : 0; +} + +int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN() + }; + const size_t insn_cnt = ARRAY_SIZE(insns); + int ret; + + if (opts) + return libbpf_err(-EINVAL); + + ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0); + return libbpf_err(ret); +} + +int libbpf__load_raw_btf(const char *raw_types, size_t types_len, + const char *str_sec, size_t str_len) +{ + struct btf_header hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = types_len, + .str_off = types_len, + .str_len = str_len, + }; + int btf_fd, btf_len; + __u8 *raw_btf; + + btf_len = hdr.hdr_len + hdr.type_len + hdr.str_len; + raw_btf = malloc(btf_len); + if (!raw_btf) + return -ENOMEM; + + memcpy(raw_btf, &hdr, sizeof(hdr)); + memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); + memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); + + btf_fd = bpf_btf_load(raw_btf, btf_len, NULL); + + free(raw_btf); + return btf_fd; +} + +static int load_local_storage_btf(void) +{ + const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l"; + /* struct bpf_spin_lock { + * int val; + * }; + * struct val { + * int cnt; + * struct bpf_spin_lock l; + * }; + */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + }; + + return libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); +} + +static int probe_map_create(enum bpf_map_type map_type) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; + __u32 btf_key_type_id = 0, btf_value_type_id = 0; + int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err = 0; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + + switch (map_type) { + case BPF_MAP_TYPE_STACK_TRACE: + value_size = sizeof(__u64); + break; + case BPF_MAP_TYPE_LPM_TRIE: + key_size = sizeof(__u64); + value_size = sizeof(__u64); + opts.map_flags = BPF_F_NO_PREALLOC; + break; + case BPF_MAP_TYPE_CGROUP_STORAGE: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: + key_size = sizeof(struct bpf_cgroup_storage_key); + value_size = sizeof(__u64); + max_entries = 0; + break; + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + key_size = 0; + break; + case BPF_MAP_TYPE_SK_STORAGE: + case BPF_MAP_TYPE_INODE_STORAGE: + case BPF_MAP_TYPE_TASK_STORAGE: + btf_key_type_id = 1; + btf_value_type_id = 3; + value_size = 8; + max_entries = 0; + opts.map_flags = BPF_F_NO_PREALLOC; + btf_fd = load_local_storage_btf(); + if (btf_fd < 0) + return btf_fd; + break; + case BPF_MAP_TYPE_RINGBUF: + case BPF_MAP_TYPE_USER_RINGBUF: + key_size = 0; + value_size = 0; + max_entries = sysconf(_SC_PAGE_SIZE); + break; + case BPF_MAP_TYPE_STRUCT_OPS: + /* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */ + opts.btf_vmlinux_value_type_id = 1; + exp_err = -524; /* -ENOTSUPP */ + break; + case BPF_MAP_TYPE_BLOOM_FILTER: + key_size = 0; + max_entries = 1; + break; + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + case BPF_MAP_TYPE_PROG_ARRAY: + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_PERCPU_HASH: + case BPF_MAP_TYPE_PERCPU_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_LRU_HASH: + case BPF_MAP_TYPE_LRU_PERCPU_HASH: + 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: + break; + case BPF_MAP_TYPE_UNSPEC: + default: + return -EOPNOTSUPP; + } + + if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS || + map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, + sizeof(__u32), sizeof(__u32), 1, NULL); + if (fd_inner < 0) + goto cleanup; + + opts.inner_map_fd = fd_inner; + } + + if (btf_fd >= 0) { + opts.btf_fd = btf_fd; + opts.btf_key_type_id = btf_key_type_id; + opts.btf_value_type_id = btf_value_type_id; + } + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts); + err = -errno; + +cleanup: + if (fd >= 0) + close(fd); + if (fd_inner >= 0) + close(fd_inner); + if (btf_fd >= 0) + close(btf_fd); + + if (exp_err) + return fd < 0 && err == exp_err ? 1 : 0; + else + return fd >= 0 ? 1 : 0; +} + +int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts) +{ + int ret; + + if (opts) + return libbpf_err(-EINVAL); + + ret = probe_map_create(map_type); + return libbpf_err(ret); +} + +int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id, + const void *opts) +{ + struct bpf_insn insns[] = { + BPF_EMIT_CALL((__u32)helper_id), + BPF_EXIT_INSN(), + }; + const size_t insn_cnt = ARRAY_SIZE(insns); + char buf[4096]; + int ret; + + if (opts) + return libbpf_err(-EINVAL); + + /* we can't successfully load all prog types to check for BPF helper + * support, so bail out with -EOPNOTSUPP error + */ + switch (prog_type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: + return -EOPNOTSUPP; + default: + break; + } + + buf[0] = '\0'; + ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf)); + if (ret < 0) + return libbpf_err(ret); + + /* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id) + * at all, it will emit something like "invalid func unknown#181". + * If BPF verifier recognizes BPF helper but it's not supported for + * given BPF program type, it will emit "unknown func bpf_sys_bpf#166". + * In both cases, provided combination of BPF program type and BPF + * helper is not supported by the kernel. + * In all other cases, probe_prog_load() above will either succeed (e.g., + * because BPF helper happens to accept no input arguments or it + * accepts one input argument and initial PTR_TO_CTX is fine for + * that), or we'll get some more specific BPF verifier error about + * some unsatisfied conditions. + */ + if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func "))) + return 0; + return 1; /* assume supported */ +} diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h new file mode 100644 index 000000000..e944f5bce --- /dev/null +++ b/tools/lib/bpf/libbpf_version.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (C) 2021 Facebook */ +#ifndef __LIBBPF_VERSION_H +#define __LIBBPF_VERSION_H + +#define LIBBPF_MAJOR_VERSION 1 +#define LIBBPF_MINOR_VERSION 1 + +#endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c new file mode 100644 index 000000000..4ac02c28e --- /dev/null +++ b/tools/lib/bpf/linker.c @@ -0,0 +1,2900 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* + * BPF static linker + * + * Copyright (c) 2021 Facebook + */ +#include <stdbool.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <linux/err.h> +#include <linux/btf.h> +#include <elf.h> +#include <libelf.h> +#include <fcntl.h> +#include "libbpf.h" +#include "btf.h" +#include "libbpf_internal.h" +#include "strset.h" + +#define BTF_EXTERN_SEC ".extern" + +struct src_sec { + const char *sec_name; + /* positional (not necessarily ELF) index in an array of sections */ + int id; + /* positional (not necessarily ELF) index of a matching section in a final object file */ + int dst_id; + /* section data offset in a matching output section */ + int dst_off; + /* whether section is omitted from the final ELF file */ + bool skipped; + /* whether section is an ephemeral section, not mapped to an ELF section */ + bool ephemeral; + + /* ELF info */ + size_t sec_idx; + Elf_Scn *scn; + Elf64_Shdr *shdr; + Elf_Data *data; + + /* corresponding BTF DATASEC type ID */ + int sec_type_id; +}; + +struct src_obj { + const char *filename; + int fd; + Elf *elf; + /* Section header strings section index */ + size_t shstrs_sec_idx; + /* SYMTAB section index */ + size_t symtab_sec_idx; + + struct btf *btf; + struct btf_ext *btf_ext; + + /* List of sections (including ephemeral). Slot zero is unused. */ + struct src_sec *secs; + int sec_cnt; + + /* mapping of symbol indices from src to dst ELF */ + int *sym_map; + /* mapping from the src BTF type IDs to dst ones */ + int *btf_type_map; +}; + +/* single .BTF.ext data section */ +struct btf_ext_sec_data { + size_t rec_cnt; + __u32 rec_sz; + void *recs; +}; + +struct glob_sym { + /* ELF symbol index */ + int sym_idx; + /* associated section id for .ksyms, .kconfig, etc, but not .extern */ + int sec_id; + /* extern name offset in STRTAB */ + int name_off; + /* optional associated BTF type ID */ + int btf_id; + /* BTF type ID to which VAR/FUNC type is pointing to; used for + * rewriting types when extern VAR/FUNC is resolved to a concrete + * definition + */ + int underlying_btf_id; + /* sec_var index in the corresponding dst_sec, if exists */ + int var_idx; + + /* extern or resolved/global symbol */ + bool is_extern; + /* weak or strong symbol, never goes back from strong to weak */ + bool is_weak; +}; + +struct dst_sec { + char *sec_name; + /* positional (not necessarily ELF) index in an array of sections */ + int id; + + bool ephemeral; + + /* ELF info */ + size_t sec_idx; + Elf_Scn *scn; + Elf64_Shdr *shdr; + Elf_Data *data; + + /* final output section size */ + int sec_sz; + /* final output contents of the section */ + void *raw_data; + + /* corresponding STT_SECTION symbol index in SYMTAB */ + int sec_sym_idx; + + /* section's DATASEC variable info, emitted on BTF finalization */ + bool has_btf; + int sec_var_cnt; + struct btf_var_secinfo *sec_vars; + + /* section's .BTF.ext data */ + struct btf_ext_sec_data func_info; + struct btf_ext_sec_data line_info; + struct btf_ext_sec_data core_relo_info; +}; + +struct bpf_linker { + char *filename; + int fd; + Elf *elf; + Elf64_Ehdr *elf_hdr; + + /* Output sections metadata */ + struct dst_sec *secs; + int sec_cnt; + + struct strset *strtab_strs; /* STRTAB unique strings */ + size_t strtab_sec_idx; /* STRTAB section index */ + size_t symtab_sec_idx; /* SYMTAB section index */ + + struct btf *btf; + struct btf_ext *btf_ext; + + /* global (including extern) ELF symbols */ + int glob_sym_cnt; + struct glob_sym *glob_syms; +}; + +#define pr_warn_elf(fmt, ...) \ + libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1)) + +static int init_output_elf(struct bpf_linker *linker, const char *file); + +static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts, + struct src_obj *obj); +static int linker_sanity_check_elf(struct src_obj *obj); +static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec); +static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec); +static int linker_sanity_check_btf(struct src_obj *obj); +static int linker_sanity_check_btf_ext(struct src_obj *obj); +static int linker_fixup_btf(struct src_obj *obj); +static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj); +static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj); +static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, + Elf64_Sym *sym, const char *sym_name, int src_sym_idx); +static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj); +static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj); +static int linker_append_btf_ext(struct bpf_linker *linker, struct src_obj *obj); + +static int finalize_btf(struct bpf_linker *linker); +static int finalize_btf_ext(struct bpf_linker *linker); + +void bpf_linker__free(struct bpf_linker *linker) +{ + int i; + + if (!linker) + return; + + free(linker->filename); + + if (linker->elf) + elf_end(linker->elf); + + if (linker->fd >= 0) + close(linker->fd); + + strset__free(linker->strtab_strs); + + btf__free(linker->btf); + btf_ext__free(linker->btf_ext); + + for (i = 1; i < linker->sec_cnt; i++) { + struct dst_sec *sec = &linker->secs[i]; + + free(sec->sec_name); + free(sec->raw_data); + free(sec->sec_vars); + + free(sec->func_info.recs); + free(sec->line_info.recs); + free(sec->core_relo_info.recs); + } + free(linker->secs); + + free(linker->glob_syms); + free(linker); +} + +struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts) +{ + struct bpf_linker *linker; + int err; + + if (!OPTS_VALID(opts, bpf_linker_opts)) + return errno = EINVAL, NULL; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn_elf("libelf initialization failed"); + return errno = EINVAL, NULL; + } + + linker = calloc(1, sizeof(*linker)); + if (!linker) + return errno = ENOMEM, NULL; + + linker->fd = -1; + + err = init_output_elf(linker, filename); + if (err) + goto err_out; + + return linker; + +err_out: + bpf_linker__free(linker); + return errno = -err, NULL; +} + +static struct dst_sec *add_dst_sec(struct bpf_linker *linker, const char *sec_name) +{ + struct dst_sec *secs = linker->secs, *sec; + size_t new_cnt = linker->sec_cnt ? linker->sec_cnt + 1 : 2; + + secs = libbpf_reallocarray(secs, new_cnt, sizeof(*secs)); + if (!secs) + return NULL; + + /* zero out newly allocated memory */ + memset(secs + linker->sec_cnt, 0, (new_cnt - linker->sec_cnt) * sizeof(*secs)); + + linker->secs = secs; + linker->sec_cnt = new_cnt; + + sec = &linker->secs[new_cnt - 1]; + sec->id = new_cnt - 1; + sec->sec_name = strdup(sec_name); + if (!sec->sec_name) + return NULL; + + return sec; +} + +static Elf64_Sym *add_new_sym(struct bpf_linker *linker, size_t *sym_idx) +{ + struct dst_sec *symtab = &linker->secs[linker->symtab_sec_idx]; + Elf64_Sym *syms, *sym; + size_t sym_cnt = symtab->sec_sz / sizeof(*sym); + + syms = libbpf_reallocarray(symtab->raw_data, sym_cnt + 1, sizeof(*sym)); + if (!syms) + return NULL; + + sym = &syms[sym_cnt]; + memset(sym, 0, sizeof(*sym)); + + symtab->raw_data = syms; + symtab->sec_sz += sizeof(*sym); + symtab->shdr->sh_size += sizeof(*sym); + symtab->data->d_size += sizeof(*sym); + + if (sym_idx) + *sym_idx = sym_cnt; + + return sym; +} + +static int init_output_elf(struct bpf_linker *linker, const char *file) +{ + int err, str_off; + Elf64_Sym *init_sym; + struct dst_sec *sec; + + linker->filename = strdup(file); + if (!linker->filename) + return -ENOMEM; + + linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644); + if (linker->fd < 0) { + err = -errno; + pr_warn("failed to create '%s': %d\n", file, err); + return err; + } + + linker->elf = elf_begin(linker->fd, ELF_C_WRITE, NULL); + if (!linker->elf) { + pr_warn_elf("failed to create ELF object"); + return -EINVAL; + } + + /* ELF header */ + linker->elf_hdr = elf64_newehdr(linker->elf); + if (!linker->elf_hdr) { + pr_warn_elf("failed to create ELF header"); + return -EINVAL; + } + + linker->elf_hdr->e_machine = EM_BPF; + linker->elf_hdr->e_type = ET_REL; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB; +#else +#error "Unknown __BYTE_ORDER__" +#endif + + /* STRTAB */ + /* initialize strset with an empty string to conform to ELF */ + linker->strtab_strs = strset__new(INT_MAX, "", sizeof("")); + if (libbpf_get_error(linker->strtab_strs)) + return libbpf_get_error(linker->strtab_strs); + + sec = add_dst_sec(linker, ".strtab"); + if (!sec) + return -ENOMEM; + + sec->scn = elf_newscn(linker->elf); + if (!sec->scn) { + pr_warn_elf("failed to create STRTAB section"); + return -EINVAL; + } + + sec->shdr = elf64_getshdr(sec->scn); + if (!sec->shdr) + return -EINVAL; + + sec->data = elf_newdata(sec->scn); + if (!sec->data) { + pr_warn_elf("failed to create STRTAB data"); + return -EINVAL; + } + + str_off = strset__add_str(linker->strtab_strs, sec->sec_name); + if (str_off < 0) + return str_off; + + sec->sec_idx = elf_ndxscn(sec->scn); + linker->elf_hdr->e_shstrndx = sec->sec_idx; + linker->strtab_sec_idx = sec->sec_idx; + + sec->shdr->sh_name = str_off; + sec->shdr->sh_type = SHT_STRTAB; + sec->shdr->sh_flags = SHF_STRINGS; + sec->shdr->sh_offset = 0; + sec->shdr->sh_link = 0; + sec->shdr->sh_info = 0; + sec->shdr->sh_addralign = 1; + sec->shdr->sh_size = sec->sec_sz = 0; + sec->shdr->sh_entsize = 0; + + /* SYMTAB */ + sec = add_dst_sec(linker, ".symtab"); + if (!sec) + return -ENOMEM; + + sec->scn = elf_newscn(linker->elf); + if (!sec->scn) { + pr_warn_elf("failed to create SYMTAB section"); + return -EINVAL; + } + + sec->shdr = elf64_getshdr(sec->scn); + if (!sec->shdr) + return -EINVAL; + + sec->data = elf_newdata(sec->scn); + if (!sec->data) { + pr_warn_elf("failed to create SYMTAB data"); + return -EINVAL; + } + + str_off = strset__add_str(linker->strtab_strs, sec->sec_name); + if (str_off < 0) + return str_off; + + sec->sec_idx = elf_ndxscn(sec->scn); + linker->symtab_sec_idx = sec->sec_idx; + + sec->shdr->sh_name = str_off; + sec->shdr->sh_type = SHT_SYMTAB; + sec->shdr->sh_flags = 0; + sec->shdr->sh_offset = 0; + sec->shdr->sh_link = linker->strtab_sec_idx; + /* sh_info should be one greater than the index of the last local + * symbol (i.e., binding is STB_LOCAL). But why and who cares? + */ + sec->shdr->sh_info = 0; + sec->shdr->sh_addralign = 8; + sec->shdr->sh_entsize = sizeof(Elf64_Sym); + + /* .BTF */ + linker->btf = btf__new_empty(); + err = libbpf_get_error(linker->btf); + if (err) + return err; + + /* add the special all-zero symbol */ + init_sym = add_new_sym(linker, NULL); + if (!init_sym) + return -EINVAL; + + init_sym->st_name = 0; + init_sym->st_info = 0; + init_sym->st_other = 0; + init_sym->st_shndx = SHN_UNDEF; + init_sym->st_value = 0; + init_sym->st_size = 0; + + return 0; +} + +int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts) +{ + struct src_obj obj = {}; + int err = 0; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + err = err ?: linker_load_obj_file(linker, filename, opts, &obj); + err = err ?: linker_append_sec_data(linker, &obj); + err = err ?: linker_append_elf_syms(linker, &obj); + err = err ?: linker_append_elf_relos(linker, &obj); + err = err ?: linker_append_btf(linker, &obj); + err = err ?: linker_append_btf_ext(linker, &obj); + + /* free up src_obj resources */ + free(obj.btf_type_map); + btf__free(obj.btf); + btf_ext__free(obj.btf_ext); + free(obj.secs); + free(obj.sym_map); + if (obj.elf) + elf_end(obj.elf); + if (obj.fd >= 0) + close(obj.fd); + + return libbpf_err(err); +} + +static bool is_dwarf_sec_name(const char *name) +{ + /* approximation, but the actual list is too long */ + return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0; +} + +static bool is_ignored_sec(struct src_sec *sec) +{ + Elf64_Shdr *shdr = sec->shdr; + const char *name = sec->sec_name; + + /* no special handling of .strtab */ + if (shdr->sh_type == SHT_STRTAB) + return true; + + /* ignore .llvm_addrsig section as well */ + if (shdr->sh_type == SHT_LLVM_ADDRSIG) + return true; + + /* no subprograms will lead to an empty .text section, ignore it */ + if (shdr->sh_type == SHT_PROGBITS && shdr->sh_size == 0 && + strcmp(sec->sec_name, ".text") == 0) + return true; + + /* DWARF sections */ + if (is_dwarf_sec_name(sec->sec_name)) + return true; + + if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) { + name += sizeof(".rel") - 1; + /* DWARF section relocations */ + if (is_dwarf_sec_name(name)) + return true; + + /* .BTF and .BTF.ext don't need relocations */ + if (strcmp(name, BTF_ELF_SEC) == 0 || + strcmp(name, BTF_EXT_ELF_SEC) == 0) + return true; + } + + return false; +} + +static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name) +{ + struct src_sec *secs = obj->secs, *sec; + size_t new_cnt = obj->sec_cnt ? obj->sec_cnt + 1 : 2; + + secs = libbpf_reallocarray(secs, new_cnt, sizeof(*secs)); + if (!secs) + return NULL; + + /* zero out newly allocated memory */ + memset(secs + obj->sec_cnt, 0, (new_cnt - obj->sec_cnt) * sizeof(*secs)); + + obj->secs = secs; + obj->sec_cnt = new_cnt; + + sec = &obj->secs[new_cnt - 1]; + sec->id = new_cnt - 1; + sec->sec_name = sec_name; + + return sec; +} + +static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts, + struct src_obj *obj) +{ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + const int host_endianness = ELFDATA2LSB; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + const int host_endianness = ELFDATA2MSB; +#else +#error "Unknown __BYTE_ORDER__" +#endif + int err = 0; + Elf_Scn *scn; + Elf_Data *data; + Elf64_Ehdr *ehdr; + Elf64_Shdr *shdr; + struct src_sec *sec; + + pr_debug("linker: adding object file '%s'...\n", filename); + + obj->filename = filename; + + obj->fd = open(filename, O_RDONLY | O_CLOEXEC); + if (obj->fd < 0) { + err = -errno; + pr_warn("failed to open file '%s': %d\n", filename, err); + return err; + } + obj->elf = elf_begin(obj->fd, ELF_C_READ_MMAP, NULL); + if (!obj->elf) { + err = -errno; + pr_warn_elf("failed to parse ELF file '%s'", filename); + return err; + } + + /* Sanity check ELF file high-level properties */ + ehdr = elf64_getehdr(obj->elf); + if (!ehdr) { + err = -errno; + pr_warn_elf("failed to get ELF header for %s", filename); + return err; + } + if (ehdr->e_ident[EI_DATA] != host_endianness) { + err = -EOPNOTSUPP; + pr_warn_elf("unsupported byte order of ELF file %s", filename); + return err; + } + if (ehdr->e_type != ET_REL + || ehdr->e_machine != EM_BPF + || ehdr->e_ident[EI_CLASS] != ELFCLASS64) { + err = -EOPNOTSUPP; + pr_warn_elf("unsupported kind of ELF file %s", filename); + return err; + } + + if (elf_getshdrstrndx(obj->elf, &obj->shstrs_sec_idx)) { + err = -errno; + pr_warn_elf("failed to get SHSTRTAB section index for %s", filename); + return err; + } + + scn = NULL; + while ((scn = elf_nextscn(obj->elf, scn)) != NULL) { + size_t sec_idx = elf_ndxscn(scn); + const char *sec_name; + + shdr = elf64_getshdr(scn); + if (!shdr) { + err = -errno; + pr_warn_elf("failed to get section #%zu header for %s", + sec_idx, filename); + return err; + } + + sec_name = elf_strptr(obj->elf, obj->shstrs_sec_idx, shdr->sh_name); + if (!sec_name) { + err = -errno; + pr_warn_elf("failed to get section #%zu name for %s", + sec_idx, filename); + return err; + } + + data = elf_getdata(scn, 0); + if (!data) { + err = -errno; + pr_warn_elf("failed to get section #%zu (%s) data from %s", + sec_idx, sec_name, filename); + return err; + } + + sec = add_src_sec(obj, sec_name); + if (!sec) + return -ENOMEM; + + sec->scn = scn; + sec->shdr = shdr; + sec->data = data; + sec->sec_idx = elf_ndxscn(scn); + + if (is_ignored_sec(sec)) { + sec->skipped = true; + continue; + } + + switch (shdr->sh_type) { + case SHT_SYMTAB: + if (obj->symtab_sec_idx) { + err = -EOPNOTSUPP; + pr_warn("multiple SYMTAB sections found, not supported\n"); + return err; + } + obj->symtab_sec_idx = sec_idx; + break; + case SHT_STRTAB: + /* we'll construct our own string table */ + break; + case SHT_PROGBITS: + if (strcmp(sec_name, BTF_ELF_SEC) == 0) { + obj->btf = btf__new(data->d_buf, shdr->sh_size); + err = libbpf_get_error(obj->btf); + if (err) { + pr_warn("failed to parse .BTF from %s: %d\n", filename, err); + return err; + } + sec->skipped = true; + continue; + } + if (strcmp(sec_name, BTF_EXT_ELF_SEC) == 0) { + obj->btf_ext = btf_ext__new(data->d_buf, shdr->sh_size); + err = libbpf_get_error(obj->btf_ext); + if (err) { + pr_warn("failed to parse .BTF.ext from '%s': %d\n", filename, err); + return err; + } + sec->skipped = true; + continue; + } + + /* data & code */ + break; + case SHT_NOBITS: + /* BSS */ + break; + case SHT_REL: + /* relocations */ + break; + default: + pr_warn("unrecognized section #%zu (%s) in %s\n", + sec_idx, sec_name, filename); + err = -EINVAL; + return err; + } + } + + err = err ?: linker_sanity_check_elf(obj); + err = err ?: linker_sanity_check_btf(obj); + err = err ?: linker_sanity_check_btf_ext(obj); + err = err ?: linker_fixup_btf(obj); + + return err; +} + +static int linker_sanity_check_elf(struct src_obj *obj) +{ + struct src_sec *sec; + int i, err; + + if (!obj->symtab_sec_idx) { + pr_warn("ELF is missing SYMTAB section in %s\n", obj->filename); + return -EINVAL; + } + if (!obj->shstrs_sec_idx) { + pr_warn("ELF is missing section headers STRTAB section in %s\n", obj->filename); + return -EINVAL; + } + + for (i = 1; i < obj->sec_cnt; i++) { + sec = &obj->secs[i]; + + if (sec->sec_name[0] == '\0') { + pr_warn("ELF section #%zu has empty name in %s\n", sec->sec_idx, obj->filename); + return -EINVAL; + } + + if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) + return -EINVAL; + if (sec->shdr->sh_addralign != sec->data->d_align) + return -EINVAL; + + if (sec->shdr->sh_size != sec->data->d_size) + return -EINVAL; + + switch (sec->shdr->sh_type) { + case SHT_SYMTAB: + err = linker_sanity_check_elf_symtab(obj, sec); + if (err) + return err; + break; + case SHT_STRTAB: + break; + case SHT_PROGBITS: + if (sec->shdr->sh_flags & SHF_EXECINSTR) { + if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) + return -EINVAL; + } + break; + case SHT_NOBITS: + break; + case SHT_REL: + err = linker_sanity_check_elf_relos(obj, sec); + if (err) + return err; + break; + case SHT_LLVM_ADDRSIG: + break; + default: + pr_warn("ELF section #%zu (%s) has unrecognized type %zu in %s\n", + sec->sec_idx, sec->sec_name, (size_t)sec->shdr->sh_type, obj->filename); + return -EINVAL; + } + } + + return 0; +} + +static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec) +{ + struct src_sec *link_sec; + Elf64_Sym *sym; + int i, n; + + if (sec->shdr->sh_entsize != sizeof(Elf64_Sym)) + return -EINVAL; + if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0) + return -EINVAL; + + if (!sec->shdr->sh_link || sec->shdr->sh_link >= obj->sec_cnt) { + pr_warn("ELF SYMTAB section #%zu points to missing STRTAB section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); + return -EINVAL; + } + link_sec = &obj->secs[sec->shdr->sh_link]; + if (link_sec->shdr->sh_type != SHT_STRTAB) { + pr_warn("ELF SYMTAB section #%zu points to invalid STRTAB section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); + return -EINVAL; + } + + n = sec->shdr->sh_size / sec->shdr->sh_entsize; + sym = sec->data->d_buf; + for (i = 0; i < n; i++, sym++) { + int sym_type = ELF64_ST_TYPE(sym->st_info); + int sym_bind = ELF64_ST_BIND(sym->st_info); + int sym_vis = ELF64_ST_VISIBILITY(sym->st_other); + + if (i == 0) { + if (sym->st_name != 0 || sym->st_info != 0 + || sym->st_other != 0 || sym->st_shndx != 0 + || sym->st_value != 0 || sym->st_size != 0) { + pr_warn("ELF sym #0 is invalid in %s\n", obj->filename); + return -EINVAL; + } + continue; + } + if (sym_bind != STB_LOCAL && sym_bind != STB_GLOBAL && sym_bind != STB_WEAK) { + pr_warn("ELF sym #%d in section #%zu has unsupported symbol binding %d\n", + i, sec->sec_idx, sym_bind); + return -EINVAL; + } + if (sym_vis != STV_DEFAULT && sym_vis != STV_HIDDEN) { + pr_warn("ELF sym #%d in section #%zu has unsupported symbol visibility %d\n", + i, sec->sec_idx, sym_vis); + return -EINVAL; + } + if (sym->st_shndx == 0) { + if (sym_type != STT_NOTYPE || sym_bind == STB_LOCAL + || sym->st_value != 0 || sym->st_size != 0) { + pr_warn("ELF sym #%d is invalid extern symbol in %s\n", + i, obj->filename); + + return -EINVAL; + } + continue; + } + if (sym->st_shndx < SHN_LORESERVE && sym->st_shndx >= obj->sec_cnt) { + pr_warn("ELF sym #%d in section #%zu points to missing section #%zu in %s\n", + i, sec->sec_idx, (size_t)sym->st_shndx, obj->filename); + return -EINVAL; + } + if (sym_type == STT_SECTION) { + if (sym->st_value != 0) + return -EINVAL; + continue; + } + } + + return 0; +} + +static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec) +{ + struct src_sec *link_sec, *sym_sec; + Elf64_Rel *relo; + int i, n; + + if (sec->shdr->sh_entsize != sizeof(Elf64_Rel)) + return -EINVAL; + if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0) + return -EINVAL; + + /* SHT_REL's sh_link should point to SYMTAB */ + if (sec->shdr->sh_link != obj->symtab_sec_idx) { + pr_warn("ELF relo section #%zu points to invalid SYMTAB section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); + return -EINVAL; + } + + /* SHT_REL's sh_info points to relocated section */ + if (!sec->shdr->sh_info || sec->shdr->sh_info >= obj->sec_cnt) { + pr_warn("ELF relo section #%zu points to missing section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename); + return -EINVAL; + } + link_sec = &obj->secs[sec->shdr->sh_info]; + + /* .rel<secname> -> <secname> pattern is followed */ + if (strncmp(sec->sec_name, ".rel", sizeof(".rel") - 1) != 0 + || strcmp(sec->sec_name + sizeof(".rel") - 1, link_sec->sec_name) != 0) { + pr_warn("ELF relo section #%zu name has invalid name in %s\n", + sec->sec_idx, obj->filename); + return -EINVAL; + } + + /* don't further validate relocations for ignored sections */ + if (link_sec->skipped) + return 0; + + /* relocatable section is data or instructions */ + if (link_sec->shdr->sh_type != SHT_PROGBITS && link_sec->shdr->sh_type != SHT_NOBITS) { + pr_warn("ELF relo section #%zu points to invalid section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename); + return -EINVAL; + } + + /* check sanity of each relocation */ + n = sec->shdr->sh_size / sec->shdr->sh_entsize; + relo = sec->data->d_buf; + sym_sec = &obj->secs[obj->symtab_sec_idx]; + for (i = 0; i < n; i++, relo++) { + size_t sym_idx = ELF64_R_SYM(relo->r_info); + size_t sym_type = ELF64_R_TYPE(relo->r_info); + + if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32 && + sym_type != R_BPF_64_ABS64 && sym_type != R_BPF_64_ABS32) { + pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n", + i, sec->sec_idx, sym_type, obj->filename); + return -EINVAL; + } + + if (!sym_idx || sym_idx * sizeof(Elf64_Sym) >= sym_sec->shdr->sh_size) { + pr_warn("ELF relo #%d in section #%zu points to invalid symbol #%zu in %s\n", + i, sec->sec_idx, sym_idx, obj->filename); + return -EINVAL; + } + + if (link_sec->shdr->sh_flags & SHF_EXECINSTR) { + if (relo->r_offset % sizeof(struct bpf_insn) != 0) { + pr_warn("ELF relo #%d in section #%zu points to missing symbol #%zu in %s\n", + i, sec->sec_idx, sym_idx, obj->filename); + return -EINVAL; + } + } + } + + return 0; +} + +static int check_btf_type_id(__u32 *type_id, void *ctx) +{ + struct btf *btf = ctx; + + if (*type_id >= btf__type_cnt(btf)) + return -EINVAL; + + return 0; +} + +static int check_btf_str_off(__u32 *str_off, void *ctx) +{ + struct btf *btf = ctx; + const char *s; + + s = btf__str_by_offset(btf, *str_off); + + if (!s) + return -EINVAL; + + return 0; +} + +static int linker_sanity_check_btf(struct src_obj *obj) +{ + struct btf_type *t; + int i, n, err = 0; + + if (!obj->btf) + return 0; + + n = btf__type_cnt(obj->btf); + for (i = 1; i < n; i++) { + t = btf_type_by_id(obj->btf, i); + + err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf); + err = err ?: btf_type_visit_str_offs(t, check_btf_str_off, obj->btf); + if (err) + return err; + } + + return 0; +} + +static int linker_sanity_check_btf_ext(struct src_obj *obj) +{ + int err = 0; + + if (!obj->btf_ext) + return 0; + + /* can't use .BTF.ext without .BTF */ + if (!obj->btf) + return -EINVAL; + + err = err ?: btf_ext_visit_type_ids(obj->btf_ext, check_btf_type_id, obj->btf); + err = err ?: btf_ext_visit_str_offs(obj->btf_ext, check_btf_str_off, obj->btf); + if (err) + return err; + + return 0; +} + +static int init_sec(struct bpf_linker *linker, struct dst_sec *dst_sec, struct src_sec *src_sec) +{ + Elf_Scn *scn; + Elf_Data *data; + Elf64_Shdr *shdr; + int name_off; + + dst_sec->sec_sz = 0; + dst_sec->sec_idx = 0; + dst_sec->ephemeral = src_sec->ephemeral; + + /* ephemeral sections are just thin section shells lacking most parts */ + if (src_sec->ephemeral) + return 0; + + scn = elf_newscn(linker->elf); + if (!scn) + return -ENOMEM; + data = elf_newdata(scn); + if (!data) + return -ENOMEM; + shdr = elf64_getshdr(scn); + if (!shdr) + return -ENOMEM; + + dst_sec->scn = scn; + dst_sec->shdr = shdr; + dst_sec->data = data; + dst_sec->sec_idx = elf_ndxscn(scn); + + name_off = strset__add_str(linker->strtab_strs, src_sec->sec_name); + if (name_off < 0) + return name_off; + + shdr->sh_name = name_off; + shdr->sh_type = src_sec->shdr->sh_type; + shdr->sh_flags = src_sec->shdr->sh_flags; + shdr->sh_size = 0; + /* sh_link and sh_info have different meaning for different types of + * sections, so we leave it up to the caller code to fill them in, if + * necessary + */ + shdr->sh_link = 0; + shdr->sh_info = 0; + shdr->sh_addralign = src_sec->shdr->sh_addralign; + shdr->sh_entsize = src_sec->shdr->sh_entsize; + + data->d_type = src_sec->data->d_type; + data->d_size = 0; + data->d_buf = NULL; + data->d_align = src_sec->data->d_align; + data->d_off = 0; + + return 0; +} + +static struct dst_sec *find_dst_sec_by_name(struct bpf_linker *linker, const char *sec_name) +{ + struct dst_sec *sec; + int i; + + for (i = 1; i < linker->sec_cnt; i++) { + sec = &linker->secs[i]; + + if (strcmp(sec->sec_name, sec_name) == 0) + return sec; + } + + return NULL; +} + +static bool secs_match(struct dst_sec *dst, struct src_sec *src) +{ + if (dst->ephemeral || src->ephemeral) + return true; + + if (dst->shdr->sh_type != src->shdr->sh_type) { + pr_warn("sec %s types mismatch\n", dst->sec_name); + return false; + } + if (dst->shdr->sh_flags != src->shdr->sh_flags) { + pr_warn("sec %s flags mismatch\n", dst->sec_name); + return false; + } + if (dst->shdr->sh_entsize != src->shdr->sh_entsize) { + pr_warn("sec %s entsize mismatch\n", dst->sec_name); + return false; + } + + return true; +} + +static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec) +{ + if (dst_sec->sec_sz != src_sec->shdr->sh_size) + return false; + if (memcmp(dst_sec->raw_data, src_sec->data->d_buf, dst_sec->sec_sz) != 0) + return false; + return true; +} + +static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src_sec *src) +{ + void *tmp; + size_t dst_align, src_align; + size_t dst_align_sz, dst_final_sz; + int err; + + /* Ephemeral source section doesn't contribute anything to ELF + * section data. + */ + if (src->ephemeral) + return 0; + + /* Some sections (like .maps) can contain both externs (and thus be + * ephemeral) and non-externs (map definitions). So it's possible that + * it has to be "upgraded" from ephemeral to non-ephemeral when the + * first non-ephemeral entity appears. In such case, we add ELF + * section, data, etc. + */ + if (dst->ephemeral) { + err = init_sec(linker, dst, src); + if (err) + return err; + } + + dst_align = dst->shdr->sh_addralign; + src_align = src->shdr->sh_addralign; + if (dst_align == 0) + dst_align = 1; + if (dst_align < src_align) + dst_align = src_align; + + dst_align_sz = (dst->sec_sz + dst_align - 1) / dst_align * dst_align; + + /* no need to re-align final size */ + dst_final_sz = dst_align_sz + src->shdr->sh_size; + + if (src->shdr->sh_type != SHT_NOBITS) { + tmp = realloc(dst->raw_data, dst_final_sz); + if (!tmp) + return -ENOMEM; + dst->raw_data = tmp; + + /* pad dst section, if it's alignment forced size increase */ + memset(dst->raw_data + dst->sec_sz, 0, dst_align_sz - dst->sec_sz); + /* now copy src data at a properly aligned offset */ + memcpy(dst->raw_data + dst_align_sz, src->data->d_buf, src->shdr->sh_size); + } + + dst->sec_sz = dst_final_sz; + dst->shdr->sh_size = dst_final_sz; + dst->data->d_size = dst_final_sz; + + dst->shdr->sh_addralign = dst_align; + dst->data->d_align = dst_align; + + src->dst_off = dst_align_sz; + + return 0; +} + +static bool is_data_sec(struct src_sec *sec) +{ + if (!sec || sec->skipped) + return false; + /* ephemeral sections are data sections, e.g., .kconfig, .ksyms */ + if (sec->ephemeral) + return true; + return sec->shdr->sh_type == SHT_PROGBITS || sec->shdr->sh_type == SHT_NOBITS; +} + +static bool is_relo_sec(struct src_sec *sec) +{ + if (!sec || sec->skipped || sec->ephemeral) + return false; + return sec->shdr->sh_type == SHT_REL; +} + +static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj) +{ + int i, err; + + for (i = 1; i < obj->sec_cnt; i++) { + struct src_sec *src_sec; + struct dst_sec *dst_sec; + + src_sec = &obj->secs[i]; + if (!is_data_sec(src_sec)) + continue; + + dst_sec = find_dst_sec_by_name(linker, src_sec->sec_name); + if (!dst_sec) { + dst_sec = add_dst_sec(linker, src_sec->sec_name); + if (!dst_sec) + return -ENOMEM; + err = init_sec(linker, dst_sec, src_sec); + if (err) { + pr_warn("failed to init section '%s'\n", src_sec->sec_name); + return err; + } + } else { + if (!secs_match(dst_sec, src_sec)) { + pr_warn("ELF sections %s are incompatible\n", src_sec->sec_name); + return -1; + } + + /* "license" and "version" sections are deduped */ + if (strcmp(src_sec->sec_name, "license") == 0 + || strcmp(src_sec->sec_name, "version") == 0) { + if (!sec_content_is_same(dst_sec, src_sec)) { + pr_warn("non-identical contents of section '%s' are not supported\n", src_sec->sec_name); + return -EINVAL; + } + src_sec->skipped = true; + src_sec->dst_id = dst_sec->id; + continue; + } + } + + /* record mapped section index */ + src_sec->dst_id = dst_sec->id; + + err = extend_sec(linker, dst_sec, src_sec); + if (err) + return err; + } + + return 0; +} + +static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj) +{ + struct src_sec *symtab = &obj->secs[obj->symtab_sec_idx]; + Elf64_Sym *sym = symtab->data->d_buf; + int i, n = symtab->shdr->sh_size / symtab->shdr->sh_entsize, err; + int str_sec_idx = symtab->shdr->sh_link; + const char *sym_name; + + obj->sym_map = calloc(n + 1, sizeof(*obj->sym_map)); + if (!obj->sym_map) + return -ENOMEM; + + for (i = 0; i < n; i++, sym++) { + /* We already validated all-zero symbol #0 and we already + * appended it preventively to the final SYMTAB, so skip it. + */ + if (i == 0) + continue; + + sym_name = elf_strptr(obj->elf, str_sec_idx, sym->st_name); + if (!sym_name) { + pr_warn("can't fetch symbol name for symbol #%d in '%s'\n", i, obj->filename); + return -EINVAL; + } + + err = linker_append_elf_sym(linker, obj, sym, sym_name, i); + if (err) + return err; + } + + return 0; +} + +static Elf64_Sym *get_sym_by_idx(struct bpf_linker *linker, size_t sym_idx) +{ + struct dst_sec *symtab = &linker->secs[linker->symtab_sec_idx]; + Elf64_Sym *syms = symtab->raw_data; + + return &syms[sym_idx]; +} + +static struct glob_sym *find_glob_sym(struct bpf_linker *linker, const char *sym_name) +{ + struct glob_sym *glob_sym; + const char *name; + int i; + + for (i = 0; i < linker->glob_sym_cnt; i++) { + glob_sym = &linker->glob_syms[i]; + name = strset__data(linker->strtab_strs) + glob_sym->name_off; + + if (strcmp(name, sym_name) == 0) + return glob_sym; + } + + return NULL; +} + +static struct glob_sym *add_glob_sym(struct bpf_linker *linker) +{ + struct glob_sym *syms, *sym; + + syms = libbpf_reallocarray(linker->glob_syms, linker->glob_sym_cnt + 1, + sizeof(*linker->glob_syms)); + if (!syms) + return NULL; + + sym = &syms[linker->glob_sym_cnt]; + memset(sym, 0, sizeof(*sym)); + sym->var_idx = -1; + + linker->glob_syms = syms; + linker->glob_sym_cnt++; + + return sym; +} + +static bool glob_sym_btf_matches(const char *sym_name, bool exact, + const struct btf *btf1, __u32 id1, + const struct btf *btf2, __u32 id2) +{ + const struct btf_type *t1, *t2; + bool is_static1, is_static2; + const char *n1, *n2; + int i, n; + +recur: + n1 = n2 = NULL; + t1 = skip_mods_and_typedefs(btf1, id1, &id1); + t2 = skip_mods_and_typedefs(btf2, id2, &id2); + + /* check if only one side is FWD, otherwise handle with common logic */ + if (!exact && btf_is_fwd(t1) != btf_is_fwd(t2)) { + n1 = btf__str_by_offset(btf1, t1->name_off); + n2 = btf__str_by_offset(btf2, t2->name_off); + if (strcmp(n1, n2) != 0) { + pr_warn("global '%s': incompatible forward declaration names '%s' and '%s'\n", + sym_name, n1, n2); + return false; + } + /* validate if FWD kind matches concrete kind */ + if (btf_is_fwd(t1)) { + if (btf_kflag(t1) && btf_is_union(t2)) + return true; + if (!btf_kflag(t1) && btf_is_struct(t2)) + return true; + pr_warn("global '%s': incompatible %s forward declaration and concrete kind %s\n", + sym_name, btf_kflag(t1) ? "union" : "struct", btf_kind_str(t2)); + } else { + if (btf_kflag(t2) && btf_is_union(t1)) + return true; + if (!btf_kflag(t2) && btf_is_struct(t1)) + return true; + pr_warn("global '%s': incompatible %s forward declaration and concrete kind %s\n", + sym_name, btf_kflag(t2) ? "union" : "struct", btf_kind_str(t1)); + } + return false; + } + + if (btf_kind(t1) != btf_kind(t2)) { + pr_warn("global '%s': incompatible BTF kinds %s and %s\n", + sym_name, btf_kind_str(t1), btf_kind_str(t2)); + return false; + } + + switch (btf_kind(t1)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_FWD: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + n1 = btf__str_by_offset(btf1, t1->name_off); + n2 = btf__str_by_offset(btf2, t2->name_off); + if (strcmp(n1, n2) != 0) { + pr_warn("global '%s': incompatible %s names '%s' and '%s'\n", + sym_name, btf_kind_str(t1), n1, n2); + return false; + } + break; + default: + break; + } + + switch (btf_kind(t1)) { + case BTF_KIND_UNKN: /* void */ + case BTF_KIND_FWD: + return true; + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + /* ignore encoding for int and enum values for enum */ + if (t1->size != t2->size) { + pr_warn("global '%s': incompatible %s '%s' size %u and %u\n", + sym_name, btf_kind_str(t1), n1, t1->size, t2->size); + return false; + } + return true; + case BTF_KIND_PTR: + /* just validate overall shape of the referenced type, so no + * contents comparison for struct/union, and allowd fwd vs + * struct/union + */ + exact = false; + id1 = t1->type; + id2 = t2->type; + goto recur; + case BTF_KIND_ARRAY: + /* ignore index type and array size */ + id1 = btf_array(t1)->type; + id2 = btf_array(t2)->type; + goto recur; + case BTF_KIND_FUNC: + /* extern and global linkages are compatible */ + is_static1 = btf_func_linkage(t1) == BTF_FUNC_STATIC; + is_static2 = btf_func_linkage(t2) == BTF_FUNC_STATIC; + if (is_static1 != is_static2) { + pr_warn("global '%s': incompatible func '%s' linkage\n", sym_name, n1); + return false; + } + + id1 = t1->type; + id2 = t2->type; + goto recur; + case BTF_KIND_VAR: + /* extern and global linkages are compatible */ + is_static1 = btf_var(t1)->linkage == BTF_VAR_STATIC; + is_static2 = btf_var(t2)->linkage == BTF_VAR_STATIC; + if (is_static1 != is_static2) { + pr_warn("global '%s': incompatible var '%s' linkage\n", sym_name, n1); + return false; + } + + id1 = t1->type; + id2 = t2->type; + goto recur; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m1, *m2; + + if (!exact) + return true; + + if (btf_vlen(t1) != btf_vlen(t2)) { + pr_warn("global '%s': incompatible number of %s fields %u and %u\n", + sym_name, btf_kind_str(t1), btf_vlen(t1), btf_vlen(t2)); + return false; + } + + n = btf_vlen(t1); + m1 = btf_members(t1); + m2 = btf_members(t2); + for (i = 0; i < n; i++, m1++, m2++) { + n1 = btf__str_by_offset(btf1, m1->name_off); + n2 = btf__str_by_offset(btf2, m2->name_off); + if (strcmp(n1, n2) != 0) { + pr_warn("global '%s': incompatible field #%d names '%s' and '%s'\n", + sym_name, i, n1, n2); + return false; + } + if (m1->offset != m2->offset) { + pr_warn("global '%s': incompatible field #%d ('%s') offsets\n", + sym_name, i, n1); + return false; + } + if (!glob_sym_btf_matches(sym_name, exact, btf1, m1->type, btf2, m2->type)) + return false; + } + + return true; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *m1, *m2; + + if (btf_vlen(t1) != btf_vlen(t2)) { + pr_warn("global '%s': incompatible number of %s params %u and %u\n", + sym_name, btf_kind_str(t1), btf_vlen(t1), btf_vlen(t2)); + return false; + } + + n = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); + for (i = 0; i < n; i++, m1++, m2++) { + /* ignore func arg names */ + if (!glob_sym_btf_matches(sym_name, exact, btf1, m1->type, btf2, m2->type)) + return false; + } + + /* now check return type as well */ + id1 = t1->type; + id2 = t2->type; + goto recur; + } + + /* skip_mods_and_typedefs() make this impossible */ + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + /* DATASECs are never compared with each other */ + case BTF_KIND_DATASEC: + default: + pr_warn("global '%s': unsupported BTF kind %s\n", + sym_name, btf_kind_str(t1)); + return false; + } +} + +static bool map_defs_match(const char *sym_name, + const struct btf *main_btf, + const struct btf_map_def *main_def, + const struct btf_map_def *main_inner_def, + const struct btf *extra_btf, + const struct btf_map_def *extra_def, + const struct btf_map_def *extra_inner_def) +{ + const char *reason; + + if (main_def->map_type != extra_def->map_type) { + reason = "type"; + goto mismatch; + } + + /* check key type/size match */ + if (main_def->key_size != extra_def->key_size) { + reason = "key_size"; + goto mismatch; + } + if (!!main_def->key_type_id != !!extra_def->key_type_id) { + reason = "key type"; + goto mismatch; + } + if ((main_def->parts & MAP_DEF_KEY_TYPE) + && !glob_sym_btf_matches(sym_name, true /*exact*/, + main_btf, main_def->key_type_id, + extra_btf, extra_def->key_type_id)) { + reason = "key type"; + goto mismatch; + } + + /* validate value type/size match */ + if (main_def->value_size != extra_def->value_size) { + reason = "value_size"; + goto mismatch; + } + if (!!main_def->value_type_id != !!extra_def->value_type_id) { + reason = "value type"; + goto mismatch; + } + if ((main_def->parts & MAP_DEF_VALUE_TYPE) + && !glob_sym_btf_matches(sym_name, true /*exact*/, + main_btf, main_def->value_type_id, + extra_btf, extra_def->value_type_id)) { + reason = "key type"; + goto mismatch; + } + + if (main_def->max_entries != extra_def->max_entries) { + reason = "max_entries"; + goto mismatch; + } + if (main_def->map_flags != extra_def->map_flags) { + reason = "map_flags"; + goto mismatch; + } + if (main_def->numa_node != extra_def->numa_node) { + reason = "numa_node"; + goto mismatch; + } + if (main_def->pinning != extra_def->pinning) { + reason = "pinning"; + goto mismatch; + } + + if ((main_def->parts & MAP_DEF_INNER_MAP) != (extra_def->parts & MAP_DEF_INNER_MAP)) { + reason = "inner map"; + goto mismatch; + } + + if (main_def->parts & MAP_DEF_INNER_MAP) { + char inner_map_name[128]; + + snprintf(inner_map_name, sizeof(inner_map_name), "%s.inner", sym_name); + + return map_defs_match(inner_map_name, + main_btf, main_inner_def, NULL, + extra_btf, extra_inner_def, NULL); + } + + return true; + +mismatch: + pr_warn("global '%s': map %s mismatch\n", sym_name, reason); + return false; +} + +static bool glob_map_defs_match(const char *sym_name, + struct bpf_linker *linker, struct glob_sym *glob_sym, + struct src_obj *obj, Elf64_Sym *sym, int btf_id) +{ + struct btf_map_def dst_def = {}, dst_inner_def = {}; + struct btf_map_def src_def = {}, src_inner_def = {}; + const struct btf_type *t; + int err; + + t = btf__type_by_id(obj->btf, btf_id); + if (!btf_is_var(t)) { + pr_warn("global '%s': invalid map definition type [%d]\n", sym_name, btf_id); + return false; + } + t = skip_mods_and_typedefs(obj->btf, t->type, NULL); + + err = parse_btf_map_def(sym_name, obj->btf, t, true /*strict*/, &src_def, &src_inner_def); + if (err) { + pr_warn("global '%s': invalid map definition\n", sym_name); + return false; + } + + /* re-parse existing map definition */ + t = btf__type_by_id(linker->btf, glob_sym->btf_id); + t = skip_mods_and_typedefs(linker->btf, t->type, NULL); + err = parse_btf_map_def(sym_name, linker->btf, t, true /*strict*/, &dst_def, &dst_inner_def); + if (err) { + /* this should not happen, because we already validated it */ + pr_warn("global '%s': invalid dst map definition\n", sym_name); + return false; + } + + /* Currently extern map definition has to be complete and match + * concrete map definition exactly. This restriction might be lifted + * in the future. + */ + return map_defs_match(sym_name, linker->btf, &dst_def, &dst_inner_def, + obj->btf, &src_def, &src_inner_def); +} + +static bool glob_syms_match(const char *sym_name, + struct bpf_linker *linker, struct glob_sym *glob_sym, + struct src_obj *obj, Elf64_Sym *sym, size_t sym_idx, int btf_id) +{ + const struct btf_type *src_t; + + /* if we are dealing with externs, BTF types describing both global + * and extern VARs/FUNCs should be completely present in all files + */ + if (!glob_sym->btf_id || !btf_id) { + pr_warn("BTF info is missing for global symbol '%s'\n", sym_name); + return false; + } + + src_t = btf__type_by_id(obj->btf, btf_id); + if (!btf_is_var(src_t) && !btf_is_func(src_t)) { + pr_warn("only extern variables and functions are supported, but got '%s' for '%s'\n", + btf_kind_str(src_t), sym_name); + return false; + } + + /* deal with .maps definitions specially */ + if (glob_sym->sec_id && strcmp(linker->secs[glob_sym->sec_id].sec_name, MAPS_ELF_SEC) == 0) + return glob_map_defs_match(sym_name, linker, glob_sym, obj, sym, btf_id); + + if (!glob_sym_btf_matches(sym_name, true /*exact*/, + linker->btf, glob_sym->btf_id, obj->btf, btf_id)) + return false; + + return true; +} + +static bool btf_is_non_static(const struct btf_type *t) +{ + return (btf_is_var(t) && btf_var(t)->linkage != BTF_VAR_STATIC) + || (btf_is_func(t) && btf_func_linkage(t) != BTF_FUNC_STATIC); +} + +static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name, + int *out_btf_sec_id, int *out_btf_id) +{ + int i, j, n, m, btf_id = 0; + const struct btf_type *t; + const struct btf_var_secinfo *vi; + const char *name; + + if (!obj->btf) { + pr_warn("failed to find BTF info for object '%s'\n", obj->filename); + return -EINVAL; + } + + n = btf__type_cnt(obj->btf); + for (i = 1; i < n; i++) { + t = btf__type_by_id(obj->btf, i); + + /* some global and extern FUNCs and VARs might not be associated with any + * DATASEC, so try to detect them in the same pass + */ + if (btf_is_non_static(t)) { + name = btf__str_by_offset(obj->btf, t->name_off); + if (strcmp(name, sym_name) != 0) + continue; + + /* remember and still try to find DATASEC */ + btf_id = i; + continue; + } + + if (!btf_is_datasec(t)) + continue; + + vi = btf_var_secinfos(t); + for (j = 0, m = btf_vlen(t); j < m; j++, vi++) { + t = btf__type_by_id(obj->btf, vi->type); + name = btf__str_by_offset(obj->btf, t->name_off); + + if (strcmp(name, sym_name) != 0) + continue; + if (btf_is_var(t) && btf_var(t)->linkage == BTF_VAR_STATIC) + continue; + if (btf_is_func(t) && btf_func_linkage(t) == BTF_FUNC_STATIC) + continue; + + if (btf_id && btf_id != vi->type) { + pr_warn("global/extern '%s' BTF is ambiguous: both types #%d and #%u match\n", + sym_name, btf_id, vi->type); + return -EINVAL; + } + + *out_btf_sec_id = i; + *out_btf_id = vi->type; + + return 0; + } + } + + /* free-floating extern or global FUNC */ + if (btf_id) { + *out_btf_sec_id = 0; + *out_btf_id = btf_id; + return 0; + } + + pr_warn("failed to find BTF info for global/extern symbol '%s'\n", sym_name); + return -ENOENT; +} + +static struct src_sec *find_src_sec_by_name(struct src_obj *obj, const char *sec_name) +{ + struct src_sec *sec; + int i; + + for (i = 1; i < obj->sec_cnt; i++) { + sec = &obj->secs[i]; + + if (strcmp(sec->sec_name, sec_name) == 0) + return sec; + } + + return NULL; +} + +static int complete_extern_btf_info(struct btf *dst_btf, int dst_id, + struct btf *src_btf, int src_id) +{ + struct btf_type *dst_t = btf_type_by_id(dst_btf, dst_id); + struct btf_type *src_t = btf_type_by_id(src_btf, src_id); + struct btf_param *src_p, *dst_p; + const char *s; + int i, n, off; + + /* We already made sure that source and destination types (FUNC or + * VAR) match in terms of types and argument names. + */ + if (btf_is_var(dst_t)) { + btf_var(dst_t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + return 0; + } + + dst_t->info = btf_type_info(BTF_KIND_FUNC, BTF_FUNC_GLOBAL, 0); + + /* now onto FUNC_PROTO types */ + src_t = btf_type_by_id(src_btf, src_t->type); + dst_t = btf_type_by_id(dst_btf, dst_t->type); + + /* Fill in all the argument names, which for extern FUNCs are missing. + * We'll end up with two copies of FUNCs/VARs for externs, but that + * will be taken care of by BTF dedup at the very end. + * It might be that BTF types for extern in one file has less/more BTF + * information (e.g., FWD instead of full STRUCT/UNION information), + * but that should be (in most cases, subject to BTF dedup rules) + * handled and resolved by BTF dedup algorithm as well, so we won't + * worry about it. Our only job is to make sure that argument names + * are populated on both sides, otherwise BTF dedup will pedantically + * consider them different. + */ + src_p = btf_params(src_t); + dst_p = btf_params(dst_t); + for (i = 0, n = btf_vlen(dst_t); i < n; i++, src_p++, dst_p++) { + if (!src_p->name_off) + continue; + + /* src_btf has more complete info, so add name to dst_btf */ + s = btf__str_by_offset(src_btf, src_p->name_off); + off = btf__add_str(dst_btf, s); + if (off < 0) + return off; + dst_p->name_off = off; + } + return 0; +} + +static void sym_update_bind(Elf64_Sym *sym, int sym_bind) +{ + sym->st_info = ELF64_ST_INFO(sym_bind, ELF64_ST_TYPE(sym->st_info)); +} + +static void sym_update_type(Elf64_Sym *sym, int sym_type) +{ + sym->st_info = ELF64_ST_INFO(ELF64_ST_BIND(sym->st_info), sym_type); +} + +static void sym_update_visibility(Elf64_Sym *sym, int sym_vis) +{ + /* libelf doesn't provide setters for ST_VISIBILITY, + * but it is stored in the lower 2 bits of st_other + */ + sym->st_other &= ~0x03; + sym->st_other |= sym_vis; +} + +static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, + Elf64_Sym *sym, const char *sym_name, int src_sym_idx) +{ + struct src_sec *src_sec = NULL; + struct dst_sec *dst_sec = NULL; + struct glob_sym *glob_sym = NULL; + int name_off, sym_type, sym_bind, sym_vis, err; + int btf_sec_id = 0, btf_id = 0; + size_t dst_sym_idx; + Elf64_Sym *dst_sym; + bool sym_is_extern; + + sym_type = ELF64_ST_TYPE(sym->st_info); + sym_bind = ELF64_ST_BIND(sym->st_info); + sym_vis = ELF64_ST_VISIBILITY(sym->st_other); + sym_is_extern = sym->st_shndx == SHN_UNDEF; + + if (sym_is_extern) { + if (!obj->btf) { + pr_warn("externs without BTF info are not supported\n"); + return -ENOTSUP; + } + } else if (sym->st_shndx < SHN_LORESERVE) { + src_sec = &obj->secs[sym->st_shndx]; + if (src_sec->skipped) + return 0; + dst_sec = &linker->secs[src_sec->dst_id]; + + /* allow only one STT_SECTION symbol per section */ + if (sym_type == STT_SECTION && dst_sec->sec_sym_idx) { + obj->sym_map[src_sym_idx] = dst_sec->sec_sym_idx; + return 0; + } + } + + if (sym_bind == STB_LOCAL) + goto add_sym; + + /* find matching BTF info */ + err = find_glob_sym_btf(obj, sym, sym_name, &btf_sec_id, &btf_id); + if (err) + return err; + + if (sym_is_extern && btf_sec_id) { + const char *sec_name = NULL; + const struct btf_type *t; + + t = btf__type_by_id(obj->btf, btf_sec_id); + sec_name = btf__str_by_offset(obj->btf, t->name_off); + + /* Clang puts unannotated extern vars into + * '.extern' BTF DATASEC. Treat them the same + * as unannotated extern funcs (which are + * currently not put into any DATASECs). + * Those don't have associated src_sec/dst_sec. + */ + if (strcmp(sec_name, BTF_EXTERN_SEC) != 0) { + src_sec = find_src_sec_by_name(obj, sec_name); + if (!src_sec) { + pr_warn("failed to find matching ELF sec '%s'\n", sec_name); + return -ENOENT; + } + dst_sec = &linker->secs[src_sec->dst_id]; + } + } + + glob_sym = find_glob_sym(linker, sym_name); + if (glob_sym) { + /* Preventively resolve to existing symbol. This is + * needed for further relocation symbol remapping in + * the next step of linking. + */ + obj->sym_map[src_sym_idx] = glob_sym->sym_idx; + + /* If both symbols are non-externs, at least one of + * them has to be STB_WEAK, otherwise they are in + * a conflict with each other. + */ + if (!sym_is_extern && !glob_sym->is_extern + && !glob_sym->is_weak && sym_bind != STB_WEAK) { + pr_warn("conflicting non-weak symbol #%d (%s) definition in '%s'\n", + src_sym_idx, sym_name, obj->filename); + return -EINVAL; + } + + if (!glob_syms_match(sym_name, linker, glob_sym, obj, sym, src_sym_idx, btf_id)) + return -EINVAL; + + dst_sym = get_sym_by_idx(linker, glob_sym->sym_idx); + + /* If new symbol is strong, then force dst_sym to be strong as + * well; this way a mix of weak and non-weak extern + * definitions will end up being strong. + */ + if (sym_bind == STB_GLOBAL) { + /* We still need to preserve type (NOTYPE or + * OBJECT/FUNC, depending on whether the symbol is + * extern or not) + */ + sym_update_bind(dst_sym, STB_GLOBAL); + glob_sym->is_weak = false; + } + + /* Non-default visibility is "contaminating", with stricter + * visibility overwriting more permissive ones, even if more + * permissive visibility comes from just an extern definition. + * Currently only STV_DEFAULT and STV_HIDDEN are allowed and + * ensured by ELF symbol sanity checks above. + */ + if (sym_vis > ELF64_ST_VISIBILITY(dst_sym->st_other)) + sym_update_visibility(dst_sym, sym_vis); + + /* If the new symbol is extern, then regardless if + * existing symbol is extern or resolved global, just + * keep the existing one untouched. + */ + if (sym_is_extern) + return 0; + + /* If existing symbol is a strong resolved symbol, bail out, + * because we lost resolution battle have nothing to + * contribute. We already checked abover that there is no + * strong-strong conflict. We also already tightened binding + * and visibility, so nothing else to contribute at that point. + */ + if (!glob_sym->is_extern && sym_bind == STB_WEAK) + return 0; + + /* At this point, new symbol is strong non-extern, + * so overwrite glob_sym with new symbol information. + * Preserve binding and visibility. + */ + sym_update_type(dst_sym, sym_type); + dst_sym->st_shndx = dst_sec->sec_idx; + dst_sym->st_value = src_sec->dst_off + sym->st_value; + dst_sym->st_size = sym->st_size; + + /* see comment below about dst_sec->id vs dst_sec->sec_idx */ + glob_sym->sec_id = dst_sec->id; + glob_sym->is_extern = false; + + if (complete_extern_btf_info(linker->btf, glob_sym->btf_id, + obj->btf, btf_id)) + return -EINVAL; + + /* request updating VAR's/FUNC's underlying BTF type when appending BTF type */ + glob_sym->underlying_btf_id = 0; + + obj->sym_map[src_sym_idx] = glob_sym->sym_idx; + return 0; + } + +add_sym: + name_off = strset__add_str(linker->strtab_strs, sym_name); + if (name_off < 0) + return name_off; + + dst_sym = add_new_sym(linker, &dst_sym_idx); + if (!dst_sym) + return -ENOMEM; + + dst_sym->st_name = name_off; + dst_sym->st_info = sym->st_info; + dst_sym->st_other = sym->st_other; + dst_sym->st_shndx = dst_sec ? dst_sec->sec_idx : sym->st_shndx; + dst_sym->st_value = (src_sec ? src_sec->dst_off : 0) + sym->st_value; + dst_sym->st_size = sym->st_size; + + obj->sym_map[src_sym_idx] = dst_sym_idx; + + if (sym_type == STT_SECTION && dst_sym) { + dst_sec->sec_sym_idx = dst_sym_idx; + dst_sym->st_value = 0; + } + + if (sym_bind != STB_LOCAL) { + glob_sym = add_glob_sym(linker); + if (!glob_sym) + return -ENOMEM; + + glob_sym->sym_idx = dst_sym_idx; + /* we use dst_sec->id (and not dst_sec->sec_idx), because + * ephemeral sections (.kconfig, .ksyms, etc) don't have + * sec_idx (as they don't have corresponding ELF section), but + * still have id. .extern doesn't have even ephemeral section + * associated with it, so dst_sec->id == dst_sec->sec_idx == 0. + */ + glob_sym->sec_id = dst_sec ? dst_sec->id : 0; + glob_sym->name_off = name_off; + /* we will fill btf_id in during BTF merging step */ + glob_sym->btf_id = 0; + glob_sym->is_extern = sym_is_extern; + glob_sym->is_weak = sym_bind == STB_WEAK; + } + + return 0; +} + +static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj) +{ + struct src_sec *src_symtab = &obj->secs[obj->symtab_sec_idx]; + struct dst_sec *dst_symtab; + int i, err; + + for (i = 1; i < obj->sec_cnt; i++) { + struct src_sec *src_sec, *src_linked_sec; + struct dst_sec *dst_sec, *dst_linked_sec; + Elf64_Rel *src_rel, *dst_rel; + int j, n; + + src_sec = &obj->secs[i]; + if (!is_relo_sec(src_sec)) + continue; + + /* shdr->sh_info points to relocatable section */ + src_linked_sec = &obj->secs[src_sec->shdr->sh_info]; + if (src_linked_sec->skipped) + continue; + + dst_sec = find_dst_sec_by_name(linker, src_sec->sec_name); + if (!dst_sec) { + dst_sec = add_dst_sec(linker, src_sec->sec_name); + if (!dst_sec) + return -ENOMEM; + err = init_sec(linker, dst_sec, src_sec); + if (err) { + pr_warn("failed to init section '%s'\n", src_sec->sec_name); + return err; + } + } else if (!secs_match(dst_sec, src_sec)) { + pr_warn("sections %s are not compatible\n", src_sec->sec_name); + return -1; + } + + /* add_dst_sec() above could have invalidated linker->secs */ + dst_symtab = &linker->secs[linker->symtab_sec_idx]; + + /* shdr->sh_link points to SYMTAB */ + dst_sec->shdr->sh_link = linker->symtab_sec_idx; + + /* shdr->sh_info points to relocated section */ + dst_linked_sec = &linker->secs[src_linked_sec->dst_id]; + dst_sec->shdr->sh_info = dst_linked_sec->sec_idx; + + src_sec->dst_id = dst_sec->id; + err = extend_sec(linker, dst_sec, src_sec); + if (err) + return err; + + src_rel = src_sec->data->d_buf; + dst_rel = dst_sec->raw_data + src_sec->dst_off; + n = src_sec->shdr->sh_size / src_sec->shdr->sh_entsize; + for (j = 0; j < n; j++, src_rel++, dst_rel++) { + size_t src_sym_idx = ELF64_R_SYM(src_rel->r_info); + size_t sym_type = ELF64_R_TYPE(src_rel->r_info); + Elf64_Sym *src_sym, *dst_sym; + size_t dst_sym_idx; + + src_sym_idx = ELF64_R_SYM(src_rel->r_info); + src_sym = src_symtab->data->d_buf + sizeof(*src_sym) * src_sym_idx; + + dst_sym_idx = obj->sym_map[src_sym_idx]; + dst_sym = dst_symtab->raw_data + sizeof(*dst_sym) * dst_sym_idx; + dst_rel->r_offset += src_linked_sec->dst_off; + sym_type = ELF64_R_TYPE(src_rel->r_info); + dst_rel->r_info = ELF64_R_INFO(dst_sym_idx, sym_type); + + if (ELF64_ST_TYPE(src_sym->st_info) == STT_SECTION) { + struct src_sec *sec = &obj->secs[src_sym->st_shndx]; + struct bpf_insn *insn; + + if (src_linked_sec->shdr->sh_flags & SHF_EXECINSTR) { + /* calls to the very first static function inside + * .text section at offset 0 will + * reference section symbol, not the + * function symbol. Fix that up, + * otherwise it won't be possible to + * relocate calls to two different + * static functions with the same name + * (rom two different object files) + */ + insn = dst_linked_sec->raw_data + dst_rel->r_offset; + if (insn->code == (BPF_JMP | BPF_CALL)) + insn->imm += sec->dst_off / sizeof(struct bpf_insn); + else + insn->imm += sec->dst_off; + } else { + pr_warn("relocation against STT_SECTION in non-exec section is not supported!\n"); + return -EINVAL; + } + } + + } + } + + return 0; +} + +static Elf64_Sym *find_sym_by_name(struct src_obj *obj, size_t sec_idx, + int sym_type, const char *sym_name) +{ + struct src_sec *symtab = &obj->secs[obj->symtab_sec_idx]; + Elf64_Sym *sym = symtab->data->d_buf; + int i, n = symtab->shdr->sh_size / symtab->shdr->sh_entsize; + int str_sec_idx = symtab->shdr->sh_link; + const char *name; + + for (i = 0; i < n; i++, sym++) { + if (sym->st_shndx != sec_idx) + continue; + if (ELF64_ST_TYPE(sym->st_info) != sym_type) + continue; + + name = elf_strptr(obj->elf, str_sec_idx, sym->st_name); + if (!name) + return NULL; + + if (strcmp(sym_name, name) != 0) + continue; + + return sym; + } + + return NULL; +} + +static int linker_fixup_btf(struct src_obj *obj) +{ + const char *sec_name; + struct src_sec *sec; + int i, j, n, m; + + if (!obj->btf) + return 0; + + n = btf__type_cnt(obj->btf); + for (i = 1; i < n; i++) { + struct btf_var_secinfo *vi; + struct btf_type *t; + + t = btf_type_by_id(obj->btf, i); + if (btf_kind(t) != BTF_KIND_DATASEC) + continue; + + sec_name = btf__str_by_offset(obj->btf, t->name_off); + sec = find_src_sec_by_name(obj, sec_name); + if (sec) { + /* record actual section size, unless ephemeral */ + if (sec->shdr) + t->size = sec->shdr->sh_size; + } else { + /* BTF can have some sections that are not represented + * in ELF, e.g., .kconfig, .ksyms, .extern, which are used + * for special extern variables. + * + * For all but one such special (ephemeral) + * sections, we pre-create "section shells" to be able + * to keep track of extra per-section metadata later + * (e.g., those BTF extern variables). + * + * .extern is even more special, though, because it + * contains extern variables that need to be resolved + * by static linker, not libbpf and kernel. When such + * externs are resolved, we are going to remove them + * from .extern BTF section and might end up not + * needing it at all. Each resolved extern should have + * matching non-extern VAR/FUNC in other sections. + * + * We do support leaving some of the externs + * unresolved, though, to support cases of building + * libraries, which will later be linked against final + * BPF applications. So if at finalization we still + * see unresolved externs, we'll create .extern + * section on our own. + */ + if (strcmp(sec_name, BTF_EXTERN_SEC) == 0) + continue; + + sec = add_src_sec(obj, sec_name); + if (!sec) + return -ENOMEM; + + sec->ephemeral = true; + sec->sec_idx = 0; /* will match UNDEF shndx in ELF */ + } + + /* remember ELF section and its BTF type ID match */ + sec->sec_type_id = i; + + /* fix up variable offsets */ + vi = btf_var_secinfos(t); + for (j = 0, m = btf_vlen(t); j < m; j++, vi++) { + const struct btf_type *vt = btf__type_by_id(obj->btf, vi->type); + const char *var_name = btf__str_by_offset(obj->btf, vt->name_off); + int var_linkage = btf_var(vt)->linkage; + Elf64_Sym *sym; + + /* no need to patch up static or extern vars */ + if (var_linkage != BTF_VAR_GLOBAL_ALLOCATED) + continue; + + sym = find_sym_by_name(obj, sec->sec_idx, STT_OBJECT, var_name); + if (!sym) { + pr_warn("failed to find symbol for variable '%s' in section '%s'\n", var_name, sec_name); + return -ENOENT; + } + + vi->offset = sym->st_value; + } + } + + return 0; +} + +static int remap_type_id(__u32 *type_id, void *ctx) +{ + int *id_map = ctx; + int new_id = id_map[*type_id]; + + /* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */ + if (new_id == 0 && *type_id != 0) { + pr_warn("failed to find new ID mapping for original BTF type ID %u\n", *type_id); + return -EINVAL; + } + + *type_id = id_map[*type_id]; + + return 0; +} + +static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) +{ + const struct btf_type *t; + int i, j, n, start_id, id; + const char *name; + + if (!obj->btf) + return 0; + + start_id = btf__type_cnt(linker->btf); + n = btf__type_cnt(obj->btf); + + obj->btf_type_map = calloc(n + 1, sizeof(int)); + if (!obj->btf_type_map) + return -ENOMEM; + + for (i = 1; i < n; i++) { + struct glob_sym *glob_sym = NULL; + + t = btf__type_by_id(obj->btf, i); + + /* DATASECs are handled specially below */ + if (btf_kind(t) == BTF_KIND_DATASEC) + continue; + + if (btf_is_non_static(t)) { + /* there should be glob_sym already */ + name = btf__str_by_offset(obj->btf, t->name_off); + glob_sym = find_glob_sym(linker, name); + + /* VARs without corresponding glob_sym are those that + * belong to skipped/deduplicated sections (i.e., + * license and version), so just skip them + */ + if (!glob_sym) + continue; + + /* linker_append_elf_sym() might have requested + * updating underlying type ID, if extern was resolved + * to strong symbol or weak got upgraded to non-weak + */ + if (glob_sym->underlying_btf_id == 0) + glob_sym->underlying_btf_id = -t->type; + + /* globals from previous object files that match our + * VAR/FUNC already have a corresponding associated + * BTF type, so just make sure to use it + */ + if (glob_sym->btf_id) { + /* reuse existing BTF type for global var/func */ + obj->btf_type_map[i] = glob_sym->btf_id; + continue; + } + } + + id = btf__add_type(linker->btf, obj->btf, t); + if (id < 0) { + pr_warn("failed to append BTF type #%d from file '%s'\n", i, obj->filename); + return id; + } + + obj->btf_type_map[i] = id; + + /* record just appended BTF type for var/func */ + if (glob_sym) { + glob_sym->btf_id = id; + glob_sym->underlying_btf_id = -t->type; + } + } + + /* remap all the types except DATASECs */ + n = btf__type_cnt(linker->btf); + for (i = start_id; i < n; i++) { + struct btf_type *dst_t = btf_type_by_id(linker->btf, i); + + if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map)) + return -EINVAL; + } + + /* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's + * actual type), if necessary + */ + for (i = 0; i < linker->glob_sym_cnt; i++) { + struct glob_sym *glob_sym = &linker->glob_syms[i]; + struct btf_type *glob_t; + + if (glob_sym->underlying_btf_id >= 0) + continue; + + glob_sym->underlying_btf_id = obj->btf_type_map[-glob_sym->underlying_btf_id]; + + glob_t = btf_type_by_id(linker->btf, glob_sym->btf_id); + glob_t->type = glob_sym->underlying_btf_id; + } + + /* append DATASEC info */ + for (i = 1; i < obj->sec_cnt; i++) { + struct src_sec *src_sec; + struct dst_sec *dst_sec; + const struct btf_var_secinfo *src_var; + struct btf_var_secinfo *dst_var; + + src_sec = &obj->secs[i]; + if (!src_sec->sec_type_id || src_sec->skipped) + continue; + dst_sec = &linker->secs[src_sec->dst_id]; + + /* Mark section as having BTF regardless of the presence of + * variables. In some cases compiler might generate empty BTF + * with no variables information. E.g., when promoting local + * array/structure variable initial values and BPF object + * file otherwise has no read-only static variables in + * .rodata. We need to preserve such empty BTF and just set + * correct section size. + */ + dst_sec->has_btf = true; + + t = btf__type_by_id(obj->btf, src_sec->sec_type_id); + src_var = btf_var_secinfos(t); + n = btf_vlen(t); + for (j = 0; j < n; j++, src_var++) { + void *sec_vars = dst_sec->sec_vars; + int new_id = obj->btf_type_map[src_var->type]; + struct glob_sym *glob_sym = NULL; + + t = btf_type_by_id(linker->btf, new_id); + if (btf_is_non_static(t)) { + name = btf__str_by_offset(linker->btf, t->name_off); + glob_sym = find_glob_sym(linker, name); + if (glob_sym->sec_id != dst_sec->id) { + pr_warn("global '%s': section mismatch %d vs %d\n", + name, glob_sym->sec_id, dst_sec->id); + return -EINVAL; + } + } + + /* If there is already a member (VAR or FUNC) mapped + * to the same type, don't add a duplicate entry. + * This will happen when multiple object files define + * the same extern VARs/FUNCs. + */ + if (glob_sym && glob_sym->var_idx >= 0) { + __s64 sz; + + dst_var = &dst_sec->sec_vars[glob_sym->var_idx]; + /* Because underlying BTF type might have + * changed, so might its size have changed, so + * re-calculate and update it in sec_var. + */ + sz = btf__resolve_size(linker->btf, glob_sym->underlying_btf_id); + if (sz < 0) { + pr_warn("global '%s': failed to resolve size of underlying type: %d\n", + name, (int)sz); + return -EINVAL; + } + dst_var->size = sz; + continue; + } + + sec_vars = libbpf_reallocarray(sec_vars, + dst_sec->sec_var_cnt + 1, + sizeof(*dst_sec->sec_vars)); + if (!sec_vars) + return -ENOMEM; + + dst_sec->sec_vars = sec_vars; + dst_sec->sec_var_cnt++; + + dst_var = &dst_sec->sec_vars[dst_sec->sec_var_cnt - 1]; + dst_var->type = obj->btf_type_map[src_var->type]; + dst_var->size = src_var->size; + dst_var->offset = src_sec->dst_off + src_var->offset; + + if (glob_sym) + glob_sym->var_idx = dst_sec->sec_var_cnt - 1; + } + } + + return 0; +} + +static void *add_btf_ext_rec(struct btf_ext_sec_data *ext_data, const void *src_rec) +{ + void *tmp; + + tmp = libbpf_reallocarray(ext_data->recs, ext_data->rec_cnt + 1, ext_data->rec_sz); + if (!tmp) + return NULL; + ext_data->recs = tmp; + + tmp += ext_data->rec_cnt * ext_data->rec_sz; + memcpy(tmp, src_rec, ext_data->rec_sz); + + ext_data->rec_cnt++; + + return tmp; +} + +static int linker_append_btf_ext(struct bpf_linker *linker, struct src_obj *obj) +{ + const struct btf_ext_info_sec *ext_sec; + const char *sec_name, *s; + struct src_sec *src_sec; + struct dst_sec *dst_sec; + int rec_sz, str_off, i; + + if (!obj->btf_ext) + return 0; + + rec_sz = obj->btf_ext->func_info.rec_size; + for_each_btf_ext_sec(&obj->btf_ext->func_info, ext_sec) { + struct bpf_func_info_min *src_rec, *dst_rec; + + sec_name = btf__name_by_offset(obj->btf, ext_sec->sec_name_off); + src_sec = find_src_sec_by_name(obj, sec_name); + if (!src_sec) { + pr_warn("can't find section '%s' referenced from .BTF.ext\n", sec_name); + return -EINVAL; + } + dst_sec = &linker->secs[src_sec->dst_id]; + + if (dst_sec->func_info.rec_sz == 0) + dst_sec->func_info.rec_sz = rec_sz; + if (dst_sec->func_info.rec_sz != rec_sz) { + pr_warn("incompatible .BTF.ext record sizes for section '%s'\n", sec_name); + return -EINVAL; + } + + for_each_btf_ext_rec(&obj->btf_ext->func_info, ext_sec, i, src_rec) { + dst_rec = add_btf_ext_rec(&dst_sec->func_info, src_rec); + if (!dst_rec) + return -ENOMEM; + + dst_rec->insn_off += src_sec->dst_off; + dst_rec->type_id = obj->btf_type_map[dst_rec->type_id]; + } + } + + rec_sz = obj->btf_ext->line_info.rec_size; + for_each_btf_ext_sec(&obj->btf_ext->line_info, ext_sec) { + struct bpf_line_info_min *src_rec, *dst_rec; + + sec_name = btf__name_by_offset(obj->btf, ext_sec->sec_name_off); + src_sec = find_src_sec_by_name(obj, sec_name); + if (!src_sec) { + pr_warn("can't find section '%s' referenced from .BTF.ext\n", sec_name); + return -EINVAL; + } + dst_sec = &linker->secs[src_sec->dst_id]; + + if (dst_sec->line_info.rec_sz == 0) + dst_sec->line_info.rec_sz = rec_sz; + if (dst_sec->line_info.rec_sz != rec_sz) { + pr_warn("incompatible .BTF.ext record sizes for section '%s'\n", sec_name); + return -EINVAL; + } + + for_each_btf_ext_rec(&obj->btf_ext->line_info, ext_sec, i, src_rec) { + dst_rec = add_btf_ext_rec(&dst_sec->line_info, src_rec); + if (!dst_rec) + return -ENOMEM; + + dst_rec->insn_off += src_sec->dst_off; + + s = btf__str_by_offset(obj->btf, src_rec->file_name_off); + str_off = btf__add_str(linker->btf, s); + if (str_off < 0) + return -ENOMEM; + dst_rec->file_name_off = str_off; + + s = btf__str_by_offset(obj->btf, src_rec->line_off); + str_off = btf__add_str(linker->btf, s); + if (str_off < 0) + return -ENOMEM; + dst_rec->line_off = str_off; + + /* dst_rec->line_col is fine */ + } + } + + rec_sz = obj->btf_ext->core_relo_info.rec_size; + for_each_btf_ext_sec(&obj->btf_ext->core_relo_info, ext_sec) { + struct bpf_core_relo *src_rec, *dst_rec; + + sec_name = btf__name_by_offset(obj->btf, ext_sec->sec_name_off); + src_sec = find_src_sec_by_name(obj, sec_name); + if (!src_sec) { + pr_warn("can't find section '%s' referenced from .BTF.ext\n", sec_name); + return -EINVAL; + } + dst_sec = &linker->secs[src_sec->dst_id]; + + if (dst_sec->core_relo_info.rec_sz == 0) + dst_sec->core_relo_info.rec_sz = rec_sz; + if (dst_sec->core_relo_info.rec_sz != rec_sz) { + pr_warn("incompatible .BTF.ext record sizes for section '%s'\n", sec_name); + return -EINVAL; + } + + for_each_btf_ext_rec(&obj->btf_ext->core_relo_info, ext_sec, i, src_rec) { + dst_rec = add_btf_ext_rec(&dst_sec->core_relo_info, src_rec); + if (!dst_rec) + return -ENOMEM; + + dst_rec->insn_off += src_sec->dst_off; + dst_rec->type_id = obj->btf_type_map[dst_rec->type_id]; + + s = btf__str_by_offset(obj->btf, src_rec->access_str_off); + str_off = btf__add_str(linker->btf, s); + if (str_off < 0) + return -ENOMEM; + dst_rec->access_str_off = str_off; + + /* dst_rec->kind is fine */ + } + } + + return 0; +} + +int bpf_linker__finalize(struct bpf_linker *linker) +{ + struct dst_sec *sec; + size_t strs_sz; + const void *strs; + int err, i; + + if (!linker->elf) + return libbpf_err(-EINVAL); + + err = finalize_btf(linker); + if (err) + return libbpf_err(err); + + /* Finalize strings */ + strs_sz = strset__data_size(linker->strtab_strs); + strs = strset__data(linker->strtab_strs); + + sec = &linker->secs[linker->strtab_sec_idx]; + sec->data->d_align = 1; + sec->data->d_off = 0LL; + sec->data->d_buf = (void *)strs; + sec->data->d_type = ELF_T_BYTE; + sec->data->d_size = strs_sz; + sec->shdr->sh_size = strs_sz; + + for (i = 1; i < linker->sec_cnt; i++) { + sec = &linker->secs[i]; + + /* STRTAB is handled specially above */ + if (sec->sec_idx == linker->strtab_sec_idx) + continue; + + /* special ephemeral sections (.ksyms, .kconfig, etc) */ + if (!sec->scn) + continue; + + sec->data->d_buf = sec->raw_data; + } + + /* Finalize ELF layout */ + if (elf_update(linker->elf, ELF_C_NULL) < 0) { + err = -errno; + pr_warn_elf("failed to finalize ELF layout"); + return libbpf_err(err); + } + + /* Write out final ELF contents */ + if (elf_update(linker->elf, ELF_C_WRITE) < 0) { + err = -errno; + pr_warn_elf("failed to write ELF contents"); + return libbpf_err(err); + } + + elf_end(linker->elf); + close(linker->fd); + + linker->elf = NULL; + linker->fd = -1; + + return 0; +} + +static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name, + size_t align, const void *raw_data, size_t raw_sz) +{ + Elf_Scn *scn; + Elf_Data *data; + Elf64_Shdr *shdr; + int name_off; + + name_off = strset__add_str(linker->strtab_strs, sec_name); + if (name_off < 0) + return name_off; + + scn = elf_newscn(linker->elf); + if (!scn) + return -ENOMEM; + data = elf_newdata(scn); + if (!data) + return -ENOMEM; + shdr = elf64_getshdr(scn); + if (!shdr) + return -EINVAL; + + shdr->sh_name = name_off; + shdr->sh_type = SHT_PROGBITS; + shdr->sh_flags = 0; + shdr->sh_size = raw_sz; + shdr->sh_link = 0; + shdr->sh_info = 0; + shdr->sh_addralign = align; + shdr->sh_entsize = 0; + + data->d_type = ELF_T_BYTE; + data->d_size = raw_sz; + data->d_buf = (void *)raw_data; + data->d_align = align; + data->d_off = 0; + + return 0; +} + +static int finalize_btf(struct bpf_linker *linker) +{ + LIBBPF_OPTS(btf_dedup_opts, opts); + struct btf *btf = linker->btf; + const void *raw_data; + int i, j, id, err; + __u32 raw_sz; + + /* bail out if no BTF data was produced */ + if (btf__type_cnt(linker->btf) == 1) + return 0; + + for (i = 1; i < linker->sec_cnt; i++) { + struct dst_sec *sec = &linker->secs[i]; + + if (!sec->has_btf) + continue; + + id = btf__add_datasec(btf, sec->sec_name, sec->sec_sz); + if (id < 0) { + pr_warn("failed to add consolidated BTF type for datasec '%s': %d\n", + sec->sec_name, id); + return id; + } + + for (j = 0; j < sec->sec_var_cnt; j++) { + struct btf_var_secinfo *vi = &sec->sec_vars[j]; + + if (btf__add_datasec_var_info(btf, vi->type, vi->offset, vi->size)) + return -EINVAL; + } + } + + err = finalize_btf_ext(linker); + if (err) { + pr_warn(".BTF.ext generation failed: %d\n", err); + return err; + } + + opts.btf_ext = linker->btf_ext; + err = btf__dedup(linker->btf, &opts); + if (err) { + pr_warn("BTF dedup failed: %d\n", err); + return err; + } + + /* Emit .BTF section */ + raw_data = btf__raw_data(linker->btf, &raw_sz); + if (!raw_data) + return -ENOMEM; + + err = emit_elf_data_sec(linker, BTF_ELF_SEC, 8, raw_data, raw_sz); + if (err) { + pr_warn("failed to write out .BTF ELF section: %d\n", err); + return err; + } + + /* Emit .BTF.ext section */ + if (linker->btf_ext) { + raw_data = btf_ext__get_raw_data(linker->btf_ext, &raw_sz); + if (!raw_data) + return -ENOMEM; + + err = emit_elf_data_sec(linker, BTF_EXT_ELF_SEC, 8, raw_data, raw_sz); + if (err) { + pr_warn("failed to write out .BTF.ext ELF section: %d\n", err); + return err; + } + } + + return 0; +} + +static int emit_btf_ext_data(struct bpf_linker *linker, void *output, + const char *sec_name, struct btf_ext_sec_data *sec_data) +{ + struct btf_ext_info_sec *sec_info; + void *cur = output; + int str_off; + size_t sz; + + if (!sec_data->rec_cnt) + return 0; + + str_off = btf__add_str(linker->btf, sec_name); + if (str_off < 0) + return -ENOMEM; + + sec_info = cur; + sec_info->sec_name_off = str_off; + sec_info->num_info = sec_data->rec_cnt; + cur += sizeof(struct btf_ext_info_sec); + + sz = sec_data->rec_cnt * sec_data->rec_sz; + memcpy(cur, sec_data->recs, sz); + cur += sz; + + return cur - output; +} + +static int finalize_btf_ext(struct bpf_linker *linker) +{ + size_t funcs_sz = 0, lines_sz = 0, core_relos_sz = 0, total_sz = 0; + size_t func_rec_sz = 0, line_rec_sz = 0, core_relo_rec_sz = 0; + struct btf_ext_header *hdr; + void *data, *cur; + int i, err, sz; + + /* validate that all sections have the same .BTF.ext record sizes + * and calculate total data size for each type of data (func info, + * line info, core relos) + */ + for (i = 1; i < linker->sec_cnt; i++) { + struct dst_sec *sec = &linker->secs[i]; + + if (sec->func_info.rec_cnt) { + if (func_rec_sz == 0) + func_rec_sz = sec->func_info.rec_sz; + if (func_rec_sz != sec->func_info.rec_sz) { + pr_warn("mismatch in func_info record size %zu != %u\n", + func_rec_sz, sec->func_info.rec_sz); + return -EINVAL; + } + + funcs_sz += sizeof(struct btf_ext_info_sec) + func_rec_sz * sec->func_info.rec_cnt; + } + if (sec->line_info.rec_cnt) { + if (line_rec_sz == 0) + line_rec_sz = sec->line_info.rec_sz; + if (line_rec_sz != sec->line_info.rec_sz) { + pr_warn("mismatch in line_info record size %zu != %u\n", + line_rec_sz, sec->line_info.rec_sz); + return -EINVAL; + } + + lines_sz += sizeof(struct btf_ext_info_sec) + line_rec_sz * sec->line_info.rec_cnt; + } + if (sec->core_relo_info.rec_cnt) { + if (core_relo_rec_sz == 0) + core_relo_rec_sz = sec->core_relo_info.rec_sz; + if (core_relo_rec_sz != sec->core_relo_info.rec_sz) { + pr_warn("mismatch in core_relo_info record size %zu != %u\n", + core_relo_rec_sz, sec->core_relo_info.rec_sz); + return -EINVAL; + } + + core_relos_sz += sizeof(struct btf_ext_info_sec) + core_relo_rec_sz * sec->core_relo_info.rec_cnt; + } + } + + if (!funcs_sz && !lines_sz && !core_relos_sz) + return 0; + + total_sz += sizeof(struct btf_ext_header); + if (funcs_sz) { + funcs_sz += sizeof(__u32); /* record size prefix */ + total_sz += funcs_sz; + } + if (lines_sz) { + lines_sz += sizeof(__u32); /* record size prefix */ + total_sz += lines_sz; + } + if (core_relos_sz) { + core_relos_sz += sizeof(__u32); /* record size prefix */ + total_sz += core_relos_sz; + } + + cur = data = calloc(1, total_sz); + if (!data) + return -ENOMEM; + + hdr = cur; + hdr->magic = BTF_MAGIC; + hdr->version = BTF_VERSION; + hdr->flags = 0; + hdr->hdr_len = sizeof(struct btf_ext_header); + cur += sizeof(struct btf_ext_header); + + /* All offsets are in bytes relative to the end of this header */ + hdr->func_info_off = 0; + hdr->func_info_len = funcs_sz; + hdr->line_info_off = funcs_sz; + hdr->line_info_len = lines_sz; + hdr->core_relo_off = funcs_sz + lines_sz; + hdr->core_relo_len = core_relos_sz; + + if (funcs_sz) { + *(__u32 *)cur = func_rec_sz; + cur += sizeof(__u32); + + for (i = 1; i < linker->sec_cnt; i++) { + struct dst_sec *sec = &linker->secs[i]; + + sz = emit_btf_ext_data(linker, cur, sec->sec_name, &sec->func_info); + if (sz < 0) { + err = sz; + goto out; + } + + cur += sz; + } + } + + if (lines_sz) { + *(__u32 *)cur = line_rec_sz; + cur += sizeof(__u32); + + for (i = 1; i < linker->sec_cnt; i++) { + struct dst_sec *sec = &linker->secs[i]; + + sz = emit_btf_ext_data(linker, cur, sec->sec_name, &sec->line_info); + if (sz < 0) { + err = sz; + goto out; + } + + cur += sz; + } + } + + if (core_relos_sz) { + *(__u32 *)cur = core_relo_rec_sz; + cur += sizeof(__u32); + + for (i = 1; i < linker->sec_cnt; i++) { + struct dst_sec *sec = &linker->secs[i]; + + sz = emit_btf_ext_data(linker, cur, sec->sec_name, &sec->core_relo_info); + if (sz < 0) { + err = sz; + goto out; + } + + cur += sz; + } + } + + linker->btf_ext = btf_ext__new(data, total_sz); + err = libbpf_get_error(linker->btf_ext); + if (err) { + linker->btf_ext = NULL; + pr_warn("failed to parse final .BTF.ext data: %d\n", err); + goto out; + } + +out: + free(data); + return err; +} diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c new file mode 100644 index 000000000..351045808 --- /dev/null +++ b/tools/lib/bpf/netlink.c @@ -0,0 +1,813 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include <stdlib.h> +#include <memory.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> +#include <linux/rtnetlink.h> +#include <sys/socket.h> +#include <errno.h> +#include <time.h> + +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" +#include "nlattr.h" + +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif + +typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); + +typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t, + void *cookie); + +struct xdp_link_info { + __u32 prog_id; + __u32 drv_prog_id; + __u32 hw_prog_id; + __u32 skb_prog_id; + __u8 attach_mode; +}; + +struct xdp_id_md { + int ifindex; + __u32 flags; + struct xdp_link_info info; +}; + +static int libbpf_netlink_open(__u32 *nl_pid) +{ + struct sockaddr_nl sa; + socklen_t addrlen; + int one = 1, ret; + int sock; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE); + if (sock < 0) + return -errno; + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + pr_warn("Netlink error reporting not supported\n"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + *nl_pid = sa.nl_pid; + return sock; + +cleanup: + close(sock); + return ret; +} + +static void libbpf_netlink_close(int sock) +{ + close(sock); +} + +enum { + NL_CONT, + NL_NEXT, + NL_DONE, +}; + +static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags) +{ + int len; + + do { + len = recvmsg(sock, mhdr, flags); + } while (len < 0 && (errno == EINTR || errno == EAGAIN)); + + if (len < 0) + return -errno; + return len; +} + +static int alloc_iov(struct iovec *iov, int len) +{ + void *nbuf; + + nbuf = realloc(iov->iov_base, len); + if (!nbuf) + return -ENOMEM; + + iov->iov_base = nbuf; + iov->iov_len = len; + return 0; +} + +static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, + __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct iovec iov = {}; + struct msghdr mhdr = { + .msg_iov = &iov, + .msg_iovlen = 1, + }; + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + int len, ret; + + ret = alloc_iov(&iov, 4096); + if (ret) + goto done; + + while (multipart) { +start: + multipart = false; + len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC); + if (len < 0) { + ret = len; + goto done; + } + + if (len > iov.iov_len) { + ret = alloc_iov(&iov, len); + if (ret) + goto done; + } + + len = netlink_recvmsg(sock, &mhdr, 0); + if (len < 0) { + ret = len; + goto done; + } + + if (len == 0) + break; + + for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto done; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto done; + } + if (nh->nlmsg_flags & NLM_F_MULTI) + multipart = true; + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + libbpf_nla_dump_errormsg(nh); + goto done; + case NLMSG_DONE: + ret = 0; + goto done; + default: + break; + } + if (_fn) { + ret = _fn(nh, fn, cookie); + switch (ret) { + case NL_CONT: + break; + case NL_NEXT: + goto start; + case NL_DONE: + ret = 0; + goto done; + default: + goto done; + } + } + } + } + ret = 0; +done: + free(iov.iov_base); + return ret; +} + +static int libbpf_netlink_send_recv(struct libbpf_nla_req *req, + __dump_nlmsg_t parse_msg, + libbpf_dump_nlmsg_t parse_attr, + void *cookie) +{ + __u32 nl_pid = 0; + int sock, ret; + + sock = libbpf_netlink_open(&nl_pid); + if (sock < 0) + return sock; + + req->nh.nlmsg_pid = 0; + req->nh.nlmsg_seq = time(NULL); + + if (send(sock, req, req->nh.nlmsg_len, 0) < 0) { + ret = -errno; + goto out; + } + + ret = libbpf_netlink_recv(sock, nl_pid, req->nh.nlmsg_seq, + parse_msg, parse_attr, cookie); +out: + libbpf_netlink_close(sock); + return ret; +} + +static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, + __u32 flags) +{ + struct nlattr *nla; + int ret; + struct libbpf_nla_req req; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; + req.ifinfo.ifi_family = AF_UNSPEC; + req.ifinfo.ifi_index = ifindex; + + nla = nlattr_begin_nested(&req, IFLA_XDP); + if (!nla) + return -EMSGSIZE; + ret = nlattr_add(&req, IFLA_XDP_FD, &fd, sizeof(fd)); + if (ret < 0) + return ret; + if (flags) { + ret = nlattr_add(&req, IFLA_XDP_FLAGS, &flags, sizeof(flags)); + if (ret < 0) + return ret; + } + if (flags & XDP_FLAGS_REPLACE) { + ret = nlattr_add(&req, IFLA_XDP_EXPECTED_FD, &old_fd, + sizeof(old_fd)); + if (ret < 0) + return ret; + } + nlattr_end_nested(&req, nla); + + return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); +} + +int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + int old_prog_fd, err; + + if (!OPTS_VALID(opts, bpf_xdp_attach_opts)) + return libbpf_err(-EINVAL); + + old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + if (old_prog_fd) + flags |= XDP_FLAGS_REPLACE; + else + old_prog_fd = -1; + + err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags); + return libbpf_err(err); +} + +int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + return bpf_xdp_attach(ifindex, -1, flags, opts); +} + +static int __dump_link_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct nlattr *tb[IFLA_MAX + 1], *attr; + struct ifinfomsg *ifi = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); + attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_link_nlmsg(cookie, ifi, 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; + int ret; + + if (xdp_id->ifindex && xdp_id->ifindex != ifinfo->ifi_index) + return 0; + + if (!tb[IFLA_XDP]) + return 0; + + ret = libbpf_nla_parse_nested(xdp_tb, IFLA_XDP_MAX, tb[IFLA_XDP], NULL); + if (ret) + return ret; + + if (!xdp_tb[IFLA_XDP_ATTACHED]) + return 0; + + xdp_id->info.attach_mode = libbpf_nla_getattr_u8( + xdp_tb[IFLA_XDP_ATTACHED]); + + if (xdp_id->info.attach_mode == XDP_ATTACHED_NONE) + return 0; + + 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_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) +{ + struct libbpf_nla_req req = { + .nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nh.nlmsg_type = RTM_GETLINK, + .nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifinfo.ifi_family = AF_PACKET, + }; + struct xdp_id_md xdp_id = {}; + int err; + + if (!OPTS_VALID(opts, bpf_xdp_query_opts)) + return libbpf_err(-EINVAL); + + if (xdp_flags & ~XDP_FLAGS_MASK) + return libbpf_err(-EINVAL); + + /* Check whether the single {HW,DRV,SKB} mode is set */ + xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE; + if (xdp_flags & (xdp_flags - 1)) + return libbpf_err(-EINVAL); + + xdp_id.ifindex = ifindex; + xdp_id.flags = xdp_flags; + + err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + get_xdp_info, &xdp_id); + if (err) + return libbpf_err(err); + + OPTS_SET(opts, prog_id, xdp_id.info.prog_id); + OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id); + OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id); + OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); + OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); + + return 0; +} + +int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + int ret; + + ret = bpf_xdp_query(ifindex, flags, &opts); + if (ret) + return libbpf_err(ret); + + flags &= XDP_FLAGS_MODES; + + if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags) + *prog_id = opts.prog_id; + else if (flags & XDP_FLAGS_DRV_MODE) + *prog_id = opts.drv_prog_id; + else if (flags & XDP_FLAGS_HW_MODE) + *prog_id = opts.hw_prog_id; + else if (flags & XDP_FLAGS_SKB_MODE) + *prog_id = opts.skb_prog_id; + else + *prog_id = 0; + + return 0; +} + + +typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); + +static int clsact_config(struct libbpf_nla_req *req) +{ + req->tc.tcm_parent = TC_H_CLSACT; + req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0); + + return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact")); +} + +static int attach_point_to_config(struct bpf_tc_hook *hook, + qdisc_config_t *config) +{ + switch (OPTS_GET(hook, attach_point, 0)) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + case BPF_TC_INGRESS | BPF_TC_EGRESS: + if (OPTS_GET(hook, parent, 0)) + return -EINVAL; + *config = &clsact_config; + return 0; + case BPF_TC_CUSTOM: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +static int tc_get_tcm_parent(enum bpf_tc_attach_point attach_point, + __u32 *parent) +{ + switch (attach_point) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + if (*parent) + return -EINVAL; + *parent = TC_H_MAKE(TC_H_CLSACT, + attach_point == BPF_TC_INGRESS ? + TC_H_MIN_INGRESS : TC_H_MIN_EGRESS); + break; + case BPF_TC_CUSTOM: + if (!*parent) + return -EINVAL; + break; + default: + return -EINVAL; + } + return 0; +} + +static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) +{ + qdisc_config_t config; + int ret; + struct libbpf_nla_req req; + + ret = attach_point_to_config(hook, &config); + if (ret < 0) + return ret; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags; + req.nh.nlmsg_type = cmd; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0); + + ret = config(&req); + if (ret < 0) + return ret; + + return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); +} + +static int tc_qdisc_create_excl(struct bpf_tc_hook *hook) +{ + return tc_qdisc_modify(hook, RTM_NEWQDISC, NLM_F_CREATE | NLM_F_EXCL); +} + +static int tc_qdisc_delete(struct bpf_tc_hook *hook) +{ + return tc_qdisc_modify(hook, RTM_DELQDISC, 0); +} + +int bpf_tc_hook_create(struct bpf_tc_hook *hook) +{ + int ret; + + if (!hook || !OPTS_VALID(hook, bpf_tc_hook) || + OPTS_GET(hook, ifindex, 0) <= 0) + return libbpf_err(-EINVAL); + + ret = tc_qdisc_create_excl(hook); + return libbpf_err(ret); +} + +static int __bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts, + const bool flush); + +int bpf_tc_hook_destroy(struct bpf_tc_hook *hook) +{ + if (!hook || !OPTS_VALID(hook, bpf_tc_hook) || + OPTS_GET(hook, ifindex, 0) <= 0) + return libbpf_err(-EINVAL); + + switch (OPTS_GET(hook, attach_point, 0)) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + return libbpf_err(__bpf_tc_detach(hook, NULL, true)); + case BPF_TC_INGRESS | BPF_TC_EGRESS: + return libbpf_err(tc_qdisc_delete(hook)); + case BPF_TC_CUSTOM: + return libbpf_err(-EOPNOTSUPP); + default: + return libbpf_err(-EINVAL); + } +} + +struct bpf_cb_ctx { + struct bpf_tc_opts *opts; + bool processed; +}; + +static int __get_tc_info(void *cookie, struct tcmsg *tc, struct nlattr **tb, + bool unicast) +{ + struct nlattr *tbb[TCA_BPF_MAX + 1]; + struct bpf_cb_ctx *info = cookie; + + if (!info || !info->opts) + return -EINVAL; + if (unicast && info->processed) + return -EINVAL; + if (!tb[TCA_OPTIONS]) + return NL_CONT; + + libbpf_nla_parse_nested(tbb, TCA_BPF_MAX, tb[TCA_OPTIONS], NULL); + if (!tbb[TCA_BPF_ID]) + return -EINVAL; + + OPTS_SET(info->opts, prog_id, libbpf_nla_getattr_u32(tbb[TCA_BPF_ID])); + OPTS_SET(info->opts, handle, tc->tcm_handle); + OPTS_SET(info->opts, priority, TC_H_MAJ(tc->tcm_info) >> 16); + + info->processed = true; + return unicast ? NL_NEXT : NL_DONE; +} + +static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct tcmsg *tc = NLMSG_DATA(nh); + struct nlattr *tb[TCA_MAX + 1]; + + libbpf_nla_parse(tb, TCA_MAX, + (struct nlattr *)((void *)tc + NLMSG_ALIGN(sizeof(*tc))), + NLMSG_PAYLOAD(nh, sizeof(*tc)), NULL); + if (!tb[TCA_KIND]) + return NL_CONT; + return __get_tc_info(cookie, tc, tb, nh->nlmsg_flags & NLM_F_ECHO); +} + +static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd) +{ + struct bpf_prog_info info; + __u32 info_len = sizeof(info); + char name[256]; + int len, ret; + + memset(&info, 0, info_len); + ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (ret < 0) + return ret; + + ret = nlattr_add(req, TCA_BPF_FD, &fd, sizeof(fd)); + if (ret < 0) + return ret; + len = snprintf(name, sizeof(name), "%s:[%u]", info.name, info.id); + if (len < 0) + return -errno; + if (len >= sizeof(name)) + return -ENAMETOOLONG; + return nlattr_add(req, TCA_BPF_NAME, name, len + 1); +} + +int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) +{ + __u32 protocol, bpf_flags, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct bpf_cb_ctx info = {}; + struct libbpf_nla_req req; + struct nlattr *nla; + + if (!hook || !opts || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return libbpf_err(-EINVAL); + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || !prog_fd || prog_id) + return libbpf_err(-EINVAL); + if (priority > UINT16_MAX) + return libbpf_err(-EINVAL); + if (flags & ~BPF_TC_F_REPLACE) + return libbpf_err(-EINVAL); + + flags = (flags & BPF_TC_F_REPLACE) ? NLM_F_REPLACE : NLM_F_EXCL; + protocol = ETH_P_ALL; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE | + NLM_F_ECHO | flags; + req.nh.nlmsg_type = RTM_NEWTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return libbpf_err(ret); + req.tc.tcm_parent = parent; + + ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return libbpf_err(ret); + nla = nlattr_begin_nested(&req, TCA_OPTIONS); + if (!nla) + return libbpf_err(-EMSGSIZE); + ret = tc_add_fd_and_name(&req, prog_fd); + if (ret < 0) + return libbpf_err(ret); + bpf_flags = TCA_BPF_FLAG_ACT_DIRECT; + ret = nlattr_add(&req, TCA_BPF_FLAGS, &bpf_flags, sizeof(bpf_flags)); + if (ret < 0) + return libbpf_err(ret); + nlattr_end_nested(&req, nla); + + info.opts = opts; + + ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + if (ret < 0) + return libbpf_err(ret); + if (!info.processed) + return libbpf_err(-ENOENT); + return ret; +} + +static int __bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts, + const bool flush) +{ + __u32 protocol = 0, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct libbpf_nla_req req; + + if (!hook || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return -EINVAL; + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || flags || prog_fd || prog_id) + return -EINVAL; + if (priority > UINT16_MAX) + return -EINVAL; + if (!flush) { + if (!handle || !priority) + return -EINVAL; + protocol = ETH_P_ALL; + } else { + if (handle || priority) + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_DELTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + if (!flush) { + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + } + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return ret; + req.tc.tcm_parent = parent; + + if (!flush) { + ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return ret; + } + + return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); +} + +int bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts) +{ + int ret; + + if (!opts) + return libbpf_err(-EINVAL); + + ret = __bpf_tc_detach(hook, opts, false); + return libbpf_err(ret); +} + +int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) +{ + __u32 protocol, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct bpf_cb_ctx info = {}; + struct libbpf_nla_req req; + + if (!hook || !opts || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return libbpf_err(-EINVAL); + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || flags || prog_fd || prog_id || + !handle || !priority) + return libbpf_err(-EINVAL); + if (priority > UINT16_MAX) + return libbpf_err(-EINVAL); + + protocol = ETH_P_ALL; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_type = RTM_GETTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return libbpf_err(ret); + req.tc.tcm_parent = parent; + + ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return libbpf_err(ret); + + info.opts = opts; + + ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + if (ret < 0) + return libbpf_err(ret); + if (!info.processed) + return libbpf_err(-ENOENT); + return ret; +} diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c new file mode 100644 index 000000000..975e265ea --- /dev/null +++ b/tools/lib/bpf/nlattr.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * NETLINK Netlink attributes + * + * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch> + */ + +#include <errno.h> +#include <string.h> +#include <stdio.h> +#include <linux/rtnetlink.h> +#include "nlattr.h" +#include "libbpf_internal.h" + +static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = { + [LIBBPF_NLA_U8] = sizeof(uint8_t), + [LIBBPF_NLA_U16] = sizeof(uint16_t), + [LIBBPF_NLA_U32] = sizeof(uint32_t), + [LIBBPF_NLA_U64] = sizeof(uint64_t), + [LIBBPF_NLA_STRING] = 1, + [LIBBPF_NLA_FLAG] = 0, +}; + +static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) +{ + int totlen = NLA_ALIGN(nla->nla_len); + + *remaining -= totlen; + return (struct nlattr *)((void *)nla + totlen); +} + +static int nla_ok(const struct nlattr *nla, int remaining) +{ + return remaining >= (int)sizeof(*nla) && + nla->nla_len >= sizeof(*nla) && + nla->nla_len <= remaining; +} + +static int nla_type(const struct nlattr *nla) +{ + return nla->nla_type & NLA_TYPE_MASK; +} + +static int validate_nla(struct nlattr *nla, int maxtype, + struct libbpf_nla_policy *policy) +{ + struct libbpf_nla_policy *pt; + unsigned int minlen = 0; + int type = nla_type(nla); + + if (type < 0 || type > maxtype) + return 0; + + pt = &policy[type]; + + if (pt->type > LIBBPF_NLA_TYPE_MAX) + return 0; + + if (pt->minlen) + minlen = pt->minlen; + else if (pt->type != LIBBPF_NLA_UNSPEC) + minlen = nla_attr_minlen[pt->type]; + + if (libbpf_nla_len(nla) < minlen) + return -1; + + if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen) + return -1; + + if (pt->type == LIBBPF_NLA_STRING) { + char *data = libbpf_nla_data(nla); + + if (data[libbpf_nla_len(nla) - 1] != '\0') + return -1; + } + + return 0; +} + +static inline int nlmsg_len(const struct nlmsghdr *nlh) +{ + return nlh->nlmsg_len - NLMSG_HDRLEN; +} + +/** + * Create attribute index based on a stream of attributes. + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg head Head of attribute stream. + * @arg len Length of attribute stream. + * @arg policy Attribute validation policy. + * + * Iterates over the stream of attributes and stores a pointer to each + * attribute in the index array using the attribute type as index to + * the array. Attribute with a type greater than the maximum type + * specified will be silently ignored in order to maintain backwards + * compatibility. If \a policy is not NULL, the attribute will be + * validated using the specified policy. + * + * @see nla_validate + * @return 0 on success or a negative error code. + */ +int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, + int len, struct libbpf_nla_policy *policy) +{ + struct nlattr *nla; + int rem, err; + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + + libbpf_nla_for_each_attr(nla, head, len, rem) { + int type = nla_type(nla); + + if (type > maxtype) + continue; + + if (policy) { + err = validate_nla(nla, maxtype, policy); + if (err < 0) + goto errout; + } + + if (tb[type]) + pr_warn("Attribute of type %#x found multiple times in message, " + "previous attribute is being ignored.\n", type); + + tb[type] = nla; + } + + err = 0; +errout: + return err; +} + +/** + * Create attribute index based on nested attribute + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg nla Nested Attribute. + * @arg policy Attribute validation policy. + * + * Feeds the stream of attributes nested into the specified attribute + * to libbpf_nla_parse(). + * + * @see libbpf_nla_parse + * @return 0 on success or a negative error code. + */ +int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype, + struct nlattr *nla, + struct libbpf_nla_policy *policy) +{ + return libbpf_nla_parse(tb, maxtype, libbpf_nla_data(nla), + libbpf_nla_len(nla), policy); +} + +/* dump netlink extended ack error message */ +int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) +{ + struct libbpf_nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = { + [NLMSGERR_ATTR_MSG] = { .type = LIBBPF_NLA_STRING }, + [NLMSGERR_ATTR_OFFS] = { .type = LIBBPF_NLA_U32 }, + }; + struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr; + struct nlmsgerr *err; + char *errmsg = NULL; + int hlen, alen; + + /* no TLVs, nothing to do here */ + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 0; + + err = (struct nlmsgerr *)NLMSG_DATA(nlh); + hlen = sizeof(*err); + + /* if NLM_F_CAPPED is set then the inner err msg was capped */ + if (!(nlh->nlmsg_flags & NLM_F_CAPPED)) + hlen += nlmsg_len(&err->msg); + + attr = (struct nlattr *) ((void *) err + hlen); + alen = (void *)nlh + nlh->nlmsg_len - (void *)attr; + + if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, + extack_policy) != 0) { + 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]); + + pr_warn("Kernel error message: %s\n", errmsg); + + return 0; +} diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h new file mode 100644 index 000000000..4d15ae2ff --- /dev/null +++ b/tools/lib/bpf/nlattr.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * NETLINK Netlink attributes + * + * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch> + */ + +#ifndef __LIBBPF_NLATTR_H +#define __LIBBPF_NLATTR_H + +#include <stdint.h> +#include <string.h> +#include <errno.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> + +/* avoid multiple definition of netlink features */ +#define __LINUX_NETLINK_H + +/** + * Standard attribute types to specify validation policy + */ +enum { + LIBBPF_NLA_UNSPEC, /**< Unspecified type, binary data chunk */ + LIBBPF_NLA_U8, /**< 8 bit integer */ + LIBBPF_NLA_U16, /**< 16 bit integer */ + LIBBPF_NLA_U32, /**< 32 bit integer */ + LIBBPF_NLA_U64, /**< 64 bit integer */ + LIBBPF_NLA_STRING, /**< NUL terminated character string */ + LIBBPF_NLA_FLAG, /**< Flag */ + LIBBPF_NLA_MSECS, /**< Micro seconds (64bit) */ + LIBBPF_NLA_NESTED, /**< Nested attributes */ + __LIBBPF_NLA_TYPE_MAX, +}; + +#define LIBBPF_NLA_TYPE_MAX (__LIBBPF_NLA_TYPE_MAX - 1) + +/** + * @ingroup attr + * Attribute validation policy. + * + * See section @core_doc{core_attr_parse,Attribute Parsing} for more details. + */ +struct libbpf_nla_policy { + /** Type of attribute or LIBBPF_NLA_UNSPEC */ + uint16_t type; + + /** Minimal length of payload required */ + uint16_t minlen; + + /** Maximal length of payload allowed */ + uint16_t maxlen; +}; + +struct libbpf_nla_req { + struct nlmsghdr nh; + union { + struct ifinfomsg ifinfo; + struct tcmsg tc; + }; + char buf[128]; +}; + +/** + * @ingroup attr + * Iterate over a stream of attributes + * @arg pos loop counter, set to current attribute + * @arg head head of attribute stream + * @arg len length of attribute stream + * @arg rem initialized to len, holds bytes currently remaining in stream + */ +#define libbpf_nla_for_each_attr(pos, head, len, rem) \ + for (pos = head, rem = len; \ + nla_ok(pos, rem); \ + pos = nla_next(pos, &(rem))) + +/** + * libbpf_nla_data - head of payload + * @nla: netlink attribute + */ +static inline void *libbpf_nla_data(const struct nlattr *nla) +{ + return (void *)nla + NLA_HDRLEN; +} + +static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla) +{ + return *(uint8_t *)libbpf_nla_data(nla); +} + +static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla) +{ + return *(uint32_t *)libbpf_nla_data(nla); +} + +static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla) +{ + return (const char *)libbpf_nla_data(nla); +} + +/** + * libbpf_nla_len - length of payload + * @nla: netlink attribute + */ +static inline int libbpf_nla_len(const struct nlattr *nla) +{ + return nla->nla_len - NLA_HDRLEN; +} + +int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, + int len, struct libbpf_nla_policy *policy); +int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype, + struct nlattr *nla, + struct libbpf_nla_policy *policy); + +int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh); + +static inline struct nlattr *nla_data(struct nlattr *nla) +{ + return (struct nlattr *)((void *)nla + NLA_HDRLEN); +} + +static inline struct nlattr *req_tail(struct libbpf_nla_req *req) +{ + return (struct nlattr *)((void *)req + NLMSG_ALIGN(req->nh.nlmsg_len)); +} + +static inline int nlattr_add(struct libbpf_nla_req *req, int type, + const void *data, int len) +{ + struct nlattr *nla; + + if (NLMSG_ALIGN(req->nh.nlmsg_len) + NLA_ALIGN(NLA_HDRLEN + len) > sizeof(*req)) + return -EMSGSIZE; + if (!!data != !!len) + return -EINVAL; + + nla = req_tail(req); + nla->nla_type = type; + nla->nla_len = NLA_HDRLEN + len; + if (data) + memcpy(nla_data(nla), data, len); + req->nh.nlmsg_len = NLMSG_ALIGN(req->nh.nlmsg_len) + NLA_ALIGN(nla->nla_len); + return 0; +} + +static inline struct nlattr *nlattr_begin_nested(struct libbpf_nla_req *req, int type) +{ + struct nlattr *tail; + + tail = req_tail(req); + if (nlattr_add(req, type | NLA_F_NESTED, NULL, 0)) + return NULL; + return tail; +} + +static inline void nlattr_end_nested(struct libbpf_nla_req *req, + struct nlattr *tail) +{ + tail->nla_len = (void *)req_tail(req) - (void *)tail; +} + +#endif /* __LIBBPF_NLATTR_H */ diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c new file mode 100644 index 000000000..c4b0e81ae --- /dev/null +++ b/tools/lib/bpf/relo_core.c @@ -0,0 +1,1690 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2019 Facebook */ + +#ifdef __KERNEL__ +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/string.h> +#include <linux/bpf_verifier.h> +#include "relo_core.h" + +static const char *btf_kind_str(const struct btf_type *t) +{ + return btf_type_str(t); +} + +static bool is_ldimm64_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id) +{ + return btf_type_skip_modifiers(btf, id, res_id); +} + +static const char *btf__name_by_offset(const struct btf *btf, u32 offset) +{ + return btf_name_by_offset(btf, offset); +} + +static s64 btf__resolve_size(const struct btf *btf, u32 type_id) +{ + const struct btf_type *t; + int size; + + t = btf_type_by_id(btf, type_id); + t = btf_resolve_size(btf, t, &size); + if (IS_ERR(t)) + return PTR_ERR(t); + return size; +} + +enum libbpf_print_level { + LIBBPF_WARN, + LIBBPF_INFO, + LIBBPF_DEBUG, +}; + +#undef pr_warn +#undef pr_info +#undef pr_debug +#define pr_warn(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_info(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_debug(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define libbpf_print(level, fmt, ...) bpf_log((void *)prog_name, fmt, ##__VA_ARGS__) +#else +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <ctype.h> +#include <linux/err.h> + +#include "libbpf.h" +#include "bpf.h" +#include "btf.h" +#include "str_error.h" +#include "libbpf_internal.h" +#endif + +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; +} + +static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) +{ + switch (kind) { + case BPF_CORE_FIELD_BYTE_OFFSET: return "byte_off"; + case BPF_CORE_FIELD_BYTE_SIZE: return "byte_sz"; + case BPF_CORE_FIELD_EXISTS: return "field_exists"; + case BPF_CORE_FIELD_SIGNED: return "signed"; + case BPF_CORE_FIELD_LSHIFT_U64: return "lshift_u64"; + case BPF_CORE_FIELD_RSHIFT_U64: return "rshift_u64"; + case BPF_CORE_TYPE_ID_LOCAL: return "local_type_id"; + case BPF_CORE_TYPE_ID_TARGET: return "target_type_id"; + case BPF_CORE_TYPE_EXISTS: return "type_exists"; + case BPF_CORE_TYPE_MATCHES: return "type_matches"; + case BPF_CORE_TYPE_SIZE: return "type_size"; + case BPF_CORE_ENUMVAL_EXISTS: return "enumval_exists"; + case BPF_CORE_ENUMVAL_VALUE: return "enumval_value"; + default: return "unknown"; + } +} + +static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) +{ + switch (kind) { + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: + return true; + default: + return false; + } +} + +static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) +{ + switch (kind) { + case BPF_CORE_TYPE_ID_LOCAL: + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_MATCHES: + case BPF_CORE_TYPE_SIZE: + return true; + default: + return false; + } +} + +static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) +{ + switch (kind) { + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: + return true; + default: + return false; + } +} + +int __bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id, int level) +{ + const struct btf_type *local_type, *targ_type; + int depth = 32; /* max recursion depth */ + + /* caller made sure that names match (ignoring flavor suffix) */ + local_type = btf_type_by_id(local_btf, local_id); + targ_type = btf_type_by_id(targ_btf, targ_id); + if (!btf_kind_core_compat(local_type, targ_type)) + return 0; + +recur: + depth--; + if (depth < 0) + return -EINVAL; + + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (!btf_kind_core_compat(local_type, targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + case BTF_KIND_ENUM64: + return 1; + case BTF_KIND_INT: + /* just reject deprecated bitfield-like integers; all other + * integers are by default compatible between each other + */ + return btf_int_offset(local_type) == 0 && btf_int_offset(targ_type) == 0; + case BTF_KIND_PTR: + local_id = local_type->type; + targ_id = targ_type->type; + goto recur; + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + case BTF_KIND_FUNC_PROTO: { + struct btf_param *local_p = btf_params(local_type); + struct btf_param *targ_p = btf_params(targ_type); + __u16 local_vlen = btf_vlen(local_type); + __u16 targ_vlen = btf_vlen(targ_type); + int i, err; + + if (local_vlen != targ_vlen) + return 0; + + for (i = 0; i < local_vlen; i++, local_p++, targ_p++) { + if (level <= 0) + return -EINVAL; + + skip_mods_and_typedefs(local_btf, local_p->type, &local_id); + skip_mods_and_typedefs(targ_btf, targ_p->type, &targ_id); + err = __bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id, + level - 1); + if (err <= 0) + return err; + } + + /* tail recurse for return type check */ + skip_mods_and_typedefs(local_btf, local_type->type, &local_id); + skip_mods_and_typedefs(targ_btf, targ_type->type, &targ_id); + goto recur; + } + default: + pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n", + btf_kind_str(local_type), local_id, targ_id); + return 0; + } +} + +/* + * Turn bpf_core_relo into a low- and high-level spec representation, + * validating correctness along the way, as well as calculating resulting + * 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: + * - initial zero-index access by pointer (&s->... is the same as &s[0]...); + * - field 'a' access (corresponds to '2' in low-level spec); + * - array element #3 access (corresponds to '3' in low-level spec). + * + * Type-based relocations (TYPE_EXISTS/TYPE_MATCHES/TYPE_SIZE, + * TYPE_ID_LOCAL/TYPE_ID_TARGET) don't capture any field information. Their + * spec and raw_spec are kept empty. + * + * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access + * string to specify enumerator's value index that need to be relocated. + */ +int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, + const struct bpf_core_relo *relo, + struct bpf_core_spec *spec) +{ + int access_idx, parsed_len, i; + struct bpf_core_accessor *acc; + const struct btf_type *t; + const char *name, *spec_str; + __u32 id, name_off; + __s64 sz; + + spec_str = btf__name_by_offset(btf, relo->access_str_off); + if (str_is_empty(spec_str) || *spec_str == ':') + return -EINVAL; + + memset(spec, 0, sizeof(*spec)); + spec->btf = btf; + spec->root_type_id = relo->type_id; + spec->relo_kind = relo->kind; + + /* type-based relocations don't have a field access string */ + if (core_relo_is_type_based(relo->kind)) { + if (strcmp(spec_str, "0")) + return -EINVAL; + return 0; + } + + /* 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; + + t = skip_mods_and_typedefs(btf, relo->type_id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[0]; + acc = &spec->spec[0]; + acc->type_id = id; + acc->idx = access_idx; + spec->len++; + + if (core_relo_is_enumval_based(relo->kind)) { + if (!btf_is_any_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t)) + return -EINVAL; + + /* record enumerator name in a first accessor */ + name_off = btf_is_enum(t) ? btf_enum(t)[access_idx].name_off + : btf_enum64(t)[access_idx].name_off; + acc->name = btf__name_by_offset(btf, name_off); + return 0; + } + + if (!core_relo_is_field_based(relo->kind)) + return -EINVAL; + + 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("prog '%s': relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", + prog_name, relo->type_id, spec_str, i, id, btf_kind_str(t)); + return -EINVAL; + } + } + + return 0; +} + +/* Check two types for compatibility for the purpose of field access + * relocation. const/volatile/restrict and typedefs are skipped to ensure we + * are relocating semantically 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; + * - any two FLOATs are always compatible; + * - 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_core_compat(local_type, targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_PTR: + case BTF_KIND_FLOAT: + return 1; + case BTF_KIND_FWD: + case BTF_KIND_ENUM64: + case BTF_KIND_ENUM: { + const char *local_name, *targ_name; + size_t local_len, targ_len; + + 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: + 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; + __u32 name_off; + + memset(targ_spec, 0, sizeof(*targ_spec)); + targ_spec->btf = targ_btf; + targ_spec->root_type_id = targ_id; + targ_spec->relo_kind = local_spec->relo_kind; + + if (core_relo_is_type_based(local_spec->relo_kind)) { + if (local_spec->relo_kind == BPF_CORE_TYPE_MATCHES) + return bpf_core_types_match(local_spec->btf, + local_spec->root_type_id, + targ_btf, targ_id); + else + return bpf_core_types_are_compat(local_spec->btf, + local_spec->root_type_id, + targ_btf, targ_id); + } + + local_acc = &local_spec->spec[0]; + targ_acc = &targ_spec->spec[0]; + + if (core_relo_is_enumval_based(local_spec->relo_kind)) { + size_t local_essent_len, targ_essent_len; + const char *targ_name; + + /* has to resolve to an enum */ + targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, &targ_id); + if (!btf_is_any_enum(targ_type)) + return 0; + + local_essent_len = bpf_core_essential_name_len(local_acc->name); + + for (i = 0; i < btf_vlen(targ_type); i++) { + if (btf_is_enum(targ_type)) + name_off = btf_enum(targ_type)[i].name_off; + else + name_off = btf_enum64(targ_type)[i].name_off; + + targ_name = btf__name_by_offset(targ_spec->btf, name_off); + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != local_essent_len) + continue; + if (strncmp(local_acc->name, targ_name, local_essent_len) == 0) { + targ_acc->type_id = targ_id; + targ_acc->idx = i; + targ_acc->name = targ_name; + targ_spec->len++; + targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx; + targ_spec->raw_len++; + return 1; + } + } + return 0; + } + + if (!core_relo_is_field_based(local_spec->relo_kind)) + return -EINVAL; + + 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 char *prog_name, + const struct bpf_core_relo *relo, + const struct bpf_core_spec *spec, + __u64 *val, __u32 *field_sz, __u32 *type_id, + bool *validate) +{ + const struct bpf_core_accessor *acc; + const struct btf_type *t; + __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id; + const struct btf_member *m; + const struct btf_type *mt; + bool bitfield; + __s64 sz; + + *field_sz = 0; + + if (relo->kind == BPF_CORE_FIELD_EXISTS) { + *val = spec ? 1 : 0; + return 0; + } + + if (!spec) + return -EUCLEAN; /* request instruction poisoning */ + + acc = &spec->spec[spec->len - 1]; + t = btf_type_by_id(spec->btf, acc->type_id); + + /* a[n] accessor needs special handling */ + if (!acc->name) { + if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) { + *val = spec->bit_offset / 8; + /* remember field size for load/store mem size */ + sz = btf__resolve_size(spec->btf, acc->type_id); + if (sz < 0) + return -EINVAL; + *field_sz = sz; + *type_id = acc->type_id; + } else if (relo->kind == BPF_CORE_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", + prog_name, 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, &field_type_id); + 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", + prog_name, 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, field_type_id); + 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_CORE_FIELD_BYTE_OFFSET: + *val = byte_off; + if (!bitfield) { + *field_sz = byte_sz; + *type_id = field_type_id; + } + break; + case BPF_CORE_FIELD_BYTE_SIZE: + *val = byte_sz; + break; + case BPF_CORE_FIELD_SIGNED: + *val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) || + (btf_int_encoding(mt) & BTF_INT_SIGNED); + if (validate) + *validate = true; /* signedness is never ambiguous */ + break; + case BPF_CORE_FIELD_LSHIFT_U64: +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + *val = 64 - (bit_off + bit_sz - byte_off * 8); +#else + *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8); +#endif + break; + case BPF_CORE_FIELD_RSHIFT_U64: + *val = 64 - bit_sz; + if (validate) + *validate = true; /* right shift is never ambiguous */ + break; + case BPF_CORE_FIELD_EXISTS: + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, + const struct bpf_core_spec *spec, + __u64 *val, bool *validate) +{ + __s64 sz; + + /* by default, always check expected value in bpf_insn */ + if (validate) + *validate = true; + + /* type-based relos return zero when target type is not found */ + if (!spec) { + *val = 0; + return 0; + } + + switch (relo->kind) { + case BPF_CORE_TYPE_ID_TARGET: + *val = spec->root_type_id; + /* type ID, embedded in bpf_insn, might change during linking, + * so enforcing it is pointless + */ + if (validate) + *validate = false; + break; + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_MATCHES: + *val = 1; + break; + case BPF_CORE_TYPE_SIZE: + sz = btf__resolve_size(spec->btf, spec->root_type_id); + if (sz < 0) + return -EINVAL; + *val = sz; + break; + case BPF_CORE_TYPE_ID_LOCAL: + /* BPF_CORE_TYPE_ID_LOCAL is handled specially and shouldn't get here */ + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, + const struct bpf_core_spec *spec, + __u64 *val) +{ + const struct btf_type *t; + + switch (relo->kind) { + case BPF_CORE_ENUMVAL_EXISTS: + *val = spec ? 1 : 0; + break; + case BPF_CORE_ENUMVAL_VALUE: + if (!spec) + return -EUCLEAN; /* request instruction poisoning */ + t = btf_type_by_id(spec->btf, spec->spec[0].type_id); + if (btf_is_enum(t)) + *val = btf_enum(t)[spec->spec[0].idx].val; + else + *val = btf_enum64_value(btf_enum64(t) + spec->spec[0].idx); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +/* Calculate original and target relocation values, given local and target + * specs and relocation kind. These values are calculated for each candidate. + * If there are multiple candidates, resulting values should all be consistent + * with each other. Otherwise, libbpf will refuse to proceed due to ambiguity. + * If instruction has to be poisoned, *poison will be set to true. + */ +static int bpf_core_calc_relo(const char *prog_name, + const struct bpf_core_relo *relo, + int relo_idx, + const struct bpf_core_spec *local_spec, + const struct bpf_core_spec *targ_spec, + struct bpf_core_relo_res *res) +{ + int err = -EOPNOTSUPP; + + res->orig_val = 0; + res->new_val = 0; + res->poison = false; + res->validate = true; + res->fail_memsz_adjust = false; + res->orig_sz = res->new_sz = 0; + res->orig_type_id = res->new_type_id = 0; + + if (core_relo_is_field_based(relo->kind)) { + err = bpf_core_calc_field_relo(prog_name, relo, local_spec, + &res->orig_val, &res->orig_sz, + &res->orig_type_id, &res->validate); + err = err ?: bpf_core_calc_field_relo(prog_name, relo, targ_spec, + &res->new_val, &res->new_sz, + &res->new_type_id, NULL); + if (err) + goto done; + /* Validate if it's safe to adjust load/store memory size. + * Adjustments are performed only if original and new memory + * sizes differ. + */ + res->fail_memsz_adjust = false; + if (res->orig_sz != res->new_sz) { + const struct btf_type *orig_t, *new_t; + + orig_t = btf_type_by_id(local_spec->btf, res->orig_type_id); + new_t = btf_type_by_id(targ_spec->btf, res->new_type_id); + + /* There are two use cases in which it's safe to + * adjust load/store's mem size: + * - reading a 32-bit kernel pointer, while on BPF + * size pointers are always 64-bit; in this case + * it's safe to "downsize" instruction size due to + * pointer being treated as unsigned integer with + * zero-extended upper 32-bits; + * - reading unsigned integers, again due to + * zero-extension is preserving the value correctly. + * + * In all other cases it's incorrect to attempt to + * load/store field because read value will be + * incorrect, so we poison relocated instruction. + */ + if (btf_is_ptr(orig_t) && btf_is_ptr(new_t)) + goto done; + if (btf_is_int(orig_t) && btf_is_int(new_t) && + btf_int_encoding(orig_t) != BTF_INT_SIGNED && + btf_int_encoding(new_t) != BTF_INT_SIGNED) + goto done; + + /* mark as invalid mem size adjustment, but this will + * only be checked for LDX/STX/ST insns + */ + res->fail_memsz_adjust = true; + } + } else if (core_relo_is_type_based(relo->kind)) { + err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val, &res->validate); + err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val, NULL); + } else if (core_relo_is_enumval_based(relo->kind)) { + err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val); + err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val); + } + +done: + if (err == -EUCLEAN) { + /* EUCLEAN is used to signal instruction poisoning request */ + res->poison = true; + err = 0; + } else if (err == -EOPNOTSUPP) { + /* EOPNOTSUPP means unknown/unsupported relocation */ + pr_warn("prog '%s': relo #%d: unrecognized CO-RE relocation %s (%d) at insn #%d\n", + prog_name, relo_idx, core_relo_kind_str(relo->kind), + relo->kind, relo->insn_off / 8); + } + + return err; +} + +/* + * Turn instruction for which CO_RE relocation failed into invalid one with + * distinct signature. + */ +static void bpf_core_poison_insn(const char *prog_name, int relo_idx, + int insn_idx, struct bpf_insn *insn) +{ + pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n", + prog_name, 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" */ +} + +static int insn_bpf_size_to_bytes(struct bpf_insn *insn) +{ + switch (BPF_SIZE(insn->code)) { + case BPF_DW: return 8; + case BPF_W: return 4; + case BPF_H: return 2; + case BPF_B: return 1; + default: return -1; + } +} + +static int insn_bytes_to_bpf_size(__u32 sz) +{ + switch (sz) { + case 8: return BPF_DW; + case 4: return BPF_W; + case 2: return BPF_H; + case 1: return BPF_B; + default: return -1; + } +} + +/* + * Patch relocatable BPF instruction. + * + * Patched value is determined by relocation kind and target specification. + * For existence relocations target spec will be NULL if field/type 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 supported classes of BPF instruction are: + * 1. rX = <imm> (assignment with immediate operand); + * 2. rX += <imm> (arithmetic operations with immediate operand); + * 3. rX = <imm64> (load with 64-bit immediate value); + * 4. rX = *(T *)(rY + <off>), where T is one of {u8, u16, u32, u64}; + * 5. *(T *)(rX + <off>) = rY, where T is one of {u8, u16, u32, u64}; + * 6. *(T *)(rX + <off>) = <imm>, where T is one of {u8, u16, u32, u64}. + */ +int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, + int insn_idx, const struct bpf_core_relo *relo, + int relo_idx, const struct bpf_core_relo_res *res) +{ + __u64 orig_val, new_val; + __u8 class; + + class = BPF_CLASS(insn->code); + + if (res->poison) { +poison: + /* poison second part of ldimm64 to avoid confusing error from + * verifier about "unknown opcode 00" + */ + if (is_ldimm64_insn(insn)) + bpf_core_poison_insn(prog_name, relo_idx, insn_idx + 1, insn + 1); + bpf_core_poison_insn(prog_name, relo_idx, insn_idx, insn); + return 0; + } + + orig_val = res->orig_val; + new_val = res->new_val; + + switch (class) { + case BPF_ALU: + case BPF_ALU64: + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + if (res->validate && insn->imm != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %llu -> %llu\n", + prog_name, relo_idx, + insn_idx, insn->imm, (unsigned long long)orig_val, + (unsigned long long)new_val); + return -EINVAL; + } + orig_val = insn->imm; + insn->imm = new_val; + pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %llu -> %llu\n", + prog_name, relo_idx, insn_idx, + (unsigned long long)orig_val, (unsigned long long)new_val); + break; + case BPF_LDX: + case BPF_ST: + case BPF_STX: + if (res->validate && insn->off != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %llu -> %llu\n", + prog_name, relo_idx, insn_idx, insn->off, (unsigned long long)orig_val, + (unsigned long long)new_val); + return -EINVAL; + } + if (new_val > SHRT_MAX) { + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %llu\n", + prog_name, relo_idx, insn_idx, (unsigned long long)new_val); + return -ERANGE; + } + if (res->fail_memsz_adjust) { + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) accesses field incorrectly. " + "Make sure you are accessing pointers, unsigned integers, or fields of matching type and size.\n", + prog_name, relo_idx, insn_idx); + goto poison; + } + + orig_val = insn->off; + insn->off = new_val; + pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %llu -> %llu\n", + prog_name, relo_idx, insn_idx, (unsigned long long)orig_val, + (unsigned long long)new_val); + + if (res->new_sz != res->orig_sz) { + int insn_bytes_sz, insn_bpf_sz; + + insn_bytes_sz = insn_bpf_size_to_bytes(insn); + if (insn_bytes_sz != res->orig_sz) { + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) unexpected mem size: got %d, exp %u\n", + prog_name, relo_idx, insn_idx, insn_bytes_sz, res->orig_sz); + return -EINVAL; + } + + insn_bpf_sz = insn_bytes_to_bpf_size(res->new_sz); + if (insn_bpf_sz < 0) { + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) invalid new mem size: %u\n", + prog_name, relo_idx, insn_idx, res->new_sz); + return -EINVAL; + } + + insn->code = BPF_MODE(insn->code) | insn_bpf_sz | BPF_CLASS(insn->code); + pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) mem_sz %u -> %u\n", + prog_name, relo_idx, insn_idx, res->orig_sz, res->new_sz); + } + break; + case BPF_LD: { + __u64 imm; + + if (!is_ldimm64_insn(insn) || + insn[0].src_reg != 0 || insn[0].off != 0 || + insn[1].code != 0 || insn[1].dst_reg != 0 || + insn[1].src_reg != 0 || insn[1].off != 0) { + pr_warn("prog '%s': relo #%d: insn #%d (LDIMM64) has unexpected form\n", + prog_name, relo_idx, insn_idx); + return -EINVAL; + } + + imm = (__u32)insn[0].imm | ((__u64)insn[1].imm << 32); + if (res->validate && imm != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %llu -> %llu\n", + prog_name, relo_idx, + insn_idx, (unsigned long long)imm, + (unsigned long long)orig_val, (unsigned long long)new_val); + return -EINVAL; + } + + insn[0].imm = new_val; + insn[1].imm = new_val >> 32; + pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %llu\n", + prog_name, relo_idx, insn_idx, + (unsigned long long)imm, (unsigned long long)new_val); + break; + } + default: + pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:0x%x, src:0x%x, dst:0x%x, off:0x%x, imm:0x%x\n", + prog_name, 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 + */ +int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *spec) +{ + const struct btf_type *t; + const char *s; + __u32 type_id; + int i, len = 0; + +#define append_buf(fmt, args...) \ + ({ \ + int r; \ + r = snprintf(buf, buf_sz, fmt, ##args); \ + len += r; \ + if (r >= buf_sz) \ + r = buf_sz; \ + buf += r; \ + buf_sz -= r; \ + }) + + type_id = spec->root_type_id; + t = btf_type_by_id(spec->btf, type_id); + s = btf__name_by_offset(spec->btf, t->name_off); + + append_buf("<%s> [%u] %s %s", + core_relo_kind_str(spec->relo_kind), + type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s); + + if (core_relo_is_type_based(spec->relo_kind)) + return len; + + if (core_relo_is_enumval_based(spec->relo_kind)) { + t = skip_mods_and_typedefs(spec->btf, type_id, NULL); + if (btf_is_enum(t)) { + const struct btf_enum *e; + const char *fmt_str; + + e = btf_enum(t) + spec->raw_spec[0]; + s = btf__name_by_offset(spec->btf, e->name_off); + fmt_str = BTF_INFO_KFLAG(t->info) ? "::%s = %d" : "::%s = %u"; + append_buf(fmt_str, s, e->val); + } else { + const struct btf_enum64 *e; + const char *fmt_str; + + e = btf_enum64(t) + spec->raw_spec[0]; + s = btf__name_by_offset(spec->btf, e->name_off); + fmt_str = BTF_INFO_KFLAG(t->info) ? "::%s = %lld" : "::%s = %llu"; + append_buf(fmt_str, s, (unsigned long long)btf_enum64_value(e)); + } + return len; + } + + if (core_relo_is_field_based(spec->relo_kind)) { + for (i = 0; i < spec->len; i++) { + if (spec->spec[i].name) + append_buf(".%s", spec->spec[i].name); + else if (i > 0 || spec->spec[i].idx > 0) + append_buf("[%u]", spec->spec[i].idx); + } + + append_buf(" ("); + for (i = 0; i < spec->raw_len; i++) + append_buf("%s%d", i == 0 ? "" : ":", spec->raw_spec[i]); + + if (spec->bit_offset % 8) + append_buf(" @ offset %u.%u)", spec->bit_offset / 8, spec->bit_offset % 8); + else + append_buf(" @ offset %u)", spec->bit_offset / 8); + return len; + } + + return len; +#undef append_buf +} + +/* + * Calculate CO-RE relocation target result. + * + * 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 accommodate + * imperfection of BTF deduplication, which can cause slight duplication of + * the same BTF type, if some directly or indirectly referenced (by + * pointer) type gets resolved to different actual types in different + * object files. If such a situation occurs, deduplicated BTF will end up + * with two (or more) structurally identical types, which differ only in + * types they refer to through pointer. This should be OK in most cases and + * is not an error. + * 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_core_relo 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. + */ +int bpf_core_calc_relo_insn(const char *prog_name, + const struct bpf_core_relo *relo, + int relo_idx, + const struct btf *local_btf, + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch, + struct bpf_core_relo_res *targ_res) +{ + struct bpf_core_spec *local_spec = &specs_scratch[0]; + struct bpf_core_spec *cand_spec = &specs_scratch[1]; + struct bpf_core_spec *targ_spec = &specs_scratch[2]; + struct bpf_core_relo_res cand_res; + const struct btf_type *local_type; + const char *local_name; + __u32 local_id; + char spec_buf[256]; + int i, j, err; + + local_id = relo->type_id; + local_type = btf_type_by_id(local_btf, local_id); + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (!local_name) + return -EINVAL; + + err = bpf_core_parse_spec(prog_name, local_btf, relo, local_spec); + if (err) { + const char *spec_str; + + spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n", + prog_name, relo_idx, local_id, btf_kind_str(local_type), + str_is_empty(local_name) ? "<anon>" : local_name, + spec_str ?: "<?>", err); + return -EINVAL; + } + + bpf_core_format_spec(spec_buf, sizeof(spec_buf), local_spec); + pr_debug("prog '%s': relo #%d: %s\n", prog_name, relo_idx, spec_buf); + + /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ + if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) { + /* bpf_insn's imm value could get out of sync during linking */ + memset(targ_res, 0, sizeof(*targ_res)); + targ_res->validate = false; + targ_res->poison = false; + targ_res->orig_val = local_spec->root_type_id; + targ_res->new_val = local_spec->root_type_id; + return 0; + } + + /* libbpf doesn't support candidate search for anonymous types */ + if (str_is_empty(local_name)) { + pr_warn("prog '%s': relo #%d: <%s> (%d) relocation doesn't support anonymous types\n", + prog_name, relo_idx, core_relo_kind_str(relo->kind), relo->kind); + return -EOPNOTSUPP; + } + + for (i = 0, j = 0; i < cands->len; i++) { + err = bpf_core_spec_match(local_spec, cands->cands[i].btf, + cands->cands[i].id, cand_spec); + if (err < 0) { + bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec); + pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n ", + prog_name, relo_idx, i, spec_buf, err); + return err; + } + + bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec); + pr_debug("prog '%s': relo #%d: %s candidate #%d %s\n", prog_name, + relo_idx, err == 0 ? "non-matching" : "matching", i, spec_buf); + + if (err == 0) + continue; + + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, cand_spec, &cand_res); + if (err) + return err; + + if (j == 0) { + *targ_res = cand_res; + *targ_spec = *cand_spec; + } else if (cand_spec->bit_offset != targ_spec->bit_offset) { + /* if there are many field relo candidates, they + * should all resolve to the same bit offset + */ + pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n", + prog_name, relo_idx, cand_spec->bit_offset, + targ_spec->bit_offset); + return -EINVAL; + } else if (cand_res.poison != targ_res->poison || + cand_res.new_val != targ_res->new_val) { + /* all candidates should result in the same relocation + * decision and value, otherwise it's dangerous to + * proceed due to ambiguity + */ + pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %llu != %s %llu\n", + prog_name, relo_idx, + cand_res.poison ? "failure" : "success", + (unsigned long long)cand_res.new_val, + targ_res->poison ? "failure" : "success", + (unsigned long long)targ_res->new_val); + return -EINVAL; + } + + cands->cands[j++] = cands->cands[i]; + } + + /* + * For BPF_CORE_FIELD_EXISTS relo or when used BPF program has field + * existence checks or kernel version/config checks, it's expected + * that we might not find any candidates. In this case, if field + * wasn't found in any candidate, the list of candidates shouldn't + * change at all, we'll just handle relocating appropriately, + * depending on relo's kind. + */ + if (j > 0) + cands->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_patch_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\n", + prog_name, relo_idx); + + /* calculate single target relo result explicitly */ + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, targ_res); + if (err) + return err; + } + + return 0; +} + +static bool bpf_core_names_match(const struct btf *local_btf, size_t local_name_off, + const struct btf *targ_btf, size_t targ_name_off) +{ + const char *local_n, *targ_n; + size_t local_len, targ_len; + + local_n = btf__name_by_offset(local_btf, local_name_off); + targ_n = btf__name_by_offset(targ_btf, targ_name_off); + + if (str_is_empty(targ_n)) + return str_is_empty(local_n); + + targ_len = bpf_core_essential_name_len(targ_n); + local_len = bpf_core_essential_name_len(local_n); + + return targ_len == local_len && strncmp(local_n, targ_n, local_len) == 0; +} + +static int bpf_core_enums_match(const struct btf *local_btf, const struct btf_type *local_t, + const struct btf *targ_btf, const struct btf_type *targ_t) +{ + __u16 local_vlen = btf_vlen(local_t); + __u16 targ_vlen = btf_vlen(targ_t); + int i, j; + + if (local_t->size != targ_t->size) + return 0; + + if (local_vlen > targ_vlen) + return 0; + + /* iterate over the local enum's variants and make sure each has + * a symbolic name correspondent in the target + */ + for (i = 0; i < local_vlen; i++) { + bool matched = false; + __u32 local_n_off, targ_n_off; + + local_n_off = btf_is_enum(local_t) ? btf_enum(local_t)[i].name_off : + btf_enum64(local_t)[i].name_off; + + for (j = 0; j < targ_vlen; j++) { + targ_n_off = btf_is_enum(targ_t) ? btf_enum(targ_t)[j].name_off : + btf_enum64(targ_t)[j].name_off; + + if (bpf_core_names_match(local_btf, local_n_off, targ_btf, targ_n_off)) { + matched = true; + break; + } + } + + if (!matched) + return 0; + } + return 1; +} + +static int bpf_core_composites_match(const struct btf *local_btf, const struct btf_type *local_t, + const struct btf *targ_btf, const struct btf_type *targ_t, + bool behind_ptr, int level) +{ + const struct btf_member *local_m = btf_members(local_t); + __u16 local_vlen = btf_vlen(local_t); + __u16 targ_vlen = btf_vlen(targ_t); + int i, j, err; + + if (local_vlen > targ_vlen) + return 0; + + /* check that all local members have a match in the target */ + for (i = 0; i < local_vlen; i++, local_m++) { + const struct btf_member *targ_m = btf_members(targ_t); + bool matched = false; + + for (j = 0; j < targ_vlen; j++, targ_m++) { + if (!bpf_core_names_match(local_btf, local_m->name_off, + targ_btf, targ_m->name_off)) + continue; + + err = __bpf_core_types_match(local_btf, local_m->type, targ_btf, + targ_m->type, behind_ptr, level - 1); + if (err < 0) + return err; + if (err > 0) { + matched = true; + break; + } + } + + if (!matched) + return 0; + } + return 1; +} + +/* Check that two types "match". This function assumes that root types were + * already checked for name match. + * + * The matching relation is defined as follows: + * - modifiers and typedefs are stripped (and, hence, effectively ignored) + * - generally speaking types need to be of same kind (struct vs. struct, union + * vs. union, etc.) + * - exceptions are struct/union behind a pointer which could also match a + * forward declaration of a struct or union, respectively, and enum vs. + * enum64 (see below) + * Then, depending on type: + * - integers: + * - match if size and signedness match + * - arrays & pointers: + * - target types are recursively matched + * - structs & unions: + * - local members need to exist in target with the same name + * - for each member we recursively check match unless it is already behind a + * pointer, in which case we only check matching names and compatible kind + * - enums: + * - local variants have to have a match in target by symbolic name (but not + * numeric value) + * - size has to match (but enum may match enum64 and vice versa) + * - function pointers: + * - number and position of arguments in local type has to match target + * - for each argument and the return value we recursively check match + */ +int __bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, + __u32 targ_id, bool behind_ptr, int level) +{ + const struct btf_type *local_t, *targ_t; + int depth = 32; /* max recursion depth */ + __u16 local_k, targ_k; + + if (level <= 0) + return -EINVAL; + + local_t = btf_type_by_id(local_btf, local_id); + targ_t = btf_type_by_id(targ_btf, targ_id); + +recur: + depth--; + if (depth < 0) + return -EINVAL; + + local_t = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_t = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_t || !targ_t) + return -EINVAL; + + /* While the name check happens after typedefs are skipped, root-level + * typedefs would still be name-matched as that's the contract with + * callers. + */ + if (!bpf_core_names_match(local_btf, local_t->name_off, targ_btf, targ_t->name_off)) + return 0; + + local_k = btf_kind(local_t); + targ_k = btf_kind(targ_t); + + switch (local_k) { + case BTF_KIND_UNKN: + return local_k == targ_k; + case BTF_KIND_FWD: { + bool local_f = BTF_INFO_KFLAG(local_t->info); + + if (behind_ptr) { + if (local_k == targ_k) + return local_f == BTF_INFO_KFLAG(targ_t->info); + + /* for forward declarations kflag dictates whether the + * target is a struct (0) or union (1) + */ + return (targ_k == BTF_KIND_STRUCT && !local_f) || + (targ_k == BTF_KIND_UNION && local_f); + } else { + if (local_k != targ_k) + return 0; + + /* match if the forward declaration is for the same kind */ + return local_f == BTF_INFO_KFLAG(targ_t->info); + } + } + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + if (!btf_is_any_enum(targ_t)) + return 0; + + return bpf_core_enums_match(local_btf, local_t, targ_btf, targ_t); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + if (behind_ptr) { + bool targ_f = BTF_INFO_KFLAG(targ_t->info); + + if (local_k == targ_k) + return 1; + + if (targ_k != BTF_KIND_FWD) + return 0; + + return (local_k == BTF_KIND_UNION) == targ_f; + } else { + if (local_k != targ_k) + return 0; + + return bpf_core_composites_match(local_btf, local_t, targ_btf, targ_t, + behind_ptr, level); + } + case BTF_KIND_INT: { + __u8 local_sgn; + __u8 targ_sgn; + + if (local_k != targ_k) + return 0; + + local_sgn = btf_int_encoding(local_t) & BTF_INT_SIGNED; + targ_sgn = btf_int_encoding(targ_t) & BTF_INT_SIGNED; + + return local_t->size == targ_t->size && local_sgn == targ_sgn; + } + case BTF_KIND_PTR: + if (local_k != targ_k) + return 0; + + behind_ptr = true; + + local_id = local_t->type; + targ_id = targ_t->type; + goto recur; + case BTF_KIND_ARRAY: { + const struct btf_array *local_array = btf_array(local_t); + const struct btf_array *targ_array = btf_array(targ_t); + + if (local_k != targ_k) + return 0; + + if (local_array->nelems != targ_array->nelems) + return 0; + + local_id = local_array->type; + targ_id = targ_array->type; + goto recur; + } + case BTF_KIND_FUNC_PROTO: { + struct btf_param *local_p = btf_params(local_t); + struct btf_param *targ_p = btf_params(targ_t); + __u16 local_vlen = btf_vlen(local_t); + __u16 targ_vlen = btf_vlen(targ_t); + int i, err; + + if (local_k != targ_k) + return 0; + + if (local_vlen != targ_vlen) + return 0; + + for (i = 0; i < local_vlen; i++, local_p++, targ_p++) { + err = __bpf_core_types_match(local_btf, local_p->type, targ_btf, + targ_p->type, behind_ptr, level - 1); + if (err <= 0) + return err; + } + + /* tail recurse for return type check */ + local_id = local_t->type; + targ_id = targ_t->type; + goto recur; + } + default: + pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n", + btf_kind_str(local_t), local_id, targ_id); + return 0; + } +} diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h new file mode 100644 index 000000000..1c0566daf --- /dev/null +++ b/tools/lib/bpf/relo_core.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2019 Facebook */ + +#ifndef __RELO_CORE_H +#define __RELO_CORE_H + +#include <linux/bpf.h> + +struct bpf_core_cand { + const struct btf *btf; + __u32 id; +}; + +/* dynamically sized list of type IDs and its associated struct btf */ +struct bpf_core_cand_list { + struct bpf_core_cand *cands; + int len; +}; + +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* original unresolved (no skip_mods_or_typedefs) root type ID */ + __u32 root_type_id; + /* CO-RE relocation kind */ + enum bpf_core_relo_kind relo_kind; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field bit offset represented by spec */ + __u32 bit_offset; +}; + +struct bpf_core_relo_res { + /* expected value in the instruction, unless validate == false */ + __u64 orig_val; + /* new value that needs to be patched up to */ + __u64 new_val; + /* relocation unsuccessful, poison instruction, but don't fail load */ + bool poison; + /* some relocations can't be validated against orig_val */ + bool validate; + /* for field byte offset relocations or the forms: + * *(T *)(rX + <off>) = rY + * rX = *(T *)(rY + <off>), + * we remember original and resolved field size to adjust direct + * memory loads of pointers and integers; this is necessary for 32-bit + * host kernel architectures, but also allows to automatically + * relocate fields that were resized from, e.g., u32 to u64, etc. + */ + bool fail_memsz_adjust; + __u32 orig_sz; + __u32 orig_type_id; + __u32 new_sz; + __u32 new_type_id; +}; + +int __bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id, int level); +int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id); +int __bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, + __u32 targ_id, bool behind_ptr, int level); +int bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, + __u32 targ_id); + +size_t bpf_core_essential_name_len(const char *name); + +int bpf_core_calc_relo_insn(const char *prog_name, + const struct bpf_core_relo *relo, int relo_idx, + const struct btf *local_btf, + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch, + struct bpf_core_relo_res *targ_res); + +int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, + int insn_idx, const struct bpf_core_relo *relo, + int relo_idx, const struct bpf_core_relo_res *res); + +int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, + const struct bpf_core_relo *relo, + struct bpf_core_spec *spec); + +int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *spec); + +#endif diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c new file mode 100644 index 000000000..6af142953 --- /dev/null +++ b/tools/lib/bpf/ringbuf.c @@ -0,0 +1,587 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* + * Ring buffer operations. + * + * Copyright (C) 2020 Facebook, Inc. + */ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <unistd.h> +#include <linux/err.h> +#include <linux/bpf.h> +#include <asm/barrier.h> +#include <sys/mman.h> +#include <sys/epoll.h> +#include <time.h> + +#include "libbpf.h" +#include "libbpf_internal.h" +#include "bpf.h" + +struct ring { + ring_buffer_sample_fn sample_cb; + void *ctx; + void *data; + unsigned long *consumer_pos; + unsigned long *producer_pos; + unsigned long mask; + int map_fd; +}; + +struct ring_buffer { + struct epoll_event *events; + struct ring *rings; + size_t page_size; + int epoll_fd; + int ring_cnt; +}; + +struct user_ring_buffer { + struct epoll_event event; + unsigned long *consumer_pos; + unsigned long *producer_pos; + void *data; + unsigned long mask; + size_t page_size; + int map_fd; + int epoll_fd; +}; + +/* 8-byte ring buffer header structure */ +struct ringbuf_hdr { + __u32 len; + __u32 pad; +}; + +static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r) +{ + if (r->consumer_pos) { + munmap(r->consumer_pos, rb->page_size); + r->consumer_pos = NULL; + } + if (r->producer_pos) { + munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1)); + r->producer_pos = NULL; + } +} + +/* Add extra RINGBUF maps to this ring buffer manager */ +int ring_buffer__add(struct ring_buffer *rb, int map_fd, + ring_buffer_sample_fn sample_cb, void *ctx) +{ + struct bpf_map_info info; + __u32 len = sizeof(info); + struct epoll_event *e; + struct ring *r; + __u64 mmap_sz; + void *tmp; + int err; + + memset(&info, 0, sizeof(info)); + + err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + if (err) { + err = -errno; + pr_warn("ringbuf: failed to get map info for fd=%d: %d\n", + map_fd, err); + return libbpf_err(err); + } + + if (info.type != BPF_MAP_TYPE_RINGBUF) { + pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n", + map_fd); + return libbpf_err(-EINVAL); + } + + tmp = libbpf_reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings)); + if (!tmp) + return libbpf_err(-ENOMEM); + rb->rings = tmp; + + tmp = libbpf_reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events)); + if (!tmp) + return libbpf_err(-ENOMEM); + rb->events = tmp; + + r = &rb->rings[rb->ring_cnt]; + memset(r, 0, sizeof(*r)); + + r->map_fd = map_fd; + r->sample_cb = sample_cb; + r->ctx = ctx; + r->mask = info.max_entries - 1; + + /* Map writable consumer page */ + tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n", + map_fd, err); + return libbpf_err(err); + } + r->consumer_pos = tmp; + + /* Map read-only producer page and data pages. We map twice as big + * data size to allow simple reading of samples that wrap around the + * end of a ring buffer. See kernel implementation for details. + * */ + mmap_sz = rb->page_size + 2 * (__u64)info.max_entries; + if (mmap_sz != (__u64)(size_t)mmap_sz) { + pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries); + return libbpf_err(-E2BIG); + } + tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size); + if (tmp == MAP_FAILED) { + err = -errno; + ringbuf_unmap_ring(rb, r); + pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n", + map_fd, err); + return libbpf_err(err); + } + r->producer_pos = tmp; + r->data = tmp + rb->page_size; + + e = &rb->events[rb->ring_cnt]; + memset(e, 0, sizeof(*e)); + + e->events = EPOLLIN; + e->data.fd = rb->ring_cnt; + if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) { + err = -errno; + ringbuf_unmap_ring(rb, r); + pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n", + map_fd, err); + return libbpf_err(err); + } + + rb->ring_cnt++; + return 0; +} + +void ring_buffer__free(struct ring_buffer *rb) +{ + int i; + + if (!rb) + return; + + for (i = 0; i < rb->ring_cnt; ++i) + ringbuf_unmap_ring(rb, &rb->rings[i]); + if (rb->epoll_fd >= 0) + close(rb->epoll_fd); + + free(rb->events); + free(rb->rings); + free(rb); +} + +struct ring_buffer * +ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, + const struct ring_buffer_opts *opts) +{ + struct ring_buffer *rb; + int err; + + if (!OPTS_VALID(opts, ring_buffer_opts)) + return errno = EINVAL, NULL; + + rb = calloc(1, sizeof(*rb)); + if (!rb) + return errno = ENOMEM, NULL; + + rb->page_size = getpagesize(); + + rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (rb->epoll_fd < 0) { + err = -errno; + pr_warn("ringbuf: failed to create epoll instance: %d\n", err); + goto err_out; + } + + err = ring_buffer__add(rb, map_fd, sample_cb, ctx); + if (err) + goto err_out; + + return rb; + +err_out: + ring_buffer__free(rb); + return errno = -err, NULL; +} + +static inline int roundup_len(__u32 len) +{ + /* clear out top 2 bits (discard and busy, if set) */ + len <<= 2; + len >>= 2; + /* add length prefix */ + len += BPF_RINGBUF_HDR_SZ; + /* round up to 8 byte alignment */ + return (len + 7) / 8 * 8; +} + +static int64_t ringbuf_process_ring(struct ring* r) +{ + int *len_ptr, len, err; + /* 64-bit to avoid overflow in case of extreme application behavior */ + int64_t cnt = 0; + unsigned long cons_pos, prod_pos; + bool got_new_data; + void *sample; + + cons_pos = smp_load_acquire(r->consumer_pos); + do { + got_new_data = false; + prod_pos = smp_load_acquire(r->producer_pos); + while (cons_pos < prod_pos) { + len_ptr = r->data + (cons_pos & r->mask); + len = smp_load_acquire(len_ptr); + + /* sample not committed yet, bail out for now */ + if (len & BPF_RINGBUF_BUSY_BIT) + goto done; + + got_new_data = true; + cons_pos += roundup_len(len); + + if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) { + sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ; + err = r->sample_cb(r->ctx, sample, len); + if (err < 0) { + /* update consumer pos and bail out */ + smp_store_release(r->consumer_pos, + cons_pos); + return err; + } + cnt++; + } + + smp_store_release(r->consumer_pos, cons_pos); + } + } while (got_new_data); +done: + return cnt; +} + +/* Consume available ring buffer(s) data without event polling. + * Returns number of records consumed across all registered ring buffers (or + * INT_MAX, whichever is less), or negative number if any of the callbacks + * return error. + */ +int ring_buffer__consume(struct ring_buffer *rb) +{ + int64_t err, res = 0; + int i; + + for (i = 0; i < rb->ring_cnt; i++) { + struct ring *ring = &rb->rings[i]; + + err = ringbuf_process_ring(ring); + if (err < 0) + return libbpf_err(err); + res += err; + } + if (res > INT_MAX) + return INT_MAX; + return res; +} + +/* Poll for available data and consume records, if any are available. + * Returns number of records consumed (or INT_MAX, whichever is less), or + * negative number, if any of the registered callbacks returned error. + */ +int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) +{ + int i, cnt; + int64_t err, res = 0; + + cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms); + if (cnt < 0) + return libbpf_err(-errno); + + for (i = 0; i < cnt; i++) { + __u32 ring_id = rb->events[i].data.fd; + struct ring *ring = &rb->rings[ring_id]; + + err = ringbuf_process_ring(ring); + if (err < 0) + return libbpf_err(err); + res += err; + } + if (res > INT_MAX) + return INT_MAX; + return res; +} + +/* Get an fd that can be used to sleep until data is available in the ring(s) */ +int ring_buffer__epoll_fd(const struct ring_buffer *rb) +{ + return rb->epoll_fd; +} + +static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb) +{ + if (rb->consumer_pos) { + munmap(rb->consumer_pos, rb->page_size); + rb->consumer_pos = NULL; + } + if (rb->producer_pos) { + munmap(rb->producer_pos, rb->page_size + 2 * (rb->mask + 1)); + rb->producer_pos = NULL; + } +} + +void user_ring_buffer__free(struct user_ring_buffer *rb) +{ + if (!rb) + return; + + user_ringbuf_unmap_ring(rb); + + if (rb->epoll_fd >= 0) + close(rb->epoll_fd); + + free(rb); +} + +static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) +{ + struct bpf_map_info info; + __u32 len = sizeof(info); + __u64 mmap_sz; + void *tmp; + struct epoll_event *rb_epoll; + int err; + + memset(&info, 0, sizeof(info)); + + err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + if (err) { + err = -errno; + pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err); + return err; + } + + if (info.type != BPF_MAP_TYPE_USER_RINGBUF) { + pr_warn("user ringbuf: map fd=%d is not BPF_MAP_TYPE_USER_RINGBUF\n", map_fd); + return -EINVAL; + } + + rb->map_fd = map_fd; + rb->mask = info.max_entries - 1; + + /* Map read-only consumer page */ + tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n", + map_fd, err); + return err; + } + rb->consumer_pos = tmp; + + /* Map read-write the producer page and data pages. We map the data + * region as twice the total size of the ring buffer to allow the + * simple reading and writing of samples that wrap around the end of + * the buffer. See the kernel implementation for details. + */ + mmap_sz = rb->page_size + 2 * (__u64)info.max_entries; + if (mmap_sz != (__u64)(size_t)mmap_sz) { + pr_warn("user ringbuf: ring buf size (%u) is too big\n", info.max_entries); + return -E2BIG; + } + tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED, + map_fd, rb->page_size); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n", + map_fd, err); + return err; + } + + rb->producer_pos = tmp; + rb->data = tmp + rb->page_size; + + rb_epoll = &rb->event; + rb_epoll->events = EPOLLOUT; + if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) { + err = -errno; + pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err); + return err; + } + + return 0; +} + +struct user_ring_buffer * +user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts) +{ + struct user_ring_buffer *rb; + int err; + + if (!OPTS_VALID(opts, user_ring_buffer_opts)) + return errno = EINVAL, NULL; + + rb = calloc(1, sizeof(*rb)); + if (!rb) + return errno = ENOMEM, NULL; + + rb->page_size = getpagesize(); + + rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (rb->epoll_fd < 0) { + err = -errno; + pr_warn("user ringbuf: failed to create epoll instance: %d\n", err); + goto err_out; + } + + err = user_ringbuf_map(rb, map_fd); + if (err) + goto err_out; + + return rb; + +err_out: + user_ring_buffer__free(rb); + return errno = -err, NULL; +} + +static void user_ringbuf_commit(struct user_ring_buffer *rb, void *sample, bool discard) +{ + __u32 new_len; + struct ringbuf_hdr *hdr; + uintptr_t hdr_offset; + + hdr_offset = rb->mask + 1 + (sample - rb->data) - BPF_RINGBUF_HDR_SZ; + hdr = rb->data + (hdr_offset & rb->mask); + + new_len = hdr->len & ~BPF_RINGBUF_BUSY_BIT; + if (discard) + new_len |= BPF_RINGBUF_DISCARD_BIT; + + /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + __atomic_exchange_n(&hdr->len, new_len, __ATOMIC_ACQ_REL); +} + +void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample) +{ + user_ringbuf_commit(rb, sample, true); +} + +void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample) +{ + user_ringbuf_commit(rb, sample, false); +} + +void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size) +{ + __u32 avail_size, total_size, max_size; + /* 64-bit to avoid overflow in case of extreme application behavior */ + __u64 cons_pos, prod_pos; + struct ringbuf_hdr *hdr; + + /* The top two bits are used as special flags */ + if (size & (BPF_RINGBUF_BUSY_BIT | BPF_RINGBUF_DISCARD_BIT)) + return errno = E2BIG, NULL; + + /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + cons_pos = smp_load_acquire(rb->consumer_pos); + /* Synchronizes with smp_store_release() in user_ringbuf_commit() */ + prod_pos = smp_load_acquire(rb->producer_pos); + + max_size = rb->mask + 1; + avail_size = max_size - (prod_pos - cons_pos); + /* Round up total size to a multiple of 8. */ + total_size = (size + BPF_RINGBUF_HDR_SZ + 7) / 8 * 8; + + if (total_size > max_size) + return errno = E2BIG, NULL; + + if (avail_size < total_size) + return errno = ENOSPC, NULL; + + hdr = rb->data + (prod_pos & rb->mask); + hdr->len = size | BPF_RINGBUF_BUSY_BIT; + hdr->pad = 0; + + /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + smp_store_release(rb->producer_pos, prod_pos + total_size); + + return (void *)rb->data + ((prod_pos + BPF_RINGBUF_HDR_SZ) & rb->mask); +} + +static __u64 ns_elapsed_timespec(const struct timespec *start, const struct timespec *end) +{ + __u64 start_ns, end_ns, ns_per_s = 1000000000; + + start_ns = (__u64)start->tv_sec * ns_per_s + start->tv_nsec; + end_ns = (__u64)end->tv_sec * ns_per_s + end->tv_nsec; + + return end_ns - start_ns; +} + +void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms) +{ + void *sample; + int err, ms_remaining = timeout_ms; + struct timespec start; + + if (timeout_ms < 0 && timeout_ms != -1) + return errno = EINVAL, NULL; + + if (timeout_ms != -1) { + err = clock_gettime(CLOCK_MONOTONIC, &start); + if (err) + return NULL; + } + + do { + int cnt, ms_elapsed; + struct timespec curr; + __u64 ns_per_ms = 1000000; + + sample = user_ring_buffer__reserve(rb, size); + if (sample) + return sample; + else if (errno != ENOSPC) + return NULL; + + /* The kernel guarantees at least one event notification + * delivery whenever at least one sample is drained from the + * ring buffer in an invocation to bpf_ringbuf_drain(). Other + * additional events may be delivered at any time, but only one + * event is guaranteed per bpf_ringbuf_drain() invocation, + * provided that a sample is drained, and the BPF program did + * not pass BPF_RB_NO_WAKEUP to bpf_ringbuf_drain(). If + * BPF_RB_FORCE_WAKEUP is passed to bpf_ringbuf_drain(), a + * wakeup event will be delivered even if no samples are + * drained. + */ + cnt = epoll_wait(rb->epoll_fd, &rb->event, 1, ms_remaining); + if (cnt < 0) + return NULL; + + if (timeout_ms == -1) + continue; + + err = clock_gettime(CLOCK_MONOTONIC, &curr); + if (err) + return NULL; + + ms_elapsed = ns_elapsed_timespec(&start, &curr) / ns_per_ms; + ms_remaining = timeout_ms - ms_elapsed; + } while (ms_remaining > 0); + + /* Try one more time to reserve a sample after the specified timeout has elapsed. */ + return user_ring_buffer__reserve(rb, size); +} diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h new file mode 100644 index 000000000..1e82ab06c --- /dev/null +++ b/tools/lib/bpf/skel_internal.h @@ -0,0 +1,374 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2021 Facebook */ +#ifndef __SKEL_INTERNAL_H +#define __SKEL_INTERNAL_H + +#ifdef __KERNEL__ +#include <linux/fdtable.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#else +#include <unistd.h> +#include <sys/syscall.h> +#include <sys/mman.h> +#include <stdlib.h> +#include "bpf.h" +#endif + +#ifndef __NR_bpf +# if defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 +# endif +#endif + +/* This file is a base header for auto-generated *.lskel.h files. + * Its contents will change and may become part of auto-generation in the future. + * + * The layout of bpf_[map|prog]_desc and bpf_loader_ctx is feature dependent + * and will change from one version of libbpf to another and features + * requested during loader program generation. + */ +struct bpf_map_desc { + /* output of the loader prog */ + int map_fd; + /* input for the loader prog */ + __u32 max_entries; + __aligned_u64 initial_value; +}; +struct bpf_prog_desc { + int prog_fd; +}; + +enum { + BPF_SKEL_KERNEL = (1ULL << 0), +}; + +struct bpf_loader_ctx { + __u32 sz; + __u32 flags; + __u32 log_level; + __u32 log_size; + __u64 log_buf; +}; + +struct bpf_load_and_run_opts { + struct bpf_loader_ctx *ctx; + const void *data; + const void *insns; + __u32 data_sz; + __u32 insns_sz; + const char *errstr; +}; + +long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size); + +static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) +{ +#ifdef __KERNEL__ + return kern_sys_bpf(cmd, attr, size); +#else + return syscall(__NR_bpf, cmd, attr, size); +#endif +} + +#ifdef __KERNEL__ +static inline int close(int fd) +{ + return close_fd(fd); +} + +static inline void *skel_alloc(size_t size) +{ + struct bpf_loader_ctx *ctx = kzalloc(size, GFP_KERNEL); + + if (!ctx) + return NULL; + ctx->flags |= BPF_SKEL_KERNEL; + return ctx; +} + +static inline void skel_free(const void *p) +{ + kfree(p); +} + +/* skel->bss/rodata maps are populated the following way: + * + * For kernel use: + * skel_prep_map_data() allocates kernel memory that kernel module can directly access. + * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value. + * The loader program will perform probe_read_kernel() from maps.rodata.initial_value. + * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and + * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree + * is not nessary. + * + * For user space: + * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly. + * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value. + * The loader program will perform copy_from_user() from maps.rodata.initial_value. + * skel_finalize_map_data() remaps bpf array map value from the kernel memory into + * skel->rodata address. + * + * The "bpftool gen skeleton -L" command generates lskel.h that is suitable for + * both kernel and user space. The generated loader program does + * either bpf_probe_read_kernel() or bpf_copy_from_user() from initial_value + * depending on bpf_loader_ctx->flags. + */ +static inline void skel_free_map_data(void *p, __u64 addr, size_t sz) +{ + if (addr != ~0ULL) + kvfree(p); + /* When addr == ~0ULL the 'p' points to + * ((struct bpf_array *)map)->value. See skel_finalize_map_data. + */ +} + +static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz) +{ + void *addr; + + addr = kvmalloc(val_sz, GFP_KERNEL); + if (!addr) + return NULL; + memcpy(addr, val, val_sz); + return addr; +} + +static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd) +{ + struct bpf_map *map; + void *addr = NULL; + + kvfree((void *) (long) *init_val); + *init_val = ~0ULL; + + /* At this point bpf_load_and_run() finished without error and + * 'fd' is a valid bpf map FD. All sanity checks below should succeed. + */ + map = bpf_map_get(fd); + if (IS_ERR(map)) + return NULL; + if (map->map_type != BPF_MAP_TYPE_ARRAY) + goto out; + addr = ((struct bpf_array *)map)->value; + /* the addr stays valid, since FD is not closed */ +out: + bpf_map_put(map); + return addr; +} + +#else + +static inline void *skel_alloc(size_t size) +{ + return calloc(1, size); +} + +static inline void skel_free(void *p) +{ + free(p); +} + +static inline void skel_free_map_data(void *p, __u64 addr, size_t sz) +{ + munmap(p, sz); +} + +static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz) +{ + void *addr; + + addr = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (addr == (void *) -1) + return NULL; + memcpy(addr, val, val_sz); + return addr; +} + +static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd) +{ + void *addr; + + addr = mmap((void *) (long) *init_val, mmap_sz, flags, MAP_SHARED | MAP_FIXED, fd, 0); + if (addr == (void *) -1) + return NULL; + return addr; +} +#endif + +static inline int skel_closenz(int fd) +{ + if (fd > 0) + return close(fd); + return -EINVAL; +} + +#ifndef offsetofend +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) +#endif + +static inline int skel_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + + attr.map_type = map_type; + strncpy(attr.map_name, map_name, sizeof(attr.map_name)); + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; + + return skel_sys_bpf(BPF_MAP_CREATE, &attr, attr_sz); +} + +static inline int skel_map_update_elem(int fd, const void *key, + const void *value, __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = (long) key; + attr.value = (long) value; + attr.flags = flags; + + return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); +} + +static inline int skel_map_delete_elem(int fd, const void *key) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = (long)key; + + return skel_sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); +} + +static inline int skel_map_get_fd_by_id(__u32 id) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_id = id; + + return skel_sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz); +} + +static inline int skel_raw_tracepoint_open(const char *name, int prog_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.raw_tracepoint.name = (long) name; + attr.raw_tracepoint.prog_fd = prog_fd; + + return skel_sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); +} + +static inline int skel_link_create(int prog_fd, int target_fd, + enum bpf_attach_type attach_type) +{ + const size_t attr_sz = offsetofend(union bpf_attr, link_create.iter_info_len); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.link_create.prog_fd = prog_fd; + attr.link_create.target_fd = target_fd; + attr.link_create.attach_type = attach_type; + + return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz); +} + +#ifdef __KERNEL__ +#define set_err +#else +#define set_err err = -errno +#endif + +static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) +{ + const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array); + const size_t test_run_attr_sz = offsetofend(union bpf_attr, test); + int map_fd = -1, prog_fd = -1, key = 0, err; + union bpf_attr attr; + + err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1); + if (map_fd < 0) { + opts->errstr = "failed to create loader map"; + set_err; + goto out; + } + + err = skel_map_update_elem(map_fd, &key, opts->data, 0); + if (err < 0) { + opts->errstr = "failed to update loader map"; + set_err; + goto out; + } + + memset(&attr, 0, prog_load_attr_sz); + attr.prog_type = BPF_PROG_TYPE_SYSCALL; + attr.insns = (long) opts->insns; + attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); + attr.license = (long) "Dual BSD/GPL"; + memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog")); + attr.fd_array = (long) &map_fd; + attr.log_level = opts->ctx->log_level; + attr.log_size = opts->ctx->log_size; + attr.log_buf = opts->ctx->log_buf; + attr.prog_flags = BPF_F_SLEEPABLE; + err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, prog_load_attr_sz); + if (prog_fd < 0) { + opts->errstr = "failed to load loader prog"; + set_err; + goto out; + } + + memset(&attr, 0, test_run_attr_sz); + attr.test.prog_fd = prog_fd; + attr.test.ctx_in = (long) opts->ctx; + attr.test.ctx_size_in = opts->ctx->sz; + err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz); + if (err < 0 || (int)attr.test.retval < 0) { + opts->errstr = "failed to execute loader prog"; + if (err < 0) { + set_err; + } else { + err = (int)attr.test.retval; +#ifndef __KERNEL__ + errno = -err; +#endif + } + goto out; + } + err = 0; +out: + if (map_fd >= 0) + close(map_fd); + if (prog_fd >= 0) + close(prog_fd); + return err; +} + +#endif diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c new file mode 100644 index 000000000..146da0197 --- /dev/null +++ b/tools/lib/bpf/str_error.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +#undef _GNU_SOURCE +#include <string.h> +#include <stdio.h> +#include "str_error.h" + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +/* + * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl + * libc, while checking strerror_r() return to avoid having to check this in + * all places calling it. + */ +char *libbpf_strerror_r(int err, char *dst, int len) +{ + int ret = strerror_r(err < 0 ? -err : err, dst, len); + if (ret) + snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); + return dst; +} diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h new file mode 100644 index 000000000..a139334d5 --- /dev/null +++ b/tools/lib/bpf/str_error.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __LIBBPF_STR_ERROR_H +#define __LIBBPF_STR_ERROR_H + +char *libbpf_strerror_r(int err, char *dst, int len); +#endif /* __LIBBPF_STR_ERROR_H */ diff --git a/tools/lib/bpf/strset.c b/tools/lib/bpf/strset.c new file mode 100644 index 000000000..ea6553181 --- /dev/null +++ b/tools/lib/bpf/strset.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2021 Facebook */ +#include <stdint.h> +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <linux/err.h> +#include "hashmap.h" +#include "libbpf_internal.h" +#include "strset.h" + +struct strset { + void *strs_data; + size_t strs_data_len; + size_t strs_data_cap; + size_t strs_data_max_len; + + /* lookup index for each unique string in strings set */ + struct hashmap *strs_hash; +}; + +static size_t strset_hash_fn(const void *key, void *ctx) +{ + const struct strset *s = ctx; + const char *str = s->strs_data + (long)key; + + return str_hash(str); +} + +static bool strset_equal_fn(const void *key1, const void *key2, void *ctx) +{ + const struct strset *s = ctx; + const char *str1 = s->strs_data + (long)key1; + const char *str2 = s->strs_data + (long)key2; + + return strcmp(str1, str2) == 0; +} + +struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t init_data_sz) +{ + struct strset *set = calloc(1, sizeof(*set)); + struct hashmap *hash; + int err = -ENOMEM; + + if (!set) + return ERR_PTR(-ENOMEM); + + hash = hashmap__new(strset_hash_fn, strset_equal_fn, set); + if (IS_ERR(hash)) + goto err_out; + + set->strs_data_max_len = max_data_sz; + set->strs_hash = hash; + + if (init_data) { + long off; + + set->strs_data = malloc(init_data_sz); + if (!set->strs_data) + goto err_out; + + memcpy(set->strs_data, init_data, init_data_sz); + set->strs_data_len = init_data_sz; + set->strs_data_cap = init_data_sz; + + for (off = 0; off < set->strs_data_len; off += strlen(set->strs_data + off) + 1) { + /* hashmap__add() returns EEXIST if string with the same + * content already is in the hash map + */ + err = hashmap__add(hash, (void *)off, (void *)off); + if (err == -EEXIST) + continue; /* duplicate */ + if (err) + goto err_out; + } + } + + return set; +err_out: + strset__free(set); + return ERR_PTR(err); +} + +void strset__free(struct strset *set) +{ + if (IS_ERR_OR_NULL(set)) + return; + + hashmap__free(set->strs_hash); + free(set->strs_data); + free(set); +} + +size_t strset__data_size(const struct strset *set) +{ + return set->strs_data_len; +} + +const char *strset__data(const struct strset *set) +{ + return set->strs_data; +} + +static void *strset_add_str_mem(struct strset *set, size_t add_sz) +{ + return libbpf_add_mem(&set->strs_data, &set->strs_data_cap, 1, + set->strs_data_len, set->strs_data_max_len, add_sz); +} + +/* Find string offset that corresponds to a given string *s*. + * Returns: + * - >0 offset into string data, if string is found; + * - -ENOENT, if string is not in the string data; + * - <0, on any other error. + */ +int strset__find_str(struct strset *set, const char *s) +{ + long old_off, new_off, len; + void *p; + + /* see strset__add_str() for why we do this */ + len = strlen(s) + 1; + p = strset_add_str_mem(set, len); + if (!p) + return -ENOMEM; + + new_off = set->strs_data_len; + memcpy(p, s, len); + + if (hashmap__find(set->strs_hash, (void *)new_off, (void **)&old_off)) + return old_off; + + return -ENOENT; +} + +/* Add a string s to the string data. If the string already exists, return its + * offset within string data. + * Returns: + * - > 0 offset into string data, on success; + * - < 0, on error. + */ +int strset__add_str(struct strset *set, const char *s) +{ + long old_off, new_off, len; + void *p; + int err; + + /* Hashmap keys are always offsets within set->strs_data, so to even + * look up some string from the "outside", we need to first append it + * at the end, so that it can be addressed with an offset. Luckily, + * until set->strs_data_len is incremented, that string is just a piece + * of garbage for the rest of the code, so no harm, no foul. On the + * other hand, if the string is unique, it's already appended and + * ready to be used, only a simple set->strs_data_len increment away. + */ + len = strlen(s) + 1; + p = strset_add_str_mem(set, len); + if (!p) + return -ENOMEM; + + new_off = set->strs_data_len; + memcpy(p, s, len); + + /* Now attempt to add the string, but only if the string with the same + * contents doesn't exist already (HASHMAP_ADD strategy). If such + * string exists, we'll get its offset in old_off (that's old_key). + */ + err = hashmap__insert(set->strs_hash, (void *)new_off, (void *)new_off, + HASHMAP_ADD, (const void **)&old_off, NULL); + if (err == -EEXIST) + return old_off; /* duplicated string, return existing offset */ + if (err) + return err; + + set->strs_data_len += len; /* new unique string, adjust data length */ + return new_off; +} diff --git a/tools/lib/bpf/strset.h b/tools/lib/bpf/strset.h new file mode 100644 index 000000000..b6ddf77a8 --- /dev/null +++ b/tools/lib/bpf/strset.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* Copyright (c) 2021 Facebook */ +#ifndef __LIBBPF_STRSET_H +#define __LIBBPF_STRSET_H + +#include <stdbool.h> +#include <stddef.h> + +struct strset; + +struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t init_data_sz); +void strset__free(struct strset *set); + +const char *strset__data(const struct strset *set); +size_t strset__data_size(const struct strset *set); + +int strset__find_str(struct strset *set, const char *s); +int strset__add_str(struct strset *set, const char *s); + +#endif /* __LIBBPF_STRSET_H */ diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h new file mode 100644 index 000000000..fdfd235e5 --- /dev/null +++ b/tools/lib/bpf/usdt.bpf.h @@ -0,0 +1,247 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#ifndef __USDT_BPF_H__ +#define __USDT_BPF_H__ + +#include <linux/errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +/* Below types and maps are internal implementation details of libbpf's USDT + * support and are subjects to change. Also, bpf_usdt_xxx() API helpers should + * be considered an unstable API as well and might be adjusted based on user + * feedback from using libbpf's USDT support in production. + */ + +/* User can override BPF_USDT_MAX_SPEC_CNT to change default size of internal + * map that keeps track of USDT argument specifications. This might be + * necessary if there are a lot of USDT attachments. + */ +#ifndef BPF_USDT_MAX_SPEC_CNT +#define BPF_USDT_MAX_SPEC_CNT 256 +#endif +/* User can override BPF_USDT_MAX_IP_CNT to change default size of internal + * map that keeps track of IP (memory address) mapping to USDT argument + * specification. + * Note, if kernel supports BPF cookies, this map is not used and could be + * resized all the way to 1 to save a bit of memory. + */ +#ifndef BPF_USDT_MAX_IP_CNT +#define BPF_USDT_MAX_IP_CNT (4 * BPF_USDT_MAX_SPEC_CNT) +#endif + +enum __bpf_usdt_arg_type { + BPF_USDT_ARG_CONST, + BPF_USDT_ARG_REG, + BPF_USDT_ARG_REG_DEREF, +}; + +struct __bpf_usdt_arg_spec { + /* u64 scalar interpreted depending on arg_type, see below */ + __u64 val_off; + /* arg location case, see bpf_udst_arg() for details */ + enum __bpf_usdt_arg_type arg_type; + /* offset of referenced register within struct pt_regs */ + short reg_off; + /* whether arg should be interpreted as signed value */ + bool arg_signed; + /* number of bits that need to be cleared and, optionally, + * sign-extended to cast arguments that are 1, 2, or 4 bytes + * long into final 8-byte u64/s64 value returned to user + */ + char arg_bitshift; +}; + +/* should match USDT_MAX_ARG_CNT in usdt.c exactly */ +#define BPF_USDT_MAX_ARG_CNT 12 +struct __bpf_usdt_spec { + struct __bpf_usdt_arg_spec args[BPF_USDT_MAX_ARG_CNT]; + __u64 usdt_cookie; + short arg_cnt; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, BPF_USDT_MAX_SPEC_CNT); + __type(key, int); + __type(value, struct __bpf_usdt_spec); +} __bpf_usdt_specs SEC(".maps") __weak; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, BPF_USDT_MAX_IP_CNT); + __type(key, long); + __type(value, __u32); +} __bpf_usdt_ip_to_spec_id SEC(".maps") __weak; + +extern const _Bool LINUX_HAS_BPF_COOKIE __kconfig; + +static __always_inline +int __bpf_usdt_spec_id(struct pt_regs *ctx) +{ + if (!LINUX_HAS_BPF_COOKIE) { + long ip = PT_REGS_IP(ctx); + int *spec_id_ptr; + + spec_id_ptr = bpf_map_lookup_elem(&__bpf_usdt_ip_to_spec_id, &ip); + return spec_id_ptr ? *spec_id_ptr : -ESRCH; + } + + return bpf_get_attach_cookie(ctx); +} + +/* Return number of USDT arguments defined for currently traced USDT. */ +__weak __hidden +int bpf_usdt_arg_cnt(struct pt_regs *ctx) +{ + struct __bpf_usdt_spec *spec; + int spec_id; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return -ESRCH; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return -ESRCH; + + return spec->arg_cnt; +} + +/* Fetch USDT argument #*arg_num* (zero-indexed) and put its value into *res. + * Returns 0 on success; negative error, otherwise. + * On error *res is guaranteed to be set to zero. + */ +__weak __hidden +int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) +{ + struct __bpf_usdt_spec *spec; + struct __bpf_usdt_arg_spec *arg_spec; + unsigned long val; + int err, spec_id; + + *res = 0; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return -ESRCH; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return -ESRCH; + + if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt) + return -ENOENT; + + arg_spec = &spec->args[arg_num]; + switch (arg_spec->arg_type) { + case BPF_USDT_ARG_CONST: + /* Arg is just a constant ("-4@$-9" in USDT arg spec). + * value is recorded in arg_spec->val_off directly. + */ + val = arg_spec->val_off; + break; + case BPF_USDT_ARG_REG: + /* Arg is in a register (e.g, "8@%rax" in USDT arg spec), + * so we read the contents of that register directly from + * struct pt_regs. To keep things simple user-space parts + * record offsetof(struct pt_regs, <regname>) in arg_spec->reg_off. + */ + err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); + if (err) + return err; + break; + case BPF_USDT_ARG_REG_DEREF: + /* Arg is in memory addressed by register, plus some offset + * (e.g., "-4@-1204(%rbp)" in USDT arg spec). Register is + * identified like with BPF_USDT_ARG_REG case, and the offset + * is in arg_spec->val_off. We first fetch register contents + * from pt_regs, then do another user-space probe read to + * fetch argument value itself. + */ + err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); + if (err) + return err; + err = bpf_probe_read_user(&val, sizeof(val), (void *)val + arg_spec->val_off); + if (err) + return err; +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + val >>= arg_spec->arg_bitshift; +#endif + break; + default: + return -EINVAL; + } + + /* cast arg from 1, 2, or 4 bytes to final 8 byte size clearing + * necessary upper arg_bitshift bits, with sign extension if argument + * is signed + */ + val <<= arg_spec->arg_bitshift; + if (arg_spec->arg_signed) + val = ((long)val) >> arg_spec->arg_bitshift; + else + val = val >> arg_spec->arg_bitshift; + *res = val; + return 0; +} + +/* Retrieve user-specified cookie value provided during attach as + * bpf_usdt_opts.usdt_cookie. This serves the same purpose as BPF cookie + * returned by bpf_get_attach_cookie(). Libbpf's support for USDT is itself + * utilizing BPF cookies internally, so user can't use BPF cookie directly + * for USDT programs and has to use bpf_usdt_cookie() API instead. + */ +__weak __hidden +long bpf_usdt_cookie(struct pt_regs *ctx) +{ + struct __bpf_usdt_spec *spec; + int spec_id; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return 0; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return 0; + + return spec->usdt_cookie; +} + +/* we rely on ___bpf_apply() and ___bpf_narg() macros already defined in bpf_tracing.h */ +#define ___bpf_usdt_args0() ctx +#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); (void *)_x; }) +#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); (void *)_x; }) +#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); (void *)_x; }) +#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); (void *)_x; }) +#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); (void *)_x; }) +#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); (void *)_x; }) +#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); (void *)_x; }) +#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); (void *)_x; }) +#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); (void *)_x; }) +#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); (void *)_x; }) +#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); (void *)_x; }) +#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); (void *)_x; }) +#define ___bpf_usdt_args(args...) ___bpf_apply(___bpf_usdt_args, ___bpf_narg(args))(args) + +/* + * BPF_USDT serves the same purpose for USDT handlers as BPF_PROG for + * tp_btf/fentry/fexit BPF programs and BPF_KPROBE for kprobes. + * Original struct pt_regs * context is preserved as 'ctx' argument. + */ +#define BPF_USDT(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_usdt_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + +#endif /* __USDT_BPF_H__ */ diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c new file mode 100644 index 000000000..af1cb3055 --- /dev/null +++ b/tools/lib/bpf/usdt.c @@ -0,0 +1,1519 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#include <ctype.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <libelf.h> +#include <gelf.h> +#include <unistd.h> +#include <linux/ptrace.h> +#include <linux/kernel.h> + +/* s8 will be marked as poison while it's a reg of riscv */ +#if defined(__riscv) +#define rv_s8 s8 +#endif + +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_common.h" +#include "libbpf_internal.h" +#include "hashmap.h" + +/* libbpf's USDT support consists of BPF-side state/code and user-space + * state/code working together in concert. BPF-side parts are defined in + * usdt.bpf.h header library. User-space state is encapsulated by struct + * usdt_manager and all the supporting code centered around usdt_manager. + * + * usdt.bpf.h defines two BPF maps that usdt_manager expects: USDT spec map + * and IP-to-spec-ID map, which is auxiliary map necessary for kernels that + * don't support BPF cookie (see below). These two maps are implicitly + * embedded into user's end BPF object file when user's code included + * usdt.bpf.h. This means that libbpf doesn't do anything special to create + * these USDT support maps. They are created by normal libbpf logic of + * instantiating BPF maps when opening and loading BPF object. + * + * As such, libbpf is basically unaware of the need to do anything + * USDT-related until the very first call to bpf_program__attach_usdt(), which + * can be called by user explicitly or happen automatically during skeleton + * attach (or, equivalently, through generic bpf_program__attach() call). At + * this point, libbpf will instantiate and initialize struct usdt_manager and + * store it in bpf_object. USDT manager is per-BPF object construct, as each + * independent BPF object might or might not have USDT programs, and thus all + * the expected USDT-related state. There is no coordination between two + * bpf_object in parts of USDT attachment, they are oblivious of each other's + * existence and libbpf is just oblivious, dealing with bpf_object-specific + * USDT state. + * + * Quick crash course on USDTs. + * + * From user-space application's point of view, USDT is essentially just + * a slightly special function call that normally has zero overhead, unless it + * is being traced by some external entity (e.g, BPF-based tool). Here's how + * a typical application can trigger USDT probe: + * + * #include <sys/sdt.h> // provided by systemtap-sdt-devel package + * // folly also provide similar functionality in folly/tracing/StaticTracepoint.h + * + * STAP_PROBE3(my_usdt_provider, my_usdt_probe_name, 123, x, &y); + * + * USDT is identified by it's <provider-name>:<probe-name> pair of names. Each + * individual USDT has a fixed number of arguments (3 in the above example) + * and specifies values of each argument as if it was a function call. + * + * USDT call is actually not a function call, but is instead replaced by + * a single NOP instruction (thus zero overhead, effectively). But in addition + * to that, those USDT macros generate special SHT_NOTE ELF records in + * .note.stapsdt ELF section. Here's an example USDT definition as emitted by + * `readelf -n <binary>`: + * + * stapsdt 0x00000089 NT_STAPSDT (SystemTap probe descriptors) + * Provider: test + * Name: usdt12 + * Location: 0x0000000000549df3, Base: 0x00000000008effa4, Semaphore: 0x0000000000a4606e + * Arguments: -4@-1204(%rbp) -4@%edi -8@-1216(%rbp) -8@%r8 -4@$5 -8@%r9 8@%rdx 8@%r10 -4@$-9 -2@%cx -2@%ax -1@%sil + * + * In this case we have USDT test:usdt12 with 12 arguments. + * + * Location and base are offsets used to calculate absolute IP address of that + * NOP instruction that kernel can replace with an interrupt instruction to + * trigger instrumentation code (BPF program for all that we care about). + * + * Semaphore above is and optional feature. It records an address of a 2-byte + * refcount variable (normally in '.probes' ELF section) used for signaling if + * there is anything that is attached to USDT. This is useful for user + * applications if, for example, they need to prepare some arguments that are + * passed only to USDTs and preparation is expensive. By checking if USDT is + * "activated", an application can avoid paying those costs unnecessarily. + * Recent enough kernel has built-in support for automatically managing this + * refcount, which libbpf expects and relies on. If USDT is defined without + * associated semaphore, this value will be zero. See selftests for semaphore + * examples. + * + * Arguments is the most interesting part. This USDT specification string is + * providing information about all the USDT arguments and their locations. The + * part before @ sign defined byte size of the argument (1, 2, 4, or 8) and + * whether the argument is signed or unsigned (negative size means signed). + * The part after @ sign is assembly-like definition of argument location + * (see [0] for more details). Technically, assembler can provide some pretty + * advanced definitions, but libbpf is currently supporting three most common + * cases: + * 1) immediate constant, see 5th and 9th args above (-4@$5 and -4@-9); + * 2) register value, e.g., 8@%rdx, which means "unsigned 8-byte integer + * whose value is in register %rdx"; + * 3) memory dereference addressed by register, e.g., -4@-1204(%rbp), which + * specifies signed 32-bit integer stored at offset -1204 bytes from + * memory address stored in %rbp. + * + * [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation + * + * During attachment, libbpf parses all the relevant USDT specifications and + * prepares `struct usdt_spec` (USDT spec), which is then provided to BPF-side + * code through spec map. This allows BPF applications to quickly fetch the + * actual value at runtime using a simple BPF-side code. + * + * With basics out of the way, let's go over less immediately obvious aspects + * of supporting USDTs. + * + * First, there is no special USDT BPF program type. It is actually just + * a uprobe BPF program (which for kernel, at least currently, is just a kprobe + * program, so BPF_PROG_TYPE_KPROBE program type). With the only difference + * that uprobe is usually attached at the function entry, while USDT will + * normally will be somewhere inside the function. But it should always be + * pointing to NOP instruction, which makes such uprobes the fastest uprobe + * kind. + * + * Second, it's important to realize that such STAP_PROBEn(provider, name, ...) + * macro invocations can end up being inlined many-many times, depending on + * specifics of each individual user application. So single conceptual USDT + * (identified by provider:name pair of identifiers) is, generally speaking, + * multiple uprobe locations (USDT call sites) in different places in user + * application. Further, again due to inlining, each USDT call site might end + * up having the same argument #N be located in a different place. In one call + * site it could be a constant, in another will end up in a register, and in + * yet another could be some other register or even somewhere on the stack. + * + * As such, "attaching to USDT" means (in general case) attaching the same + * uprobe BPF program to multiple target locations in user application, each + * potentially having a completely different USDT spec associated with it. + * To wire all this up together libbpf allocates a unique integer spec ID for + * each unique USDT spec. Spec IDs are allocated as sequential small integers + * so that they can be used as keys in array BPF map (for performance reasons). + * Spec ID allocation and accounting is big part of what usdt_manager is + * about. This state has to be maintained per-BPF object and coordinate + * between different USDT attachments within the same BPF object. + * + * Spec ID is the key in spec BPF map, value is the actual USDT spec layed out + * as struct usdt_spec. Each invocation of BPF program at runtime needs to + * know its associated spec ID. It gets it either through BPF cookie, which + * libbpf sets to spec ID during attach time, or, if kernel is too old to + * support BPF cookie, through IP-to-spec-ID map that libbpf maintains in such + * case. The latter means that some modes of operation can't be supported + * without BPF cookie. Such mode is attaching to shared library "generically", + * without specifying target process. In such case, it's impossible to + * calculate absolute IP addresses for IP-to-spec-ID map, and thus such mode + * is not supported without BPF cookie support. + * + * Note that libbpf is using BPF cookie functionality for its own internal + * needs, so user itself can't rely on BPF cookie feature. To that end, libbpf + * provides conceptually equivalent USDT cookie support. It's still u64 + * user-provided value that can be associated with USDT attachment. Note that + * this will be the same value for all USDT call sites within the same single + * *logical* USDT attachment. This makes sense because to user attaching to + * USDT is a single BPF program triggered for singular USDT probe. The fact + * that this is done at multiple actual locations is a mostly hidden + * implementation details. This USDT cookie value can be fetched with + * bpf_usdt_cookie(ctx) API provided by usdt.bpf.h + * + * Lastly, while single USDT can have tons of USDT call sites, it doesn't + * necessarily have that many different USDT specs. It very well might be + * that 1000 USDT call sites only need 5 different USDT specs, because all the + * arguments are typically contained in a small set of registers or stack + * locations. As such, it's wasteful to allocate as many USDT spec IDs as + * there are USDT call sites. So libbpf tries to be frugal and performs + * on-the-fly deduplication during a single USDT attachment to only allocate + * the minimal required amount of unique USDT specs (and thus spec IDs). This + * is trivially achieved by using USDT spec string (Arguments string from USDT + * note) as a lookup key in a hashmap. USDT spec string uniquely defines + * everything about how to fetch USDT arguments, so two USDT call sites + * sharing USDT spec string can safely share the same USDT spec and spec ID. + * Note, this spec string deduplication is happening only during the same USDT + * attachment, so each USDT spec shares the same USDT cookie value. This is + * not generally true for other USDT attachments within the same BPF object, + * as even if USDT spec string is the same, USDT cookie value can be + * different. It was deemed excessive to try to deduplicate across independent + * USDT attachments by taking into account USDT spec string *and* USDT cookie + * value, which would complicated spec ID accounting significantly for little + * gain. + */ + +#define USDT_BASE_SEC ".stapsdt.base" +#define USDT_SEMA_SEC ".probes" +#define USDT_NOTE_SEC ".note.stapsdt" +#define USDT_NOTE_TYPE 3 +#define USDT_NOTE_NAME "stapsdt" + +/* should match exactly enum __bpf_usdt_arg_type from usdt.bpf.h */ +enum usdt_arg_type { + USDT_ARG_CONST, + USDT_ARG_REG, + USDT_ARG_REG_DEREF, +}; + +/* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */ +struct usdt_arg_spec { + __u64 val_off; + enum usdt_arg_type arg_type; + short reg_off; + bool arg_signed; + char arg_bitshift; +}; + +/* should match BPF_USDT_MAX_ARG_CNT in usdt.bpf.h */ +#define USDT_MAX_ARG_CNT 12 + +/* should match struct __bpf_usdt_spec from usdt.bpf.h */ +struct usdt_spec { + struct usdt_arg_spec args[USDT_MAX_ARG_CNT]; + __u64 usdt_cookie; + short arg_cnt; +}; + +struct usdt_note { + const char *provider; + const char *name; + /* USDT args specification string, e.g.: + * "-4@%esi -4@-24(%rbp) -4@%ecx 2@%ax 8@%rdx" + */ + const char *args; + long loc_addr; + long base_addr; + long sema_addr; +}; + +struct usdt_target { + long abs_ip; + long rel_ip; + long sema_off; + struct usdt_spec spec; + const char *spec_str; +}; + +struct usdt_manager { + struct bpf_map *specs_map; + struct bpf_map *ip_to_spec_id_map; + + int *free_spec_ids; + size_t free_spec_cnt; + size_t next_free_spec_id; + + bool has_bpf_cookie; + bool has_sema_refcnt; +}; + +struct usdt_manager *usdt_manager_new(struct bpf_object *obj) +{ + static const char *ref_ctr_sysfs_path = "/sys/bus/event_source/devices/uprobe/format/ref_ctr_offset"; + struct usdt_manager *man; + struct bpf_map *specs_map, *ip_to_spec_id_map; + + specs_map = bpf_object__find_map_by_name(obj, "__bpf_usdt_specs"); + ip_to_spec_id_map = bpf_object__find_map_by_name(obj, "__bpf_usdt_ip_to_spec_id"); + if (!specs_map || !ip_to_spec_id_map) { + pr_warn("usdt: failed to find USDT support BPF maps, did you forget to include bpf/usdt.bpf.h?\n"); + return ERR_PTR(-ESRCH); + } + + man = calloc(1, sizeof(*man)); + if (!man) + return ERR_PTR(-ENOMEM); + + man->specs_map = specs_map; + man->ip_to_spec_id_map = ip_to_spec_id_map; + + /* Detect if BPF cookie is supported for kprobes. + * We don't need IP-to-ID mapping if we can use BPF cookies. + * Added in: 7adfc6c9b315 ("bpf: Add bpf_get_attach_cookie() BPF helper to access bpf_cookie value") + */ + man->has_bpf_cookie = kernel_supports(obj, FEAT_BPF_COOKIE); + + /* Detect kernel support for automatic refcounting of USDT semaphore. + * If this is not supported, USDTs with semaphores will not be supported. + * Added in: a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe") + */ + man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0; + + return man; +} + +void usdt_manager_free(struct usdt_manager *man) +{ + if (IS_ERR_OR_NULL(man)) + return; + + free(man->free_spec_ids); + free(man); +} + +static int sanity_check_usdt_elf(Elf *elf, const char *path) +{ + GElf_Ehdr ehdr; + int endianness; + + if (elf_kind(elf) != ELF_K_ELF) { + pr_warn("usdt: unrecognized ELF kind %d for '%s'\n", elf_kind(elf), path); + return -EBADF; + } + + switch (gelf_getclass(elf)) { + case ELFCLASS64: + if (sizeof(void *) != 8) { + pr_warn("usdt: attaching to 64-bit ELF binary '%s' is not supported\n", path); + return -EBADF; + } + break; + case ELFCLASS32: + if (sizeof(void *) != 4) { + pr_warn("usdt: attaching to 32-bit ELF binary '%s' is not supported\n", path); + return -EBADF; + } + break; + default: + pr_warn("usdt: unsupported ELF class for '%s'\n", path); + return -EBADF; + } + + if (!gelf_getehdr(elf, &ehdr)) + return -EINVAL; + + if (ehdr.e_type != ET_EXEC && ehdr.e_type != ET_DYN) { + pr_warn("usdt: unsupported type of ELF binary '%s' (%d), only ET_EXEC and ET_DYN are supported\n", + path, ehdr.e_type); + return -EBADF; + } + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + endianness = ELFDATA2LSB; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + endianness = ELFDATA2MSB; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + if (endianness != ehdr.e_ident[EI_DATA]) { + pr_warn("usdt: ELF endianness mismatch for '%s'\n", path); + return -EBADF; + } + + return 0; +} + +static int find_elf_sec_by_name(Elf *elf, const char *sec_name, GElf_Shdr *shdr, Elf_Scn **scn) +{ + Elf_Scn *sec = NULL; + size_t shstrndx; + + if (elf_getshdrstrndx(elf, &shstrndx)) + return -EINVAL; + + /* check if ELF is corrupted and avoid calling elf_strptr if yes */ + if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) + return -EINVAL; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + char *name; + + if (!gelf_getshdr(sec, shdr)) + return -EINVAL; + + name = elf_strptr(elf, shstrndx, shdr->sh_name); + if (name && strcmp(sec_name, name) == 0) { + *scn = sec; + return 0; + } + } + + return -ENOENT; +} + +struct elf_seg { + long start; + long end; + long offset; + bool is_exec; +}; + +static int cmp_elf_segs(const void *_a, const void *_b) +{ + const struct elf_seg *a = _a; + const struct elf_seg *b = _b; + + return a->start < b->start ? -1 : 1; +} + +static int parse_elf_segs(Elf *elf, const char *path, struct elf_seg **segs, size_t *seg_cnt) +{ + GElf_Phdr phdr; + size_t n; + int i, err; + struct elf_seg *seg; + void *tmp; + + *seg_cnt = 0; + + if (elf_getphdrnum(elf, &n)) { + err = -errno; + return err; + } + + for (i = 0; i < n; i++) { + if (!gelf_getphdr(elf, i, &phdr)) { + err = -errno; + return err; + } + + pr_debug("usdt: discovered PHDR #%d in '%s': vaddr 0x%lx memsz 0x%lx offset 0x%lx type 0x%lx flags 0x%lx\n", + i, path, (long)phdr.p_vaddr, (long)phdr.p_memsz, (long)phdr.p_offset, + (long)phdr.p_type, (long)phdr.p_flags); + if (phdr.p_type != PT_LOAD) + continue; + + tmp = libbpf_reallocarray(*segs, *seg_cnt + 1, sizeof(**segs)); + if (!tmp) + return -ENOMEM; + + *segs = tmp; + seg = *segs + *seg_cnt; + (*seg_cnt)++; + + seg->start = phdr.p_vaddr; + seg->end = phdr.p_vaddr + phdr.p_memsz; + seg->offset = phdr.p_offset; + seg->is_exec = phdr.p_flags & PF_X; + } + + if (*seg_cnt == 0) { + pr_warn("usdt: failed to find PT_LOAD program headers in '%s'\n", path); + return -ESRCH; + } + + qsort(*segs, *seg_cnt, sizeof(**segs), cmp_elf_segs); + return 0; +} + +static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs, size_t *seg_cnt) +{ + char path[PATH_MAX], line[PATH_MAX], mode[16]; + size_t seg_start, seg_end, seg_off; + struct elf_seg *seg; + int tmp_pid, i, err; + FILE *f; + + *seg_cnt = 0; + + /* Handle containerized binaries only accessible from + * /proc/<pid>/root/<path>. They will be reported as just /<path> in + * /proc/<pid>/maps. + */ + if (sscanf(lib_path, "/proc/%d/root%s", &tmp_pid, path) == 2 && pid == tmp_pid) + goto proceed; + + if (!realpath(lib_path, path)) { + pr_warn("usdt: failed to get absolute path of '%s' (err %d), using path as is...\n", + lib_path, -errno); + libbpf_strlcpy(path, lib_path, sizeof(path)); + } + +proceed: + sprintf(line, "/proc/%d/maps", pid); + f = fopen(line, "r"); + if (!f) { + err = -errno; + pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n", + line, lib_path, err); + return err; + } + + /* We need to handle lines with no path at the end: + * + * 7f5c6f5d1000-7f5c6f5d3000 rw-p 001c7000 08:04 21238613 /usr/lib64/libc-2.17.so + * 7f5c6f5d3000-7f5c6f5d8000 rw-p 00000000 00:00 0 + * 7f5c6f5d8000-7f5c6f5d9000 r-xp 00000000 103:01 362990598 /data/users/andriin/linux/tools/bpf/usdt/libhello_usdt.so + */ + while (fscanf(f, "%zx-%zx %s %zx %*s %*d%[^\n]\n", + &seg_start, &seg_end, mode, &seg_off, line) == 5) { + void *tmp; + + /* to handle no path case (see above) we need to capture line + * without skipping any whitespaces. So we need to strip + * leading whitespaces manually here + */ + i = 0; + while (isblank(line[i])) + i++; + if (strcmp(line + i, path) != 0) + continue; + + pr_debug("usdt: discovered segment for lib '%s': addrs %zx-%zx mode %s offset %zx\n", + path, seg_start, seg_end, mode, seg_off); + + /* ignore non-executable sections for shared libs */ + if (mode[2] != 'x') + continue; + + tmp = libbpf_reallocarray(*segs, *seg_cnt + 1, sizeof(**segs)); + if (!tmp) { + err = -ENOMEM; + goto err_out; + } + + *segs = tmp; + seg = *segs + *seg_cnt; + *seg_cnt += 1; + + seg->start = seg_start; + seg->end = seg_end; + seg->offset = seg_off; + seg->is_exec = true; + } + + if (*seg_cnt == 0) { + pr_warn("usdt: failed to find '%s' (resolved to '%s') within PID %d memory mappings\n", + lib_path, path, pid); + err = -ESRCH; + goto err_out; + } + + qsort(*segs, *seg_cnt, sizeof(**segs), cmp_elf_segs); + err = 0; +err_out: + fclose(f); + return err; +} + +static struct elf_seg *find_elf_seg(struct elf_seg *segs, size_t seg_cnt, long virtaddr) +{ + struct elf_seg *seg; + int i; + + /* for ELF binaries (both executables and shared libraries), we are + * given virtual address (absolute for executables, relative for + * libraries) which should match address range of [seg_start, seg_end) + */ + for (i = 0, seg = segs; i < seg_cnt; i++, seg++) { + if (seg->start <= virtaddr && virtaddr < seg->end) + return seg; + } + return NULL; +} + +static struct elf_seg *find_vma_seg(struct elf_seg *segs, size_t seg_cnt, long offset) +{ + struct elf_seg *seg; + int i; + + /* for VMA segments from /proc/<pid>/maps file, provided "address" is + * actually a file offset, so should be fall within logical + * offset-based range of [offset_start, offset_end) + */ + for (i = 0, seg = segs; i < seg_cnt; i++, seg++) { + if (seg->offset <= offset && offset < seg->offset + (seg->end - seg->start)) + return seg; + } + return NULL; +} + +static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, + const char *data, size_t name_off, size_t desc_off, + struct usdt_note *usdt_note); + +static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie); + +static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *path, pid_t pid, + const char *usdt_provider, const char *usdt_name, __u64 usdt_cookie, + struct usdt_target **out_targets, size_t *out_target_cnt) +{ + size_t off, name_off, desc_off, seg_cnt = 0, vma_seg_cnt = 0, target_cnt = 0; + struct elf_seg *segs = NULL, *vma_segs = NULL; + struct usdt_target *targets = NULL, *target; + long base_addr = 0; + Elf_Scn *notes_scn, *base_scn; + GElf_Shdr base_shdr, notes_shdr; + GElf_Ehdr ehdr; + GElf_Nhdr nhdr; + Elf_Data *data; + int err; + + *out_targets = NULL; + *out_target_cnt = 0; + + err = find_elf_sec_by_name(elf, USDT_NOTE_SEC, ¬es_shdr, ¬es_scn); + if (err) { + pr_warn("usdt: no USDT notes section (%s) found in '%s'\n", USDT_NOTE_SEC, path); + return err; + } + + if (notes_shdr.sh_type != SHT_NOTE || !gelf_getehdr(elf, &ehdr)) { + pr_warn("usdt: invalid USDT notes section (%s) in '%s'\n", USDT_NOTE_SEC, path); + return -EINVAL; + } + + err = parse_elf_segs(elf, path, &segs, &seg_cnt); + if (err) { + pr_warn("usdt: failed to process ELF program segments for '%s': %d\n", path, err); + goto err_out; + } + + /* .stapsdt.base ELF section is optional, but is used for prelink + * offset compensation (see a big comment further below) + */ + if (find_elf_sec_by_name(elf, USDT_BASE_SEC, &base_shdr, &base_scn) == 0) + base_addr = base_shdr.sh_addr; + + data = elf_getdata(notes_scn, 0); + off = 0; + while ((off = gelf_getnote(data, off, &nhdr, &name_off, &desc_off)) > 0) { + long usdt_abs_ip, usdt_rel_ip, usdt_sema_off = 0; + struct usdt_note note; + struct elf_seg *seg = NULL; + void *tmp; + + err = parse_usdt_note(elf, path, &nhdr, data->d_buf, name_off, desc_off, ¬e); + if (err) + goto err_out; + + if (strcmp(note.provider, usdt_provider) != 0 || strcmp(note.name, usdt_name) != 0) + continue; + + /* We need to compensate "prelink effect". See [0] for details, + * relevant parts quoted here: + * + * Each SDT probe also expands into a non-allocated ELF note. You can + * find this by looking at SHT_NOTE sections and decoding the format; + * see below for details. Because the note is non-allocated, it means + * there is no runtime cost, and also preserved in both stripped files + * and .debug files. + * + * However, this means that prelink won't adjust the note's contents + * for address offsets. Instead, this is done via the .stapsdt.base + * section. This is a special section that is added to the text. We + * will only ever have one of these sections in a final link and it + * will only ever be one byte long. Nothing about this section itself + * matters, we just use it as a marker to detect prelink address + * adjustments. + * + * Each probe note records the link-time address of the .stapsdt.base + * section alongside the probe PC address. The decoder compares the + * base address stored in the note with the .stapsdt.base section's + * sh_addr. Initially these are the same, but the section header will + * be adjusted by prelink. So the decoder applies the difference to + * the probe PC address to get the correct prelinked PC address; the + * same adjustment is applied to the semaphore address, if any. + * + * [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation + */ + usdt_abs_ip = note.loc_addr; + if (base_addr) + usdt_abs_ip += base_addr - note.base_addr; + + /* When attaching uprobes (which is what USDTs basically are) + * kernel expects file offset to be specified, not a relative + * virtual address, so we need to translate virtual address to + * file offset, for both ET_EXEC and ET_DYN binaries. + */ + seg = find_elf_seg(segs, seg_cnt, usdt_abs_ip); + if (!seg) { + err = -ESRCH; + pr_warn("usdt: failed to find ELF program segment for '%s:%s' in '%s' at IP 0x%lx\n", + usdt_provider, usdt_name, path, usdt_abs_ip); + goto err_out; + } + if (!seg->is_exec) { + err = -ESRCH; + pr_warn("usdt: matched ELF binary '%s' segment [0x%lx, 0x%lx) for '%s:%s' at IP 0x%lx is not executable\n", + path, seg->start, seg->end, usdt_provider, usdt_name, + usdt_abs_ip); + goto err_out; + } + /* translate from virtual address to file offset */ + usdt_rel_ip = usdt_abs_ip - seg->start + seg->offset; + + if (ehdr.e_type == ET_DYN && !man->has_bpf_cookie) { + /* If we don't have BPF cookie support but need to + * attach to a shared library, we'll need to know and + * record absolute addresses of attach points due to + * the need to lookup USDT spec by absolute IP of + * triggered uprobe. Doing this resolution is only + * possible when we have a specific PID of the process + * that's using specified shared library. BPF cookie + * removes the absolute address limitation as we don't + * need to do this lookup (we just use BPF cookie as + * an index of USDT spec), so for newer kernels with + * BPF cookie support libbpf supports USDT attachment + * to shared libraries with no PID filter. + */ + if (pid < 0) { + pr_warn("usdt: attaching to shared libraries without specific PID is not supported on current kernel\n"); + err = -ENOTSUP; + goto err_out; + } + + /* vma_segs are lazily initialized only if necessary */ + if (vma_seg_cnt == 0) { + err = parse_vma_segs(pid, path, &vma_segs, &vma_seg_cnt); + if (err) { + pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %d\n", + pid, path, err); + goto err_out; + } + } + + seg = find_vma_seg(vma_segs, vma_seg_cnt, usdt_rel_ip); + if (!seg) { + err = -ESRCH; + pr_warn("usdt: failed to find shared lib memory segment for '%s:%s' in '%s' at relative IP 0x%lx\n", + usdt_provider, usdt_name, path, usdt_rel_ip); + goto err_out; + } + + usdt_abs_ip = seg->start - seg->offset + usdt_rel_ip; + } + + pr_debug("usdt: probe for '%s:%s' in %s '%s': addr 0x%lx base 0x%lx (resolved abs_ip 0x%lx rel_ip 0x%lx) args '%s' in segment [0x%lx, 0x%lx) at offset 0x%lx\n", + usdt_provider, usdt_name, ehdr.e_type == ET_EXEC ? "exec" : "lib ", path, + note.loc_addr, note.base_addr, usdt_abs_ip, usdt_rel_ip, note.args, + seg ? seg->start : 0, seg ? seg->end : 0, seg ? seg->offset : 0); + + /* Adjust semaphore address to be a file offset */ + if (note.sema_addr) { + if (!man->has_sema_refcnt) { + pr_warn("usdt: kernel doesn't support USDT semaphore refcounting for '%s:%s' in '%s'\n", + usdt_provider, usdt_name, path); + err = -ENOTSUP; + goto err_out; + } + + seg = find_elf_seg(segs, seg_cnt, note.sema_addr); + if (!seg) { + err = -ESRCH; + pr_warn("usdt: failed to find ELF loadable segment with semaphore of '%s:%s' in '%s' at 0x%lx\n", + usdt_provider, usdt_name, path, note.sema_addr); + goto err_out; + } + if (seg->is_exec) { + err = -ESRCH; + pr_warn("usdt: matched ELF binary '%s' segment [0x%lx, 0x%lx] for semaphore of '%s:%s' at 0x%lx is executable\n", + path, seg->start, seg->end, usdt_provider, usdt_name, + note.sema_addr); + goto err_out; + } + + usdt_sema_off = note.sema_addr - seg->start + seg->offset; + + pr_debug("usdt: sema for '%s:%s' in %s '%s': addr 0x%lx base 0x%lx (resolved 0x%lx) in segment [0x%lx, 0x%lx] at offset 0x%lx\n", + usdt_provider, usdt_name, ehdr.e_type == ET_EXEC ? "exec" : "lib ", + path, note.sema_addr, note.base_addr, usdt_sema_off, + seg->start, seg->end, seg->offset); + } + + /* Record adjusted addresses and offsets and parse USDT spec */ + tmp = libbpf_reallocarray(targets, target_cnt + 1, sizeof(*targets)); + if (!tmp) { + err = -ENOMEM; + goto err_out; + } + targets = tmp; + + target = &targets[target_cnt]; + memset(target, 0, sizeof(*target)); + + target->abs_ip = usdt_abs_ip; + target->rel_ip = usdt_rel_ip; + target->sema_off = usdt_sema_off; + + /* notes.args references strings from Elf itself, so they can + * be referenced safely until elf_end() call + */ + target->spec_str = note.args; + + err = parse_usdt_spec(&target->spec, ¬e, usdt_cookie); + if (err) + goto err_out; + + target_cnt++; + } + + *out_targets = targets; + *out_target_cnt = target_cnt; + err = target_cnt; + +err_out: + free(segs); + free(vma_segs); + if (err < 0) + free(targets); + return err; +} + +struct bpf_link_usdt { + struct bpf_link link; + + struct usdt_manager *usdt_man; + + size_t spec_cnt; + int *spec_ids; + + size_t uprobe_cnt; + struct { + long abs_ip; + struct bpf_link *link; + } *uprobes; +}; + +static int bpf_link_usdt_detach(struct bpf_link *link) +{ + struct bpf_link_usdt *usdt_link = container_of(link, struct bpf_link_usdt, link); + struct usdt_manager *man = usdt_link->usdt_man; + int i; + + for (i = 0; i < usdt_link->uprobe_cnt; i++) { + /* detach underlying uprobe link */ + bpf_link__destroy(usdt_link->uprobes[i].link); + /* there is no need to update specs map because it will be + * unconditionally overwritten on subsequent USDT attaches, + * but if BPF cookies are not used we need to remove entry + * from ip_to_spec_id map, otherwise we'll run into false + * conflicting IP errors + */ + if (!man->has_bpf_cookie) { + /* not much we can do about errors here */ + (void)bpf_map_delete_elem(bpf_map__fd(man->ip_to_spec_id_map), + &usdt_link->uprobes[i].abs_ip); + } + } + + /* try to return the list of previously used spec IDs to usdt_manager + * for future reuse for subsequent USDT attaches + */ + if (!man->free_spec_ids) { + /* if there were no free spec IDs yet, just transfer our IDs */ + man->free_spec_ids = usdt_link->spec_ids; + man->free_spec_cnt = usdt_link->spec_cnt; + usdt_link->spec_ids = NULL; + } else { + /* otherwise concat IDs */ + size_t new_cnt = man->free_spec_cnt + usdt_link->spec_cnt; + int *new_free_ids; + + new_free_ids = libbpf_reallocarray(man->free_spec_ids, new_cnt, + sizeof(*new_free_ids)); + /* If we couldn't resize free_spec_ids, we'll just leak + * a bunch of free IDs; this is very unlikely to happen and if + * system is so exhausted on memory, it's the least of user's + * concerns, probably. + * So just do our best here to return those IDs to usdt_manager. + * Another edge case when we can legitimately get NULL is when + * new_cnt is zero, which can happen in some edge cases, so we + * need to be careful about that. + */ + if (new_free_ids || new_cnt == 0) { + memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids, + usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids)); + man->free_spec_ids = new_free_ids; + man->free_spec_cnt = new_cnt; + } + } + + return 0; +} + +static void bpf_link_usdt_dealloc(struct bpf_link *link) +{ + struct bpf_link_usdt *usdt_link = container_of(link, struct bpf_link_usdt, link); + + free(usdt_link->spec_ids); + free(usdt_link->uprobes); + free(usdt_link); +} + +static size_t specs_hash_fn(const void *key, void *ctx) +{ + const char *s = key; + + return str_hash(s); +} + +static bool specs_equal_fn(const void *key1, const void *key2, void *ctx) +{ + const char *s1 = key1; + const char *s2 = key2; + + return strcmp(s1, s2) == 0; +} + +static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash, + struct bpf_link_usdt *link, struct usdt_target *target, + int *spec_id, bool *is_new) +{ + void *tmp; + int err; + + /* check if we already allocated spec ID for this spec string */ + if (hashmap__find(specs_hash, target->spec_str, &tmp)) { + *spec_id = (long)tmp; + *is_new = false; + return 0; + } + + /* otherwise it's a new ID that needs to be set up in specs map and + * returned back to usdt_manager when USDT link is detached + */ + tmp = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids)); + if (!tmp) + return -ENOMEM; + link->spec_ids = tmp; + + /* get next free spec ID, giving preference to free list, if not empty */ + if (man->free_spec_cnt) { + *spec_id = man->free_spec_ids[man->free_spec_cnt - 1]; + + /* cache spec ID for current spec string for future lookups */ + err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id); + if (err) + return err; + + man->free_spec_cnt--; + } else { + /* don't allocate spec ID bigger than what fits in specs map */ + if (man->next_free_spec_id >= bpf_map__max_entries(man->specs_map)) + return -E2BIG; + + *spec_id = man->next_free_spec_id; + + /* cache spec ID for current spec string for future lookups */ + err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id); + if (err) + return err; + + man->next_free_spec_id++; + } + + /* remember new spec ID in the link for later return back to free list on detach */ + link->spec_ids[link->spec_cnt] = *spec_id; + link->spec_cnt++; + *is_new = true; + return 0; +} + +struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct bpf_program *prog, + pid_t pid, const char *path, + const char *usdt_provider, const char *usdt_name, + __u64 usdt_cookie) +{ + int i, fd, err, spec_map_fd, ip_map_fd; + LIBBPF_OPTS(bpf_uprobe_opts, opts); + struct hashmap *specs_hash = NULL; + struct bpf_link_usdt *link = NULL; + struct usdt_target *targets = NULL; + size_t target_cnt; + Elf *elf; + + spec_map_fd = bpf_map__fd(man->specs_map); + ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map); + + /* TODO: perform path resolution similar to uprobe's */ + fd = open(path, O_RDONLY); + if (fd < 0) { + err = -errno; + pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err); + return libbpf_err_ptr(err); + } + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) { + err = -EBADF; + pr_warn("usdt: failed to parse ELF binary '%s': %s\n", path, elf_errmsg(-1)); + goto err_out; + } + + err = sanity_check_usdt_elf(elf, path); + if (err) + goto err_out; + + /* normalize PID filter */ + if (pid < 0) + pid = -1; + else if (pid == 0) + pid = getpid(); + + /* discover USDT in given binary, optionally limiting + * activations to a given PID, if pid > 0 + */ + err = collect_usdt_targets(man, elf, path, pid, usdt_provider, usdt_name, + usdt_cookie, &targets, &target_cnt); + if (err <= 0) { + err = (err == 0) ? -ENOENT : err; + goto err_out; + } + + specs_hash = hashmap__new(specs_hash_fn, specs_equal_fn, NULL); + if (IS_ERR(specs_hash)) { + err = PTR_ERR(specs_hash); + goto err_out; + } + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto err_out; + } + + link->usdt_man = man; + link->link.detach = &bpf_link_usdt_detach; + link->link.dealloc = &bpf_link_usdt_dealloc; + + link->uprobes = calloc(target_cnt, sizeof(*link->uprobes)); + if (!link->uprobes) { + err = -ENOMEM; + goto err_out; + } + + for (i = 0; i < target_cnt; i++) { + struct usdt_target *target = &targets[i]; + struct bpf_link *uprobe_link; + bool is_new; + int spec_id; + + /* Spec ID can be either reused or newly allocated. If it is + * newly allocated, we'll need to fill out spec map, otherwise + * entire spec should be valid and can be just used by a new + * uprobe. We reuse spec when USDT arg spec is identical. We + * also never share specs between two different USDT + * attachments ("links"), so all the reused specs already + * share USDT cookie value implicitly. + */ + err = allocate_spec_id(man, specs_hash, link, target, &spec_id, &is_new); + if (err) + goto err_out; + + if (is_new && bpf_map_update_elem(spec_map_fd, &spec_id, &target->spec, BPF_ANY)) { + err = -errno; + pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %d\n", + spec_id, usdt_provider, usdt_name, path, err); + goto err_out; + } + if (!man->has_bpf_cookie && + bpf_map_update_elem(ip_map_fd, &target->abs_ip, &spec_id, BPF_NOEXIST)) { + err = -errno; + if (err == -EEXIST) { + pr_warn("usdt: IP collision detected for spec #%d for '%s:%s' in '%s'\n", + spec_id, usdt_provider, usdt_name, path); + } else { + pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %d\n", + target->abs_ip, spec_id, usdt_provider, usdt_name, + path, err); + } + goto err_out; + } + + opts.ref_ctr_offset = target->sema_off; + opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0; + uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path, + target->rel_ip, &opts); + err = libbpf_get_error(uprobe_link); + if (err) { + pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n", + i, usdt_provider, usdt_name, path, err); + goto err_out; + } + + link->uprobes[i].link = uprobe_link; + link->uprobes[i].abs_ip = target->abs_ip; + link->uprobe_cnt++; + } + + free(targets); + hashmap__free(specs_hash); + elf_end(elf); + close(fd); + + return &link->link; + +err_out: + if (link) + bpf_link__destroy(&link->link); + free(targets); + hashmap__free(specs_hash); + if (elf) + elf_end(elf); + close(fd); + return libbpf_err_ptr(err); +} + +/* Parse out USDT ELF note from '.note.stapsdt' section. + * Logic inspired by perf's code. + */ +static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, + const char *data, size_t name_off, size_t desc_off, + struct usdt_note *note) +{ + const char *provider, *name, *args; + long addrs[3]; + size_t len; + + /* sanity check USDT note name and type first */ + if (strncmp(data + name_off, USDT_NOTE_NAME, nhdr->n_namesz) != 0) + return -EINVAL; + if (nhdr->n_type != USDT_NOTE_TYPE) + return -EINVAL; + + /* sanity check USDT note contents ("description" in ELF terminology) */ + len = nhdr->n_descsz; + data = data + desc_off; + + /* +3 is the very minimum required to store three empty strings */ + if (len < sizeof(addrs) + 3) + return -EINVAL; + + /* get location, base, and semaphore addrs */ + memcpy(&addrs, data, sizeof(addrs)); + + /* parse string fields: provider, name, args */ + provider = data + sizeof(addrs); + + name = (const char *)memchr(provider, '\0', data + len - provider); + if (!name) /* non-zero-terminated provider */ + return -EINVAL; + name++; + if (name >= data + len || *name == '\0') /* missing or empty name */ + return -EINVAL; + + args = memchr(name, '\0', data + len - name); + if (!args) /* non-zero-terminated name */ + return -EINVAL; + ++args; + if (args >= data + len) /* missing arguments spec */ + return -EINVAL; + + note->provider = provider; + note->name = name; + if (*args == '\0' || *args == ':') + note->args = ""; + else + note->args = args; + note->loc_addr = addrs[0]; + note->base_addr = addrs[1]; + note->sema_addr = addrs[2]; + + return 0; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg); + +static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie) +{ + const char *s; + int len; + + spec->usdt_cookie = usdt_cookie; + spec->arg_cnt = 0; + + s = note->args; + while (s[0]) { + if (spec->arg_cnt >= USDT_MAX_ARG_CNT) { + pr_warn("usdt: too many USDT arguments (> %d) for '%s:%s' with args spec '%s'\n", + USDT_MAX_ARG_CNT, note->provider, note->name, note->args); + return -E2BIG; + } + + len = parse_usdt_arg(s, spec->arg_cnt, &spec->args[spec->arg_cnt]); + if (len < 0) + return len; + + s += len; + spec->arg_cnt++; + } + + return 0; +} + +/* Architecture-specific logic for parsing USDT argument location specs */ + +#if defined(__x86_64__) || defined(__i386__) + +static int calc_pt_regs_off(const char *reg_name) +{ + static struct { + const char *names[4]; + size_t pt_regs_off; + } reg_map[] = { +#ifdef __x86_64__ +#define reg_off(reg64, reg32) offsetof(struct pt_regs, reg64) +#else +#define reg_off(reg64, reg32) offsetof(struct pt_regs, reg32) +#endif + { {"rip", "eip", "", ""}, reg_off(rip, eip) }, + { {"rax", "eax", "ax", "al"}, reg_off(rax, eax) }, + { {"rbx", "ebx", "bx", "bl"}, reg_off(rbx, ebx) }, + { {"rcx", "ecx", "cx", "cl"}, reg_off(rcx, ecx) }, + { {"rdx", "edx", "dx", "dl"}, reg_off(rdx, edx) }, + { {"rsi", "esi", "si", "sil"}, reg_off(rsi, esi) }, + { {"rdi", "edi", "di", "dil"}, reg_off(rdi, edi) }, + { {"rbp", "ebp", "bp", "bpl"}, reg_off(rbp, ebp) }, + { {"rsp", "esp", "sp", "spl"}, reg_off(rsp, esp) }, +#undef reg_off +#ifdef __x86_64__ + { {"r8", "r8d", "r8w", "r8b"}, offsetof(struct pt_regs, r8) }, + { {"r9", "r9d", "r9w", "r9b"}, offsetof(struct pt_regs, r9) }, + { {"r10", "r10d", "r10w", "r10b"}, offsetof(struct pt_regs, r10) }, + { {"r11", "r11d", "r11w", "r11b"}, offsetof(struct pt_regs, r11) }, + { {"r12", "r12d", "r12w", "r12b"}, offsetof(struct pt_regs, r12) }, + { {"r13", "r13d", "r13w", "r13b"}, offsetof(struct pt_regs, r13) }, + { {"r14", "r14d", "r14w", "r14b"}, offsetof(struct pt_regs, r14) }, + { {"r15", "r15d", "r15w", "r15b"}, offsetof(struct pt_regs, r15) }, +#endif + }; + int i, j; + + for (i = 0; i < ARRAY_SIZE(reg_map); i++) { + for (j = 0; j < ARRAY_SIZE(reg_map[i].names); j++) { + if (strcmp(reg_name, reg_map[i].names[j]) == 0) + return reg_map[i].pt_regs_off; + } + } + + pr_warn("usdt: unrecognized register '%s'\n", reg_name); + return -ENOENT; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + char *reg_name = NULL; + int arg_sz, len, reg_off; + long off; + + if (sscanf(arg_str, " %d @ %ld ( %%%m[^)] ) %n", &arg_sz, &off, ®_name, &len) == 3) { + /* Memory dereference case, e.g., -4@-20(%rbp) */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ %%%ms %n", &arg_sz, ®_name, &len) == 2) { + /* Register read case, e.g., -4@%eax */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ $%ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@$71 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return -EINVAL; + } + + return len; +} + +#elif defined(__s390x__) + +/* Do not support __s390__ for now, since user_pt_regs is broken with -m31. */ + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + unsigned int reg; + int arg_sz, len; + long off; + + if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", &arg_sz, &off, ®, &len) == 3) { + /* Memory dereference case, e.g., -2@-28(%r15) */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + if (reg > 15) { + pr_warn("usdt: unrecognized register '%%r%u'\n", reg); + return -EINVAL; + } + arg->reg_off = offsetof(user_pt_regs, gprs[reg]); + } else if (sscanf(arg_str, " %d @ %%r%u %n", &arg_sz, ®, &len) == 2) { + /* Register read case, e.g., -8@%r0 */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + if (reg > 15) { + pr_warn("usdt: unrecognized register '%%r%u'\n", reg); + return -EINVAL; + } + arg->reg_off = offsetof(user_pt_regs, gprs[reg]); + } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@71 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return -EINVAL; + } + + return len; +} + +#elif defined(__aarch64__) + +static int calc_pt_regs_off(const char *reg_name) +{ + int reg_num; + + if (sscanf(reg_name, "x%d", ®_num) == 1) { + if (reg_num >= 0 && reg_num < 31) + return offsetof(struct user_pt_regs, regs[reg_num]); + } else if (strcmp(reg_name, "sp") == 0) { + return offsetof(struct user_pt_regs, sp); + } + pr_warn("usdt: unrecognized register '%s'\n", reg_name); + return -ENOENT; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + char reg_name[16]; + int arg_sz, len, reg_off; + long off; + + if (sscanf(arg_str, " %d @ \[ %15[a-z0-9], %ld ] %n", &arg_sz, reg_name, &off, &len) == 3) { + /* Memory dereference case, e.g., -4@[sp, 96] */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", &arg_sz, reg_name, &len) == 2) { + /* Memory dereference case, e.g., -4@[sp] */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = 0; + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@5 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) { + /* Register read case, e.g., -8@x4 */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return -EINVAL; + } + + return len; +} + +#elif defined(__riscv) + +static int calc_pt_regs_off(const char *reg_name) +{ + static struct { + const char *name; + size_t pt_regs_off; + } reg_map[] = { + { "ra", offsetof(struct user_regs_struct, ra) }, + { "sp", offsetof(struct user_regs_struct, sp) }, + { "gp", offsetof(struct user_regs_struct, gp) }, + { "tp", offsetof(struct user_regs_struct, tp) }, + { "a0", offsetof(struct user_regs_struct, a0) }, + { "a1", offsetof(struct user_regs_struct, a1) }, + { "a2", offsetof(struct user_regs_struct, a2) }, + { "a3", offsetof(struct user_regs_struct, a3) }, + { "a4", offsetof(struct user_regs_struct, a4) }, + { "a5", offsetof(struct user_regs_struct, a5) }, + { "a6", offsetof(struct user_regs_struct, a6) }, + { "a7", offsetof(struct user_regs_struct, a7) }, + { "s0", offsetof(struct user_regs_struct, s0) }, + { "s1", offsetof(struct user_regs_struct, s1) }, + { "s2", offsetof(struct user_regs_struct, s2) }, + { "s3", offsetof(struct user_regs_struct, s3) }, + { "s4", offsetof(struct user_regs_struct, s4) }, + { "s5", offsetof(struct user_regs_struct, s5) }, + { "s6", offsetof(struct user_regs_struct, s6) }, + { "s7", offsetof(struct user_regs_struct, s7) }, + { "s8", offsetof(struct user_regs_struct, rv_s8) }, + { "s9", offsetof(struct user_regs_struct, s9) }, + { "s10", offsetof(struct user_regs_struct, s10) }, + { "s11", offsetof(struct user_regs_struct, s11) }, + { "t0", offsetof(struct user_regs_struct, t0) }, + { "t1", offsetof(struct user_regs_struct, t1) }, + { "t2", offsetof(struct user_regs_struct, t2) }, + { "t3", offsetof(struct user_regs_struct, t3) }, + { "t4", offsetof(struct user_regs_struct, t4) }, + { "t5", offsetof(struct user_regs_struct, t5) }, + { "t6", offsetof(struct user_regs_struct, t6) }, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(reg_map); i++) { + if (strcmp(reg_name, reg_map[i].name) == 0) + return reg_map[i].pt_regs_off; + } + + pr_warn("usdt: unrecognized register '%s'\n", reg_name); + return -ENOENT; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + char *reg_name = NULL; + int arg_sz, len, reg_off; + long off; + + if (sscanf(arg_str, " %d @ %ld ( %m[a-z0-9] ) %n", &arg_sz, &off, ®_name, &len) == 3) { + /* Memory dereference case, e.g., -8@-88(s0) */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@5 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, ®_name, &len) == 2) { + /* Register read case, e.g., -8@a1 */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return -EINVAL; + } + + return len; +} + +#else + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + pr_warn("usdt: libbpf doesn't support USDTs on current architecture\n"); + return -ENOTSUP; +} + +#endif diff --git a/tools/lib/ctype.c b/tools/lib/ctype.c new file mode 100644 index 000000000..4d2e05fd3 --- /dev/null +++ b/tools/lib/ctype.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/lib/ctype.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#include <linux/ctype.h> +#include <linux/compiler.h> + +const unsigned char _ctype[] = { +_C,_C,_C,_C,_C,_C,_C,_C, /* 0-7 */ +_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C, /* 8-15 */ +_C,_C,_C,_C,_C,_C,_C,_C, /* 16-23 */ +_C,_C,_C,_C,_C,_C,_C,_C, /* 24-31 */ +_S|_SP,_P,_P,_P,_P,_P,_P,_P, /* 32-39 */ +_P,_P,_P,_P,_P,_P,_P,_P, /* 40-47 */ +_D,_D,_D,_D,_D,_D,_D,_D, /* 48-55 */ +_D,_D,_P,_P,_P,_P,_P,_P, /* 56-63 */ +_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U, /* 64-71 */ +_U,_U,_U,_U,_U,_U,_U,_U, /* 72-79 */ +_U,_U,_U,_U,_U,_U,_U,_U, /* 80-87 */ +_U,_U,_U,_P,_P,_P,_P,_P, /* 88-95 */ +_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L, /* 96-103 */ +_L,_L,_L,_L,_L,_L,_L,_L, /* 104-111 */ +_L,_L,_L,_L,_L,_L,_L,_L, /* 112-119 */ +_L,_L,_L,_P,_P,_P,_P,_C, /* 120-127 */ +0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 128-143 */ +0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 144-159 */ +_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 160-175 */ +_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 176-191 */ +_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U, /* 192-207 */ +_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L, /* 208-223 */ +_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L, /* 224-239 */ +_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L}; /* 240-255 */ diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c new file mode 100644 index 000000000..6a3dc167d --- /dev/null +++ b/tools/lib/find_bit.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* bit search implementation + * + * Copied from lib/find_bit.c to tools/lib/find_bit.c + * + * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * Copyright (C) 2008 IBM Corporation + * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> + * (Inspired by David Howell's find_next_bit implementation) + * + * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease + * size and improve performance, 2015. + */ + +#include <linux/bitops.h> +#include <linux/bitmap.h> +#include <linux/kernel.h> + +/* + * Common helper for find_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + */ +#define FIND_FIRST_BIT(FETCH, MUNGE, size) \ +({ \ + unsigned long idx, val, sz = (size); \ + \ + for (idx = 0; idx * BITS_PER_LONG < sz; idx++) { \ + val = (FETCH); \ + if (val) { \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz); \ + break; \ + } \ + } \ + \ + sz; \ +}) + +/* + * Common helper for find_next_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + */ +#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \ +({ \ + unsigned long mask, idx, tmp, sz = (size), __start = (start); \ + \ + if (unlikely(__start >= sz)) \ + goto out; \ + \ + mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \ + idx = __start / BITS_PER_LONG; \ + \ + for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \ + if ((idx + 1) * BITS_PER_LONG >= sz) \ + goto out; \ + idx++; \ + } \ + \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \ +out: \ + sz; \ +}) + +#ifndef find_first_bit +/* + * Find the first set bit in a memory region. + */ +unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) +{ + return FIND_FIRST_BIT(addr[idx], /* nop */, size); +} +#endif + +#ifndef find_first_and_bit +/* + * Find the first set bit in two memory regions. + */ +unsigned long _find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size); +} +#endif + +#ifndef find_first_zero_bit +/* + * Find the first cleared bit in a memory region. + */ +unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) +{ + return FIND_FIRST_BIT(~addr[idx], /* nop */, size); +} +#endif + +#ifndef find_next_bit +unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start); +} +#endif + +#ifndef find_next_and_bit +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start); +} +#endif + +#ifndef find_next_zero_bit +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start) +{ + return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start); +} +#endif diff --git a/tools/lib/hweight.c b/tools/lib/hweight.c new file mode 100644 index 000000000..a16ebf515 --- /dev/null +++ b/tools/lib/hweight.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bitops.h> +#include <asm/types.h> + +/** + * hweightN - returns the hamming weight of a N-bit word + * @x: the word to weigh + * + * The Hamming Weight of a number is the total number of bits set in it. + */ + +unsigned int __sw_hweight32(unsigned int w) +{ +#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER + w -= (w >> 1) & 0x55555555; + w = (w & 0x33333333) + ((w >> 2) & 0x33333333); + w = (w + (w >> 4)) & 0x0f0f0f0f; + return (w * 0x01010101) >> 24; +#else + unsigned int res = w - ((w >> 1) & 0x55555555); + res = (res & 0x33333333) + ((res >> 2) & 0x33333333); + res = (res + (res >> 4)) & 0x0F0F0F0F; + res = res + (res >> 8); + return (res + (res >> 16)) & 0x000000FF; +#endif +} + +unsigned int __sw_hweight16(unsigned int w) +{ + unsigned int res = w - ((w >> 1) & 0x5555); + res = (res & 0x3333) + ((res >> 2) & 0x3333); + res = (res + (res >> 4)) & 0x0F0F; + return (res + (res >> 8)) & 0x00FF; +} + +unsigned int __sw_hweight8(unsigned int w) +{ + unsigned int res = w - ((w >> 1) & 0x55); + res = (res & 0x33) + ((res >> 2) & 0x33); + return (res + (res >> 4)) & 0x0F; +} + +unsigned long __sw_hweight64(__u64 w) +{ +#if BITS_PER_LONG == 32 + return __sw_hweight32((unsigned int)(w >> 32)) + + __sw_hweight32((unsigned int)w); +#elif BITS_PER_LONG == 64 +#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER + w -= (w >> 1) & 0x5555555555555555ul; + w = (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul); + w = (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful; + return (w * 0x0101010101010101ul) >> 56; +#else + __u64 res = w - ((w >> 1) & 0x5555555555555555ul); + res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul); + res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful; + res = res + (res >> 8); + res = res + (res >> 16); + return (res + (res >> 32)) & 0x00000000000000FFul; +#endif +#endif +} diff --git a/tools/lib/list_sort.c b/tools/lib/list_sort.c new file mode 100644 index 000000000..10c067e3a --- /dev/null +++ b/tools/lib/list_sort.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/compiler.h> +#include <linux/export.h> +#include <linux/string.h> +#include <linux/list_sort.h> +#include <linux/list.h> + +/* + * Returns a list organized in an intermediate format suited + * to chaining of merge() calls: null-terminated, no reserved or + * sentinel head node, "prev" links not maintained. + */ +__attribute__((nonnull(2,3,4))) +static struct list_head *merge(void *priv, list_cmp_func_t cmp, + struct list_head *a, struct list_head *b) +{ + struct list_head *head, **tail = &head; + + for (;;) { + /* if equal, take 'a' -- important for sort stability */ + if (cmp(priv, a, b) <= 0) { + *tail = a; + tail = &a->next; + a = a->next; + if (!a) { + *tail = b; + break; + } + } else { + *tail = b; + tail = &b->next; + b = b->next; + if (!b) { + *tail = a; + break; + } + } + } + return head; +} + +/* + * Combine final list merge with restoration of standard doubly-linked + * list structure. This approach duplicates code from merge(), but + * runs faster than the tidier alternatives of either a separate final + * prev-link restoration pass, or maintaining the prev links + * throughout. + */ +__attribute__((nonnull(2,3,4,5))) +static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head, + struct list_head *a, struct list_head *b) +{ + struct list_head *tail = head; + u8 count = 0; + + for (;;) { + /* if equal, take 'a' -- important for sort stability */ + if (cmp(priv, a, b) <= 0) { + tail->next = a; + a->prev = tail; + tail = a; + a = a->next; + if (!a) + break; + } else { + tail->next = b; + b->prev = tail; + tail = b; + b = b->next; + if (!b) { + b = a; + break; + } + } + } + + /* Finish linking remainder of list b on to tail */ + tail->next = b; + do { + /* + * If the merge is highly unbalanced (e.g. the input is + * already sorted), this loop may run many iterations. + * Continue callbacks to the client even though no + * element comparison is needed, so the client's cmp() + * routine can invoke cond_resched() periodically. + */ + if (unlikely(!++count)) + cmp(priv, b, b); + b->prev = tail; + tail = b; + b = b->next; + } while (b); + + /* And the final links to make a circular doubly-linked list */ + tail->next = head; + head->prev = tail; +} + +/** + * list_sort - sort a list + * @priv: private data, opaque to list_sort(), passed to @cmp + * @head: the list to sort + * @cmp: the elements comparison function + * + * The comparison function @cmp must return > 0 if @a should sort after + * @b ("@a > @b" if you want an ascending sort), and <= 0 if @a should + * sort before @b *or* their original order should be preserved. It is + * always called with the element that came first in the input in @a, + * and list_sort is a stable sort, so it is not necessary to distinguish + * the @a < @b and @a == @b cases. + * + * This is compatible with two styles of @cmp function: + * - The traditional style which returns <0 / =0 / >0, or + * - Returning a boolean 0/1. + * The latter offers a chance to save a few cycles in the comparison + * (which is used by e.g. plug_ctx_cmp() in block/blk-mq.c). + * + * A good way to write a multi-word comparison is:: + * + * if (a->high != b->high) + * return a->high > b->high; + * if (a->middle != b->middle) + * return a->middle > b->middle; + * return a->low > b->low; + * + * + * This mergesort is as eager as possible while always performing at least + * 2:1 balanced merges. Given two pending sublists of size 2^k, they are + * merged to a size-2^(k+1) list as soon as we have 2^k following elements. + * + * Thus, it will avoid cache thrashing as long as 3*2^k elements can + * fit into the cache. Not quite as good as a fully-eager bottom-up + * mergesort, but it does use 0.2*n fewer comparisons, so is faster in + * the common case that everything fits into L1. + * + * + * The merging is controlled by "count", the number of elements in the + * pending lists. This is beautifully simple code, but rather subtle. + * + * Each time we increment "count", we set one bit (bit k) and clear + * bits k-1 .. 0. Each time this happens (except the very first time + * for each bit, when count increments to 2^k), we merge two lists of + * size 2^k into one list of size 2^(k+1). + * + * This merge happens exactly when the count reaches an odd multiple of + * 2^k, which is when we have 2^k elements pending in smaller lists, + * so it's safe to merge away two lists of size 2^k. + * + * After this happens twice, we have created two lists of size 2^(k+1), + * which will be merged into a list of size 2^(k+2) before we create + * a third list of size 2^(k+1), so there are never more than two pending. + * + * The number of pending lists of size 2^k is determined by the + * state of bit k of "count" plus two extra pieces of information: + * + * - The state of bit k-1 (when k == 0, consider bit -1 always set), and + * - Whether the higher-order bits are zero or non-zero (i.e. + * is count >= 2^(k+1)). + * + * There are six states we distinguish. "x" represents some arbitrary + * bits, and "y" represents some arbitrary non-zero bits: + * 0: 00x: 0 pending of size 2^k; x pending of sizes < 2^k + * 1: 01x: 0 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k + * 2: x10x: 0 pending of size 2^k; 2^k + x pending of sizes < 2^k + * 3: x11x: 1 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k + * 4: y00x: 1 pending of size 2^k; 2^k + x pending of sizes < 2^k + * 5: y01x: 2 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k + * (merge and loop back to state 2) + * + * We gain lists of size 2^k in the 2->3 and 4->5 transitions (because + * bit k-1 is set while the more significant bits are non-zero) and + * merge them away in the 5->2 transition. Note in particular that just + * before the 5->2 transition, all lower-order bits are 11 (state 3), + * so there is one list of each smaller size. + * + * When we reach the end of the input, we merge all the pending + * lists, from smallest to largest. If you work through cases 2 to + * 5 above, you can see that the number of elements we merge with a list + * of size 2^k varies from 2^(k-1) (cases 3 and 5 when x == 0) to + * 2^(k+1) - 1 (second merge of case 5 when x == 2^(k-1) - 1). + */ +__attribute__((nonnull(2,3))) +void list_sort(void *priv, struct list_head *head, list_cmp_func_t cmp) +{ + struct list_head *list = head->next, *pending = NULL; + size_t count = 0; /* Count of pending */ + + if (list == head->prev) /* Zero or one elements */ + return; + + /* Convert to a null-terminated singly-linked list. */ + head->prev->next = NULL; + + /* + * Data structure invariants: + * - All lists are singly linked and null-terminated; prev + * pointers are not maintained. + * - pending is a prev-linked "list of lists" of sorted + * sublists awaiting further merging. + * - Each of the sorted sublists is power-of-two in size. + * - Sublists are sorted by size and age, smallest & newest at front. + * - There are zero to two sublists of each size. + * - A pair of pending sublists are merged as soon as the number + * of following pending elements equals their size (i.e. + * each time count reaches an odd multiple of that size). + * That ensures each later final merge will be at worst 2:1. + * - Each round consists of: + * - Merging the two sublists selected by the highest bit + * which flips when count is incremented, and + * - Adding an element from the input as a size-1 sublist. + */ + do { + size_t bits; + struct list_head **tail = &pending; + + /* Find the least-significant clear bit in count */ + for (bits = count; bits & 1; bits >>= 1) + tail = &(*tail)->prev; + /* Do the indicated merge */ + if (likely(bits)) { + struct list_head *a = *tail, *b = a->prev; + + a = merge(priv, cmp, b, a); + /* Install the merged result in place of the inputs */ + a->prev = b->prev; + *tail = a; + } + + /* Move one element from input list to pending */ + list->prev = pending; + pending = list; + list = list->next; + pending->next = NULL; + count++; + } while (list); + + /* End of input; merge together all the pending lists. */ + list = pending; + pending = pending->prev; + for (;;) { + struct list_head *next = pending->prev; + + if (!next) + break; + list = merge(priv, cmp, pending, list); + pending = next; + } + /* The final merge, rebuilding prev links */ + merge_final(priv, cmp, head, pending, list); +} +EXPORT_SYMBOL(list_sort); diff --git a/tools/lib/perf/Build b/tools/lib/perf/Build new file mode 100644 index 000000000..e8f5b7fb9 --- /dev/null +++ b/tools/lib/perf/Build @@ -0,0 +1,15 @@ +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) + +tests-y += tests/ diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile new file mode 100644 index 000000000..972754082 --- /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 000000000..9d5a5a5ee --- /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/counting.c b/tools/lib/perf/Documentation/examples/counting.c new file mode 100644 index 000000000..608569357 --- /dev/null +++ b/tools/lib/perf/Documentation/examples/counting.c @@ -0,0 +1,83 @@ +#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); +} + +int main(int argc, char **argv) +{ + int count = 100000, err = 0; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_thread_map *threads; + struct perf_counts_values counts; + + struct perf_event_attr attr1 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING, + .disabled = 1, + }; + struct perf_event_attr attr2 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING, + .disabled = 1, + }; + + libperf_init(libperf_print); + threads = perf_thread_map__new_dummy(); + if (!threads) { + fprintf(stderr, "failed to create threads\n"); + return -1; + } + perf_thread_map__set_pid(threads, 0, 0); + evlist = perf_evlist__new(); + if (!evlist) { + fprintf(stderr, "failed to create evlist\n"); + goto out_threads; + } + evsel = perf_evsel__new(&attr1); + if (!evsel) { + fprintf(stderr, "failed to create evsel1\n"); + goto out_evlist; + } + perf_evlist__add(evlist, evsel); + evsel = perf_evsel__new(&attr2); + if (!evsel) { + fprintf(stderr, "failed to create evsel2\n"); + goto out_evlist; + } + perf_evlist__add(evlist, evsel); + perf_evlist__set_maps(evlist, NULL, threads); + err = perf_evlist__open(evlist); + if (err) { + fprintf(stderr, "failed to open evsel\n"); + goto out_evlist; + } + perf_evlist__enable(evlist); + while (count--); + perf_evlist__disable(evlist); + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts); + fprintf(stdout, "count %llu, enabled %llu, run %llu\n", + counts.val, counts.ena, counts.run); + } + perf_evlist__close(evlist); +out_evlist: + perf_evlist__delete(evlist); +out_threads: + perf_thread_map__put(threads); + return err; +} diff --git a/tools/lib/perf/Documentation/examples/sampling.c b/tools/lib/perf/Documentation/examples/sampling.c new file mode 100644 index 000000000..8e1a926a9 --- /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 000000000..8b75efcd6 --- /dev/null +++ b/tools/lib/perf/Documentation/libperf-counting.txt @@ -0,0 +1,213 @@ +libperf-counting(7) +=================== + +NAME +---- +libperf-counting - counting interface + +DESCRIPTION +----------- +The counting interface provides API to measure 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 libperf 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 nutshell 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 explicitly (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 through 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 finally 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 000000000..d6ca24f6e --- /dev/null +++ b/tools/lib/perf/Documentation/libperf-sampling.txt @@ -0,0 +1,244 @@ +libperf-sampling(7) +=================== + +NAME +---- +libperf-sampling - sampling interface + + +DESCRIPTION +----------- +The sampling interface provides API to measure 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 libperf 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 +nutshell 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 explicitly. + +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 finally 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 000000000..a8f1a2379 --- /dev/null +++ b/tools/lib/perf/Documentation/libperf.txt @@ -0,0 +1,251 @@ +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); + bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu); + + #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); + struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array); + + void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, pid_t pid); + char *perf_thread_map__comm(struct perf_thread_map *map, int idx); + int perf_thread_map__nr(struct perf_thread_map *threads); + pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx); + + 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_map_idx); + int perf_evsel__mmap(struct perf_evsel *evsel, int pages); + void perf_evsel__munmap(struct perf_evsel *evsel); + void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread); + int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, + struct perf_counts_values *count); + int perf_evsel__enable(struct perf_evsel *evsel); + int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); + int perf_evsel__disable(struct perf_evsel *evsel); + int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); + struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); + struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); + struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); +-- + +*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 000000000..b4d315cb8 --- /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 000000000..a264fa616 --- /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="$git.docbook.dot"/> + <xsl:text>br </xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-bold-literal.xsl b/tools/lib/perf/Documentation/manpage-bold-literal.xsl new file mode 100644 index 000000000..608eb5df6 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-bold-literal.xsl @@ -0,0 +1,17 @@ +<!-- manpage-bold-literal.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- render literal text as bold (instead of plain or monospace); + this makes literal text easier to distinguish in manpages + viewed on a tty --> +<xsl:template match="literal"> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fB</xsl:text> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fR</xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-normal.xsl b/tools/lib/perf/Documentation/manpage-normal.xsl new file mode 100644 index 000000000..a48f5b11f --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-normal.xsl @@ -0,0 +1,13 @@ +<!-- manpage-normal.xsl: + special settings for manpages rendered from asciidoc+docbook + handles anything we want to keep away from docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the normal values for the roff control characters --> +<xsl:param name="git.docbook.backslash">\</xsl:param> +<xsl:param name="git.docbook.dot" >.</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-suppress-sp.xsl b/tools/lib/perf/Documentation/manpage-suppress-sp.xsl new file mode 100644 index 000000000..a63c7632a --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-suppress-sp.xsl @@ -0,0 +1,21 @@ +<!-- manpage-suppress-sp.xsl: + special settings for manpages rendered from asciidoc+docbook + handles erroneous, inline .sp in manpage output of some + versions of docbook-xsl --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- attempt to work around spurious .sp at the tail of the line + that some versions of docbook stylesheets seem to add --> +<xsl:template match="simpara"> + <xsl:variable name="content"> + <xsl:apply-templates/> + </xsl:variable> + <xsl:value-of select="normalize-space($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 000000000..21df023a2 --- /dev/null +++ b/tools/lib/perf/Makefile @@ -0,0 +1,211 @@ +# 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 + +TEST_ARGS := $(if $(V),-v) + +# 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 tests/*.o LIBPERF-CFLAGS $(LIBPERF_PC) \ + $(TESTS_STATIC) $(TESTS_SHARED) + +TESTS_IN = tests-in.o + +TESTS_STATIC = $(OUTPUT)tests-static +TESTS_SHARED = $(OUTPUT)tests-shared + +$(TESTS_IN): FORCE + $(Q)$(MAKE) $(build)=tests + +$(TESTS_STATIC): $(TESTS_IN) $(LIBPERF_A) $(LIBAPI) + $(QUIET_LINK)$(CC) -o $@ $^ + +$(TESTS_SHARED): $(TESTS_IN) $(LIBAPI) + $(QUIET_LINK)$(CC) -o $@ -L$(or $(OUTPUT),.) $^ -lperf + +make-tests: libs $(TESTS_SHARED) $(TESTS_STATIC) + +tests: make-tests + @echo "running static:" + @./$(TESTS_STATIC) $(TEST_ARGS) + @echo "running dynamic:" + @LD_LIBRARY_PATH=. ./$(TESTS_SHARED) $(TEST_ARGS) + +$(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 000000000..58fc894b7 --- /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 000000000..6cd0be7c1 --- /dev/null +++ b/tools/lib/perf/cpumap.c @@ -0,0 +1,392 @@ +// 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> + +static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) +{ + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); + + if (cpus != NULL) { + cpus->nr = nr_cpus; + refcount_set(&cpus->refcnt, 1); + + } + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__dummy_new(void) +{ + struct perf_cpu_map *cpus = perf_cpu_map__alloc(1); + + if (cpus) + cpus->map[0].cpu = -1; + + return cpus; +} + +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 = perf_cpu_map__alloc(nr_cpus); + if (cpus != NULL) { + int i; + + for (i = 0; i < nr_cpus; ++i) + cpus->map[i].cpu = i; + } + + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__default_new(void) +{ + return cpu_map__default_new(); +} + + +static int cmp_cpu(const void *a, const void *b) +{ + const struct perf_cpu *cpu_a = a, *cpu_b = b; + + return cpu_a->cpu - cpu_b->cpu; +} + +static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus) +{ + size_t payload_size = nr_cpus * sizeof(struct perf_cpu); + struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus); + int i, j; + + if (cpus != NULL) { + memcpy(cpus->map, tmp_cpus, payload_size); + qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu); + /* Remove dups */ + j = 0; + for (i = 0; i < nr_cpus; i++) { + if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu) + cpus->map[j++].cpu = cpus->map[i].cpu; + } + cpus->nr = j; + assert(j <= nr_cpus); + } + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__read(FILE *file) +{ + struct perf_cpu_map *cpus = NULL; + int nr_cpus = 0; + struct perf_cpu *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(struct perf_cpu)); + if (tmp == NULL) + goto out_free_tmp; + tmp_cpus = tmp; + } + + while (++prev < cpu) + tmp_cpus[nr_cpus++].cpu = prev; + } + if (nr_cpus == max_entries) { + max_entries += MAX_NR_CPUS; + tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); + if (tmp == NULL) + goto out_free_tmp; + tmp_cpus = tmp; + } + + tmp_cpus[nr_cpus++].cpu = 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; + struct perf_cpu *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].cpu == (int)start_cpu) + goto invalid; + + if (nr_cpus == max_entries) { + max_entries += MAX_NR_CPUS; + tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); + if (tmp == NULL) + goto invalid; + tmp_cpus = tmp; + } + tmp_cpus[nr_cpus++].cpu = (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; +} + +struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) +{ + struct perf_cpu result = { + .cpu = -1 + }; + + if (cpus && idx < cpus->nr) + return cpus->map[idx]; + + return result; +} + +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].cpu == -1 : true; +} + +int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) +{ + int low, high; + + if (!cpus) + return -1; + + low = 0; + high = cpus->nr; + while (low < high) { + int idx = (low + high) / 2; + struct perf_cpu cpu_at_idx = cpus->map[idx]; + + if (cpu_at_idx.cpu == cpu.cpu) + return idx; + + if (cpu_at_idx.cpu > cpu.cpu) + high = idx; + else + low = idx + 1; + } + + return -1; +} + +bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu) +{ + return perf_cpu_map__idx(cpus, cpu) != -1; +} + +struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map) +{ + struct perf_cpu result = { + .cpu = -1 + }; + + // cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well. + return map->nr > 0 ? map->map[map->nr - 1] : result; +} + +/** Is 'b' a subset of 'a'. */ +bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b) +{ + if (a == b || !b) + return true; + if (!a || b->nr > a->nr) + return false; + + for (int i = 0, j = 0; i < a->nr; i++) { + if (a->map[i].cpu > b->map[j].cpu) + return false; + if (a->map[i].cpu == b->map[j].cpu) { + j++; + if (j == b->nr) + return true; + } + } + return false; +} + +/* + * 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) +{ + struct perf_cpu *tmp_cpus; + int tmp_len; + int i, j, k; + struct perf_cpu_map *merged; + + if (perf_cpu_map__is_subset(orig, other)) + return orig; + if (perf_cpu_map__is_subset(other, orig)) { + perf_cpu_map__put(orig); + return perf_cpu_map__get(other); + } + + tmp_len = orig->nr + other->nr; + tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); + if (!tmp_cpus) + return NULL; + + /* Standard merge algorithm from wikipedia */ + i = j = k = 0; + while (i < orig->nr && j < other->nr) { + if (orig->map[i].cpu <= other->map[j].cpu) { + if (orig->map[i].cpu == other->map[j].cpu) + 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 000000000..61b637f29 --- /dev/null +++ b/tools/lib/perf/evlist.c @@ -0,0 +1,710 @@ +// 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/lib.h> +#include <linux/zalloc.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> +#include "internal.h" + +void perf_evlist__init(struct perf_evlist *evlist) +{ + INIT_LIST_HEAD(&evlist->entries); + evlist->nr_entries = 0; + fdarray__init(&evlist->pollfd, 64); + perf_evlist__reset_id_hash(evlist); +} + +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->system_wide) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__new(NULL); + } else if (!evsel->own_cpus || evlist->has_user_cpus || + (!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } else if (evsel->cpus != evsel->own_cpus) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evsel->own_cpus); + } + + if (evsel->system_wide) { + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__new_dummy(); + } else { + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__get(evlist->threads); + } + + evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus); +} + +static void perf_evlist__propagate_maps(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist->needs_map_propagation = true; + + perf_evlist__for_each_evsel(evlist, evsel) + __perf_evlist__propagate_maps(evlist, evsel); +} + +void perf_evlist__add(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + evsel->idx = evlist->nr_entries; + list_add_tail(&evsel->node, &evlist->entries); + evlist->nr_entries += 1; + + if (evlist->needs_map_propagation) + __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->user_requested_cpus); + perf_cpu_map__put(evlist->all_cpus); + perf_thread_map__put(evlist->threads); + evlist->user_requested_cpus = NULL; + evlist->all_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->user_requested_cpus) { + perf_cpu_map__put(evlist->user_requested_cpus); + evlist->user_requested_cpus = perf_cpu_map__get(cpus); + } + + if (threads != evlist->threads) { + perf_thread_map__put(evlist->threads); + evlist->threads = perf_thread_map__get(threads); + } + + 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__reset_id_hash(struct perf_evlist *evlist) +{ + int i; + + for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i) + INIT_HLIST_HEAD(&evlist->heads[i]); +} + +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->all_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, enum fdarray_flags flags) +{ + int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP, flags); + + 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_evsel__set_sid_idx(struct perf_evsel *evsel, int idx, int cpu, int thread) +{ + struct perf_sample_id *sid = SID(evsel, cpu, thread); + + sid->idx = idx; + sid->cpu = perf_cpu_map__cpu(evsel->cpus, cpu); + sid->tid = perf_thread_map__pid(evsel->threads, thread); +} + +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, struct perf_cpu 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 *nr_mmaps) +{ + struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->all_cpus, cpu_idx); + struct perf_evsel *evsel; + int revent; + + perf_evlist__for_each_entry(evlist, evsel) { + bool overwrite = evsel->attr.write_backward; + enum fdarray_flags flgs; + struct perf_mmap *map; + int *output, fd, cpu; + + 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->idx) + ops->idx(evlist, evsel, mp, idx); + + /* Debug message used by test scripts */ + pr_debug("idx %d: mmapping fd %d\n", idx, *output); + if (ops->mmap(map, mp, *output, evlist_cpu) < 0) + return -1; + + *nr_mmaps += 1; + + if (!idx) + perf_evlist__set_mmap_first(evlist, map, overwrite); + } else { + /* Debug message used by test scripts */ + pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output); + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) + return -1; + + perf_mmap__get(map); + } + + revent = !overwrite ? POLLIN : 0; + + flgs = evsel->system_wide ? fdarray_flag__nonfilterable : fdarray_flag__default; + if (perf_evlist__add_pollfd(evlist, fd, map, revent, flgs) < 0) { + perf_mmap__put(map); + return -1; + } + + if (evsel->attr.read_format & PERF_FORMAT_ID) { + if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread, + fd) < 0) + return -1; + perf_evsel__set_sid_idx(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 nr_threads = perf_thread_map__nr(evlist->threads); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); + int cpu, thread, idx = 0; + int nr_mmaps = 0; + + pr_debug("%s: nr cpu values (may include -1) %d nr threads %d\n", + __func__, nr_cpus, nr_threads); + + /* per-thread mmaps */ + for (thread = 0; thread < nr_threads; thread++, idx++) { + int output = -1; + int output_overwrite = -1; + + if (mmap_per_evsel(evlist, ops, idx, mp, 0, thread, &output, + &output_overwrite, &nr_mmaps)) + goto out_unmap; + } + + /* system-wide mmaps i.e. per-cpu */ + for (cpu = 1; cpu < nr_cpus; cpu++, idx++) { + int output = -1; + int output_overwrite = -1; + + if (mmap_per_evsel(evlist, ops, idx, mp, cpu, 0, &output, + &output_overwrite, &nr_mmaps)) + goto out_unmap; + } + + if (nr_mmaps != evlist->nr_mmaps) + pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps); + + return 0; + +out_unmap: + 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->all_cpus); + int nr_mmaps = 0; + int cpu, thread; + + pr_debug("%s: nr cpu values %d nr threads %d\n", __func__, nr_cpus, nr_threads); + + for (cpu = 0; cpu < nr_cpus; cpu++) { + int output = -1; + int output_overwrite = -1; + + for (thread = 0; thread < nr_threads; thread++) { + if (mmap_per_evsel(evlist, ops, cpu, mp, cpu, + thread, &output, &output_overwrite, &nr_mmaps)) + goto out_unmap; + } + } + + if (nr_mmaps != evlist->nr_mmaps) + pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps); + + return 0; + +out_unmap: + perf_evlist__munmap(evlist); + return -1; +} + +static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) +{ + int nr_mmaps; + + /* One for each CPU */ + nr_mmaps = perf_cpu_map__nr(evlist->all_cpus); + if (perf_cpu_map__empty(evlist->all_cpus)) { + /* Plus one for each thread */ + nr_mmaps += perf_thread_map__nr(evlist->threads); + /* Minus the per-thread CPU (-1) */ + nr_mmaps -= 1; + } + + return nr_mmaps; +} + +int perf_evlist__mmap_ops(struct perf_evlist *evlist, + struct perf_evlist_mmap_ops *ops, + struct perf_mmap_param *mp) +{ + const struct perf_cpu_map *cpus = evlist->all_cpus; + struct perf_evsel *evsel; + + 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, evsel->fd->max_x, evsel->fd->max_y) < 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; +} + +void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader) +{ + struct perf_evsel *first, *last, *evsel; + + first = list_first_entry(list, struct perf_evsel, node); + last = list_last_entry(list, struct perf_evsel, node); + + leader->nr_members = last->idx - first->idx + 1; + + __perf_evlist__for_each_entry(list, evsel) + evsel->leader = leader; +} + +void perf_evlist__set_leader(struct perf_evlist *evlist) +{ + if (evlist->nr_entries) { + struct perf_evsel *first = list_entry(evlist->entries.next, + struct perf_evsel, node); + + evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; + __perf_evlist__set_leader(&evlist->entries, first); + } +} diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c new file mode 100644 index 000000000..8b51b008a --- /dev/null +++ b/tools/lib/perf/evsel.c @@ -0,0 +1,557 @@ +// 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/mmap.h> +#include <internal/threadmap.h> +#include <internal/lib.h> +#include <linux/string.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <asm/bug.h> + +void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, + int idx) +{ + INIT_LIST_HEAD(&evsel->node); + evsel->attr = *attr; + evsel->idx = idx; + evsel->leader = evsel; +} + +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, 0); + + return evsel; +} + +void perf_evsel__delete(struct perf_evsel *evsel) +{ + free(evsel); +} + +#define FD(_evsel, _cpu_map_idx, _thread) \ + ((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread)) +#define MMAP(_evsel, _cpu_map_idx, _thread) \ + (_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \ + : NULL) + +int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); + + if (evsel->fd) { + int idx, thread; + + for (idx = 0; idx < ncpus; idx++) { + for (thread = 0; thread < nthreads; thread++) { + int *fd = FD(evsel, idx, thread); + + if (fd) + *fd = -1; + } + } + } + + return evsel->fd != NULL ? 0 : -ENOMEM; +} + +static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + evsel->mmap = xyarray__new(ncpus, nthreads, sizeof(struct perf_mmap)); + + return evsel->mmap != NULL ? 0 : -ENOMEM; +} + +static int +sys_perf_event_open(struct perf_event_attr *attr, + pid_t pid, struct perf_cpu cpu, int group_fd, + unsigned long flags) +{ + return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags); +} + +static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd) +{ + struct perf_evsel *leader = evsel->leader; + int *fd; + + if (evsel == leader) { + *group_fd = -1; + return 0; + } + + /* + * Leader must be already processed/open, + * if not it's a bug. + */ + if (!leader->fd) + return -ENOTCONN; + + fd = FD(leader, cpu_map_idx, thread); + if (fd == NULL || *fd == -1) + return -EBADF; + + *group_fd = *fd; + + return 0; +} + +int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) +{ + struct perf_cpu cpu; + int idx, 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, perf_cpu_map__nr(cpus), threads->nr) < 0) + return -ENOMEM; + + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + for (thread = 0; thread < threads->nr; thread++) { + int fd, group_fd, *evsel_fd; + + evsel_fd = FD(evsel, idx, thread); + if (evsel_fd == NULL) { + err = -EINVAL; + goto out; + } + + err = get_group_fd(evsel, idx, thread, &group_fd); + if (err < 0) + goto out; + + fd = sys_perf_event_open(&evsel->attr, + threads->map[thread].pid, + cpu, group_fd, 0); + + if (fd < 0) { + err = -errno; + goto out; + } + + *evsel_fd = fd; + } + } +out: + if (err) + perf_evsel__close(evsel); + + return err; +} + +static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx) +{ + int thread; + + for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { + int *fd = FD(evsel, cpu_map_idx, thread); + + if (fd && *fd >= 0) { + close(*fd); + *fd = -1; + } + } +} + +void perf_evsel__close_fd(struct perf_evsel *evsel) +{ + for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++) + perf_evsel__close_fd_cpu(evsel, idx); +} + +void perf_evsel__free_fd(struct perf_evsel *evsel) +{ + 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_map_idx) +{ + if (evsel->fd == NULL) + return; + + perf_evsel__close_fd_cpu(evsel, cpu_map_idx); +} + +void perf_evsel__munmap(struct perf_evsel *evsel) +{ + int idx, thread; + + if (evsel->fd == NULL || evsel->mmap == NULL) + return; + + for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) { + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { + int *fd = FD(evsel, idx, thread); + + if (fd == NULL || *fd < 0) + continue; + + perf_mmap__munmap(MMAP(evsel, idx, thread)); + } + } + + xyarray__delete(evsel->mmap); + evsel->mmap = NULL; +} + +int perf_evsel__mmap(struct perf_evsel *evsel, int pages) +{ + int ret, idx, thread; + struct perf_mmap_param mp = { + .prot = PROT_READ | PROT_WRITE, + .mask = (pages * page_size) - 1, + }; + + if (evsel->fd == NULL || evsel->mmap) + return -EINVAL; + + if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0) + return -ENOMEM; + + for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) { + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { + int *fd = FD(evsel, idx, thread); + struct perf_mmap *map; + struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx); + + if (fd == NULL || *fd < 0) + continue; + + map = MMAP(evsel, idx, thread); + perf_mmap__init(map, NULL, false, NULL); + + ret = perf_mmap__mmap(map, &mp, *fd, cpu); + if (ret) { + perf_evsel__munmap(evsel); + return ret; + } + } + } + + return 0; +} + +void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread) +{ + int *fd = FD(evsel, cpu_map_idx, thread); + + if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL) + return NULL; + + return MMAP(evsel, cpu_map_idx, thread)->base; +} + +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_LOST) + entry += sizeof(u64); + + if (read_format & PERF_FORMAT_GROUP) { + nr = evsel->nr_members; + size += sizeof(u64); + } + + size += entry * nr; + return size; +} + +/* This only reads values for the leader */ +static int perf_evsel__read_group(struct perf_evsel *evsel, int cpu_map_idx, + int thread, struct perf_counts_values *count) +{ + size_t size = perf_evsel__read_size(evsel); + int *fd = FD(evsel, cpu_map_idx, thread); + u64 read_format = evsel->attr.read_format; + u64 *data; + int idx = 1; + + if (fd == NULL || *fd < 0) + return -EINVAL; + + data = calloc(1, size); + if (data == NULL) + return -ENOMEM; + + if (readn(*fd, data, size) <= 0) { + free(data); + return -errno; + } + + /* + * This reads only the leader event intentionally since we don't have + * perf counts values for sibling events. + */ + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + count->ena = data[idx++]; + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + count->run = data[idx++]; + + /* value is always available */ + count->val = data[idx++]; + if (read_format & PERF_FORMAT_ID) + count->id = data[idx++]; + if (read_format & PERF_FORMAT_LOST) + count->lost = data[idx++]; + + free(data); + return 0; +} + +/* + * The perf read format is very flexible. It needs to set the proper + * values according to the read format. + */ +static void perf_evsel__adjust_values(struct perf_evsel *evsel, u64 *buf, + struct perf_counts_values *count) +{ + u64 read_format = evsel->attr.read_format; + int n = 0; + + count->val = buf[n++]; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + count->ena = buf[n++]; + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + count->run = buf[n++]; + + if (read_format & PERF_FORMAT_ID) + count->id = buf[n++]; + + if (read_format & PERF_FORMAT_LOST) + count->lost = buf[n++]; +} + +int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, + struct perf_counts_values *count) +{ + size_t size = perf_evsel__read_size(evsel); + int *fd = FD(evsel, cpu_map_idx, thread); + u64 read_format = evsel->attr.read_format; + struct perf_counts_values buf; + + memset(count, 0, sizeof(*count)); + + if (fd == NULL || *fd < 0) + return -EINVAL; + + if (read_format & PERF_FORMAT_GROUP) + return perf_evsel__read_group(evsel, cpu_map_idx, thread, count); + + if (MMAP(evsel, cpu_map_idx, thread) && + !(read_format & (PERF_FORMAT_ID | PERF_FORMAT_LOST)) && + !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count)) + return 0; + + if (readn(*fd, buf.values, size) <= 0) + return -errno; + + perf_evsel__adjust_values(evsel, buf.values, count); + return 0; +} + +static int perf_evsel__ioctl(struct perf_evsel *evsel, int ioc, void *arg, + int cpu_map_idx, int thread) +{ + int *fd = FD(evsel, cpu_map_idx, thread); + + if (fd == NULL || *fd < 0) + return -1; + + return ioctl(*fd, ioc, arg); +} + +static int perf_evsel__run_ioctl(struct perf_evsel *evsel, + int ioc, void *arg, + int cpu_map_idx) +{ + int thread; + + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { + int err = perf_evsel__ioctl(evsel, ioc, arg, cpu_map_idx, thread); + + if (err) + return err; + } + + return 0; +} + +int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx); +} + +int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread) +{ + struct perf_cpu cpu __maybe_unused; + int idx; + int err; + + perf_cpu_map__for_each_cpu(cpu, idx, evsel->cpus) { + err = perf_evsel__ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, idx, thread); + if (err) + return err; + } + + return 0; +} + +int perf_evsel__enable(struct perf_evsel *evsel) +{ + 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_map_idx) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx); +} + +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 < perf_cpu_map__nr(evsel->cpus) && !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; + + 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; +} + +void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, __s8 *pscaled) +{ + s8 scaled = 0; + + if (scale) { + if (count->run == 0) { + scaled = -1; + count->val = 0; + } else if (count->run < count->ena) { + scaled = 1; + count->val = (u64)((double)count->val * count->ena / count->run); + } + } + + if (pscaled) + *pscaled = scaled; +} diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h new file mode 100644 index 000000000..35dd29642 --- /dev/null +++ b/tools/lib/perf/include/internal/cpumap.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_CPUMAP_H +#define __LIBPERF_INTERNAL_CPUMAP_H + +#include <linux/refcount.h> +#include <perf/cpumap.h> + +/** + * A sized, reference counted, sorted array of integers representing CPU + * numbers. This is commonly used to capture which CPUs a PMU is associated + * with. The indices into the cpumap are frequently used as they avoid having + * gaps if CPU numbers were used. For events associated with a pid, rather than + * a CPU, a single dummy map with an entry of -1 is used. + */ +struct perf_cpu_map { + refcount_t refcnt; + /** Length of the map array. */ + int nr; + /** The CPU values. */ + struct perf_cpu map[]; +}; + +#ifndef MAX_NR_CPUS +#define MAX_NR_CPUS 2048 +#endif + +int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu); +bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b); + +#endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h new file mode 100644 index 000000000..850f07070 --- /dev/null +++ b/tools/lib/perf/include/internal/evlist.h @@ -0,0 +1,139 @@ +/* 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/cpumap.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; + int nr_groups; + bool has_user_cpus; + bool needs_map_propagation; + /** + * The cpus passed from the command line or all online CPUs by + * default. + */ + struct perf_cpu_map *user_requested_cpus; + /** The union of all evsel cpu maps. */ + struct perf_cpu_map *all_cpus; + struct perf_thread_map *threads; + int nr_mmaps; + 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_evsel*, + struct perf_mmap_param*, int); +typedef struct perf_mmap* +(*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int); +typedef int +(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, struct perf_cpu); + +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, enum fdarray_flags flags); + +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); + +void perf_evlist__reset_id_hash(struct perf_evlist *evlist); + +void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader); +#endif /* __LIBPERF_INTERNAL_EVLIST_H */ diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h new file mode 100644 index 000000000..a99a75d9e --- /dev/null +++ b/tools/lib/perf/include/internal/evsel.h @@ -0,0 +1,82 @@ +/* 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> +#include <internal/cpumap.h> + +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; + struct perf_cpu cpu; + pid_t tid; + + /* Guest machine pid and VCPU, valid only if machine_pid is non-zero */ + pid_t machine_pid; + struct perf_cpu vcpu; + + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ + u64 period; +}; + +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 *mmap; + struct xyarray *sample_id; + u64 *id; + u32 ids; + struct perf_evsel *leader; + + /* parse modifier helper */ + int nr_members; + /* + * system_wide is for events that need to be on every CPU, irrespective + * of user requested CPUs or threads. Map propagation will set cpus to + * this event's own_cpus, whereby they will contribute to evlist + * all_cpus. + */ + bool system_wide; + /* + * Some events, for example uncore events, require a CPU. + * i.e. it cannot be the 'any CPU' value of -1. + */ + bool requires_cpu; + int idx; +}; + +void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, + int idx); +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 000000000..85471a4b9 --- /dev/null +++ b/tools/lib/perf/include/internal/lib.h @@ -0,0 +1,14 @@ +/* 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); + +ssize_t preadn(int fd, void *buf, size_t n, off_t offs); + +#endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h new file mode 100644 index 000000000..5a062af8e --- /dev/null +++ b/tools/lib/perf/include/internal/mmap.h @@ -0,0 +1,59 @@ +/* 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> +#include <internal/cpumap.h> + +/* perf sample has 16 bits size limit */ +#define PERF_SAMPLE_MAX_SIZE (1 << 16) + +struct perf_mmap; +struct perf_counts_values; + +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; + struct perf_cpu 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, struct perf_cpu cpu); +void perf_mmap__munmap(struct perf_mmap *map); +void perf_mmap__get(struct perf_mmap *map); +void perf_mmap__put(struct perf_mmap *map); + +u64 perf_mmap__read_head(struct perf_mmap *map); + +int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count); + +#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 000000000..b130a6663 --- /dev/null +++ b/tools/lib/perf/include/internal/tests.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_TESTS_H +#define __LIBPERF_INTERNAL_TESTS_H + +#include <stdio.h> +#include <unistd.h> + +extern int tests_failed; +extern int tests_verbose; + +static inline int get_verbose(char **argv, int argc) +{ + int c; + int verbose = 0; + + while ((c = getopt(argc, argv, "v")) != -1) { + switch (c) + { + case 'v': + verbose = 1; + break; + default: + break; + } + } + optind = 1; + + return verbose; +} + +#define __T_START \ +do { \ + tests_verbose = get_verbose(argv, argc); \ + 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) + +#define __T_VERBOSE(...) \ +do { \ + if (tests_verbose) { \ + if (tests_verbose == 1) { \ + fputc('\n', stderr); \ + tests_verbose++; \ + } \ + fprintf(stderr, ##__VA_ARGS__); \ + } \ +} 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 000000000..df748baf9 --- /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 000000000..f10af3da7 --- /dev/null +++ b/tools/lib/perf/include/internal/xyarray.h @@ -0,0 +1,43 @@ +/* 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 void *xyarray__entry(struct xyarray *xy, size_t x, size_t y) +{ + if (x >= xy->max_x || y >= xy->max_y) + return NULL; + return __xyarray__entry(xy, x, y); +} + +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/bpf_perf.h b/tools/lib/perf/include/perf/bpf_perf.h new file mode 100644 index 000000000..e7cf6ba7b --- /dev/null +++ b/tools/lib/perf/include/perf/bpf_perf.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __LIBPERF_BPF_PERF_H +#define __LIBPERF_BPF_PERF_H + +#include <linux/types.h> /* for __u32 */ + +/* + * bpf_perf uses a hashmap, the attr_map, to track all the leader programs. + * The hashmap is pinned in bpffs. flock() on this file is used to ensure + * no concurrent access to the attr_map. The key of attr_map is struct + * perf_event_attr, and the value is struct perf_event_attr_map_entry. + * + * struct perf_event_attr_map_entry contains two __u32 IDs, bpf_link of the + * leader prog, and the diff_map. Each perf-stat session holds a reference + * to the bpf_link to make sure the leader prog is attached to sched_switch + * tracepoint. + * + * Since the hashmap only contains IDs of the bpf_link and diff_map, it + * does not hold any references to the leader program. Once all perf-stat + * sessions of these events exit, the leader prog, its maps, and the + * perf_events will be freed. + */ +struct perf_event_attr_map_entry { + __u32 link_id; + __u32 diff_map_id; +}; + +/* default attr_map name */ +#define BPF_PERF_DEFAULT_ATTR_MAP_PATH "perf_attr_map" + +#endif /* __LIBPERF_BPF_PERF_H */ diff --git a/tools/lib/perf/include/perf/core.h b/tools/lib/perf/include/perf/core.h new file mode 100644 index 000000000..a3f6d68ed --- /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 000000000..03aceb72a --- /dev/null +++ b/tools/lib/perf/include/perf/cpumap.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_CPUMAP_H +#define __LIBPERF_CPUMAP_H + +#include <perf/core.h> +#include <perf/cpumap.h> +#include <stdio.h> +#include <stdbool.h> + +/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */ +struct perf_cpu { + int cpu; +}; + +LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void); +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 struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); +LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); +LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); +LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map); +LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); + +#define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \ + for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \ + (idx) < perf_cpu_map__nr(cpus); \ + (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx)) + +#define perf_cpu_map__for_each_idx(idx, cpus) \ + for ((idx) = 0; (idx) < perf_cpu_map__nr(cpus); (idx)++) + +#endif /* __LIBPERF_CPUMAP_H */ diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h new file mode 100644 index 000000000..ad47d7b31 --- /dev/null +++ b/tools/lib/perf/include/perf/event.h @@ -0,0 +1,504 @@ +/* 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 */ + +#define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem)) + +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; + union { + struct { + __u32 maj; + __u32 min; + __u64 ino; + __u64 ino_generation; + }; + struct { + __u8 build_id_size; + __u8 __reserved_1; + __u16 __reserved_2; + __u8 build_id[20]; + }; + }; + __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 | PERF_FORMAT_LOST + */ +struct perf_record_read { + struct perf_event_header header; + __u32 pid, tid; + __u64 value; + __u64 time_enabled; + __u64 time_running; + __u64 id; + __u64 lost; +}; + +struct perf_record_throttle { + struct perf_event_header header; + __u64 time; + __u64 id; + __u64 stream_id; +}; + +#ifndef KSYM_NAME_LEN +#define KSYM_NAME_LEN 512 +#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_cgroup { + struct perf_event_header header; + __u64 id; + char path[PATH_MAX]; +}; + +struct perf_record_text_poke_event { + struct perf_event_header header; + __u64 addr; + __u16 old_len; + __u16 new_len; + __u8 bytes[]; +}; + +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, + PERF_CPU_MAP__RANGE_CPUS = 2, +}; + +/* + * Array encoding of a perf_cpu_map where nr is the number of entries in cpu[] + * and each entry is a value for a CPU in the map. + */ +struct cpu_map_entries { + __u16 nr; + __u16 cpu[]; +}; + +/* Bitmap encoding of a perf_cpu_map where bitmap entries are 32-bit. */ +struct perf_record_mask_cpu_map32 { + /* Number of mask values. */ + __u16 nr; + /* Constant 4. */ + __u16 long_size; + /* Bitmap data. */ + __u32 mask[]; +}; + +/* Bitmap encoding of a perf_cpu_map where bitmap entries are 64-bit. */ +struct perf_record_mask_cpu_map64 { + /* Number of mask values. */ + __u16 nr; + /* Constant 8. */ + __u16 long_size; + /* Legacy padding. */ + char __pad[4]; + /* Bitmap data. */ + __u64 mask[]; +}; + +/* + * 'struct perf_record_cpu_map_data' is packed as unfortunately an earlier + * version had unaligned data and we wish to retain file format compatibility. + * -irogers + */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpacked" +#pragma GCC diagnostic ignored "-Wattributes" + +/* + * An encoding of a CPU map for a range starting at start_cpu through to + * end_cpu. If any_cpu is 1, an any CPU (-1) value (aka dummy value) is present. + */ +struct perf_record_range_cpu_map { + __u8 any_cpu; + __u8 __pad; + __u16 start_cpu; + __u16 end_cpu; +}; + +struct perf_record_cpu_map_data { + __u16 type; + union { + /* Used when type == PERF_CPU_MAP__CPUS. */ + struct cpu_map_entries cpus_data; + /* Used when type == PERF_CPU_MAP__MASK and long_size == 4. */ + struct perf_record_mask_cpu_map32 mask32_data; + /* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */ + struct perf_record_mask_cpu_map64 mask64_data; + /* Used when type == PERF_CPU_MAP__RANGE_CPUS. */ + struct perf_record_range_cpu_map range_cpu_data; + }; +} __attribute__((packed)); + +#pragma GCC diagnostic pop + +struct perf_record_cpu_map { + struct perf_event_header header; + 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; + union { + /* Used when type == PERF_EVENT_UPDATE__SCALE. */ + struct perf_record_event_update_scale scale; + /* Used when type == PERF_EVENT_UPDATE__UNIT. */ + char unit[0]; + /* Used when type == PERF_EVENT_UPDATE__NAME. */ + char name[0]; + /* Used when type == PERF_EVENT_UPDATE__CPUS. */ + struct perf_record_event_update_cpus cpus; + }; +}; + +#define MAX_EVENT_NAME 64 + +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; +}; + +#define PERF_RECORD_MISC_BUILD_ID_SIZE (1 << 15) + +struct perf_record_header_build_id { + struct perf_event_header header; + pid_t pid; + union { + __u8 build_id[24]; + struct { + __u8 data[20]; + __u8 size; + __u8 reserved1__; + __u16 reserved2__; + }; + }; + char filename[]; +}; + +struct id_index_entry { + __u64 id; + __u64 idx; + __u64 cpu; + __u64 tid; +}; + +struct id_index_entry_2 { + __u64 machine_pid; + __u64 vcpu; +}; + +struct perf_record_id_index { + struct perf_event_header header; + __u64 nr; + struct id_index_entry entries[]; +}; + +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]; + __u32 machine_pid; + __u32 vcpu; +}; + +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_aux_output_hw_id { + struct perf_event_header header; + __u64 hw_id; +}; + +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; + __u64 time_cycles; + __u64 time_mask; + __u8 cap_user_time_zero; + __u8 cap_user_time_short; + __u8 reserved[6]; /* For alignment */ +}; + +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_FINISHED_INIT = 82, + 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_cgroup cgroup; + 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_text_poke_event text_poke; + 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_aux_output_hw_id aux_output_hw_id; + 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 000000000..9ca399d49 --- /dev/null +++ b/tools/lib/perf/include/perf/evlist.h @@ -0,0 +1,50 @@ +/* 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)) + +LIBPERF_API void perf_evlist__set_leader(struct perf_evlist *evlist); +#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 000000000..6f9220407 --- /dev/null +++ b/tools/lib/perf/include/perf/evsel.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_EVSEL_H +#define __LIBPERF_EVSEL_H + +#include <stdint.h> +#include <perf/core.h> +#include <stdbool.h> +#include <linux/types.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 id; + uint64_t lost; + }; + uint64_t values[5]; + }; +}; + +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_map_idx); +LIBPERF_API int perf_evsel__mmap(struct perf_evsel *evsel, int pages); +LIBPERF_API void perf_evsel__munmap(struct perf_evsel *evsel); +LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread); +LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, + struct perf_counts_values *count); +LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); +LIBPERF_API int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread); +LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); +LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); +LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); +LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); +LIBPERF_API void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, __s8 *pscaled); + +#endif /* __LIBPERF_EVSEL_H */ diff --git a/tools/lib/perf/include/perf/mmap.h b/tools/lib/perf/include/perf/mmap.h new file mode 100644 index 000000000..9508ad90d --- /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 000000000..8b40e7777 --- /dev/null +++ b/tools/lib/perf/include/perf/threadmap.h @@ -0,0 +1,21 @@ +/* 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 struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array); + +LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, pid_t pid); +LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int idx); +LIBPERF_API int perf_thread_map__nr(struct perf_thread_map *threads); +LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx); + +LIBPERF_API struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); +LIBPERF_API void perf_thread_map__put(struct perf_thread_map *map); + +#endif /* __LIBPERF_THREADMAP_H */ diff --git a/tools/lib/perf/internal.h b/tools/lib/perf/internal.h new file mode 100644 index 000000000..2c27e158d --- /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 000000000..696fb0ea6 --- /dev/null +++ b/tools/lib/perf/lib.c @@ -0,0 +1,68 @@ +// 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); +} + +ssize_t preadn(int fd, void *buf, size_t n, off_t offs) +{ + size_t left = n; + + while (left) { + ssize_t ret = pread(fd, buf, left, offs); + + if (ret < 0 && errno == EINTR) + continue; + if (ret <= 0) + return ret; + + left -= ret; + buf += ret; + offs += ret; + } + + return n; +} + +/* + * Write exactly 'n' bytes or return an error. + */ +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 000000000..190b56ae9 --- /dev/null +++ b/tools/lib/perf/libperf.map @@ -0,0 +1,59 @@ +LIBPERF_0.0.1 { + global: + libperf_init; + perf_cpu_map__dummy_new; + perf_cpu_map__default_new; + perf_cpu_map__get; + perf_cpu_map__put; + perf_cpu_map__new; + perf_cpu_map__read; + perf_cpu_map__nr; + perf_cpu_map__cpu; + perf_cpu_map__empty; + perf_cpu_map__max; + perf_cpu_map__has; + perf_thread_map__new_array; + perf_thread_map__new_dummy; + perf_thread_map__set_pid; + perf_thread_map__comm; + 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__mmap; + perf_evsel__munmap; + perf_evsel__mmap_base; + 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_evlist__set_leader; + perf_mmap__consume; + perf_mmap__read_init; + perf_mmap__read_done; + perf_mmap__read_event; + perf_counts_values__scale; + local: + *; +}; diff --git a/tools/lib/perf/libperf.pc.template b/tools/lib/perf/libperf.pc.template new file mode 100644 index 000000000..117e4a237 --- /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 000000000..0d1634ced --- /dev/null +++ b/tools/lib/perf/mmap.c @@ -0,0 +1,459 @@ +// 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 <perf/evsel.h> +#include <internal/mmap.h> +#include <internal/lib.h> +#include <linux/kernel.h> +#include <linux/math64.h> +#include <linux/stringify.h> +#include "internal.h" + +void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, + 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, struct perf_cpu 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; +} + +#if defined(__i386__) || defined(__x86_64__) +static u64 read_perf_counter(unsigned int counter) +{ + unsigned int low, high; + + asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter)); + + return low | ((u64)high) << 32; +} + +static u64 read_timestamp(void) +{ + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((u64)high) << 32; +} +#elif defined(__aarch64__) +#define read_sysreg(r) ({ \ + u64 __val; \ + asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \ + __val; \ +}) + +static u64 read_pmccntr(void) +{ + return read_sysreg(pmccntr_el0); +} + +#define PMEVCNTR_READ(idx) \ + static u64 read_pmevcntr_##idx(void) { \ + return read_sysreg(pmevcntr##idx##_el0); \ + } + +PMEVCNTR_READ(0); +PMEVCNTR_READ(1); +PMEVCNTR_READ(2); +PMEVCNTR_READ(3); +PMEVCNTR_READ(4); +PMEVCNTR_READ(5); +PMEVCNTR_READ(6); +PMEVCNTR_READ(7); +PMEVCNTR_READ(8); +PMEVCNTR_READ(9); +PMEVCNTR_READ(10); +PMEVCNTR_READ(11); +PMEVCNTR_READ(12); +PMEVCNTR_READ(13); +PMEVCNTR_READ(14); +PMEVCNTR_READ(15); +PMEVCNTR_READ(16); +PMEVCNTR_READ(17); +PMEVCNTR_READ(18); +PMEVCNTR_READ(19); +PMEVCNTR_READ(20); +PMEVCNTR_READ(21); +PMEVCNTR_READ(22); +PMEVCNTR_READ(23); +PMEVCNTR_READ(24); +PMEVCNTR_READ(25); +PMEVCNTR_READ(26); +PMEVCNTR_READ(27); +PMEVCNTR_READ(28); +PMEVCNTR_READ(29); +PMEVCNTR_READ(30); + +/* + * Read a value direct from PMEVCNTR<idx> + */ +static u64 read_perf_counter(unsigned int counter) +{ + static u64 (* const read_f[])(void) = { + read_pmevcntr_0, + read_pmevcntr_1, + read_pmevcntr_2, + read_pmevcntr_3, + read_pmevcntr_4, + read_pmevcntr_5, + read_pmevcntr_6, + read_pmevcntr_7, + read_pmevcntr_8, + read_pmevcntr_9, + read_pmevcntr_10, + read_pmevcntr_11, + read_pmevcntr_13, + read_pmevcntr_12, + read_pmevcntr_14, + read_pmevcntr_15, + read_pmevcntr_16, + read_pmevcntr_17, + read_pmevcntr_18, + read_pmevcntr_19, + read_pmevcntr_20, + read_pmevcntr_21, + read_pmevcntr_22, + read_pmevcntr_23, + read_pmevcntr_24, + read_pmevcntr_25, + read_pmevcntr_26, + read_pmevcntr_27, + read_pmevcntr_28, + read_pmevcntr_29, + read_pmevcntr_30, + read_pmccntr + }; + + if (counter < ARRAY_SIZE(read_f)) + return (read_f[counter])(); + + return 0; +} + +static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); } + +#else +static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; } +static u64 read_timestamp(void) { return 0; } +#endif + +int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count) +{ + struct perf_event_mmap_page *pc = map->base; + u32 seq, idx, time_mult = 0, time_shift = 0; + u64 cnt, cyc = 0, time_offset = 0, time_cycles = 0, time_mask = ~0ULL; + + if (!pc || !pc->cap_user_rdpmc) + return -1; + + do { + seq = READ_ONCE(pc->lock); + barrier(); + + count->ena = READ_ONCE(pc->time_enabled); + count->run = READ_ONCE(pc->time_running); + + if (pc->cap_user_time && count->ena != count->run) { + cyc = read_timestamp(); + time_mult = READ_ONCE(pc->time_mult); + time_shift = READ_ONCE(pc->time_shift); + time_offset = READ_ONCE(pc->time_offset); + + if (pc->cap_user_time_short) { + time_cycles = READ_ONCE(pc->time_cycles); + time_mask = READ_ONCE(pc->time_mask); + } + } + + idx = READ_ONCE(pc->index); + cnt = READ_ONCE(pc->offset); + if (pc->cap_user_rdpmc && idx) { + s64 evcnt = read_perf_counter(idx - 1); + u16 width = READ_ONCE(pc->pmc_width); + + evcnt <<= 64 - width; + evcnt >>= 64 - width; + cnt += evcnt; + } else + return -1; + + barrier(); + } while (READ_ONCE(pc->lock) != seq); + + if (count->ena != count->run) { + u64 delta; + + /* Adjust for cap_usr_time_short, a nop if not */ + cyc = time_cycles + ((cyc - time_cycles) & time_mask); + + delta = time_offset + mul_u64_u32_shr(cyc, time_mult, time_shift); + + count->ena += delta; + if (idx) + count->run += delta; + } + + count->val = cnt; + + return 0; +} diff --git a/tools/lib/perf/tests/Build b/tools/lib/perf/tests/Build new file mode 100644 index 000000000..56e81378d --- /dev/null +++ b/tools/lib/perf/tests/Build @@ -0,0 +1,5 @@ +tests-y += main.o +tests-y += test-evsel.o +tests-y += test-evlist.o +tests-y += test-cpumap.o +tests-y += test-threadmap.o diff --git a/tools/lib/perf/tests/main.c b/tools/lib/perf/tests/main.c new file mode 100644 index 000000000..56423fd4d --- /dev/null +++ b/tools/lib/perf/tests/main.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <internal/tests.h> +#include "tests.h" + +int tests_failed; +int tests_verbose; + +int main(int argc, char **argv) +{ + __T("test cpumap", !test_cpumap(argc, argv)); + __T("test threadmap", !test_threadmap(argc, argv)); + __T("test evlist", !test_evlist(argc, argv)); + __T("test evsel", !test_evsel(argc, argv)); + return 0; +} diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c new file mode 100644 index 000000000..87b0510a5 --- /dev/null +++ b/tools/lib/perf/tests/test-cpumap.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> +#include <perf/cpumap.h> +#include <internal/tests.h> +#include "tests.h" + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +int test_cpumap(int argc, char **argv) +{ + struct perf_cpu_map *cpus; + struct perf_cpu cpu; + int idx; + + __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); + + cpus = perf_cpu_map__default_new(); + if (!cpus) + return -1; + + perf_cpu_map__for_each_cpu(cpu, idx, cpus) + __T("wrong cpu number", cpu.cpu != -1); + + perf_cpu_map__put(cpus); + + __T_END; + return tests_failed == 0 ? 0 : -1; +} diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c new file mode 100644 index 000000000..ed616fc19 --- /dev/null +++ b/tools/lib/perf/tests/test-evlist.c @@ -0,0 +1,589 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE // needed for sched.h to get sched_[gs]etaffinity and CPU_(ZERO,SET) +#include <inttypes.h> +#include <sched.h> +#include <stdio.h> +#include <stdarg.h> +#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> +#include "tests.h" +#include <internal/evsel.h> + +#define EVENT_NUM 15 +#define WAIT_COUNT 100000000UL + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +static int test_stat_cpu(void) +{ + struct perf_cpu_map *cpus; + struct perf_evlist *evlist; + struct perf_evsel *evsel, *leader; + 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, idx; + + cpus = perf_cpu_map__new(NULL); + __T("failed to create cpus", cpus); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = leader = 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_leader(evlist); + __T("failed to set leader", leader->leader == leader); + __T("failed to set leader", evsel->leader == leader); + + perf_evlist__set_maps(evlist, cpus, NULL); + + err = perf_evlist__open(evlist); + __T("failed to open evlist", err == 0); + + perf_evlist__for_each_evsel(evlist, evsel) { + cpus = perf_evsel__cpus(evsel); + + for (idx = 0; idx < perf_cpu_map__nr(cpus); idx++) { + struct perf_counts_values counts = { .val = 0 }; + + perf_evsel__read(evsel, idx, 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, *leader; + 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 = leader = 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_leader(evlist); + __T("failed to set leader", leader->leader == leader); + __T("failed to set leader", evsel->leader == leader); + + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evlist", 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, *leader; + 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 = leader = 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_leader(evlist); + __T("failed to set leader", leader->leader == leader); + __T("failed to set leader", evsel->leader == leader); + + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evlist", 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; + 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)) { + tests_failed++; + 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; + char bf; + + 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); + __T("failed to set leader", evsel->leader == 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], "A", 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, tmp; + struct perf_cpu cpu; + 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); + __T("failed to set leader", evsel->leader == 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.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; +} + +static double display_error(long long average, + long long high, + long long low, + long long expected) +{ + double error; + + error = (((double)average - expected) / expected) * 100.0; + + __T_VERBOSE(" Expected: %lld\n", expected); + __T_VERBOSE(" High: %lld Low: %lld Average: %lld\n", + high, low, average); + + __T_VERBOSE(" Average Error = %.2f%%\n", error); + + return error; +} + +static int test_stat_multiplexing(void) +{ + struct perf_counts_values expected_counts = { .val = 0 }; + struct perf_counts_values counts[EVENT_NUM] = {{ .val = 0 },}; + struct perf_thread_map *threads; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_INSTRUCTIONS, + .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING, + .disabled = 1, + }; + int err, i, nonzero = 0; + unsigned long count; + long long max = 0, min = 0, avg = 0; + double error = 0.0; + s8 scaled = 0; + + /* read for non-multiplexing event count */ + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + __T("failed to open evsel", err == 0); + + err = perf_evsel__enable(evsel); + __T("failed to enable evsel", err == 0); + + /* wait loop */ + count = WAIT_COUNT; + while (count--) + ; + + perf_evsel__read(evsel, 0, 0, &expected_counts); + __T("failed to read value for evsel", expected_counts.val != 0); + __T("failed to read non-multiplexing event count", + expected_counts.ena == expected_counts.run); + + err = perf_evsel__disable(evsel); + __T("failed to enable evsel", err == 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + + /* read for multiplexing event count */ + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + for (i = 0; i < EVENT_NUM; i++) { + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + perf_evlist__add(evlist, evsel); + } + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evlist", err == 0); + + perf_evlist__enable(evlist); + + /* wait loop */ + count = WAIT_COUNT; + while (count--) + ; + + i = 0; + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts[i]); + __T("failed to read value for evsel", counts[i].val != 0); + i++; + } + + perf_evlist__disable(evlist); + + min = counts[0].val; + for (i = 0; i < EVENT_NUM; i++) { + __T_VERBOSE("Event %2d -- Raw count = %" PRIu64 ", run = %" PRIu64 ", enable = %" PRIu64 "\n", + i, counts[i].val, counts[i].run, counts[i].ena); + + perf_counts_values__scale(&counts[i], true, &scaled); + if (scaled == 1) { + __T_VERBOSE("\t Scaled count = %" PRIu64 " (%.2lf%%, %" PRIu64 "/%" PRIu64 ")\n", + counts[i].val, + (double)counts[i].run / (double)counts[i].ena * 100.0, + counts[i].run, counts[i].ena); + } else if (scaled == -1) { + __T_VERBOSE("\t Not Running\n"); + } else { + __T_VERBOSE("\t Not Scaling\n"); + } + + if (counts[i].val > max) + max = counts[i].val; + + if (counts[i].val < min) + min = counts[i].val; + + avg += counts[i].val; + + if (counts[i].val != 0) + nonzero++; + } + + if (nonzero != 0) + avg = avg / nonzero; + else + avg = 0; + + error = display_error(avg, max, min, expected_counts.val); + + __T("Error out of range!", ((error <= 1.0) && (error >= -1.0))); + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_thread_map__put(threads); + + return 0; +} + +int test_evlist(int argc, char **argv) +{ + __T_START; + + libperf_init(libperf_print); + + test_stat_cpu(); + test_stat_thread(); + test_stat_thread_enable(); + test_mmap_thread(); + test_mmap_cpus(); + test_stat_multiplexing(); + + __T_END; + return tests_failed == 0 ? 0 : -1; +} diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c new file mode 100644 index 000000000..a11fc51bf --- /dev/null +++ b/tools/lib/perf/tests/test-evsel.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> +#include <string.h> +#include <linux/perf_event.h> +#include <linux/kernel.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <perf/evsel.h> +#include <internal/evsel.h> +#include <internal/tests.h> +#include "tests.h" + +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, idx; + + 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); + + for (idx = 0; idx < perf_cpu_map__nr(cpus); idx++) { + struct perf_counts_values counts = { .val = 0 }; + + perf_evsel__read(evsel, idx, 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; +} + +static int test_stat_user_read(int event) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evsel *evsel; + struct perf_event_mmap_page *pc; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = event, +#ifdef __aarch64__ + .config1 = 0x2, /* Request user access */ +#endif + }; + int err, i; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + __T("failed to open evsel", err == 0); + + err = perf_evsel__mmap(evsel, 0); + __T("failed to mmap evsel", err == 0); + + pc = perf_evsel__mmap_base(evsel, 0, 0); + __T("failed to get mmapped address", pc); + +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) + __T("userspace counter access not supported", pc->cap_user_rdpmc); + __T("userspace counter access not enabled", pc->index); + __T("userspace counter width not set", pc->pmc_width >= 32); +#endif + + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + + for (i = 0; i < 5; i++) { + volatile int count = 0x10000 << i; + __u64 start, end, last = 0; + + __T_VERBOSE("\tloop = %u, ", count); + + perf_evsel__read(evsel, 0, 0, &counts); + start = counts.val; + + while (count--) ; + + perf_evsel__read(evsel, 0, 0, &counts); + end = counts.val; + + __T("invalid counter data", (end - start) > last); + last = end - start; + __T_VERBOSE("count = %llu\n", end - start); + } + + perf_evsel__munmap(evsel); + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + return 0; +} + +static int test_stat_read_format_single(struct perf_event_attr *attr, struct perf_thread_map *threads) +{ + struct perf_evsel *evsel; + struct perf_counts_values counts; + volatile int count = 0x100000; + int err; + + evsel = perf_evsel__new(attr); + __T("failed to create evsel", evsel); + + /* skip old kernels that don't support the format */ + err = perf_evsel__open(evsel, NULL, threads); + if (err < 0) + return 0; + + while (count--) ; + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(evsel, 0, 0, &counts); + + __T("failed to read value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read LOST", counts.lost == 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + return 0; +} + +static int test_stat_read_format_group(struct perf_event_attr *attr, struct perf_thread_map *threads) +{ + struct perf_evsel *leader, *member; + struct perf_counts_values counts; + volatile int count = 0x100000; + int err; + + attr->read_format |= PERF_FORMAT_GROUP; + leader = perf_evsel__new(attr); + __T("failed to create leader", leader); + + attr->read_format &= ~PERF_FORMAT_GROUP; + member = perf_evsel__new(attr); + __T("failed to create member", member); + + member->leader = leader; + leader->nr_members = 2; + + /* skip old kernels that don't support the format */ + err = perf_evsel__open(leader, NULL, threads); + if (err < 0) + return 0; + err = perf_evsel__open(member, NULL, threads); + if (err < 0) + return 0; + + while (count--) ; + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(leader, 0, 0, &counts); + + __T("failed to read leader value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read leader TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read leader TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read leader ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read leader LOST", counts.lost == 0); + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(member, 0, 0, &counts); + + __T("failed to read member value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read member TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read member TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read member ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read member LOST", counts.lost == 0); + + perf_evsel__close(member); + perf_evsel__close(leader); + perf_evsel__delete(member); + perf_evsel__delete(leader); + return 0; +} + +static int test_stat_read_format(void) +{ + struct perf_thread_map *threads; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err, i; + +#define FMT(_fmt) PERF_FORMAT_ ## _fmt +#define FMT_TIME (FMT(TOTAL_TIME_ENABLED) | FMT(TOTAL_TIME_RUNNING)) + + uint64_t test_formats [] = { + 0, + FMT_TIME, + FMT(ID), + FMT(LOST), + FMT_TIME | FMT(ID), + FMT_TIME | FMT(LOST), + FMT_TIME | FMT(ID) | FMT(LOST), + FMT(ID) | FMT(LOST), + }; + +#undef FMT +#undef FMT_TIME + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) { + attr.read_format = test_formats[i]; + __T_VERBOSE("testing single read with read_format: %lx\n", + (unsigned long)test_formats[i]); + + err = test_stat_read_format_single(&attr, threads); + __T("failed to read single format", err == 0); + } + + perf_thread_map__put(threads); + + threads = perf_thread_map__new_array(2, NULL); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + perf_thread_map__set_pid(threads, 1, 0); + + for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) { + attr.read_format = test_formats[i]; + __T_VERBOSE("testing group read with read_format: %lx\n", + (unsigned long)test_formats[i]); + + err = test_stat_read_format_group(&attr, threads); + __T("failed to read group format", err == 0); + } + + perf_thread_map__put(threads); + return 0; +} + +int test_evsel(int argc, char **argv) +{ + __T_START; + + libperf_init(libperf_print); + + test_stat_cpu(); + test_stat_thread(); + test_stat_thread_enable(); + test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS); + test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES); + test_stat_read_format(); + + __T_END; + return tests_failed == 0 ? 0 : -1; +} diff --git a/tools/lib/perf/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c new file mode 100644 index 000000000..f728ad700 --- /dev/null +++ b/tools/lib/perf/tests/test-threadmap.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> +#include <perf/threadmap.h> +#include <internal/tests.h> +#include "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_threadmap_array(int nr, pid_t *array) +{ + struct perf_thread_map *threads; + int i; + + threads = perf_thread_map__new_array(nr, array); + __T("Failed to allocate new thread map", threads); + + __T("Unexpected number of threads", perf_thread_map__nr(threads) == nr); + + for (i = 0; i < nr; i++) { + __T("Unexpected initial value of thread", + perf_thread_map__pid(threads, i) == (array ? array[i] : -1)); + } + + for (i = 1; i < nr; i++) + perf_thread_map__set_pid(threads, i, i * 100); + + __T("Unexpected value of thread 0", + perf_thread_map__pid(threads, 0) == (array ? array[0] : -1)); + + for (i = 1; i < nr; i++) { + __T("Unexpected thread value", + perf_thread_map__pid(threads, i) == i * 100); + } + + perf_thread_map__put(threads); + + return 0; +} + +#define THREADS_NR 10 +int test_threadmap(int argc, char **argv) +{ + struct perf_thread_map *threads; + pid_t thr_array[THREADS_NR]; + int i; + + __T_START; + + 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); + + test_threadmap_array(THREADS_NR, NULL); + + for (i = 0; i < THREADS_NR; i++) + thr_array[i] = i + 100; + + test_threadmap_array(THREADS_NR, thr_array); + + __T_END; + return tests_failed == 0 ? 0 : -1; +} diff --git a/tools/lib/perf/tests/tests.h b/tools/lib/perf/tests/tests.h new file mode 100644 index 000000000..604838f21 --- /dev/null +++ b/tools/lib/perf/tests/tests.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef TESTS_H +#define TESTS_H + +int test_cpumap(int argc, char **argv); +int test_threadmap(int argc, char **argv); +int test_evlist(int argc, char **argv); +int test_evsel(int argc, char **argv); + +#endif /* TESTS_H */ diff --git a/tools/lib/perf/threadmap.c b/tools/lib/perf/threadmap.c new file mode 100644 index 000000000..07968f3ea --- /dev/null +++ b/tools/lib/perf/threadmap.c @@ -0,0 +1,101 @@ +// 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 idx, pid_t pid) +{ + map->map[idx].pid = pid; +} + +char *perf_thread_map__comm(struct perf_thread_map *map, int idx) +{ + return map->map[idx].comm; +} + +struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array) +{ + struct perf_thread_map *threads = thread_map__alloc(nr_threads); + int i; + + if (!threads) + return NULL; + + for (i = 0; i < nr_threads; i++) + perf_thread_map__set_pid(threads, i, array ? array[i] : -1); + + threads->nr = nr_threads; + refcount_set(&threads->refcnt, 1); + + return threads; +} + +struct perf_thread_map *perf_thread_map__new_dummy(void) +{ + return perf_thread_map__new_array(1, NULL); +} + +static void perf_thread_map__delete(struct perf_thread_map *threads) +{ + if (threads) { + 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 idx) +{ + return map->map[idx].pid; +} diff --git a/tools/lib/perf/xyarray.c b/tools/lib/perf/xyarray.c new file mode 100644 index 000000000..dcd901d15 --- /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 new file mode 100644 index 000000000..727396de6 --- /dev/null +++ b/tools/lib/rbtree.c @@ -0,0 +1,597 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + Red Black Trees + (C) 1999 Andrea Arcangeli <andrea@suse.de> + (C) 2002 David Woodhouse <dwmw2@infradead.org> + (C) 2012 Michel Lespinasse <walken@google.com> + + + linux/lib/rbtree.c +*/ + +#include <linux/rbtree_augmented.h> +#include <linux/export.h> + +/* + * red-black trees properties: https://en.wikipedia.org/wiki/Rbtree + * + * 1) A node is either red or black + * 2) The root is black + * 3) All leaves (NULL) are black + * 4) Both children of every red node are black + * 5) Every simple path from root to leaves contains the same number + * of black nodes. + * + * 4 and 5 give the O(log n) guarantee, since 4 implies you cannot have two + * consecutive red nodes in a path and every red node is therefore followed by + * a black. So if B is the number of black nodes on every simple path (as per + * 5), then the longest possible path due to 4 is 2B. + * + * We shall indicate color with case, where black nodes are uppercase and red + * nodes will be lowercase. Unknown color nodes shall be drawn as red within + * parentheses and have some accompanying text comment. + */ + +/* + * Notes on lockless lookups: + * + * All stores to the tree structure (rb_left and rb_right) must be done using + * WRITE_ONCE(). And we must not inadvertently cause (temporary) loops in the + * tree structure as seen in program order. + * + * These two requirements will allow lockless iteration of the tree -- not + * correct iteration mind you, tree rotations are not atomic so a lookup might + * miss entire subtrees. + * + * But they do guarantee that any such traversal will only see valid elements + * and that it will indeed complete -- does not get stuck in a loop. + * + * It also guarantees that if the lookup returns an element it is the 'correct' + * one. But not returning an element does _NOT_ mean it's not present. + * + * NOTE: + * + * Stores to __rb_parent_color are not important for simple lookups so those + * are left undone as of now. Nor did I check for loops involving parent + * pointers. + */ + +static inline void rb_set_black(struct rb_node *rb) +{ + rb->__rb_parent_color |= RB_BLACK; +} + +static inline struct rb_node *rb_red_parent(struct rb_node *red) +{ + return (struct rb_node *)red->__rb_parent_color; +} + +/* + * Helper function for rotations: + * - old's parent and color get assigned to new + * - old gets assigned new as a parent and 'color' as a color. + */ +static inline void +__rb_rotate_set_parents(struct rb_node *old, struct rb_node *new, + struct rb_root *root, int color) +{ + struct rb_node *parent = rb_parent(old); + new->__rb_parent_color = old->__rb_parent_color; + rb_set_parent_color(old, new, color); + __rb_change_child(old, new, parent, root); +} + +static __always_inline void +__rb_insert(struct rb_node *node, struct rb_root *root, + void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) +{ + struct rb_node *parent = rb_red_parent(node), *gparent, *tmp; + + while (true) { + /* + * Loop invariant: node is red. + */ + if (unlikely(!parent)) { + /* + * The inserted node is root. Either this is the + * first node, or we recursed at Case 1 below and + * are no longer violating 4). + */ + rb_set_parent_color(node, NULL, RB_BLACK); + break; + } + + /* + * If there is a black parent, we are done. + * Otherwise, take some corrective action as, + * per 4), we don't want a red root or two + * consecutive red nodes. + */ + if(rb_is_black(parent)) + break; + + gparent = rb_red_parent(parent); + + tmp = gparent->rb_right; + if (parent != tmp) { /* parent == gparent->rb_left */ + if (tmp && rb_is_red(tmp)) { + /* + * Case 1 - node's uncle is red (color flips). + * + * G g + * / \ / \ + * p u --> P U + * / / + * n n + * + * However, since g's parent might be red, and + * 4) does not allow this, we need to recurse + * at g. + */ + rb_set_parent_color(tmp, gparent, RB_BLACK); + rb_set_parent_color(parent, gparent, RB_BLACK); + node = gparent; + parent = rb_parent(node); + rb_set_parent_color(node, parent, RB_RED); + continue; + } + + tmp = parent->rb_right; + if (node == tmp) { + /* + * Case 2 - node's uncle is black and node is + * the parent's right child (left rotate at parent). + * + * G G + * / \ / \ + * p U --> n U + * \ / + * n p + * + * This still leaves us in violation of 4), the + * continuation into Case 3 will fix that. + */ + tmp = node->rb_left; + WRITE_ONCE(parent->rb_right, tmp); + WRITE_ONCE(node->rb_left, parent); + if (tmp) + rb_set_parent_color(tmp, parent, + RB_BLACK); + rb_set_parent_color(parent, node, RB_RED); + augment_rotate(parent, node); + parent = node; + tmp = node->rb_right; + } + + /* + * Case 3 - node's uncle is black and node is + * the parent's left child (right rotate at gparent). + * + * G P + * / \ / \ + * p U --> n g + * / \ + * n U + */ + WRITE_ONCE(gparent->rb_left, tmp); /* == parent->rb_right */ + WRITE_ONCE(parent->rb_right, gparent); + if (tmp) + rb_set_parent_color(tmp, gparent, RB_BLACK); + __rb_rotate_set_parents(gparent, parent, root, RB_RED); + augment_rotate(gparent, parent); + break; + } else { + tmp = gparent->rb_left; + if (tmp && rb_is_red(tmp)) { + /* Case 1 - color flips */ + rb_set_parent_color(tmp, gparent, RB_BLACK); + rb_set_parent_color(parent, gparent, RB_BLACK); + node = gparent; + parent = rb_parent(node); + rb_set_parent_color(node, parent, RB_RED); + continue; + } + + tmp = parent->rb_left; + if (node == tmp) { + /* Case 2 - right rotate at parent */ + tmp = node->rb_right; + WRITE_ONCE(parent->rb_left, tmp); + WRITE_ONCE(node->rb_right, parent); + if (tmp) + rb_set_parent_color(tmp, parent, + RB_BLACK); + rb_set_parent_color(parent, node, RB_RED); + augment_rotate(parent, node); + parent = node; + tmp = node->rb_left; + } + + /* Case 3 - left rotate at gparent */ + WRITE_ONCE(gparent->rb_right, tmp); /* == parent->rb_left */ + WRITE_ONCE(parent->rb_left, gparent); + if (tmp) + rb_set_parent_color(tmp, gparent, RB_BLACK); + __rb_rotate_set_parents(gparent, parent, root, RB_RED); + augment_rotate(gparent, parent); + break; + } + } +} + +/* + * Inline version for rb_erase() use - we want to be able to inline + * and eliminate the dummy_rotate callback there + */ +static __always_inline void +____rb_erase_color(struct rb_node *parent, struct rb_root *root, + void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) +{ + struct rb_node *node = NULL, *sibling, *tmp1, *tmp2; + + while (true) { + /* + * Loop invariants: + * - node is black (or NULL on first iteration) + * - node is not the root (parent is not NULL) + * - All leaf paths going through parent and node have a + * black node count that is 1 lower than other leaf paths. + */ + sibling = parent->rb_right; + if (node != sibling) { /* node == parent->rb_left */ + if (rb_is_red(sibling)) { + /* + * Case 1 - left rotate at parent + * + * P S + * / \ / \ + * N s --> p Sr + * / \ / \ + * Sl Sr N Sl + */ + tmp1 = sibling->rb_left; + WRITE_ONCE(parent->rb_right, tmp1); + WRITE_ONCE(sibling->rb_left, parent); + rb_set_parent_color(tmp1, parent, RB_BLACK); + __rb_rotate_set_parents(parent, sibling, root, + RB_RED); + augment_rotate(parent, sibling); + sibling = tmp1; + } + tmp1 = sibling->rb_right; + if (!tmp1 || rb_is_black(tmp1)) { + tmp2 = sibling->rb_left; + if (!tmp2 || rb_is_black(tmp2)) { + /* + * Case 2 - sibling color flip + * (p could be either color here) + * + * (p) (p) + * / \ / \ + * N S --> N s + * / \ / \ + * Sl Sr Sl Sr + * + * This leaves us violating 5) which + * can be fixed by flipping p to black + * if it was red, or by recursing at p. + * p is red when coming from Case 1. + */ + rb_set_parent_color(sibling, parent, + RB_RED); + if (rb_is_red(parent)) + rb_set_black(parent); + else { + node = parent; + parent = rb_parent(node); + if (parent) + continue; + } + break; + } + /* + * Case 3 - right rotate at sibling + * (p could be either color here) + * + * (p) (p) + * / \ / \ + * N S --> N sl + * / \ \ + * sl Sr S + * \ + * Sr + * + * Note: p might be red, and then both + * p and sl are red after rotation(which + * breaks property 4). This is fixed in + * Case 4 (in __rb_rotate_set_parents() + * which set sl the color of p + * and set p RB_BLACK) + * + * (p) (sl) + * / \ / \ + * N sl --> P S + * \ / \ + * S N Sr + * \ + * Sr + */ + tmp1 = tmp2->rb_right; + WRITE_ONCE(sibling->rb_left, tmp1); + WRITE_ONCE(tmp2->rb_right, sibling); + WRITE_ONCE(parent->rb_right, tmp2); + if (tmp1) + rb_set_parent_color(tmp1, sibling, + RB_BLACK); + augment_rotate(sibling, tmp2); + tmp1 = sibling; + sibling = tmp2; + } + /* + * Case 4 - left rotate at parent + color flips + * (p and sl could be either color here. + * After rotation, p becomes black, s acquires + * p's color, and sl keeps its color) + * + * (p) (s) + * / \ / \ + * N S --> P Sr + * / \ / \ + * (sl) sr N (sl) + */ + tmp2 = sibling->rb_left; + WRITE_ONCE(parent->rb_right, tmp2); + WRITE_ONCE(sibling->rb_left, parent); + rb_set_parent_color(tmp1, sibling, RB_BLACK); + if (tmp2) + rb_set_parent(tmp2, parent); + __rb_rotate_set_parents(parent, sibling, root, + RB_BLACK); + augment_rotate(parent, sibling); + break; + } else { + sibling = parent->rb_left; + if (rb_is_red(sibling)) { + /* Case 1 - right rotate at parent */ + tmp1 = sibling->rb_right; + WRITE_ONCE(parent->rb_left, tmp1); + WRITE_ONCE(sibling->rb_right, parent); + rb_set_parent_color(tmp1, parent, RB_BLACK); + __rb_rotate_set_parents(parent, sibling, root, + RB_RED); + augment_rotate(parent, sibling); + sibling = tmp1; + } + tmp1 = sibling->rb_left; + if (!tmp1 || rb_is_black(tmp1)) { + tmp2 = sibling->rb_right; + if (!tmp2 || rb_is_black(tmp2)) { + /* Case 2 - sibling color flip */ + rb_set_parent_color(sibling, parent, + RB_RED); + if (rb_is_red(parent)) + rb_set_black(parent); + else { + node = parent; + parent = rb_parent(node); + if (parent) + continue; + } + break; + } + /* Case 3 - left rotate at sibling */ + tmp1 = tmp2->rb_left; + WRITE_ONCE(sibling->rb_right, tmp1); + WRITE_ONCE(tmp2->rb_left, sibling); + WRITE_ONCE(parent->rb_left, tmp2); + if (tmp1) + rb_set_parent_color(tmp1, sibling, + RB_BLACK); + augment_rotate(sibling, tmp2); + tmp1 = sibling; + sibling = tmp2; + } + /* Case 4 - right rotate at parent + color flips */ + tmp2 = sibling->rb_right; + WRITE_ONCE(parent->rb_left, tmp2); + WRITE_ONCE(sibling->rb_right, parent); + rb_set_parent_color(tmp1, sibling, RB_BLACK); + if (tmp2) + rb_set_parent(tmp2, parent); + __rb_rotate_set_parents(parent, sibling, root, + RB_BLACK); + augment_rotate(parent, sibling); + break; + } + } +} + +/* Non-inline version for rb_erase_augmented() use */ +void __rb_erase_color(struct rb_node *parent, struct rb_root *root, + void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) +{ + ____rb_erase_color(parent, root, augment_rotate); +} + +/* + * Non-augmented rbtree manipulation functions. + * + * We use dummy augmented callbacks here, and have the compiler optimize them + * out of the rb_insert_color() and rb_erase() function definitions. + */ + +static inline void dummy_propagate(struct rb_node *node, struct rb_node *stop) {} +static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {} +static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {} + +static const struct rb_augment_callbacks dummy_callbacks = { + .propagate = dummy_propagate, + .copy = dummy_copy, + .rotate = dummy_rotate +}; + +void rb_insert_color(struct rb_node *node, struct rb_root *root) +{ + __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, &dummy_callbacks); + if (rebalance) + ____rb_erase_color(rebalance, root, dummy_rotate); +} + +/* + * Augmented rbtree manipulation functions. + * + * This instantiates the same __always_inline functions as in the non-augmented + * case, but this time with user-defined callbacks. + */ + +void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, + void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) +{ + __rb_insert(node, root, augment_rotate); +} + +/* + * This function returns the first node (in sort order) of the tree. + */ +struct rb_node *rb_first(const struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_left) + n = n->rb_left; + return n; +} + +struct rb_node *rb_last(const struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_right) + n = n->rb_right; + return n; +} + +struct rb_node *rb_next(const struct rb_node *node) +{ + struct rb_node *parent; + + if (RB_EMPTY_NODE(node)) + return NULL; + + /* + * If we have a right-hand child, go down and then left as far + * as we can. + */ + if (node->rb_right) { + node = node->rb_right; + while (node->rb_left) + node = node->rb_left; + return (struct rb_node *)node; + } + + /* + * No right-hand children. Everything down and left is smaller than us, + * so any 'next' node must be in the general direction of our parent. + * Go up the tree; any time the ancestor is a right-hand child of its + * parent, keep going up. First time it's a left-hand child of its + * parent, said parent is our 'next' node. + */ + while ((parent = rb_parent(node)) && node == parent->rb_right) + node = parent; + + return parent; +} + +struct rb_node *rb_prev(const struct rb_node *node) +{ + struct rb_node *parent; + + if (RB_EMPTY_NODE(node)) + return NULL; + + /* + * If we have a left-hand child, go down and then right as far + * as we can. + */ + if (node->rb_left) { + node = node->rb_left; + while (node->rb_right) + node = node->rb_right; + return (struct rb_node *)node; + } + + /* + * No left-hand children. Go up till we find an ancestor which + * is a right-hand child of its parent. + */ + while ((parent = rb_parent(node)) && node == parent->rb_left) + node = parent; + + return parent; +} + +void rb_replace_node(struct rb_node *victim, struct rb_node *new, + struct rb_root *root) +{ + struct rb_node *parent = rb_parent(victim); + + /* Copy the pointers/colour from the victim to the replacement */ + *new = *victim; + + /* Set the surrounding nodes to point to the replacement */ + if (victim->rb_left) + rb_set_parent(victim->rb_left, new); + if (victim->rb_right) + rb_set_parent(victim->rb_right, new); + __rb_change_child(victim, new, parent, root); +} + +static struct rb_node *rb_left_deepest_node(const struct rb_node *node) +{ + for (;;) { + if (node->rb_left) + node = node->rb_left; + else if (node->rb_right) + node = node->rb_right; + else + return (struct rb_node *)node; + } +} + +struct rb_node *rb_next_postorder(const struct rb_node *node) +{ + const struct rb_node *parent; + if (!node) + return NULL; + parent = rb_parent(node); + + /* If we're sitting on node, we've already seen our children */ + if (parent && node == parent->rb_left && parent->rb_right) { + /* If we are the parent's left node, go to the parent's right + * node then all the way down to the left */ + return rb_left_deepest_node(parent->rb_right); + } else + /* Otherwise we are the parent's right node, and the parent + * should be next */ + return (struct rb_node *)parent; +} + +struct rb_node *rb_first_postorder(const struct rb_root *root) +{ + if (!root->rb_node) + return NULL; + + return rb_left_deepest_node(root->rb_node); +} diff --git a/tools/lib/slab.c b/tools/lib/slab.c new file mode 100644 index 000000000..959997fb0 --- /dev/null +++ b/tools/lib/slab.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <string.h> + +#include <urcu/uatomic.h> +#include <linux/slab.h> +#include <malloc.h> +#include <linux/gfp.h> + +int kmalloc_nr_allocated; +int kmalloc_verbose; + +void *kmalloc(size_t size, gfp_t gfp) +{ + void *ret; + + if (!(gfp & __GFP_DIRECT_RECLAIM)) + return NULL; + + ret = malloc(size); + uatomic_inc(&kmalloc_nr_allocated); + if (kmalloc_verbose) + printf("Allocating %p from malloc\n", ret); + if (gfp & __GFP_ZERO) + memset(ret, 0, size); + return ret; +} + +void kfree(void *p) +{ + if (!p) + return; + uatomic_dec(&kmalloc_nr_allocated); + if (kmalloc_verbose) + printf("Freeing %p to malloc\n", p); + free(p); +} diff --git a/tools/lib/str_error_r.c b/tools/lib/str_error_r.c new file mode 100644 index 000000000..6aad8308a --- /dev/null +++ b/tools/lib/str_error_r.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +#undef _GNU_SOURCE +#include <string.h> +#include <stdio.h> +#include <linux/string.h> + +/* + * The tools so far have been using the strerror_r() GNU variant, that returns + * a string, be it the buffer passed or something else. + * + * But that, besides being tricky in cases where we expect that the function + * using strerror_r() returns the error formatted in a provided buffer (we have + * to check if it returned something else and copy that instead), breaks the + * build on systems not using glibc, like Alpine Linux, where musl libc is + * used. + * + * So, introduce yet another wrapper, str_error_r(), that has the GNU + * interface, but uses the portable XSI variant of strerror_r(), so that users + * rest asured that the provided buffer is used and it is what is returned. + */ +char *str_error_r(int errnum, char *buf, size_t buflen) +{ + int err = strerror_r(errnum, buf, buflen); + if (err) + snprintf(buf, buflen, "INTERNAL ERROR: strerror_r(%d, [buf], %zd)=%d", errnum, buflen, err); + return buf; +} diff --git a/tools/lib/string.c b/tools/lib/string.c new file mode 100644 index 000000000..8b6892f95 --- /dev/null +++ b/tools/lib/string.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/tools/lib/string.c + * + * Copied from linux/lib/string.c, where it is: + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * More specifically, the first copied function was strtobool, which + * was introduced by: + * + * d0f1fed29e6e ("Add a strtobool function matching semantics of existing in kernel equivalents") + * Author: Jonathan Cameron <jic23@cam.ac.uk> + */ + +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <linux/compiler.h> + +/** + * memdup - duplicate region of memory + * + * @src: memory region to duplicate + * @len: memory region length + */ +void *memdup(const void *src, size_t len) +{ + void *p = malloc(len); + + if (p) + memcpy(p, src, len); + + return p; +} + +/** + * strtobool - convert common user inputs into boolean values + * @s: input string + * @res: result + * + * This routine returns 0 iff the first character is one of 'Yy1Nn0', or + * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value + * pointed to by res is updated upon finding a match. + */ +int strtobool(const char *s, bool *res) +{ + if (!s) + return -EINVAL; + + switch (s[0]) { + case 'y': + case 'Y': + case '1': + *res = true; + return 0; + case 'n': + case 'N': + case '0': + *res = false; + return 0; + case 'o': + case 'O': + switch (s[1]) { + case 'n': + case 'N': + *res = true; + return 0; + case 'f': + case 'F': + *res = false; + return 0; + default: + break; + } + default: + break; + } + + return -EINVAL; +} + +/** + * strlcpy - Copy a C-string into a sized buffer + * @dest: Where to copy the string to + * @src: Where to copy the string from + * @size: size of destination buffer + * + * Compatible with *BSD: the result is always a valid + * NUL-terminated string that fits in the buffer (unless, + * of course, the buffer size is zero). It does not pad + * out the result like strncpy() does. + * + * 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); + + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + memcpy(dest, src, len); + dest[len] = '\0'; + } + return ret; +} +#ifdef __clang__ +#pragma clang diagnostic pop +#endif + +/** + * skip_spaces - Removes leading whitespace from @str. + * @str: The string to be stripped. + * + * Returns a pointer to the first non-whitespace character in @str. + */ +char *skip_spaces(const char *str) +{ + while (isspace(*str)) + ++str; + return (char *)str; +} + +/** + * strim - Removes leading and trailing whitespace from @s. + * @s: The string to be stripped. + * + * Note that the first trailing whitespace is replaced with a %NUL-terminator + * in the given string @s. Returns a pointer to the first non-whitespace + * character in @s. + */ +char *strim(char *s) +{ + size_t size; + char *end; + + size = strlen(s); + if (!size) + return s; + + end = s + size - 1; + while (end >= s && isspace(*end)) + end--; + *(end + 1) = '\0'; + + return skip_spaces(s); +} + +/** + * strreplace - Replace all occurrences of character in string. + * @s: The string to operate on. + * @old: The character being replaced. + * @new: The character @old is replaced with. + * + * Returns pointer to the nul byte at the end of @s. + */ +char *strreplace(char *s, char old, char new) +{ + for (; *s; ++s) + if (*s == old) + *s = new; + return s; +} + +static void *check_bytes8(const u8 *start, u8 value, unsigned int bytes) +{ + while (bytes) { + if (*start != value) + return (void *)start; + start++; + bytes--; + } + return NULL; +} + +/** + * memchr_inv - Find an unmatching character in an area of memory. + * @start: The memory area + * @c: Find a character other than c + * @bytes: The size of the area. + * + * returns the address of the first character other than @c, or %NULL + * if the whole buffer contains just @c. + */ +void *memchr_inv(const void *start, int c, size_t bytes) +{ + u8 value = c; + u64 value64; + unsigned int words, prefix; + + if (bytes <= 16) + return check_bytes8(start, value, bytes); + + value64 = value; + value64 |= value64 << 8; + value64 |= value64 << 16; + value64 |= value64 << 32; + + prefix = (unsigned long)start % 8; + if (prefix) { + u8 *r; + + prefix = 8 - prefix; + r = check_bytes8(start, value, prefix); + if (r) + return r; + start += prefix; + bytes -= prefix; + } + + words = bytes / 8; + + while (words) { + if (*(u64 *)start != value64) + return check_bytes8(start, value, 8); + start += 8; + words--; + } + + return check_bytes8(start, value, bytes % 8); +} diff --git a/tools/lib/subcmd/Build b/tools/lib/subcmd/Build new file mode 100644 index 000000000..ee3128878 --- /dev/null +++ b/tools/lib/subcmd/Build @@ -0,0 +1,7 @@ +libsubcmd-y += exec-cmd.o +libsubcmd-y += help.o +libsubcmd-y += pager.o +libsubcmd-y += parse-options.o +libsubcmd-y += run-command.o +libsubcmd-y += sigchain.o +libsubcmd-y += subcmd-config.o diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile new file mode 100644 index 000000000..b87213263 --- /dev/null +++ b/tools/lib/subcmd/Makefile @@ -0,0 +1,122 @@ +# SPDX-License-Identifier: GPL-2.0 +include ../../scripts/Makefile.include +include ../../scripts/utilities.mak # QUIET_CLEAN + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +CC ?= $(CROSS_COMPILE)gcc +LD ?= $(CROSS_COMPILE)ld +AR ?= $(CROSS_COMPILE)ar + +RM = rm -f + +MAKEFLAGS += --no-print-directory + +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +LIBFILE = $(OUTPUT)libsubcmd.a + +CFLAGS := -ggdb3 -Wall -Wextra -std=gnu99 -fPIC + +ifeq ($(DEBUG),0) + ifeq ($(feature-fortify-source), 1) + CFLAGS += -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 + endif +endif + +ifeq ($(DEBUG),1) + CFLAGS += -O0 +else ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -O3 +else + CFLAGS += -O6 +endif + +# Treat warnings as errors unless directed not to +ifneq ($(WERROR),0) + CFLAGS += -Werror +endif + +CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE + +CFLAGS += -I$(srctree)/tools/include/ + +CFLAGS += $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) + +SUBCMD_IN := $(OUTPUT)libsubcmd-in.o + +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= +libdir = $(prefix)/$(libdir_relative) + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) + +all: + +export srctree OUTPUT CC LD CFLAGS V +include $(srctree)/tools/build/Makefile.include + +all: fixdep $(LIBFILE) + +$(SUBCMD_IN): FORCE + @$(MAKE) $(build)=libsubcmd + +$(LIBFILE): $(SUBCMD_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(SUBCMD_IN) + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + if [ ! -d '$2' ]; then \ + $(INSTALL) -d -m 755 '$2'; \ + fi; \ + $(INSTALL) $1 $(if $3,-m $3,) '$2' +endef + +install_lib: $(LIBFILE) + $(call QUIET_INSTALL, $(LIBFILE)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIBFILE) $(DESTDIR)$(libdir_SQ) + +HDRS := exec-cmd.h help.h pager.h parse-options.h run-command.h +INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/subcmd +INSTALL_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(HDRS)) + +$(INSTALL_HDRS): $(INSTALL_HDRS_PFX)/%.h: %.h + $(call QUIET_INSTALL, $@) \ + $(call do_install,$<,$(INSTALL_HDRS_PFX)/,644) + +install_headers: $(INSTALL_HDRS) + $(call QUIET_INSTALL, libsubcmd_headers) + +install: install_lib install_headers + +clean: + $(call QUIET_CLEAN, libsubcmd) $(RM) $(LIBFILE); \ + find $(or $(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) + +FORCE: + +.PHONY: clean FORCE diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c new file mode 100644 index 000000000..5dbea4569 --- /dev/null +++ b/tools/lib/subcmd/exec-cmd.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <linux/string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include "subcmd-util.h" +#include "exec-cmd.h" +#include "subcmd-config.h" + +#define MAX_ARGS 32 +#define PATH_MAX 4096 + +static const char *argv_exec_path; +static const char *argv0_path; + +void exec_cmd_init(const char *exec_name, const char *prefix, + const char *exec_path, const char *exec_path_env) +{ + subcmd_config.exec_name = exec_name; + subcmd_config.prefix = prefix; + subcmd_config.exec_path = exec_path; + subcmd_config.exec_path_env = exec_path_env; + + /* Setup environment variable for invoked shell script. */ + setenv("PREFIX", prefix, 1); +} + +#define is_dir_sep(c) ((c) == '/') + +static int is_absolute_path(const char *path) +{ + return path[0] == '/'; +} + +static const char *get_pwd_cwd(void) +{ + static char cwd[PATH_MAX + 1]; + char *pwd; + struct stat cwd_stat, pwd_stat; + if (getcwd(cwd, PATH_MAX) == NULL) + return NULL; + pwd = getenv("PWD"); + if (pwd && strcmp(pwd, cwd)) { + stat(cwd, &cwd_stat); + if (!stat(pwd, &pwd_stat) && + pwd_stat.st_dev == cwd_stat.st_dev && + pwd_stat.st_ino == cwd_stat.st_ino) { + strlcpy(cwd, pwd, PATH_MAX); + } + } + return cwd; +} + +static const char *make_nonrelative_path(const char *path) +{ + static char buf[PATH_MAX + 1]; + + if (is_absolute_path(path)) { + if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + } else { + const char *cwd = get_pwd_cwd(); + if (!cwd) + die("Cannot determine the current working directory"); + if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + } + return buf; +} + +char *system_path(const char *path) +{ + char *buf = NULL; + + if (is_absolute_path(path)) + return strdup(path); + + astrcatf(&buf, "%s/%s", subcmd_config.prefix, path); + + return buf; +} + +const char *extract_argv0_path(const char *argv0) +{ + const char *slash; + + if (!argv0 || !*argv0) + return NULL; + slash = argv0 + strlen(argv0); + + while (argv0 <= slash && !is_dir_sep(*slash)) + slash--; + + if (slash >= argv0) { + argv0_path = strndup(argv0, slash - argv0); + return argv0_path ? slash + 1 : NULL; + } + + return argv0; +} + +void set_argv_exec_path(const char *exec_path) +{ + argv_exec_path = exec_path; + /* + * Propagate this setting to external programs. + */ + setenv(subcmd_config.exec_path_env, exec_path, 1); +} + + +/* Returns the highest-priority location to look for subprograms. */ +char *get_argv_exec_path(void) +{ + char *env; + + if (argv_exec_path) + return strdup(argv_exec_path); + + env = getenv(subcmd_config.exec_path_env); + if (env && *env) + return strdup(env); + + return system_path(subcmd_config.exec_path); +} + +static void add_path(char **out, const char *path) +{ + if (path && *path) { + if (is_absolute_path(path)) + astrcat(out, path); + else + astrcat(out, make_nonrelative_path(path)); + + astrcat(out, ":"); + } +} + +void setup_path(void) +{ + const char *old_path = getenv("PATH"); + char *new_path = NULL; + char *tmp = get_argv_exec_path(); + + add_path(&new_path, tmp); + add_path(&new_path, argv0_path); + free(tmp); + + if (old_path) + astrcat(&new_path, old_path); + else + astrcat(&new_path, "/usr/local/bin:/usr/bin:/bin"); + + setenv("PATH", new_path, 1); + + free(new_path); +} + +static const char **prepare_exec_cmd(const char **argv) +{ + int argc; + const char **nargv; + + for (argc = 0; argv[argc]; argc++) + ; /* just counting */ + nargv = malloc(sizeof(*nargv) * (argc + 2)); + + nargv[0] = subcmd_config.exec_name; + for (argc = 0; argv[argc]; argc++) + nargv[argc + 1] = argv[argc]; + nargv[argc + 1] = NULL; + return nargv; +} + +int execv_cmd(const char **argv) { + const char **nargv = prepare_exec_cmd(argv); + + /* execvp() can only ever return if it fails */ + execvp(subcmd_config.exec_name, (char **)nargv); + + free(nargv); + return -1; +} + + +int execl_cmd(const char *cmd,...) +{ + int argc; + const char *argv[MAX_ARGS + 1]; + const char *arg; + va_list param; + + va_start(param, cmd); + argv[0] = cmd; + argc = 1; + while (argc < MAX_ARGS) { + arg = argv[argc++] = va_arg(param, char *); + if (!arg) + break; + } + va_end(param); + if (MAX_ARGS <= argc) { + fprintf(stderr, " Error: too many args to run %s\n", cmd); + return -1; + } + + argv[argc] = NULL; + return execv_cmd(argv); +} diff --git a/tools/lib/subcmd/exec-cmd.h b/tools/lib/subcmd/exec-cmd.h new file mode 100644 index 000000000..aba591b8d --- /dev/null +++ b/tools/lib/subcmd/exec-cmd.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SUBCMD_EXEC_CMD_H +#define __SUBCMD_EXEC_CMD_H + +extern void exec_cmd_init(const char *exec_name, const char *prefix, + const char *exec_path, const char *exec_path_env); + +extern void set_argv_exec_path(const char *exec_path); +extern const char *extract_argv0_path(const char *path); +extern void setup_path(void); +extern int execv_cmd(const char **argv); /* NULL terminated */ +extern int execl_cmd(const char *cmd, ...); +/* get_argv_exec_path and system_path return malloc'd string, caller must free it */ +extern char *get_argv_exec_path(void); +extern char *system_path(const char *path); + +#endif /* __SUBCMD_EXEC_CMD_H */ diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c new file mode 100644 index 000000000..bf02d62a3 --- /dev/null +++ b/tools/lib/subcmd/help.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <linux/string.h> +#include <termios.h> +#include <sys/ioctl.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <dirent.h> +#include "subcmd-util.h" +#include "help.h" +#include "exec-cmd.h" + +void add_cmdname(struct cmdnames *cmds, const char *name, size_t len) +{ + struct cmdname *ent = malloc(sizeof(*ent) + len + 1); + + ent->len = len; + memcpy(ent->name, name, len); + ent->name[len] = 0; + + ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc); + cmds->names[cmds->cnt++] = ent; +} + +void clean_cmdnames(struct cmdnames *cmds) +{ + unsigned int i; + + for (i = 0; i < cmds->cnt; ++i) + zfree(&cmds->names[i]); + zfree(&cmds->names); + cmds->cnt = 0; + cmds->alloc = 0; +} + +int cmdname_compare(const void *a_, const void *b_) +{ + struct cmdname *a = *(struct cmdname **)a_; + struct cmdname *b = *(struct cmdname **)b_; + return strcmp(a->name, b->name); +} + +void uniq(struct cmdnames *cmds) +{ + unsigned int i, j; + + if (!cmds->cnt) + return; + + for (i = j = 1; i < cmds->cnt; i++) + if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) + cmds->names[j++] = cmds->names[i]; + + cmds->cnt = j; +} + +void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) +{ + size_t ci, cj, ei; + int cmp; + + ci = cj = ei = 0; + while (ci < cmds->cnt && ei < excludes->cnt) { + cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name); + if (cmp < 0) { + cmds->names[cj++] = cmds->names[ci++]; + } else if (cmp == 0) { + ci++; + ei++; + } else if (cmp > 0) { + ei++; + } + } + + while (ci < cmds->cnt) + cmds->names[cj++] = cmds->names[ci++]; + + cmds->cnt = cj; +} + +static void get_term_dimensions(struct winsize *ws) +{ + char *s = getenv("LINES"); + + if (s != NULL) { + ws->ws_row = atoi(s); + s = getenv("COLUMNS"); + if (s != NULL) { + ws->ws_col = atoi(s); + if (ws->ws_row && ws->ws_col) + return; + } + } +#ifdef TIOCGWINSZ + if (ioctl(1, TIOCGWINSZ, ws) == 0 && + ws->ws_row && ws->ws_col) + return; +#endif + ws->ws_row = 25; + ws->ws_col = 80; +} + +static void pretty_print_string_list(struct cmdnames *cmds, int longest) +{ + int cols = 1, rows; + int space = longest + 1; /* min 1 SP between words */ + struct winsize win; + int max_cols; + int i, j; + + get_term_dimensions(&win); + max_cols = win.ws_col - 1; /* don't print *on* the edge */ + + if (space < max_cols) + cols = max_cols / space; + rows = (cmds->cnt + cols - 1) / cols; + + for (i = 0; i < rows; i++) { + printf(" "); + + for (j = 0; j < cols; j++) { + unsigned int n = j * rows + i; + unsigned int size = space; + + if (n >= cmds->cnt) + break; + if (j == cols-1 || n + rows >= cmds->cnt) + size = 1; + printf("%-*s", size, cmds->names[n]->name); + } + putchar('\n'); + } +} + +static int is_executable(const char *name) +{ + struct stat st; + + if (stat(name, &st) || /* stat, not lstat */ + !S_ISREG(st.st_mode)) + return 0; + + return st.st_mode & S_IXUSR; +} + +static int has_extension(const char *filename, const char *ext) +{ + size_t len = strlen(filename); + size_t extlen = strlen(ext); + + return len > extlen && !memcmp(filename + len - extlen, ext, extlen); +} + +static void list_commands_in_dir(struct cmdnames *cmds, + const char *path, + const char *prefix) +{ + int prefix_len; + DIR *dir = opendir(path); + struct dirent *de; + char *buf = NULL; + + if (!dir) + return; + if (!prefix) + prefix = "perf-"; + prefix_len = strlen(prefix); + + astrcatf(&buf, "%s/", path); + + while ((de = readdir(dir)) != NULL) { + int entlen; + + if (!strstarts(de->d_name, prefix)) + continue; + + astrcat(&buf, de->d_name); + if (!is_executable(buf)) + continue; + + entlen = strlen(de->d_name) - prefix_len; + if (has_extension(de->d_name, ".exe")) + entlen -= 4; + + add_cmdname(cmds, de->d_name + prefix_len, entlen); + } + closedir(dir); + free(buf); +} + +void load_command_list(const char *prefix, + struct cmdnames *main_cmds, + struct cmdnames *other_cmds) +{ + const char *env_path = getenv("PATH"); + char *exec_path = get_argv_exec_path(); + + if (exec_path) { + list_commands_in_dir(main_cmds, exec_path, prefix); + qsort(main_cmds->names, main_cmds->cnt, + sizeof(*main_cmds->names), cmdname_compare); + uniq(main_cmds); + } + + if (env_path) { + char *paths, *path, *colon; + path = paths = strdup(env_path); + while (1) { + if ((colon = strchr(path, ':'))) + *colon = 0; + if (!exec_path || strcmp(path, exec_path)) + list_commands_in_dir(other_cmds, path, prefix); + + if (!colon) + break; + path = colon + 1; + } + free(paths); + + qsort(other_cmds->names, other_cmds->cnt, + sizeof(*other_cmds->names), cmdname_compare); + uniq(other_cmds); + } + free(exec_path); + exclude_cmds(other_cmds, main_cmds); +} + +void list_commands(const char *title, struct cmdnames *main_cmds, + struct cmdnames *other_cmds) +{ + unsigned int i, longest = 0; + + for (i = 0; i < main_cmds->cnt; i++) + if (longest < main_cmds->names[i]->len) + longest = main_cmds->names[i]->len; + for (i = 0; i < other_cmds->cnt; i++) + if (longest < other_cmds->names[i]->len) + longest = other_cmds->names[i]->len; + + if (main_cmds->cnt) { + char *exec_path = get_argv_exec_path(); + printf("available %s in '%s'\n", title, exec_path); + printf("----------------"); + mput_char('-', strlen(title) + strlen(exec_path)); + putchar('\n'); + pretty_print_string_list(main_cmds, longest); + putchar('\n'); + free(exec_path); + } + + if (other_cmds->cnt) { + printf("%s available from elsewhere on your $PATH\n", title); + printf("---------------------------------------"); + mput_char('-', strlen(title)); + putchar('\n'); + pretty_print_string_list(other_cmds, longest); + putchar('\n'); + } +} + +int is_in_cmdlist(struct cmdnames *c, const char *s) +{ + unsigned int i; + + for (i = 0; i < c->cnt; i++) + if (!strcmp(s, c->names[i]->name)) + return 1; + return 0; +} diff --git a/tools/lib/subcmd/help.h b/tools/lib/subcmd/help.h new file mode 100644 index 000000000..355c066c8 --- /dev/null +++ b/tools/lib/subcmd/help.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SUBCMD_HELP_H +#define __SUBCMD_HELP_H + +#include <sys/types.h> +#include <stdio.h> + +struct cmdnames { + size_t alloc; + size_t cnt; + struct cmdname { + size_t len; /* also used for similarity index in help.c */ + char name[]; + } **names; +}; + +static inline void mput_char(char c, unsigned int num) +{ + while(num--) + putchar(c); +} + +void load_command_list(const char *prefix, + struct cmdnames *main_cmds, + struct cmdnames *other_cmds); +void add_cmdname(struct cmdnames *cmds, const char *name, size_t len); +void clean_cmdnames(struct cmdnames *cmds); +int cmdname_compare(const void *a, const void *b); +void uniq(struct cmdnames *cmds); +/* Here we require that excludes is a sorted list. */ +void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes); +int is_in_cmdlist(struct cmdnames *c, const char *s); +void list_commands(const char *title, struct cmdnames *main_cmds, + struct cmdnames *other_cmds); + +#endif /* __SUBCMD_HELP_H */ diff --git a/tools/lib/subcmd/pager.c b/tools/lib/subcmd/pager.c new file mode 100644 index 000000000..e3d47b59b --- /dev/null +++ b/tools/lib/subcmd/pager.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <sys/select.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <signal.h> +#include <sys/ioctl.h> +#include "pager.h" +#include "run-command.h" +#include "sigchain.h" +#include "subcmd-config.h" + +/* + * This is split up from the rest of git so that we can do + * something different on Windows. + */ + +static int spawned_pager; +static int pager_columns; + +void pager_init(const char *pager_env) +{ + subcmd_config.pager_env = pager_env; +} + +static const char *forced_pager; + +void force_pager(const char *pager) +{ + forced_pager = pager; +} + +static void pager_preexec(void) +{ + /* + * Work around bug in "less" by not starting it until we + * have real input + */ + fd_set in; + fd_set exception; + + FD_ZERO(&in); + FD_ZERO(&exception); + FD_SET(0, &in); + FD_SET(0, &exception); + select(1, &in, NULL, &exception, NULL); + + setenv("LESS", "FRSX", 0); +} + +static const char *pager_argv[] = { "sh", "-c", NULL, NULL }; +static struct child_process pager_process; + +static void wait_for_pager(void) +{ + fflush(stdout); + fflush(stderr); + /* signal EOF to pager */ + close(1); + close(2); + finish_command(&pager_process); +} + +static void wait_for_pager_signal(int signo) +{ + wait_for_pager(); + sigchain_pop(signo); + raise(signo); +} + +void setup_pager(void) +{ + const char *pager = getenv(subcmd_config.pager_env); + struct winsize sz; + + if (forced_pager) + pager = forced_pager; + if (!isatty(1) && !forced_pager) + return; + if (ioctl(1, TIOCGWINSZ, &sz) == 0) + pager_columns = sz.ws_col; + if (!pager) + pager = getenv("PAGER"); + if (!(pager || access("/usr/bin/pager", X_OK))) + pager = "/usr/bin/pager"; + if (!(pager || access("/usr/bin/less", X_OK))) + pager = "/usr/bin/less"; + if (!pager) + pager = "cat"; + if (!*pager || !strcmp(pager, "cat")) + return; + + spawned_pager = 1; /* means we are emitting to terminal */ + + /* spawn the pager */ + pager_argv[2] = pager; + pager_process.argv = pager_argv; + pager_process.in = -1; + pager_process.preexec_cb = pager_preexec; + + if (start_command(&pager_process)) + return; + + /* original process continues, but writes to the pipe */ + dup2(pager_process.in, 1); + if (isatty(2)) + dup2(pager_process.in, 2); + close(pager_process.in); + + /* this makes sure that the parent terminates after the pager */ + sigchain_push_common(wait_for_pager_signal); + atexit(wait_for_pager); +} + +int pager_in_use(void) +{ + return spawned_pager; +} + +int pager_get_columns(void) +{ + char *s; + + s = getenv("COLUMNS"); + if (s) + return atoi(s); + + return (pager_columns ? pager_columns : 80) - 2; +} diff --git a/tools/lib/subcmd/pager.h b/tools/lib/subcmd/pager.h new file mode 100644 index 000000000..a81896469 --- /dev/null +++ b/tools/lib/subcmd/pager.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SUBCMD_PAGER_H +#define __SUBCMD_PAGER_H + +extern void pager_init(const char *pager_env); + +extern void setup_pager(void); +extern int pager_in_use(void); +extern int pager_get_columns(void); +extern void force_pager(const char *); + +#endif /* __SUBCMD_PAGER_H */ diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c new file mode 100644 index 000000000..9fa75943f --- /dev/null +++ b/tools/lib/subcmd/parse-options.c @@ -0,0 +1,1039 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <linux/string.h> +#include <linux/types.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <ctype.h> +#include "subcmd-util.h" +#include "parse-options.h" +#include "subcmd-config.h" +#include "pager.h" + +#define OPT_SHORT 1 +#define OPT_UNSET 2 + +char *error_buf; + +static int opterror(const struct option *opt, const char *reason, int flags) +{ + if (flags & OPT_SHORT) + fprintf(stderr, " Error: switch `%c' %s", opt->short_name, reason); + else if (flags & OPT_UNSET) + fprintf(stderr, " Error: option `no-%s' %s", opt->long_name, reason); + else + fprintf(stderr, " Error: option `%s' %s", opt->long_name, reason); + + return -1; +} + +static const char *skip_prefix(const char *str, const char *prefix) +{ + size_t len = strlen(prefix); + return strncmp(str, prefix, len) ? NULL : str + len; +} + +static void optwarning(const struct option *opt, const char *reason, int flags) +{ + if (flags & OPT_SHORT) + fprintf(stderr, " Warning: switch `%c' %s", opt->short_name, reason); + else if (flags & OPT_UNSET) + fprintf(stderr, " Warning: option `no-%s' %s", opt->long_name, reason); + else + fprintf(stderr, " Warning: option `%s' %s", opt->long_name, reason); +} + +static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt, + int flags, const char **arg) +{ + const char *res; + + if (p->opt) { + res = p->opt; + p->opt = NULL; + } else if ((opt->flags & PARSE_OPT_LASTARG_DEFAULT) && (p->argc == 1 || + **(p->argv + 1) == '-')) { + res = (const char *)opt->defval; + } else if (p->argc > 1) { + p->argc--; + res = *++p->argv; + } else + return opterror(opt, "requires a value", flags); + if (arg) + *arg = res; + return 0; +} + +static int get_value(struct parse_opt_ctx_t *p, + const struct option *opt, int flags) +{ + const char *s, *arg = NULL; + const int unset = flags & OPT_UNSET; + int err; + + if (unset && p->opt) + return opterror(opt, "takes no value", flags); + if (unset && (opt->flags & PARSE_OPT_NONEG)) + return opterror(opt, "isn't available", flags); + if (opt->flags & PARSE_OPT_DISABLED) + return opterror(opt, "is not usable", flags); + + if (opt->flags & PARSE_OPT_EXCLUSIVE) { + if (p->excl_opt && p->excl_opt != opt) { + char msg[128]; + + if (((flags & OPT_SHORT) && p->excl_opt->short_name) || + p->excl_opt->long_name == NULL) { + snprintf(msg, sizeof(msg), "cannot be used with switch `%c'", + p->excl_opt->short_name); + } else { + snprintf(msg, sizeof(msg), "cannot be used with %s", + p->excl_opt->long_name); + } + opterror(opt, msg, flags); + return -3; + } + p->excl_opt = opt; + } + if (!(flags & OPT_SHORT) && p->opt) { + switch (opt->type) { + case OPTION_CALLBACK: + if (!(opt->flags & PARSE_OPT_NOARG)) + break; + /* FALLTHROUGH */ + case OPTION_BOOLEAN: + case OPTION_INCR: + case OPTION_BIT: + case OPTION_SET_UINT: + case OPTION_SET_PTR: + return opterror(opt, "takes no value", flags); + case OPTION_END: + case OPTION_ARGUMENT: + case OPTION_GROUP: + case OPTION_STRING: + case OPTION_INTEGER: + case OPTION_UINTEGER: + case OPTION_LONG: + case OPTION_ULONG: + case OPTION_U64: + default: + break; + } + } + + if (opt->flags & PARSE_OPT_NOBUILD) { + char reason[128]; + bool noarg = false; + + err = snprintf(reason, sizeof(reason), + opt->flags & PARSE_OPT_CANSKIP ? + "is being ignored because %s " : + "is not available because %s", + opt->build_opt); + reason[sizeof(reason) - 1] = '\0'; + + if (err < 0) + strncpy(reason, opt->flags & PARSE_OPT_CANSKIP ? + "is being ignored" : + "is not available", + sizeof(reason)); + + if (!(opt->flags & PARSE_OPT_CANSKIP)) + return opterror(opt, reason, flags); + + err = 0; + if (unset) + noarg = true; + if (opt->flags & PARSE_OPT_NOARG) + noarg = true; + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) + noarg = true; + + switch (opt->type) { + case OPTION_BOOLEAN: + case OPTION_INCR: + case OPTION_BIT: + case OPTION_SET_UINT: + case OPTION_SET_PTR: + case OPTION_END: + case OPTION_ARGUMENT: + case OPTION_GROUP: + noarg = true; + break; + case OPTION_CALLBACK: + case OPTION_STRING: + case OPTION_INTEGER: + case OPTION_UINTEGER: + case OPTION_LONG: + case OPTION_ULONG: + case OPTION_U64: + default: + break; + } + + if (!noarg) + err = get_arg(p, opt, flags, NULL); + if (err) + return err; + + optwarning(opt, reason, flags); + return 0; + } + + switch (opt->type) { + case OPTION_BIT: + if (unset) + *(int *)opt->value &= ~opt->defval; + else + *(int *)opt->value |= opt->defval; + return 0; + + case OPTION_BOOLEAN: + *(bool *)opt->value = unset ? false : true; + if (opt->set) + *(bool *)opt->set = true; + return 0; + + case OPTION_INCR: + *(int *)opt->value = unset ? 0 : *(int *)opt->value + 1; + return 0; + + case OPTION_SET_UINT: + *(unsigned int *)opt->value = unset ? 0 : opt->defval; + return 0; + + case OPTION_SET_PTR: + *(void **)opt->value = unset ? NULL : (void *)opt->defval; + return 0; + + case OPTION_STRING: + err = 0; + if (unset) + *(const char **)opt->value = NULL; + else if (opt->flags & PARSE_OPT_OPTARG && !p->opt) + *(const char **)opt->value = (const char *)opt->defval; + else + err = get_arg(p, opt, flags, (const char **)opt->value); + + if (opt->set) + *(bool *)opt->set = true; + + /* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */ + if (opt->flags & PARSE_OPT_NOEMPTY) { + const char *val = *(const char **)opt->value; + + if (!val) + return err; + + /* Similar to unset if we are given an empty string. */ + if (val[0] == '\0') { + *(const char **)opt->value = NULL; + return 0; + } + } + + return err; + + case OPTION_CALLBACK: + if (opt->set) + *(bool *)opt->set = true; + + if (unset) + return (*opt->callback)(opt, NULL, 1) ? (-1) : 0; + if (opt->flags & PARSE_OPT_NOARG) + return (*opt->callback)(opt, NULL, 0) ? (-1) : 0; + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) + return (*opt->callback)(opt, NULL, 0) ? (-1) : 0; + if (get_arg(p, opt, flags, &arg)) + return -1; + return (*opt->callback)(opt, arg, 0) ? (-1) : 0; + + case OPTION_INTEGER: + if (unset) { + *(int *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(int *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + *(int *)opt->value = strtol(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + case OPTION_UINTEGER: + if (unset) { + *(unsigned int *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(unsigned int *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + if (arg[0] == '-') + return opterror(opt, "expects an unsigned numerical value", flags); + *(unsigned int *)opt->value = strtol(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + case OPTION_LONG: + if (unset) { + *(long *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(long *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + *(long *)opt->value = strtol(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + case OPTION_ULONG: + if (unset) { + *(unsigned long *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(unsigned long *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + *(unsigned long *)opt->value = strtoul(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + case OPTION_U64: + if (unset) { + *(u64 *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(u64 *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + if (arg[0] == '-') + return opterror(opt, "expects an unsigned numerical value", flags); + *(u64 *)opt->value = strtoull(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + case OPTION_END: + case OPTION_ARGUMENT: + case OPTION_GROUP: + default: + die("should not happen, someone must be hit on the forehead"); + } +} + +static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *options) +{ +retry: + for (; options->type != OPTION_END; options++) { + if (options->short_name == *p->opt) { + p->opt = p->opt[1] ? p->opt + 1 : NULL; + return get_value(p, options, OPT_SHORT); + } + } + + if (options->parent) { + options = options->parent; + goto retry; + } + + return -2; +} + +static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg, + const struct option *options) +{ + const char *arg_end = strchr(arg, '='); + const struct option *abbrev_option = NULL, *ambiguous_option = NULL; + int abbrev_flags = 0, ambiguous_flags = 0; + + if (!arg_end) + arg_end = arg + strlen(arg); + +retry: + for (; options->type != OPTION_END; options++) { + const char *rest; + int flags = 0; + + if (!options->long_name) + continue; + + rest = skip_prefix(arg, options->long_name); + if (options->type == OPTION_ARGUMENT) { + if (!rest) + continue; + if (*rest == '=') + return opterror(options, "takes no value", flags); + if (*rest) + continue; + p->out[p->cpidx++] = arg - 2; + return 0; + } + if (!rest) { + if (strstarts(options->long_name, "no-")) { + /* + * The long name itself starts with "no-", so + * accept the option without "no-" so that users + * do not have to enter "no-no-" to get the + * negation. + */ + rest = skip_prefix(arg, options->long_name + 3); + if (rest) { + flags |= OPT_UNSET; + goto match; + } + /* Abbreviated case */ + if (strstarts(options->long_name + 3, arg)) { + flags |= OPT_UNSET; + goto is_abbreviated; + } + } + /* abbreviated? */ + if (!strncmp(options->long_name, arg, arg_end - arg)) { +is_abbreviated: + if (abbrev_option) { + /* + * If this is abbreviated, it is + * ambiguous. So when there is no + * exact match later, we need to + * error out. + */ + ambiguous_option = abbrev_option; + ambiguous_flags = abbrev_flags; + } + if (!(flags & OPT_UNSET) && *arg_end) + p->opt = arg_end + 1; + abbrev_option = options; + abbrev_flags = flags; + continue; + } + /* negated and abbreviated very much? */ + if (strstarts("no-", arg)) { + flags |= OPT_UNSET; + goto is_abbreviated; + } + /* negated? */ + if (strncmp(arg, "no-", 3)) + continue; + flags |= OPT_UNSET; + rest = skip_prefix(arg + 3, options->long_name); + /* abbreviated and negated? */ + if (!rest && strstarts(options->long_name, arg + 3)) + goto is_abbreviated; + if (!rest) + continue; + } +match: + if (*rest) { + if (*rest != '=') + continue; + p->opt = rest + 1; + } + return get_value(p, options, flags); + } + + if (ambiguous_option) { + fprintf(stderr, + " Error: Ambiguous option: %s (could be --%s%s or --%s%s)\n", + arg, + (ambiguous_flags & OPT_UNSET) ? "no-" : "", + ambiguous_option->long_name, + (abbrev_flags & OPT_UNSET) ? "no-" : "", + abbrev_option->long_name); + return -1; + } + if (abbrev_option) + return get_value(p, abbrev_option, abbrev_flags); + + if (options->parent) { + options = options->parent; + goto retry; + } + + return -2; +} + +static void check_typos(const char *arg, const struct option *options) +{ + if (strlen(arg) < 3) + return; + + if (strstarts(arg, "no-")) { + fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg); + exit(129); + } + + for (; options->type != OPTION_END; options++) { + if (!options->long_name) + continue; + if (strstarts(options->long_name, arg)) { + fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg); + exit(129); + } + } +} + +static void parse_options_start(struct parse_opt_ctx_t *ctx, + int argc, const char **argv, int flags) +{ + memset(ctx, 0, sizeof(*ctx)); + ctx->argc = argc - 1; + ctx->argv = argv + 1; + ctx->out = argv; + ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0); + ctx->flags = flags; + if ((flags & PARSE_OPT_KEEP_UNKNOWN) && + (flags & PARSE_OPT_STOP_AT_NON_OPTION)) + die("STOP_AT_NON_OPTION and KEEP_UNKNOWN don't go together"); +} + +static int usage_with_options_internal(const char * const *, + const struct option *, int, + struct parse_opt_ctx_t *); + +static int parse_options_step(struct parse_opt_ctx_t *ctx, + const struct option *options, + const char * const usagestr[]) +{ + int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP); + int excl_short_opt = 1; + const char *arg; + + /* we must reset ->opt, unknown short option leave it dangling */ + ctx->opt = NULL; + + for (; ctx->argc; ctx->argc--, ctx->argv++) { + arg = ctx->argv[0]; + if (*arg != '-' || !arg[1]) { + if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION) + break; + ctx->out[ctx->cpidx++] = ctx->argv[0]; + continue; + } + + if (arg[1] != '-') { + ctx->opt = ++arg; + if (internal_help && *ctx->opt == 'h') { + return usage_with_options_internal(usagestr, options, 0, ctx); + } + switch (parse_short_opt(ctx, options)) { + case -1: + return parse_options_usage(usagestr, options, arg, 1); + case -2: + goto unknown; + case -3: + goto exclusive; + default: + break; + } + if (ctx->opt) + check_typos(arg, options); + while (ctx->opt) { + if (internal_help && *ctx->opt == 'h') + return usage_with_options_internal(usagestr, options, 0, ctx); + arg = ctx->opt; + switch (parse_short_opt(ctx, options)) { + case -1: + return parse_options_usage(usagestr, options, arg, 1); + case -2: + /* fake a short option thing to hide the fact that we may have + * started to parse aggregated stuff + * + * This is leaky, too bad. + */ + ctx->argv[0] = strdup(ctx->opt - 1); + *(char *)ctx->argv[0] = '-'; + goto unknown; + case -3: + goto exclusive; + default: + break; + } + } + continue; + } + + if (!arg[2]) { /* "--" */ + if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) { + ctx->argc--; + ctx->argv++; + } + break; + } + + arg += 2; + if (internal_help && !strcmp(arg, "help-all")) + return usage_with_options_internal(usagestr, options, 1, ctx); + if (internal_help && !strcmp(arg, "help")) + return usage_with_options_internal(usagestr, options, 0, ctx); + if (!strcmp(arg, "list-opts")) + return PARSE_OPT_LIST_OPTS; + if (!strcmp(arg, "list-cmds")) + return PARSE_OPT_LIST_SUBCMDS; + switch (parse_long_opt(ctx, arg, options)) { + case -1: + return parse_options_usage(usagestr, options, arg, 0); + case -2: + goto unknown; + case -3: + excl_short_opt = 0; + goto exclusive; + default: + break; + } + continue; +unknown: + if (!(ctx->flags & PARSE_OPT_KEEP_UNKNOWN)) + return PARSE_OPT_UNKNOWN; + ctx->out[ctx->cpidx++] = ctx->argv[0]; + ctx->opt = NULL; + } + return PARSE_OPT_DONE; + +exclusive: + parse_options_usage(usagestr, options, arg, excl_short_opt); + if ((excl_short_opt && ctx->excl_opt->short_name) || + ctx->excl_opt->long_name == NULL) { + char opt = ctx->excl_opt->short_name; + parse_options_usage(NULL, options, &opt, 1); + } else { + parse_options_usage(NULL, options, ctx->excl_opt->long_name, 0); + } + return PARSE_OPT_HELP; +} + +static int parse_options_end(struct parse_opt_ctx_t *ctx) +{ + memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out)); + ctx->out[ctx->cpidx + ctx->argc] = NULL; + return ctx->cpidx + ctx->argc; +} + +int parse_options_subcommand(int argc, const char **argv, const struct option *options, + const char *const subcommands[], const char *usagestr[], int flags) +{ + struct parse_opt_ctx_t ctx; + + /* build usage string if it's not provided */ + if (subcommands && !usagestr[0]) { + char *buf = NULL; + + astrcatf(&buf, "%s %s [<options>] {", subcmd_config.exec_name, argv[0]); + + for (int i = 0; subcommands[i]; i++) { + if (i) + astrcat(&buf, "|"); + astrcat(&buf, subcommands[i]); + } + astrcat(&buf, "}"); + + usagestr[0] = buf; + } + + parse_options_start(&ctx, argc, argv, flags); + switch (parse_options_step(&ctx, options, usagestr)) { + case PARSE_OPT_HELP: + exit(129); + case PARSE_OPT_DONE: + break; + case PARSE_OPT_LIST_OPTS: + while (options->type != OPTION_END) { + if (options->long_name) + printf("--%s ", options->long_name); + options++; + } + putchar('\n'); + exit(130); + case PARSE_OPT_LIST_SUBCMDS: + if (subcommands) { + for (int i = 0; subcommands[i]; i++) + printf("%s ", subcommands[i]); + } + putchar('\n'); + exit(130); + default: /* PARSE_OPT_UNKNOWN */ + if (ctx.argv[0][1] == '-') + astrcatf(&error_buf, "unknown option `%s'", + ctx.argv[0] + 2); + else + astrcatf(&error_buf, "unknown switch `%c'", *ctx.opt); + usage_with_options(usagestr, options); + } + + return parse_options_end(&ctx); +} + +int parse_options(int argc, const char **argv, const struct option *options, + const char * const usagestr[], int flags) +{ + return parse_options_subcommand(argc, argv, options, NULL, + (const char **) usagestr, flags); +} + +#define USAGE_OPTS_WIDTH 24 +#define USAGE_GAP 2 + +static void print_option_help(const struct option *opts, int full) +{ + size_t pos; + int pad; + + if (opts->type == OPTION_GROUP) { + fputc('\n', stderr); + if (*opts->help) + fprintf(stderr, "%s\n", opts->help); + return; + } + if (!full && (opts->flags & PARSE_OPT_HIDDEN)) + return; + if (opts->flags & PARSE_OPT_DISABLED) + return; + + pos = fprintf(stderr, " "); + if (opts->short_name) + pos += fprintf(stderr, "-%c", opts->short_name); + else + pos += fprintf(stderr, " "); + + if (opts->long_name && opts->short_name) + pos += fprintf(stderr, ", "); + if (opts->long_name) + pos += fprintf(stderr, "--%s", opts->long_name); + + switch (opts->type) { + case OPTION_ARGUMENT: + break; + case OPTION_LONG: + case OPTION_ULONG: + case OPTION_U64: + case OPTION_INTEGER: + case OPTION_UINTEGER: + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=<n>]"); + else + pos += fprintf(stderr, "[<n>]"); + else + pos += fprintf(stderr, " <n>"); + break; + case OPTION_CALLBACK: + if (opts->flags & PARSE_OPT_NOARG) + break; + /* FALLTHROUGH */ + case OPTION_STRING: + if (opts->argh) { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=<%s>]", opts->argh); + else + pos += fprintf(stderr, "[<%s>]", opts->argh); + else + pos += fprintf(stderr, " <%s>", opts->argh); + } else { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=...]"); + else + pos += fprintf(stderr, "[...]"); + else + pos += fprintf(stderr, " ..."); + } + break; + default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */ + case OPTION_END: + case OPTION_GROUP: + case OPTION_BIT: + case OPTION_BOOLEAN: + case OPTION_INCR: + case OPTION_SET_UINT: + case OPTION_SET_PTR: + break; + } + + if (pos <= USAGE_OPTS_WIDTH) + pad = USAGE_OPTS_WIDTH - pos; + else { + fputc('\n', stderr); + pad = USAGE_OPTS_WIDTH; + } + fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help); + if (opts->flags & PARSE_OPT_NOBUILD) + fprintf(stderr, "%*s(not built-in because %s)\n", + USAGE_OPTS_WIDTH + USAGE_GAP, "", + opts->build_opt); +} + +static int option__cmp(const void *va, const void *vb) +{ + const struct option *a = va, *b = vb; + int sa = tolower(a->short_name), sb = tolower(b->short_name), ret; + + if (sa == 0) + sa = 'z' + 1; + if (sb == 0) + sb = 'z' + 1; + + ret = sa - sb; + + if (ret == 0) { + const char *la = a->long_name ?: "", + *lb = b->long_name ?: ""; + ret = strcmp(la, lb); + } + + return ret; +} + +static struct option *options__order(const struct option *opts) +{ + int nr_opts = 0, nr_group = 0, len; + const struct option *o = opts; + struct option *opt, *ordered, *group; + + for (o = opts; o->type != OPTION_END; o++) + ++nr_opts; + + len = sizeof(*o) * (nr_opts + 1); + ordered = malloc(len); + if (!ordered) + goto out; + memcpy(ordered, opts, len); + + /* sort each option group individually */ + for (opt = group = ordered; opt->type != OPTION_END; opt++) { + if (opt->type == OPTION_GROUP) { + qsort(group, nr_group, sizeof(*opt), option__cmp); + group = opt + 1; + nr_group = 0; + continue; + } + nr_group++; + } + qsort(group, nr_group, sizeof(*opt), option__cmp); + +out: + return ordered; +} + +static bool option__in_argv(const struct option *opt, const struct parse_opt_ctx_t *ctx) +{ + int i; + + for (i = 1; i < ctx->argc; ++i) { + const char *arg = ctx->argv[i]; + + if (arg[0] != '-') { + if (arg[1] == '\0') { + if (arg[0] == opt->short_name) + return true; + continue; + } + + if (opt->long_name && strcmp(opt->long_name, arg) == 0) + return true; + + if (opt->help && strcasestr(opt->help, arg) != NULL) + return true; + + continue; + } + + if (arg[1] == opt->short_name || + (arg[1] == '-' && opt->long_name && strcmp(opt->long_name, arg + 2) == 0)) + return true; + } + + return false; +} + +static int usage_with_options_internal(const char * const *usagestr, + const struct option *opts, int full, + struct parse_opt_ctx_t *ctx) +{ + struct option *ordered; + + if (!usagestr) + return PARSE_OPT_HELP; + + setup_pager(); + + if (error_buf) { + fprintf(stderr, " Error: %s\n", error_buf); + zfree(&error_buf); + } + + fprintf(stderr, "\n Usage: %s\n", *usagestr++); + while (*usagestr && **usagestr) + fprintf(stderr, " or: %s\n", *usagestr++); + while (*usagestr) { + fprintf(stderr, "%s%s\n", + **usagestr ? " " : "", + *usagestr); + usagestr++; + } + + if (opts->type != OPTION_GROUP) + fputc('\n', stderr); + + ordered = options__order(opts); + if (ordered) + opts = ordered; + + for ( ; opts->type != OPTION_END; opts++) { + if (ctx && ctx->argc > 1 && !option__in_argv(opts, ctx)) + continue; + print_option_help(opts, full); + } + + fputc('\n', stderr); + + free(ordered); + + return PARSE_OPT_HELP; +} + +void usage_with_options(const char * const *usagestr, + const struct option *opts) +{ + usage_with_options_internal(usagestr, opts, 0, NULL); + exit(129); +} + +void usage_with_options_msg(const char * const *usagestr, + const struct option *opts, const char *fmt, ...) +{ + va_list ap; + char *tmp = error_buf; + + va_start(ap, fmt); + if (vasprintf(&error_buf, fmt, ap) == -1) + die("vasprintf failed"); + va_end(ap); + + free(tmp); + + usage_with_options_internal(usagestr, opts, 0, NULL); + exit(129); +} + +int parse_options_usage(const char * const *usagestr, + const struct option *opts, + const char *optstr, bool short_opt) +{ + if (!usagestr) + goto opt; + + fprintf(stderr, "\n Usage: %s\n", *usagestr++); + while (*usagestr && **usagestr) + fprintf(stderr, " or: %s\n", *usagestr++); + while (*usagestr) { + fprintf(stderr, "%s%s\n", + **usagestr ? " " : "", + *usagestr); + usagestr++; + } + fputc('\n', stderr); + +opt: + for ( ; opts->type != OPTION_END; opts++) { + if (short_opt) { + if (opts->short_name == *optstr) { + print_option_help(opts, 0); + break; + } + continue; + } + + if (opts->long_name == NULL) + continue; + + if (strstarts(opts->long_name, optstr)) + print_option_help(opts, 0); + if (strstarts("no-", optstr) && + strstarts(opts->long_name, optstr + 3)) + print_option_help(opts, 0); + } + + return PARSE_OPT_HELP; +} + + +int parse_opt_verbosity_cb(const struct option *opt, + const char *arg __maybe_unused, + int unset) +{ + int *target = opt->value; + + if (unset) + /* --no-quiet, --no-verbose */ + *target = 0; + else if (opt->short_name == 'v') { + if (*target >= 0) + (*target)++; + else + *target = 1; + } else { + if (*target <= 0) + (*target)--; + else + *target = -1; + } + return 0; +} + +static struct option * +find_option(struct option *opts, int shortopt, const char *longopt) +{ + for (; opts->type != OPTION_END; opts++) { + if ((shortopt && opts->short_name == shortopt) || + (opts->long_name && longopt && + !strcmp(opts->long_name, longopt))) + return opts; + } + return NULL; +} + +void set_option_flag(struct option *opts, int shortopt, const char *longopt, + int flag) +{ + struct option *opt = find_option(opts, shortopt, longopt); + + if (opt) + opt->flags |= flag; + return; +} + +void set_option_nobuild(struct option *opts, int shortopt, + const char *longopt, + const char *build_opt, + bool can_skip) +{ + struct option *opt = find_option(opts, shortopt, longopt); + + if (!opt) + return; + + opt->flags |= PARSE_OPT_NOBUILD; + opt->flags |= can_skip ? PARSE_OPT_CANSKIP : 0; + opt->build_opt = build_opt; +} diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h new file mode 100644 index 000000000..41b9b9425 --- /dev/null +++ b/tools/lib/subcmd/parse-options.h @@ -0,0 +1,247 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SUBCMD_PARSE_OPTIONS_H +#define __SUBCMD_PARSE_OPTIONS_H + +#include <linux/kernel.h> +#include <stdbool.h> +#include <stdint.h> + +#ifndef NORETURN +#define NORETURN __attribute__((__noreturn__)) +#endif + +enum parse_opt_type { + /* special types */ + OPTION_END, + OPTION_ARGUMENT, + OPTION_GROUP, + /* options with no arguments */ + OPTION_BIT, + OPTION_BOOLEAN, + OPTION_INCR, + OPTION_SET_UINT, + OPTION_SET_PTR, + /* options with arguments (usually) */ + OPTION_STRING, + OPTION_INTEGER, + OPTION_LONG, + OPTION_ULONG, + OPTION_CALLBACK, + OPTION_U64, + OPTION_UINTEGER, +}; + +enum parse_opt_flags { + PARSE_OPT_KEEP_DASHDASH = 1, + PARSE_OPT_STOP_AT_NON_OPTION = 2, + PARSE_OPT_KEEP_ARGV0 = 4, + PARSE_OPT_KEEP_UNKNOWN = 8, + PARSE_OPT_NO_INTERNAL_HELP = 16, +}; + +enum parse_opt_option_flags { + PARSE_OPT_OPTARG = 1, + PARSE_OPT_NOARG = 2, + PARSE_OPT_NONEG = 4, + PARSE_OPT_HIDDEN = 8, + PARSE_OPT_LASTARG_DEFAULT = 16, + PARSE_OPT_DISABLED = 32, + PARSE_OPT_EXCLUSIVE = 64, + PARSE_OPT_NOEMPTY = 128, + PARSE_OPT_NOBUILD = 256, + PARSE_OPT_CANSKIP = 512, +}; + +struct option; +typedef int parse_opt_cb(const struct option *, const char *arg, int unset); + +/* + * `type`:: + * holds the type of the option, you must have an OPTION_END last in your + * array. + * + * `short_name`:: + * the character to use as a short option name, '\0' if none. + * + * `long_name`:: + * the long option name, without the leading dashes, NULL if none. + * + * `value`:: + * stores pointers to the values to be filled. + * + * `argh`:: + * token to explain the kind of argument this option wants. Keep it + * homogeneous across the repository. + * + * `help`:: + * the short help associated to what the option does. + * Must never be NULL (except for OPTION_END). + * OPTION_GROUP uses this pointer to store the group header. + * + * `flags`:: + * mask of parse_opt_option_flags. + * PARSE_OPT_OPTARG: says that the argument is optional (not for BOOLEANs) + * PARSE_OPT_NOARG: says that this option takes no argument, for CALLBACKs + * PARSE_OPT_NONEG: says that this option cannot be negated + * PARSE_OPT_HIDDEN this option is skipped in the default usage, showed in + * the long one. + * + * `callback`:: + * pointer to the callback to use for OPTION_CALLBACK. + * + * `defval`:: + * default value to fill (*->value) with for PARSE_OPT_OPTARG. + * OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in + * the value when met. + * CALLBACKS can use it like they want. + * + * `set`:: + * whether an option was set by the user + */ +struct option { + enum parse_opt_type type; + int short_name; + const char *long_name; + void *value; + const char *argh; + const char *help; + const char *build_opt; + + int flags; + parse_opt_cb *callback; + intptr_t defval; + bool *set; + void *data; + const struct option *parent; +}; + +#define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v ) + +#define OPT_END() { .type = OPTION_END } +#define OPT_PARENT(p) { .type = OPTION_END, .parent = (p) } +#define OPT_ARGUMENT(l, h) { .type = OPTION_ARGUMENT, .long_name = (l), .help = (h) } +#define OPT_GROUP(h) { .type = OPTION_GROUP, .help = (h) } +#define OPT_BIT(s, l, v, h, b) { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) } +#define OPT_BOOLEAN(s, l, v, h) { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) } +#define OPT_BOOLEAN_FLAG(s, l, v, h, f) { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h), .flags = (f) } +#define OPT_BOOLEAN_SET(s, l, v, os, h) \ + { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \ + .value = check_vtype(v, bool *), .help = (h), \ + .set = check_vtype(os, bool *)} +#define OPT_INCR(s, l, v, h) { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) } +#define OPT_SET_UINT(s, l, v, h, i) { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) } +#define OPT_SET_PTR(s, l, v, h, p) { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) } +#define OPT_INTEGER(s, l, v, h) { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) } +#define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) } +#define OPT_UINTEGER_OPTARG(s, l, v, d, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) } +#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) } +#define OPT_ULONG(s, l, v, h) { .type = OPTION_ULONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned long *), .help = (h) } +#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) } +#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) } +#define OPT_STRING_OPTARG(s, l, v, a, h, d) \ + { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ + .value = check_vtype(v, const char **), .argh =(a), .help = (h), \ + .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) } +#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \ + { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ + .value = check_vtype(v, const char **), .argh = (a), .help = (h), \ + .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \ + .set = check_vtype(os, bool *)} +#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} +#define OPT_DATE(s, l, v, h) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } +#define OPT_CALLBACK(s, l, v, a, h, f) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) } +#define OPT_CALLBACK_SET(s, l, v, os, a, h, f) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .set = check_vtype(os, bool *)} +#define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG } +#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT } +#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\ + .value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ + .flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG} +#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \ + .value = (v), .argh = (a), .help = (h), .callback = (f), \ + .flags = PARSE_OPT_OPTARG, .data = (d) } + +/* parse_options() will filter out the processed options and leave the + * non-option argments in argv[]. + * Returns the number of arguments left in argv[]. + * + * NOTE: parse_options() and parse_options_subcommand() may call exit() in the + * case of an error (or for 'special' options like --list-cmds or --list-opts). + */ +extern int parse_options(int argc, const char **argv, + const struct option *options, + const char * const usagestr[], int flags); + +extern int parse_options_subcommand(int argc, const char **argv, + const struct option *options, + const char *const subcommands[], + const char *usagestr[], int flags); + +extern NORETURN void usage_with_options(const char * const *usagestr, + const struct option *options); +extern NORETURN __attribute__((format(printf,3,4))) +void usage_with_options_msg(const char * const *usagestr, + const struct option *options, + const char *fmt, ...); + +/*----- incremantal advanced APIs -----*/ + +enum { + PARSE_OPT_HELP = -1, + PARSE_OPT_DONE, + PARSE_OPT_LIST_OPTS, + PARSE_OPT_LIST_SUBCMDS, + PARSE_OPT_UNKNOWN, +}; + +/* + * It's okay for the caller to consume argv/argc in the usual way. + * Other fields of that structure are private to parse-options and should not + * be modified in any way. + */ +struct parse_opt_ctx_t { + const char **argv; + const char **out; + int argc, cpidx; + const char *opt; + const struct option *excl_opt; + int flags; +}; + +extern int parse_options_usage(const char * const *usagestr, + const struct option *opts, + const char *optstr, + bool short_opt); + + +/*----- some often used options -----*/ +extern int parse_opt_abbrev_cb(const struct option *, const char *, int); +extern int parse_opt_approxidate_cb(const struct option *, const char *, int); +extern int parse_opt_verbosity_cb(const struct option *, const char *, int); + +#define OPT__VERBOSE(var) OPT_BOOLEAN('v', "verbose", (var), "be verbose") +#define OPT__QUIET(var) OPT_BOOLEAN('q', "quiet", (var), "be quiet") +#define OPT__VERBOSITY(var) \ + { OPTION_CALLBACK, 'v', "verbose", (var), NULL, "be more verbose", \ + PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 }, \ + { OPTION_CALLBACK, 'q', "quiet", (var), NULL, "be more quiet", \ + PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 } +#define OPT__DRY_RUN(var) OPT_BOOLEAN('n', "dry-run", (var), "dry run") +#define OPT__ABBREV(var) \ + { OPTION_CALLBACK, 0, "abbrev", (var), "n", \ + "use <n> digits to display SHA-1s", \ + PARSE_OPT_OPTARG, &parse_opt_abbrev_cb, 0 } + +extern const char *parse_options_fix_filename(const char *prefix, const char *file); + +void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag); +void set_option_nobuild(struct option *opts, int shortopt, const char *longopt, + const char *build_opt, bool can_skip); + +#endif /* __SUBCMD_PARSE_OPTIONS_H */ diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c new file mode 100644 index 000000000..5cdac2162 --- /dev/null +++ b/tools/lib/subcmd/run-command.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <string.h> +#include <linux/string.h> +#include <errno.h> +#include <sys/wait.h> +#include "subcmd-util.h" +#include "run-command.h" +#include "exec-cmd.h" + +#define STRERR_BUFSIZE 128 + +static inline void close_pair(int fd[2]) +{ + close(fd[0]); + close(fd[1]); +} + +static inline void dup_devnull(int to) +{ + int fd = open("/dev/null", O_RDWR); + dup2(fd, to); + close(fd); +} + +int start_command(struct child_process *cmd) +{ + int need_in, need_out, need_err; + int fdin[2], fdout[2], fderr[2]; + char sbuf[STRERR_BUFSIZE]; + + /* + * In case of errors we must keep the promise to close FDs + * that have been passed in via ->in and ->out. + */ + + need_in = !cmd->no_stdin && cmd->in < 0; + if (need_in) { + if (pipe(fdin) < 0) { + if (cmd->out > 0) + close(cmd->out); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->in = fdin[1]; + } + + need_out = !cmd->no_stdout + && !cmd->stdout_to_stderr + && cmd->out < 0; + if (need_out) { + if (pipe(fdout) < 0) { + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->out = fdout[0]; + } + + need_err = !cmd->no_stderr && cmd->err < 0; + if (need_err) { + if (pipe(fderr) < 0) { + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + if (need_out) + close_pair(fdout); + else if (cmd->out) + close(cmd->out); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->err = fderr[0]; + } + + fflush(NULL); + cmd->pid = fork(); + if (!cmd->pid) { + if (cmd->no_stdin) + dup_devnull(0); + else if (need_in) { + dup2(fdin[0], 0); + close_pair(fdin); + } else if (cmd->in) { + dup2(cmd->in, 0); + close(cmd->in); + } + + if (cmd->no_stderr) + dup_devnull(2); + else if (need_err) { + dup2(fderr[1], 2); + close_pair(fderr); + } + + if (cmd->no_stdout) + dup_devnull(1); + else if (cmd->stdout_to_stderr) + dup2(2, 1); + else if (need_out) { + dup2(fdout[1], 1); + close_pair(fdout); + } else if (cmd->out > 1) { + dup2(cmd->out, 1); + close(cmd->out); + } + + if (cmd->dir && chdir(cmd->dir)) + die("exec %s: cd to %s failed (%s)", cmd->argv[0], + cmd->dir, str_error_r(errno, sbuf, sizeof(sbuf))); + if (cmd->env) { + for (; *cmd->env; cmd->env++) { + if (strchr(*cmd->env, '=')) + putenv((char*)*cmd->env); + else + unsetenv(*cmd->env); + } + } + if (cmd->preexec_cb) + cmd->preexec_cb(); + if (cmd->exec_cmd) { + execv_cmd(cmd->argv); + } else { + execvp(cmd->argv[0], (char *const*) cmd->argv); + } + exit(127); + } + + if (cmd->pid < 0) { + int err = errno; + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + if (need_out) + close_pair(fdout); + else if (cmd->out) + close(cmd->out); + if (need_err) + close_pair(fderr); + return err == ENOENT ? + -ERR_RUN_COMMAND_EXEC : + -ERR_RUN_COMMAND_FORK; + } + + if (need_in) + close(fdin[0]); + else if (cmd->in) + close(cmd->in); + + if (need_out) + close(fdout[1]); + else if (cmd->out) + close(cmd->out); + + if (need_err) + close(fderr[1]); + + return 0; +} + +static int wait_or_whine(pid_t pid) +{ + char sbuf[STRERR_BUFSIZE]; + + for (;;) { + int status, code; + pid_t waiting = waitpid(pid, &status, 0); + + if (waiting < 0) { + if (errno == EINTR) + continue; + fprintf(stderr, " Error: waitpid failed (%s)", + str_error_r(errno, sbuf, sizeof(sbuf))); + return -ERR_RUN_COMMAND_WAITPID; + } + if (waiting != pid) + return -ERR_RUN_COMMAND_WAITPID_WRONG_PID; + if (WIFSIGNALED(status)) + return -ERR_RUN_COMMAND_WAITPID_SIGNAL; + + if (!WIFEXITED(status)) + return -ERR_RUN_COMMAND_WAITPID_NOEXIT; + code = WEXITSTATUS(status); + switch (code) { + case 127: + return -ERR_RUN_COMMAND_EXEC; + case 0: + return 0; + default: + return -code; + } + } +} + +int finish_command(struct child_process *cmd) +{ + return wait_or_whine(cmd->pid); +} + +int run_command(struct child_process *cmd) +{ + int code = start_command(cmd); + if (code) + return code; + return finish_command(cmd); +} + +static void prepare_run_command_v_opt(struct child_process *cmd, + const char **argv, + int opt) +{ + memset(cmd, 0, sizeof(*cmd)); + cmd->argv = argv; + cmd->no_stdin = opt & RUN_COMMAND_NO_STDIN ? 1 : 0; + cmd->exec_cmd = opt & RUN_EXEC_CMD ? 1 : 0; + cmd->stdout_to_stderr = opt & RUN_COMMAND_STDOUT_TO_STDERR ? 1 : 0; +} + +int run_command_v_opt(const char **argv, int opt) +{ + struct child_process cmd; + prepare_run_command_v_opt(&cmd, argv, opt); + return run_command(&cmd); +} diff --git a/tools/lib/subcmd/run-command.h b/tools/lib/subcmd/run-command.h new file mode 100644 index 000000000..17d969c6a --- /dev/null +++ b/tools/lib/subcmd/run-command.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SUBCMD_RUN_COMMAND_H +#define __SUBCMD_RUN_COMMAND_H + +#include <unistd.h> + +enum { + ERR_RUN_COMMAND_FORK = 10000, + ERR_RUN_COMMAND_EXEC, + ERR_RUN_COMMAND_PIPE, + ERR_RUN_COMMAND_WAITPID, + ERR_RUN_COMMAND_WAITPID_WRONG_PID, + ERR_RUN_COMMAND_WAITPID_SIGNAL, + ERR_RUN_COMMAND_WAITPID_NOEXIT, +}; +#define IS_RUN_COMMAND_ERR(x) (-(x) >= ERR_RUN_COMMAND_FORK) + +struct child_process { + const char **argv; + pid_t pid; + /* + * Using .in, .out, .err: + * - Specify 0 for no redirections (child inherits stdin, stdout, + * stderr from parent). + * - Specify -1 to have a pipe allocated as follows: + * .in: returns the writable pipe end; parent writes to it, + * the readable pipe end becomes child's stdin + * .out, .err: returns the readable pipe end; parent reads from + * it, the writable pipe end becomes child's stdout/stderr + * The caller of start_command() must close the returned FDs + * after it has completed reading from/writing to it! + * - Specify > 0 to set a channel to a particular FD as follows: + * .in: a readable FD, becomes child's stdin + * .out: a writable FD, becomes child's stdout/stderr + * .err > 0 not supported + * The specified FD is closed by start_command(), even in case + * of errors! + */ + int in; + int out; + int err; + const char *dir; + const char *const *env; + unsigned no_stdin:1; + unsigned no_stdout:1; + unsigned no_stderr:1; + unsigned exec_cmd:1; /* if this is to be external sub-command */ + unsigned stdout_to_stderr:1; + void (*preexec_cb)(void); +}; + +int start_command(struct child_process *); +int finish_command(struct child_process *); +int run_command(struct child_process *); + +#define RUN_COMMAND_NO_STDIN 1 +#define RUN_EXEC_CMD 2 /*If this is to be external sub-command */ +#define RUN_COMMAND_STDOUT_TO_STDERR 4 +int run_command_v_opt(const char **argv, int opt); + +#endif /* __SUBCMD_RUN_COMMAND_H */ diff --git a/tools/lib/subcmd/sigchain.c b/tools/lib/subcmd/sigchain.c new file mode 100644 index 000000000..f0fe3dbef --- /dev/null +++ b/tools/lib/subcmd/sigchain.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <signal.h> +#include "subcmd-util.h" +#include "sigchain.h" + +#define SIGCHAIN_MAX_SIGNALS 32 + +struct sigchain_signal { + sigchain_fun *old; + int n; + int alloc; +}; +static struct sigchain_signal signals[SIGCHAIN_MAX_SIGNALS]; + +static void check_signum(int sig) +{ + if (sig < 1 || sig >= SIGCHAIN_MAX_SIGNALS) + die("BUG: signal out of range: %d", sig); +} + +static int sigchain_push(int sig, sigchain_fun f) +{ + struct sigchain_signal *s = signals + sig; + check_signum(sig); + + ALLOC_GROW(s->old, s->n + 1, s->alloc); + s->old[s->n] = signal(sig, f); + if (s->old[s->n] == SIG_ERR) + return -1; + s->n++; + return 0; +} + +int sigchain_pop(int sig) +{ + struct sigchain_signal *s = signals + sig; + check_signum(sig); + if (s->n < 1) + return 0; + + if (signal(sig, s->old[s->n - 1]) == SIG_ERR) + return -1; + s->n--; + return 0; +} + +void sigchain_push_common(sigchain_fun f) +{ + sigchain_push(SIGINT, f); + sigchain_push(SIGHUP, f); + sigchain_push(SIGTERM, f); + sigchain_push(SIGQUIT, f); + sigchain_push(SIGPIPE, f); +} diff --git a/tools/lib/subcmd/sigchain.h b/tools/lib/subcmd/sigchain.h new file mode 100644 index 000000000..1ec663af4 --- /dev/null +++ b/tools/lib/subcmd/sigchain.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SUBCMD_SIGCHAIN_H +#define __SUBCMD_SIGCHAIN_H + +typedef void (*sigchain_fun)(int); + +int sigchain_pop(int sig); + +void sigchain_push_common(sigchain_fun f); + +#endif /* __SUBCMD_SIGCHAIN_H */ diff --git a/tools/lib/subcmd/subcmd-config.c b/tools/lib/subcmd/subcmd-config.c new file mode 100644 index 000000000..84a7cf6c7 --- /dev/null +++ b/tools/lib/subcmd/subcmd-config.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "subcmd-config.h" + +#define UNDEFINED "SUBCMD_HAS_NOT_BEEN_INITIALIZED" + +struct subcmd_config subcmd_config = { + .exec_name = UNDEFINED, + .prefix = UNDEFINED, + .exec_path = UNDEFINED, + .exec_path_env = UNDEFINED, + .pager_env = UNDEFINED, +}; diff --git a/tools/lib/subcmd/subcmd-config.h b/tools/lib/subcmd/subcmd-config.h new file mode 100644 index 000000000..9024dc17d --- /dev/null +++ b/tools/lib/subcmd/subcmd-config.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_SUBCMD_CONFIG_H +#define __PERF_SUBCMD_CONFIG_H + +struct subcmd_config { + const char *exec_name; + const char *prefix; + const char *exec_path; + const char *exec_path_env; + const char *pager_env; +}; + +extern struct subcmd_config subcmd_config; + +#endif /* __PERF_SUBCMD_CONFIG_H */ diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h new file mode 100644 index 000000000..b2aec04fc --- /dev/null +++ b/tools/lib/subcmd/subcmd-util.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SUBCMD_UTIL_H +#define __SUBCMD_UTIL_H + +#include <stdarg.h> +#include <stdlib.h> +#include <stdio.h> + +#define NORETURN __attribute__((__noreturn__)) + +static inline void report(const char *prefix, const char *err, va_list params) +{ + char msg[1024]; + vsnprintf(msg, sizeof(msg), err, params); + fprintf(stderr, " %s%s\n", prefix, msg); +} + +static NORETURN inline void die(const char *err, ...) +{ + va_list params; + + va_start(params, err); + report(" Fatal: ", err, params); + exit(128); + va_end(params); +} + +#define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) + +#define alloc_nr(x) (((x)+16)*3/2) + +/* + * Realloc the buffer pointed at by variable 'x' so that it can hold + * at least 'nr' entries; the number of entries currently allocated + * is 'alloc', using the standard growing factor alloc_nr() macro. + * + * DO NOT USE any expression with side-effect for 'x' or 'alloc'. + */ +#define ALLOC_GROW(x, nr, alloc) \ + do { \ + if ((nr) > alloc) { \ + if (alloc_nr(alloc) < (nr)) \ + alloc = (nr); \ + else \ + alloc = alloc_nr(alloc); \ + x = xrealloc((x), alloc * sizeof(*(x))); \ + } \ + } while(0) + +static inline void *xrealloc(void *ptr, size_t size) +{ + void *ret = realloc(ptr, size); + if (!ret) + die("Out of memory, realloc failed"); + return ret; +} + +#define astrcatf(out, fmt, ...) \ +({ \ + char *tmp = *(out); \ + if (asprintf((out), "%s" fmt, tmp ?: "", ## __VA_ARGS__) == -1) \ + die("asprintf failed"); \ + free(tmp); \ +}) + +static inline void astrcat(char **out, const char *add) +{ + char *tmp = *out; + + if (asprintf(out, "%s%s", tmp ?: "", add) == -1) + die("asprintf failed"); + + free(tmp); +} + +#endif /* __SUBCMD_UTIL_H */ diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c new file mode 100644 index 000000000..e335ac2b9 --- /dev/null +++ b/tools/lib/symbol/kallsyms.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "symbol/kallsyms.h" +#include "api/io.h" +#include <stdio.h> +#include <sys/stat.h> +#include <fcntl.h> + +u8 kallsyms2elf_type(char type) +{ + type = tolower(type); + return (type == 't' || type == 'w') ? STT_FUNC : STT_OBJECT; +} + +bool kallsyms__is_function(char symbol_type) +{ + symbol_type = toupper(symbol_type); + return symbol_type == 'T' || symbol_type == 'W'; +} + +static void read_to_eol(struct io *io) +{ + int ch; + + for (;;) { + ch = io__get_char(io); + if (ch < 0 || ch == '\n') + return; + } +} + +int kallsyms__parse(const char *filename, void *arg, + int (*process_symbol)(void *arg, const char *name, + char type, u64 start)) +{ + struct io io; + char bf[BUFSIZ]; + int err; + + io.fd = open(filename, O_RDONLY, 0); + + if (io.fd < 0) + return -1; + + io__init(&io, io.fd, bf, sizeof(bf)); + + err = 0; + while (!io.eof) { + __u64 start; + int ch; + size_t i; + char symbol_type; + char symbol_name[KSYM_NAME_LEN + 1]; + + if (io__get_hex(&io, &start) != ' ') { + read_to_eol(&io); + continue; + } + symbol_type = io__get_char(&io); + if (io__get_char(&io) != ' ') { + read_to_eol(&io); + continue; + } + for (i = 0; i < sizeof(symbol_name); i++) { + ch = io__get_char(&io); + if (ch < 0 || ch == '\n') + break; + symbol_name[i] = ch; + } + symbol_name[i] = '\0'; + + err = process_symbol(arg, symbol_name, symbol_type, start); + if (err) + break; + } + + close(io.fd); + return err; +} diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h new file mode 100644 index 000000000..542f9b059 --- /dev/null +++ b/tools/lib/symbol/kallsyms.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __TOOLS_KALLSYMS_H_ +#define __TOOLS_KALLSYMS_H_ 1 + +#include <elf.h> +#include <linux/ctype.h> +#include <linux/types.h> + +#ifndef KSYM_NAME_LEN +#define KSYM_NAME_LEN 512 +#endif + +static inline u8 kallsyms2elf_binding(char type) +{ + if (type == 'W') + return STB_WEAK; + + return isupper(type) ? STB_GLOBAL : STB_LOCAL; +} + +u8 kallsyms2elf_type(char type); + +bool kallsyms__is_function(char symbol_type); + +int kallsyms__parse(const char *filename, void *arg, + int (*process_symbol)(void *arg, const char *name, + char type, u64 start)); + +#endif /* __TOOLS_KALLSYMS_H_ */ diff --git a/tools/lib/thermal/.gitignore b/tools/lib/thermal/.gitignore new file mode 100644 index 000000000..5d2aeda80 --- /dev/null +++ b/tools/lib/thermal/.gitignore @@ -0,0 +1,2 @@ +libthermal.so* +libthermal.pc diff --git a/tools/lib/thermal/Build b/tools/lib/thermal/Build new file mode 100644 index 000000000..4a892d9e2 --- /dev/null +++ b/tools/lib/thermal/Build @@ -0,0 +1,5 @@ +libthermal-y += commands.o +libthermal-y += events.o +libthermal-y += thermal_nl.o +libthermal-y += sampling.o +libthermal-y += thermal.o diff --git a/tools/lib/thermal/Makefile b/tools/lib/thermal/Makefile new file mode 100644 index 000000000..2d0d255fd --- /dev/null +++ b/tools/lib/thermal/Makefile @@ -0,0 +1,165 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/lib/perf/Makefile + +LIBTHERMAL_VERSION = 0 +LIBTHERMAL_PATCHLEVEL = 0 +LIBTHERMAL_EXTRAVERSION = 1 + +MAKEFLAGS += --no-print-directory + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +# $(info Determined 'srctree' to be $(srctree)) +endif + +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +include $(srctree)/tools/scripts/Makefile.include +include $(srctree)/tools/scripts/Makefile.arch + +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= +libdir = $(prefix)/$(libdir_relative) + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) +libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +ifeq ($(VERBOSE),1) + Q = +else + Q = @ +endif + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +INCLUDES = \ +-I/usr/include/libnl3 \ +-I$(srctree)/tools/lib/thermal/include \ +-I$(srctree)/tools/lib/ \ +-I$(srctree)/tools/include \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/ \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \ +-I$(srctree)/tools/include/uapi + +# Append required CFLAGS +override CFLAGS += $(EXTRA_WARNINGS) +override CFLAGS += -Werror -Wall +override CFLAGS += -fPIC +override CFLAGS += $(INCLUDES) +override CFLAGS += -fvisibility=hidden +override CFGLAS += -Wl,-L. +override CFGLAS += -Wl,-lthermal + +all: + +export srctree OUTPUT CC LD CFLAGS V +export DESTDIR DESTDIR_SQ + +include $(srctree)/tools/build/Makefile.include + +VERSION_SCRIPT := libthermal.map + +PATCHLEVEL = $(LIBTHERMAL_PATCHLEVEL) +EXTRAVERSION = $(LIBTHERMAL_EXTRAVERSION) +VERSION = $(LIBTHERMAL_VERSION).$(LIBTHERMAL_PATCHLEVEL).$(LIBTHERMAL_EXTRAVERSION) + +LIBTHERMAL_SO := $(OUTPUT)libthermal.so.$(VERSION) +LIBTHERMAL_A := $(OUTPUT)libthermal.a +LIBTHERMAL_IN := $(OUTPUT)libthermal-in.o +LIBTHERMAL_PC := $(OUTPUT)libthermal.pc +LIBTHERMAL_ALL := $(LIBTHERMAL_A) $(OUTPUT)libthermal.so* + +THERMAL_UAPI := include/uapi/linux/thermal.h + +$(THERMAL_UAPI): FORCE + ln -sf $(srctree)/$@ $(srctree)/tools/$@ + +$(LIBTHERMAL_IN): FORCE + $(Q)$(MAKE) $(build)=libthermal + +$(LIBTHERMAL_A): $(LIBTHERMAL_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBTHERMAL_IN) + +$(LIBTHERMAL_SO): $(LIBTHERMAL_IN) + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libthermal.so \ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@ + @ln -sf $(@F) $(OUTPUT)libthermal.so + @ln -sf $(@F) $(OUTPUT)libthermal.so.$(LIBTHERMAL_VERSION) + + +libs: $(THERMAL_UAPI) $(LIBTHERMAL_A) $(LIBTHERMAL_SO) $(LIBTHERMAL_PC) + +all: fixdep + $(Q)$(MAKE) libs + +clean: + $(call QUIET_CLEAN, libthermal) $(RM) $(LIBTHERMAL_A) \ + *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBTHERMAL_VERSION) .*.d .*.cmd LIBTHERMAL-CFLAGS $(LIBTHERMAL_PC) + +$(LIBTHERMAL_PC): + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(VERSION)|" \ + < libthermal.pc.template > $@ + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ + fi; \ + $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' +endef + +install_lib: libs + $(call QUIET_INSTALL, $(LIBTHERMAL_ALL)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIBTHERMAL_ALL) $(DESTDIR)$(libdir_SQ) + +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,include/thermal.h,$(prefix)/include/thermal,644); \ + +install_pkgconfig: $(LIBTHERMAL_PC) + $(call QUIET_INSTALL, $(LIBTHERMAL_PC)) \ + $(call do_install,$(LIBTHERMAL_PC),$(libdir_SQ)/pkgconfig,644) + +install_doc: + $(Q)$(MAKE) -C Documentation install-man install-html install-examples + +install: install_lib install_headers install_pkgconfig + +FORCE: + +.PHONY: all install clean FORCE diff --git a/tools/lib/thermal/commands.c b/tools/lib/thermal/commands.c new file mode 100644 index 000000000..73d4d4e8d --- /dev/null +++ b/tools/lib/thermal/commands.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +static struct nla_policy thermal_genl_policy[THERMAL_GENL_ATTR_MAX + 1] = { + /* Thermal zone */ + [THERMAL_GENL_ATTR_TZ] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TEMP] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_TRIP_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_TEMP] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_TYPE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_HYST] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_MODE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_CDEV_WEIGHT] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_NAME] = { .type = NLA_STRING }, + + /* Governor(s) */ + [THERMAL_GENL_ATTR_TZ_GOV] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_GOV_NAME] = { .type = NLA_STRING }, + + /* Cooling devices */ + [THERMAL_GENL_ATTR_CDEV] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_CDEV_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_CUR_STATE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_MAX_STATE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_NAME] = { .type = NLA_STRING }, +}; + +static int parse_tz_get(struct genl_info *info, struct thermal_zone **tz) +{ + struct nlattr *attr; + struct thermal_zone *__tz = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_TZ], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_ID) { + + size++; + + __tz = realloc(__tz, sizeof(*__tz) * (size + 2)); + if (!__tz) + return THERMAL_ERROR; + + __tz[size - 1].id = nla_get_u32(attr); + } + + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_NAME) + nla_strlcpy(__tz[size - 1].name, attr, + THERMAL_NAME_LENGTH); + } + + if (__tz) + __tz[size].id = -1; + + *tz = __tz; + + return THERMAL_SUCCESS; +} + +static int parse_cdev_get(struct genl_info *info, struct thermal_cdev **cdev) +{ + struct nlattr *attr; + struct thermal_cdev *__cdev = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_CDEV], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_ID) { + + size++; + + __cdev = realloc(__cdev, sizeof(*__cdev) * (size + 2)); + if (!__cdev) + return THERMAL_ERROR; + + __cdev[size - 1].id = nla_get_u32(attr); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_NAME) { + nla_strlcpy(__cdev[size - 1].name, attr, + THERMAL_NAME_LENGTH); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_CUR_STATE) + __cdev[size - 1].cur_state = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_MAX_STATE) + __cdev[size - 1].max_state = nla_get_u32(attr); + } + + if (__cdev) + __cdev[size].id = -1; + + *cdev = __cdev; + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_trip(struct genl_info *info, struct thermal_zone *tz) +{ + struct nlattr *attr; + struct thermal_trip *__tt = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_TZ_TRIP], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_ID) { + + size++; + + __tt = realloc(__tt, sizeof(*__tt) * (size + 2)); + if (!__tt) + return THERMAL_ERROR; + + __tt[size - 1].id = nla_get_u32(attr); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_TYPE) + __tt[size - 1].type = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_TEMP) + __tt[size - 1].temp = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_HYST) + __tt[size - 1].hyst = nla_get_u32(attr); + } + + if (__tt) + __tt[size].id = -1; + + tz->trip = __tt; + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_temp(struct genl_info *info, struct thermal_zone *tz) +{ + int id = -1; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_ID]) + id = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_ID]); + + if (tz->id != id) + return THERMAL_ERROR; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_TEMP]) + tz->temp = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_TEMP]); + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_gov(struct genl_info *info, struct thermal_zone *tz) +{ + int id = -1; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_ID]) + id = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_ID]); + + if (tz->id != id) + return THERMAL_ERROR; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_GOV_NAME]) { + nla_strlcpy(tz->governor, + info->attrs[THERMAL_GENL_ATTR_TZ_GOV_NAME], + THERMAL_NAME_LENGTH); + } + + return THERMAL_SUCCESS; +} + +static int handle_netlink(struct nl_cache_ops *unused, + struct genl_cmd *cmd, + struct genl_info *info, void *arg) +{ + int ret; + + switch (cmd->c_id) { + + case THERMAL_GENL_CMD_TZ_GET_ID: + ret = parse_tz_get(info, arg); + break; + + case THERMAL_GENL_CMD_CDEV_GET: + ret = parse_cdev_get(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_TEMP: + ret = parse_tz_get_temp(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_TRIP: + ret = parse_tz_get_trip(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_GOV: + ret = parse_tz_get_gov(info, arg); + break; + + default: + return THERMAL_ERROR; + } + + return ret; +} + +static struct genl_cmd thermal_cmds[] = { + { + .c_id = THERMAL_GENL_CMD_TZ_GET_ID, + .c_name = (char *)"List thermal zones", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_GOV, + .c_name = (char *)"Get governor", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_TEMP, + .c_name = (char *)"Get thermal zone temperature", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_TRIP, + .c_name = (char *)"Get thermal zone trip points", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_CDEV_GET, + .c_name = (char *)"Get cooling devices", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, +}; + +static struct genl_ops thermal_cmd_ops = { + .o_name = (char *)"thermal", + .o_cmds = thermal_cmds, + .o_ncmds = ARRAY_SIZE(thermal_cmds), +}; + +static thermal_error_t thermal_genl_auto(struct thermal_handler *th, int id, int cmd, + int flags, void *arg) +{ + struct nl_msg *msg; + void *hdr; + + msg = nlmsg_alloc(); + if (!msg) + return THERMAL_ERROR; + + hdr = genlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, thermal_cmd_ops.o_id, + 0, flags, cmd, THERMAL_GENL_VERSION); + if (!hdr) + return THERMAL_ERROR; + + if (id >= 0 && nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, id)) + return THERMAL_ERROR; + + if (nl_send_msg(th->sk_cmd, th->cb_cmd, msg, genl_handle_msg, arg)) + return THERMAL_ERROR; + + nlmsg_free(msg); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_cmd_get_tz(struct thermal_handler *th, struct thermal_zone **tz) +{ + return thermal_genl_auto(th, -1, THERMAL_GENL_CMD_TZ_GET_ID, + NLM_F_DUMP | NLM_F_ACK, tz); +} + +thermal_error_t thermal_cmd_get_cdev(struct thermal_handler *th, struct thermal_cdev **tc) +{ + return thermal_genl_auto(th, -1, THERMAL_GENL_CMD_CDEV_GET, + NLM_F_DUMP | NLM_F_ACK, tc); +} + +thermal_error_t thermal_cmd_get_trip(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_TRIP, + 0, tz); +} + +thermal_error_t thermal_cmd_get_governor(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_GOV, 0, tz); +} + +thermal_error_t thermal_cmd_get_temp(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_TEMP, 0, tz); +} + +thermal_error_t thermal_cmd_exit(struct thermal_handler *th) +{ + if (genl_unregister_family(&thermal_cmd_ops)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_cmd, th->cb_cmd); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_cmd_init(struct thermal_handler *th) +{ + int ret; + int family; + + if (nl_thermal_connect(&th->sk_cmd, &th->cb_cmd)) + return THERMAL_ERROR; + + ret = genl_register_family(&thermal_cmd_ops); + if (ret) + return THERMAL_ERROR; + + ret = genl_ops_resolve(th->sk_cmd, &thermal_cmd_ops); + if (ret) + return THERMAL_ERROR; + + family = genl_ctrl_resolve(th->sk_cmd, "nlctrl"); + if (family != GENL_ID_CTRL) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/events.c b/tools/lib/thermal/events.c new file mode 100644 index 000000000..a7a55d1a0 --- /dev/null +++ b/tools/lib/thermal/events.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <linux/netlink.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + + +#include <thermal.h> +#include "thermal_nl.h" + +/* + * Optimization: fill this array to tell which event we do want to pay + * attention to. That happens at init time with the ops + * structure. Each ops will enable the event and the general handler + * will be able to discard the event if there is not ops associated + * with it. + */ +static int enabled_ops[__THERMAL_GENL_EVENT_MAX]; + +static int handle_thermal_event(struct nl_msg *n, void *arg) +{ + struct nlmsghdr *nlh = nlmsg_hdr(n); + struct genlmsghdr *genlhdr = genlmsg_hdr(nlh); + struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1]; + struct thermal_handler_param *thp = arg; + struct thermal_events_ops *ops = &thp->th->ops->events; + + genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); + + arg = thp->arg; + + /* + * This is an event we don't care of, bail out. + */ + if (!enabled_ops[genlhdr->cmd]) + return THERMAL_SUCCESS; + + switch (genlhdr->cmd) { + + case THERMAL_GENL_EVENT_TZ_CREATE: + return ops->tz_create(nla_get_string(attrs[THERMAL_GENL_ATTR_TZ_NAME]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_DELETE: + return ops->tz_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_ENABLE: + return ops->tz_enable(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_DISABLE: + return ops->tz_disable(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_CHANGE: + return ops->trip_change(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_HYST]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_ADD: + return ops->trip_add(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_HYST]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_DELETE: + return ops->trip_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_UP: + return ops->trip_high(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_DOWN: + return ops->trip_low(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + + case THERMAL_GENL_EVENT_CDEV_ADD: + return ops->cdev_add(nla_get_string(attrs[THERMAL_GENL_ATTR_CDEV_NAME]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_MAX_STATE]), arg); + + case THERMAL_GENL_EVENT_CDEV_DELETE: + return ops->cdev_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), arg); + + case THERMAL_GENL_EVENT_CDEV_STATE_UPDATE: + return ops->cdev_update(nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_CUR_STATE]), arg); + + case THERMAL_GENL_EVENT_TZ_GOV_CHANGE: + return ops->gov_change(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_string(attrs[THERMAL_GENL_ATTR_GOV_NAME]), arg); + default: + return -1; + } +} + +static void thermal_events_ops_init(struct thermal_events_ops *ops) +{ + enabled_ops[THERMAL_GENL_EVENT_TZ_CREATE] = !!ops->tz_create; + enabled_ops[THERMAL_GENL_EVENT_TZ_DELETE] = !!ops->tz_delete; + enabled_ops[THERMAL_GENL_EVENT_TZ_DISABLE] = !!ops->tz_disable; + enabled_ops[THERMAL_GENL_EVENT_TZ_ENABLE] = !!ops->tz_enable; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_UP] = !!ops->trip_high; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_DOWN] = !!ops->trip_low; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_CHANGE] = !!ops->trip_change; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_ADD] = !!ops->trip_add; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_DELETE] = !!ops->trip_delete; + enabled_ops[THERMAL_GENL_EVENT_CDEV_ADD] = !!ops->cdev_add; + enabled_ops[THERMAL_GENL_EVENT_CDEV_DELETE] = !!ops->cdev_delete; + enabled_ops[THERMAL_GENL_EVENT_CDEV_STATE_UPDATE] = !!ops->cdev_update; + enabled_ops[THERMAL_GENL_EVENT_TZ_GOV_CHANGE] = !!ops->gov_change; +} + +thermal_error_t thermal_events_handle(struct thermal_handler *th, void *arg) +{ + struct thermal_handler_param thp = { .th = th, .arg = arg }; + + if (!th) + return THERMAL_ERROR; + + if (nl_cb_set(th->cb_event, NL_CB_VALID, NL_CB_CUSTOM, + handle_thermal_event, &thp)) + return THERMAL_ERROR; + + return nl_recvmsgs(th->sk_event, th->cb_event); +} + +int thermal_events_fd(struct thermal_handler *th) +{ + if (!th) + return -1; + + return nl_socket_get_fd(th->sk_event); +} + +thermal_error_t thermal_events_exit(struct thermal_handler *th) +{ + if (nl_unsubscribe_thermal(th->sk_event, th->cb_event, + THERMAL_GENL_EVENT_GROUP_NAME)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_event, th->cb_event); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_events_init(struct thermal_handler *th) +{ + thermal_events_ops_init(&th->ops->events); + + if (nl_thermal_connect(&th->sk_event, &th->cb_event)) + return THERMAL_ERROR; + + if (nl_subscribe_thermal(th->sk_event, th->cb_event, + THERMAL_GENL_EVENT_GROUP_NAME)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/include/thermal.h b/tools/lib/thermal/include/thermal.h new file mode 100644 index 000000000..1abc56060 --- /dev/null +++ b/tools/lib/thermal/include/thermal.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __LIBTHERMAL_H +#define __LIBTHERMAL_H + +#include <linux/thermal.h> + +#ifndef LIBTHERMAL_API +#define LIBTHERMAL_API __attribute__((visibility("default"))) +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +struct thermal_sampling_ops { + int (*tz_temp)(int tz_id, int temp, void *arg); +}; + +struct thermal_events_ops { + int (*tz_create)(const char *name, int tz_id, void *arg); + int (*tz_delete)(int tz_id, void *arg); + int (*tz_enable)(int tz_id, void *arg); + int (*tz_disable)(int tz_id, void *arg); + int (*trip_high)(int tz_id, int trip_id, int temp, void *arg); + int (*trip_low)(int tz_id, int trip_id, int temp, void *arg); + int (*trip_add)(int tz_id, int trip_id, int type, int temp, int hyst, void *arg); + int (*trip_change)(int tz_id, int trip_id, int type, int temp, int hyst, void *arg); + int (*trip_delete)(int tz_id, int trip_id, void *arg); + int (*cdev_add)(const char *name, int cdev_id, int max_state, void *arg); + int (*cdev_delete)(int cdev_id, void *arg); + int (*cdev_update)(int cdev_id, int cur_state, void *arg); + int (*gov_change)(int tz_id, const char *gov_name, void *arg); +}; + +struct thermal_ops { + struct thermal_sampling_ops sampling; + struct thermal_events_ops events; +}; + +struct thermal_trip { + int id; + int type; + int temp; + int hyst; +}; + +struct thermal_zone { + int id; + int temp; + char name[THERMAL_NAME_LENGTH]; + char governor[THERMAL_NAME_LENGTH]; + struct thermal_trip *trip; +}; + +struct thermal_cdev { + int id; + char name[THERMAL_NAME_LENGTH]; + int max_state; + int min_state; + int cur_state; +}; + +typedef enum { + THERMAL_ERROR = -1, + THERMAL_SUCCESS = 0, +} thermal_error_t; + +struct thermal_handler; + +typedef int (*cb_tz_t)(struct thermal_zone *, void *); + +typedef int (*cb_tt_t)(struct thermal_trip *, void *); + +typedef int (*cb_tc_t)(struct thermal_cdev *, void *); + +LIBTHERMAL_API int for_each_thermal_zone(struct thermal_zone *tz, cb_tz_t cb, void *arg); + +LIBTHERMAL_API int for_each_thermal_trip(struct thermal_trip *tt, cb_tt_t cb, void *arg); + +LIBTHERMAL_API int for_each_thermal_cdev(struct thermal_cdev *cdev, cb_tc_t cb, void *arg); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_find_by_name(struct thermal_zone *tz, + const char *name); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_find_by_id(struct thermal_zone *tz, int id); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_discover(struct thermal_handler *th); + +LIBTHERMAL_API struct thermal_handler *thermal_init(struct thermal_ops *ops); + +LIBTHERMAL_API void thermal_exit(struct thermal_handler *th); + +/* + * Netlink thermal events + */ +LIBTHERMAL_API thermal_error_t thermal_events_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_events_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_events_handle(struct thermal_handler *th, void *arg); + +LIBTHERMAL_API int thermal_events_fd(struct thermal_handler *th); + +/* + * Netlink thermal commands + */ +LIBTHERMAL_API thermal_error_t thermal_cmd_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_cmd_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_tz(struct thermal_handler *th, + struct thermal_zone **tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_cdev(struct thermal_handler *th, + struct thermal_cdev **tc); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_trip(struct thermal_handler *th, + struct thermal_zone *tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_governor(struct thermal_handler *th, + struct thermal_zone *tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_temp(struct thermal_handler *th, + struct thermal_zone *tz); + +/* + * Netlink thermal samples + */ +LIBTHERMAL_API thermal_error_t thermal_sampling_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_sampling_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_sampling_handle(struct thermal_handler *th, void *arg); + +LIBTHERMAL_API int thermal_sampling_fd(struct thermal_handler *th); + +#endif /* __LIBTHERMAL_H */ + +#ifdef __cplusplus +} +#endif diff --git a/tools/lib/thermal/libthermal.map b/tools/lib/thermal/libthermal.map new file mode 100644 index 000000000..d5e77738c --- /dev/null +++ b/tools/lib/thermal/libthermal.map @@ -0,0 +1,25 @@ +LIBTHERMAL_0.0.1 { + global: + thermal_init; + for_each_thermal_zone; + for_each_thermal_trip; + for_each_thermal_cdev; + thermal_zone_find_by_name; + thermal_zone_find_by_id; + thermal_zone_discover; + thermal_init; + thermal_events_init; + thermal_events_handle; + thermal_events_fd; + thermal_cmd_init; + thermal_cmd_get_tz; + thermal_cmd_get_cdev; + thermal_cmd_get_trip; + thermal_cmd_get_governor; + thermal_cmd_get_temp; + thermal_sampling_init; + thermal_sampling_handle; + thermal_sampling_fd; +local: + *; +}; diff --git a/tools/lib/thermal/libthermal.pc.template b/tools/lib/thermal/libthermal.pc.template new file mode 100644 index 000000000..6f3769731 --- /dev/null +++ b/tools/lib/thermal/libthermal.pc.template @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libthermal +Description: thermal library +Requires: libnl-3.0 libnl-genl-3.0 +Version: @VERSION@ +Libs: -L${libdir} -lnl-genl-3 -lnl-3 +Cflags: -I${includedir} -I{include}/libnl3 diff --git a/tools/lib/thermal/sampling.c b/tools/lib/thermal/sampling.c new file mode 100644 index 000000000..70577423a --- /dev/null +++ b/tools/lib/thermal/sampling.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +static int handle_thermal_sample(struct nl_msg *n, void *arg) +{ + struct nlmsghdr *nlh = nlmsg_hdr(n); + struct genlmsghdr *genlhdr = genlmsg_hdr(nlh); + struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1]; + struct thermal_handler_param *thp = arg; + struct thermal_handler *th = thp->th; + + genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); + + switch (genlhdr->cmd) { + + case THERMAL_GENL_SAMPLING_TEMP: + return th->ops->sampling.tz_temp( + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + default: + return THERMAL_ERROR; + } +} + +thermal_error_t thermal_sampling_handle(struct thermal_handler *th, void *arg) +{ + struct thermal_handler_param thp = { .th = th, .arg = arg }; + + if (!th) + return THERMAL_ERROR; + + if (nl_cb_set(th->cb_sampling, NL_CB_VALID, NL_CB_CUSTOM, + handle_thermal_sample, &thp)) + return THERMAL_ERROR; + + return nl_recvmsgs(th->sk_sampling, th->cb_sampling); +} + +int thermal_sampling_fd(struct thermal_handler *th) +{ + if (!th) + return -1; + + return nl_socket_get_fd(th->sk_sampling); +} + +thermal_error_t thermal_sampling_exit(struct thermal_handler *th) +{ + if (nl_unsubscribe_thermal(th->sk_sampling, th->cb_sampling, + THERMAL_GENL_SAMPLING_GROUP_NAME)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_sampling, th->cb_sampling); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_sampling_init(struct thermal_handler *th) +{ + if (nl_thermal_connect(&th->sk_sampling, &th->cb_sampling)) + return THERMAL_ERROR; + + if (nl_subscribe_thermal(th->sk_sampling, th->cb_sampling, + THERMAL_GENL_SAMPLING_GROUP_NAME)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/thermal.c b/tools/lib/thermal/thermal.c new file mode 100644 index 000000000..72a76dc20 --- /dev/null +++ b/tools/lib/thermal/thermal.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <stdio.h> +#include <thermal.h> + +#include "thermal_nl.h" + +int for_each_thermal_cdev(struct thermal_cdev *cdev, cb_tc_t cb, void *arg) +{ + int i, ret = 0; + + if (!cdev) + return 0; + + for (i = 0; cdev[i].id != -1; i++) + ret |= cb(&cdev[i], arg); + + return ret; +} + +int for_each_thermal_trip(struct thermal_trip *tt, cb_tt_t cb, void *arg) +{ + int i, ret = 0; + + if (!tt) + return 0; + + for (i = 0; tt[i].id != -1; i++) + ret |= cb(&tt[i], arg); + + return ret; +} + +int for_each_thermal_zone(struct thermal_zone *tz, cb_tz_t cb, void *arg) +{ + int i, ret = 0; + + if (!tz) + return 0; + + for (i = 0; tz[i].id != -1; i++) + ret |= cb(&tz[i], arg); + + return ret; +} + +struct thermal_zone *thermal_zone_find_by_name(struct thermal_zone *tz, + const char *name) +{ + int i; + + if (!tz || !name) + return NULL; + + for (i = 0; tz[i].id != -1; i++) { + if (!strcmp(tz[i].name, name)) + return &tz[i]; + } + + return NULL; +} + +struct thermal_zone *thermal_zone_find_by_id(struct thermal_zone *tz, int id) +{ + int i; + + if (!tz || id < 0) + return NULL; + + for (i = 0; tz[i].id != -1; i++) { + if (tz[i].id == id) + return &tz[i]; + } + + return NULL; +} + +static int __thermal_zone_discover(struct thermal_zone *tz, void *th) +{ + if (thermal_cmd_get_trip(th, tz) < 0) + return -1; + + if (thermal_cmd_get_governor(th, tz)) + return -1; + + return 0; +} + +struct thermal_zone *thermal_zone_discover(struct thermal_handler *th) +{ + struct thermal_zone *tz; + + if (thermal_cmd_get_tz(th, &tz) < 0) + return NULL; + + if (for_each_thermal_zone(tz, __thermal_zone_discover, th)) + return NULL; + + return tz; +} + +void thermal_exit(struct thermal_handler *th) +{ + thermal_cmd_exit(th); + thermal_events_exit(th); + thermal_sampling_exit(th); + + free(th); +} + +struct thermal_handler *thermal_init(struct thermal_ops *ops) +{ + struct thermal_handler *th; + + th = malloc(sizeof(*th)); + if (!th) + return NULL; + th->ops = ops; + + if (thermal_events_init(th)) + goto out_free; + + if (thermal_sampling_init(th)) + goto out_free; + + if (thermal_cmd_init(th)) + goto out_free; + + return th; + +out_free: + free(th); + + return NULL; +} diff --git a/tools/lib/thermal/thermal_nl.c b/tools/lib/thermal/thermal_nl.c new file mode 100644 index 000000000..b05cf9569 --- /dev/null +++ b/tools/lib/thermal/thermal_nl.c @@ -0,0 +1,215 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +struct handler_args { + const char *group; + int id; +}; + +static __thread int err; +static __thread int done; + +static int nl_seq_check_handler(struct nl_msg *msg, void *arg) +{ + return NL_OK; +} + +static int nl_error_handler(struct sockaddr_nl *nla, struct nlmsgerr *nl_err, + void *arg) +{ + int *ret = arg; + + if (ret) + *ret = nl_err->error; + + return NL_STOP; +} + +static int nl_finish_handler(struct nl_msg *msg, void *arg) +{ + int *ret = arg; + + if (ret) + *ret = 1; + + return NL_OK; +} + +static int nl_ack_handler(struct nl_msg *msg, void *arg) +{ + int *ret = arg; + + if (ret) + *ret = 1; + + return NL_OK; +} + +int nl_send_msg(struct nl_sock *sock, struct nl_cb *cb, struct nl_msg *msg, + int (*rx_handler)(struct nl_msg *, void *), void *data) +{ + if (!rx_handler) + return THERMAL_ERROR; + + err = nl_send_auto_complete(sock, msg); + if (err < 0) + return err; + + nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, rx_handler, data); + + err = done = 0; + + while (err == 0 && done == 0) + nl_recvmsgs(sock, cb); + + return err; +} + +static int nl_family_handler(struct nl_msg *msg, void *arg) +{ + struct handler_args *grp = arg; + struct nlattr *tb[CTRL_ATTR_MAX + 1]; + struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg)); + struct nlattr *mcgrp; + int rem_mcgrp; + + nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0), + genlmsg_attrlen(gnlh, 0), NULL); + + if (!tb[CTRL_ATTR_MCAST_GROUPS]) + return THERMAL_ERROR; + + nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], rem_mcgrp) { + + struct nlattr *tb_mcgrp[CTRL_ATTR_MCAST_GRP_MAX + 1]; + + nla_parse(tb_mcgrp, CTRL_ATTR_MCAST_GRP_MAX, + nla_data(mcgrp), nla_len(mcgrp), NULL); + + if (!tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME] || + !tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]) + continue; + + if (strncmp(nla_data(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]), + grp->group, + nla_len(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]))) + continue; + + grp->id = nla_get_u32(tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]); + + break; + } + + return THERMAL_SUCCESS; +} + +static int nl_get_multicast_id(struct nl_sock *sock, struct nl_cb *cb, + const char *family, const char *group) +{ + struct nl_msg *msg; + int ret = 0, ctrlid; + struct handler_args grp = { + .group = group, + .id = -ENOENT, + }; + + msg = nlmsg_alloc(); + if (!msg) + return THERMAL_ERROR; + + ctrlid = genl_ctrl_resolve(sock, "nlctrl"); + + genlmsg_put(msg, 0, 0, ctrlid, 0, 0, CTRL_CMD_GETFAMILY, 0); + + nla_put_string(msg, CTRL_ATTR_FAMILY_NAME, family); + + ret = nl_send_msg(sock, cb, msg, nl_family_handler, &grp); + if (ret) + goto nla_put_failure; + + ret = grp.id; + +nla_put_failure: + nlmsg_free(msg); + return ret; +} + +int nl_thermal_connect(struct nl_sock **nl_sock, struct nl_cb **nl_cb) +{ + struct nl_cb *cb; + struct nl_sock *sock; + + cb = nl_cb_alloc(NL_CB_DEFAULT); + if (!cb) + return THERMAL_ERROR; + + sock = nl_socket_alloc(); + if (!sock) + goto out_cb_free; + + if (genl_connect(sock)) + goto out_socket_free; + + if (nl_cb_err(cb, NL_CB_CUSTOM, nl_error_handler, &err) || + nl_cb_set(cb, NL_CB_FINISH, NL_CB_CUSTOM, nl_finish_handler, &done) || + nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, nl_ack_handler, &done) || + nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, nl_seq_check_handler, &done)) + return THERMAL_ERROR; + + *nl_sock = sock; + *nl_cb = cb; + + return THERMAL_SUCCESS; + +out_socket_free: + nl_socket_free(sock); +out_cb_free: + nl_cb_put(cb); + return THERMAL_ERROR; +} + +void nl_thermal_disconnect(struct nl_sock *nl_sock, struct nl_cb *nl_cb) +{ + nl_close(nl_sock); + nl_socket_free(nl_sock); + nl_cb_put(nl_cb); +} + +int nl_unsubscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group) +{ + int mcid; + + mcid = nl_get_multicast_id(nl_sock, nl_cb, THERMAL_GENL_FAMILY_NAME, + group); + if (mcid < 0) + return THERMAL_ERROR; + + if (nl_socket_drop_membership(nl_sock, mcid)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} + +int nl_subscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group) +{ + int mcid; + + mcid = nl_get_multicast_id(nl_sock, nl_cb, THERMAL_GENL_FAMILY_NAME, + group); + if (mcid < 0) + return THERMAL_ERROR; + + if (nl_socket_add_membership(nl_sock, mcid)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/thermal_nl.h b/tools/lib/thermal/thermal_nl.h new file mode 100644 index 000000000..ddf635642 --- /dev/null +++ b/tools/lib/thermal/thermal_nl.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __THERMAL_H +#define __THERMAL_H + +#include <netlink/netlink.h> +#include <netlink/genl/genl.h> +#include <netlink/genl/mngt.h> +#include <netlink/genl/ctrl.h> + +struct thermal_handler { + int done; + int error; + struct thermal_ops *ops; + struct nl_msg *msg; + struct nl_sock *sk_event; + struct nl_sock *sk_sampling; + struct nl_sock *sk_cmd; + struct nl_cb *cb_cmd; + struct nl_cb *cb_event; + struct nl_cb *cb_sampling; +}; + +struct thermal_handler_param { + struct thermal_handler *th; + void *arg; +}; + +/* + * Low level netlink + */ +extern int nl_subscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group); + +extern int nl_unsubscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group); + +extern int nl_thermal_connect(struct nl_sock **nl_sock, struct nl_cb **nl_cb); + +extern void nl_thermal_disconnect(struct nl_sock *nl_sock, struct nl_cb *nl_cb); + +extern int nl_send_msg(struct nl_sock *sock, struct nl_cb *nl_cb, struct nl_msg *msg, + int (*rx_handler)(struct nl_msg *, void *), + void *data); + +#endif /* __THERMAL_H */ diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore new file mode 100644 index 000000000..7123c70b9 --- /dev/null +++ b/tools/lib/traceevent/.gitignore @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +TRACEEVENT-CFLAGS +libtraceevent-dynamic-list +libtraceevent.so.* diff --git a/tools/lib/traceevent/Build b/tools/lib/traceevent/Build new file mode 100644 index 000000000..f9a5d7957 --- /dev/null +++ b/tools/lib/traceevent/Build @@ -0,0 +1,8 @@ +libtraceevent-y += event-parse.o +libtraceevent-y += event-plugin.o +libtraceevent-y += trace-seq.o +libtraceevent-y += parse-filter.o +libtraceevent-y += parse-utils.o +libtraceevent-y += kbuffer-parse.o +libtraceevent-y += tep_strerror.o +libtraceevent-y += event-parse-api.o diff --git a/tools/lib/traceevent/Documentation/Makefile b/tools/lib/traceevent/Documentation/Makefile new file mode 100644 index 000000000..aa72ab96c --- /dev/null +++ b/tools/lib/traceevent/Documentation/Makefile @@ -0,0 +1,207 @@ +include ../../../scripts/Makefile.include +include ../../../scripts/utilities.mak + +# This Makefile and manpage XSL files were taken from tools/perf/Documentation +# and modified for libtraceevent. + +MAN3_TXT= \ + $(wildcard libtraceevent-*.txt) \ + libtraceevent.txt + +MAN_TXT = $(MAN3_TXT) +_MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT)) +_MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT)) +_DOC_MAN3=$(patsubst %.txt,%.3,$(MAN3_TXT)) + +MAN_XML=$(addprefix $(OUTPUT),$(_MAN_XML)) +MAN_HTML=$(addprefix $(OUTPUT),$(_MAN_HTML)) +DOC_MAN3=$(addprefix $(OUTPUT),$(_DOC_MAN3)) + +# Make the path relative to DESTDIR, not prefix +ifndef DESTDIR +prefix?=$(HOME) +endif +bindir?=$(prefix)/bin +htmldir?=$(prefix)/share/doc/libtraceevent-doc +pdfdir?=$(prefix)/share/doc/libtraceevent-doc +mandir?=$(prefix)/share/man +man3dir=$(mandir)/man3 + +ASCIIDOC=asciidoc +ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf +ASCIIDOC_HTML = xhtml11 +MANPAGE_XSL = manpage-normal.xsl +XMLTO_EXTRA = +INSTALL?=install +RM ?= rm -f + +ifdef USE_ASCIIDOCTOR +ASCIIDOC = asciidoctor +ASCIIDOC_EXTRA = -a compat-mode +ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions +ASCIIDOC_EXTRA += -a mansource="libtraceevent" -a manmanual="libtraceevent Manual" +ASCIIDOC_HTML = xhtml5 +endif + +XMLTO=xmlto + +_tmp_tool_path := $(call get-executable,$(ASCIIDOC)) +ifeq ($(_tmp_tool_path),) + missing_tools = $(ASCIIDOC) +endif + +ifndef USE_ASCIIDOCTOR +_tmp_tool_path := $(call get-executable,$(XMLTO)) +ifeq ($(_tmp_tool_path),) + missing_tools += $(XMLTO) +endif +endif + +# +# 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 libtraceevent-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 libtraceevent-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 + +SHELL_PATH ?= $(SHELL) +# Shell quote; +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) + +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 '$@; + QUIET_XMLTO = @echo ' XMLTO '$@; + QUIET_SUBDIR0 = +@subdir= + QUIET_SUBDIR1 = ;$(NO_SUBDIR) \ + echo ' SUBDIR ' $$subdir; \ + $(MAKE) $(PRINT_DIR) -C $$subdir + export V +endif +endif + +all: html man + +man: man3 +man3: $(DOC_MAN3) + +html: $(MAN_HTML) + +$(MAN_HTML) $(DOC_MAN3): asciidoc.conf + +install: install-man + +check-man-tools: +ifdef missing_tools + $(error "You need to install $(missing_tools) for man pages") +endif + +do-install-man: man + $(call QUIET_INSTALL, Documentation-man) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man3dir); \ + $(INSTALL) -m 644 $(DOC_MAN3) $(DESTDIR)$(man3dir); + +install-man: check-man-tools man do-install-man + +uninstall: uninstall-man + +uninstall-man: + $(call QUIET_UNINST, Documentation-man) \ + $(Q)$(RM) $(addprefix $(DESTDIR)$(man3dir)/,$(DOC_MAN3)) + + +ifdef missing_tools + DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed) +else + DO_INSTALL_MAN = do-install-man +endif + +CLEAN_FILES = \ + $(MAN_XML) $(addsuffix +,$(MAN_XML)) \ + $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) \ + $(DOC_MAN3) *.3 + +clean: + $(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES) + +ifdef USE_ASCIIDOCTOR +$(OUTPUT)%.3 : $(OUTPUT)%.txt + $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ + $(ASCIIDOC) -b manpage -d manpage \ + $(ASCIIDOC_EXTRA) -alibtraceevent_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ +endif + +$(OUTPUT)%.3 : $(OUTPUT)%.xml + $(QUIET_XMLTO)$(RM) $@ && \ + $(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + +$(OUTPUT)%.xml : %.txt + $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ + $(ASCIIDOC) -b docbook -d manpage \ + $(ASCIIDOC_EXTRA) -alibtraceevent_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ + +$(MAN_HTML): $(OUTPUT)%.html : %.txt + $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ + $(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \ + $(ASCIIDOC_EXTRA) -aperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ diff --git a/tools/lib/traceevent/Documentation/asciidoc.conf b/tools/lib/traceevent/Documentation/asciidoc.conf new file mode 100644 index 000000000..07595717f --- /dev/null +++ b/tools/lib/traceevent/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">libtraceevent</refmiscinfo> +<refmiscinfo class="version">{libtraceevent_version}</refmiscinfo> +<refmiscinfo class="manual">libtraceevent 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/traceevent/Documentation/libtraceevent-commands.txt b/tools/lib/traceevent/Documentation/libtraceevent-commands.txt new file mode 100644 index 000000000..bec552001 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-commands.txt @@ -0,0 +1,153 @@ +libtraceevent(3) +================ + +NAME +---- +tep_register_comm, tep_override_comm, tep_pid_is_registered, +tep_data_comm_from_pid, tep_data_pid_from_comm, tep_cmdline_pid - +Manage pid to process name mappings. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_register_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_); +int *tep_override_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_); +bool *tep_is_pid_registered*(struct tep_handle pass:[*]_tep_, int _pid_); +const char pass:[*]*tep_data_comm_from_pid*(struct tep_handle pass:[*]_pevent_, int _pid_); +struct cmdline pass:[*]*tep_data_pid_from_comm*(struct tep_handle pass:[*]_pevent_, const char pass:[*]_comm_, struct cmdline pass:[*]_next_); +int *tep_cmdline_pid*(struct tep_handle pass:[*]_pevent_, struct cmdline pass:[*]_cmdline_); +-- + +DESCRIPTION +----------- +These functions can be used to handle the mapping between pid and process name. +The library builds a cache of these mappings, which is used to display the name +of the process, instead of its pid. This information can be retrieved from +tracefs/saved_cmdlines file. + +The _tep_register_comm()_ function registers a _pid_ / process name mapping. +If a command with the same _pid_ is already registered, an error is returned. +The _pid_ argument is the process ID, the _comm_ argument is the process name, +_tep_ is the event context. The _comm_ is duplicated internally. + +The _tep_override_comm()_ function registers a _pid_ / process name mapping. +If a process with the same pid is already registered, the process name string is +udapted with the new one. The _pid_ argument is the process ID, the _comm_ +argument is the process name, _tep_ is the event context. The _comm_ is +duplicated internally. + +The _tep_is_pid_registered()_ function checks if a pid has a process name +mapping registered. The _pid_ argument is the process ID, _tep_ is the event +context. + +The _tep_data_comm_from_pid()_ function returns the process name for a given +pid. The _pid_ argument is the process ID, _tep_ is the event context. +The returned string should not be freed, but will be freed when the _tep_ +handler is closed. + +The _tep_data_pid_from_comm()_ function returns a pid for a given process name. +The _comm_ argument is the process name, _tep_ is the event context. +The argument _next_ is the cmdline structure to search for the next pid. +As there may be more than one pid for a given process, the result of this call +can be passed back into a recurring call in the _next_ parameter, to search for +the next pid. If _next_ is NULL, it will return the first pid associated with +the _comm_. The function performs a linear search, so it may be slow. + +The _tep_cmdline_pid()_ function returns the pid associated with a given +_cmdline_. The _tep_ argument is the event context. + +RETURN VALUE +------------ +_tep_register_comm()_ function returns 0 on success. In case of an error -1 is +returned and errno is set to indicate the cause of the problem: ENOMEM, if there +is not enough memory to duplicate the _comm_ or EEXIST if a mapping for this +_pid_ is already registered. + +_tep_override_comm()_ function returns 0 on success. In case of an error -1 is +returned and errno is set to indicate the cause of the problem: ENOMEM, if there +is not enough memory to duplicate the _comm_. + +_tep_is_pid_registered()_ function returns true if the _pid_ has a process name +mapped to it, false otherwise. + +_tep_data_comm_from_pid()_ function returns the process name as string, or the +string "<...>" if there is no mapping for the given pid. + +_tep_data_pid_from_comm()_ function returns a pointer to a struct cmdline, that +holds a pid for a given process, or NULL if none is found. This result can be +passed back into a recurring call as the _next_ parameter of the function. + +_tep_cmdline_pid()_ functions returns the pid for the give cmdline. If _cmdline_ + is NULL, then -1 is returned. + +EXAMPLE +------- +The following example registers pid for command "ls", in context of event _tep_ +and performs various searches for pid / process name mappings: +[source,c] +-- +#include <event-parse.h> +... +int ret; +int ls_pid = 1021; +struct tep_handle *tep = tep_alloc(); +... + ret = tep_register_comm(tep, "ls", ls_pid); + if (ret != 0 && errno == EEXIST) + ret = tep_override_comm(tep, "ls", ls_pid); + if (ret != 0) { + /* Failed to register pid / command mapping */ + } +... + if (tep_is_pid_registered(tep, ls_pid) == 0) { + /* Command mapping for ls_pid is not registered */ + } +... + const char *comm = tep_data_comm_from_pid(tep, ls_pid); + if (comm) { + /* Found process name for ls_pid */ + } +... + int pid; + struct cmdline *cmd = tep_data_pid_from_comm(tep, "ls", NULL); + while (cmd) { + pid = tep_cmdline_pid(tep, cmd); + /* Found pid for process "ls" */ + cmd = tep_data_pid_from_comm(tep, "ls", cmd); + } +-- +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)_ + +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-cpus.txt b/tools/lib/traceevent/Documentation/libtraceevent-cpus.txt new file mode 100644 index 000000000..5ad70e43b --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-cpus.txt @@ -0,0 +1,77 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_cpus, tep_set_cpus - Get / set the number of CPUs, which have a tracing +buffer representing it. Note, the buffer may be empty. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_get_cpus*(struct tep_handle pass:[*]_tep_); +void *tep_set_cpus*(struct tep_handle pass:[*]_tep_, int _cpus_); +-- + +DESCRIPTION +----------- +The _tep_get_cpus()_ function gets the number of CPUs, which have a tracing +buffer representing it. The _tep_ argument is trace event parser context. + +The _tep_set_cpus()_ function sets the number of CPUs, which have a tracing +buffer representing it. The _tep_ argument is trace event parser context. +The _cpu_ argument is the number of CPUs with tracing data. + +RETURN VALUE +------------ +The _tep_get_cpus()_ functions returns the number of CPUs, which have tracing +data recorded. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + tep_set_cpus(tep, 5); +... + printf("We have tracing data for %d CPUs", tep_get_cpus(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)_ + +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-endian_read.txt b/tools/lib/traceevent/Documentation/libtraceevent-endian_read.txt new file mode 100644 index 000000000..e64851b6e --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-endian_read.txt @@ -0,0 +1,78 @@ +libtraceevent(3) +================ + +NAME +---- +tep_read_number - Reads a number from raw data. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +unsigned long long *tep_read_number*(struct tep_handle pass:[*]_tep_, const void pass:[*]_ptr_, int _size_); +-- + +DESCRIPTION +----------- +The _tep_read_number()_ function reads an integer from raw data, taking into +account the endianness of the raw data and the current host. The _tep_ argument +is the trace event parser context. The _ptr_ is a pointer to the raw data, where +the integer is, and the _size_ is the size of the integer. + +RETURN VALUE +------------ +The _tep_read_number()_ function returns the integer in the byte order of +the current host. In case of an error, 0 is returned. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +void process_record(struct tep_record *record) +{ + int offset = 24; + int data = tep_read_number(tep, record->data + offset, 4); + + /* Read the 4 bytes at the offset 24 of data as an integer */ +} +... +-- + +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)_ + +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-event_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_find.txt new file mode 100644 index 000000000..7bc062c9f --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-event_find.txt @@ -0,0 +1,103 @@ +libtraceevent(3) +================ + +NAME +---- +tep_find_event,tep_find_event_by_name,tep_find_event_by_record - +Find events by given key. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_event pass:[*]*tep_find_event*(struct tep_handle pass:[*]_tep_, int _id_); +struct tep_event pass:[*]*tep_find_event_by_name*(struct tep_handle pass:[*]_tep_, const char pass:[*]_sys_, const char pass:[*]_name_); +struct tep_event pass:[*]*tep_find_event_by_record*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_record_); +-- + +DESCRIPTION +----------- +This set of functions can be used to search for an event, based on a given +criteria. All functions require a pointer to a _tep_, trace event parser +context. + +The _tep_find_event()_ function searches for an event by given event _id_. The +event ID is assigned dynamically and can be viewed in event's format file, +"ID" field. + +The tep_find_event_by_name()_ function searches for an event by given +event _name_, under the system _sys_. If the _sys_ is NULL (not specified), +the first event with _name_ is returned. + +The tep_find_event_by_record()_ function searches for an event from a given +_record_. + +RETURN VALUE +------------ +All these functions return a pointer to the found event, or NULL if there is no +such event. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct tep_event *event; + +event = tep_find_event(tep, 1857); +if (event == NULL) { + /* There is no event with ID 1857 */ +} + +event = tep_find_event_by_name(tep, "kvm", "kvm_exit"); +if (event == NULL) { + /* There is no kvm_exit event, from kvm system */ +} + +void event_from_record(struct tep_record *record) +{ + struct tep_event *event = tep_find_event_by_record(tep, record); + if (event == NULL) { + /* There is no event from given record */ + } +} +... +-- + +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)_ + +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-event_get.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_get.txt new file mode 100644 index 000000000..6525092fc --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-event_get.txt @@ -0,0 +1,99 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_event, tep_get_first_event, tep_get_events_count - Access events. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_event pass:[*]*tep_get_event*(struct tep_handle pass:[*]_tep_, int _index_); +struct tep_event pass:[*]*tep_get_first_event*(struct tep_handle pass:[*]_tep_); +int *tep_get_events_count*(struct tep_handle pass:[*]_tep_); +-- + +DESCRIPTION +----------- +The _tep_get_event()_ function returns a pointer to event at the given _index_. +The _tep_ argument is trace event parser context, the _index_ is the index of +the requested event. + +The _tep_get_first_event()_ function returns a pointer to the first event. +As events are stored in an array, this function returns the pointer to the +beginning of the array. The _tep_ argument is trace event parser context. + +The _tep_get_events_count()_ function returns the number of the events +in the array. The _tep_ argument is trace event parser context. + +RETURN VALUE +------------ +The _tep_get_event()_ returns a pointer to the event located at _index_. +NULL is returned in case of error, in case there are no events or _index_ is +out of range. + +The _tep_get_first_event()_ returns a pointer to the first event. NULL is +returned in case of error, or in case there are no events. + +The _tep_get_events_count()_ returns the number of the events. 0 is +returned in case of error, or in case there are no events. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +int i,count = tep_get_events_count(tep); +struct tep_event *event, *events = tep_get_first_event(tep); + +if (events == NULL) { + /* There are no events */ +} else { + for (i = 0; i < count; i++) { + event = (events+i); + /* process events[i] */ + } + + /* Get the last event */ + event = tep_get_event(tep, count-1); +} +-- + +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)_ + +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-event_list.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_list.txt new file mode 100644 index 000000000..fba350e5a --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-event_list.txt @@ -0,0 +1,122 @@ +libtraceevent(3) +================ + +NAME +---- +tep_list_events, tep_list_events_copy - +Get list of events, sorted by given criteria. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_event_sort_type* { + _TEP_EVENT_SORT_ID_, + _TEP_EVENT_SORT_NAME_, + _TEP_EVENT_SORT_SYSTEM_, +}; + +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_); +-- + +DESCRIPTION +----------- +The _tep_list_events()_ function returns an array of pointers to the events, +sorted by the _sort_type_ criteria. The last element of the array is NULL. +The returned memory must not be freed, it is managed by the library. +The function is not thread safe. The _tep_ argument is trace event parser +context. The _sort_type_ argument is the required sort criteria: +[verse] +-- + _TEP_EVENT_SORT_ID_ - sort by the event ID. + _TEP_EVENT_SORT_NAME_ - sort by the event (name, system, id) triplet. + _TEP_EVENT_SORT_SYSTEM_ - sort by the event (system, name, id) triplet. +-- + +The _tep_list_events_copy()_ is a thread safe version of _tep_list_events()_. +It has the same behavior, but the returned array is allocated internally and +must be freed by the caller. Note that the content of the array must not be +freed (see the EXAMPLE below). + +RETURN VALUE +------------ +The _tep_list_events()_ function returns an array of pointers to events. +In case of an error, NULL is returned. The returned array must not be freed, +it is managed by the library. + +The _tep_list_events_copy()_ function returns an array of pointers to events. +In case of an error, NULL is returned. The returned array must be freed by +the caller. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +int i; +struct tep_event_format **events; + +i=0; +events = tep_list_events(tep, TEP_EVENT_SORT_ID); +if (events == NULL) { + /* Failed to get the events, sorted by ID */ +} else { + while(events[i]) { + /* walk through the list of the events, sorted by ID */ + i++; + } +} + +i=0; +events = tep_list_events_copy(tep, TEP_EVENT_SORT_NAME); +if (events == NULL) { + /* Failed to get the events, sorted by name */ +} else { + while(events[i]) { + /* walk through the list of the events, sorted by name */ + i++; + } + free(events); +} + +... +-- + +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)_ + +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-event_print.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt new file mode 100644 index 000000000..2c6a61811 --- /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-field_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_find.txt new file mode 100644 index 000000000..0896af5b9 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-field_find.txt @@ -0,0 +1,118 @@ +libtraceevent(3) +================ + +NAME +---- +tep_find_common_field, tep_find_field, tep_find_any_field - +Search for a field in an event. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_format_field pass:[*]*tep_find_common_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_); +struct tep_format_field pass:[*]*tep_find_field*(struct tep_event_ormat pass:[*]_event_, const char pass:[*]_name_); +struct tep_format_field pass:[*]*tep_find_any_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_); +-- + +DESCRIPTION +----------- +These functions search for a field with given name in an event. The field +returned can be used to find the field content from within a data record. + +The _tep_find_common_field()_ function searches for a common field with _name_ +in the _event_. + +The _tep_find_field()_ function searches for an event specific field with +_name_ in the _event_. + +The _tep_find_any_field()_ function searches for any field with _name_ in the +_event_. + +RETURN VALUE +------------ +The _tep_find_common_field(), _tep_find_field()_ and _tep_find_any_field()_ +functions return a pointer to the found field, or NULL in case there is no field +with the requested name. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +void get_htimer_info(struct tep_handle *tep, struct tep_record *record) +{ + struct tep_format_field *field; + struct tep_event *event; + long long softexpires; + int mode; + int pid; + + event = tep_find_event_by_name(tep, "timer", "hrtimer_start"); + + field = tep_find_common_field(event, "common_pid"); + if (field == NULL) { + /* Cannot find "common_pid" field in the event */ + } else { + /* Get pid from the data record */ + pid = tep_read_number(tep, record->data + field->offset, + field->size); + } + + field = tep_find_field(event, "softexpires"); + if (field == NULL) { + /* Cannot find "softexpires" event specific field in the event */ + } else { + /* Get softexpires parameter from the data record */ + softexpires = tep_read_number(tep, record->data + field->offset, + field->size); + } + + field = tep_find_any_field(event, "mode"); + if (field == NULL) { + /* Cannot find "mode" field in the event */ + } else + { + /* Get mode parameter from the data record */ + mode = tep_read_number(tep, record->data + field->offset, + field->size); + } +} +... +-- + +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)_ + +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-field_get_val.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_get_val.txt new file mode 100644 index 000000000..6324f0d48 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-field_get_val.txt @@ -0,0 +1,122 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_any_field_val, tep_get_common_field_val, tep_get_field_val, +tep_get_field_raw - Get value of a field. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* +*#include <trace-seq.h>* + +int *tep_get_any_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); +int *tep_get_common_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); +int *tep_get_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); +void pass:[*]*tep_get_field_raw*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int pass:[*]_len_, int _err_); +-- + +DESCRIPTION +----------- +These functions can be used to find a field and retrieve its value. + +The _tep_get_any_field_val()_ function searches in the _record_ for a field +with _name_, part of the _event_. If the field is found, its value is stored in +_val_. If there is an error and _err_ is not zero, then an error string is +written into _s_. + +The _tep_get_common_field_val()_ function does the same as +_tep_get_any_field_val()_, but searches only in the common fields. This works +for any event as all events include the common fields. + +The _tep_get_field_val()_ function does the same as _tep_get_any_field_val()_, +but searches only in the event specific fields. + +The _tep_get_field_raw()_ function searches in the _record_ for a field with +_name_, part of the _event_. If the field is found, a pointer to where the field +exists in the record's raw data is returned. The size of the data is stored in +_len_. If there is an error and _err_ is not zero, then an error string is +written into _s_. + +RETURN VALUE +------------ +The _tep_get_any_field_val()_, _tep_get_common_field_val()_ and +_tep_get_field_val()_ functions return 0 on success, or -1 in case of an error. + +The _tep_get_field_raw()_ function returns a pointer to field's raw data, and +places the length of this data in _len_. In case of an error NULL is returned. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct tep_event *event = tep_find_event_by_name(tep, "kvm", "kvm_exit"); +... +void process_record(struct tep_record *record) +{ + int len; + char *comm; + struct tep_event_format *event; + unsigned long long val; + + event = tep_find_event_by_record(pevent, record); + if (event != NULL) { + if (tep_get_common_field_val(NULL, event, "common_type", + record, &val, 0) == 0) { + /* Got the value of common type field */ + } + if (tep_get_field_val(NULL, event, "pid", record, &val, 0) == 0) { + /* Got the value of pid specific field */ + } + comm = tep_get_field_raw(NULL, event, "comm", record, &len, 0); + if (comm != NULL) { + /* Got a pointer to the comm event specific field */ + } + } +} +-- + +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-field_print.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_print.txt new file mode 100644 index 000000000..9a9df98ac --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-field_print.txt @@ -0,0 +1,126 @@ +libtraceevent(3) +================ + +NAME +---- +tep_print_field, tep_print_fields, tep_print_num_field, tep_print_func_field - +Print the field content. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* +*#include <trace-seq.h>* + +void *tep_print_field*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, struct tep_format_field pass:[*]_field_); +void *tep_print_fields*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, int _size_, struct tep_event pass:[*]_event_); +int *tep_print_num_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_); +int *tep_print_func_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_); +-- + +DESCRIPTION +----------- +These functions print recorded field's data, according to the field's type. + +The _tep_print_field()_ function extracts from the recorded raw _data_ value of +the _field_ and prints it into _s_, according to the field type. + +The _tep_print_fields()_ prints each field name followed by the record's field +value according to the field's type: +[verse] +-- +"field1_name=field1_value field2_name=field2_value ..." +-- +It iterates all fields of the _event_, and calls _tep_print_field()_ for each of +them. + +The _tep_print_num_field()_ function prints a numeric field with given format +string. A search is performed in the _event_ for a field with _name_. If such +field is found, its value is extracted from the _record_ and is printed in the +_s_, according to the given format string _fmt_. If the argument _err_ is +non-zero, and an error occures - it is printed in the _s_. + +The _tep_print_func_field()_ function prints a function field with given format +string. A search is performed in the _event_ for a field with _name_. If such +field is found, its value is extracted from the _record_. The value is assumed +to be a function address, and a search is perform to find the name of this +function. The function name (if found) and its address are printed in the _s_, +according to the given format string _fmt_. If the argument _err_ is non-zero, +and an error occures - it is printed in _s_. + +RETURN VALUE +------------ +The _tep_print_num_field()_ and _tep_print_func_field()_ functions return 1 +on success, -1 in case of an error or 0 if the print buffer _s_ is full. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct trace_seq seq; +trace_seq_init(&seq); +struct tep_event *event = tep_find_event_by_name(tep, "timer", "hrtimer_start"); +... +void process_record(struct tep_record *record) +{ + struct tep_format_field *field_pid = tep_find_common_field(event, "common_pid"); + + trace_seq_reset(&seq); + + /* Print the value of "common_pid" */ + tep_print_field(&seq, record->data, field_pid); + + /* Print all fields of the "hrtimer_start" event */ + tep_print_fields(&seq, record->data, record->size, event); + + /* Print the value of "expires" field with custom format string */ + tep_print_num_field(&seq, " timer expires in %llu ", event, "expires", record, 0); + + /* Print the address and the name of "function" field with custom format string */ + tep_print_func_field(&seq, " timer function is %s ", event, "function", record, 0); + } + ... +-- + +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-field_read.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_read.txt new file mode 100644 index 000000000..64e9e25d3 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-field_read.txt @@ -0,0 +1,81 @@ +libtraceevent(3) +================ + +NAME +---- +tep_read_number_field - Reads a number from raw data. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_read_number_field*(struct tep_format_field pass:[*]_field_, const void pass:[*]_data_, unsigned long long pass:[*]_value_); +-- + +DESCRIPTION +----------- +The _tep_read_number_field()_ function reads the value of the _field_ from the +raw _data_ and stores it in the _value_. The function sets the _value_ according +to the endianness of the raw data and the current machine and stores it in +_value_. + +RETURN VALUE +------------ +The _tep_read_number_field()_ function retunrs 0 in case of success, or -1 in +case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct tep_event *event = tep_find_event_by_name(tep, "timer", "hrtimer_start"); +... +void process_record(struct tep_record *record) +{ + unsigned long long pid; + struct tep_format_field *field_pid = tep_find_common_field(event, "common_pid"); + + if (tep_read_number_field(field_pid, record->data, &pid) != 0) { + /* Failed to get "common_pid" value */ + } +} +... +-- +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)_ + +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-fields.txt b/tools/lib/traceevent/Documentation/libtraceevent-fields.txt new file mode 100644 index 000000000..1ccb531d5 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-fields.txt @@ -0,0 +1,105 @@ +libtraceevent(3) +================ + +NAME +---- +tep_event_common_fields, tep_event_fields - Get a list of fields for an event. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_format_field pass:[*]pass:[*]*tep_event_common_fields*(struct tep_event pass:[*]_event_); +struct tep_format_field pass:[*]pass:[*]*tep_event_fields*(struct tep_event pass:[*]_event_); +-- + +DESCRIPTION +----------- +The _tep_event_common_fields()_ function returns an array of pointers to common +fields for the _event_. The array is allocated in the function and must be freed +by free(). The last element of the array is NULL. + +The _tep_event_fields()_ function returns an array of pointers to event specific +fields for the _event_. The array is allocated in the function and must be freed +by free(). The last element of the array is NULL. + +RETURN VALUE +------------ +Both _tep_event_common_fields()_ and _tep_event_fields()_ functions return +an array of pointers to tep_format_field structures in case of success, or +NULL in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +int i; +struct tep_format_field **fields; +struct tep_event *event = tep_find_event_by_name(tep, "kvm", "kvm_exit"); +if (event != NULL) { + fields = tep_event_common_fields(event); + if (fields != NULL) { + i = 0; + while (fields[i]) { + /* + walk through the list of the common fields + of the kvm_exit event + */ + i++; + } + free(fields); + } + fields = tep_event_fields(event); + if (fields != NULL) { + i = 0; + while (fields[i]) { + /* + walk through the list of the event specific + fields of the kvm_exit event + */ + i++; + } + free(fields); + } +} +... +-- + +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)_ + +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-file_endian.txt b/tools/lib/traceevent/Documentation/libtraceevent-file_endian.txt new file mode 100644 index 000000000..f401ad311 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-file_endian.txt @@ -0,0 +1,91 @@ +libtraceevent(3) +================ + +NAME +---- +tep_is_file_bigendian, tep_set_file_bigendian - Get / set the endianness of the +raw data being accessed by the tep handler. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_endian* { + TEP_LITTLE_ENDIAN = 0, + TEP_BIG_ENDIAN +}; + +bool *tep_is_file_bigendian*(struct tep_handle pass:[*]_tep_); +void *tep_set_file_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_); + +-- +DESCRIPTION +----------- +The _tep_is_file_bigendian()_ function gets the endianness of the raw data, +being accessed by the tep handler. The _tep_ argument is trace event parser +context. + +The _tep_set_file_bigendian()_ function sets the endianness of raw data being +accessed by the tep handler. The _tep_ argument is trace event parser context. +[verse] +-- +The _endian_ argument is the endianness: + _TEP_LITTLE_ENDIAN_ - the raw data is in little endian format, + _TEP_BIG_ENDIAN_ - the raw data is in big endian format. +-- +RETURN VALUE +------------ +The _tep_is_file_bigendian()_ function returns true if the data is in bigendian +format, false otherwise. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + tep_set_file_bigendian(tep, TEP_LITTLE_ENDIAN); +... + if (tep_is_file_bigendian(tep)) { + /* The raw data is in big endian */ + } else { + /* The raw data is in little endian */ + } +-- + +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)_ + +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-filter.txt b/tools/lib/traceevent/Documentation/libtraceevent-filter.txt new file mode 100644 index 000000000..4a9962d8c --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-filter.txt @@ -0,0 +1,209 @@ +libtraceevent(3) +================ + +NAME +---- +tep_filter_alloc, tep_filter_free, tep_filter_reset, tep_filter_make_string, +tep_filter_copy, tep_filter_compare, tep_filter_match, tep_event_filtered, +tep_filter_remove_event, tep_filter_strerror, tep_filter_add_filter_str - +Event filter related APIs. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_event_filter pass:[*]*tep_filter_alloc*(struct tep_handle pass:[*]_tep_); +void *tep_filter_free*(struct tep_event_filter pass:[*]_filter_); +void *tep_filter_reset*(struct tep_event_filter pass:[*]_filter_); +enum tep_errno *tep_filter_add_filter_str*(struct tep_event_filter pass:[*]_filter_, const char pass:[*]_filter_str_); +int *tep_event_filtered*(struct tep_event_filter pass:[*]_filter_, int _event_id_); +int *tep_filter_remove_event*(struct tep_event_filter pass:[*]_filter_, int _event_id_); +enum tep_errno *tep_filter_match*(struct tep_event_filter pass:[*]_filter_, struct tep_record pass:[*]_record_); +int *tep_filter_copy*(struct tep_event_filter pass:[*]_dest_, struct tep_event_filter pass:[*]_source_); +int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_); +char pass:[*]*tep_filter_make_string*(struct tep_event_filter pass:[*]_filter_, int _event_id_); +int *tep_filter_strerror*(struct tep_event_filter pass:[*]_filter_, enum tep_errno _err_, char pass:[*]buf, size_t _buflen_); +-- + +DESCRIPTION +----------- +Filters can be attached to traced events. They can be used to filter out various +events when outputting them. Each event can be filtered based on its parameters, +described in the event's format file. This set of functions can be used to +create, delete, modify and attach event filters. + +The _tep_filter_alloc()_ function creates a new event filter. The _tep_ argument +is the trace event parser context. + +The _tep_filter_free()_ function frees an event filter and all resources that it +had used. + +The _tep_filter_reset()_ function removes all rules from an event filter and +resets it. + +The _tep_filter_add_filter_str()_ function adds a new rule to the _filter_. The +_filter_str_ argument is the filter string, that contains the rule. + +The _tep_event_filtered()_ function checks if the event with _event_id_ has +_filter_. + +The _tep_filter_remove_event()_ function removes a _filter_ for an event with +_event_id_. + +The _tep_filter_match()_ function tests if a _record_ matches given _filter_. + +The _tep_filter_copy()_ function copies a _source_ filter into a _dest_ filter. + +The _tep_filter_compare()_ function compares two filers - _filter1_ and _filter2_. + +The _tep_filter_make_string()_ function constructs a string, displaying +the _filter_ contents for given _event_id_. + +The _tep_filter_strerror()_ function copies the _filter_ error buffer into the +given _buf_ with the size _buflen_. If the error buffer is empty, in the _buf_ +is copied a string, describing the error _err_. + +RETURN VALUE +------------ +The _tep_filter_alloc()_ function returns a pointer to the newly created event +filter, or NULL in case of an error. + +The _tep_filter_add_filter_str()_ function returns 0 if the rule was +successfully added or a negative error code. Use _tep_filter_strerror()_ to see +actual error message in case of an error. + +The _tep_event_filtered()_ function returns 1 if the filter is found for given +event, or 0 otherwise. + +The _tep_filter_remove_event()_ function returns 1 if the vent was removed, or +0 if the event was not found. + +The _tep_filter_match()_ function returns _tep_errno_, according to the result: +[verse] +-- +_pass:[TEP_ERRNO__FILTER_MATCH]_ - filter found for event, the record matches. +_pass:[TEP_ERRNO__FILTER_MISS]_ - filter found for event, the record does not match. +_pass:[TEP_ERRNO__FILTER_NOT_FOUND]_ - no filter found for record's event. +_pass:[TEP_ERRNO__NO_FILTER]_ - no rules in the filter. +-- +or any other _tep_errno_, if an error occurred during the test. + +The _tep_filter_copy()_ function returns 0 on success or -1 if not all rules + were copied. + +The _tep_filter_compare()_ function returns 1 if the two filters hold the same +content, or 0 if they do not. + +The _tep_filter_make_string()_ function returns a string, which must be freed +with free(), or NULL in case of an error. + +The _tep_filter_strerror()_ function returns 0 if message was filled +successfully, or -1 in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char errstr[200]; +int ret; + +struct tep_event_filter *filter = tep_filter_alloc(tep); +struct tep_event_filter *filter1 = tep_filter_alloc(tep); +ret = tep_filter_add_filter_str(filter, "sched/sched_wakeup:target_cpu==1"); +if(ret < 0) { + tep_filter_strerror(filter, ret, errstr, sizeof(errstr)); + /* Failed to add a new rule to the filter, the error string is in errstr */ +} +if (tep_filter_copy(filter1, filter) != 0) { + /* Failed to copy filter in filter1 */ +} +... +if (tep_filter_compare(filter, filter1) != 1) { + /* Both filters are different */ +} +... +void process_record(struct tep_handle *tep, struct tep_record *record) +{ + struct tep_event *event; + char *fstring; + + event = tep_find_event_by_record(tep, record); + + if (tep_event_filtered(filter, event->id) == 1) { + /* The event has filter */ + fstring = tep_filter_make_string(filter, event->id); + if (fstring != NULL) { + /* The filter for the event is in fstring */ + free(fstring); + } + } + + switch (tep_filter_match(filter, record)) { + case TEP_ERRNO__FILTER_MATCH: + /* The filter matches the record */ + break; + case TEP_ERRNO__FILTER_MISS: + /* The filter does not match the record */ + break; + case TEP_ERRNO__FILTER_NOT_FOUND: + /* No filter found for record's event */ + break; + case TEP_ERRNO__NO_FILTER: + /* There are no rules in the filter */ + break + default: + /* An error occurred during the test */ + break; + } + + if (tep_filter_remove_event(filter, event->id) == 1) { + /* The event was removed from the filter */ + } +} + +... +tep_filter_reset(filter); +... +tep_filter_free(filter); +tep_filter_free(filter1); +... +-- + +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)_ + +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 new file mode 100644 index 000000000..f6aca0df2 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt @@ -0,0 +1,183 @@ +libtraceevent(3) +================ + +NAME +---- +tep_find_function, tep_find_function_address, tep_set_function_resolver, +tep_reset_function_resolver, tep_register_function, tep_register_print_string - +function related tep APIs + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +typedef char pass:[*](*tep_func_resolver_t*)(void pass:[*]_priv_, unsigned long long pass:[*]_addrp_, char pass:[**]_modp_); +int *tep_set_function_resolver*(struct tep_handle pass:[*]_tep_, tep_func_resolver_t pass:[*]_func_, void pass:[*]_priv_); +void *tep_reset_function_resolver*(struct tep_handle pass:[*]_tep_); +const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); +unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); +int *tep_register_function*(struct tep_handle pass:[*]_tep_, char pass:[*]_name_, unsigned long long _addr_, char pass:[*]_mod_); +int *tep_register_print_string*(struct tep_handle pass:[*]_tep_, const char pass:[*]_fmt_, unsigned long long _addr_); +-- + +DESCRIPTION +----------- +Some tools may have already a way to resolve the kernel functions. These APIs +allow them to keep using it instead of duplicating all the entries inside. + +The _tep_func_resolver_t_ type is the prototype of the alternative kernel +functions resolver. This function receives a pointer to its custom context +(set with the _tep_set_function_resolver()_ call ) and the address of a kernel +function, which has to be resolved. In case of success, it should return +the name of the function and its module (if any) in _modp_. + +The _tep_set_function_resolver()_ function registers _func_ as an alternative +kernel functions resolver. The _tep_ argument is trace event parser context. +The _priv_ argument is a custom context of the _func_ function. The function +resolver is used by the APIs _tep_find_function()_, +_tep_find_function_address()_, and _tep_print_func_field()_ to resolve +a function address to a function name. + +The _tep_reset_function_resolver()_ function resets the kernel functions +resolver to the default function. The _tep_ argument is trace event parser +context. + + +These APIs can be used to find function name and start address, by given +address. The given address does not have to be exact, it will select +the function that would contain it. + +The _tep_find_function()_ function returns the function name, which contains the +given address _addr_. The _tep_ argument is the trace event parser context. + +The _tep_find_function_address()_ function returns the function start address, +by given address _addr_. The _addr_ does not have to be exact, it will select +the function that would contain it. The _tep_ argument is the trace event +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 "%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 _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 +address are passed to certain events. The "%s" in the event's format field +which has an address needs to know what string would be at that address. The +tep_register_print_string() supplies the parsing with the mapping between kernel +addresses and those strings. The _tep_ argument is the trace event parser +context. The _fmt_ is the string to register, it is copied internally. +The _addr_ is the address the string was located at. + + +RETURN VALUE +------------ +The _tep_set_function_resolver()_ function returns 0 in case of success, or -1 +in case of an error. + +The _tep_find_function()_ function returns the function name, or NULL in case +it cannot be found. + +The _tep_find_function_address()_ function returns the function start address, +or 0 in case it cannot be found. + +The _tep_register_function()_ function returns 0 in case of success. In case of +an error -1 is returned, and errno is set to the appropriate error number. + +The _tep_register_print_string()_ function returns 0 in case of success. In case +of an error -1 is returned, and errno is set to the appropriate error number. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char *my_resolve_kernel_addr(void *context, + unsigned long long *addrp, char **modp) +{ + struct db *function_database = context; + struct symbol *sym = sql_lookup(function_database, *addrp); + + if (!sym) + return NULL; + + *modp = sym->module_name; + return sym->name; +} + +void show_function( unsigned long long addr) +{ + unsigned long long fstart; + const char *fname; + + if (tep_set_function_resolver(tep, my_resolve_kernel_addr, + function_database) != 0) { + /* failed to register my_resolve_kernel_addr */ + } + + /* These APIs use my_resolve_kernel_addr() to resolve the addr */ + fname = tep_find_function(tep, addr); + fstart = tep_find_function_address(tep, addr); + + /* + addr is in function named fname, starting at fstart address, + at offset (addr - fstart) + */ + + tep_reset_function_resolver(tep); + +} +... + if (tep_register_function(tep, "kvm_exit", + (unsigned long long) 0x12345678, "kvm") != 0) { + /* Failed to register kvm_exit address mapping */ + } +... + if (tep_register_print_string(tep, "print string", + (unsigned long long) 0x87654321, NULL) != 0) { + /* Failed to register "print string" address mapping */ + } +... +-- + +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)_ + +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_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-func_find.txt new file mode 100644 index 000000000..04840e244 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-func_find.txt @@ -0,0 +1,88 @@ +libtraceevent(3) +================ + +NAME +---- +tep_find_function,tep_find_function_address - Find function name / start address. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); +unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); +-- + +DESCRIPTION +----------- +These functions can be used to find function name and start address, by given +address. The given address does not have to be exact, it will select the function +that would contain it. + +The _tep_find_function()_ function returns the function name, which contains the +given address _addr_. The _tep_ argument is the trace event parser context. + +The _tep_find_function_address()_ function returns the function start address, +by given address _addr_. The _addr_ does not have to be exact, it will select the +function that would contain it. The _tep_ argument is the trace event parser context. + +RETURN VALUE +------------ +The _tep_find_function()_ function returns the function name, or NULL in case +it cannot be found. + +The _tep_find_function_address()_ function returns the function start address, +or 0 in case it cannot be found. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +void show_function( unsigned long long addr) +{ + const char *fname = tep_find_function(tep, addr); + unsigned long long fstart = tep_find_function_address(tep, addr); + + /* addr is in function named fname, starting at fstart address, at offset (addr - fstart) */ +} +... +-- + +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)_ + +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-handle.txt b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt new file mode 100644 index 000000000..45b20172e --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt @@ -0,0 +1,101 @@ +libtraceevent(3) +================ + +NAME +---- +tep_alloc, tep_free,tep_ref, tep_unref,tep_get_ref - Create, destroy, manage +references of trace event parser context. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +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_get_ref*(struct tep_handle pass:[*]_tep_); +-- + +DESCRIPTION +----------- +These are the main functions to create and destroy tep_handle - the main +structure, representing the trace event parser context. This context is used as +the input parameter of most library APIs. + +The _tep_alloc()_ function allocates and initializes the tep context. + +The _tep_free()_ function will decrement the reference of the _tep_ handler. +When there is no more references, then it will free the handler, as well +as clean up all its resources that it had used. The argument _tep_ is +the pointer to the trace event parser context. + +The _tep_ref()_ function adds a reference to the _tep_ handler. + +The _tep_unref()_ function removes a reference from the _tep_ handler. When +the last reference is removed, the _tep_ is destroyed, and all resources that +it had used are cleaned up. + +The _tep_ref_get()_ functions gets the current references of the _tep_ handler. + +RETURN VALUE +------------ +_tep_alloc()_ returns a pointer to a newly created tep_handle structure. +NULL is returned in case there is not enough free memory to allocate it. + +_tep_ref_get()_ returns the current references of _tep_. +If _tep_ is NULL, 0 is returned. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> + +... +struct tep_handle *tep = tep_alloc(); +... +int ref = tep_get_ref(tep); +tep_ref(tep); +if ( (ref+1) != tep_get_ref(tep)) { + /* Something wrong happened, the counter is not incremented by 1 */ +} +tep_unref(tep); +... +tep_free(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)_ + +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-header_page.txt b/tools/lib/traceevent/Documentation/libtraceevent-header_page.txt new file mode 100644 index 000000000..615d117dc --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-header_page.txt @@ -0,0 +1,102 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_header_page_size, tep_get_header_timestamp_size, tep_is_old_format - +Get the data stored in the header page, in kernel context. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +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_); +-- +DESCRIPTION +----------- +These functions retrieve information from kernel context, stored in tracefs +events/header_page. Old kernels do not have header page info, so default values +from user space context are used. + +The _tep_get_header_page_size()_ function returns the size of a long integer, +in kernel context. The _tep_ argument is trace event parser context. +This information is retrieved from tracefs events/header_page, "commit" field. + +The _tep_get_header_timestamp_size()_ function returns the size of timestamps, +in kernel context. The _tep_ argument is trace event parser context. This +information is retrieved from tracefs events/header_page, "timestamp" field. + +The _tep_is_old_format()_ function returns true if the kernel predates +the addition of events/header_page, otherwise it returns false. + +RETURN VALUE +------------ +The _tep_get_header_page_size()_ function returns the size of a long integer, +in bytes. + +The _tep_get_header_timestamp_size()_ function returns the size of timestamps, +in bytes. + +The _tep_is_old_format()_ function returns true, if an old kernel is used to +generate the tracing data, which has no event/header_page. If the kernel is new, +or _tep_ is NULL, false is returned. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + int longsize; + int timesize; + bool old; + + longsize = tep_get_header_page_size(tep); + timesize = tep_get_header_timestamp_size(tep); + old = tep_is_old_format(tep); + + printf ("%s kernel is used to generate the tracing data.\n", + old?"Old":"New"); + printf("The size of a long integer is %d bytes.\n", longsize); + printf("The timestamps size is %d bytes.\n", timesize); +... +-- + +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)_ + +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-host_endian.txt b/tools/lib/traceevent/Documentation/libtraceevent-host_endian.txt new file mode 100644 index 000000000..d5d375eb8 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-host_endian.txt @@ -0,0 +1,104 @@ +libtraceevent(3) +================ + +NAME +---- +tep_is_bigendian, tep_is_local_bigendian, tep_set_local_bigendian - Get / set +the endianness of the local machine. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_endian* { + TEP_LITTLE_ENDIAN = 0, + TEP_BIG_ENDIAN +}; + +int *tep_is_bigendian*(void); +bool *tep_is_local_bigendian*(struct tep_handle pass:[*]_tep_); +void *tep_set_local_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_); +-- + +DESCRIPTION +----------- + +The _tep_is_bigendian()_ gets the endianness of the machine, executing +the function. + +The _tep_is_local_bigendian()_ function gets the endianness of the local +machine, saved in the _tep_ handler. The _tep_ argument is the trace event +parser context. This API is a bit faster than _tep_is_bigendian()_, as it +returns cached endianness of the local machine instead of checking it each time. + +The _tep_set_local_bigendian()_ function sets the endianness of the local +machine in the _tep_ handler. The _tep_ argument is trace event parser context. +The _endian_ argument is the endianness: +[verse] +-- + _TEP_LITTLE_ENDIAN_ - the machine is little endian, + _TEP_BIG_ENDIAN_ - the machine is big endian. +-- + +RETURN VALUE +------------ +The _tep_is_bigendian()_ function returns non zero if the endianness of the +machine, executing the code, is big endian and zero otherwise. + +The _tep_is_local_bigendian()_ function returns true, if the endianness of the +local machine, saved in the _tep_ handler, is big endian, or false otherwise. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + if (tep_is_bigendian()) + tep_set_local_bigendian(tep, TEP_BIG_ENDIAN); + else + tep_set_local_bigendian(tep, TEP_LITTLE_ENDIAN); +... + if (tep_is_local_bigendian(tep)) + printf("This machine you are running on is bigendian\n"); + else + printf("This machine you are running on is little endian\n"); + +-- + +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)_ + +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-long_size.txt b/tools/lib/traceevent/Documentation/libtraceevent-long_size.txt new file mode 100644 index 000000000..01d78ea25 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-long_size.txt @@ -0,0 +1,78 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_long_size, tep_set_long_size - Get / set the size of a long integer on +the machine, where the trace is generated, in bytes + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_get_long_size*(strucqt tep_handle pass:[*]_tep_); +void *tep_set_long_size*(struct tep_handle pass:[*]_tep_, int _long_size_); +-- + +DESCRIPTION +----------- +The _tep_get_long_size()_ function returns the size of a long integer on the machine, +where the trace is generated. The _tep_ argument is trace event parser context. + +The _tep_set_long_size()_ function sets the size of a long integer on the machine, +where the trace is generated. The _tep_ argument is trace event parser context. +The _long_size_ is the size of a long integer, in bytes. + +RETURN VALUE +------------ +The _tep_get_long_size()_ function returns the size of a long integer on the machine, +where the trace is generated, in bytes. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +tep_set_long_size(tep, 4); +... +int long_size = tep_get_long_size(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)_ + +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-page_size.txt b/tools/lib/traceevent/Documentation/libtraceevent-page_size.txt new file mode 100644 index 000000000..452c0cfa1 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-page_size.txt @@ -0,0 +1,82 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_page_size, tep_set_page_size - Get / set the size of a memory page on +the machine, where the trace is generated + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_get_page_size*(struct tep_handle pass:[*]_tep_); +void *tep_set_page_size*(struct tep_handle pass:[*]_tep_, int _page_size_); +-- + +DESCRIPTION +----------- +The _tep_get_page_size()_ function returns the size of a memory page on +the machine, where the trace is generated. The _tep_ argument is trace +event parser context. + +The _tep_set_page_size()_ function stores in the _tep_ context the size of a +memory page on the machine, where the trace is generated. +The _tep_ argument is trace event parser context. +The _page_size_ argument is the size of a memory page, in bytes. + +RETURN VALUE +------------ +The _tep_get_page_size()_ function returns size of the memory page, in bytes. + +EXAMPLE +------- +[source,c] +-- +#include <unistd.h> +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + int page_size = getpagesize(); + + tep_set_page_size(tep, page_size); + + printf("The page size for this machine is %d\n", tep_get_page_size(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)_ + +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-parse_event.txt b/tools/lib/traceevent/Documentation/libtraceevent-parse_event.txt new file mode 100644 index 000000000..f248114ca --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-parse_event.txt @@ -0,0 +1,90 @@ +libtraceevent(3) +================ + +NAME +---- +tep_parse_event, tep_parse_format - Parse the event format information + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum tep_errno *tep_parse_event*(struct tep_handle pass:[*]_tep_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_); +enum tep_errno *tep_parse_format*(struct tep_handle pass:[*]_tep_, struct tep_event pass:[*]pass:[*]_eventp_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_); +-- + +DESCRIPTION +----------- +The _tep_parse_event()_ function parses the event format and creates an event +structure to quickly parse raw data for a given event. The _tep_ argument is +the trace event parser context. The created event structure is stored in the +_tep_ context. The _buf_ argument is a buffer with _size_, where the event +format data is. The event format data can be taken from +tracefs/events/.../.../format files. The _sys_ argument is the system of +the event. + +The _tep_parse_format()_ function does the same as _tep_parse_event()_. The only +difference is in the extra _eventp_ argument, where the newly created event +structure is returned. + +RETURN VALUE +------------ +Both _tep_parse_event()_ and _tep_parse_format()_ functions return 0 on success, +or TEP_ERRNO__... in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char *buf; +int size; +struct tep_event *event = NULL; +buf = read_file("/sys/kernel/tracing/events/ftrace/print/format", &size); +if (tep_parse_event(tep, buf, size, "ftrace") != 0) { + /* Failed to parse the ftrace print format */ +} + +if (tep_parse_format(tep, &event, buf, size, "ftrace") != 0) { + /* Failed to parse the ftrace print format */ +} +... +-- + +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)_ + +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-parse_head.txt b/tools/lib/traceevent/Documentation/libtraceevent-parse_head.txt new file mode 100644 index 000000000..c90f16c7d --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-parse_head.txt @@ -0,0 +1,82 @@ +libtraceevent(3) +================ + +NAME +---- +tep_parse_header_page - Parses the data stored in the header page. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_parse_header_page*(struct tep_handle pass:[*]_tep_, char pass:[*]_buf_, unsigned long _size_, int _long_size_); +-- + +DESCRIPTION +----------- +The _tep_parse_header_page()_ function parses the header page data from _buf_, +and initializes the _tep_, trace event parser context, with it. The buffer +_buf_ is with _size_, and is supposed to be copied from +tracefs/events/header_page. + +Some old kernels do not have header page info, in this case the +_tep_parse_header_page()_ function can be called with _size_ equal to 0. The +_tep_ context is initialized with default values. The _long_size_ can be used in +this use case, to set the size of a long integer to be used. + +RETURN VALUE +------------ +The _tep_parse_header_page()_ function returns 0 in case of success, or -1 +in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char *buf; +int size; +buf = read_file("/sys/kernel/tracing/events/header_page", &size); +if (tep_parse_header_page(tep, buf, size, sizeof(unsigned long)) != 0) { + /* Failed to parse the header page */ +} +... +-- + +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)_ + +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-plugins.txt b/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt new file mode 100644 index 000000000..4d6394397 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt @@ -0,0 +1,122 @@ +libtraceevent(3) +================ + +NAME +---- +tep_load_plugins, tep_unload_plugins, tep_load_plugins_hook - 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_); +void *tep_load_plugins_hook*(struct tep_handle pass:[*]_tep_, const char pass:[*]_suffix_, + void (pass:[*]_load_plugin_)(struct tep_handle pass:[*]tep, + const char pass:[*]path, + const char pass:[*]name, + void pass:[*]data), + void pass:[*]_data_); +-- + +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] +-- + - Directories, specified in _tep_->plugins_dir with priority TEP_PLUGIN_FIRST + - 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_ + - Directories, specified in _tep_->plugins_dir with priority TEP_PLUGIN_LAST +-- +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. + +The _tep_load_plugins_hook_ function walks through all directories with plugins +and calls user specified _load_plugin()_ hook for each plugin file. Only files +with given _suffix_ are considered to be plugins. The _data_ is a user specified +context, passed to _load_plugin()_. Directories and the walk order are the same +as in _tep_load_plugins()_ API. + +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); +... +void print_plugin(struct tep_handle *tep, const char *path, + const char *name, void *data) +{ + pritnf("Found libtraceevent plugin %s/%s\n", path, name); +} +... +tep_load_plugins_hook(tep, ".so", print_plugin, NULL); +... +-- + +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-record_parse.txt b/tools/lib/traceevent/Documentation/libtraceevent-record_parse.txt new file mode 100644 index 000000000..e9a69116c --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-record_parse.txt @@ -0,0 +1,137 @@ +libtraceevent(3) +================ + +NAME +---- +tep_data_type, tep_data_pid,tep_data_preempt_count, tep_data_flags - +Extract common fields from a record. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *trace_flag_type* { + _TRACE_FLAG_IRQS_OFF_, + _TRACE_FLAG_IRQS_NOSUPPORT_, + _TRACE_FLAG_NEED_RESCHED_, + _TRACE_FLAG_HARDIRQ_, + _TRACE_FLAG_SOFTIRQ_, +}; + +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_); +int *tep_data_flags*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); +-- + +DESCRIPTION +----------- +This set of functions can be used to extract common fields from a record. + +The _tep_data_type()_ function gets the event id from the record _rec_. +It reads the "common_type" field. The _tep_ argument is the trace event parser +context. + +The _tep_data_pid()_ function gets the process id from the record _rec_. +It reads the "common_pid" field. The _tep_ argument is the trace event parser +context. + +The _tep_data_preempt_count()_ function gets the preemption count from the +record _rec_. It reads the "common_preempt_count" field. The _tep_ argument is +the trace event parser context. + +The _tep_data_flags()_ function gets the latency flags from the record _rec_. +It reads the "common_flags" field. The _tep_ argument is the trace event parser +context. Supported latency flags are: +[verse] +-- + _TRACE_FLAG_IRQS_OFF_, Interrupts are disabled. + _TRACE_FLAG_IRQS_NOSUPPORT_, Reading IRQ flag is not supported by the architecture. + _TRACE_FLAG_NEED_RESCHED_, Task needs rescheduling. + _TRACE_FLAG_HARDIRQ_, Hard IRQ is running. + _TRACE_FLAG_SOFTIRQ_, Soft IRQ is running. +-- + +RETURN VALUE +------------ +The _tep_data_type()_ function returns an integer, representing the event id. + +The _tep_data_pid()_ function returns an integer, representing the process id + +The _tep_data_preempt_count()_ function returns an integer, representing the +preemption count. + +The _tep_data_flags()_ function returns an integer, representing the latency +flags. Look at the _trace_flag_type_ enum for supported flags. + +All these functions in case of an error return a negative integer. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +void process_record(struct tep_record *record) +{ + int data; + + data = tep_data_type(tep, record); + if (data >= 0) { + /* Got the ID of the event */ + } + + data = tep_data_pid(tep, record); + if (data >= 0) { + /* Got the process ID */ + } + + data = tep_data_preempt_count(tep, record); + if (data >= 0) { + /* Got the preemption count */ + } + + data = tep_data_flags(tep, record); + if (data >= 0) { + /* Got the latency flags */ + } +} +... +-- + +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)_ + +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-reg_event_handler.txt b/tools/lib/traceevent/Documentation/libtraceevent-reg_event_handler.txt new file mode 100644 index 000000000..53d37d72a --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-reg_event_handler.txt @@ -0,0 +1,156 @@ +libtraceevent(3) +================ + +NAME +---- +tep_register_event_handler, tep_unregister_event_handler - Register / +unregisters a callback function to parse an event information. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_reg_handler* { + _TEP_REGISTER_SUCCESS_, + _TEP_REGISTER_SUCCESS_OVERWRITE_, +}; + +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_); + +typedef int (*pass:[*]tep_event_handler_func*)(struct trace_seq pass:[*]s, struct tep_record pass:[*]record, struct tep_event pass:[*]event, void pass:[*]context); +-- + +DESCRIPTION +----------- +The _tep_register_event_handler()_ function registers a handler function, +which is going to be called to parse the information for a given event. +The _tep_ argument is the trace event parser context. The _id_ argument is +the id of the event. The _sys_name_ argument is the name of the system, +the event belongs to. The _event_name_ argument is the name of the event. +If _id_ is >= 0, it is used to find the event, otherwise _sys_name_ and +_event_name_ are used. The _func_ is a pointer to the function, which is going +to be called to parse the event information. The _context_ argument is a pointer +to the context data, which will be passed to the _func_. If a handler function +for the same event is already registered, it will be overridden with the new +one. This mechanism allows a developer to override the parsing of a given event. +If for some reason the default print format is not sufficient, the developer +can register a function for an event to be used to parse the data instead. + +The _tep_unregister_event_handler()_ function unregisters the handler function, +previously registered with _tep_register_event_handler()_. The _tep_ argument +is the trace event parser context. The _id_, _sys_name_, _event_name_, _func_, +and _context_ are the same arguments, as when the callback function _func_ was +registered. + +The _tep_event_handler_func_ is the type of the custom event handler +function. The _s_ argument is the trace sequence, it can be used to create a +custom string, describing the event. A _record_ to get the event from is passed +as input parameter and also the _event_ - the handle to the record's event. The +_context_ is custom context, set when the custom event handler is registered. + +RETURN VALUE +------------ +The _tep_register_event_handler()_ function returns _TEP_REGISTER_SUCCESS_ +if the new handler is registered successfully or +_TEP_REGISTER_SUCCESS_OVERWRITE_ if an existing handler is overwritten. +If there is not enough memory to complete the registration, +TEP_ERRNO__MEM_ALLOC_FAILED is returned. + +The _tep_unregister_event_handler()_ function returns 0 if _func_ was removed +successful or, -1 if the event was not found. + +The _tep_event_handler_func_ should return -1 in case of an error, +or 0 otherwise. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct tep_handle *tep = tep_alloc(); +... +int timer_expire_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + trace_seq_printf(s, "hrtimer="); + + if (tep_print_num_field(s, "0x%llx", event, "timer", record, 0) == -1) + tep_print_num_field(s, "0x%llx", event, "hrtimer", record, 1); + + trace_seq_printf(s, " now="); + + tep_print_num_field(s, "%llu", event, "now", record, 1); + + tep_print_func_field(s, " function=%s", event, "function", record, 0); + + return 0; +} +... + int ret; + + ret = tep_register_event_handler(tep, -1, "timer", "hrtimer_expire_entry", + timer_expire_handler, NULL); + if (ret < 0) { + char buf[32]; + + tep_strerror(tep, ret, buf, 32) + printf("Failed to register handler for hrtimer_expire_entry: %s\n", buf); + } else { + switch (ret) { + case TEP_REGISTER_SUCCESS: + printf ("Registered handler for hrtimer_expire_entry\n"); + break; + case TEP_REGISTER_SUCCESS_OVERWRITE: + printf ("Overwrote handler for hrtimer_expire_entry\n"); + break; + } + } +... + ret = tep_unregister_event_handler(tep, -1, "timer", "hrtimer_expire_entry", + timer_expire_handler, NULL); + if ( ret ) + printf ("Failed to unregister handler for hrtimer_expire_entry\n"); + +-- + +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-reg_print_func.txt b/tools/lib/traceevent/Documentation/libtraceevent-reg_print_func.txt new file mode 100644 index 000000000..708dce91e --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-reg_print_func.txt @@ -0,0 +1,155 @@ +libtraceevent(3) +================ + +NAME +---- +tep_register_print_function,tep_unregister_print_function - +Registers / Unregisters a helper function. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_func_arg_type* { + TEP_FUNC_ARG_VOID, + TEP_FUNC_ARG_INT, + TEP_FUNC_ARG_LONG, + TEP_FUNC_ARG_STRING, + TEP_FUNC_ARG_PTR, + TEP_FUNC_ARG_MAX_TYPES +}; + +typedef unsigned long long (*pass:[*]tep_func_handler*)(struct trace_seq pass:[*]s, unsigned long long pass:[*]args); + +int *tep_register_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, enum tep_func_arg_type _ret_type_, char pass:[*]_name_, _..._); +int *tep_unregister_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, char pass:[*]_name_); +-- + +DESCRIPTION +----------- +Some events may have helper functions in the print format arguments. +This allows a plugin to dynamically create a way to process one of +these functions. + +The _tep_register_print_function()_ registers such helper function. The _tep_ +argument is the trace event parser context. The _func_ argument is a pointer +to the helper function. The _ret_type_ argument is the return type of the +helper function, value from the _tep_func_arg_type_ enum. The _name_ is the name +of the helper function, as seen in the print format arguments. The _..._ is a +variable list of _tep_func_arg_type_ enums, the _func_ function arguments. +This list must end with _TEP_FUNC_ARG_VOID_. See 'EXAMPLE' section. + +The _tep_unregister_print_function()_ unregisters a helper function, previously +registered with _tep_register_print_function()_. The _tep_ argument is the +trace event parser context. The _func_ and _name_ arguments are the same, used +when the helper function was registered. + +The _tep_func_handler_ is the type of the helper function. The _s_ argument is +the trace sequence, it can be used to create a custom string. +The _args_ is a list of arguments, defined when the helper function was +registered. + +RETURN VALUE +------------ +The _tep_register_print_function()_ function returns 0 in case of success. +In case of an error, TEP_ERRNO_... code is returned. + +The _tep_unregister_print_function()_ returns 0 in case of success, or -1 in +case of an error. + +EXAMPLE +------- +Some events have internal functions calls, that appear in the print format +output. For example "tracefs/events/i915/g4x_wm/format" has: +[source,c] +-- +print fmt: "pipe %c, frame=%u, scanline=%u, wm %d/%d/%d, sr %s/%d/%d/%d, hpll %s/%d/%d/%d, fbc %s", + ((REC->pipe) + 'A'), REC->frame, REC->scanline, REC->primary, + REC->sprite, REC->cursor, yesno(REC->cxsr), REC->sr_plane, + REC->sr_cursor, REC->sr_fbc, yesno(REC->hpll), REC->hpll_plane, + REC->hpll_cursor, REC->hpll_fbc, yesno(REC->fbc) +-- +Notice the call to function _yesno()_ in the print arguments. In the kernel +context, this function has the following implementation: +[source,c] +-- +static const char *yesno(int x) +{ + static const char *yes = "yes"; + static const char *no = "no"; + + return x ? yes : no; +} +-- +The user space event parser has no idea how to handle this _yesno()_ function. +The _tep_register_print_function()_ API can be used to register a user space +helper function, mapped to the kernel's _yesno()_: +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct tep_handle *tep = tep_alloc(); +... +static const char *yes_no_helper(int x) +{ + return x ? "yes" : "no"; +} +... + if ( tep_register_print_function(tep, + yes_no_helper, + TEP_FUNC_ARG_STRING, + "yesno", + TEP_FUNC_ARG_INT, + TEP_FUNC_ARG_VOID) != 0) { + /* Failed to register yes_no_helper function */ + } + +/* + Now, when the event parser encounters this yesno() function, it will know + how to handle it. +*/ +... + if (tep_unregister_print_function(tep, yes_no_helper, "yesno") != 0) { + /* Failed to unregister yes_no_helper function */ + } +-- + +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-set_flag.txt b/tools/lib/traceevent/Documentation/libtraceevent-set_flag.txt new file mode 100644 index 000000000..b0599780b --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-set_flag.txt @@ -0,0 +1,104 @@ +libtraceevent(3) +================ + +NAME +---- +tep_set_flag, tep_clear_flag, tep_test_flag - +Manage flags of trace event parser context. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_flag* { + _TEP_NSEC_OUTPUT_, + _TEP_DISABLE_SYS_PLUGINS_, + _TEP_DISABLE_PLUGINS_ +}; +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 _flag_); +-- + +DESCRIPTION +----------- +Trace event parser context flags are defined in *enum tep_flag*: +[verse] +-- +_TEP_NSEC_OUTPUT_ - print event's timestamp in nano seconds, instead of micro seconds. +_TEP_DISABLE_SYS_PLUGINS_ - disable plugins, located in system's plugin + directory. This directory is defined at library compile + time, and usually depends on library installation + prefix: (install_preffix)/lib/traceevent/plugins +_TEP_DISABLE_PLUGINS_ - disable all library plugins: + - in system's plugin directory + - in directory, defined by the environment variable _TRACEEVENT_PLUGIN_DIR_ + - in user's home directory, _~/.traceevent/plugins_ +-- +Note: plugin related flags must me set before calling _tep_load_plugins()_ API. + +The _tep_set_flag()_ function sets _flag_ to _tep_ context. + +The _tep_clear_flag()_ function clears _flag_ from _tep_ context. + +The _tep_test_flag()_ function tests if _flag_ is set to _tep_ context. + +RETURN VALUE +------------ +_tep_test_flag()_ function returns true if _flag_ is set, false otherwise. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +/* Print timestamps in nanoseconds */ +tep_set_flag(tep, TEP_NSEC_OUTPUT); +... +if (tep_test_flag(tep, TEP_NSEC_OUTPUT)) { + /* print timestamps in nanoseconds */ +} else { + /* print timestamps in microseconds */ +} +... +/* Print timestamps in microseconds */ +tep_clear_flag(tep, TEP_NSEC_OUTPUT); +... +-- +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)_ + +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-strerror.txt b/tools/lib/traceevent/Documentation/libtraceevent-strerror.txt new file mode 100644 index 000000000..ee4062a00 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-strerror.txt @@ -0,0 +1,85 @@ +libtraceevent(3) +================ + +NAME +---- +tep_strerror - Returns a string describing regular errno and tep error number. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_strerror*(struct tep_handle pass:[*]_tep_, enum tep_errno _errnum_, char pass:[*]_buf_, size_t _buflen_); + +-- +DESCRIPTION +----------- +The _tep_strerror()_ function converts tep error number into a human +readable string. +The _tep_ argument is trace event parser context. The _errnum_ is a regular +errno, defined in errno.h, or a tep error number. The string, describing this +error number is copied in the _buf_ argument. The _buflen_ argument is +the size of the _buf_. + +It as a thread safe wrapper around strerror_r(). The library function has two +different behaviors - POSIX and GNU specific. The _tep_strerror()_ API always +behaves as the POSIX version - the error string is copied in the user supplied +buffer. + +RETURN VALUE +------------ +The _tep_strerror()_ function returns 0, if a valid _errnum_ is passed and the +string is copied into _buf_. If _errnum_ is not a valid error number, +-1 is returned and _buf_ is not modified. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char buf[32]; +char *pool = calloc(1, 128); +if (tep == NULL) { + tep_strerror(tep, TEP_ERRNO__MEM_ALLOC_FAILED, buf, 32); + printf ("The pool is not initialized, %s", buf); +} +... +-- + +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)_ + +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-tseq.txt b/tools/lib/traceevent/Documentation/libtraceevent-tseq.txt new file mode 100644 index 000000000..8ac6aa174 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-tseq.txt @@ -0,0 +1,158 @@ +libtraceevent(3) +================ + +NAME +---- +trace_seq_init, trace_seq_destroy, trace_seq_reset, trace_seq_terminate, +trace_seq_putc, trace_seq_puts, trace_seq_printf, trace_seq_vprintf, +trace_seq_do_fprintf, trace_seq_do_printf - +Initialize / destroy a trace sequence. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* +*#include <trace-seq.h>* + +void *trace_seq_init*(struct trace_seq pass:[*]_s_); +void *trace_seq_destroy*(struct trace_seq pass:[*]_s_); +void *trace_seq_reset*(struct trace_seq pass:[*]_s_); +void *trace_seq_terminate*(struct trace_seq pass:[*]_s_); +int *trace_seq_putc*(struct trace_seq pass:[*]_s_, unsigned char _c_); +int *trace_seq_puts*(struct trace_seq pass:[*]_s_, const char pass:[*]_str_); +int *trace_seq_printf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, _..._); +int *trace_seq_vprintf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, va_list _args_); +int *trace_seq_do_printf*(struct trace_seq pass:[*]_s_); +int *trace_seq_do_fprintf*(struct trace_seq pass:[*]_s_, FILE pass:[*]_fp_); +-- + +DESCRIPTION +----------- +Trace sequences are used to allow a function to call several other functions +to create a string of data to use. + +The _trace_seq_init()_ function initializes the trace sequence _s_. + +The _trace_seq_destroy()_ function destroys the trace sequence _s_ and frees +all its resources that it had used. + +The _trace_seq_reset()_ function re-initializes the trace sequence _s_. All +characters already written in _s_ will be deleted. + +The _trace_seq_terminate()_ function terminates the trace sequence _s_. It puts +the null character pass:['\0'] at the end of the buffer. + +The _trace_seq_putc()_ function puts a single character _c_ in the trace +sequence _s_. + +The _trace_seq_puts()_ function puts a NULL terminated string _str_ in the +trace sequence _s_. + +The _trace_seq_printf()_ function puts a formated string _fmt _with +variable arguments _..._ in the trace sequence _s_. + +The _trace_seq_vprintf()_ function puts a formated string _fmt _with +list of arguments _args_ in the trace sequence _s_. + +The _trace_seq_do_printf()_ function prints the buffer of trace sequence _s_ to +the standard output stdout. + +The _trace_seq_do_fprintf()_ function prints the buffer of trace sequence _s_ +to the given file _fp_. + +RETURN VALUE +------------ +Both _trace_seq_putc()_ and _trace_seq_puts()_ functions return the number of +characters put in the trace sequence, or 0 in case of an error + +Both _trace_seq_printf()_ and _trace_seq_vprintf()_ functions return 0 if the +trace oversizes the buffer's free space, the number of characters printed, or +a negative value in case of an error. + +Both _trace_seq_do_printf()_ and _trace_seq_do_fprintf()_ functions return the +number of printed characters, or -1 in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct trace_seq seq; +trace_seq_init(&seq); +... +void foo_seq_print(struct trace_seq *tseq, char *format, ...) +{ + va_list ap; + va_start(ap, format); + if (trace_seq_vprintf(tseq, format, ap) <= 0) { + /* Failed to print in the trace sequence */ + } + va_end(ap); +} + +trace_seq_reset(&seq); + +char *str = " MAN page example"; +if (trace_seq_puts(&seq, str) != strlen(str)) { + /* Failed to put str in the trace sequence */ +} +if (trace_seq_putc(&seq, ':') != 1) { + /* Failed to put ':' in the trace sequence */ +} +if (trace_seq_printf(&seq, " trace sequence: %d", 1) <= 0) { + /* Failed to print in the trace sequence */ +} +foo_seq_print( &seq, " %d\n", 2); + +trace_seq_terminate(&seq); +... + +if (trace_seq_do_printf(&seq) < 0 ) { + /* Failed to print the sequence buffer to the standard output */ +} +FILE *fp = fopen("trace.txt", "w"); +if (trace_seq_do_fprintf(&seq, fp) < 0 ) [ + /* Failed to print the sequence buffer to the trace.txt file */ +} + +trace_seq_destroy(&seq); +... +-- + +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. +*-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.txt b/tools/lib/traceevent/Documentation/libtraceevent.txt new file mode 100644 index 000000000..d530a7ce8 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent.txt @@ -0,0 +1,192 @@ +libtraceevent(3) +================ + +NAME +---- +libtraceevent - Linux kernel trace event library + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +Management of tep handler data structure and access of its members: + 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_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_); + int *tep_get_cpus*(struct tep_handle pass:[*]_tep_); + void *tep_set_cpus*(struct tep_handle pass:[*]_tep_, int _cpus_); + int *tep_get_long_size*(strucqt tep_handle pass:[*]_tep_); + 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_); + 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_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_); + int *tep_register_print_string*(struct tep_handle pass:[*]_tep_, const char pass:[*]_fmt_, unsigned long long _addr_); + int *tep_register_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, enum tep_func_arg_type _ret_type_, char pass:[*]_name_, _..._); + int *tep_unregister_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, char pass:[*]_name_); + +Plugins management: + 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_); + char pass:[*]pass:[*]*tep_plugin_list_options*(void); + void *tep_plugin_free_options_list*(char pass:[*]pass:[*]_list_); + int *tep_plugin_add_options*(const char pass:[*]_name_, struct tep_plugin_option pass:[*]_options_); + void *tep_plugin_remove_options*(struct tep_plugin_option pass:[*]_options_); + void *tep_print_plugins*(struct trace_seq pass:[*]_s_, const char pass:[*]_prefix_, const char pass:[*]_suffix_, const struct tep_plugin_list pass:[*]_list_); + +Event related APIs: + struct tep_event pass:[*]*tep_get_event*(struct tep_handle pass:[*]_tep_, int _index_); + struct tep_event pass:[*]*tep_get_first_event*(struct tep_handle pass:[*]_tep_); + 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_); + 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_); + struct tep_event pass:[*]*tep_find_event_by_name*(struct tep_handle pass:[*]_tep_, const char pass:[*]_sys_, const char pass:[*]_name_); + struct tep_event pass:[*]*tep_find_event_by_record*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_record_); + +Parsing of event files: + int *tep_parse_header_page*(struct tep_handle pass:[*]_tep_, char pass:[*]_buf_, unsigned long _size_, int _long_size_); + enum tep_errno *tep_parse_event*(struct tep_handle pass:[*]_tep_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_); + enum tep_errno *tep_parse_format*(struct tep_handle pass:[*]_tep_, struct tep_event pass:[*]pass:[*]_eventp_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_); + +APIs related to fields from event's format files: + struct tep_format_field pass:[*]pass:[*]*tep_event_common_fields*(struct tep_event pass:[*]_event_); + struct tep_format_field pass:[*]pass:[*]*tep_event_fields*(struct tep_event pass:[*]_event_); + void pass:[*]*tep_get_field_raw*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int pass:[*]_len_, int _err_); + int *tep_get_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); + int *tep_get_common_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); + int *tep_get_any_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); + int *tep_read_number_field*(struct tep_format_field pass:[*]_field_, const void pass:[*]_data_, unsigned long long pass:[*]_value_); + +Event fields printing: + void *tep_print_field*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, struct tep_format_field pass:[*]_field_); + void *tep_print_fields*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, int _size_, struct tep_event pass:[*]_event_); + int *tep_print_num_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_); + int *tep_print_func_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_); + +Event fields finding: + struct tep_format_field pass:[*]*tep_find_common_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_); + struct tep_format_field pass:[*]*tep_find_field*(struct tep_event_ormat pass:[*]_event_, const char pass:[*]_name_); + struct tep_format_field pass:[*]*tep_find_any_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_); + +Functions resolver: + int *tep_set_function_resolver*(struct tep_handle pass:[*]_tep_, tep_func_resolver_t pass:[*]_func_, void pass:[*]_priv_); + void *tep_reset_function_resolver*(struct tep_handle pass:[*]_tep_); + const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); + unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); + +Filter management: + struct tep_event_filter pass:[*]*tep_filter_alloc*(struct tep_handle pass:[*]_tep_); + enum tep_errno *tep_filter_add_filter_str*(struct tep_event_filter pass:[*]_filter_, const char pass:[*]_filter_str_); + enum tep_errno *tep_filter_match*(struct tep_event_filter pass:[*]_filter_, struct tep_record pass:[*]_record_); + int *tep_filter_strerror*(struct tep_event_filter pass:[*]_filter_, enum tep_errno _err_, char pass:[*]buf, size_t _buflen_); + int *tep_event_filtered*(struct tep_event_filter pass:[*]_filter_, int _event_id_); + void *tep_filter_reset*(struct tep_event_filter pass:[*]_filter_); + void *tep_filter_free*(struct tep_event_filter pass:[*]_filter_); + char pass:[*]*tep_filter_make_string*(struct tep_event_filter pass:[*]_filter_, int _event_id_); + int *tep_filter_remove_event*(struct tep_event_filter pass:[*]_filter_, int _event_id_); + int *tep_filter_copy*(struct tep_event_filter pass:[*]_dest_, struct tep_event_filter pass:[*]_source_); + int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_); + +Parsing various data from the records: + 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_); + int *tep_data_flags*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); + +Command and task related APIs: + const char pass:[*]*tep_data_comm_from_pid*(struct tep_handle pass:[*]_tep_, int _pid_); + struct cmdline pass:[*]*tep_data_pid_from_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, struct cmdline pass:[*]_next_); + int *tep_register_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_); + int *tep_override_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_); + bool *tep_is_pid_registered*(struct tep_handle pass:[*]_tep_, int _pid_); + int *tep_cmdline_pid*(struct tep_handle pass:[*]_tep_, struct cmdline pass:[*]_cmdline_); + +Endian related APIs: + int *tep_is_bigendian*(void); + unsigned long long *tep_read_number*(struct tep_handle pass:[*]_tep_, const void pass:[*]_ptr_, int _size_); + bool *tep_is_file_bigendian*(struct tep_handle pass:[*]_tep_); + void *tep_set_file_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_); + bool *tep_is_local_bigendian*(struct tep_handle pass:[*]_tep_); + void *tep_set_local_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_); + +Trace sequences: +*#include <trace-seq.h>* + void *trace_seq_init*(struct trace_seq pass:[*]_s_); + void *trace_seq_reset*(struct trace_seq pass:[*]_s_); + void *trace_seq_destroy*(struct trace_seq pass:[*]_s_); + int *trace_seq_printf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, ...); + int *trace_seq_vprintf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, va_list _args_); + int *trace_seq_puts*(struct trace_seq pass:[*]_s_, const char pass:[*]_str_); + int *trace_seq_putc*(struct trace_seq pass:[*]_s_, unsigned char _c_); + void *trace_seq_terminate*(struct trace_seq pass:[*]_s_); + int *trace_seq_do_fprintf*(struct trace_seq pass:[*]_s_, FILE pass:[*]_fp_); + int *trace_seq_do_printf*(struct trace_seq pass:[*]_s_); +-- + +DESCRIPTION +----------- +The libtraceevent(3) library provides APIs to access kernel tracepoint events, +located in the tracefs file system under the events directory. + +ENVIRONMENT +----------- +[verse] +-- +TRACEEVENT_PLUGIN_DIR + Additional plugin directory. All shared object files, located in this directory will be loaded as traceevent plugins. +-- + +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 +-------- +_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/manpage-1.72.xsl b/tools/lib/traceevent/Documentation/manpage-1.72.xsl new file mode 100644 index 000000000..b4d315cb8 --- /dev/null +++ b/tools/lib/traceevent/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/traceevent/Documentation/manpage-base.xsl b/tools/lib/traceevent/Documentation/manpage-base.xsl new file mode 100644 index 000000000..a264fa616 --- /dev/null +++ b/tools/lib/traceevent/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="$git.docbook.dot"/> + <xsl:text>br </xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl b/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl new file mode 100644 index 000000000..608eb5df6 --- /dev/null +++ b/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl @@ -0,0 +1,17 @@ +<!-- manpage-bold-literal.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- render literal text as bold (instead of plain or monospace); + this makes literal text easier to distinguish in manpages + viewed on a tty --> +<xsl:template match="literal"> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fB</xsl:text> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fR</xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/traceevent/Documentation/manpage-normal.xsl b/tools/lib/traceevent/Documentation/manpage-normal.xsl new file mode 100644 index 000000000..a48f5b11f --- /dev/null +++ b/tools/lib/traceevent/Documentation/manpage-normal.xsl @@ -0,0 +1,13 @@ +<!-- manpage-normal.xsl: + special settings for manpages rendered from asciidoc+docbook + handles anything we want to keep away from docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the normal values for the roff control characters --> +<xsl:param name="git.docbook.backslash">\</xsl:param> +<xsl:param name="git.docbook.dot" >.</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl b/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl new file mode 100644 index 000000000..a63c7632a --- /dev/null +++ b/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl @@ -0,0 +1,21 @@ +<!-- manpage-suppress-sp.xsl: + special settings for manpages rendered from asciidoc+docbook + handles erroneous, inline .sp in manpage output of some + versions of docbook-xsl --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- attempt to work around spurious .sp at the tail of the line + that some versions of docbook stylesheets seem to add --> +<xsl:template match="simpara"> + <xsl:variable name="content"> + <xsl:apply-templates/> + </xsl:variable> + <xsl:value-of select="normalize-space($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/traceevent/Makefile b/tools/lib/traceevent/Makefile new file mode 100644 index 000000000..c874c017c --- /dev/null +++ b/tools/lib/traceevent/Makefile @@ -0,0 +1,300 @@ +# SPDX-License-Identifier: GPL-2.0 +# trace-cmd version +EP_VERSION = 1 +EP_PATCHLEVEL = 1 +EP_EXTRAVERSION = 0 + +# file format version +FILE_VERSION = 6 + +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_temp = lib64 +else + libdir_relative_temp = lib +endif + +libdir_relative ?= $(libdir_relative_temp) +prefix ?= /usr/local +libdir = $(prefix)/$(libdir_relative) +man_dir = $(prefix)/share/man +man_dir_SQ = '$(subst ','\'',$(man_dir))' +pkgconfig_dir ?= $(word 1,$(shell $(PKG_CONFIG) \ + --variable pc_path pkg-config | tr ":" " ")) +includedir_relative = traceevent +includedir = $(prefix)/include/$(includedir_relative) +includedir_SQ = '$(subst ','\'',$(includedir))' + +export man_dir man_dir_SQ INSTALL +export DESTDIR DESTDIR_SQ +export EVENT_PARSE_VERSION + +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 $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +export prefix libdir src obj + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) +libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) + +CONFIG_INCLUDES = +CONFIG_LIBS = +CONFIG_FLAGS = + +VERSION = $(EP_VERSION) +PATCHLEVEL = $(EP_PATCHLEVEL) +EXTRAVERSION = $(EP_EXTRAVERSION) + +OBJ = $@ +N = + +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) + +# 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 + +TE_IN := $(OUTPUT)libtraceevent-in.o +LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) + +CMD_TARGETS = $(LIB_TARGET) + +TARGETS = $(CMD_TARGETS) + +all: all_cmd plugins + +all_cmd: $(CMD_TARGETS) + +$(TE_IN): force + $(Q)$(MAKE) $(build)=libtraceevent + +$(OUTPUT)libtraceevent.so.$(EVENT_PARSE_VERSION): $(TE_IN) + $(QUIET_LINK)$(CC) --shared $(LDFLAGS) $^ -Wl,-soname,libtraceevent.so.$(EP_VERSION) -o $@ + @ln -sf $(@F) $(OUTPUT)libtraceevent.so + @ln -sf $(@F) $(OUTPUT)libtraceevent.so.$(EP_VERSION) + +$(OUTPUT)libtraceevent.a: $(TE_IN) + $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ + +$(OUTPUT)%.so: $(OUTPUT)%-in.o + $(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^ + +define make_version.h + (echo '/* This file is automatically generated. Do not modify. */'; \ + echo \#define VERSION_CODE $(shell \ + expr $(VERSION) \* 256 + $(PATCHLEVEL)); \ + echo '#define EXTRAVERSION ' $(EXTRAVERSION); \ + echo '#define VERSION_STRING "'$(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)'"'; \ + echo '#define FILE_VERSION '$(FILE_VERSION); \ + ) > $1 +endef + +define update_version.h + ($(call make_version.h, $@.tmp); \ + if [ -r $@ ] && cmp -s $@ $@.tmp; then \ + rm -f $@.tmp; \ + else \ + echo ' UPDATE $@'; \ + mv -f $@.tmp $@; \ + fi); +endef + +ep_version.h: force + $(Q)$(N)$(call update_version.h) + +VERSION_FILES = ep_version.h + +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 + +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_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" ${PKG_CONFIG_FILE}; \ + sed -i "s|HEADER_DIR|$(includedir)|g" ${PKG_CONFIG_FILE}; \ + $(call do_install,$(PKG_CONFIG_FILE),$(pkgconfig_dir),644); \ + else \ + (echo Failed to locate pkg-config directory) 1>&2; \ + fi +endef + +install_lib: all_cmd install_plugins install_headers install_pkgconfig + $(call QUIET_INSTALL, $(LIB_TARGET)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIB_INSTALL) $(DESTDIR)$(libdir_SQ) + +install_pkgconfig: + $(call QUIET_INSTALL, $(PKG_CONFIG_FILE)) \ + $(call do_install_pkgconfig_file,$(prefix)) + +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,event-parse.h,$(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_plugins + $(call QUIET_CLEAN, libtraceevent) \ + $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \ + $(RM) TRACEEVENT-CFLAGS tags TAGS; \ + $(RM) $(PKG_CONFIG_FILE) + +PHONY += doc +doc: + $(call descend,Documentation) + +PHONY += doc-clean +doc-clean: + $(call descend,Documentation,clean) + +PHONY += doc-install +doc-install: + $(call descend,Documentation,install) + +PHONY += doc-uninstall +doc-uninstall: + $(call descend,Documentation,uninstall) + +PHONY += help +help: + @echo 'Possible targets:' + @echo'' + @echo ' all - default, compile the library and the'\ + 'plugins' + @echo ' plugins - compile the plugins' + @echo ' install - install the library, the plugins,'\ + 'the header and pkgconfig files' + @echo ' clean - clean the library and the plugins object files' + @echo ' doc - compile the documentation files - man'\ + 'and html pages, in the Documentation directory' + @echo ' doc-clean - clean the documentation files' + @echo ' doc-install - install the man pages' + @echo ' doc-uninstall - uninstall the man pages' + @echo'' + +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 +# information in a variable so we can use it in if_changed and friends. +.PHONY: $(PHONY) diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c new file mode 100644 index 000000000..f8361e45d --- /dev/null +++ b/tools/lib/traceevent/event-parse-api.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ + +#include "event-parse.h" +#include "event-parse-local.h" +#include "event-utils.h" + +/** + * tep_get_event - returns the event with the given index + * @tep: a handle to the tep_handle + * @index: index of the requested event, in the range 0 .. nr_events + * + * This returns pointer to the element of the events array with the given index + * If @tep is NULL, or @index is not in the range 0 .. nr_events, NULL is returned. + */ +struct tep_event *tep_get_event(struct tep_handle *tep, int index) +{ + if (tep && tep->events && index < tep->nr_events) + return tep->events[index]; + + return NULL; +} + +/** + * tep_get_first_event - returns the first event in the events array + * @tep: a handle to the tep_handle + * + * This returns pointer to the first element of the events array + * If @tep is NULL, NULL is returned. + */ +struct tep_event *tep_get_first_event(struct tep_handle *tep) +{ + return tep_get_event(tep, 0); +} + +/** + * tep_get_events_count - get the number of defined events + * @tep: a handle to the tep_handle + * + * This returns number of elements in event array + * If @tep is NULL, 0 is returned. + */ +int tep_get_events_count(struct tep_handle *tep) +{ + if (tep) + return tep->nr_events; + return 0; +} + +/** + * tep_set_flag - set event parser flag + * @tep: a handle to the tep_handle + * @flag: flag, or combination of flags to be set + * can be any combination from enum tep_flag + * + * This sets a flag or combination of flags from enum tep_flag + */ +void tep_set_flag(struct tep_handle *tep, int flag) +{ + if (tep) + tep->flags |= flag; +} + +/** + * tep_clear_flag - clear event parser flag + * @tep: a handle to the tep_handle + * @flag: flag to be cleared + * + * This clears a tep flag + */ +void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag) +{ + if (tep) + tep->flags &= ~flag; +} + +/** + * tep_test_flag - check the state of event parser flag + * @tep: a handle to the tep_handle + * @flag: flag to be checked + * + * This returns the state of the requested tep flag. + * Returns: true if the flag is set, false otherwise. + */ +bool tep_test_flag(struct tep_handle *tep, enum tep_flag flag) +{ + if (tep) + return tep->flags & flag; + return false; +} + +__hidden unsigned short data2host2(struct tep_handle *tep, unsigned short data) +{ + unsigned short swap; + + if (!tep || tep->host_bigendian == tep->file_bigendian) + return data; + + swap = ((data & 0xffULL) << 8) | + ((data & (0xffULL << 8)) >> 8); + + return swap; +} + +__hidden unsigned int data2host4(struct tep_handle *tep, unsigned int data) +{ + unsigned int swap; + + if (!tep || tep->host_bigendian == tep->file_bigendian) + return data; + + swap = ((data & 0xffULL) << 24) | + ((data & (0xffULL << 8)) << 8) | + ((data & (0xffULL << 16)) >> 8) | + ((data & (0xffULL << 24)) >> 24); + + return swap; +} + +__hidden unsigned long long +data2host8(struct tep_handle *tep, unsigned long long data) +{ + unsigned long long swap; + + if (!tep || tep->host_bigendian == tep->file_bigendian) + return data; + + swap = ((data & 0xffULL) << 56) | + ((data & (0xffULL << 8)) << 40) | + ((data & (0xffULL << 16)) << 24) | + ((data & (0xffULL << 24)) << 8) | + ((data & (0xffULL << 32)) >> 8) | + ((data & (0xffULL << 40)) >> 24) | + ((data & (0xffULL << 48)) >> 40) | + ((data & (0xffULL << 56)) >> 56); + + return swap; +} + +/** + * tep_get_header_page_size - get size of the header page + * @tep: a handle to the tep_handle + * + * This returns size of the header page + * If @tep is NULL, 0 is returned. + */ +int tep_get_header_page_size(struct tep_handle *tep) +{ + if (tep) + return tep->header_page_size_size; + return 0; +} + +/** + * tep_get_header_timestamp_size - get size of the timestamp in the header page + * @tep: a handle to the tep_handle + * + * This returns size of the timestamp in the header page + * If @tep is NULL, 0 is returned. + */ +int tep_get_header_timestamp_size(struct tep_handle *tep) +{ + if (tep) + return tep->header_page_ts_size; + return 0; +} + +/** + * tep_get_cpus - get the number of CPUs + * @tep: a handle to the tep_handle + * + * This returns the number of CPUs + * If @tep is NULL, 0 is returned. + */ +int tep_get_cpus(struct tep_handle *tep) +{ + if (tep) + return tep->cpus; + return 0; +} + +/** + * tep_set_cpus - set the number of CPUs + * @tep: a handle to the tep_handle + * + * This sets the number of CPUs + */ +void tep_set_cpus(struct tep_handle *tep, int cpus) +{ + if (tep) + tep->cpus = cpus; +} + +/** + * tep_get_long_size - get the size of a long integer on the traced machine + * @tep: a handle to the tep_handle + * + * This returns the size of a long integer on the traced machine + * If @tep is NULL, 0 is returned. + */ +int tep_get_long_size(struct tep_handle *tep) +{ + if (tep) + return tep->long_size; + return 0; +} + +/** + * tep_set_long_size - set the size of a long integer on the traced machine + * @tep: a handle to the tep_handle + * @size: size, in bytes, of a long integer + * + * This sets the size of a long integer on the traced machine + */ +void tep_set_long_size(struct tep_handle *tep, int long_size) +{ + if (tep) + tep->long_size = long_size; +} + +/** + * tep_get_page_size - get the size of a memory page on the traced machine + * @tep: a handle to the tep_handle + * + * This returns the size of a memory page on the traced machine + * If @tep is NULL, 0 is returned. + */ +int tep_get_page_size(struct tep_handle *tep) +{ + if (tep) + return tep->page_size; + return 0; +} + +/** + * tep_set_page_size - set the size of a memory page on the traced machine + * @tep: a handle to the tep_handle + * @_page_size: size of a memory page, in bytes + * + * This sets the size of a memory page on the traced machine + */ +void tep_set_page_size(struct tep_handle *tep, int _page_size) +{ + if (tep) + tep->page_size = _page_size; +} + +/** + * tep_is_file_bigendian - return the endian of the file + * @tep: a handle to the tep_handle + * + * This returns true if the file is in big endian order + * If @tep is NULL, false is returned. + */ +bool tep_is_file_bigendian(struct tep_handle *tep) +{ + if (tep) + return (tep->file_bigendian == TEP_BIG_ENDIAN); + return false; +} + +/** + * tep_set_file_bigendian - set if the file is in big endian order + * @tep: a handle to the tep_handle + * @endian: non zero, if the file is in big endian order + * + * This sets if the file is in big endian order + */ +void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian) +{ + if (tep) + tep->file_bigendian = endian; +} + +/** + * tep_is_local_bigendian - return the endian of the saved local machine + * @tep: a handle to the tep_handle + * + * This returns true if the saved local machine in @tep is big endian. + * If @tep is NULL, false is returned. + */ +bool tep_is_local_bigendian(struct tep_handle *tep) +{ + if (tep) + return (tep->host_bigendian == TEP_BIG_ENDIAN); + return 0; +} + +/** + * tep_set_local_bigendian - set the stored local machine endian order + * @tep: a handle to the tep_handle + * @endian: non zero, if the local host has big endian order + * + * This sets the endian order for the local machine. + */ +void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian) +{ + if (tep) + tep->host_bigendian = endian; +} + +/** + * tep_is_old_format - get if an old kernel is used + * @tep: a handle to the tep_handle + * + * This returns true, if an old kernel is used to generate the tracing events or + * false if a new kernel is used. Old kernels did not have header page info. + * If @tep is NULL, false is returned. + */ +bool tep_is_old_format(struct tep_handle *tep) +{ + if (tep) + return tep->old_format; + return false; +} + +/** + * 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 + * + * This sets a flag to test a filter string. If this flag is set, when + * tep_filter_add_filter_str() API as called,it will print the filter string + * instead of adding it. + */ +void tep_set_test_filters(struct tep_handle *tep, int test_filters) +{ + if (tep) + tep->test_filters = test_filters; +} diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h new file mode 100644 index 000000000..fd4bbcfbb --- /dev/null +++ b/tools/lib/traceevent/event-parse-local.h @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ + +#ifndef _PARSE_EVENTS_INT_H +#define _PARSE_EVENTS_INT_H + +struct tep_cmdline; +struct cmdline_list; +struct func_map; +struct func_list; +struct event_handler; +struct func_resolver; +struct tep_plugins_dir; + +#define __hidden __attribute__((visibility ("hidden"))) + +struct tep_handle { + int ref_count; + + int header_page_ts_offset; + int header_page_ts_size; + int header_page_size_offset; + int header_page_size_size; + int header_page_data_offset; + int header_page_data_size; + int header_page_overwrite; + + enum tep_endian file_bigendian; + enum tep_endian host_bigendian; + + int old_format; + + int cpus; + int long_size; + int page_size; + + struct tep_cmdline *cmdlines; + struct cmdline_list *cmdlist; + int cmdline_count; + + struct func_map *func_map; + struct func_resolver *func_resolver; + struct func_list *funclist; + unsigned int func_count; + + struct printk_map *printk_map; + struct printk_list *printklist; + unsigned int printk_count; + + struct tep_event **events; + int nr_events; + struct tep_event **sort_events; + enum tep_event_sort_type last_type; + + int type_offset; + int type_size; + + int pid_offset; + int pid_size; + + int pc_offset; + int pc_size; + + int flags_offset; + int flags_size; + + int ld_offset; + int ld_size; + + int test_filters; + + int flags; + + struct tep_format_field *bprint_ip_field; + struct tep_format_field *bprint_fmt_field; + struct tep_format_field *bprint_buf_field; + + struct event_handler *handlers; + struct tep_function_handler *func_handlers; + + /* cache */ + struct tep_event *last_event; + + struct tep_plugins_dir *plugins_dir; +}; + +enum tep_print_parse_type { + PRINT_FMT_STRING, + PRINT_FMT_ARG_DIGIT, + PRINT_FMT_ARG_POINTER, + PRINT_FMT_ARG_STRING, +}; + +struct tep_print_parse { + struct tep_print_parse *next; + + char *format; + int ls; + enum tep_print_parse_type type; + struct tep_print_arg *arg; + struct tep_print_arg *len_as_arg; +}; + +void free_tep_event(struct tep_event *event); +void free_tep_format_field(struct tep_format_field *field); +void free_tep_plugin_paths(struct tep_handle *tep); + +unsigned short data2host2(struct tep_handle *tep, unsigned short data); +unsigned int data2host4(struct tep_handle *tep, unsigned int data); +unsigned long long data2host8(struct tep_handle *tep, unsigned long long data); + +/* access to the internal parser */ +int peek_char(void); +void init_input_buf(const char *buf, unsigned long long size); +unsigned long long get_input_buf_ptr(void); +const char *get_input_buf(void); +enum tep_event_type read_token(char **tok); +void free_token(char *tok); + +#endif /* _PARSE_EVENTS_INT_H */ diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c new file mode 100644 index 000000000..8e24c4c78 --- /dev/null +++ b/tools/lib/traceevent/event-parse.c @@ -0,0 +1,7624 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + * + * The parts for function graph printing was taken and modified from the + * Linux Kernel that were written by + * - Copyright (C) 2009 Frederic Weisbecker, + * Frederic Weisbecker gave his permission to relicense the code to + * the Lesser General Public License. + */ +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdarg.h> +#include <ctype.h> +#include <errno.h> +#include <stdint.h> +#include <limits.h> +#include <linux/time64.h> + +#include <netinet/in.h> +#include "event-parse.h" + +#include "event-parse-local.h" +#include "event-utils.h" +#include "trace-seq.h" + +static const char *input_buf; +static unsigned long long input_buf_ptr; +static unsigned long long input_buf_siz; + +static int is_flag_field; +static int is_symbolic_field; + +static int show_warning = 1; + +#define do_warning(fmt, ...) \ + do { \ + if (show_warning) \ + warning(fmt, ##__VA_ARGS__); \ + } while (0) + +#define do_warning_event(event, fmt, ...) \ + do { \ + if (!show_warning) \ + continue; \ + \ + if (event) \ + warning("[%s:%s] " fmt, event->system, \ + event->name, ##__VA_ARGS__); \ + else \ + warning(fmt, ##__VA_ARGS__); \ + } while (0) + +/** + * init_input_buf - init buffer for parsing + * @buf: buffer to parse + * @size: the size of the buffer + * + * Initializes the internal buffer that tep_read_token() will parse. + */ +__hidden void init_input_buf(const char *buf, unsigned long long size) +{ + input_buf = buf; + input_buf_siz = size; + input_buf_ptr = 0; +} + +__hidden const char *get_input_buf(void) +{ + return input_buf; +} + +__hidden unsigned long long get_input_buf_ptr(void) +{ + return input_buf_ptr; +} + +struct event_handler { + struct event_handler *next; + int id; + const char *sys_name; + const char *event_name; + tep_event_handler_func func; + void *context; +}; + +struct func_params { + struct func_params *next; + enum tep_func_arg_type type; +}; + +struct tep_function_handler { + struct tep_function_handler *next; + enum tep_func_arg_type ret_type; + char *name; + tep_func_handler func; + struct func_params *params; + int nr_args; +}; + +static unsigned long long +process_defined_func(struct trace_seq *s, void *data, int size, + struct tep_event *event, struct tep_print_arg *arg); + +static void free_func_handle(struct tep_function_handler *func); + +void breakpoint(void) +{ + static int x; + x++; +} + +static struct tep_print_arg *alloc_arg(void) +{ + return calloc(1, sizeof(struct tep_print_arg)); +} + +struct tep_cmdline { + char *comm; + int pid; +}; + +static int cmdline_cmp(const void *a, const void *b) +{ + const struct tep_cmdline *ca = a; + const struct tep_cmdline *cb = b; + + if (ca->pid < cb->pid) + return -1; + if (ca->pid > cb->pid) + return 1; + + 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; + int pid; +}; + +static int cmdline_init(struct tep_handle *tep) +{ + struct cmdline_list *cmdlist = tep->cmdlist; + struct cmdline_list *item; + struct tep_cmdline *cmdlines; + int i; + + cmdlines = malloc(sizeof(*cmdlines) * tep->cmdline_count); + if (!cmdlines) + return -1; + + i = 0; + while (cmdlist) { + cmdlines[i].pid = cmdlist->pid; + cmdlines[i].comm = cmdlist->comm; + i++; + item = cmdlist; + cmdlist = cmdlist->next; + free(item); + } + + qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp); + + tep->cmdlines = cmdlines; + tep->cmdlist = NULL; + + return 0; +} + +static const char *find_cmdline(struct tep_handle *tep, int pid) +{ + const struct tep_cmdline *comm; + struct tep_cmdline key; + + if (!pid) + return "<idle>"; + + if (!tep->cmdlines && cmdline_init(tep)) + return "<not enough memory for cmdlines!>"; + + key.pid = pid; + + comm = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); + + if (comm) + return comm->comm; + return "<...>"; +} + +/** + * tep_is_pid_registered - return if a pid has a cmdline registered + * @tep: a handle to the trace event parser context + * @pid: The pid to check if it has a cmdline registered with. + * + * Returns true if the pid has a cmdline mapped to it + * false otherwise. + */ +bool tep_is_pid_registered(struct tep_handle *tep, int pid) +{ + const struct tep_cmdline *comm; + struct tep_cmdline key; + + if (!pid) + return true; + + if (!tep->cmdlines && cmdline_init(tep)) + return false; + + key.pid = pid; + + comm = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); + + if (comm) + return true; + return false; +} + +/* + * If the command lines have been converted to an array, then + * we must add this pid. This is much slower than when cmdlines + * are added before the array is initialized. + */ +static int add_new_comm(struct tep_handle *tep, + const char *comm, int pid, bool override) +{ + struct tep_cmdline *cmdlines = tep->cmdlines; + struct tep_cmdline *cmdline; + struct tep_cmdline key; + char *new_comm; + int cnt; + + if (!pid) + return 0; + + /* avoid duplicates */ + key.pid = pid; + + cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); + if (cmdline) { + if (!override) { + errno = EEXIST; + return -1; + } + new_comm = strdup(comm); + if (!new_comm) { + errno = ENOMEM; + return -1; + } + free(cmdline->comm); + cmdline->comm = new_comm; + + return 0; + } + + cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (tep->cmdline_count + 1)); + if (!cmdlines) { + errno = ENOMEM; + return -1; + } + tep->cmdlines = cmdlines; + + key.comm = strdup(comm); + if (!key.comm) { + errno = ENOMEM; + return -1; + } + + if (!tep->cmdline_count) { + /* no entries yet */ + tep->cmdlines[0] = key; + tep->cmdline_count++; + return 0; + } + + /* 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; +} + +static int _tep_register_comm(struct tep_handle *tep, + const char *comm, int pid, bool override) +{ + struct cmdline_list *item; + + if (tep->cmdlines) + return add_new_comm(tep, comm, pid, override); + + item = malloc(sizeof(*item)); + if (!item) + return -1; + + if (comm) + item->comm = strdup(comm); + else + item->comm = strdup("<...>"); + if (!item->comm) { + free(item); + return -1; + } + item->pid = pid; + item->next = tep->cmdlist; + + tep->cmdlist = item; + tep->cmdline_count++; + + return 0; +} + +/** + * tep_register_comm - register a pid / comm mapping + * @tep: a handle to the trace event parser context + * @comm: the command line to register + * @pid: the pid to map the command line to + * + * This adds a mapping to search for command line names with + * a given pid. The comm is duplicated. If a command with the same pid + * already exist, -1 is returned and errno is set to EEXIST + */ +int tep_register_comm(struct tep_handle *tep, const char *comm, int pid) +{ + return _tep_register_comm(tep, comm, pid, false); +} + +/** + * tep_override_comm - register a pid / comm mapping + * @tep: a handle to the trace event parser context + * @comm: the command line to register + * @pid: the pid to map the command line to + * + * This adds a mapping to search for command line names with + * a given pid. The comm is duplicated. If a command with the same pid + * already exist, the command string is udapted with the new one + */ +int tep_override_comm(struct tep_handle *tep, const char *comm, int pid) +{ + if (!tep->cmdlines && cmdline_init(tep)) { + errno = ENOMEM; + return -1; + } + return _tep_register_comm(tep, comm, pid, true); +} + +struct func_map { + unsigned long long addr; + char *func; + char *mod; +}; + +struct func_list { + struct func_list *next; + unsigned long long addr; + char *func; + char *mod; +}; + +static int func_cmp(const void *a, const void *b) +{ + const struct func_map *fa = a; + const struct func_map *fb = b; + + if (fa->addr < fb->addr) + return -1; + if (fa->addr > fb->addr) + return 1; + + return 0; +} + +/* + * We are searching for a record in between, not an exact + * match. + */ +static int func_bcmp(const void *a, const void *b) +{ + const struct func_map *fa = a; + const struct func_map *fb = b; + + if ((fa->addr == fb->addr) || + + (fa->addr > fb->addr && + fa->addr < (fb+1)->addr)) + return 0; + + if (fa->addr < fb->addr) + return -1; + + return 1; +} + +static int func_map_init(struct tep_handle *tep) +{ + struct func_list *funclist; + struct func_list *item; + struct func_map *func_map; + int i; + + func_map = malloc(sizeof(*func_map) * (tep->func_count + 1)); + if (!func_map) + return -1; + + funclist = tep->funclist; + + i = 0; + while (funclist) { + func_map[i].func = funclist->func; + func_map[i].addr = funclist->addr; + func_map[i].mod = funclist->mod; + i++; + item = funclist; + funclist = funclist->next; + free(item); + } + + qsort(func_map, tep->func_count, sizeof(*func_map), func_cmp); + + /* + * Add a special record at the end. + */ + func_map[tep->func_count].func = NULL; + func_map[tep->func_count].addr = 0; + func_map[tep->func_count].mod = NULL; + + tep->func_map = func_map; + tep->funclist = NULL; + + return 0; +} + +static struct func_map * +__find_func(struct tep_handle *tep, unsigned long long addr) +{ + struct func_map *func; + struct func_map key; + + if (!tep->func_map) + func_map_init(tep); + + key.addr = addr; + + func = bsearch(&key, tep->func_map, tep->func_count, + sizeof(*tep->func_map), func_bcmp); + + return func; +} + +struct func_resolver { + tep_func_resolver_t *func; + void *priv; + struct func_map map; +}; + +/** + * tep_set_function_resolver - set an alternative function resolver + * @tep: a handle to the trace event parser context + * @resolver: function to be used + * @priv: resolver function private state. + * + * Some tools may have already a way to resolve kernel functions, allow them to + * keep using it instead of duplicating all the entries inside tep->funclist. + */ +int tep_set_function_resolver(struct tep_handle *tep, + tep_func_resolver_t *func, void *priv) +{ + struct func_resolver *resolver = malloc(sizeof(*resolver)); + + if (resolver == NULL) + return -1; + + resolver->func = func; + resolver->priv = priv; + + free(tep->func_resolver); + tep->func_resolver = resolver; + + return 0; +} + +/** + * tep_reset_function_resolver - reset alternative function resolver + * @tep: a handle to the trace event parser context + * + * Stop using whatever alternative resolver was set, use the default + * one instead. + */ +void tep_reset_function_resolver(struct tep_handle *tep) +{ + free(tep->func_resolver); + tep->func_resolver = NULL; +} + +static struct func_map * +find_func(struct tep_handle *tep, unsigned long long addr) +{ + struct func_map *map; + + if (!tep->func_resolver) + return __find_func(tep, addr); + + map = &tep->func_resolver->map; + map->mod = NULL; + map->addr = addr; + map->func = tep->func_resolver->func(tep->func_resolver->priv, + &map->addr, &map->mod); + if (map->func == NULL) + return NULL; + + return map; +} + +/** + * tep_find_function - find a function by a given address + * @tep: a handle to the trace event parser context + * @addr: the address to find the function with + * + * Returns a pointer to the function stored that has the given + * address. Note, the address does not have to be exact, it + * will select the function that would contain the address. + */ +const char *tep_find_function(struct tep_handle *tep, unsigned long long addr) +{ + struct func_map *map; + + map = find_func(tep, addr); + if (!map) + return NULL; + + return map->func; +} + +/** + * tep_find_function_address - find a function address by a given address + * @tep: a handle to the trace event parser context + * @addr: the address to find the function with + * + * Returns the address the function starts at. This can be used in + * conjunction with tep_find_function to print both the function + * name and the function offset. + */ +unsigned long long +tep_find_function_address(struct tep_handle *tep, unsigned long long addr) +{ + struct func_map *map; + + map = find_func(tep, addr); + if (!map) + return 0; + + return map->addr; +} + +/** + * tep_register_function - register a function with a given address + * @tep: a handle to the trace event parser context + * @function: the function name to register + * @addr: the address the function starts at + * @mod: the kernel module the function may be in (NULL for none) + * + * This registers a function name with an address and module. + * The @func passed in is duplicated. + */ +int tep_register_function(struct tep_handle *tep, char *func, + unsigned long long addr, char *mod) +{ + struct func_list *item = malloc(sizeof(*item)); + + if (!item) + return -1; + + item->next = tep->funclist; + item->func = strdup(func); + if (!item->func) + goto out_free; + + if (mod) { + item->mod = strdup(mod); + if (!item->mod) + goto out_free_func; + } else + item->mod = NULL; + item->addr = addr; + + tep->funclist = item; + tep->func_count++; + + return 0; + +out_free_func: + free(item->func); + item->func = NULL; +out_free: + free(item); + errno = ENOMEM; + return -1; +} + +/** + * tep_print_funcs - print out the stored functions + * @tep: a handle to the trace event parser context + * + * This prints out the stored functions. + */ +void tep_print_funcs(struct tep_handle *tep) +{ + int i; + + if (!tep->func_map) + func_map_init(tep); + + for (i = 0; i < (int)tep->func_count; i++) { + printf("%016llx %s", + tep->func_map[i].addr, + tep->func_map[i].func); + if (tep->func_map[i].mod) + printf(" [%s]\n", tep->func_map[i].mod); + else + printf("\n"); + } +} + +struct printk_map { + unsigned long long addr; + char *printk; +}; + +struct printk_list { + struct printk_list *next; + unsigned long long addr; + char *printk; +}; + +static int printk_cmp(const void *a, const void *b) +{ + const struct printk_map *pa = a; + const struct printk_map *pb = b; + + if (pa->addr < pb->addr) + return -1; + if (pa->addr > pb->addr) + return 1; + + return 0; +} + +static int printk_map_init(struct tep_handle *tep) +{ + struct printk_list *printklist; + struct printk_list *item; + struct printk_map *printk_map; + int i; + + printk_map = malloc(sizeof(*printk_map) * (tep->printk_count + 1)); + if (!printk_map) + return -1; + + printklist = tep->printklist; + + i = 0; + while (printklist) { + printk_map[i].printk = printklist->printk; + printk_map[i].addr = printklist->addr; + i++; + item = printklist; + printklist = printklist->next; + free(item); + } + + qsort(printk_map, tep->printk_count, sizeof(*printk_map), printk_cmp); + + tep->printk_map = printk_map; + tep->printklist = NULL; + + return 0; +} + +static struct printk_map * +find_printk(struct tep_handle *tep, unsigned long long addr) +{ + struct printk_map *printk; + struct printk_map key; + + if (!tep->printk_map && printk_map_init(tep)) + return NULL; + + key.addr = addr; + + printk = bsearch(&key, tep->printk_map, tep->printk_count, + sizeof(*tep->printk_map), printk_cmp); + + return printk; +} + +/** + * tep_register_print_string - register a string by its address + * @tep: a handle to the trace event parser context + * @fmt: the string format to register + * @addr: the address the string was located at + * + * This registers a string by the address it was stored in the kernel. + * The @fmt passed in is duplicated. + */ +int tep_register_print_string(struct tep_handle *tep, const char *fmt, + unsigned long long addr) +{ + struct printk_list *item = malloc(sizeof(*item)); + char *p; + + if (!item) + return -1; + + item->next = tep->printklist; + item->addr = addr; + + /* Strip off quotes and '\n' from the end */ + if (fmt[0] == '"') + fmt++; + item->printk = strdup(fmt); + if (!item->printk) + goto out_free; + + p = item->printk + strlen(item->printk) - 1; + if (*p == '"') + *p = 0; + + p -= 2; + if (strcmp(p, "\\n") == 0) + *p = 0; + + tep->printklist = item; + tep->printk_count++; + + return 0; + +out_free: + free(item); + errno = ENOMEM; + return -1; +} + +/** + * tep_print_printk - print out the stored strings + * @tep: a handle to the trace event parser context + * + * This prints the string formats that were stored. + */ +void tep_print_printk(struct tep_handle *tep) +{ + int i; + + if (!tep->printk_map) + printk_map_init(tep); + + for (i = 0; i < (int)tep->printk_count; i++) { + printf("%016llx %s\n", + tep->printk_map[i].addr, + tep->printk_map[i].printk); + } +} + +static struct tep_event *alloc_event(void) +{ + return calloc(1, sizeof(struct tep_event)); +} + +static int add_event(struct tep_handle *tep, struct tep_event *event) +{ + int i; + struct tep_event **events = realloc(tep->events, sizeof(event) * + (tep->nr_events + 1)); + if (!events) + return -1; + + tep->events = events; + + for (i = 0; i < tep->nr_events; i++) { + if (tep->events[i]->id > event->id) + break; + } + if (i < tep->nr_events) + memmove(&tep->events[i + 1], + &tep->events[i], + sizeof(event) * (tep->nr_events - i)); + + tep->events[i] = event; + tep->nr_events++; + + event->tep = tep; + + return 0; +} + +static int event_item_type(enum tep_event_type type) +{ + switch (type) { + case TEP_EVENT_ITEM ... TEP_EVENT_SQUOTE: + return 1; + case TEP_EVENT_ERROR ... TEP_EVENT_DELIM: + default: + return 0; + } +} + +static void free_flag_sym(struct tep_print_flag_sym *fsym) +{ + struct tep_print_flag_sym *next; + + while (fsym) { + next = fsym->next; + free(fsym->value); + free(fsym->str); + free(fsym); + fsym = next; + } +} + +static void free_arg(struct tep_print_arg *arg) +{ + struct tep_print_arg *farg; + + if (!arg) + return; + + switch (arg->type) { + case TEP_PRINT_ATOM: + free(arg->atom.atom); + break; + case TEP_PRINT_FIELD: + free(arg->field.name); + break; + case TEP_PRINT_FLAGS: + free_arg(arg->flags.field); + free(arg->flags.delim); + free_flag_sym(arg->flags.flags); + break; + case TEP_PRINT_SYMBOL: + free_arg(arg->symbol.field); + free_flag_sym(arg->symbol.symbols); + break; + case TEP_PRINT_HEX: + case TEP_PRINT_HEX_STR: + free_arg(arg->hex.field); + free_arg(arg->hex.size); + break; + case TEP_PRINT_INT_ARRAY: + free_arg(arg->int_array.field); + free_arg(arg->int_array.count); + free_arg(arg->int_array.el_size); + break; + case TEP_PRINT_TYPE: + free(arg->typecast.type); + free_arg(arg->typecast.item); + break; + case TEP_PRINT_STRING: + case TEP_PRINT_BSTRING: + free(arg->string.string); + break; + case TEP_PRINT_BITMASK: + free(arg->bitmask.bitmask); + break; + case TEP_PRINT_DYNAMIC_ARRAY: + case TEP_PRINT_DYNAMIC_ARRAY_LEN: + free(arg->dynarray.index); + break; + case TEP_PRINT_OP: + free(arg->op.op); + free_arg(arg->op.left); + free_arg(arg->op.right); + break; + case TEP_PRINT_FUNC: + while (arg->func.args) { + farg = arg->func.args; + arg->func.args = farg->next; + free_arg(farg); + } + break; + + case TEP_PRINT_NULL: + default: + break; + } + + free(arg); +} + +static enum tep_event_type get_type(int ch) +{ + if (ch == '\n') + return TEP_EVENT_NEWLINE; + if (isspace(ch)) + return TEP_EVENT_SPACE; + if (isalnum(ch) || ch == '_') + return TEP_EVENT_ITEM; + if (ch == '\'') + return TEP_EVENT_SQUOTE; + if (ch == '"') + return TEP_EVENT_DQUOTE; + if (!isprint(ch)) + return TEP_EVENT_NONE; + if (ch == '(' || ch == ')' || ch == ',') + return TEP_EVENT_DELIM; + + return TEP_EVENT_OP; +} + +static int __read_char(void) +{ + if (input_buf_ptr >= input_buf_siz) + return -1; + + return input_buf[input_buf_ptr++]; +} + +/** + * peek_char - peek at the next character that will be read + * + * Returns the next character read, or -1 if end of buffer. + */ +__hidden int peek_char(void) +{ + if (input_buf_ptr >= input_buf_siz) + return -1; + + return input_buf[input_buf_ptr]; +} + +static int extend_token(char **tok, char *buf, int size) +{ + char *newtok = realloc(*tok, size); + + if (!newtok) { + free(*tok); + *tok = NULL; + return -1; + } + + if (!*tok) + strcpy(newtok, buf); + else + strcat(newtok, buf); + *tok = newtok; + + return 0; +} + +static enum tep_event_type force_token(const char *str, char **tok); + +static enum tep_event_type __read_token(char **tok) +{ + char buf[BUFSIZ]; + int ch, last_ch, quote_ch, next_ch; + int i = 0; + int tok_size = 0; + enum tep_event_type type; + + *tok = NULL; + + + ch = __read_char(); + if (ch < 0) + return TEP_EVENT_NONE; + + type = get_type(ch); + if (type == TEP_EVENT_NONE) + return type; + + buf[i++] = ch; + + switch (type) { + case TEP_EVENT_NEWLINE: + case TEP_EVENT_DELIM: + if (asprintf(tok, "%c", ch) < 0) + return TEP_EVENT_ERROR; + + return type; + + case TEP_EVENT_OP: + switch (ch) { + case '-': + next_ch = peek_char(); + if (next_ch == '>') { + buf[i++] = __read_char(); + break; + } + /* fall through */ + case '+': + case '|': + case '&': + case '>': + case '<': + last_ch = ch; + ch = peek_char(); + if (ch != last_ch) + goto test_equal; + buf[i++] = __read_char(); + switch (last_ch) { + case '>': + case '<': + goto test_equal; + default: + break; + } + break; + case '!': + case '=': + goto test_equal; + default: /* what should we do instead? */ + break; + } + buf[i] = 0; + *tok = strdup(buf); + return type; + + test_equal: + ch = peek_char(); + if (ch == '=') + buf[i++] = __read_char(); + goto out; + + case TEP_EVENT_DQUOTE: + case TEP_EVENT_SQUOTE: + /* don't keep quotes */ + i--; + quote_ch = ch; + last_ch = 0; + concat: + do { + if (i == (BUFSIZ - 1)) { + buf[i] = 0; + tok_size += BUFSIZ; + + if (extend_token(tok, buf, tok_size) < 0) + return TEP_EVENT_NONE; + i = 0; + } + last_ch = ch; + ch = __read_char(); + buf[i++] = ch; + /* the '\' '\' will cancel itself */ + if (ch == '\\' && last_ch == '\\') + last_ch = 0; + } while (ch != quote_ch || last_ch == '\\'); + /* remove the last quote */ + i--; + + /* + * For strings (double quotes) check the next token. + * If it is another string, concatinate the two. + */ + if (type == TEP_EVENT_DQUOTE) { + unsigned long long save_input_buf_ptr = input_buf_ptr; + + do { + ch = __read_char(); + } while (isspace(ch)); + if (ch == '"') + goto concat; + input_buf_ptr = save_input_buf_ptr; + } + + goto out; + + case TEP_EVENT_ERROR ... TEP_EVENT_SPACE: + case TEP_EVENT_ITEM: + default: + break; + } + + while (get_type(peek_char()) == type) { + if (i == (BUFSIZ - 1)) { + buf[i] = 0; + tok_size += BUFSIZ; + + if (extend_token(tok, buf, tok_size) < 0) + return TEP_EVENT_NONE; + i = 0; + } + ch = __read_char(); + buf[i++] = ch; + } + + out: + buf[i] = 0; + if (extend_token(tok, buf, tok_size + i + 1) < 0) + return TEP_EVENT_NONE; + + if (type == TEP_EVENT_ITEM) { + /* + * Older versions of the kernel has a bug that + * creates invalid symbols and will break the mac80211 + * parsing. This is a work around to that bug. + * + * See Linux kernel commit: + * 811cb50baf63461ce0bdb234927046131fc7fa8b + */ + if (strcmp(*tok, "LOCAL_PR_FMT") == 0) { + free(*tok); + *tok = NULL; + return force_token("\"%s\" ", tok); + } else if (strcmp(*tok, "STA_PR_FMT") == 0) { + free(*tok); + *tok = NULL; + return force_token("\" sta:%pM\" ", tok); + } else if (strcmp(*tok, "VIF_PR_FMT") == 0) { + free(*tok); + *tok = NULL; + return force_token("\" vif:%p(%d)\" ", tok); + } + } + + return type; +} + +static enum tep_event_type force_token(const char *str, char **tok) +{ + const char *save_input_buf; + unsigned long long save_input_buf_ptr; + unsigned long long save_input_buf_siz; + enum tep_event_type type; + + /* save off the current input pointers */ + save_input_buf = input_buf; + save_input_buf_ptr = input_buf_ptr; + save_input_buf_siz = input_buf_siz; + + init_input_buf(str, strlen(str)); + + type = __read_token(tok); + + /* reset back to original token */ + input_buf = save_input_buf; + input_buf_ptr = save_input_buf_ptr; + input_buf_siz = save_input_buf_siz; + + return type; +} + +/** + * free_token - free a token returned by tep_read_token + * @token: the token to free + */ +__hidden void free_token(char *tok) +{ + if (tok) + free(tok); +} + +/** + * read_token - access to utilities to use the tep parser + * @tok: The token to return + * + * This will parse tokens from the string given by + * tep_init_data(). + * + * Returns the token type. + */ +__hidden enum tep_event_type read_token(char **tok) +{ + enum tep_event_type type; + + for (;;) { + type = __read_token(tok); + if (type != TEP_EVENT_SPACE) + return type; + + free_token(*tok); + } + + /* not reached */ + *tok = NULL; + return TEP_EVENT_NONE; +} + +/* no newline */ +static enum tep_event_type read_token_item(char **tok) +{ + enum tep_event_type type; + + for (;;) { + type = __read_token(tok); + if (type != TEP_EVENT_SPACE && type != TEP_EVENT_NEWLINE) + return type; + free_token(*tok); + *tok = NULL; + } + + /* not reached */ + *tok = NULL; + return TEP_EVENT_NONE; +} + +static int test_type(enum tep_event_type type, enum tep_event_type expect) +{ + if (type != expect) { + do_warning("Error: expected type %d but read %d", + expect, type); + return -1; + } + return 0; +} + +static int test_type_token(enum tep_event_type type, const char *token, + enum tep_event_type expect, const char *expect_tok) +{ + if (type != expect) { + do_warning("Error: expected type %d but read %d", + expect, type); + return -1; + } + + if (strcmp(token, expect_tok) != 0) { + do_warning("Error: expected '%s' but read '%s'", + expect_tok, token); + return -1; + } + return 0; +} + +static int __read_expect_type(enum tep_event_type expect, char **tok, int newline_ok) +{ + enum tep_event_type type; + + if (newline_ok) + type = read_token(tok); + else + type = read_token_item(tok); + return test_type(type, expect); +} + +static int read_expect_type(enum tep_event_type expect, char **tok) +{ + return __read_expect_type(expect, tok, 1); +} + +static int __read_expected(enum tep_event_type expect, const char *str, + int newline_ok) +{ + enum tep_event_type type; + char *token; + int ret; + + if (newline_ok) + type = read_token(&token); + else + type = read_token_item(&token); + + ret = test_type_token(type, token, expect, str); + + free_token(token); + + return ret; +} + +static int read_expected(enum tep_event_type expect, const char *str) +{ + return __read_expected(expect, str, 1); +} + +static int read_expected_item(enum tep_event_type expect, const char *str) +{ + return __read_expected(expect, str, 0); +} + +static char *event_read_name(void) +{ + char *token; + + if (read_expected(TEP_EVENT_ITEM, "name") < 0) + return NULL; + + if (read_expected(TEP_EVENT_OP, ":") < 0) + return NULL; + + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto fail; + + return token; + + fail: + free_token(token); + return NULL; +} + +static int event_read_id(void) +{ + char *token; + int id; + + if (read_expected_item(TEP_EVENT_ITEM, "ID") < 0) + return -1; + + if (read_expected(TEP_EVENT_OP, ":") < 0) + return -1; + + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto fail; + + id = strtoul(token, NULL, 0); + free_token(token); + return id; + + fail: + free_token(token); + return -1; +} + +static int field_is_string(struct tep_format_field *field) +{ + if ((field->flags & TEP_FIELD_IS_ARRAY) && + (strstr(field->type, "char") || strstr(field->type, "u8") || + strstr(field->type, "s8"))) + return 1; + + return 0; +} + +static int field_is_dynamic(struct tep_format_field *field) +{ + if (strncmp(field->type, "__data_loc", 10) == 0) + return 1; + + return 0; +} + +static int field_is_relative_dynamic(struct tep_format_field *field) +{ + if (strncmp(field->type, "__rel_loc", 9) == 0) + return 1; + + return 0; +} + +static int field_is_long(struct tep_format_field *field) +{ + /* includes long long */ + if (strstr(field->type, "long")) + return 1; + + return 0; +} + +static unsigned int type_size(const char *name) +{ + /* This covers all TEP_FIELD_IS_STRING types. */ + static struct { + const char *type; + unsigned int size; + } table[] = { + { "u8", 1 }, + { "u16", 2 }, + { "u32", 4 }, + { "u64", 8 }, + { "s8", 1 }, + { "s16", 2 }, + { "s32", 4 }, + { "s64", 8 }, + { "char", 1 }, + { }, + }; + int i; + + for (i = 0; table[i].type; i++) { + if (!strcmp(table[i].type, name)) + return table[i].size; + } + + return 0; +} + +static int append(char **buf, const char *delim, const char *str) +{ + char *new_buf; + + new_buf = realloc(*buf, strlen(*buf) + strlen(delim) + strlen(str) + 1); + if (!new_buf) + return -1; + strcat(new_buf, delim); + strcat(new_buf, str); + *buf = new_buf; + return 0; +} + +static int event_read_fields(struct tep_event *event, struct tep_format_field **fields) +{ + struct tep_format_field *field = NULL; + enum tep_event_type type; + char *token; + char *last_token; + char *delim = " "; + int count = 0; + int ret; + + do { + unsigned int size_dynamic = 0; + + type = read_token(&token); + if (type == TEP_EVENT_NEWLINE) { + free_token(token); + return count; + } + + count++; + + if (test_type_token(type, token, TEP_EVENT_ITEM, "field")) + goto fail; + free_token(token); + + type = read_token(&token); + /* + * The ftrace fields may still use the "special" name. + * Just ignore it. + */ + if (event->flags & TEP_EVENT_FL_ISFTRACE && + type == TEP_EVENT_ITEM && strcmp(token, "special") == 0) { + free_token(token); + type = read_token(&token); + } + + if (test_type_token(type, token, TEP_EVENT_OP, ":") < 0) + goto fail; + + free_token(token); + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto fail; + + last_token = token; + + field = calloc(1, sizeof(*field)); + if (!field) + goto fail; + + field->event = event; + + /* read the rest of the type */ + for (;;) { + type = read_token(&token); + if (type == TEP_EVENT_ITEM || + (type == TEP_EVENT_OP && strcmp(token, "*") == 0) || + /* + * Some of the ftrace fields are broken and have + * an illegal "." in them. + */ + (event->flags & TEP_EVENT_FL_ISFTRACE && + type == TEP_EVENT_OP && strcmp(token, ".") == 0)) { + + if (strcmp(token, "*") == 0) + field->flags |= TEP_FIELD_IS_POINTER; + + if (field->type) { + ret = append(&field->type, delim, last_token); + free(last_token); + if (ret < 0) + goto fail; + } else + field->type = last_token; + last_token = token; + delim = " "; + continue; + } + + /* Handle __attribute__((user)) */ + if ((type == TEP_EVENT_DELIM) && + strcmp("__attribute__", last_token) == 0 && + token[0] == '(') { + int depth = 1; + int ret; + + ret = append(&field->type, " ", last_token); + ret |= append(&field->type, "", "("); + if (ret < 0) + goto fail; + + delim = " "; + while ((type = read_token(&token)) != TEP_EVENT_NONE) { + if (type == TEP_EVENT_DELIM) { + if (token[0] == '(') + depth++; + else if (token[0] == ')') + depth--; + if (!depth) + break; + ret = append(&field->type, "", token); + delim = ""; + } else { + ret = append(&field->type, delim, token); + delim = " "; + } + if (ret < 0) + goto fail; + free(last_token); + last_token = token; + } + continue; + } + break; + } + + if (!field->type) { + do_warning_event(event, "%s: no type found", __func__); + goto fail; + } + field->name = field->alias = last_token; + + if (test_type(type, TEP_EVENT_OP)) + goto fail; + + if (strcmp(token, "[") == 0) { + enum tep_event_type last_type = type; + char *brackets = token; + + field->flags |= TEP_FIELD_IS_ARRAY; + + type = read_token(&token); + + if (type == TEP_EVENT_ITEM) + field->arraylen = strtoul(token, NULL, 0); + else + field->arraylen = 0; + + while (strcmp(token, "]") != 0) { + const char *delim; + + if (last_type == TEP_EVENT_ITEM && + type == TEP_EVENT_ITEM) + delim = " "; + else + delim = ""; + + last_type = type; + + ret = append(&brackets, delim, token); + if (ret < 0) { + free(brackets); + goto fail; + } + /* We only care about the last token */ + field->arraylen = strtoul(token, NULL, 0); + free_token(token); + type = read_token(&token); + if (type == TEP_EVENT_NONE) { + free(brackets); + do_warning_event(event, "failed to find token"); + goto fail; + } + } + + free_token(token); + + ret = append(&brackets, "", "]"); + if (ret < 0) { + free(brackets); + goto fail; + } + + /* add brackets to type */ + + type = read_token(&token); + /* + * If the next token is not an OP, then it is of + * the format: type [] item; + */ + if (type == TEP_EVENT_ITEM) { + ret = append(&field->type, " ", field->name); + if (ret < 0) { + free(brackets); + goto fail; + } + ret = append(&field->type, "", brackets); + + size_dynamic = type_size(field->name); + free_token(field->name); + field->name = field->alias = token; + type = read_token(&token); + } else { + ret = append(&field->type, "", brackets); + if (ret < 0) { + free(brackets); + goto fail; + } + } + free(brackets); + } + + if (field_is_string(field)) + field->flags |= TEP_FIELD_IS_STRING; + if (field_is_dynamic(field)) + field->flags |= TEP_FIELD_IS_DYNAMIC; + if (field_is_relative_dynamic(field)) + field->flags |= TEP_FIELD_IS_DYNAMIC | TEP_FIELD_IS_RELATIVE; + if (field_is_long(field)) + field->flags |= TEP_FIELD_IS_LONG; + + if (test_type_token(type, token, TEP_EVENT_OP, ";")) + goto fail; + free_token(token); + + if (read_expected(TEP_EVENT_ITEM, "offset") < 0) + goto fail_expect; + + if (read_expected(TEP_EVENT_OP, ":") < 0) + goto fail_expect; + + if (read_expect_type(TEP_EVENT_ITEM, &token)) + goto fail; + field->offset = strtoul(token, NULL, 0); + free_token(token); + + if (read_expected(TEP_EVENT_OP, ";") < 0) + goto fail_expect; + + if (read_expected(TEP_EVENT_ITEM, "size") < 0) + goto fail_expect; + + if (read_expected(TEP_EVENT_OP, ":") < 0) + goto fail_expect; + + if (read_expect_type(TEP_EVENT_ITEM, &token)) + goto fail; + field->size = strtoul(token, NULL, 0); + free_token(token); + + if (read_expected(TEP_EVENT_OP, ";") < 0) + goto fail_expect; + + type = read_token(&token); + if (type != TEP_EVENT_NEWLINE) { + /* newer versions of the kernel have a "signed" type */ + if (test_type_token(type, token, TEP_EVENT_ITEM, "signed")) + goto fail; + + free_token(token); + + if (read_expected(TEP_EVENT_OP, ":") < 0) + goto fail_expect; + + if (read_expect_type(TEP_EVENT_ITEM, &token)) + goto fail; + + if (strtoul(token, NULL, 0)) + field->flags |= TEP_FIELD_IS_SIGNED; + + free_token(token); + if (read_expected(TEP_EVENT_OP, ";") < 0) + goto fail_expect; + + if (read_expect_type(TEP_EVENT_NEWLINE, &token)) + goto fail; + } + + free_token(token); + + if (field->flags & TEP_FIELD_IS_ARRAY) { + if (field->arraylen) + field->elementsize = field->size / field->arraylen; + else if (field->flags & TEP_FIELD_IS_DYNAMIC) + field->elementsize = size_dynamic; + else if (field->flags & TEP_FIELD_IS_STRING) + field->elementsize = 1; + else if (field->flags & TEP_FIELD_IS_LONG) + field->elementsize = event->tep ? + event->tep->long_size : + sizeof(long); + } else + field->elementsize = field->size; + + *fields = field; + fields = &field->next; + + } while (1); + + return 0; + +fail: + free_token(token); +fail_expect: + if (field) { + free(field->type); + free(field->name); + free(field); + } + return -1; +} + +static int event_read_format(struct tep_event *event) +{ + char *token; + int ret; + + if (read_expected_item(TEP_EVENT_ITEM, "format") < 0) + return -1; + + if (read_expected(TEP_EVENT_OP, ":") < 0) + return -1; + + if (read_expect_type(TEP_EVENT_NEWLINE, &token)) + goto fail; + free_token(token); + + ret = event_read_fields(event, &event->format.common_fields); + if (ret < 0) + return ret; + event->format.nr_common = ret; + + ret = event_read_fields(event, &event->format.fields); + if (ret < 0) + return ret; + event->format.nr_fields = ret; + + return 0; + + fail: + free_token(token); + return -1; +} + +static enum tep_event_type +process_arg_token(struct tep_event *event, struct tep_print_arg *arg, + char **tok, enum tep_event_type type); + +static enum tep_event_type +process_arg(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + enum tep_event_type type; + char *token; + + type = read_token(&token); + *tok = token; + + return process_arg_token(event, arg, tok, type); +} + +static enum tep_event_type +process_op(struct tep_event *event, struct tep_print_arg *arg, char **tok); + +/* + * For __print_symbolic() and __print_flags, we need to completely + * evaluate the first argument, which defines what to print next. + */ +static enum tep_event_type +process_field_arg(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + enum tep_event_type type; + + type = process_arg(event, arg, tok); + + while (type == TEP_EVENT_OP) { + type = process_op(event, arg, tok); + } + + return type; +} + +static enum tep_event_type +process_cond(struct tep_event *event, struct tep_print_arg *top, char **tok) +{ + struct tep_print_arg *arg, *left, *right; + enum tep_event_type type; + char *token = NULL; + + arg = alloc_arg(); + left = alloc_arg(); + right = alloc_arg(); + + if (!arg || !left || !right) { + do_warning_event(event, "%s: not enough memory!", __func__); + /* arg will be freed at out_free */ + free_arg(left); + free_arg(right); + goto out_free; + } + + arg->type = TEP_PRINT_OP; + arg->op.left = left; + arg->op.right = right; + + *tok = NULL; + type = process_arg(event, left, &token); + + again: + if (type == TEP_EVENT_ERROR) + goto out_free; + + /* Handle other operations in the arguments */ + if (type == TEP_EVENT_OP && strcmp(token, ":") != 0) { + type = process_op(event, left, &token); + goto again; + } + + if (test_type_token(type, token, TEP_EVENT_OP, ":")) + goto out_free; + + arg->op.op = token; + + type = process_arg(event, right, &token); + + top->op.right = arg; + + *tok = token; + return type; + +out_free: + /* Top may point to itself */ + top->op.right = NULL; + free_token(token); + free_arg(arg); + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_array(struct tep_event *event, struct tep_print_arg *top, char **tok) +{ + struct tep_print_arg *arg; + enum tep_event_type type; + char *token = NULL; + + arg = alloc_arg(); + if (!arg) { + do_warning_event(event, "%s: not enough memory!", __func__); + /* '*tok' is set to top->op.op. No need to free. */ + *tok = NULL; + return TEP_EVENT_ERROR; + } + + *tok = NULL; + type = process_arg(event, arg, &token); + if (test_type_token(type, token, TEP_EVENT_OP, "]")) + goto out_free; + + top->op.right = arg; + + free_token(token); + type = read_token_item(&token); + *tok = token; + + return type; + +out_free: + free_token(token); + free_arg(arg); + return TEP_EVENT_ERROR; +} + +static int get_op_prio(char *op) +{ + if (!op[1]) { + switch (op[0]) { + case '~': + case '!': + return 4; + case '*': + case '/': + case '%': + return 6; + case '+': + case '-': + return 7; + /* '>>' and '<<' are 8 */ + case '<': + case '>': + return 9; + /* '==' and '!=' are 10 */ + case '&': + return 11; + case '^': + return 12; + case '|': + return 13; + case '?': + return 16; + default: + do_warning("unknown op '%c'", op[0]); + return -1; + } + } else { + if (strcmp(op, "++") == 0 || + strcmp(op, "--") == 0) { + return 3; + } else if (strcmp(op, ">>") == 0 || + strcmp(op, "<<") == 0) { + return 8; + } else if (strcmp(op, ">=") == 0 || + strcmp(op, "<=") == 0) { + return 9; + } else if (strcmp(op, "==") == 0 || + strcmp(op, "!=") == 0) { + return 10; + } else if (strcmp(op, "&&") == 0) { + return 14; + } else if (strcmp(op, "||") == 0) { + return 15; + } else { + do_warning("unknown op '%s'", op); + return -1; + } + } +} + +static int set_op_prio(struct tep_print_arg *arg) +{ + + /* single ops are the greatest */ + if (!arg->op.left || arg->op.left->type == TEP_PRINT_NULL) + arg->op.prio = 0; + else + arg->op.prio = get_op_prio(arg->op.op); + + return arg->op.prio; +} + +/* Note, *tok does not get freed, but will most likely be saved */ +static enum tep_event_type +process_op(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + struct tep_print_arg *left, *right = NULL; + enum tep_event_type type; + char *token; + + /* the op is passed in via tok */ + token = *tok; + + if (arg->type == TEP_PRINT_OP && !arg->op.left) { + /* handle single op */ + if (token[1]) { + do_warning_event(event, "bad op token %s", token); + goto out_free; + } + switch (token[0]) { + case '~': + case '!': + case '+': + case '-': + break; + default: + do_warning_event(event, "bad op token %s", token); + goto out_free; + + } + + /* make an empty left */ + left = alloc_arg(); + if (!left) + goto out_warn_free; + + left->type = TEP_PRINT_NULL; + arg->op.left = left; + + right = alloc_arg(); + if (!right) + goto out_warn_free; + + arg->op.right = right; + + /* do not free the token, it belongs to an op */ + *tok = NULL; + type = process_arg(event, right, tok); + + } else if (strcmp(token, "?") == 0) { + + left = alloc_arg(); + if (!left) + goto out_warn_free; + + /* copy the top arg to the left */ + *left = *arg; + + arg->type = TEP_PRINT_OP; + arg->op.op = token; + arg->op.left = left; + arg->op.prio = 0; + + /* it will set arg->op.right */ + type = process_cond(event, arg, tok); + + } else if (strcmp(token, ">>") == 0 || + strcmp(token, "<<") == 0 || + strcmp(token, "&") == 0 || + strcmp(token, "|") == 0 || + strcmp(token, "&&") == 0 || + strcmp(token, "||") == 0 || + strcmp(token, "-") == 0 || + strcmp(token, "+") == 0 || + strcmp(token, "*") == 0 || + strcmp(token, "^") == 0 || + strcmp(token, "/") == 0 || + strcmp(token, "%") == 0 || + strcmp(token, "<") == 0 || + strcmp(token, ">") == 0 || + strcmp(token, "<=") == 0 || + strcmp(token, ">=") == 0 || + strcmp(token, "==") == 0 || + strcmp(token, "!=") == 0) { + + left = alloc_arg(); + if (!left) + goto out_warn_free; + + /* copy the top arg to the left */ + *left = *arg; + + arg->type = TEP_PRINT_OP; + arg->op.op = token; + arg->op.left = left; + arg->op.right = NULL; + + if (set_op_prio(arg) == -1) { + event->flags |= TEP_EVENT_FL_FAILED; + /* arg->op.op (= token) will be freed at out_free */ + arg->op.op = NULL; + goto out_free; + } + + type = read_token_item(&token); + *tok = token; + + /* could just be a type pointer */ + if ((strcmp(arg->op.op, "*") == 0) && + type == TEP_EVENT_DELIM && (strcmp(token, ")") == 0)) { + int ret; + + if (left->type != TEP_PRINT_ATOM) { + do_warning_event(event, "bad pointer type"); + goto out_free; + } + ret = append(&left->atom.atom, " ", "*"); + if (ret < 0) + goto out_warn_free; + + free(arg->op.op); + *arg = *left; + free(left); + + return type; + } + + right = alloc_arg(); + if (!right) + goto out_warn_free; + + type = process_arg_token(event, right, tok, type); + if (type == TEP_EVENT_ERROR) { + free_arg(right); + /* token was freed in process_arg_token() via *tok */ + token = NULL; + goto out_free; + } + + if (right->type == TEP_PRINT_OP && + get_op_prio(arg->op.op) < get_op_prio(right->op.op)) { + struct tep_print_arg tmp; + + /* rotate ops according to the priority */ + arg->op.right = right->op.left; + + tmp = *arg; + *arg = *right; + *right = tmp; + + arg->op.left = right; + } else { + arg->op.right = right; + } + + } else if (strcmp(token, "[") == 0) { + + left = alloc_arg(); + if (!left) + goto out_warn_free; + + *left = *arg; + + arg->type = TEP_PRINT_OP; + arg->op.op = token; + arg->op.left = left; + + arg->op.prio = 0; + + /* it will set arg->op.right */ + type = process_array(event, arg, tok); + + } else { + do_warning_event(event, "unknown op '%s'", token); + event->flags |= TEP_EVENT_FL_FAILED; + /* the arg is now the left side */ + goto out_free; + } + + if (type == TEP_EVENT_OP && strcmp(*tok, ":") != 0) { + int prio; + + /* higher prios need to be closer to the root */ + prio = get_op_prio(*tok); + + if (prio > arg->op.prio) + return process_op(event, arg, tok); + + return process_op(event, right, tok); + } + + return type; + +out_warn_free: + do_warning_event(event, "%s: not enough memory!", __func__); +out_free: + free_token(token); + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_entry(struct tep_event *event __maybe_unused, struct tep_print_arg *arg, + char **tok) +{ + enum tep_event_type type; + char *field; + char *token; + + if (read_expected(TEP_EVENT_OP, "->") < 0) + goto out_err; + + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto out_free; + field = token; + + arg->type = TEP_PRINT_FIELD; + arg->field.name = field; + + if (is_flag_field) { + arg->field.field = tep_find_any_field(event, arg->field.name); + arg->field.field->flags |= TEP_FIELD_IS_FLAG; + is_flag_field = 0; + } else if (is_symbolic_field) { + arg->field.field = tep_find_any_field(event, arg->field.name); + arg->field.field->flags |= TEP_FIELD_IS_SYMBOLIC; + is_symbolic_field = 0; + } + + type = read_token(&token); + *tok = token; + + return type; + + out_free: + free_token(token); + out_err: + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static int alloc_and_process_delim(struct tep_event *event, char *next_token, + struct tep_print_arg **print_arg) +{ + struct tep_print_arg *field; + enum tep_event_type type; + char *token; + int ret = 0; + + field = alloc_arg(); + if (!field) { + do_warning_event(event, "%s: not enough memory!", __func__); + errno = ENOMEM; + return -1; + } + + type = process_arg(event, field, &token); + + if (test_type_token(type, token, TEP_EVENT_DELIM, next_token)) { + errno = EINVAL; + ret = -1; + free_arg(field); + goto out_free_token; + } + + *print_arg = field; + +out_free_token: + free_token(token); + + return ret; +} + +static char *arg_eval (struct tep_print_arg *arg); + +static unsigned long long +eval_type_str(unsigned long long val, const char *type, int pointer) +{ + int sign = 0; + char *ref; + int len; + + len = strlen(type); + + if (pointer) { + + if (type[len-1] != '*') { + do_warning("pointer expected with non pointer type"); + return val; + } + + ref = malloc(len); + if (!ref) { + do_warning("%s: not enough memory!", __func__); + return val; + } + memcpy(ref, type, len); + + /* chop off the " *" */ + ref[len - 2] = 0; + + val = eval_type_str(val, ref, 0); + free(ref); + return val; + } + + /* check if this is a pointer */ + if (type[len - 1] == '*') + return val; + + /* Try to figure out the arg size*/ + if (strncmp(type, "struct", 6) == 0) + /* all bets off */ + return val; + + if (strcmp(type, "u8") == 0) + return val & 0xff; + + if (strcmp(type, "u16") == 0) + return val & 0xffff; + + if (strcmp(type, "u32") == 0) + return val & 0xffffffff; + + if (strcmp(type, "u64") == 0 || + strcmp(type, "s64") == 0) + return val; + + if (strcmp(type, "s8") == 0) + return (unsigned long long)(char)val & 0xff; + + if (strcmp(type, "s16") == 0) + return (unsigned long long)(short)val & 0xffff; + + if (strcmp(type, "s32") == 0) + return (unsigned long long)(int)val & 0xffffffff; + + if (strncmp(type, "unsigned ", 9) == 0) { + sign = 0; + type += 9; + } + + if (strcmp(type, "char") == 0) { + if (sign) + return (unsigned long long)(char)val & 0xff; + else + return val & 0xff; + } + + if (strcmp(type, "short") == 0) { + if (sign) + return (unsigned long long)(short)val & 0xffff; + else + return val & 0xffff; + } + + if (strcmp(type, "int") == 0) { + if (sign) + return (unsigned long long)(int)val & 0xffffffff; + else + return val & 0xffffffff; + } + + return val; +} + +/* + * Try to figure out the type. + */ +static unsigned long long +eval_type(unsigned long long val, struct tep_print_arg *arg, int pointer) +{ + if (arg->type != TEP_PRINT_TYPE) { + do_warning("expected type argument"); + return 0; + } + + return eval_type_str(val, arg->typecast.type, pointer); +} + +static int arg_num_eval(struct tep_print_arg *arg, long long *val) +{ + long long left, right; + int ret = 1; + + switch (arg->type) { + case TEP_PRINT_ATOM: + *val = strtoll(arg->atom.atom, NULL, 0); + break; + case TEP_PRINT_TYPE: + ret = arg_num_eval(arg->typecast.item, val); + if (!ret) + break; + *val = eval_type(*val, arg, 0); + break; + case TEP_PRINT_OP: + switch (arg->op.op[0]) { + case '|': + ret = arg_num_eval(arg->op.left, &left); + if (!ret) + break; + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + if (arg->op.op[1]) + *val = left || right; + else + *val = left | right; + break; + case '&': + ret = arg_num_eval(arg->op.left, &left); + if (!ret) + break; + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + if (arg->op.op[1]) + *val = left && right; + else + *val = left & right; + break; + case '<': + ret = arg_num_eval(arg->op.left, &left); + if (!ret) + break; + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + switch (arg->op.op[1]) { + case 0: + *val = left < right; + break; + case '<': + *val = left << right; + break; + case '=': + *val = left <= right; + break; + default: + do_warning("unknown op '%s'", arg->op.op); + ret = 0; + } + break; + case '>': + ret = arg_num_eval(arg->op.left, &left); + if (!ret) + break; + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + switch (arg->op.op[1]) { + case 0: + *val = left > right; + break; + case '>': + *val = left >> right; + break; + case '=': + *val = left >= right; + break; + default: + do_warning("unknown op '%s'", arg->op.op); + ret = 0; + } + break; + case '=': + ret = arg_num_eval(arg->op.left, &left); + if (!ret) + break; + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + + if (arg->op.op[1] != '=') { + do_warning("unknown op '%s'", arg->op.op); + ret = 0; + } else + *val = left == right; + break; + case '!': + ret = arg_num_eval(arg->op.left, &left); + if (!ret) + break; + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + + switch (arg->op.op[1]) { + case '=': + *val = left != right; + break; + default: + do_warning("unknown op '%s'", arg->op.op); + ret = 0; + } + break; + case '-': + /* check for negative */ + if (arg->op.left->type == TEP_PRINT_NULL) + left = 0; + else + ret = arg_num_eval(arg->op.left, &left); + if (!ret) + break; + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + *val = left - right; + break; + case '+': + if (arg->op.left->type == TEP_PRINT_NULL) + left = 0; + else + ret = arg_num_eval(arg->op.left, &left); + if (!ret) + break; + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + *val = left + right; + break; + case '~': + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + *val = ~right; + break; + default: + do_warning("unknown op '%s'", arg->op.op); + ret = 0; + } + break; + + case TEP_PRINT_NULL: + case TEP_PRINT_FIELD ... TEP_PRINT_SYMBOL: + case TEP_PRINT_STRING: + case TEP_PRINT_BSTRING: + case TEP_PRINT_BITMASK: + default: + do_warning("invalid eval type %d", arg->type); + ret = 0; + + } + return ret; +} + +static char *arg_eval (struct tep_print_arg *arg) +{ + long long val; + static char buf[24]; + + switch (arg->type) { + case TEP_PRINT_ATOM: + return arg->atom.atom; + case TEP_PRINT_TYPE: + return arg_eval(arg->typecast.item); + case TEP_PRINT_OP: + if (!arg_num_eval(arg, &val)) + break; + sprintf(buf, "%lld", val); + return buf; + + case TEP_PRINT_NULL: + case TEP_PRINT_FIELD ... TEP_PRINT_SYMBOL: + case TEP_PRINT_STRING: + case TEP_PRINT_BSTRING: + case TEP_PRINT_BITMASK: + default: + do_warning("invalid eval type %d", arg->type); + break; + } + + return NULL; +} + +static enum tep_event_type +process_fields(struct tep_event *event, struct tep_print_flag_sym **list, char **tok) +{ + enum tep_event_type type; + struct tep_print_arg *arg = NULL; + struct tep_print_flag_sym *field; + char *token = *tok; + char *value; + + do { + free_token(token); + type = read_token_item(&token); + if (test_type_token(type, token, TEP_EVENT_OP, "{")) + break; + + arg = alloc_arg(); + if (!arg) + goto out_free; + + free_token(token); + type = process_arg(event, arg, &token); + + if (type == TEP_EVENT_OP) + type = process_op(event, arg, &token); + + if (type == TEP_EVENT_ERROR) + goto out_free; + + if (test_type_token(type, token, TEP_EVENT_DELIM, ",")) + goto out_free; + + field = calloc(1, sizeof(*field)); + if (!field) + goto out_free; + + value = arg_eval(arg); + if (value == NULL) + goto out_free_field; + field->value = strdup(value); + if (field->value == NULL) + goto out_free_field; + + free_arg(arg); + arg = alloc_arg(); + if (!arg) + goto out_free; + + free_token(token); + type = process_arg(event, arg, &token); + if (test_type_token(type, token, TEP_EVENT_OP, "}")) + goto out_free_field; + + value = arg_eval(arg); + if (value == NULL) + goto out_free_field; + field->str = strdup(value); + if (field->str == NULL) + goto out_free_field; + free_arg(arg); + arg = NULL; + + *list = field; + list = &field->next; + + free_token(token); + type = read_token_item(&token); + } while (type == TEP_EVENT_DELIM && strcmp(token, ",") == 0); + + *tok = token; + return type; + +out_free_field: + free_flag_sym(field); +out_free: + free_arg(arg); + free_token(token); + *tok = NULL; + + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_flags(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + struct tep_print_arg *field; + enum tep_event_type type; + char *token = NULL; + + memset(arg, 0, sizeof(*arg)); + arg->type = TEP_PRINT_FLAGS; + + field = alloc_arg(); + if (!field) { + do_warning_event(event, "%s: not enough memory!", __func__); + goto out_free; + } + + type = process_field_arg(event, field, &token); + + /* Handle operations in the first argument */ + while (type == TEP_EVENT_OP) + type = process_op(event, field, &token); + + if (test_type_token(type, token, TEP_EVENT_DELIM, ",")) + goto out_free_field; + free_token(token); + + arg->flags.field = field; + + type = read_token_item(&token); + if (event_item_type(type)) { + arg->flags.delim = token; + type = read_token_item(&token); + } + + if (test_type_token(type, token, TEP_EVENT_DELIM, ",")) + goto out_free; + + type = process_fields(event, &arg->flags.flags, &token); + if (test_type_token(type, token, TEP_EVENT_DELIM, ")")) + goto out_free; + + free_token(token); + type = read_token_item(tok); + return type; + +out_free_field: + free_arg(field); +out_free: + free_token(token); + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_symbols(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + struct tep_print_arg *field; + enum tep_event_type type; + char *token = NULL; + + memset(arg, 0, sizeof(*arg)); + arg->type = TEP_PRINT_SYMBOL; + + field = alloc_arg(); + if (!field) { + do_warning_event(event, "%s: not enough memory!", __func__); + goto out_free; + } + + type = process_field_arg(event, field, &token); + + if (test_type_token(type, token, TEP_EVENT_DELIM, ",")) + goto out_free_field; + + arg->symbol.field = field; + + type = process_fields(event, &arg->symbol.symbols, &token); + if (test_type_token(type, token, TEP_EVENT_DELIM, ")")) + goto out_free; + + free_token(token); + type = read_token_item(tok); + return type; + +out_free_field: + free_arg(field); +out_free: + free_token(token); + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_hex_common(struct tep_event *event, struct tep_print_arg *arg, + char **tok, enum tep_print_arg_type type) +{ + memset(arg, 0, sizeof(*arg)); + arg->type = type; + + if (alloc_and_process_delim(event, ",", &arg->hex.field)) + goto out; + + if (alloc_and_process_delim(event, ")", &arg->hex.size)) + goto free_field; + + return read_token_item(tok); + +free_field: + free_arg(arg->hex.field); + arg->hex.field = NULL; +out: + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_hex(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + return process_hex_common(event, arg, tok, TEP_PRINT_HEX); +} + +static enum tep_event_type +process_hex_str(struct tep_event *event, struct tep_print_arg *arg, + char **tok) +{ + return process_hex_common(event, arg, tok, TEP_PRINT_HEX_STR); +} + +static enum tep_event_type +process_int_array(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + memset(arg, 0, sizeof(*arg)); + arg->type = TEP_PRINT_INT_ARRAY; + + if (alloc_and_process_delim(event, ",", &arg->int_array.field)) + goto out; + + if (alloc_and_process_delim(event, ",", &arg->int_array.count)) + goto free_field; + + if (alloc_and_process_delim(event, ")", &arg->int_array.el_size)) + goto free_size; + + return read_token_item(tok); + +free_size: + free_arg(arg->int_array.count); + arg->int_array.count = NULL; +free_field: + free_arg(arg->int_array.field); + arg->int_array.field = NULL; +out: + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_dynamic_array(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + struct tep_format_field *field; + enum tep_event_type type; + char *token; + + memset(arg, 0, sizeof(*arg)); + arg->type = TEP_PRINT_DYNAMIC_ARRAY; + + /* + * The item within the parenthesis is another field that holds + * the index into where the array starts. + */ + type = read_token(&token); + *tok = token; + if (type != TEP_EVENT_ITEM) + goto out_free; + + /* Find the field */ + + field = tep_find_field(event, token); + if (!field) + goto out_free; + + arg->dynarray.field = field; + arg->dynarray.index = 0; + + if (read_expected(TEP_EVENT_DELIM, ")") < 0) + goto out_free; + + free_token(token); + type = read_token_item(&token); + *tok = token; + if (type != TEP_EVENT_OP || strcmp(token, "[") != 0) + return type; + + free_token(token); + arg = alloc_arg(); + if (!arg) { + do_warning_event(event, "%s: not enough memory!", __func__); + *tok = NULL; + return TEP_EVENT_ERROR; + } + + type = process_arg(event, arg, &token); + if (type == TEP_EVENT_ERROR) + goto out_free_arg; + + if (!test_type_token(type, token, TEP_EVENT_OP, "]")) + goto out_free_arg; + + free_token(token); + type = read_token_item(tok); + return type; + + out_free_arg: + free_arg(arg); + out_free: + free_token(token); + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg, + char **tok) +{ + struct tep_format_field *field; + enum tep_event_type type; + char *token; + + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto out_free; + + arg->type = TEP_PRINT_DYNAMIC_ARRAY_LEN; + + /* Find the field */ + field = tep_find_field(event, token); + if (!field) + goto out_free; + + arg->dynarray.field = field; + arg->dynarray.index = 0; + + if (read_expected(TEP_EVENT_DELIM, ")") < 0) + goto out_err; + + free_token(token); + type = read_token(&token); + *tok = token; + + return type; + + out_free: + free_token(token); + out_err: + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_paren(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + struct tep_print_arg *item_arg; + enum tep_event_type type; + char *token; + + type = process_arg(event, arg, &token); + + if (type == TEP_EVENT_ERROR) + goto out_free; + + if (type == TEP_EVENT_OP) + type = process_op(event, arg, &token); + + if (type == TEP_EVENT_ERROR) + goto out_free; + + if (test_type_token(type, token, TEP_EVENT_DELIM, ")")) + goto out_free; + + free_token(token); + type = read_token_item(&token); + + /* + * If the next token is an item or another open paren, then + * this was a typecast. + */ + if (event_item_type(type) || + (type == TEP_EVENT_DELIM && strcmp(token, "(") == 0)) { + + /* make this a typecast and contine */ + + /* prevous must be an atom */ + if (arg->type != TEP_PRINT_ATOM) { + do_warning_event(event, "previous needed to be TEP_PRINT_ATOM"); + goto out_free; + } + + item_arg = alloc_arg(); + if (!item_arg) { + do_warning_event(event, "%s: not enough memory!", + __func__); + goto out_free; + } + + arg->type = TEP_PRINT_TYPE; + arg->typecast.type = arg->atom.atom; + arg->typecast.item = item_arg; + type = process_arg_token(event, item_arg, &token, type); + + } + + *tok = token; + return type; + + out_free: + free_token(token); + *tok = NULL; + return TEP_EVENT_ERROR; +} + + +static enum tep_event_type +process_str(struct tep_event *event __maybe_unused, struct tep_print_arg *arg, + char **tok) +{ + enum tep_event_type type; + char *token; + + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto out_free; + + arg->type = TEP_PRINT_STRING; + arg->string.string = token; + arg->string.field = NULL; + + if (read_expected(TEP_EVENT_DELIM, ")") < 0) + goto out_err; + + type = read_token(&token); + *tok = token; + + return type; + + out_free: + free_token(token); + out_err: + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *arg, + char **tok) +{ + enum tep_event_type type; + char *token; + + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto out_free; + + arg->type = TEP_PRINT_BITMASK; + arg->bitmask.bitmask = token; + arg->bitmask.field = NULL; + + if (read_expected(TEP_EVENT_DELIM, ")") < 0) + goto out_err; + + type = read_token(&token); + *tok = token; + + return type; + + out_free: + free_token(token); + out_err: + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static struct tep_function_handler * +find_func_handler(struct tep_handle *tep, char *func_name) +{ + struct tep_function_handler *func; + + if (!tep) + return NULL; + + for (func = tep->func_handlers; func; func = func->next) { + if (strcmp(func->name, func_name) == 0) + break; + } + + return func; +} + +static void remove_func_handler(struct tep_handle *tep, char *func_name) +{ + struct tep_function_handler *func; + struct tep_function_handler **next; + + next = &tep->func_handlers; + while ((func = *next)) { + if (strcmp(func->name, func_name) == 0) { + *next = func->next; + free_func_handle(func); + break; + } + next = &func->next; + } +} + +static enum tep_event_type +process_func_handler(struct tep_event *event, struct tep_function_handler *func, + struct tep_print_arg *arg, char **tok) +{ + struct tep_print_arg **next_arg; + struct tep_print_arg *farg; + enum tep_event_type type; + char *token; + int i; + + arg->type = TEP_PRINT_FUNC; + arg->func.func = func; + + *tok = NULL; + + next_arg = &(arg->func.args); + for (i = 0; i < func->nr_args; i++) { + farg = alloc_arg(); + if (!farg) { + do_warning_event(event, "%s: not enough memory!", + __func__); + return TEP_EVENT_ERROR; + } + + type = process_arg(event, farg, &token); + if (i < (func->nr_args - 1)) { + if (type != TEP_EVENT_DELIM || strcmp(token, ",") != 0) { + do_warning_event(event, + "Error: function '%s()' expects %d arguments but event %s only uses %d", + func->name, func->nr_args, + event->name, i + 1); + goto err; + } + } else { + if (type != TEP_EVENT_DELIM || strcmp(token, ")") != 0) { + do_warning_event(event, + "Error: function '%s()' only expects %d arguments but event %s has more", + func->name, func->nr_args, event->name); + goto err; + } + } + + *next_arg = farg; + next_arg = &(farg->next); + free_token(token); + } + + type = read_token(&token); + *tok = token; + + return type; + +err: + free_arg(farg); + free_token(token); + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_builtin_expect(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + enum tep_event_type type; + char *token = NULL; + + /* Handle __builtin_expect( cond, #) */ + type = process_arg(event, arg, &token); + + if (type != TEP_EVENT_DELIM || token[0] != ',') + goto out_free; + + free_token(token); + + /* We don't care what the second parameter is of the __builtin_expect() */ + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto out_free; + + if (read_expected(TEP_EVENT_DELIM, ")") < 0) + goto out_free; + + free_token(token); + type = read_token_item(tok); + return type; + +out_free: + free_token(token); + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_function(struct tep_event *event, struct tep_print_arg *arg, + char *token, char **tok) +{ + struct tep_function_handler *func; + + if (strcmp(token, "__print_flags") == 0) { + free_token(token); + is_flag_field = 1; + return process_flags(event, arg, tok); + } + if (strcmp(token, "__print_symbolic") == 0) { + free_token(token); + is_symbolic_field = 1; + return process_symbols(event, arg, tok); + } + if (strcmp(token, "__print_hex") == 0) { + free_token(token); + return process_hex(event, arg, tok); + } + if (strcmp(token, "__print_hex_str") == 0) { + free_token(token); + return process_hex_str(event, arg, tok); + } + if (strcmp(token, "__print_array") == 0) { + free_token(token); + return process_int_array(event, arg, tok); + } + if (strcmp(token, "__get_str") == 0 || + strcmp(token, "__get_rel_str") == 0) { + free_token(token); + return process_str(event, arg, tok); + } + if (strcmp(token, "__get_bitmask") == 0 || + strcmp(token, "__get_rel_bitmask") == 0) { + free_token(token); + return process_bitmask(event, arg, tok); + } + if (strcmp(token, "__get_dynamic_array") == 0 || + strcmp(token, "__get_rel_dynamic_array") == 0) { + free_token(token); + return process_dynamic_array(event, arg, tok); + } + if (strcmp(token, "__get_dynamic_array_len") == 0 || + strcmp(token, "__get_rel_dynamic_array_len") == 0) { + free_token(token); + return process_dynamic_array_len(event, arg, tok); + } + if (strcmp(token, "__builtin_expect") == 0) { + free_token(token); + return process_builtin_expect(event, arg, tok); + } + + func = find_func_handler(event->tep, token); + if (func) { + free_token(token); + return process_func_handler(event, func, arg, tok); + } + + do_warning_event(event, "function %s not defined", token); + free_token(token); + return TEP_EVENT_ERROR; +} + +static enum tep_event_type +process_arg_token(struct tep_event *event, struct tep_print_arg *arg, + char **tok, enum tep_event_type type) +{ + char *token; + char *atom; + + token = *tok; + + switch (type) { + case TEP_EVENT_ITEM: + if (strcmp(token, "REC") == 0) { + free_token(token); + type = process_entry(event, arg, &token); + break; + } + atom = token; + /* test the next token */ + type = read_token_item(&token); + + /* + * If the next token is a parenthesis, then this + * is a function. + */ + if (type == TEP_EVENT_DELIM && strcmp(token, "(") == 0) { + free_token(token); + token = NULL; + /* this will free atom. */ + type = process_function(event, arg, atom, &token); + break; + } + /* atoms can be more than one token long */ + while (type == TEP_EVENT_ITEM) { + int ret; + + ret = append(&atom, " ", token); + if (ret < 0) { + free(atom); + *tok = NULL; + free_token(token); + return TEP_EVENT_ERROR; + } + free_token(token); + type = read_token_item(&token); + } + + arg->type = TEP_PRINT_ATOM; + arg->atom.atom = atom; + break; + + case TEP_EVENT_DQUOTE: + case TEP_EVENT_SQUOTE: + arg->type = TEP_PRINT_ATOM; + arg->atom.atom = token; + type = read_token_item(&token); + break; + case TEP_EVENT_DELIM: + if (strcmp(token, "(") == 0) { + free_token(token); + type = process_paren(event, arg, &token); + break; + } + case TEP_EVENT_OP: + /* handle single ops */ + arg->type = TEP_PRINT_OP; + arg->op.op = token; + arg->op.left = NULL; + type = process_op(event, arg, &token); + + /* On error, the op is freed */ + if (type == TEP_EVENT_ERROR) + arg->op.op = NULL; + + /* return error type if errored */ + break; + + case TEP_EVENT_ERROR ... TEP_EVENT_NEWLINE: + default: + do_warning_event(event, "unexpected type %d", type); + return TEP_EVENT_ERROR; + } + *tok = token; + + return type; +} + +static int event_read_print_args(struct tep_event *event, struct tep_print_arg **list) +{ + enum tep_event_type type = TEP_EVENT_ERROR; + struct tep_print_arg *arg; + char *token; + int args = 0; + + do { + if (type == TEP_EVENT_NEWLINE) { + type = read_token_item(&token); + continue; + } + + arg = alloc_arg(); + if (!arg) { + do_warning_event(event, "%s: not enough memory!", + __func__); + return -1; + } + + type = process_arg(event, arg, &token); + + if (type == TEP_EVENT_ERROR) { + free_token(token); + free_arg(arg); + return -1; + } + + *list = arg; + args++; + + if (type == TEP_EVENT_OP) { + type = process_op(event, arg, &token); + free_token(token); + if (type == TEP_EVENT_ERROR) { + *list = NULL; + free_arg(arg); + return -1; + } + list = &arg->next; + continue; + } + + if (type == TEP_EVENT_DELIM && strcmp(token, ",") == 0) { + free_token(token); + *list = arg; + list = &arg->next; + continue; + } + break; + } while (type != TEP_EVENT_NONE); + + if (type != TEP_EVENT_NONE && type != TEP_EVENT_ERROR) + free_token(token); + + return args; +} + +static int event_read_print(struct tep_event *event) +{ + enum tep_event_type type; + char *token; + int ret; + + if (read_expected_item(TEP_EVENT_ITEM, "print") < 0) + return -1; + + if (read_expected(TEP_EVENT_ITEM, "fmt") < 0) + return -1; + + if (read_expected(TEP_EVENT_OP, ":") < 0) + return -1; + + if (read_expect_type(TEP_EVENT_DQUOTE, &token) < 0) + goto fail; + + concat: + event->print_fmt.format = token; + event->print_fmt.args = NULL; + + /* ok to have no arg */ + type = read_token_item(&token); + + if (type == TEP_EVENT_NONE) + return 0; + + /* Handle concatenation of print lines */ + if (type == TEP_EVENT_DQUOTE) { + char *cat; + + if (asprintf(&cat, "%s%s", event->print_fmt.format, token) < 0) + goto fail; + free_token(token); + free_token(event->print_fmt.format); + event->print_fmt.format = NULL; + token = cat; + goto concat; + } + + if (test_type_token(type, token, TEP_EVENT_DELIM, ",")) + goto fail; + + free_token(token); + + ret = event_read_print_args(event, &event->print_fmt.args); + if (ret < 0) + return -1; + + return ret; + + fail: + free_token(token); + return -1; +} + +/** + * tep_find_common_field - return a common field by event + * @event: handle for the event + * @name: the name of the common field to return + * + * Returns a common field from the event by the given @name. + * This only searches the common fields and not all field. + */ +struct tep_format_field * +tep_find_common_field(struct tep_event *event, const char *name) +{ + struct tep_format_field *format; + + for (format = event->format.common_fields; + format; format = format->next) { + if (strcmp(format->name, name) == 0) + break; + } + + return format; +} + +/** + * tep_find_field - find a non-common field + * @event: handle for the event + * @name: the name of the non-common field + * + * Returns a non-common field by the given @name. + * This does not search common fields. + */ +struct tep_format_field * +tep_find_field(struct tep_event *event, const char *name) +{ + struct tep_format_field *format; + + for (format = event->format.fields; + format; format = format->next) { + if (strcmp(format->name, name) == 0) + break; + } + + return format; +} + +/** + * tep_find_any_field - find any field by name + * @event: handle for the event + * @name: the name of the field + * + * Returns a field by the given @name. + * This searches the common field names first, then + * the non-common ones if a common one was not found. + */ +struct tep_format_field * +tep_find_any_field(struct tep_event *event, const char *name) +{ + struct tep_format_field *format; + + format = tep_find_common_field(event, name); + if (format) + return format; + return tep_find_field(event, name); +} + +/** + * tep_read_number - read a number from data + * @tep: a handle to the trace event parser context + * @ptr: the raw data + * @size: the size of the data that holds the number + * + * Returns the number (converted to host) from the + * raw data. + */ +unsigned long long tep_read_number(struct tep_handle *tep, + const void *ptr, int size) +{ + unsigned long long val; + + switch (size) { + case 1: + return *(unsigned char *)ptr; + case 2: + return data2host2(tep, *(unsigned short *)ptr); + case 4: + return data2host4(tep, *(unsigned int *)ptr); + case 8: + memcpy(&val, (ptr), sizeof(unsigned long long)); + return data2host8(tep, val); + default: + /* BUG! */ + return 0; + } +} + +/** + * tep_read_number_field - read a number from data + * @field: a handle to the field + * @data: the raw data to read + * @value: the value to place the number in + * + * Reads raw data according to a field offset and size, + * and translates it into @value. + * + * Returns 0 on success, -1 otherwise. + */ +int tep_read_number_field(struct tep_format_field *field, const void *data, + unsigned long long *value) +{ + if (!field) + return -1; + switch (field->size) { + case 1: + case 2: + case 4: + case 8: + *value = tep_read_number(field->event->tep, + data + field->offset, field->size); + return 0; + default: + return -1; + } +} + +static int get_common_info(struct tep_handle *tep, + const char *type, int *offset, int *size) +{ + struct tep_event *event; + struct tep_format_field *field; + + /* + * All events should have the same common elements. + * Pick any event to find where the type is; + */ + if (!tep->events) { + do_warning("no event_list!"); + return -1; + } + + event = tep->events[0]; + field = tep_find_common_field(event, type); + if (!field) + return -1; + + *offset = field->offset; + *size = field->size; + + return 0; +} + +static int __parse_common(struct tep_handle *tep, void *data, + int *size, int *offset, const char *name) +{ + int ret; + + if (!*size) { + ret = get_common_info(tep, name, offset, size); + if (ret < 0) + return ret; + } + return tep_read_number(tep, data + *offset, *size); +} + +static int trace_parse_common_type(struct tep_handle *tep, void *data) +{ + return __parse_common(tep, data, + &tep->type_size, &tep->type_offset, + "common_type"); +} + +static int parse_common_pid(struct tep_handle *tep, void *data) +{ + return __parse_common(tep, data, + &tep->pid_size, &tep->pid_offset, + "common_pid"); +} + +static int parse_common_pc(struct tep_handle *tep, void *data) +{ + return __parse_common(tep, data, + &tep->pc_size, &tep->pc_offset, + "common_preempt_count"); +} + +static int parse_common_flags(struct tep_handle *tep, void *data) +{ + return __parse_common(tep, data, + &tep->flags_size, &tep->flags_offset, + "common_flags"); +} + +static int parse_common_lock_depth(struct tep_handle *tep, void *data) +{ + return __parse_common(tep, data, + &tep->ld_size, &tep->ld_offset, + "common_lock_depth"); +} + +static int parse_common_migrate_disable(struct tep_handle *tep, void *data) +{ + return __parse_common(tep, data, + &tep->ld_size, &tep->ld_offset, + "common_migrate_disable"); +} + +static int events_id_cmp(const void *a, const void *b); + +/** + * tep_find_event - find an event by given id + * @tep: a handle to the trace event parser context + * @id: the id of the event + * + * Returns an event that has a given @id. + */ +struct tep_event *tep_find_event(struct tep_handle *tep, int id) +{ + struct tep_event **eventptr; + struct tep_event key; + struct tep_event *pkey = &key; + + /* Check cache first */ + if (tep->last_event && tep->last_event->id == id) + return tep->last_event; + + key.id = id; + + eventptr = bsearch(&pkey, tep->events, tep->nr_events, + sizeof(*tep->events), events_id_cmp); + + if (eventptr) { + tep->last_event = *eventptr; + return *eventptr; + } + + return NULL; +} + +/** + * tep_find_event_by_name - find an event by given name + * @tep: a handle to the trace event parser context + * @sys: the system name to search for + * @name: the name of the event to search for + * + * This returns an event with a given @name and under the system + * @sys. If @sys is NULL the first event with @name is returned. + */ +struct tep_event * +tep_find_event_by_name(struct tep_handle *tep, + const char *sys, const char *name) +{ + struct tep_event *event = NULL; + int i; + + if (tep->last_event && + strcmp(tep->last_event->name, name) == 0 && + (!sys || strcmp(tep->last_event->system, sys) == 0)) + return tep->last_event; + + for (i = 0; i < tep->nr_events; i++) { + event = tep->events[i]; + if (strcmp(event->name, name) == 0) { + if (!sys) + break; + if (strcmp(event->system, sys) == 0) + break; + } + } + if (i == tep->nr_events) + event = NULL; + + tep->last_event = event; + return event; +} + +static unsigned long long +eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg *arg) +{ + struct tep_handle *tep = event->tep; + unsigned long long val = 0; + unsigned long long left, right; + struct tep_print_arg *typearg = NULL; + struct tep_print_arg *larg; + unsigned long offset; + unsigned int field_size; + + switch (arg->type) { + case TEP_PRINT_NULL: + /* ?? */ + return 0; + case TEP_PRINT_ATOM: + return strtoull(arg->atom.atom, NULL, 0); + case TEP_PRINT_FIELD: + if (!arg->field.field) { + arg->field.field = tep_find_any_field(event, arg->field.name); + if (!arg->field.field) + goto out_warning_field; + + } + /* must be a number */ + val = tep_read_number(tep, data + arg->field.field->offset, + arg->field.field->size); + break; + case TEP_PRINT_FLAGS: + case TEP_PRINT_SYMBOL: + case TEP_PRINT_INT_ARRAY: + case TEP_PRINT_HEX: + case TEP_PRINT_HEX_STR: + break; + case TEP_PRINT_TYPE: + val = eval_num_arg(data, size, event, arg->typecast.item); + return eval_type(val, arg, 0); + case TEP_PRINT_STRING: + case TEP_PRINT_BSTRING: + case TEP_PRINT_BITMASK: + return 0; + case TEP_PRINT_FUNC: { + struct trace_seq s; + trace_seq_init(&s); + val = process_defined_func(&s, data, size, event, arg); + trace_seq_destroy(&s); + return val; + } + case TEP_PRINT_OP: + if (strcmp(arg->op.op, "[") == 0) { + /* + * Arrays are special, since we don't want + * to read the arg as is. + */ + right = eval_num_arg(data, size, event, arg->op.right); + + /* handle typecasts */ + larg = arg->op.left; + while (larg->type == TEP_PRINT_TYPE) { + if (!typearg) + typearg = larg; + larg = larg->typecast.item; + } + + /* Default to long size */ + field_size = tep->long_size; + + switch (larg->type) { + case TEP_PRINT_DYNAMIC_ARRAY: + offset = tep_read_number(tep, + data + larg->dynarray.field->offset, + larg->dynarray.field->size); + if (larg->dynarray.field->elementsize) + field_size = larg->dynarray.field->elementsize; + /* + * The actual length of the dynamic array is stored + * in the top half of the field, and the offset + * is in the bottom half of the 32 bit field. + */ + offset &= 0xffff; + offset += right; + break; + case TEP_PRINT_FIELD: + if (!larg->field.field) { + larg->field.field = + tep_find_any_field(event, larg->field.name); + if (!larg->field.field) { + arg = larg; + goto out_warning_field; + } + } + field_size = larg->field.field->elementsize; + offset = larg->field.field->offset + + right * larg->field.field->elementsize; + break; + default: + goto default_op; /* oops, all bets off */ + } + val = tep_read_number(tep, + data + offset, field_size); + if (typearg) + val = eval_type(val, typearg, 1); + break; + } else if (strcmp(arg->op.op, "?") == 0) { + left = eval_num_arg(data, size, event, arg->op.left); + arg = arg->op.right; + if (left) + val = eval_num_arg(data, size, event, arg->op.left); + else + val = eval_num_arg(data, size, event, arg->op.right); + break; + } + default_op: + left = eval_num_arg(data, size, event, arg->op.left); + right = eval_num_arg(data, size, event, arg->op.right); + switch (arg->op.op[0]) { + case '!': + switch (arg->op.op[1]) { + case 0: + val = !right; + break; + case '=': + val = left != right; + break; + default: + goto out_warning_op; + } + break; + case '~': + val = ~right; + break; + case '|': + if (arg->op.op[1]) + val = left || right; + else + val = left | right; + break; + case '&': + if (arg->op.op[1]) + val = left && right; + else + val = left & right; + break; + case '<': + switch (arg->op.op[1]) { + case 0: + val = left < right; + break; + case '<': + val = left << right; + break; + case '=': + val = left <= right; + break; + default: + goto out_warning_op; + } + break; + case '>': + switch (arg->op.op[1]) { + case 0: + val = left > right; + break; + case '>': + val = left >> right; + break; + case '=': + val = left >= right; + break; + default: + goto out_warning_op; + } + break; + case '=': + if (arg->op.op[1] != '=') + goto out_warning_op; + + val = left == right; + break; + case '-': + val = left - right; + break; + case '+': + val = left + right; + break; + case '/': + val = left / right; + break; + case '%': + val = left % right; + break; + case '*': + val = left * right; + break; + default: + goto out_warning_op; + } + break; + case TEP_PRINT_DYNAMIC_ARRAY_LEN: + offset = tep_read_number(tep, + data + arg->dynarray.field->offset, + arg->dynarray.field->size); + /* + * The total allocated length of the dynamic array is + * stored in the top half of the field, and the offset + * is in the bottom half of the 32 bit field. + */ + val = (unsigned long long)(offset >> 16); + break; + case TEP_PRINT_DYNAMIC_ARRAY: + /* Without [], we pass the address to the dynamic data */ + offset = tep_read_number(tep, + data + arg->dynarray.field->offset, + arg->dynarray.field->size); + /* + * The total allocated length of the dynamic array is + * stored in the top half of the field, and the offset + * is in the bottom half of the 32 bit field. + */ + offset &= 0xffff; + val = (unsigned long long)((unsigned long)data + offset); + break; + default: /* not sure what to do there */ + return 0; + } + return val; + +out_warning_op: + do_warning_event(event, "%s: unknown op '%s'", __func__, arg->op.op); + return 0; + +out_warning_field: + do_warning_event(event, "%s: field %s not found", + __func__, arg->field.name); + return 0; +} + +struct flag { + const char *name; + unsigned long long value; +}; + +static const struct flag flags[] = { + { "HI_SOFTIRQ", 0 }, + { "TIMER_SOFTIRQ", 1 }, + { "NET_TX_SOFTIRQ", 2 }, + { "NET_RX_SOFTIRQ", 3 }, + { "BLOCK_SOFTIRQ", 4 }, + { "IRQ_POLL_SOFTIRQ", 5 }, + { "TASKLET_SOFTIRQ", 6 }, + { "SCHED_SOFTIRQ", 7 }, + { "HRTIMER_SOFTIRQ", 8 }, + { "RCU_SOFTIRQ", 9 }, + + { "HRTIMER_NORESTART", 0 }, + { "HRTIMER_RESTART", 1 }, +}; + +static long long eval_flag(const char *flag) +{ + int i; + + /* + * Some flags in the format files do not get converted. + * If the flag is not numeric, see if it is something that + * we already know about. + */ + if (isdigit(flag[0])) + return strtoull(flag, NULL, 0); + + for (i = 0; i < (int)(sizeof(flags)/sizeof(flags[0])); i++) + if (strcmp(flags[i].name, flag) == 0) + return flags[i].value; + + return -1LL; +} + +static void print_str_to_seq(struct trace_seq *s, const char *format, + int len_arg, const char *str) +{ + if (len_arg >= 0) + trace_seq_printf(s, format, len_arg, str); + else + trace_seq_printf(s, format, str); +} + +static void print_bitmask_to_seq(struct tep_handle *tep, + struct trace_seq *s, const char *format, + int len_arg, const void *data, int size) +{ + int nr_bits = size * 8; + int str_size = (nr_bits + 3) / 4; + int len = 0; + char buf[3]; + char *str; + int index; + int i; + + /* + * The kernel likes to put in commas every 32 bits, we + * can do the same. + */ + str_size += (nr_bits - 1) / 32; + + str = malloc(str_size + 1); + if (!str) { + do_warning("%s: not enough memory!", __func__); + return; + } + str[str_size] = 0; + + /* Start out with -2 for the two chars per byte */ + for (i = str_size - 2; i >= 0; i -= 2) { + /* + * data points to a bit mask of size bytes. + * In the kernel, this is an array of long words, thus + * endianness is very important. + */ + if (tep->file_bigendian) + index = size - (len + 1); + else + index = len; + + snprintf(buf, 3, "%02x", *((unsigned char *)data + index)); + memcpy(str + i, buf, 2); + len++; + if (!(len & 3) && i > 0) { + i--; + str[i] = ','; + } + } + + if (len_arg >= 0) + trace_seq_printf(s, format, len_arg, str); + else + trace_seq_printf(s, format, str); + + free(str); +} + +static void print_str_arg(struct trace_seq *s, void *data, int size, + struct tep_event *event, const char *format, + int len_arg, struct tep_print_arg *arg) +{ + struct tep_handle *tep = event->tep; + struct tep_print_flag_sym *flag; + struct tep_format_field *field; + struct printk_map *printk; + long long val, fval; + unsigned long long addr; + char *str; + unsigned char *hex; + int print; + int i, len; + + switch (arg->type) { + case TEP_PRINT_NULL: + /* ?? */ + return; + case TEP_PRINT_ATOM: + print_str_to_seq(s, format, len_arg, arg->atom.atom); + return; + case TEP_PRINT_FIELD: + field = arg->field.field; + if (!field) { + field = tep_find_any_field(event, arg->field.name); + if (!field) { + str = arg->field.name; + goto out_warning_field; + } + arg->field.field = field; + } + /* Zero sized fields, mean the rest of the data */ + len = field->size ? : size - field->offset; + + /* + * Some events pass in pointers. If this is not an array + * and the size is the same as long_size, assume that it + * is a pointer. + */ + if (!(field->flags & TEP_FIELD_IS_ARRAY) && + field->size == tep->long_size) { + + /* Handle heterogeneous recording and processing + * architectures + * + * CASE I: + * Traces recorded on 32-bit devices (32-bit + * addressing) and processed on 64-bit devices: + * In this case, only 32 bits should be read. + * + * CASE II: + * Traces recorded on 64 bit devices and processed + * on 32-bit devices: + * In this case, 64 bits must be read. + */ + addr = (tep->long_size == 8) ? + *(unsigned long long *)(data + field->offset) : + (unsigned long long)*(unsigned int *)(data + field->offset); + + /* Check if it matches a print format */ + printk = find_printk(tep, addr); + if (printk) + trace_seq_puts(s, printk->printk); + else + trace_seq_printf(s, "%llx", addr); + break; + } + str = malloc(len + 1); + if (!str) { + do_warning_event(event, "%s: not enough memory!", + __func__); + return; + } + memcpy(str, data + field->offset, len); + str[len] = 0; + print_str_to_seq(s, format, len_arg, str); + free(str); + break; + case TEP_PRINT_FLAGS: + val = eval_num_arg(data, size, event, arg->flags.field); + print = 0; + for (flag = arg->flags.flags; flag; flag = flag->next) { + fval = eval_flag(flag->value); + if (!val && fval < 0) { + print_str_to_seq(s, format, len_arg, flag->str); + break; + } + if (fval > 0 && (val & fval) == fval) { + if (print && arg->flags.delim) + trace_seq_puts(s, arg->flags.delim); + print_str_to_seq(s, format, len_arg, flag->str); + print = 1; + val &= ~fval; + } + } + if (val) { + if (print && arg->flags.delim) + trace_seq_puts(s, arg->flags.delim); + trace_seq_printf(s, "0x%llx", val); + } + break; + case TEP_PRINT_SYMBOL: + val = eval_num_arg(data, size, event, arg->symbol.field); + for (flag = arg->symbol.symbols; flag; flag = flag->next) { + fval = eval_flag(flag->value); + if (val == fval) { + print_str_to_seq(s, format, len_arg, flag->str); + break; + } + } + if (!flag) + trace_seq_printf(s, "0x%llx", val); + break; + case TEP_PRINT_HEX: + case TEP_PRINT_HEX_STR: + if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) { + unsigned long offset; + offset = tep_read_number(tep, + data + arg->hex.field->dynarray.field->offset, + arg->hex.field->dynarray.field->size); + hex = data + (offset & 0xffff); + } else { + field = arg->hex.field->field.field; + if (!field) { + str = arg->hex.field->field.name; + field = tep_find_any_field(event, str); + if (!field) + goto out_warning_field; + arg->hex.field->field.field = field; + } + hex = data + field->offset; + } + len = eval_num_arg(data, size, event, arg->hex.size); + for (i = 0; i < len; i++) { + if (i && arg->type == TEP_PRINT_HEX) + trace_seq_putc(s, ' '); + trace_seq_printf(s, "%02x", hex[i]); + } + break; + + case TEP_PRINT_INT_ARRAY: { + void *num; + int el_size; + + if (arg->int_array.field->type == TEP_PRINT_DYNAMIC_ARRAY) { + unsigned long offset; + struct tep_format_field *field = + arg->int_array.field->dynarray.field; + offset = tep_read_number(tep, + data + field->offset, + field->size); + num = data + (offset & 0xffff); + } else { + field = arg->int_array.field->field.field; + if (!field) { + str = arg->int_array.field->field.name; + field = tep_find_any_field(event, str); + if (!field) + goto out_warning_field; + arg->int_array.field->field.field = field; + } + num = data + field->offset; + } + len = eval_num_arg(data, size, event, arg->int_array.count); + el_size = eval_num_arg(data, size, event, + arg->int_array.el_size); + for (i = 0; i < len; i++) { + if (i) + trace_seq_putc(s, ' '); + + if (el_size == 1) { + trace_seq_printf(s, "%u", *(uint8_t *)num); + } else if (el_size == 2) { + trace_seq_printf(s, "%u", *(uint16_t *)num); + } else if (el_size == 4) { + trace_seq_printf(s, "%u", *(uint32_t *)num); + } else if (el_size == 8) { + trace_seq_printf(s, "%"PRIu64, *(uint64_t *)num); + } else { + trace_seq_printf(s, "BAD SIZE:%d 0x%x", + el_size, *(uint8_t *)num); + el_size = 1; + } + + num += el_size; + } + break; + } + case TEP_PRINT_TYPE: + break; + case TEP_PRINT_STRING: { + int str_offset; + + if (!arg->string.field) + arg->string.field = tep_find_any_field(event, arg->string.string); + if (!arg->string.field) + break; + + str_offset = data2host4(tep, + *(unsigned int *)(data + arg->string.field->offset)); + str_offset &= 0xffff; + if (arg->string.field->flags & TEP_FIELD_IS_RELATIVE) + str_offset += arg->string.field->offset + arg->string.field->size; + print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset); + break; + } + case TEP_PRINT_BSTRING: + print_str_to_seq(s, format, len_arg, arg->string.string); + break; + case TEP_PRINT_BITMASK: { + int bitmask_offset; + int bitmask_size; + + if (!arg->bitmask.field) + arg->bitmask.field = tep_find_any_field(event, arg->bitmask.bitmask); + if (!arg->bitmask.field) + break; + bitmask_offset = data2host4(tep, + *(unsigned int *)(data + arg->bitmask.field->offset)); + bitmask_size = bitmask_offset >> 16; + bitmask_offset &= 0xffff; + if (arg->bitmask.field->flags & TEP_FIELD_IS_RELATIVE) + bitmask_offset += arg->bitmask.field->offset + arg->bitmask.field->size; + print_bitmask_to_seq(tep, s, format, len_arg, + data + bitmask_offset, bitmask_size); + break; + } + case TEP_PRINT_OP: + /* + * The only op for string should be ? : + */ + if (arg->op.op[0] != '?') + return; + val = eval_num_arg(data, size, event, arg->op.left); + if (val) + print_str_arg(s, data, size, event, + format, len_arg, arg->op.right->op.left); + else + print_str_arg(s, data, size, event, + format, len_arg, arg->op.right->op.right); + break; + case TEP_PRINT_FUNC: + process_defined_func(s, data, size, event, arg); + break; + default: + /* well... */ + break; + } + + return; + +out_warning_field: + do_warning_event(event, "%s: field %s not found", + __func__, arg->field.name); +} + +static unsigned long long +process_defined_func(struct trace_seq *s, void *data, int size, + struct tep_event *event, struct tep_print_arg *arg) +{ + struct tep_function_handler *func_handle = arg->func.func; + struct func_params *param; + unsigned long long *args; + unsigned long long ret; + struct tep_print_arg *farg; + struct trace_seq str; + struct save_str { + struct save_str *next; + char *str; + } *strings = NULL, *string; + int i; + + if (!func_handle->nr_args) { + ret = (*func_handle->func)(s, NULL); + goto out; + } + + farg = arg->func.args; + param = func_handle->params; + + ret = ULLONG_MAX; + args = malloc(sizeof(*args) * func_handle->nr_args); + if (!args) + goto out; + + for (i = 0; i < func_handle->nr_args; i++) { + switch (param->type) { + case TEP_FUNC_ARG_INT: + case TEP_FUNC_ARG_LONG: + case TEP_FUNC_ARG_PTR: + args[i] = eval_num_arg(data, size, event, farg); + break; + case TEP_FUNC_ARG_STRING: + trace_seq_init(&str); + print_str_arg(&str, data, size, event, "%s", -1, farg); + trace_seq_terminate(&str); + string = malloc(sizeof(*string)); + if (!string) { + do_warning_event(event, "%s(%d): malloc str", + __func__, __LINE__); + goto out_free; + } + string->next = strings; + string->str = strdup(str.buffer); + if (!string->str) { + free(string); + do_warning_event(event, "%s(%d): malloc str", + __func__, __LINE__); + goto out_free; + } + args[i] = (uintptr_t)string->str; + strings = string; + trace_seq_destroy(&str); + break; + default: + /* + * Something went totally wrong, this is not + * an input error, something in this code broke. + */ + do_warning_event(event, "Unexpected end of arguments\n"); + goto out_free; + } + farg = farg->next; + param = param->next; + } + + ret = (*func_handle->func)(s, args); +out_free: + free(args); + while (strings) { + string = strings; + strings = string->next; + free(string->str); + free(string); + } + + out: + /* TBD : handle return type here */ + return ret; +} + +static void free_args(struct tep_print_arg *args) +{ + struct tep_print_arg *next; + + while (args) { + next = args->next; + + free_arg(args); + args = next; + } +} + +static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event *event) +{ + struct tep_handle *tep = event->tep; + struct tep_format_field *field, *ip_field; + struct tep_print_arg *args, *arg, **next; + unsigned long long ip, val; + char *ptr; + void *bptr; + int vsize = 0; + + field = tep->bprint_buf_field; + ip_field = tep->bprint_ip_field; + + if (!field) { + field = tep_find_field(event, "buf"); + if (!field) { + do_warning_event(event, "can't find buffer field for binary printk"); + return NULL; + } + ip_field = tep_find_field(event, "ip"); + if (!ip_field) { + do_warning_event(event, "can't find ip field for binary printk"); + return NULL; + } + tep->bprint_buf_field = field; + tep->bprint_ip_field = ip_field; + } + + ip = tep_read_number(tep, data + ip_field->offset, ip_field->size); + + /* + * The first arg is the IP pointer. + */ + args = alloc_arg(); + if (!args) { + do_warning_event(event, "%s(%d): not enough memory!", + __func__, __LINE__); + return NULL; + } + arg = args; + arg->next = NULL; + next = &arg->next; + + arg->type = TEP_PRINT_ATOM; + + if (asprintf(&arg->atom.atom, "%lld", ip) < 0) + goto out_free; + + /* skip the first "%ps: " */ + for (ptr = fmt + 5, bptr = data + field->offset; + bptr < data + size && *ptr; ptr++) { + int ls = 0; + + if (*ptr == '%') { + process_again: + ptr++; + switch (*ptr) { + case '%': + break; + case 'l': + ls++; + goto process_again; + case 'L': + ls = 2; + goto process_again; + case '0' ... '9': + goto process_again; + case '.': + goto process_again; + case 'z': + case 'Z': + ls = 1; + goto process_again; + case 'p': + ls = 1; + if (isalnum(ptr[1])) { + ptr++; + /* Check for special pointers */ + switch (*ptr) { + case 's': + case 'S': + 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 + * dereferenced pointers. + * Only process if the pointer + * value is a printable. + */ + if (isprint(*(char *)bptr)) + goto process_string; + } + } + /* fall through */ + case 'd': + case 'u': + case 'i': + case 'x': + case 'X': + case 'o': + switch (ls) { + case 0: + vsize = 4; + break; + case 1: + vsize = tep->long_size; + break; + case 2: + vsize = 8; + break; + default: + vsize = ls; /* ? */ + break; + } + /* fall through */ + case '*': + if (*ptr == '*') + vsize = 4; + + /* the pointers are always 4 bytes aligned */ + bptr = (void *)(((unsigned long)bptr + 3) & + ~3); + val = tep_read_number(tep, bptr, vsize); + bptr += vsize; + arg = alloc_arg(); + if (!arg) { + do_warning_event(event, "%s(%d): not enough memory!", + __func__, __LINE__); + goto out_free; + } + arg->next = NULL; + arg->type = TEP_PRINT_ATOM; + if (asprintf(&arg->atom.atom, "%lld", val) < 0) { + free(arg); + goto out_free; + } + *next = arg; + next = &arg->next; + /* + * The '*' case means that an arg is used as the length. + * We need to continue to figure out for what. + */ + if (*ptr == '*') + goto process_again; + + break; + case 's': + process_string: + arg = alloc_arg(); + if (!arg) { + do_warning_event(event, "%s(%d): not enough memory!", + __func__, __LINE__); + goto out_free; + } + arg->next = NULL; + arg->type = TEP_PRINT_BSTRING; + arg->string.string = strdup(bptr); + if (!arg->string.string) + goto out_free; + bptr += strlen(bptr) + 1; + *next = arg; + next = &arg->next; + default: + break; + } + } + } + + return args; + +out_free: + free_args(args); + return NULL; +} + +static char * +get_bprint_format(void *data, int size __maybe_unused, + struct tep_event *event) +{ + struct tep_handle *tep = event->tep; + unsigned long long addr; + struct tep_format_field *field; + struct printk_map *printk; + char *format; + + field = tep->bprint_fmt_field; + + if (!field) { + field = tep_find_field(event, "fmt"); + if (!field) { + do_warning_event(event, "can't find format field for binary printk"); + return NULL; + } + tep->bprint_fmt_field = field; + } + + addr = tep_read_number(tep, data + field->offset, field->size); + + printk = find_printk(tep, addr); + if (!printk) { + if (asprintf(&format, "%%ps: (NO FORMAT FOUND at %llx)\n", addr) < 0) + return NULL; + return format; + } + + if (asprintf(&format, "%s: %s", "%ps", printk->printk) < 0) + return NULL; + + return format; +} + +static int print_mac_arg(struct trace_seq *s, const char *format, + void *data, int size, struct tep_event *event, + struct tep_print_arg *arg) +{ + const char *fmt = "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x"; + bool reverse = false; + unsigned char *buf; + int ret = 0; + + if (arg->type == TEP_PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return 0; + } + + if (arg->type != TEP_PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", + arg->type); + return 0; + } + + if (format[0] == 'm') { + fmt = "%.2x%.2x%.2x%.2x%.2x%.2x"; + } else if (format[0] == 'M' && format[1] == 'F') { + fmt = "%.2x-%.2x-%.2x-%.2x-%.2x-%.2x"; + ret++; + } + if (format[1] == 'R') { + reverse = true; + ret++; + } + + if (!arg->field.field) { + arg->field.field = + tep_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning_event(event, "%s: field %s not found", + __func__, arg->field.name); + return ret; + } + } + if (arg->field.field->size != 6) { + trace_seq_printf(s, "INVALIDMAC"); + return ret; + } + + buf = data + arg->field.field->offset; + if (reverse) + trace_seq_printf(s, fmt, buf[5], buf[4], buf[3], buf[2], buf[1], buf[0]); + else + trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]); + + return ret; +} + +static int parse_ip4_print_args(struct tep_handle *tep, + const char *ptr, bool *reverse) +{ + int ret = 0; + + *reverse = false; + + /* hnbl */ + switch (*ptr) { + case 'h': + if (tep->file_bigendian) + *reverse = false; + else + *reverse = true; + ret++; + break; + case 'l': + *reverse = true; + ret++; + break; + case 'n': + case 'b': + ret++; + /* fall through */ + default: + *reverse = false; + break; + } + + return ret; +} + +static void print_ip4_addr(struct trace_seq *s, char i, bool reverse, unsigned char *buf) +{ + const char *fmt; + + if (i == 'i') + fmt = "%03d.%03d.%03d.%03d"; + else + fmt = "%d.%d.%d.%d"; + + if (reverse) + trace_seq_printf(s, fmt, buf[3], buf[2], buf[1], buf[0]); + else + trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3]); + +} + +static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) +{ + return ((unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | + (unsigned long)(a->s6_addr32[2] ^ htonl(0x0000ffff))) == 0UL; +} + +static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr) +{ + return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE); +} + +static void print_ip6c_addr(struct trace_seq *s, unsigned char *addr) +{ + int i, j, range; + unsigned char zerolength[8]; + int longest = 1; + int colonpos = -1; + uint16_t word; + uint8_t hi, lo; + bool needcolon = false; + bool useIPv4; + struct in6_addr in6; + + memcpy(&in6, addr, sizeof(struct in6_addr)); + + useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); + + memset(zerolength, 0, sizeof(zerolength)); + + if (useIPv4) + range = 6; + else + range = 8; + + /* find position of longest 0 run */ + for (i = 0; i < range; i++) { + for (j = i; j < range; j++) { + if (in6.s6_addr16[j] != 0) + break; + zerolength[i]++; + } + } + for (i = 0; i < range; i++) { + if (zerolength[i] > longest) { + longest = zerolength[i]; + colonpos = i; + } + } + if (longest == 1) /* don't compress a single 0 */ + colonpos = -1; + + /* emit address */ + for (i = 0; i < range; i++) { + if (i == colonpos) { + if (needcolon || i == 0) + trace_seq_printf(s, ":"); + trace_seq_printf(s, ":"); + needcolon = false; + i += longest - 1; + continue; + } + if (needcolon) { + trace_seq_printf(s, ":"); + needcolon = false; + } + /* hex u16 without leading 0s */ + word = ntohs(in6.s6_addr16[i]); + hi = word >> 8; + lo = word & 0xff; + if (hi) + trace_seq_printf(s, "%x%02x", hi, lo); + else + trace_seq_printf(s, "%x", lo); + + needcolon = true; + } + + if (useIPv4) { + if (needcolon) + trace_seq_printf(s, ":"); + print_ip4_addr(s, 'I', false, &in6.s6_addr[12]); + } + + return; +} + +static void print_ip6_addr(struct trace_seq *s, char i, unsigned char *buf) +{ + int j; + + for (j = 0; j < 16; j += 2) { + trace_seq_printf(s, "%02x%02x", buf[j], buf[j+1]); + if (i == 'I' && j < 14) + trace_seq_printf(s, ":"); + } +} + +/* + * %pi4 print an IPv4 address with leading zeros + * %pI4 print an IPv4 address without leading zeros + * %pi6 print an IPv6 address without colons + * %pI6 print an IPv6 address with colons + * %pI6c print an IPv6 address in compressed form with colons + * %pISpc print an IP address based on sockaddr; p adds port. + */ +static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct tep_event *event, + struct tep_print_arg *arg) +{ + bool reverse = false; + unsigned char *buf; + int ret; + + ret = parse_ip4_print_args(event->tep, ptr, &reverse); + + if (arg->type == TEP_PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return ret; + } + + if (arg->type != TEP_PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return ret; + } + + if (!arg->field.field) { + arg->field.field = + tep_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return ret; + } + } + + buf = data + arg->field.field->offset; + + if (arg->field.field->size != 4) { + trace_seq_printf(s, "INVALIDIPv4"); + return ret; + } + + print_ip4_addr(s, i, reverse, buf); + return ret; + +} + +static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct tep_event *event, + struct tep_print_arg *arg) +{ + char have_c = 0; + unsigned char *buf; + int rc = 0; + + /* pI6c */ + if (i == 'I' && *ptr == 'c') { + have_c = 1; + ptr++; + rc++; + } + + if (arg->type == TEP_PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return rc; + } + + if (arg->type != TEP_PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return rc; + } + + if (!arg->field.field) { + arg->field.field = + tep_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return rc; + } + } + + buf = data + arg->field.field->offset; + + if (arg->field.field->size != 16) { + trace_seq_printf(s, "INVALIDIPv6"); + return rc; + } + + if (have_c) + print_ip6c_addr(s, buf); + else + print_ip6_addr(s, i, buf); + + return rc; +} + +static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct tep_event *event, + struct tep_print_arg *arg) +{ + char have_c = 0, have_p = 0; + unsigned char *buf; + struct sockaddr_storage *sa; + bool reverse = false; + int rc = 0; + int ret; + + /* pISpc */ + if (i == 'I') { + if (*ptr == 'p') { + have_p = 1; + ptr++; + rc++; + } + if (*ptr == 'c') { + have_c = 1; + ptr++; + rc++; + } + } + ret = parse_ip4_print_args(event->tep, ptr, &reverse); + ptr += ret; + rc += ret; + + if (arg->type == TEP_PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return rc; + } + + if (arg->type != TEP_PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return rc; + } + + if (!arg->field.field) { + arg->field.field = + tep_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return rc; + } + } + + sa = (struct sockaddr_storage *) (data + arg->field.field->offset); + + if (sa->ss_family == AF_INET) { + struct sockaddr_in *sa4 = (struct sockaddr_in *) sa; + + if (arg->field.field->size < sizeof(struct sockaddr_in)) { + trace_seq_printf(s, "INVALIDIPv4"); + return rc; + } + + print_ip4_addr(s, i, reverse, (unsigned char *) &sa4->sin_addr); + if (have_p) + trace_seq_printf(s, ":%d", ntohs(sa4->sin_port)); + + + } else if (sa->ss_family == AF_INET6) { + struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) sa; + + if (arg->field.field->size < sizeof(struct sockaddr_in6)) { + trace_seq_printf(s, "INVALIDIPv6"); + return rc; + } + + if (have_p) + trace_seq_printf(s, "["); + + buf = (unsigned char *) &sa6->sin6_addr; + if (have_c) + print_ip6c_addr(s, buf); + else + print_ip6_addr(s, i, buf); + + if (have_p) + trace_seq_printf(s, "]:%d", ntohs(sa6->sin6_port)); + } + + return rc; +} + +static int print_ip_arg(struct trace_seq *s, const char *ptr, + void *data, int size, struct tep_event *event, + struct tep_print_arg *arg) +{ + char i = *ptr; /* 'i' or 'I' */ + int rc = 1; + + /* IP version */ + ptr++; + + switch (*ptr) { + case '4': + rc += print_ipv4_arg(s, ptr + 1, i, data, size, event, arg); + break; + case '6': + rc += print_ipv6_arg(s, ptr + 1, i, data, size, event, arg); + break; + case 'S': + rc += print_ipsa_arg(s, ptr + 1, i, data, size, event, arg); + break; + default: + return 0; + } + + return rc; +} + +static const int guid_index[16] = {3, 2, 1, 0, 5, 4, 7, 6, 8, 9, 10, 11, 12, 13, 14, 15}; +static const int uuid_index[16] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15}; + +static int print_uuid_arg(struct trace_seq *s, const char *ptr, + void *data, int size, struct tep_event *event, + struct tep_print_arg *arg) +{ + const int *index = uuid_index; + char *format = "%02x"; + int ret = 0; + char *buf; + int i; + + switch (*(ptr + 1)) { + case 'L': + format = "%02X"; + /* fall through */ + case 'l': + index = guid_index; + ret++; + break; + case 'B': + format = "%02X"; + /* fall through */ + case 'b': + ret++; + break; + } + + if (arg->type == TEP_PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return ret; + } + + if (arg->type != TEP_PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return ret; + } + + if (!arg->field.field) { + arg->field.field = + tep_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return ret; + } + } + + if (arg->field.field->size != 16) { + trace_seq_printf(s, "INVALIDUUID"); + return ret; + } + + buf = data + arg->field.field->offset; + + for (i = 0; i < 16; i++) { + trace_seq_printf(s, format, buf[index[i]] & 0xff); + switch (i) { + case 3: + case 5: + case 7: + case 9: + trace_seq_printf(s, "-"); + break; + } + } + + return ret; +} + +static int print_raw_buff_arg(struct trace_seq *s, const char *ptr, + void *data, int size, struct tep_event *event, + struct tep_print_arg *arg, int print_len) +{ + int plen = print_len; + char *delim = " "; + int ret = 0; + char *buf; + int i; + unsigned long offset; + int arr_len; + + switch (*(ptr + 1)) { + case 'C': + delim = ":"; + ret++; + break; + case 'D': + delim = "-"; + ret++; + break; + case 'N': + delim = ""; + ret++; + break; + } + + if (arg->type == TEP_PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return ret; + } + + if (arg->type != TEP_PRINT_DYNAMIC_ARRAY) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return ret; + } + + offset = tep_read_number(event->tep, + data + arg->dynarray.field->offset, + arg->dynarray.field->size); + arr_len = (unsigned long long)(offset >> 16); + buf = data + (offset & 0xffff); + + if (arr_len < plen) + plen = arr_len; + + if (plen < 1) + return ret; + + trace_seq_printf(s, "%02x", buf[0] & 0xff); + for (i = 1; i < plen; i++) + trace_seq_printf(s, "%s%02x", delim, buf[i] & 0xff); + + return ret; +} + +static int is_printable_array(char *p, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < len && p[i]; i++) + if (!isprint(p[i]) && !isspace(p[i])) + return 0; + return 1; +} + +void tep_print_field(struct trace_seq *s, void *data, + struct tep_format_field *field) +{ + unsigned long long val; + unsigned int offset, len, i; + struct tep_handle *tep = field->event->tep; + + if (field->flags & TEP_FIELD_IS_ARRAY) { + offset = field->offset; + len = field->size; + if (field->flags & TEP_FIELD_IS_DYNAMIC) { + val = tep_read_number(tep, data + offset, len); + offset = val; + len = offset >> 16; + offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; + } + if (field->flags & TEP_FIELD_IS_STRING && + is_printable_array(data + offset, len)) { + trace_seq_printf(s, "%s", (char *)data + offset); + } else { + trace_seq_puts(s, "ARRAY["); + for (i = 0; i < len; i++) { + if (i) + trace_seq_puts(s, ", "); + trace_seq_printf(s, "%02x", + *((unsigned char *)data + offset + i)); + } + trace_seq_putc(s, ']'); + field->flags &= ~TEP_FIELD_IS_STRING; + } + } else { + val = tep_read_number(tep, data + field->offset, + field->size); + if (field->flags & TEP_FIELD_IS_POINTER) { + trace_seq_printf(s, "0x%llx", val); + } else if (field->flags & TEP_FIELD_IS_SIGNED) { + switch (field->size) { + case 4: + /* + * If field is long then print it in hex. + * A long usually stores pointers. + */ + if (field->flags & TEP_FIELD_IS_LONG) + trace_seq_printf(s, "0x%x", (int)val); + else + trace_seq_printf(s, "%d", (int)val); + break; + case 2: + trace_seq_printf(s, "%2d", (short)val); + break; + case 1: + trace_seq_printf(s, "%1d", (char)val); + break; + default: + trace_seq_printf(s, "%lld", val); + } + } else { + if (field->flags & TEP_FIELD_IS_LONG) + trace_seq_printf(s, "0x%llx", val); + else + trace_seq_printf(s, "%llu", val); + } + } +} + +void tep_print_fields(struct trace_seq *s, void *data, + int size __maybe_unused, struct tep_event *event) +{ + struct tep_format_field *field; + + field = event->format.fields; + while (field) { + trace_seq_printf(s, " %s=", field->name); + tep_print_field(s, data, field); + field = field->next; + } +} + +static int print_function(struct trace_seq *s, const char *format, + void *data, int size, struct tep_event *event, + struct tep_print_arg *arg) +{ + struct func_map *func; + unsigned long long val; + + val = eval_num_arg(data, size, event, arg); + func = find_func(event->tep, val); + if (func) { + trace_seq_puts(s, func->func); + if (*format == 'F' || *format == 'S') + trace_seq_printf(s, "+0x%llx", val - func->addr); + } else { + if (event->tep->long_size == 4) + trace_seq_printf(s, "0x%lx", (long)val); + else + trace_seq_printf(s, "0x%llx", (long long)val); + } + + return 0; +} + +static int print_arg_pointer(struct trace_seq *s, const char *format, int plen, + void *data, int size, + struct tep_event *event, struct tep_print_arg *arg) +{ + unsigned long long val; + int ret = 1; + + if (arg->type == TEP_PRINT_BSTRING) { + trace_seq_puts(s, arg->string.string); + return 0; + } + while (*format) { + if (*format == 'p') { + format++; + break; + } + format++; + } + + switch (*format) { + case 'F': + case 'f': + case 'S': + case 's': + ret += print_function(s, format, data, size, event, arg); + break; + case 'M': + case 'm': + ret += print_mac_arg(s, format, data, size, event, arg); + break; + case 'I': + case 'i': + ret += print_ip_arg(s, format, data, size, event, arg); + break; + case 'U': + ret += print_uuid_arg(s, format, data, size, event, arg); + break; + case 'h': + ret += print_raw_buff_arg(s, format, data, size, event, arg, plen); + break; + default: + ret = 0; + val = eval_num_arg(data, size, event, arg); + trace_seq_printf(s, "%p", (void *)(intptr_t)val); + break; + } + + return ret; + +} + +static int print_arg_number(struct trace_seq *s, const char *format, int plen, + void *data, int size, int ls, + struct tep_event *event, struct tep_print_arg *arg) +{ + unsigned long long val; + + val = eval_num_arg(data, size, event, arg); + + switch (ls) { + case -2: + if (plen >= 0) + trace_seq_printf(s, format, plen, (char)val); + else + trace_seq_printf(s, format, (char)val); + break; + case -1: + if (plen >= 0) + trace_seq_printf(s, format, plen, (short)val); + else + trace_seq_printf(s, format, (short)val); + break; + case 0: + if (plen >= 0) + trace_seq_printf(s, format, plen, (int)val); + else + trace_seq_printf(s, format, (int)val); + break; + case 1: + if (plen >= 0) + trace_seq_printf(s, format, plen, (long)val); + else + trace_seq_printf(s, format, (long)val); + break; + case 2: + if (plen >= 0) + trace_seq_printf(s, format, plen, (long long)val); + else + trace_seq_printf(s, format, (long long)val); + break; + default: + do_warning_event(event, "bad count (%d)", ls); + event->flags |= TEP_EVENT_FL_FAILED; + } + return 0; +} + + +static void print_arg_string(struct trace_seq *s, const char *format, int plen, + void *data, int size, + struct tep_event *event, struct tep_print_arg *arg) +{ + struct trace_seq p; + + /* Use helper trace_seq */ + trace_seq_init(&p); + print_str_arg(&p, data, size, event, + format, plen, arg); + trace_seq_terminate(&p); + trace_seq_puts(s, p.buffer); + trace_seq_destroy(&p); +} + +static int parse_arg_format_pointer(const char *format) +{ + int ret = 0; + int index; + int loop; + + switch (*format) { + case 'F': + case 'S': + case 'f': + case 's': + ret++; + break; + case 'M': + case 'm': + /* [mM]R , [mM]F */ + switch (format[1]) { + case 'R': + case 'F': + ret++; + break; + } + ret++; + break; + case 'I': + case 'i': + index = 2; + loop = 1; + switch (format[1]) { + case 'S': + /*[S][pfs]*/ + while (loop) { + switch (format[index]) { + case 'p': + case 'f': + case 's': + ret++; + index++; + break; + default: + loop = 0; + break; + } + } + /* fall through */ + case '4': + /* [4S][hnbl] */ + switch (format[index]) { + case 'h': + case 'n': + case 'l': + case 'b': + ret++; + index++; + break; + } + if (format[1] == '4') { + ret++; + break; + } + /* fall through */ + case '6': + /* [6S]c */ + if (format[index] == 'c') + ret++; + ret++; + break; + } + ret++; + break; + case 'U': + switch (format[1]) { + case 'L': + case 'l': + case 'B': + case 'b': + ret++; + break; + } + ret++; + break; + case 'h': + switch (format[1]) { + case 'C': + case 'D': + case 'N': + ret++; + break; + } + ret++; + break; + default: + break; + } + + return ret; +} + +static void free_parse_args(struct tep_print_parse *arg) +{ + struct tep_print_parse *del; + + while (arg) { + del = arg; + arg = del->next; + free(del->format); + free(del); + } +} + +static int parse_arg_add(struct tep_print_parse **parse, char *format, + enum tep_print_parse_type type, + struct tep_print_arg *arg, + struct tep_print_arg *len_as_arg, + int ls) +{ + struct tep_print_parse *parg = NULL; + + parg = calloc(1, sizeof(*parg)); + if (!parg) + goto error; + parg->format = strdup(format); + if (!parg->format) + goto error; + parg->type = type; + parg->arg = arg; + parg->len_as_arg = len_as_arg; + parg->ls = ls; + *parse = parg; + return 0; +error: + if (parg) { + free(parg->format); + free(parg); + } + return -1; +} + +static int parse_arg_format(struct tep_print_parse **parse, + struct tep_event *event, + const char *format, struct tep_print_arg **arg) +{ + struct tep_print_arg *len_arg = NULL; + char print_format[32]; + const char *start = format; + int ret = 0; + int ls = 0; + int res; + int len; + + format++; + ret++; + for (; *format; format++) { + switch (*format) { + case '#': + /* FIXME: need to handle properly */ + break; + case 'h': + ls--; + break; + case 'l': + ls++; + break; + case 'L': + ls = 2; + break; + case '.': + case 'z': + case 'Z': + case '0' ... '9': + case '-': + break; + case '*': + /* The argument is the length. */ + if (!*arg) { + do_warning_event(event, "no argument match"); + event->flags |= TEP_EVENT_FL_FAILED; + goto out_failed; + } + if (len_arg) { + do_warning_event(event, "argument already matched"); + event->flags |= TEP_EVENT_FL_FAILED; + goto out_failed; + } + len_arg = *arg; + *arg = (*arg)->next; + break; + case 'p': + if (!*arg) { + do_warning_event(event, "no argument match"); + event->flags |= TEP_EVENT_FL_FAILED; + goto out_failed; + } + res = parse_arg_format_pointer(format + 1); + if (res > 0) { + format += res; + ret += res; + } + len = ((unsigned long)format + 1) - + (unsigned long)start; + /* should never happen */ + if (len > 31) { + do_warning_event(event, "bad format!"); + event->flags |= TEP_EVENT_FL_FAILED; + len = 31; + } + memcpy(print_format, start, len); + print_format[len] = 0; + + parse_arg_add(parse, print_format, + PRINT_FMT_ARG_POINTER, *arg, len_arg, ls); + *arg = (*arg)->next; + ret++; + return ret; + case 'd': + case 'u': + case 'i': + case 'x': + case 'X': + case 'o': + if (!*arg) { + do_warning_event(event, "no argument match"); + event->flags |= TEP_EVENT_FL_FAILED; + goto out_failed; + } + + len = ((unsigned long)format + 1) - + (unsigned long)start; + + /* should never happen */ + if (len > 30) { + do_warning_event(event, "bad format!"); + event->flags |= TEP_EVENT_FL_FAILED; + len = 31; + } + memcpy(print_format, start, len); + print_format[len] = 0; + + if (event->tep->long_size == 8 && ls == 1 && + sizeof(long) != 8) { + char *p; + + /* make %l into %ll */ + if (ls == 1 && (p = strchr(print_format, 'l'))) + memmove(p+1, p, strlen(p)+1); + ls = 2; + } + if (ls < -2 || ls > 2) { + do_warning_event(event, "bad count (%d)", ls); + event->flags |= TEP_EVENT_FL_FAILED; + } + parse_arg_add(parse, print_format, + PRINT_FMT_ARG_DIGIT, *arg, len_arg, ls); + *arg = (*arg)->next; + ret++; + return ret; + case 's': + if (!*arg) { + do_warning_event(event, "no matching argument"); + event->flags |= TEP_EVENT_FL_FAILED; + goto out_failed; + } + + len = ((unsigned long)format + 1) - + (unsigned long)start; + + /* should never happen */ + if (len > 31) { + do_warning_event(event, "bad format!"); + event->flags |= TEP_EVENT_FL_FAILED; + len = 31; + } + + memcpy(print_format, start, len); + print_format[len] = 0; + + parse_arg_add(parse, print_format, + PRINT_FMT_ARG_STRING, *arg, len_arg, 0); + *arg = (*arg)->next; + ret++; + return ret; + default: + snprintf(print_format, 32, ">%c<", *format); + parse_arg_add(parse, print_format, + PRINT_FMT_STRING, NULL, NULL, 0); + ret++; + return ret; + } + ret++; + } + +out_failed: + return ret; + +} + +static int parse_arg_string(struct tep_print_parse **parse, const char *format) +{ + struct trace_seq s; + int ret = 0; + + trace_seq_init(&s); + for (; *format; format++) { + if (*format == '\\') { + format++; + ret++; + switch (*format) { + case 'n': + trace_seq_putc(&s, '\n'); + break; + case 't': + trace_seq_putc(&s, '\t'); + break; + case 'r': + trace_seq_putc(&s, '\r'); + break; + case '\\': + trace_seq_putc(&s, '\\'); + break; + default: + trace_seq_putc(&s, *format); + break; + } + } else if (*format == '%') { + if (*(format + 1) == '%') { + trace_seq_putc(&s, '%'); + format++; + ret++; + } else + break; + } else + trace_seq_putc(&s, *format); + + ret++; + } + trace_seq_terminate(&s); + parse_arg_add(parse, s.buffer, PRINT_FMT_STRING, NULL, NULL, 0); + trace_seq_destroy(&s); + + return ret; +} + +static struct tep_print_parse * +parse_args(struct tep_event *event, const char *format, struct tep_print_arg *arg) +{ + struct tep_print_parse *parse_ret = NULL; + struct tep_print_parse **parse = NULL; + int ret; + int len; + + len = strlen(format); + while (*format) { + if (!parse_ret) + parse = &parse_ret; + if (*format == '%' && *(format + 1) != '%') + ret = parse_arg_format(parse, event, format, &arg); + else + ret = parse_arg_string(parse, format); + if (*parse) + parse = &((*parse)->next); + + len -= ret; + if (len > 0) + format += ret; + else + break; + } + return parse_ret; +} + +static void print_event_cache(struct tep_print_parse *parse, struct trace_seq *s, + void *data, int size, struct tep_event *event) +{ + int len_arg; + + while (parse) { + if (parse->len_as_arg) + len_arg = eval_num_arg(data, size, event, parse->len_as_arg); + switch (parse->type) { + case PRINT_FMT_ARG_DIGIT: + print_arg_number(s, parse->format, + parse->len_as_arg ? len_arg : -1, data, + size, parse->ls, event, parse->arg); + break; + case PRINT_FMT_ARG_POINTER: + print_arg_pointer(s, parse->format, + parse->len_as_arg ? len_arg : 1, + data, size, event, parse->arg); + break; + case PRINT_FMT_ARG_STRING: + print_arg_string(s, parse->format, + parse->len_as_arg ? len_arg : -1, + data, size, event, parse->arg); + break; + case PRINT_FMT_STRING: + default: + trace_seq_printf(s, "%s", parse->format); + break; + } + parse = parse->next; + } +} + +static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event *event) +{ + struct tep_print_parse *parse = event->print_fmt.print_cache; + struct tep_print_arg *args = NULL; + char *bprint_fmt = NULL; + + if (event->flags & TEP_EVENT_FL_FAILED) { + trace_seq_printf(s, "[FAILED TO PARSE]"); + tep_print_fields(s, data, size, event); + return; + } + + if (event->flags & TEP_EVENT_FL_ISBPRINT) { + bprint_fmt = get_bprint_format(data, size, event); + args = make_bprint_args(bprint_fmt, data, size, event); + parse = parse_args(event, bprint_fmt, args); + } + + print_event_cache(parse, s, data, size, event); + + if (event->flags & TEP_EVENT_FL_ISBPRINT) { + free_parse_args(parse); + free_args(args); + free(bprint_fmt); + } +} + +/* + * 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. + */ +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; + int hardirq; + 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 */ + if (lock_depth_exists) + lock_depth = parse_common_lock_depth(tep, data); + else if (check_lock_depth) { + lock_depth = parse_common_lock_depth(tep, data); + if (lock_depth < 0) + check_lock_depth = 0; + else + lock_depth_exists = 1; + } + + /* migrate_disable may not always exist */ + if (migrate_disable_exists) + migrate_disable = parse_common_migrate_disable(tep, data); + else if (check_migrate_disable) { + migrate_disable = parse_common_migrate_disable(tep, data); + if (migrate_disable < 0) + check_migrate_disable = 0; + else + migrate_disable_exists = 1; + } + + hardirq = lat_flags & TRACE_FLAG_HARDIRQ; + softirq = lat_flags & TRACE_FLAG_SOFTIRQ; + + trace_seq_printf(&sq, "%c%c%c", + (lat_flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + (lat_flags & TRACE_FLAG_IRQS_NOSUPPORT) ? + 'X' : '.', + (lat_flags & TRACE_FLAG_NEED_RESCHED) ? + 'N' : '.', + (hardirq && softirq) ? 'H' : + hardirq ? 'h' : softirq ? 's' : '.'); + + if (pc) + trace_seq_printf(&sq, "%x", pc); + else + trace_seq_printf(&sq, "."); + + if (migrate_disable_exists) { + if (migrate_disable < 0) + trace_seq_printf(&sq, "."); + else + trace_seq_printf(&sq, "%d", migrate_disable); + } + + if (lock_depth_exists) { + if (lock_depth < 0) + trace_seq_printf(&sq, "."); + else + 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); +} + +/** + * tep_data_type - parse out the given event type + * @tep: a handle to the trace event parser context + * @rec: the record to read from + * + * This returns the event id from the @rec. + */ +int tep_data_type(struct tep_handle *tep, struct tep_record *rec) +{ + return trace_parse_common_type(tep, rec->data); +} + +/** + * tep_data_pid - parse the PID from record + * @tep: a handle to the trace event parser context + * @rec: the record to parse + * + * This returns the PID from a record. + */ +int tep_data_pid(struct tep_handle *tep, struct tep_record *rec) +{ + return parse_common_pid(tep, rec->data); +} + +/** + * tep_data_preempt_count - parse the preempt count from the record + * @tep: a handle to the trace event parser context + * @rec: the record to parse + * + * This returns the preempt count from a record. + */ +int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec) +{ + return parse_common_pc(tep, rec->data); +} + +/** + * tep_data_flags - parse the latency flags from the record + * @tep: a handle to the trace event parser context + * @rec: the record to parse + * + * This returns the latency flags from a record. + * + * Use trace_flag_type enum for the flags (see event-parse.h). + */ +int tep_data_flags(struct tep_handle *tep, struct tep_record *rec) +{ + return parse_common_flags(tep, rec->data); +} + +/** + * tep_data_comm_from_pid - return the command line from PID + * @tep: a handle to the trace event parser context + * @pid: the PID of the task to search for + * + * This returns a pointer to the command line that has the given + * @pid. + */ +const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid) +{ + const char *comm; + + comm = find_cmdline(tep, pid); + return comm; +} + +static struct tep_cmdline * +pid_from_cmdlist(struct tep_handle *tep, const char *comm, struct tep_cmdline *next) +{ + struct cmdline_list *cmdlist = (struct cmdline_list *)next; + + if (cmdlist) + cmdlist = cmdlist->next; + else + cmdlist = tep->cmdlist; + + while (cmdlist && strcmp(cmdlist->comm, comm) != 0) + cmdlist = cmdlist->next; + + return (struct tep_cmdline *)cmdlist; +} + +/** + * tep_data_pid_from_comm - return the pid from a given comm + * @tep: a handle to the trace event parser context + * @comm: the cmdline to find the pid from + * @next: the cmdline structure to find the next comm + * + * This returns the cmdline structure that holds a pid for a given + * comm, or NULL if none found. As there may be more than one pid for + * a given comm, the result of this call can be passed back into + * a recurring call in the @next parameter, and then it will find the + * next pid. + * Also, it does a linear search, so it may be slow. + */ +struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm, + struct tep_cmdline *next) +{ + struct tep_cmdline *cmdline; + + /* + * If the cmdlines have not been converted yet, then use + * the list. + */ + if (!tep->cmdlines) + return pid_from_cmdlist(tep, comm, next); + + if (next) { + /* + * The next pointer could have been still from + * a previous call before cmdlines were created + */ + if (next < tep->cmdlines || + next >= tep->cmdlines + tep->cmdline_count) + next = NULL; + else + cmdline = next++; + } + + if (!next) + cmdline = tep->cmdlines; + + while (cmdline < tep->cmdlines + tep->cmdline_count) { + if (strcmp(cmdline->comm, comm) == 0) + return cmdline; + cmdline++; + } + return NULL; +} + +/** + * tep_cmdline_pid - return the pid associated to a given cmdline + * @tep: a handle to the trace event parser context + * @cmdline: The cmdline structure to get the pid from + * + * Returns the pid for a give cmdline. If @cmdline is NULL, then + * -1 is returned. + */ +int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline) +{ + struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline; + + if (!cmdline) + return -1; + + /* + * If cmdlines have not been created yet, or cmdline is + * not part of the array, then treat it as a cmdlist instead. + */ + if (!tep->cmdlines || + cmdline < tep->cmdlines || + cmdline >= tep->cmdlines + tep->cmdline_count) + return cmdlist->pid; + + return cmdline->pid; +} + +/* + * This parses the raw @data using the given @event information and + * writes the print format into the trace_seq. + */ +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 (raw || (event->flags & TEP_EVENT_FL_PRINTRAW)) + tep_print_fields(s, record->data, record->size, event); + else { + + if (event->handler && !(event->flags & TEP_EVENT_FL_NOHANDLE)) + print_pretty = event->handler(s, record, event, + event->context); + + if (print_pretty) + pretty_print(s, record->data, record->size, event); + } + + trace_seq_terminate(s); +} + +/** + * tep_find_event_by_record - return the event from a given record + * @tep: a handle to the trace event parser context + * @record: The record to get the event from + * + * Returns the associated event for a given record, or NULL if non is + * is found. + */ +struct tep_event * +tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record) +{ + int type; + + if (record->size < 0) { + do_warning("ug! negative record size %d", record->size); + return NULL; + } + + type = trace_parse_common_type(tep, record->data); + + return tep_find_event(tep, type); +} + +/* + * 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" + */ +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", 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) +{ + const char *comm; + int 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); + } + +} + +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) +{ + int param; + + 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); +} + +static int tep_print_event_param_type(char *format, + struct print_event_type *type) +{ + char *str = format + 1; + int i = 1; + + 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; + } + 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 - Write various event information + * @tep: a handle to the trace event parser context + * @s: the trace_seq to write to + * @record: The record to get the event from + * @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(struct tep_handle *tep, struct trace_seq *s, + 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; + + if (!format) + return; + + 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) +{ + struct tep_event * const * ea = a; + struct tep_event * const * eb = b; + + if ((*ea)->id < (*eb)->id) + return -1; + + if ((*ea)->id > (*eb)->id) + return 1; + + return 0; +} + +static int events_name_cmp(const void *a, const void *b) +{ + struct tep_event * const * ea = a; + struct tep_event * const * eb = b; + int res; + + res = strcmp((*ea)->name, (*eb)->name); + if (res) + return res; + + res = strcmp((*ea)->system, (*eb)->system); + if (res) + return res; + + return events_id_cmp(a, b); +} + +static int events_system_cmp(const void *a, const void *b) +{ + struct tep_event * const * ea = a; + struct tep_event * const * eb = b; + int res; + + res = strcmp((*ea)->system, (*eb)->system); + if (res) + return res; + + res = strcmp((*ea)->name, (*eb)->name); + if (res) + return res; + + return events_id_cmp(a, b); +} + +static struct tep_event **list_events_copy(struct tep_handle *tep) +{ + struct tep_event **events; + + if (!tep) + return NULL; + + events = malloc(sizeof(*events) * (tep->nr_events + 1)); + if (!events) + return NULL; + + memcpy(events, tep->events, sizeof(*events) * tep->nr_events); + events[tep->nr_events] = NULL; + return events; +} + +static void list_events_sort(struct tep_event **events, int nr_events, + enum tep_event_sort_type sort_type) +{ + int (*sort)(const void *a, const void *b); + + switch (sort_type) { + case TEP_EVENT_SORT_ID: + sort = events_id_cmp; + break; + case TEP_EVENT_SORT_NAME: + sort = events_name_cmp; + break; + case TEP_EVENT_SORT_SYSTEM: + sort = events_system_cmp; + break; + default: + sort = NULL; + } + + if (sort) + qsort(events, nr_events, sizeof(*events), sort); +} + +/** + * tep_list_events - Get events, sorted by given criteria. + * @tep: a handle to the tep context + * @sort_type: desired sort order of the events in the array + * + * Returns an array of pointers to all events, sorted by the given + * @sort_type criteria. The last element of the array is NULL. The returned + * memory must not be freed, it is managed by the library. + * The function is not thread safe. + */ +struct tep_event **tep_list_events(struct tep_handle *tep, + enum tep_event_sort_type sort_type) +{ + struct tep_event **events; + + if (!tep) + return NULL; + + events = tep->sort_events; + if (events && tep->last_type == sort_type) + return events; + + if (!events) { + events = list_events_copy(tep); + if (!events) + return NULL; + + tep->sort_events = events; + + /* the internal events are sorted by id */ + if (sort_type == TEP_EVENT_SORT_ID) { + tep->last_type = sort_type; + return events; + } + } + + list_events_sort(events, tep->nr_events, sort_type); + tep->last_type = sort_type; + + return events; +} + + +/** + * tep_list_events_copy - Thread safe version of tep_list_events() + * @tep: a handle to the tep context + * @sort_type: desired sort order of the events in the array + * + * Returns an array of pointers to all events, sorted by the given + * @sort_type criteria. The last element of the array is NULL. The returned + * array is newly allocated inside the function and must be freed by the caller + */ +struct tep_event **tep_list_events_copy(struct tep_handle *tep, + enum tep_event_sort_type sort_type) +{ + struct tep_event **events; + + if (!tep) + return NULL; + + events = list_events_copy(tep); + if (!events) + return NULL; + + /* the internal events are sorted by id */ + if (sort_type == TEP_EVENT_SORT_ID) + return events; + + list_events_sort(events, tep->nr_events, sort_type); + + return events; +} + +static struct tep_format_field ** +get_event_fields(const char *type, const char *name, + int count, struct tep_format_field *list) +{ + struct tep_format_field **fields; + struct tep_format_field *field; + int i = 0; + + fields = malloc(sizeof(*fields) * (count + 1)); + if (!fields) + return NULL; + + for (field = list; field; field = field->next) { + fields[i++] = field; + if (i == count + 1) { + do_warning("event %s has more %s fields than specified", + name, type); + i--; + break; + } + } + + if (i != count) + do_warning("event %s has less %s fields than specified", + name, type); + + fields[i] = NULL; + + return fields; +} + +/** + * tep_event_common_fields - return a list of common fields for an event + * @event: the event to return the common fields of. + * + * Returns an allocated array of fields. The last item in the array is NULL. + * The array must be freed with free(). + */ +struct tep_format_field **tep_event_common_fields(struct tep_event *event) +{ + return get_event_fields("common", event->name, + event->format.nr_common, + event->format.common_fields); +} + +/** + * tep_event_fields - return a list of event specific fields for an event + * @event: the event to return the fields of. + * + * Returns an allocated array of fields. The last item in the array is NULL. + * The array must be freed with free(). + */ +struct tep_format_field **tep_event_fields(struct tep_event *event) +{ + return get_event_fields("event", event->name, + event->format.nr_fields, + event->format.fields); +} + +static void print_fields(struct trace_seq *s, struct tep_print_flag_sym *field) +{ + trace_seq_printf(s, "{ %s, %s }", field->value, field->str); + if (field->next) { + trace_seq_puts(s, ", "); + print_fields(s, field->next); + } +} + +/* for debugging */ +static void print_args(struct tep_print_arg *args) +{ + int print_paren = 1; + struct trace_seq s; + + switch (args->type) { + case TEP_PRINT_NULL: + printf("null"); + break; + case TEP_PRINT_ATOM: + printf("%s", args->atom.atom); + break; + case TEP_PRINT_FIELD: + printf("REC->%s", args->field.name); + break; + case TEP_PRINT_FLAGS: + printf("__print_flags("); + print_args(args->flags.field); + printf(", %s, ", args->flags.delim); + trace_seq_init(&s); + print_fields(&s, args->flags.flags); + trace_seq_do_printf(&s); + trace_seq_destroy(&s); + printf(")"); + break; + case TEP_PRINT_SYMBOL: + printf("__print_symbolic("); + print_args(args->symbol.field); + printf(", "); + trace_seq_init(&s); + print_fields(&s, args->symbol.symbols); + trace_seq_do_printf(&s); + trace_seq_destroy(&s); + printf(")"); + break; + case TEP_PRINT_HEX: + printf("__print_hex("); + print_args(args->hex.field); + printf(", "); + print_args(args->hex.size); + printf(")"); + break; + case TEP_PRINT_HEX_STR: + printf("__print_hex_str("); + print_args(args->hex.field); + printf(", "); + print_args(args->hex.size); + printf(")"); + break; + case TEP_PRINT_INT_ARRAY: + printf("__print_array("); + print_args(args->int_array.field); + printf(", "); + print_args(args->int_array.count); + printf(", "); + print_args(args->int_array.el_size); + printf(")"); + break; + case TEP_PRINT_STRING: + case TEP_PRINT_BSTRING: + printf("__get_str(%s)", args->string.string); + break; + case TEP_PRINT_BITMASK: + printf("__get_bitmask(%s)", args->bitmask.bitmask); + break; + case TEP_PRINT_TYPE: + printf("(%s)", args->typecast.type); + print_args(args->typecast.item); + break; + case TEP_PRINT_OP: + if (strcmp(args->op.op, ":") == 0) + print_paren = 0; + if (print_paren) + printf("("); + print_args(args->op.left); + printf(" %s ", args->op.op); + print_args(args->op.right); + if (print_paren) + printf(")"); + break; + default: + /* we should warn... */ + return; + } + if (args->next) { + printf("\n"); + print_args(args->next); + } +} + +static void parse_header_field(const char *field, + int *offset, int *size, int mandatory) +{ + unsigned long long save_input_buf_ptr; + unsigned long long save_input_buf_siz; + char *token; + int type; + + save_input_buf_ptr = input_buf_ptr; + save_input_buf_siz = input_buf_siz; + + if (read_expected(TEP_EVENT_ITEM, "field") < 0) + return; + if (read_expected(TEP_EVENT_OP, ":") < 0) + return; + + /* type */ + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto fail; + free_token(token); + + /* + * If this is not a mandatory field, then test it first. + */ + if (mandatory) { + if (read_expected(TEP_EVENT_ITEM, field) < 0) + return; + } else { + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto fail; + if (strcmp(token, field) != 0) + goto discard; + free_token(token); + } + + if (read_expected(TEP_EVENT_OP, ";") < 0) + return; + if (read_expected(TEP_EVENT_ITEM, "offset") < 0) + return; + if (read_expected(TEP_EVENT_OP, ":") < 0) + return; + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto fail; + *offset = atoi(token); + free_token(token); + if (read_expected(TEP_EVENT_OP, ";") < 0) + return; + if (read_expected(TEP_EVENT_ITEM, "size") < 0) + return; + if (read_expected(TEP_EVENT_OP, ":") < 0) + return; + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto fail; + *size = atoi(token); + free_token(token); + if (read_expected(TEP_EVENT_OP, ";") < 0) + return; + type = read_token(&token); + if (type != TEP_EVENT_NEWLINE) { + /* newer versions of the kernel have a "signed" type */ + if (type != TEP_EVENT_ITEM) + goto fail; + + if (strcmp(token, "signed") != 0) + goto fail; + + free_token(token); + + if (read_expected(TEP_EVENT_OP, ":") < 0) + return; + + if (read_expect_type(TEP_EVENT_ITEM, &token)) + goto fail; + + free_token(token); + if (read_expected(TEP_EVENT_OP, ";") < 0) + return; + + if (read_expect_type(TEP_EVENT_NEWLINE, &token)) + goto fail; + } + fail: + free_token(token); + return; + + discard: + input_buf_ptr = save_input_buf_ptr; + input_buf_siz = save_input_buf_siz; + *offset = 0; + *size = 0; + free_token(token); +} + +/** + * tep_parse_header_page - parse the data stored in the header page + * @tep: a handle to the trace event parser context + * @buf: the buffer storing the header page format string + * @size: the size of @buf + * @long_size: the long size to use if there is no header + * + * This parses the header page format for information on the + * ring buffer used. The @buf should be copied from + * + * /sys/kernel/debug/tracing/events/header_page + */ +int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size, + int long_size) +{ + int ignore; + + if (!size) { + /* + * Old kernels did not have header page info. + * Sorry but we just use what we find here in user space. + */ + tep->header_page_ts_size = sizeof(long long); + tep->header_page_size_size = long_size; + tep->header_page_data_offset = sizeof(long long) + long_size; + tep->old_format = 1; + return -1; + } + init_input_buf(buf, size); + + parse_header_field("timestamp", &tep->header_page_ts_offset, + &tep->header_page_ts_size, 1); + parse_header_field("commit", &tep->header_page_size_offset, + &tep->header_page_size_size, 1); + parse_header_field("overwrite", &tep->header_page_overwrite, + &ignore, 0); + parse_header_field("data", &tep->header_page_data_offset, + &tep->header_page_data_size, 1); + + return 0; +} + +static int event_matches(struct tep_event *event, + int id, const char *sys_name, + const char *event_name) +{ + if (id >= 0 && id != event->id) + return 0; + + if (event_name && (strcmp(event_name, event->name) != 0)) + return 0; + + if (sys_name && (strcmp(sys_name, event->system) != 0)) + return 0; + + return 1; +} + +static void free_handler(struct event_handler *handle) +{ + free((void *)handle->sys_name); + free((void *)handle->event_name); + free(handle); +} + +static int find_event_handle(struct tep_handle *tep, struct tep_event *event) +{ + struct event_handler *handle, **next; + + for (next = &tep->handlers; *next; + next = &(*next)->next) { + handle = *next; + if (event_matches(event, handle->id, + handle->sys_name, + handle->event_name)) + break; + } + + if (!(*next)) + return 0; + + pr_stat("overriding event (%d) %s:%s with new print handler", + event->id, event->system, event->name); + + event->handler = handle->func; + event->context = handle->context; + + *next = handle->next; + free_handler(handle); + + return 1; +} + +/** + * parse_format - parse the event format + * @buf: the buffer storing the event format string + * @size: the size of @buf + * @sys: the system the event belongs to + * + * This parses the event format and creates an event structure + * to quickly parse raw data for a given event. + * + * These files currently come from: + * + * /sys/kernel/debug/tracing/events/.../.../format + */ +static enum tep_errno parse_format(struct tep_event **eventp, + struct tep_handle *tep, const char *buf, + unsigned long size, const char *sys) +{ + struct tep_event *event; + int ret; + + init_input_buf(buf, size); + + *eventp = event = alloc_event(); + if (!event) + return TEP_ERRNO__MEM_ALLOC_FAILED; + + event->name = event_read_name(); + if (!event->name) { + /* Bad event? */ + ret = TEP_ERRNO__MEM_ALLOC_FAILED; + goto event_alloc_failed; + } + + if (strcmp(sys, "ftrace") == 0) { + event->flags |= TEP_EVENT_FL_ISFTRACE; + + if (strcmp(event->name, "bprint") == 0) + event->flags |= TEP_EVENT_FL_ISBPRINT; + } + + event->id = event_read_id(); + if (event->id < 0) { + ret = TEP_ERRNO__READ_ID_FAILED; + /* + * This isn't an allocation error actually. + * But as the ID is critical, just bail out. + */ + goto event_alloc_failed; + } + + event->system = strdup(sys); + if (!event->system) { + ret = TEP_ERRNO__MEM_ALLOC_FAILED; + goto event_alloc_failed; + } + + /* Add tep to event so that it can be referenced */ + event->tep = tep; + + ret = event_read_format(event); + if (ret < 0) { + ret = TEP_ERRNO__READ_FORMAT_FAILED; + goto event_parse_failed; + } + + /* + * If the event has an override, don't print warnings if the event + * print format fails to parse. + */ + if (tep && find_event_handle(tep, event)) + show_warning = 0; + + ret = event_read_print(event); + show_warning = 1; + + if (ret < 0) { + ret = TEP_ERRNO__READ_PRINT_FAILED; + goto event_parse_failed; + } + + if (!ret && (event->flags & TEP_EVENT_FL_ISFTRACE)) { + struct tep_format_field *field; + struct tep_print_arg *arg, **list; + + /* old ftrace had no args */ + list = &event->print_fmt.args; + for (field = event->format.fields; field; field = field->next) { + arg = alloc_arg(); + if (!arg) { + event->flags |= TEP_EVENT_FL_FAILED; + return TEP_ERRNO__OLD_FTRACE_ARG_FAILED; + } + arg->type = TEP_PRINT_FIELD; + arg->field.name = strdup(field->name); + if (!arg->field.name) { + event->flags |= TEP_EVENT_FL_FAILED; + free_arg(arg); + return TEP_ERRNO__OLD_FTRACE_ARG_FAILED; + } + arg->field.field = field; + *list = arg; + list = &arg->next; + } + } + + if (!(event->flags & TEP_EVENT_FL_ISBPRINT)) + event->print_fmt.print_cache = parse_args(event, + event->print_fmt.format, + event->print_fmt.args); + + return 0; + + event_parse_failed: + event->flags |= TEP_EVENT_FL_FAILED; + return ret; + + event_alloc_failed: + free(event->system); + free(event->name); + free(event); + *eventp = NULL; + return ret; +} + +static enum tep_errno +__parse_event(struct tep_handle *tep, + struct tep_event **eventp, + const char *buf, unsigned long size, + const char *sys) +{ + int ret = parse_format(eventp, tep, buf, size, sys); + struct tep_event *event = *eventp; + + if (event == NULL) + return ret; + + if (tep && add_event(tep, event)) { + ret = TEP_ERRNO__MEM_ALLOC_FAILED; + goto event_add_failed; + } + +#define PRINT_ARGS 0 + if (PRINT_ARGS && event->print_fmt.args) + print_args(event->print_fmt.args); + + return 0; + +event_add_failed: + free_tep_event(event); + return ret; +} + +/** + * tep_parse_format - parse the event format + * @tep: a handle to the trace event parser context + * @eventp: returned format + * @buf: the buffer storing the event format string + * @size: the size of @buf + * @sys: the system the event belongs to + * + * This parses the event format and creates an event structure + * to quickly parse raw data for a given event. + * + * These files currently come from: + * + * /sys/kernel/debug/tracing/events/.../.../format + */ +enum tep_errno tep_parse_format(struct tep_handle *tep, + struct tep_event **eventp, + const char *buf, + unsigned long size, const char *sys) +{ + return __parse_event(tep, eventp, buf, size, sys); +} + +/** + * tep_parse_event - parse the event format + * @tep: a handle to the trace event parser context + * @buf: the buffer storing the event format string + * @size: the size of @buf + * @sys: the system the event belongs to + * + * This parses the event format and creates an event structure + * to quickly parse raw data for a given event. + * + * These files currently come from: + * + * /sys/kernel/debug/tracing/events/.../.../format + */ +enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf, + unsigned long size, const char *sys) +{ + struct tep_event *event = NULL; + return __parse_event(tep, &event, buf, size, sys); +} + +int get_field_val(struct trace_seq *s, struct tep_format_field *field, + const char *name, struct tep_record *record, + unsigned long long *val, int err) +{ + if (!field) { + if (err) + trace_seq_printf(s, "<CANT FIND FIELD %s>", name); + return -1; + } + + if (tep_read_number_field(field, record->data, val)) { + if (err) + trace_seq_printf(s, " %s=INVALID", name); + return -1; + } + + return 0; +} + +/** + * tep_get_field_raw - return the raw pointer into the data field + * @s: The seq to print to on error + * @event: the event that the field is for + * @name: The name of the field + * @record: The record with the field name. + * @len: place to store the field length. + * @err: print default error if failed. + * + * Returns a pointer into record->data of the field and places + * the length of the field in @len. + * + * On failure, it returns NULL. + */ +void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event, + const char *name, struct tep_record *record, + int *len, int err) +{ + struct tep_format_field *field; + void *data = record->data; + unsigned offset; + int dummy; + + if (!event) + return NULL; + + field = tep_find_field(event, name); + + if (!field) { + if (err) + trace_seq_printf(s, "<CANT FIND FIELD %s>", name); + return NULL; + } + + /* Allow @len to be NULL */ + if (!len) + len = &dummy; + + offset = field->offset; + if (field->flags & TEP_FIELD_IS_DYNAMIC) { + offset = tep_read_number(event->tep, + data + offset, field->size); + *len = offset >> 16; + offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; + } else + *len = field->size; + + return data + offset; +} + +/** + * tep_get_field_val - find a field and return its value + * @s: The seq to print to on error + * @event: the event that the field is for + * @name: The name of the field + * @record: The record with the field name. + * @val: place to store the value of the field. + * @err: print default error if failed. + * + * Returns 0 on success -1 on field not found. + */ +int tep_get_field_val(struct trace_seq *s, struct tep_event *event, + const char *name, struct tep_record *record, + unsigned long long *val, int err) +{ + struct tep_format_field *field; + + if (!event) + return -1; + + field = tep_find_field(event, name); + + return get_field_val(s, field, name, record, val, err); +} + +/** + * tep_get_common_field_val - find a common field and return its value + * @s: The seq to print to on error + * @event: the event that the field is for + * @name: The name of the field + * @record: The record with the field name. + * @val: place to store the value of the field. + * @err: print default error if failed. + * + * Returns 0 on success -1 on field not found. + */ +int tep_get_common_field_val(struct trace_seq *s, struct tep_event *event, + const char *name, struct tep_record *record, + unsigned long long *val, int err) +{ + struct tep_format_field *field; + + if (!event) + return -1; + + field = tep_find_common_field(event, name); + + return get_field_val(s, field, name, record, val, err); +} + +/** + * tep_get_any_field_val - find a any field and return its value + * @s: The seq to print to on error + * @event: the event that the field is for + * @name: The name of the field + * @record: The record with the field name. + * @val: place to store the value of the field. + * @err: print default error if failed. + * + * Returns 0 on success -1 on field not found. + */ +int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event, + const char *name, struct tep_record *record, + unsigned long long *val, int err) +{ + struct tep_format_field *field; + + if (!event) + return -1; + + field = tep_find_any_field(event, name); + + return get_field_val(s, field, name, record, val, err); +} + +/** + * tep_print_num_field - print a field and a format + * @s: The seq to print to + * @fmt: The printf format to print the field with. + * @event: the event that the field is for + * @name: The name of the field + * @record: The record with the field name. + * @err: print default error if failed. + * + * Returns positive value on success, negative in case of an error, + * or 0 if buffer is full. + */ +int tep_print_num_field(struct trace_seq *s, const char *fmt, + struct tep_event *event, const char *name, + struct tep_record *record, int err) +{ + struct tep_format_field *field = tep_find_field(event, name); + unsigned long long val; + + if (!field) + goto failed; + + if (tep_read_number_field(field, record->data, &val)) + goto failed; + + return trace_seq_printf(s, fmt, val); + + failed: + if (err) + trace_seq_printf(s, "CAN'T FIND FIELD \"%s\"", name); + return -1; +} + +/** + * tep_print_func_field - print a field and a format for function pointers + * @s: The seq to print to + * @fmt: The printf format to print the field with. + * @event: the event that the field is for + * @name: The name of the field + * @record: The record with the field name. + * @err: print default error if failed. + * + * Returns positive value on success, negative in case of an error, + * or 0 if buffer is full. + */ +int tep_print_func_field(struct trace_seq *s, const char *fmt, + struct tep_event *event, const char *name, + struct tep_record *record, int err) +{ + struct tep_format_field *field = tep_find_field(event, name); + struct tep_handle *tep = event->tep; + unsigned long long val; + struct func_map *func; + char tmp[128]; + + if (!field) + goto failed; + + if (tep_read_number_field(field, record->data, &val)) + goto failed; + + func = find_func(tep, val); + + if (func) + snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val); + else + sprintf(tmp, "0x%08llx", val); + + return trace_seq_printf(s, fmt, tmp); + + failed: + if (err) + trace_seq_printf(s, "CAN'T FIND FIELD \"%s\"", name); + return -1; +} + +static void free_func_handle(struct tep_function_handler *func) +{ + struct func_params *params; + + free(func->name); + + while (func->params) { + params = func->params; + func->params = params->next; + free(params); + } + + free(func); +} + +/** + * tep_register_print_function - register a helper function + * @tep: a handle to the trace event parser context + * @func: the function to process the helper function + * @ret_type: the return type of the helper function + * @name: the name of the helper function + * @parameters: A list of enum tep_func_arg_type + * + * Some events may have helper functions in the print format arguments. + * This allows a plugin to dynamically create a way to process one + * of these functions. + * + * The @parameters is a variable list of tep_func_arg_type enums that + * must end with TEP_FUNC_ARG_VOID. + */ +int tep_register_print_function(struct tep_handle *tep, + tep_func_handler func, + enum tep_func_arg_type ret_type, + char *name, ...) +{ + struct tep_function_handler *func_handle; + struct func_params **next_param; + struct func_params *param; + enum tep_func_arg_type type; + va_list ap; + int ret; + + func_handle = find_func_handler(tep, name); + if (func_handle) { + /* + * This is most like caused by the users own + * plugins updating the function. This overrides the + * system defaults. + */ + pr_stat("override of function helper '%s'", name); + remove_func_handler(tep, name); + } + + func_handle = calloc(1, sizeof(*func_handle)); + if (!func_handle) { + do_warning("Failed to allocate function handler"); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + + func_handle->ret_type = ret_type; + func_handle->name = strdup(name); + func_handle->func = func; + if (!func_handle->name) { + do_warning("Failed to allocate function name"); + free(func_handle); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + + next_param = &(func_handle->params); + va_start(ap, name); + for (;;) { + type = va_arg(ap, enum tep_func_arg_type); + if (type == TEP_FUNC_ARG_VOID) + break; + + if (type >= TEP_FUNC_ARG_MAX_TYPES) { + do_warning("Invalid argument type %d", type); + ret = TEP_ERRNO__INVALID_ARG_TYPE; + goto out_free; + } + + param = malloc(sizeof(*param)); + if (!param) { + do_warning("Failed to allocate function param"); + ret = TEP_ERRNO__MEM_ALLOC_FAILED; + goto out_free; + } + param->type = type; + param->next = NULL; + + *next_param = param; + next_param = &(param->next); + + func_handle->nr_args++; + } + va_end(ap); + + func_handle->next = tep->func_handlers; + tep->func_handlers = func_handle; + + return 0; + out_free: + va_end(ap); + free_func_handle(func_handle); + return ret; +} + +/** + * tep_unregister_print_function - unregister a helper function + * @tep: a handle to the trace event parser context + * @func: the function to process the helper function + * @name: the name of the helper function + * + * This function removes existing print handler for function @name. + * + * Returns 0 if the handler was removed successully, -1 otherwise. + */ +int tep_unregister_print_function(struct tep_handle *tep, + tep_func_handler func, char *name) +{ + struct tep_function_handler *func_handle; + + func_handle = find_func_handler(tep, name); + if (func_handle && func_handle->func == func) { + remove_func_handler(tep, name); + return 0; + } + return -1; +} + +static struct tep_event *search_event(struct tep_handle *tep, int id, + const char *sys_name, + const char *event_name) +{ + struct tep_event *event; + + if (id >= 0) { + /* search by id */ + event = tep_find_event(tep, id); + if (!event) + return NULL; + if (event_name && (strcmp(event_name, event->name) != 0)) + return NULL; + if (sys_name && (strcmp(sys_name, event->system) != 0)) + return NULL; + } else { + event = tep_find_event_by_name(tep, sys_name, event_name); + if (!event) + return NULL; + } + return event; +} + +/** + * tep_register_event_handler - register a way to parse an event + * @tep: a handle to the trace event parser context + * @id: the id of the event to register + * @sys_name: the system name the event belongs to + * @event_name: the name of the event + * @func: the function to call to parse the event information + * @context: the data to be passed to @func + * + * This function allows a developer to override the parsing of + * a given event. If for some reason the default print format + * is not sufficient, this function will register a function + * for an event to be used to parse the data instead. + * + * If @id is >= 0, then it is used to find the event. + * else @sys_name and @event_name are used. + * + * Returns: + * TEP_REGISTER_SUCCESS_OVERWRITE if an existing handler is overwritten + * TEP_REGISTER_SUCCESS if a new handler is registered successfully + * negative TEP_ERRNO_... in case of an error + * + */ +int tep_register_event_handler(struct tep_handle *tep, int id, + const char *sys_name, const char *event_name, + tep_event_handler_func func, void *context) +{ + struct tep_event *event; + struct event_handler *handle; + + event = search_event(tep, id, sys_name, event_name); + if (event == NULL) + goto not_found; + + pr_stat("overriding event (%d) %s:%s with new print handler", + event->id, event->system, event->name); + + event->handler = func; + event->context = context; + return TEP_REGISTER_SUCCESS_OVERWRITE; + + not_found: + /* Save for later use. */ + handle = calloc(1, sizeof(*handle)); + if (!handle) { + do_warning("Failed to allocate event handler"); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + + handle->id = id; + if (event_name) + handle->event_name = strdup(event_name); + if (sys_name) + handle->sys_name = strdup(sys_name); + + if ((event_name && !handle->event_name) || + (sys_name && !handle->sys_name)) { + do_warning("Failed to allocate event/sys name"); + free((void *)handle->event_name); + free((void *)handle->sys_name); + free(handle); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + + handle->func = func; + handle->next = tep->handlers; + tep->handlers = handle; + handle->context = context; + + return TEP_REGISTER_SUCCESS; +} + +static int handle_matches(struct event_handler *handler, int id, + const char *sys_name, const char *event_name, + tep_event_handler_func func, void *context) +{ + if (id >= 0 && id != handler->id) + return 0; + + if (event_name && (strcmp(event_name, handler->event_name) != 0)) + return 0; + + if (sys_name && (strcmp(sys_name, handler->sys_name) != 0)) + return 0; + + if (func != handler->func || context != handler->context) + return 0; + + return 1; +} + +/** + * tep_unregister_event_handler - unregister an existing event handler + * @tep: a handle to the trace event parser context + * @id: the id of the event to unregister + * @sys_name: the system name the handler belongs to + * @event_name: the name of the event handler + * @func: the function to call to parse the event information + * @context: the data to be passed to @func + * + * This function removes existing event handler (parser). + * + * If @id is >= 0, then it is used to find the event. + * else @sys_name and @event_name are used. + * + * Returns 0 if handler was removed successfully, -1 if event was not found. + */ +int tep_unregister_event_handler(struct tep_handle *tep, int id, + const char *sys_name, const char *event_name, + tep_event_handler_func func, void *context) +{ + struct tep_event *event; + struct event_handler *handle; + struct event_handler **next; + + event = search_event(tep, id, sys_name, event_name); + if (event == NULL) + goto not_found; + + if (event->handler == func && event->context == context) { + pr_stat("removing override handler for event (%d) %s:%s. Going back to default handler.", + event->id, event->system, event->name); + + event->handler = NULL; + event->context = NULL; + return 0; + } + +not_found: + for (next = &tep->handlers; *next; next = &(*next)->next) { + handle = *next; + if (handle_matches(handle, id, sys_name, event_name, + func, context)) + break; + } + + if (!(*next)) + return -1; + + *next = handle->next; + free_handler(handle); + + return 0; +} + +/** + * tep_alloc - create a tep handle + */ +struct tep_handle *tep_alloc(void) +{ + struct tep_handle *tep = calloc(1, sizeof(*tep)); + + if (tep) { + tep->ref_count = 1; + tep->host_bigendian = tep_is_bigendian(); + } + + return tep; +} + +void tep_ref(struct tep_handle *tep) +{ + tep->ref_count++; +} + +int tep_get_ref(struct tep_handle *tep) +{ + if (tep) + return tep->ref_count; + return 0; +} + +__hidden void free_tep_format_field(struct tep_format_field *field) +{ + free(field->type); + if (field->alias != field->name) + free(field->alias); + free(field->name); + free(field); +} + +static void free_format_fields(struct tep_format_field *field) +{ + struct tep_format_field *next; + + while (field) { + next = field->next; + free_tep_format_field(field); + field = next; + } +} + +static void free_formats(struct tep_format *format) +{ + free_format_fields(format->common_fields); + free_format_fields(format->fields); +} + +__hidden void free_tep_event(struct tep_event *event) +{ + free(event->name); + free(event->system); + + free_formats(&event->format); + + free(event->print_fmt.format); + free_args(event->print_fmt.args); + free_parse_args(event->print_fmt.print_cache); + free(event); +} + +/** + * tep_free - free a tep handle + * @tep: the tep handle to free + */ +void tep_free(struct tep_handle *tep) +{ + struct cmdline_list *cmdlist, *cmdnext; + struct func_list *funclist, *funcnext; + struct printk_list *printklist, *printknext; + struct tep_function_handler *func_handler; + struct event_handler *handle; + int i; + + if (!tep) + return; + + cmdlist = tep->cmdlist; + funclist = tep->funclist; + printklist = tep->printklist; + + tep->ref_count--; + if (tep->ref_count) + return; + + if (tep->cmdlines) { + for (i = 0; i < tep->cmdline_count; i++) + free(tep->cmdlines[i].comm); + free(tep->cmdlines); + } + + while (cmdlist) { + cmdnext = cmdlist->next; + free(cmdlist->comm); + free(cmdlist); + cmdlist = cmdnext; + } + + if (tep->func_map) { + for (i = 0; i < (int)tep->func_count; i++) { + free(tep->func_map[i].func); + free(tep->func_map[i].mod); + } + free(tep->func_map); + } + + while (funclist) { + funcnext = funclist->next; + free(funclist->func); + free(funclist->mod); + free(funclist); + funclist = funcnext; + } + + while (tep->func_handlers) { + func_handler = tep->func_handlers; + tep->func_handlers = func_handler->next; + free_func_handle(func_handler); + } + + if (tep->printk_map) { + for (i = 0; i < (int)tep->printk_count; i++) + free(tep->printk_map[i].printk); + free(tep->printk_map); + } + + while (printklist) { + printknext = printklist->next; + free(printklist->printk); + free(printklist); + printklist = printknext; + } + + for (i = 0; i < tep->nr_events; i++) + free_tep_event(tep->events[i]); + + while (tep->handlers) { + handle = tep->handlers; + tep->handlers = handle->next; + free_handler(handle); + } + + free(tep->events); + free(tep->sort_events); + free(tep->func_resolver); + free_tep_plugin_paths(tep); + + free(tep); +} + +void tep_unref(struct tep_handle *tep) +{ + tep_free(tep); +} diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h new file mode 100644 index 000000000..41d4f9f6a --- /dev/null +++ b/tools/lib/traceevent/event-parse.h @@ -0,0 +1,750 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ +#ifndef _PARSE_EVENTS_H +#define _PARSE_EVENTS_H + +#include <stdbool.h> +#include <stdarg.h> +#include <stdio.h> +#include <regex.h> +#include <string.h> + +#include "trace-seq.h" + +#ifndef __maybe_unused +#define __maybe_unused __attribute__((unused)) +#endif + +#ifndef DEBUG_RECORD +#define DEBUG_RECORD 0 +#endif + +struct tep_record { + unsigned long long ts; + unsigned long long offset; + long long missed_events; /* buffer dropped events before */ + int record_size; /* size of binary record */ + int size; /* size of data */ + void *data; + int cpu; + int ref_count; + int locked; /* Do not free, even if ref_count is zero */ + void *priv; +#if DEBUG_RECORD + struct tep_record *prev; + struct tep_record *next; + long alloc_addr; +#endif +}; + +/* ----------------------- tep ----------------------- */ + +struct tep_handle; +struct tep_event; + +typedef int (*tep_event_handler_func)(struct trace_seq *s, + struct tep_record *record, + struct tep_event *event, + void *context); + +typedef int (*tep_plugin_load_func)(struct tep_handle *tep); +typedef int (*tep_plugin_unload_func)(struct tep_handle *tep); + +struct tep_plugin_option { + struct tep_plugin_option *next; + void *handle; + char *file; + char *name; + char *plugin_alias; + char *description; + const char *value; + void *priv; + int set; +}; + +/* + * Plugin hooks that can be called: + * + * TEP_PLUGIN_LOADER: (required) + * The function name to initialized the plugin. + * + * int TEP_PLUGIN_LOADER(struct tep_handle *tep) + * + * TEP_PLUGIN_UNLOADER: (optional) + * The function called just before unloading + * + * int TEP_PLUGIN_UNLOADER(struct tep_handle *tep) + * + * TEP_PLUGIN_OPTIONS: (optional) + * Plugin options that can be set before loading + * + * struct tep_plugin_option TEP_PLUGIN_OPTIONS[] = { + * { + * .name = "option-name", + * .plugin_alias = "override-file-name", (optional) + * .description = "description of option to show users", + * }, + * { + * .name = NULL, + * }, + * }; + * + * Array must end with .name = NULL; + * + * + * .plugin_alias is used to give a shorter name to access + * the vairable. Useful if a plugin handles more than one event. + * + * If .value is not set, then it is considered a boolean and only + * .set will be processed. If .value is defined, then it is considered + * a string option and .set will be ignored. + * + * TEP_PLUGIN_ALIAS: (optional) + * The name to use for finding options (uses filename if not defined) + */ +#define TEP_PLUGIN_LOADER tep_plugin_loader +#define TEP_PLUGIN_UNLOADER tep_plugin_unloader +#define TEP_PLUGIN_OPTIONS tep_plugin_options +#define TEP_PLUGIN_ALIAS tep_plugin_alias +#define _MAKE_STR(x) #x +#define MAKE_STR(x) _MAKE_STR(x) +#define TEP_PLUGIN_LOADER_NAME MAKE_STR(TEP_PLUGIN_LOADER) +#define TEP_PLUGIN_UNLOADER_NAME MAKE_STR(TEP_PLUGIN_UNLOADER) +#define TEP_PLUGIN_OPTIONS_NAME MAKE_STR(TEP_PLUGIN_OPTIONS) +#define TEP_PLUGIN_ALIAS_NAME MAKE_STR(TEP_PLUGIN_ALIAS) + +enum tep_format_flags { + TEP_FIELD_IS_ARRAY = 1, + TEP_FIELD_IS_POINTER = 2, + TEP_FIELD_IS_SIGNED = 4, + TEP_FIELD_IS_STRING = 8, + TEP_FIELD_IS_DYNAMIC = 16, + TEP_FIELD_IS_LONG = 32, + TEP_FIELD_IS_FLAG = 64, + TEP_FIELD_IS_SYMBOLIC = 128, + TEP_FIELD_IS_RELATIVE = 256, +}; + +struct tep_format_field { + struct tep_format_field *next; + struct tep_event *event; + char *type; + char *name; + char *alias; + int offset; + int size; + unsigned int arraylen; + unsigned int elementsize; + unsigned long flags; +}; + +struct tep_format { + int nr_common; + int nr_fields; + struct tep_format_field *common_fields; + struct tep_format_field *fields; +}; + +struct tep_print_arg_atom { + char *atom; +}; + +struct tep_print_arg_string { + char *string; + struct tep_format_field *field; +}; + +struct tep_print_arg_bitmask { + char *bitmask; + struct tep_format_field *field; +}; + +struct tep_print_arg_field { + char *name; + struct tep_format_field *field; +}; + +struct tep_print_flag_sym { + struct tep_print_flag_sym *next; + char *value; + char *str; +}; + +struct tep_print_arg_typecast { + char *type; + struct tep_print_arg *item; +}; + +struct tep_print_arg_flags { + struct tep_print_arg *field; + char *delim; + struct tep_print_flag_sym *flags; +}; + +struct tep_print_arg_symbol { + struct tep_print_arg *field; + struct tep_print_flag_sym *symbols; +}; + +struct tep_print_arg_hex { + struct tep_print_arg *field; + struct tep_print_arg *size; +}; + +struct tep_print_arg_int_array { + struct tep_print_arg *field; + struct tep_print_arg *count; + struct tep_print_arg *el_size; +}; + +struct tep_print_arg_dynarray { + struct tep_format_field *field; + struct tep_print_arg *index; +}; + +struct tep_print_arg; + +struct tep_print_arg_op { + char *op; + int prio; + struct tep_print_arg *left; + struct tep_print_arg *right; +}; + +struct tep_function_handler; + +struct tep_print_arg_func { + struct tep_function_handler *func; + struct tep_print_arg *args; +}; + +enum tep_print_arg_type { + TEP_PRINT_NULL, + TEP_PRINT_ATOM, + TEP_PRINT_FIELD, + TEP_PRINT_FLAGS, + TEP_PRINT_SYMBOL, + TEP_PRINT_HEX, + TEP_PRINT_INT_ARRAY, + TEP_PRINT_TYPE, + TEP_PRINT_STRING, + TEP_PRINT_BSTRING, + TEP_PRINT_DYNAMIC_ARRAY, + TEP_PRINT_OP, + TEP_PRINT_FUNC, + TEP_PRINT_BITMASK, + TEP_PRINT_DYNAMIC_ARRAY_LEN, + TEP_PRINT_HEX_STR, +}; + +struct tep_print_arg { + struct tep_print_arg *next; + enum tep_print_arg_type type; + union { + struct tep_print_arg_atom atom; + struct tep_print_arg_field field; + struct tep_print_arg_typecast typecast; + struct tep_print_arg_flags flags; + struct tep_print_arg_symbol symbol; + struct tep_print_arg_hex hex; + struct tep_print_arg_int_array int_array; + struct tep_print_arg_func func; + struct tep_print_arg_string string; + struct tep_print_arg_bitmask bitmask; + struct tep_print_arg_op op; + struct tep_print_arg_dynarray dynarray; + }; +}; + +struct tep_print_parse; + +struct tep_print_fmt { + char *format; + struct tep_print_arg *args; + struct tep_print_parse *print_cache; +}; + +struct tep_event { + struct tep_handle *tep; + char *name; + int id; + int flags; + struct tep_format format; + struct tep_print_fmt print_fmt; + char *system; + tep_event_handler_func handler; + void *context; +}; + +enum { + TEP_EVENT_FL_ISFTRACE = 0x01, + TEP_EVENT_FL_ISPRINT = 0x02, + TEP_EVENT_FL_ISBPRINT = 0x04, + TEP_EVENT_FL_ISFUNCENT = 0x10, + TEP_EVENT_FL_ISFUNCRET = 0x20, + TEP_EVENT_FL_NOHANDLE = 0x40, + TEP_EVENT_FL_PRINTRAW = 0x80, + + TEP_EVENT_FL_FAILED = 0x80000000 +}; + +enum tep_event_sort_type { + TEP_EVENT_SORT_ID, + TEP_EVENT_SORT_NAME, + TEP_EVENT_SORT_SYSTEM, +}; + +enum tep_event_type { + TEP_EVENT_ERROR, + TEP_EVENT_NONE, + TEP_EVENT_SPACE, + TEP_EVENT_NEWLINE, + TEP_EVENT_OP, + TEP_EVENT_DELIM, + TEP_EVENT_ITEM, + TEP_EVENT_DQUOTE, + TEP_EVENT_SQUOTE, +}; + +typedef unsigned long long (*tep_func_handler)(struct trace_seq *s, + unsigned long long *args); + +enum tep_func_arg_type { + TEP_FUNC_ARG_VOID, + TEP_FUNC_ARG_INT, + TEP_FUNC_ARG_LONG, + TEP_FUNC_ARG_STRING, + TEP_FUNC_ARG_PTR, + TEP_FUNC_ARG_MAX_TYPES +}; + +enum tep_flag { + TEP_NSEC_OUTPUT = 1, /* output in NSECS */ + TEP_DISABLE_SYS_PLUGINS = 1 << 1, + TEP_DISABLE_PLUGINS = 1 << 2, +}; + +#define TEP_ERRORS \ + _PE(MEM_ALLOC_FAILED, "failed to allocate memory"), \ + _PE(PARSE_EVENT_FAILED, "failed to parse event"), \ + _PE(READ_ID_FAILED, "failed to read event id"), \ + _PE(READ_FORMAT_FAILED, "failed to read event format"), \ + _PE(READ_PRINT_FAILED, "failed to read event print fmt"), \ + _PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace"),\ + _PE(INVALID_ARG_TYPE, "invalid argument type"), \ + _PE(INVALID_EXP_TYPE, "invalid expression type"), \ + _PE(INVALID_OP_TYPE, "invalid operator type"), \ + _PE(INVALID_EVENT_NAME, "invalid event name"), \ + _PE(EVENT_NOT_FOUND, "no event found"), \ + _PE(SYNTAX_ERROR, "syntax error"), \ + _PE(ILLEGAL_RVALUE, "illegal rvalue"), \ + _PE(ILLEGAL_LVALUE, "illegal lvalue for string comparison"), \ + _PE(INVALID_REGEX, "regex did not compute"), \ + _PE(ILLEGAL_STRING_CMP, "illegal comparison for string"), \ + _PE(ILLEGAL_INTEGER_CMP,"illegal comparison for integer"), \ + _PE(REPARENT_NOT_OP, "cannot reparent other than OP"), \ + _PE(REPARENT_FAILED, "failed to reparent filter OP"), \ + _PE(BAD_FILTER_ARG, "bad arg in filter tree"), \ + _PE(UNEXPECTED_TYPE, "unexpected type (not a value)"), \ + _PE(ILLEGAL_TOKEN, "illegal token"), \ + _PE(INVALID_PAREN, "open parenthesis cannot come here"), \ + _PE(UNBALANCED_PAREN, "unbalanced number of parenthesis"), \ + _PE(UNKNOWN_TOKEN, "unknown token"), \ + _PE(FILTER_NOT_FOUND, "no filter found"), \ + _PE(NOT_A_NUMBER, "must have number field"), \ + _PE(NO_FILTER, "no filters exists"), \ + _PE(FILTER_MISS, "record does not match to filter") + +#undef _PE +#define _PE(__code, __str) TEP_ERRNO__ ## __code +enum tep_errno { + TEP_ERRNO__SUCCESS = 0, + TEP_ERRNO__FILTER_MATCH = TEP_ERRNO__SUCCESS, + + /* + * Choose an arbitrary negative big number not to clash with standard + * errno since SUS requires the errno has distinct positive values. + * See 'Issue 6' in the link below. + * + * https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html + */ + __TEP_ERRNO__START = -100000, + + TEP_ERRORS, + + __TEP_ERRNO__END, +}; +#undef _PE + +struct tep_plugin_list; + +#define INVALID_PLUGIN_LIST_OPTION ((char **)((unsigned long)-1)) + +enum tep_plugin_load_priority { + TEP_PLUGIN_FIRST, + TEP_PLUGIN_LAST, +}; + +int tep_add_plugin_path(struct tep_handle *tep, char *path, + enum tep_plugin_load_priority prio); +struct tep_plugin_list *tep_load_plugins(struct tep_handle *tep); +void tep_unload_plugins(struct tep_plugin_list *plugin_list, + struct tep_handle *tep); +void tep_load_plugins_hook(struct tep_handle *tep, const char *suffix, + void (*load_plugin)(struct tep_handle *tep, + const char *path, + const char *name, + void *data), + void *data); +char **tep_plugin_list_options(void); +void tep_plugin_free_options_list(char **list); +int tep_plugin_add_options(const char *name, + struct tep_plugin_option *options); +int tep_plugin_add_option(const char *name, const char *val); +void tep_plugin_remove_options(struct tep_plugin_option *options); +void tep_plugin_print_options(struct trace_seq *s); +void tep_print_plugins(struct trace_seq *s, + const char *prefix, const char *suffix, + const struct tep_plugin_list *list); + +/* tep_handle */ +typedef char *(tep_func_resolver_t)(void *priv, + unsigned long long *addrp, char **modp); +void tep_set_flag(struct tep_handle *tep, int flag); +void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag); +bool tep_test_flag(struct tep_handle *tep, enum tep_flag flags); + +static inline int tep_is_bigendian(void) +{ + unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 }; + unsigned int val; + + memcpy(&val, str, 4); + return val == 0x01020304; +} + +/* taken from kernel/trace/trace.h */ +enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, + TRACE_FLAG_IRQS_NOSUPPORT = 0x02, + TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, +}; + +int tep_set_function_resolver(struct tep_handle *tep, + tep_func_resolver_t *func, void *priv); +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_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); + +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, 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); + +enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf, + unsigned long size, const char *sys); +enum tep_errno tep_parse_format(struct tep_handle *tep, + struct tep_event **eventp, + const char *buf, + unsigned long size, const char *sys); + +void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event, + const char *name, struct tep_record *record, + int *len, int err); + +int tep_get_field_val(struct trace_seq *s, struct tep_event *event, + const char *name, struct tep_record *record, + unsigned long long *val, int err); +int tep_get_common_field_val(struct trace_seq *s, struct tep_event *event, + const char *name, struct tep_record *record, + unsigned long long *val, int err); +int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event, + const char *name, struct tep_record *record, + unsigned long long *val, int err); + +int tep_print_num_field(struct trace_seq *s, const char *fmt, + struct tep_event *event, const char *name, + struct tep_record *record, int err); + +int tep_print_func_field(struct trace_seq *s, const char *fmt, + struct tep_event *event, const char *name, + struct tep_record *record, int err); + +enum tep_reg_handler { + TEP_REGISTER_SUCCESS = 0, + TEP_REGISTER_SUCCESS_OVERWRITE, +}; + +int tep_register_event_handler(struct tep_handle *tep, int id, + const char *sys_name, const char *event_name, + tep_event_handler_func func, void *context); +int tep_unregister_event_handler(struct tep_handle *tep, int id, + const char *sys_name, const char *event_name, + tep_event_handler_func func, void *context); +int tep_register_print_function(struct tep_handle *tep, + tep_func_handler func, + enum tep_func_arg_type ret_type, + char *name, ...); +int tep_unregister_print_function(struct tep_handle *tep, + tep_func_handler func, char *name); + +struct tep_format_field *tep_find_common_field(struct tep_event *event, const char *name); +struct tep_format_field *tep_find_field(struct tep_event *event, const char *name); +struct tep_format_field *tep_find_any_field(struct tep_event *event, const char *name); + +const char *tep_find_function(struct tep_handle *tep, unsigned long long addr); +unsigned long long +tep_find_function_address(struct tep_handle *tep, unsigned long long addr); +unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size); +int tep_read_number_field(struct tep_format_field *field, const void *data, + unsigned long long *value); + +struct tep_event *tep_get_first_event(struct tep_handle *tep); +int tep_get_events_count(struct tep_handle *tep); +struct tep_event *tep_find_event(struct tep_handle *tep, int id); + +struct tep_event * +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); + +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); +int tep_data_flags(struct tep_handle *tep, struct tep_record *rec); +const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid); +struct tep_cmdline; +struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm, + struct tep_cmdline *next); +int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline); + +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); +int tep_strerror(struct tep_handle *tep, enum tep_errno errnum, + char *buf, size_t buflen); + +struct tep_event **tep_list_events(struct tep_handle *tep, enum tep_event_sort_type); +struct tep_event **tep_list_events_copy(struct tep_handle *tep, + enum tep_event_sort_type); +struct tep_format_field **tep_event_common_fields(struct tep_event *event); +struct tep_format_field **tep_event_fields(struct tep_event *event); + +enum tep_endian { + TEP_LITTLE_ENDIAN = 0, + TEP_BIG_ENDIAN +}; +int tep_get_cpus(struct tep_handle *tep); +void tep_set_cpus(struct tep_handle *tep, int cpus); +int tep_get_long_size(struct tep_handle *tep); +void tep_set_long_size(struct tep_handle *tep, int long_size); +int tep_get_page_size(struct tep_handle *tep); +void tep_set_page_size(struct tep_handle *tep, int _page_size); +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); +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_test_filters(struct tep_handle *tep, int test_filters); + +struct tep_handle *tep_alloc(void); +void tep_free(struct tep_handle *tep); +void tep_ref(struct tep_handle *tep); +void tep_unref(struct tep_handle *tep); +int tep_get_ref(struct tep_handle *tep); + +/* for debugging */ +void tep_print_funcs(struct tep_handle *tep); +void tep_print_printk(struct tep_handle *tep); + +/* ----------------------- filtering ----------------------- */ + +enum tep_filter_boolean_type { + TEP_FILTER_FALSE, + TEP_FILTER_TRUE, +}; + +enum tep_filter_op_type { + TEP_FILTER_OP_AND = 1, + TEP_FILTER_OP_OR, + TEP_FILTER_OP_NOT, +}; + +enum tep_filter_cmp_type { + TEP_FILTER_CMP_NONE, + TEP_FILTER_CMP_EQ, + TEP_FILTER_CMP_NE, + TEP_FILTER_CMP_GT, + TEP_FILTER_CMP_LT, + TEP_FILTER_CMP_GE, + TEP_FILTER_CMP_LE, + TEP_FILTER_CMP_MATCH, + TEP_FILTER_CMP_NOT_MATCH, + TEP_FILTER_CMP_REGEX, + TEP_FILTER_CMP_NOT_REGEX, +}; + +enum tep_filter_exp_type { + TEP_FILTER_EXP_NONE, + TEP_FILTER_EXP_ADD, + TEP_FILTER_EXP_SUB, + TEP_FILTER_EXP_MUL, + TEP_FILTER_EXP_DIV, + TEP_FILTER_EXP_MOD, + TEP_FILTER_EXP_RSHIFT, + TEP_FILTER_EXP_LSHIFT, + TEP_FILTER_EXP_AND, + TEP_FILTER_EXP_OR, + TEP_FILTER_EXP_XOR, + TEP_FILTER_EXP_NOT, +}; + +enum tep_filter_arg_type { + TEP_FILTER_ARG_NONE, + TEP_FILTER_ARG_BOOLEAN, + TEP_FILTER_ARG_VALUE, + TEP_FILTER_ARG_FIELD, + TEP_FILTER_ARG_EXP, + TEP_FILTER_ARG_OP, + TEP_FILTER_ARG_NUM, + TEP_FILTER_ARG_STR, +}; + +enum tep_filter_value_type { + TEP_FILTER_NUMBER, + TEP_FILTER_STRING, + TEP_FILTER_CHAR +}; + +struct tep_filter_arg; + +struct tep_filter_arg_boolean { + enum tep_filter_boolean_type value; +}; + +struct tep_filter_arg_field { + struct tep_format_field *field; +}; + +struct tep_filter_arg_value { + enum tep_filter_value_type type; + union { + char *str; + unsigned long long val; + }; +}; + +struct tep_filter_arg_op { + enum tep_filter_op_type type; + struct tep_filter_arg *left; + struct tep_filter_arg *right; +}; + +struct tep_filter_arg_exp { + enum tep_filter_exp_type type; + struct tep_filter_arg *left; + struct tep_filter_arg *right; +}; + +struct tep_filter_arg_num { + enum tep_filter_cmp_type type; + struct tep_filter_arg *left; + struct tep_filter_arg *right; +}; + +struct tep_filter_arg_str { + enum tep_filter_cmp_type type; + struct tep_format_field *field; + char *val; + char *buffer; + regex_t reg; +}; + +struct tep_filter_arg { + enum tep_filter_arg_type type; + union { + struct tep_filter_arg_boolean boolean; + struct tep_filter_arg_field field; + struct tep_filter_arg_value value; + struct tep_filter_arg_op op; + struct tep_filter_arg_exp exp; + struct tep_filter_arg_num num; + struct tep_filter_arg_str str; + }; +}; + +struct tep_filter_type { + int event_id; + struct tep_event *event; + struct tep_filter_arg *filter; +}; + +#define TEP_FILTER_ERROR_BUFSZ 1024 + +struct tep_event_filter { + struct tep_handle *tep; + int filters; + struct tep_filter_type *event_filters; + char error_buffer[TEP_FILTER_ERROR_BUFSZ]; +}; + +struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep); + +/* for backward compatibility */ +#define FILTER_NONE TEP_ERRNO__NO_FILTER +#define FILTER_NOEXIST TEP_ERRNO__FILTER_NOT_FOUND +#define FILTER_MISS TEP_ERRNO__FILTER_MISS +#define FILTER_MATCH TEP_ERRNO__FILTER_MATCH + +enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, + const char *filter_str); + +enum tep_errno tep_filter_match(struct tep_event_filter *filter, + struct tep_record *record); + +int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err, + char *buf, size_t buflen); + +int tep_event_filtered(struct tep_event_filter *filter, + int event_id); + +void tep_filter_reset(struct tep_event_filter *filter); + +void tep_filter_free(struct tep_event_filter *filter); + +char *tep_filter_make_string(struct tep_event_filter *filter, int event_id); + +int tep_filter_remove_event(struct tep_event_filter *filter, + int event_id); + +int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source); + +int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2); + +#endif /* _PARSE_EVENTS_H */ diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c new file mode 100644 index 000000000..e7f93d5fe --- /dev/null +++ b/tools/lib/traceevent/event-plugin.c @@ -0,0 +1,711 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ + +#include <ctype.h> +#include <stdio.h> +#include <string.h> +#include <dlfcn.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <dirent.h> +#include <errno.h> +#include "event-parse.h" +#include "event-parse-local.h" +#include "event-utils.h" +#include "trace-seq.h" + +#define LOCAL_PLUGIN_DIR ".local/lib/traceevent/plugins/" + +static struct registered_plugin_options { + struct registered_plugin_options *next; + struct tep_plugin_option *options; +} *registered_options; + +static struct trace_plugin_options { + struct trace_plugin_options *next; + char *plugin; + char *option; + char *value; +} *trace_plugin_options; + +struct tep_plugin_list { + struct tep_plugin_list *next; + char *name; + void *handle; +}; + +struct tep_plugins_dir { + struct tep_plugins_dir *next; + char *path; + enum tep_plugin_load_priority prio; +}; + +static void lower_case(char *str) +{ + if (!str) + return; + for (; *str; str++) + *str = tolower(*str); +} + +static int update_option_value(struct tep_plugin_option *op, const char *val) +{ + char *op_val; + + if (!val) { + /* toggle, only if option is boolean */ + if (op->value) + /* Warn? */ + return 0; + op->set ^= 1; + return 0; + } + + /* + * If the option has a value then it takes a string + * otherwise the option is a boolean. + */ + if (op->value) { + op->value = val; + return 0; + } + + /* Option is boolean, must be either "1", "0", "true" or "false" */ + + op_val = strdup(val); + if (!op_val) + return -1; + lower_case(op_val); + + if (strcmp(val, "1") == 0 || strcmp(val, "true") == 0) + op->set = 1; + else if (strcmp(val, "0") == 0 || strcmp(val, "false") == 0) + op->set = 0; + free(op_val); + + return 0; +} + +/** + * tep_plugin_list_options - get list of plugin options + * + * Returns an array of char strings that list the currently registered + * plugin options in the format of <plugin>:<option>. This list can be + * used by toggling the option. + * + * Returns NULL if there's no options registered. On error it returns + * INVALID_PLUGIN_LIST_OPTION + * + * Must be freed with tep_plugin_free_options_list(). + */ +char **tep_plugin_list_options(void) +{ + struct registered_plugin_options *reg; + struct tep_plugin_option *op; + char **list = NULL; + char *name; + int count = 0; + + for (reg = registered_options; reg; reg = reg->next) { + for (op = reg->options; op->name; op++) { + char *alias = op->plugin_alias ? op->plugin_alias : op->file; + char **temp = list; + int ret; + + ret = asprintf(&name, "%s:%s", alias, op->name); + if (ret < 0) + goto err; + + list = realloc(list, count + 2); + if (!list) { + list = temp; + free(name); + goto err; + } + list[count++] = name; + list[count] = NULL; + } + } + return list; + + err: + while (--count >= 0) + free(list[count]); + free(list); + + return INVALID_PLUGIN_LIST_OPTION; +} + +void tep_plugin_free_options_list(char **list) +{ + int i; + + if (!list) + return; + + if (list == INVALID_PLUGIN_LIST_OPTION) + return; + + for (i = 0; list[i]; i++) + free(list[i]); + + free(list); +} + +static int +update_option(const char *file, struct tep_plugin_option *option) +{ + struct trace_plugin_options *op; + char *plugin; + int ret = 0; + + if (option->plugin_alias) { + plugin = strdup(option->plugin_alias); + if (!plugin) + return -1; + } else { + char *p; + plugin = strdup(file); + if (!plugin) + return -1; + p = strstr(plugin, "."); + if (p) + *p = '\0'; + } + + /* first look for named options */ + for (op = trace_plugin_options; op; op = op->next) { + if (!op->plugin) + continue; + if (strcmp(op->plugin, plugin) != 0) + continue; + if (strcmp(op->option, option->name) != 0) + continue; + + ret = update_option_value(option, op->value); + if (ret) + goto out; + break; + } + + /* first look for unnamed options */ + for (op = trace_plugin_options; op; op = op->next) { + if (op->plugin) + continue; + if (strcmp(op->option, option->name) != 0) + continue; + + ret = update_option_value(option, op->value); + break; + } + + out: + free(plugin); + return ret; +} + +/** + * tep_plugin_add_options - Add a set of options by a plugin + * @name: The name of the plugin adding the options + * @options: The set of options being loaded + * + * Sets the options with the values that have been added by user. + */ +int tep_plugin_add_options(const char *name, + struct tep_plugin_option *options) +{ + struct registered_plugin_options *reg; + + reg = malloc(sizeof(*reg)); + if (!reg) + return -1; + reg->next = registered_options; + reg->options = options; + registered_options = reg; + + while (options->name) { + update_option(name, options); + options++; + } + return 0; +} + +/** + * tep_plugin_remove_options - remove plugin options that were registered + * @options: Options to removed that were registered with tep_plugin_add_options + */ +void tep_plugin_remove_options(struct tep_plugin_option *options) +{ + struct registered_plugin_options **last; + struct registered_plugin_options *reg; + + for (last = ®istered_options; *last; last = &(*last)->next) { + if ((*last)->options == options) { + reg = *last; + *last = reg->next; + free(reg); + return; + } + } +} + +static int parse_option_name(char **option, char **plugin) +{ + char *p; + + *plugin = NULL; + + if ((p = strstr(*option, ":"))) { + *plugin = *option; + *p = '\0'; + *option = strdup(p + 1); + if (!*option) + return -1; + } + return 0; +} + +static struct tep_plugin_option * +find_registered_option(const char *plugin, const char *option) +{ + struct registered_plugin_options *reg; + struct tep_plugin_option *op; + const char *op_plugin; + + for (reg = registered_options; reg; reg = reg->next) { + for (op = reg->options; op->name; op++) { + if (op->plugin_alias) + op_plugin = op->plugin_alias; + else + op_plugin = op->file; + + if (plugin && strcmp(plugin, op_plugin) != 0) + continue; + if (strcmp(option, op->name) != 0) + continue; + + return op; + } + } + + return NULL; +} + +static int process_option(const char *plugin, const char *option, const char *val) +{ + struct tep_plugin_option *op; + + op = find_registered_option(plugin, option); + if (!op) + return 0; + + return update_option_value(op, val); +} + +/** + * tep_plugin_add_option - add an option/val pair to set plugin options + * @name: The name of the option (format: <plugin>:<option> or just <option>) + * @val: (optional) the value for the option + * + * Modify a plugin option. If @val is given than the value of the option + * is set (note, some options just take a boolean, so @val must be either + * "1" or "0" or "true" or "false"). + */ +int tep_plugin_add_option(const char *name, const char *val) +{ + struct trace_plugin_options *op; + char *option_str; + char *plugin; + + option_str = strdup(name); + if (!option_str) + return -ENOMEM; + + if (parse_option_name(&option_str, &plugin) < 0) + return -ENOMEM; + + /* If the option exists, update the val */ + for (op = trace_plugin_options; op; op = op->next) { + /* Both must be NULL or not NULL */ + if ((!plugin || !op->plugin) && plugin != op->plugin) + continue; + if (plugin && strcmp(plugin, op->plugin) != 0) + continue; + if (strcmp(op->option, option_str) != 0) + continue; + + /* update option */ + free(op->value); + if (val) { + op->value = strdup(val); + if (!op->value) + goto out_free; + } else + op->value = NULL; + + /* plugin and option_str don't get freed at the end */ + free(plugin); + free(option_str); + + plugin = op->plugin; + option_str = op->option; + break; + } + + /* If not found, create */ + if (!op) { + op = malloc(sizeof(*op)); + if (!op) + goto out_free; + memset(op, 0, sizeof(*op)); + op->plugin = plugin; + op->option = option_str; + if (val) { + op->value = strdup(val); + if (!op->value) { + free(op); + goto out_free; + } + } + op->next = trace_plugin_options; + trace_plugin_options = op; + } + + return process_option(plugin, option_str, val); + +out_free: + free(plugin); + free(option_str); + return -ENOMEM; +} + +static void print_op_data(struct trace_seq *s, const char *name, + const char *op) +{ + if (op) + trace_seq_printf(s, "%8s:\t%s\n", name, op); +} + +/** + * tep_plugin_print_options - print out the registered plugin options + * @s: The trace_seq descriptor to write the plugin options into + * + * Writes a list of options into trace_seq @s. + */ +void tep_plugin_print_options(struct trace_seq *s) +{ + struct registered_plugin_options *reg; + struct tep_plugin_option *op; + + for (reg = registered_options; reg; reg = reg->next) { + if (reg != registered_options) + trace_seq_printf(s, "============\n"); + for (op = reg->options; op->name; op++) { + if (op != reg->options) + trace_seq_printf(s, "------------\n"); + print_op_data(s, "file", op->file); + print_op_data(s, "plugin", op->plugin_alias); + print_op_data(s, "option", op->name); + print_op_data(s, "desc", op->description); + print_op_data(s, "value", op->value); + trace_seq_printf(s, "%8s:\t%d\n", "set", op->set); + } + } +} + +/** + * tep_print_plugins - print out the list of plugins loaded + * @s: the trace_seq descripter to write to + * @prefix: The prefix string to add before listing the option name + * @suffix: The suffix string ot append after the option name + * @list: The list of plugins (usually returned by tep_load_plugins() + * + * Writes to the trace_seq @s the list of plugins (files) that is + * returned by tep_load_plugins(). Use @prefix and @suffix for formating: + * @prefix = " ", @suffix = "\n". + */ +void tep_print_plugins(struct trace_seq *s, + const char *prefix, const char *suffix, + const struct tep_plugin_list *list) +{ + while (list) { + trace_seq_printf(s, "%s%s%s", prefix, list->name, suffix); + list = list->next; + } +} + +static void +load_plugin(struct tep_handle *tep, const char *path, + const char *file, void *data) +{ + struct tep_plugin_list **plugin_list = data; + struct tep_plugin_option *options; + tep_plugin_load_func func; + struct tep_plugin_list *list; + const char *alias; + char *plugin; + void *handle; + int ret; + + ret = asprintf(&plugin, "%s/%s", path, file); + if (ret < 0) { + warning("could not allocate plugin memory\n"); + return; + } + + handle = dlopen(plugin, RTLD_NOW | RTLD_GLOBAL); + if (!handle) { + warning("could not load plugin '%s'\n%s\n", + plugin, dlerror()); + goto out_free; + } + + alias = dlsym(handle, TEP_PLUGIN_ALIAS_NAME); + if (!alias) + alias = file; + + options = dlsym(handle, TEP_PLUGIN_OPTIONS_NAME); + if (options) { + while (options->name) { + ret = update_option(alias, options); + if (ret < 0) + goto out_free; + options++; + } + } + + func = dlsym(handle, TEP_PLUGIN_LOADER_NAME); + if (!func) { + warning("could not find func '%s' in plugin '%s'\n%s\n", + TEP_PLUGIN_LOADER_NAME, plugin, dlerror()); + goto out_free; + } + + list = malloc(sizeof(*list)); + if (!list) { + warning("could not allocate plugin memory\n"); + goto out_free; + } + + list->next = *plugin_list; + list->handle = handle; + list->name = plugin; + *plugin_list = list; + + pr_stat("registering plugin: %s", plugin); + func(tep); + return; + + out_free: + free(plugin); +} + +static void +load_plugins_dir(struct tep_handle *tep, const char *suffix, + const char *path, + void (*load_plugin)(struct tep_handle *tep, + const char *path, + const char *name, + void *data), + void *data) +{ + struct dirent *dent; + struct stat st; + DIR *dir; + int ret; + + ret = stat(path, &st); + if (ret < 0) + return; + + if (!S_ISDIR(st.st_mode)) + return; + + dir = opendir(path); + if (!dir) + return; + + while ((dent = readdir(dir))) { + const char *name = dent->d_name; + + if (strcmp(name, ".") == 0 || + strcmp(name, "..") == 0) + continue; + + /* Only load plugins that end in suffix */ + if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0) + continue; + + load_plugin(tep, path, name, data); + } + + closedir(dir); +} + +/** + * tep_load_plugins_hook - call a user specified callback to load a plugin + * @tep: handler to traceevent context + * @suffix: filter only plugin files with given suffix + * @load_plugin: user specified callback, called for each plugin file + * @data: custom context, passed to @load_plugin + * + * Searches for traceevent plugin files and calls @load_plugin for each + * The order of plugins search is: + * - Directories, specified in @tep->plugins_dir and priority TEP_PLUGIN_FIRST + * - Directory, specified at compile time with PLUGIN_TRACEEVENT_DIR + * - Directory, specified by environment variable TRACEEVENT_PLUGIN_DIR + * - In user's home: ~/.local/lib/traceevent/plugins/ + * - Directories, specified in @tep->plugins_dir and priority TEP_PLUGIN_LAST + * + */ +void tep_load_plugins_hook(struct tep_handle *tep, const char *suffix, + void (*load_plugin)(struct tep_handle *tep, + const char *path, + const char *name, + void *data), + void *data) +{ + struct tep_plugins_dir *dir = NULL; + char *home; + char *path; + char *envdir; + int ret; + + if (tep && tep->flags & TEP_DISABLE_PLUGINS) + return; + + if (tep) + dir = tep->plugins_dir; + while (dir) { + if (dir->prio == TEP_PLUGIN_FIRST) + load_plugins_dir(tep, suffix, dir->path, + load_plugin, data); + dir = dir->next; + } + + /* + * If a system plugin directory was defined, + * check that first. + */ +#ifdef PLUGIN_DIR + if (!tep || !(tep->flags & TEP_DISABLE_SYS_PLUGINS)) + load_plugins_dir(tep, suffix, PLUGIN_DIR, + load_plugin, data); +#endif + + /* + * Next let the environment-set plugin directory + * override the system defaults. + */ + envdir = getenv("TRACEEVENT_PLUGIN_DIR"); + if (envdir) + load_plugins_dir(tep, suffix, envdir, load_plugin, data); + + /* + * Now let the home directory override the environment + * or system defaults. + */ + home = getenv("HOME"); + if (!home) + return; + + ret = asprintf(&path, "%s/%s", home, LOCAL_PLUGIN_DIR); + if (ret < 0) { + warning("could not allocate plugin memory\n"); + return; + } + + load_plugins_dir(tep, suffix, path, load_plugin, data); + + if (tep) + dir = tep->plugins_dir; + while (dir) { + if (dir->prio == TEP_PLUGIN_LAST) + load_plugins_dir(tep, suffix, dir->path, + load_plugin, data); + dir = dir->next; + } + + free(path); +} + +struct tep_plugin_list* +tep_load_plugins(struct tep_handle *tep) +{ + struct tep_plugin_list *list = NULL; + + tep_load_plugins_hook(tep, ".so", load_plugin, &list); + return list; +} + +/** + * tep_add_plugin_path - Add a new plugin directory. + * @tep: Trace event handler. + * @path: Path to a directory. All plugin files in that + * directory will be loaded. + *@prio: Load priority of the plugins in that directory. + * + * Returns -1 in case of an error, 0 otherwise. + */ +int tep_add_plugin_path(struct tep_handle *tep, char *path, + enum tep_plugin_load_priority prio) +{ + struct tep_plugins_dir *dir; + + if (!tep || !path) + return -1; + + dir = calloc(1, sizeof(*dir)); + if (!dir) + return -1; + + dir->path = strdup(path); + if (!dir->path) { + free(dir); + return -1; + } + dir->prio = prio; + dir->next = tep->plugins_dir; + tep->plugins_dir = dir; + + return 0; +} + +__hidden void free_tep_plugin_paths(struct tep_handle *tep) +{ + struct tep_plugins_dir *dir; + + if (!tep) + return; + + dir = tep->plugins_dir; + while (dir) { + tep->plugins_dir = tep->plugins_dir->next; + free(dir->path); + free(dir); + dir = tep->plugins_dir; + } +} + +void +tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *tep) +{ + tep_plugin_unload_func func; + struct tep_plugin_list *list; + + while (plugin_list) { + list = plugin_list; + plugin_list = list->next; + func = dlsym(list->handle, TEP_PLUGIN_UNLOADER_NAME); + if (func) + func(tep); + dlclose(list->handle); + free(list->name); + free(list); + } +} diff --git a/tools/lib/traceevent/event-utils.h b/tools/lib/traceevent/event-utils.h new file mode 100644 index 000000000..0560b96a3 --- /dev/null +++ b/tools/lib/traceevent/event-utils.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ +/* + * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ +#ifndef __UTIL_H +#define __UTIL_H + +#include <ctype.h> + +/* Can be overridden */ +void warning(const char *fmt, ...); +void pr_stat(const char *fmt, ...); +void vpr_stat(const char *fmt, va_list ap); + +/* Always available */ +void __warning(const char *fmt, ...); +void __pr_stat(const char *fmt, ...); + +void __vwarning(const char *fmt, ...); +void __vpr_stat(const char *fmt, ...); + +#define min(x, y) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + (void) (&_min1 == &_min2); \ + _min1 < _min2 ? _min1 : _min2; }) + +static inline char *strim(char *string) +{ + char *ret; + + if (!string) + return NULL; + while (*string) { + if (!isspace(*string)) + break; + string++; + } + ret = string; + + string = ret + strlen(ret) - 1; + while (string > ret) { + if (!isspace(*string)) + break; + string--; + } + string[1] = 0; + + return ret; +} + +static inline int has_text(const char *text) +{ + if (!text) + return 0; + + while (*text) { + if (!isspace(*text)) + return 1; + text++; + } + + return 0; +} + +#endif diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c new file mode 100644 index 000000000..f1640d651 --- /dev/null +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -0,0 +1,809 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "kbuffer.h" + +#define MISSING_EVENTS (1UL << 31) +#define MISSING_STORED (1UL << 30) + +#define COMMIT_MASK ((1 << 27) - 1) + +enum { + KBUFFER_FL_HOST_BIG_ENDIAN = (1<<0), + KBUFFER_FL_BIG_ENDIAN = (1<<1), + KBUFFER_FL_LONG_8 = (1<<2), + KBUFFER_FL_OLD_FORMAT = (1<<3), +}; + +#define ENDIAN_MASK (KBUFFER_FL_HOST_BIG_ENDIAN | KBUFFER_FL_BIG_ENDIAN) + +/** kbuffer + * @timestamp - timestamp of current event + * @lost_events - # of lost events between this subbuffer and previous + * @flags - special flags of the kbuffer + * @subbuffer - pointer to the sub-buffer page + * @data - pointer to the start of data on the sub-buffer page + * @index - index from @data to the @curr event data + * @curr - offset from @data to the start of current event + * (includes metadata) + * @next - offset from @data to the start of next event + * @size - The size of data on @data + * @start - The offset from @subbuffer where @data lives + * + * @read_4 - Function to read 4 raw bytes (may swap) + * @read_8 - Function to read 8 raw bytes (may swap) + * @read_long - Function to read a long word (4 or 8 bytes with needed swap) + */ +struct kbuffer { + unsigned long long timestamp; + long long lost_events; + unsigned long flags; + void *subbuffer; + void *data; + unsigned int index; + unsigned int curr; + unsigned int next; + unsigned int size; + unsigned int start; + + unsigned int (*read_4)(void *ptr); + unsigned long long (*read_8)(void *ptr); + unsigned long long (*read_long)(struct kbuffer *kbuf, void *ptr); + int (*next_event)(struct kbuffer *kbuf); +}; + +static void *zmalloc(size_t size) +{ + return calloc(1, size); +} + +static int host_is_bigendian(void) +{ + unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 }; + unsigned int *ptr; + + ptr = (unsigned int *)str; + return *ptr == 0x01020304; +} + +static int do_swap(struct kbuffer *kbuf) +{ + return ((kbuf->flags & KBUFFER_FL_HOST_BIG_ENDIAN) + kbuf->flags) & + ENDIAN_MASK; +} + +static unsigned long long __read_8(void *ptr) +{ + unsigned long long data = *(unsigned long long *)ptr; + + return data; +} + +static unsigned long long __read_8_sw(void *ptr) +{ + unsigned long long data = *(unsigned long long *)ptr; + unsigned long long swap; + + swap = ((data & 0xffULL) << 56) | + ((data & (0xffULL << 8)) << 40) | + ((data & (0xffULL << 16)) << 24) | + ((data & (0xffULL << 24)) << 8) | + ((data & (0xffULL << 32)) >> 8) | + ((data & (0xffULL << 40)) >> 24) | + ((data & (0xffULL << 48)) >> 40) | + ((data & (0xffULL << 56)) >> 56); + + return swap; +} + +static unsigned int __read_4(void *ptr) +{ + unsigned int data = *(unsigned int *)ptr; + + return data; +} + +static unsigned int __read_4_sw(void *ptr) +{ + unsigned int data = *(unsigned int *)ptr; + unsigned int swap; + + swap = ((data & 0xffULL) << 24) | + ((data & (0xffULL << 8)) << 8) | + ((data & (0xffULL << 16)) >> 8) | + ((data & (0xffULL << 24)) >> 24); + + return swap; +} + +static unsigned long long read_8(struct kbuffer *kbuf, void *ptr) +{ + return kbuf->read_8(ptr); +} + +static unsigned int read_4(struct kbuffer *kbuf, void *ptr) +{ + return kbuf->read_4(ptr); +} + +static unsigned long long __read_long_8(struct kbuffer *kbuf, void *ptr) +{ + return kbuf->read_8(ptr); +} + +static unsigned long long __read_long_4(struct kbuffer *kbuf, void *ptr) +{ + return kbuf->read_4(ptr); +} + +static unsigned long long read_long(struct kbuffer *kbuf, void *ptr) +{ + return kbuf->read_long(kbuf, ptr); +} + +static int calc_index(struct kbuffer *kbuf, void *ptr) +{ + return (unsigned long)ptr - (unsigned long)kbuf->data; +} + +static int __next_event(struct kbuffer *kbuf); + +/** + * kbuffer_alloc - allocat a new kbuffer + * @size; enum to denote size of word + * @endian: enum to denote endianness + * + * Allocates and returns a new kbuffer. + */ +struct kbuffer * +kbuffer_alloc(enum kbuffer_long_size size, enum kbuffer_endian endian) +{ + struct kbuffer *kbuf; + int flags = 0; + + switch (size) { + case KBUFFER_LSIZE_4: + break; + case KBUFFER_LSIZE_8: + flags |= KBUFFER_FL_LONG_8; + break; + default: + return NULL; + } + + switch (endian) { + case KBUFFER_ENDIAN_LITTLE: + break; + case KBUFFER_ENDIAN_BIG: + flags |= KBUFFER_FL_BIG_ENDIAN; + break; + default: + return NULL; + } + + kbuf = zmalloc(sizeof(*kbuf)); + if (!kbuf) + return NULL; + + kbuf->flags = flags; + + if (host_is_bigendian()) + kbuf->flags |= KBUFFER_FL_HOST_BIG_ENDIAN; + + if (do_swap(kbuf)) { + kbuf->read_8 = __read_8_sw; + kbuf->read_4 = __read_4_sw; + } else { + kbuf->read_8 = __read_8; + kbuf->read_4 = __read_4; + } + + if (kbuf->flags & KBUFFER_FL_LONG_8) + kbuf->read_long = __read_long_8; + else + kbuf->read_long = __read_long_4; + + /* May be changed by kbuffer_set_old_format() */ + kbuf->next_event = __next_event; + + return kbuf; +} + +/** kbuffer_free - free an allocated kbuffer + * @kbuf: The kbuffer to free + * + * Can take NULL as a parameter. + */ +void kbuffer_free(struct kbuffer *kbuf) +{ + free(kbuf); +} + +static unsigned int type4host(struct kbuffer *kbuf, + unsigned int type_len_ts) +{ + if (kbuf->flags & KBUFFER_FL_BIG_ENDIAN) + return (type_len_ts >> 29) & 3; + else + return type_len_ts & 3; +} + +static unsigned int len4host(struct kbuffer *kbuf, + unsigned int type_len_ts) +{ + if (kbuf->flags & KBUFFER_FL_BIG_ENDIAN) + return (type_len_ts >> 27) & 7; + else + return (type_len_ts >> 2) & 7; +} + +static unsigned int type_len4host(struct kbuffer *kbuf, + unsigned int type_len_ts) +{ + if (kbuf->flags & KBUFFER_FL_BIG_ENDIAN) + return (type_len_ts >> 27) & ((1 << 5) - 1); + else + return type_len_ts & ((1 << 5) - 1); +} + +static unsigned int ts4host(struct kbuffer *kbuf, + unsigned int type_len_ts) +{ + if (kbuf->flags & KBUFFER_FL_BIG_ENDIAN) + return type_len_ts & ((1 << 27) - 1); + else + return type_len_ts >> 5; +} + +/* + * Linux 2.6.30 and earlier (not much ealier) had a different + * ring buffer format. It should be obsolete, but we handle it anyway. + */ +enum old_ring_buffer_type { + OLD_RINGBUF_TYPE_PADDING, + OLD_RINGBUF_TYPE_TIME_EXTEND, + OLD_RINGBUF_TYPE_TIME_STAMP, + OLD_RINGBUF_TYPE_DATA, +}; + +static unsigned int old_update_pointers(struct kbuffer *kbuf) +{ + unsigned long long extend; + unsigned int type_len_ts; + unsigned int type; + unsigned int len; + unsigned int delta; + unsigned int length; + void *ptr = kbuf->data + kbuf->curr; + + type_len_ts = read_4(kbuf, ptr); + ptr += 4; + + type = type4host(kbuf, type_len_ts); + len = len4host(kbuf, type_len_ts); + delta = ts4host(kbuf, type_len_ts); + + switch (type) { + case OLD_RINGBUF_TYPE_PADDING: + kbuf->next = kbuf->size; + return 0; + + case OLD_RINGBUF_TYPE_TIME_EXTEND: + extend = read_4(kbuf, ptr); + extend <<= TS_SHIFT; + extend += delta; + delta = extend; + ptr += 4; + length = 0; + break; + + case OLD_RINGBUF_TYPE_TIME_STAMP: + /* should never happen! */ + kbuf->curr = kbuf->size; + kbuf->next = kbuf->size; + kbuf->index = kbuf->size; + return -1; + default: + if (len) + length = len * 4; + else { + length = read_4(kbuf, ptr); + length -= 4; + ptr += 4; + } + break; + } + + kbuf->timestamp += delta; + kbuf->index = calc_index(kbuf, ptr); + kbuf->next = kbuf->index + length; + + return type; +} + +static int __old_next_event(struct kbuffer *kbuf) +{ + int type; + + do { + kbuf->curr = kbuf->next; + if (kbuf->next >= kbuf->size) + return -1; + type = old_update_pointers(kbuf); + } while (type == OLD_RINGBUF_TYPE_TIME_EXTEND || type == OLD_RINGBUF_TYPE_PADDING); + + return 0; +} + +static unsigned int +translate_data(struct kbuffer *kbuf, void *data, void **rptr, + unsigned long long *delta, int *length) +{ + unsigned long long extend; + unsigned int type_len_ts; + unsigned int type_len; + + type_len_ts = read_4(kbuf, data); + data += 4; + + type_len = type_len4host(kbuf, type_len_ts); + *delta = ts4host(kbuf, type_len_ts); + + switch (type_len) { + case KBUFFER_TYPE_PADDING: + *length = read_4(kbuf, data); + break; + + case KBUFFER_TYPE_TIME_EXTEND: + case KBUFFER_TYPE_TIME_STAMP: + extend = read_4(kbuf, data); + data += 4; + extend <<= TS_SHIFT; + extend += *delta; + *delta = extend; + *length = 0; + break; + + case 0: + *length = read_4(kbuf, data) - 4; + *length = (*length + 3) & ~3; + data += 4; + break; + default: + *length = type_len * 4; + break; + } + + *rptr = data; + + return type_len; +} + +static unsigned int update_pointers(struct kbuffer *kbuf) +{ + unsigned long long delta; + unsigned int type_len; + int length; + void *ptr = kbuf->data + kbuf->curr; + + type_len = translate_data(kbuf, ptr, &ptr, &delta, &length); + + if (type_len == KBUFFER_TYPE_TIME_STAMP) + kbuf->timestamp = delta; + else + kbuf->timestamp += delta; + + kbuf->index = calc_index(kbuf, ptr); + kbuf->next = kbuf->index + length; + + return type_len; +} + +/** + * kbuffer_translate_data - read raw data to get a record + * @swap: Set to 1 if bytes in words need to be swapped when read + * @data: The raw data to read + * @size: Address to store the size of the event data. + * + * Returns a pointer to the event data. To determine the entire + * record size (record metadata + data) just add the difference between + * @data and the returned value to @size. + */ +void *kbuffer_translate_data(int swap, void *data, unsigned int *size) +{ + unsigned long long delta; + struct kbuffer kbuf; + int type_len; + int length; + void *ptr; + + if (swap) { + kbuf.read_8 = __read_8_sw; + kbuf.read_4 = __read_4_sw; + kbuf.flags = host_is_bigendian() ? 0 : KBUFFER_FL_BIG_ENDIAN; + } else { + kbuf.read_8 = __read_8; + kbuf.read_4 = __read_4; + kbuf.flags = host_is_bigendian() ? KBUFFER_FL_BIG_ENDIAN: 0; + } + + type_len = translate_data(&kbuf, data, &ptr, &delta, &length); + switch (type_len) { + case KBUFFER_TYPE_PADDING: + case KBUFFER_TYPE_TIME_EXTEND: + case KBUFFER_TYPE_TIME_STAMP: + return NULL; + } + + *size = length; + + return ptr; +} + +static int __next_event(struct kbuffer *kbuf) +{ + int type; + + do { + kbuf->curr = kbuf->next; + if (kbuf->next >= kbuf->size) + return -1; + type = update_pointers(kbuf); + } while (type == KBUFFER_TYPE_TIME_EXTEND || + type == KBUFFER_TYPE_TIME_STAMP || + type == KBUFFER_TYPE_PADDING); + + return 0; +} + +static int next_event(struct kbuffer *kbuf) +{ + return kbuf->next_event(kbuf); +} + +/** + * kbuffer_next_event - increment the current pointer + * @kbuf: The kbuffer to read + * @ts: Address to store the next record's timestamp (may be NULL to ignore) + * + * Increments the pointers into the subbuffer of the kbuffer to point to the + * next event so that the next kbuffer_read_event() will return a + * new event. + * + * Returns the data of the next event if a new event exists on the subbuffer, + * NULL otherwise. + */ +void *kbuffer_next_event(struct kbuffer *kbuf, unsigned long long *ts) +{ + int ret; + + if (!kbuf || !kbuf->subbuffer) + return NULL; + + ret = next_event(kbuf); + if (ret < 0) + return NULL; + + if (ts) + *ts = kbuf->timestamp; + + return kbuf->data + kbuf->index; +} + +/** + * kbuffer_load_subbuffer - load a new subbuffer into the kbuffer + * @kbuf: The kbuffer to load + * @subbuffer: The subbuffer to load into @kbuf. + * + * Load a new subbuffer (page) into @kbuf. This will reset all + * the pointers and update the @kbuf timestamp. The next read will + * return the first event on @subbuffer. + * + * Returns 0 on succes, -1 otherwise. + */ +int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer) +{ + unsigned long long flags; + void *ptr = subbuffer; + + if (!kbuf || !subbuffer) + return -1; + + kbuf->subbuffer = subbuffer; + + kbuf->timestamp = read_8(kbuf, ptr); + ptr += 8; + + kbuf->curr = 0; + + if (kbuf->flags & KBUFFER_FL_LONG_8) + kbuf->start = 16; + else + kbuf->start = 12; + + kbuf->data = subbuffer + kbuf->start; + + flags = read_long(kbuf, ptr); + kbuf->size = (unsigned int)flags & COMMIT_MASK; + + if (flags & MISSING_EVENTS) { + if (flags & MISSING_STORED) { + ptr = kbuf->data + kbuf->size; + kbuf->lost_events = read_long(kbuf, ptr); + } else + kbuf->lost_events = -1; + } else + kbuf->lost_events = 0; + + kbuf->index = 0; + kbuf->next = 0; + + next_event(kbuf); + + return 0; +} + +/** + * kbuffer_subbuf_timestamp - read the timestamp from a sub buffer + * @kbuf: The kbuffer to load + * @subbuf: The subbuffer to read from. + * + * Return the timestamp from a subbuffer. + */ +unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf) +{ + return kbuf->read_8(subbuf); +} + +/** + * kbuffer_ptr_delta - read the delta field from a record + * @kbuf: The kbuffer to load + * @ptr: The record in the buffe. + * + * Return the timestamp delta from a record + */ +unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr) +{ + unsigned int type_len_ts; + + type_len_ts = read_4(kbuf, ptr); + return ts4host(kbuf, type_len_ts); +} + + +/** + * kbuffer_read_event - read the next event in the kbuffer subbuffer + * @kbuf: The kbuffer to read from + * @ts: The address to store the timestamp of the event (may be NULL to ignore) + * + * Returns a pointer to the data part of the current event. + * NULL if no event is left on the subbuffer. + */ +void *kbuffer_read_event(struct kbuffer *kbuf, unsigned long long *ts) +{ + if (!kbuf || !kbuf->subbuffer) + return NULL; + + if (kbuf->curr >= kbuf->size) + return NULL; + + if (ts) + *ts = kbuf->timestamp; + return kbuf->data + kbuf->index; +} + +/** + * kbuffer_timestamp - Return the timestamp of the current event + * @kbuf: The kbuffer to read from + * + * Returns the timestamp of the current (next) event. + */ +unsigned long long kbuffer_timestamp(struct kbuffer *kbuf) +{ + return kbuf->timestamp; +} + +/** + * kbuffer_read_at_offset - read the event that is at offset + * @kbuf: The kbuffer to read from + * @offset: The offset into the subbuffer + * @ts: The address to store the timestamp of the event (may be NULL to ignore) + * + * The @offset must be an index from the @kbuf subbuffer beginning. + * If @offset is bigger than the stored subbuffer, NULL will be returned. + * + * Returns the data of the record that is at @offset. Note, @offset does + * not need to be the start of the record, the offset just needs to be + * in the record (or beginning of it). + * + * Note, the kbuf timestamp and pointers are updated to the + * returned record. That is, kbuffer_read_event() will return the same + * data and timestamp, and kbuffer_next_event() will increment from + * this record. + */ +void *kbuffer_read_at_offset(struct kbuffer *kbuf, int offset, + unsigned long long *ts) +{ + void *data; + + if (offset < kbuf->start) + offset = 0; + else + offset -= kbuf->start; + + /* Reset the buffer */ + kbuffer_load_subbuffer(kbuf, kbuf->subbuffer); + data = kbuffer_read_event(kbuf, ts); + + while (kbuf->curr < offset) { + data = kbuffer_next_event(kbuf, ts); + if (!data) + break; + } + + return data; +} + +/** + * kbuffer_subbuffer_size - the size of the loaded subbuffer + * @kbuf: The kbuffer to read from + * + * Returns the size of the subbuffer. Note, this size is + * where the last event resides. The stored subbuffer may actually be + * bigger due to padding and such. + */ +int kbuffer_subbuffer_size(struct kbuffer *kbuf) +{ + return kbuf->size; +} + +/** + * kbuffer_curr_index - Return the index of the record + * @kbuf: The kbuffer to read from + * + * Returns the index from the start of the data part of + * the subbuffer to the current location. Note this is not + * from the start of the subbuffer. An index of zero will + * point to the first record. Use kbuffer_curr_offset() for + * the actually offset (that can be used by kbuffer_read_at_offset()) + */ +int kbuffer_curr_index(struct kbuffer *kbuf) +{ + return kbuf->curr; +} + +/** + * kbuffer_curr_offset - Return the offset of the record + * @kbuf: The kbuffer to read from + * + * Returns the offset from the start of the subbuffer to the + * current location. + */ +int kbuffer_curr_offset(struct kbuffer *kbuf) +{ + return kbuf->curr + kbuf->start; +} + +/** + * kbuffer_event_size - return the size of the event data + * @kbuf: The kbuffer to read + * + * Returns the size of the event data (the payload not counting + * the meta data of the record) of the current event. + */ +int kbuffer_event_size(struct kbuffer *kbuf) +{ + return kbuf->next - kbuf->index; +} + +/** + * kbuffer_curr_size - return the size of the entire record + * @kbuf: The kbuffer to read + * + * Returns the size of the entire record (meta data and payload) + * of the current event. + */ +int kbuffer_curr_size(struct kbuffer *kbuf) +{ + return kbuf->next - kbuf->curr; +} + +/** + * kbuffer_missed_events - return the # of missed events from last event. + * @kbuf: The kbuffer to read from + * + * Returns the # of missed events (if recorded) before the current + * event. Note, only events on the beginning of a subbuffer can + * have missed events, all other events within the buffer will be + * zero. + */ +int kbuffer_missed_events(struct kbuffer *kbuf) +{ + /* Only the first event can have missed events */ + if (kbuf->curr) + return 0; + + return kbuf->lost_events; +} + +/** + * kbuffer_set_old_forma - set the kbuffer to use the old format parsing + * @kbuf: The kbuffer to set + * + * This is obsolete (or should be). The first kernels to use the + * new ring buffer had a slightly different ring buffer format + * (2.6.30 and earlier). It is still somewhat supported by kbuffer, + * but should not be counted on in the future. + */ +void kbuffer_set_old_format(struct kbuffer *kbuf) +{ + kbuf->flags |= KBUFFER_FL_OLD_FORMAT; + + kbuf->next_event = __old_next_event; +} + +/** + * kbuffer_start_of_data - return offset of where data starts on subbuffer + * @kbuf: The kbuffer + * + * Returns the location on the subbuffer where the data starts. + */ +int kbuffer_start_of_data(struct kbuffer *kbuf) +{ + return kbuf->start; +} + +/** + * kbuffer_raw_get - get raw buffer info + * @kbuf: The kbuffer + * @subbuf: Start of mapped subbuffer + * @info: Info descriptor to fill in + * + * For debugging. This can return internals of the ring buffer. + * Expects to have info->next set to what it will read. + * The type, length and timestamp delta will be filled in, and + * @info->next will be updated to the next element. + * The @subbuf is used to know if the info is passed the end of + * data and NULL will be returned if it is. + */ +struct kbuffer_raw_info * +kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, struct kbuffer_raw_info *info) +{ + unsigned long long flags; + unsigned long long delta; + unsigned int type_len; + unsigned int size; + int start; + int length; + void *ptr = info->next; + + if (!kbuf || !subbuf) + return NULL; + + if (kbuf->flags & KBUFFER_FL_LONG_8) + start = 16; + else + start = 12; + + flags = read_long(kbuf, subbuf + 8); + size = (unsigned int)flags & COMMIT_MASK; + + if (ptr < subbuf || ptr >= subbuf + start + size) + return NULL; + + type_len = translate_data(kbuf, ptr, &ptr, &delta, &length); + + info->next = ptr + length; + + info->type = type_len; + info->delta = delta; + info->length = length; + + return info; +} diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h new file mode 100644 index 000000000..a2b522093 --- /dev/null +++ b/tools/lib/traceevent/kbuffer.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ +/* + * Copyright (C) 2012 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ +#ifndef _KBUFFER_H +#define _KBUFFER_H + +#ifndef TS_SHIFT +#define TS_SHIFT 27 +#endif + +enum kbuffer_endian { + KBUFFER_ENDIAN_BIG, + KBUFFER_ENDIAN_LITTLE, +}; + +enum kbuffer_long_size { + KBUFFER_LSIZE_4, + KBUFFER_LSIZE_8, +}; + +enum { + KBUFFER_TYPE_PADDING = 29, + KBUFFER_TYPE_TIME_EXTEND = 30, + KBUFFER_TYPE_TIME_STAMP = 31, +}; + +struct kbuffer; + +struct kbuffer *kbuffer_alloc(enum kbuffer_long_size size, enum kbuffer_endian endian); +void kbuffer_free(struct kbuffer *kbuf); +int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer); +void *kbuffer_read_event(struct kbuffer *kbuf, unsigned long long *ts); +void *kbuffer_next_event(struct kbuffer *kbuf, unsigned long long *ts); +unsigned long long kbuffer_timestamp(struct kbuffer *kbuf); +unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf); +unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr); + +void *kbuffer_translate_data(int swap, void *data, unsigned int *size); + +void *kbuffer_read_at_offset(struct kbuffer *kbuf, int offset, unsigned long long *ts); + +int kbuffer_curr_index(struct kbuffer *kbuf); + +int kbuffer_curr_offset(struct kbuffer *kbuf); +int kbuffer_curr_size(struct kbuffer *kbuf); +int kbuffer_event_size(struct kbuffer *kbuf); +int kbuffer_missed_events(struct kbuffer *kbuf); +int kbuffer_subbuffer_size(struct kbuffer *kbuf); + +void kbuffer_set_old_format(struct kbuffer *kbuf); +int kbuffer_start_of_data(struct kbuffer *kbuf); + +/* Debugging */ + +struct kbuffer_raw_info { + int type; + int length; + unsigned long long delta; + void *next; +}; + +/* Read raw data */ +struct kbuffer_raw_info *kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, + struct kbuffer_raw_info *info); + +#endif /* _K_BUFFER_H */ diff --git a/tools/lib/traceevent/libtraceevent.pc.template b/tools/lib/traceevent/libtraceevent.pc.template new file mode 100644 index 000000000..86384fcd5 --- /dev/null +++ b/tools/lib/traceevent/libtraceevent.pc.template @@ -0,0 +1,10 @@ +prefix=INSTALL_PREFIX +libdir=LIB_DIR +includedir=HEADER_DIR + +Name: libtraceevent +URL: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git +Description: Linux kernel trace event library +Version: LIB_VERSION +Cflags: -I${includedir} +Libs: -L${libdir} -ltraceevent diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c new file mode 100644 index 000000000..5df177070 --- /dev/null +++ b/tools/lib/traceevent/parse-filter.c @@ -0,0 +1,2281 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdarg.h> +#include <errno.h> +#include <sys/types.h> + +#include "event-parse.h" +#include "event-parse-local.h" +#include "event-utils.h" + +#define COMM "COMM" +#define CPU "CPU" + +static struct tep_format_field comm = { + .name = "COMM", +}; + +static struct tep_format_field cpu = { + .name = "CPU", +}; + +struct event_list { + struct event_list *next; + struct tep_event *event; +}; + +static void show_error(char *error_buf, const char *fmt, ...) +{ + unsigned long long index; + const char *input; + va_list ap; + int len; + int i; + + input = get_input_buf(); + index = get_input_buf_ptr(); + len = input ? strlen(input) : 0; + + if (len) { + strcpy(error_buf, input); + error_buf[len] = '\n'; + for (i = 1; i < len && i < index; i++) + error_buf[len+i] = ' '; + error_buf[len + i] = '^'; + error_buf[len + i + 1] = '\n'; + len += i+2; + } + + va_start(ap, fmt); + vsnprintf(error_buf + len, TEP_FILTER_ERROR_BUFSZ - len, fmt, ap); + va_end(ap); +} + +static enum tep_event_type filter_read_token(char **tok) +{ + enum tep_event_type type; + char *token = NULL; + + do { + free_token(token); + type = read_token(&token); + } while (type == TEP_EVENT_NEWLINE || type == TEP_EVENT_SPACE); + + /* If token is = or ! check to see if the next char is ~ */ + if (token && + (strcmp(token, "=") == 0 || strcmp(token, "!") == 0) && + peek_char() == '~') { + /* append it */ + *tok = malloc(3); + if (*tok == NULL) { + free_token(token); + return TEP_EVENT_ERROR; + } + sprintf(*tok, "%c%c", *token, '~'); + free_token(token); + /* Now remove the '~' from the buffer */ + read_token(&token); + free_token(token); + } else + *tok = token; + + return type; +} + +static int filter_cmp(const void *a, const void *b) +{ + const struct tep_filter_type *ea = a; + const struct tep_filter_type *eb = b; + + if (ea->event_id < eb->event_id) + return -1; + + if (ea->event_id > eb->event_id) + return 1; + + return 0; +} + +static struct tep_filter_type * +find_filter_type(struct tep_event_filter *filter, int id) +{ + struct tep_filter_type *filter_type; + struct tep_filter_type key; + + key.event_id = id; + + filter_type = bsearch(&key, filter->event_filters, + filter->filters, + sizeof(*filter->event_filters), + filter_cmp); + + return filter_type; +} + +static struct tep_filter_type * +add_filter_type(struct tep_event_filter *filter, int id) +{ + struct tep_filter_type *filter_type; + int i; + + filter_type = find_filter_type(filter, id); + if (filter_type) + return filter_type; + + filter_type = realloc(filter->event_filters, + sizeof(*filter->event_filters) * + (filter->filters + 1)); + if (!filter_type) + return NULL; + + filter->event_filters = filter_type; + + for (i = 0; i < filter->filters; i++) { + if (filter->event_filters[i].event_id > id) + break; + } + + if (i < filter->filters) + memmove(&filter->event_filters[i+1], + &filter->event_filters[i], + sizeof(*filter->event_filters) * + (filter->filters - i)); + + filter_type = &filter->event_filters[i]; + filter_type->event_id = id; + filter_type->event = tep_find_event(filter->tep, id); + filter_type->filter = NULL; + + filter->filters++; + + return filter_type; +} + +/** + * tep_filter_alloc - create a new event filter + * @tep: The tep that this filter is associated with + */ +struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep) +{ + struct tep_event_filter *filter; + + filter = malloc(sizeof(*filter)); + if (filter == NULL) + return NULL; + + memset(filter, 0, sizeof(*filter)); + filter->tep = tep; + tep_ref(tep); + + return filter; +} + +static struct tep_filter_arg *allocate_arg(void) +{ + return calloc(1, sizeof(struct tep_filter_arg)); +} + +static void free_arg(struct tep_filter_arg *arg) +{ + if (!arg) + return; + + switch (arg->type) { + case TEP_FILTER_ARG_NONE: + case TEP_FILTER_ARG_BOOLEAN: + break; + + case TEP_FILTER_ARG_NUM: + free_arg(arg->num.left); + free_arg(arg->num.right); + break; + + case TEP_FILTER_ARG_EXP: + free_arg(arg->exp.left); + free_arg(arg->exp.right); + break; + + case TEP_FILTER_ARG_STR: + free(arg->str.val); + regfree(&arg->str.reg); + free(arg->str.buffer); + break; + + case TEP_FILTER_ARG_VALUE: + if (arg->value.type == TEP_FILTER_STRING || + arg->value.type == TEP_FILTER_CHAR) + free(arg->value.str); + break; + + case TEP_FILTER_ARG_OP: + free_arg(arg->op.left); + free_arg(arg->op.right); + default: + break; + } + + free(arg); +} + +static int add_event(struct event_list **events, + struct tep_event *event) +{ + struct event_list *list; + + list = malloc(sizeof(*list)); + if (list == NULL) + return -1; + + list->next = *events; + *events = list; + list->event = event; + return 0; +} + +static int event_match(struct tep_event *event, + regex_t *sreg, regex_t *ereg) +{ + if (sreg) { + return !regexec(sreg, event->system, 0, NULL, 0) && + !regexec(ereg, event->name, 0, NULL, 0); + } + + return !regexec(ereg, event->system, 0, NULL, 0) || + !regexec(ereg, event->name, 0, NULL, 0); +} + +static enum tep_errno +find_event(struct tep_handle *tep, struct event_list **events, + char *sys_name, char *event_name) +{ + struct tep_event *event; + regex_t ereg; + regex_t sreg; + int match = 0; + int fail = 0; + char *reg; + int ret; + int i; + + if (!event_name) { + /* if no name is given, then swap sys and name */ + event_name = sys_name; + sys_name = NULL; + } + + ret = asprintf(®, "^%s$", event_name); + if (ret < 0) + return TEP_ERRNO__MEM_ALLOC_FAILED; + + ret = regcomp(&ereg, reg, REG_ICASE|REG_NOSUB); + free(reg); + + if (ret) + return TEP_ERRNO__INVALID_EVENT_NAME; + + if (sys_name) { + ret = asprintf(®, "^%s$", sys_name); + if (ret < 0) { + regfree(&ereg); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + + ret = regcomp(&sreg, reg, REG_ICASE|REG_NOSUB); + free(reg); + if (ret) { + regfree(&ereg); + return TEP_ERRNO__INVALID_EVENT_NAME; + } + } + + for (i = 0; i < tep->nr_events; i++) { + event = tep->events[i]; + if (event_match(event, sys_name ? &sreg : NULL, &ereg)) { + match = 1; + if (add_event(events, event) < 0) { + fail = 1; + break; + } + } + } + + regfree(&ereg); + if (sys_name) + regfree(&sreg); + + if (!match) + return TEP_ERRNO__EVENT_NOT_FOUND; + if (fail) + return TEP_ERRNO__MEM_ALLOC_FAILED; + + return 0; +} + +static void free_events(struct event_list *events) +{ + struct event_list *event; + + while (events) { + event = events; + events = events->next; + free(event); + } +} + +static enum tep_errno +create_arg_item(struct tep_event *event, const char *token, + enum tep_event_type type, struct tep_filter_arg **parg, char *error_str) +{ + struct tep_format_field *field; + struct tep_filter_arg *arg; + + arg = allocate_arg(); + if (arg == NULL) { + show_error(error_str, "failed to allocate filter arg"); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + + switch (type) { + + case TEP_EVENT_SQUOTE: + case TEP_EVENT_DQUOTE: + arg->type = TEP_FILTER_ARG_VALUE; + arg->value.type = + type == TEP_EVENT_DQUOTE ? TEP_FILTER_STRING : TEP_FILTER_CHAR; + arg->value.str = strdup(token); + if (!arg->value.str) { + free_arg(arg); + show_error(error_str, "failed to allocate string filter arg"); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + break; + case TEP_EVENT_ITEM: + /* if it is a number, then convert it */ + if (isdigit(token[0])) { + arg->type = TEP_FILTER_ARG_VALUE; + arg->value.type = TEP_FILTER_NUMBER; + arg->value.val = strtoull(token, NULL, 0); + break; + } + /* Consider this a field */ + field = tep_find_any_field(event, token); + if (!field) { + /* If token is 'COMM' or 'CPU' then it is special */ + if (strcmp(token, COMM) == 0) { + field = &comm; + } else if (strcmp(token, CPU) == 0) { + field = &cpu; + } else { + /* not a field, Make it false */ + arg->type = TEP_FILTER_ARG_BOOLEAN; + arg->boolean.value = TEP_FILTER_FALSE; + break; + } + } + arg->type = TEP_FILTER_ARG_FIELD; + arg->field.field = field; + break; + default: + free_arg(arg); + show_error(error_str, "expected a value but found %s", token); + return TEP_ERRNO__UNEXPECTED_TYPE; + } + *parg = arg; + return 0; +} + +static struct tep_filter_arg * +create_arg_op(enum tep_filter_op_type btype) +{ + struct tep_filter_arg *arg; + + arg = allocate_arg(); + if (!arg) + return NULL; + + arg->type = TEP_FILTER_ARG_OP; + arg->op.type = btype; + + return arg; +} + +static struct tep_filter_arg * +create_arg_exp(enum tep_filter_exp_type etype) +{ + struct tep_filter_arg *arg; + + arg = allocate_arg(); + if (!arg) + return NULL; + + arg->type = TEP_FILTER_ARG_EXP; + arg->exp.type = etype; + + return arg; +} + +static struct tep_filter_arg * +create_arg_cmp(enum tep_filter_cmp_type ctype) +{ + struct tep_filter_arg *arg; + + arg = allocate_arg(); + if (!arg) + return NULL; + + /* Use NUM and change if necessary */ + arg->type = TEP_FILTER_ARG_NUM; + arg->num.type = ctype; + + return arg; +} + +static enum tep_errno +add_right(struct tep_filter_arg *op, struct tep_filter_arg *arg, char *error_str) +{ + struct tep_filter_arg *left; + char *str; + int op_type; + int ret; + + switch (op->type) { + case TEP_FILTER_ARG_EXP: + if (op->exp.right) + goto out_fail; + op->exp.right = arg; + break; + + case TEP_FILTER_ARG_OP: + if (op->op.right) + goto out_fail; + op->op.right = arg; + break; + + case TEP_FILTER_ARG_NUM: + if (op->op.right) + goto out_fail; + /* + * The arg must be num, str, or field + */ + switch (arg->type) { + case TEP_FILTER_ARG_VALUE: + case TEP_FILTER_ARG_FIELD: + break; + default: + show_error(error_str, "Illegal rvalue"); + return TEP_ERRNO__ILLEGAL_RVALUE; + } + + /* + * Depending on the type, we may need to + * convert this to a string or regex. + */ + switch (arg->value.type) { + case TEP_FILTER_CHAR: + /* + * A char should be converted to number if + * the string is 1 byte, and the compare + * is not a REGEX. + */ + if (strlen(arg->value.str) == 1 && + op->num.type != TEP_FILTER_CMP_REGEX && + op->num.type != TEP_FILTER_CMP_NOT_REGEX) { + arg->value.type = TEP_FILTER_NUMBER; + goto do_int; + } + /* fall through */ + case TEP_FILTER_STRING: + + /* convert op to a string arg */ + op_type = op->num.type; + left = op->num.left; + str = arg->value.str; + + /* reset the op for the new field */ + memset(op, 0, sizeof(*op)); + + /* + * If left arg was a field not found then + * NULL the entire op. + */ + if (left->type == TEP_FILTER_ARG_BOOLEAN) { + free_arg(left); + free_arg(arg); + op->type = TEP_FILTER_ARG_BOOLEAN; + op->boolean.value = TEP_FILTER_FALSE; + break; + } + + /* Left arg must be a field */ + if (left->type != TEP_FILTER_ARG_FIELD) { + show_error(error_str, + "Illegal lvalue for string comparison"); + return TEP_ERRNO__ILLEGAL_LVALUE; + } + + /* Make sure this is a valid string compare */ + switch (op_type) { + case TEP_FILTER_CMP_EQ: + op_type = TEP_FILTER_CMP_MATCH; + break; + case TEP_FILTER_CMP_NE: + op_type = TEP_FILTER_CMP_NOT_MATCH; + break; + + case TEP_FILTER_CMP_REGEX: + case TEP_FILTER_CMP_NOT_REGEX: + ret = regcomp(&op->str.reg, str, REG_ICASE|REG_NOSUB); + if (ret) { + show_error(error_str, + "RegEx '%s' did not compute", + str); + return TEP_ERRNO__INVALID_REGEX; + } + break; + default: + show_error(error_str, + "Illegal comparison for string"); + return TEP_ERRNO__ILLEGAL_STRING_CMP; + } + + op->type = TEP_FILTER_ARG_STR; + op->str.type = op_type; + op->str.field = left->field.field; + op->str.val = strdup(str); + if (!op->str.val) { + show_error(error_str, "Failed to allocate string filter"); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + /* + * Need a buffer to copy data for tests + */ + op->str.buffer = malloc(op->str.field->size + 1); + if (!op->str.buffer) { + show_error(error_str, "Failed to allocate string filter"); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + /* Null terminate this buffer */ + op->str.buffer[op->str.field->size] = 0; + + /* We no longer have left or right args */ + free_arg(arg); + free_arg(left); + + break; + + case TEP_FILTER_NUMBER: + + do_int: + switch (op->num.type) { + case TEP_FILTER_CMP_REGEX: + case TEP_FILTER_CMP_NOT_REGEX: + show_error(error_str, + "Op not allowed with integers"); + return TEP_ERRNO__ILLEGAL_INTEGER_CMP; + + default: + break; + } + + /* numeric compare */ + op->num.right = arg; + break; + default: + goto out_fail; + } + break; + default: + goto out_fail; + } + + return 0; + + out_fail: + show_error(error_str, "Syntax error"); + return TEP_ERRNO__SYNTAX_ERROR; +} + +static struct tep_filter_arg * +rotate_op_right(struct tep_filter_arg *a, struct tep_filter_arg *b) +{ + struct tep_filter_arg *arg; + + arg = a->op.right; + a->op.right = b; + return arg; +} + +static enum tep_errno add_left(struct tep_filter_arg *op, struct tep_filter_arg *arg) +{ + switch (op->type) { + case TEP_FILTER_ARG_EXP: + if (arg->type == TEP_FILTER_ARG_OP) + arg = rotate_op_right(arg, op); + op->exp.left = arg; + break; + + case TEP_FILTER_ARG_OP: + op->op.left = arg; + break; + case TEP_FILTER_ARG_NUM: + if (arg->type == TEP_FILTER_ARG_OP) + arg = rotate_op_right(arg, op); + + /* left arg of compares must be a field */ + if (arg->type != TEP_FILTER_ARG_FIELD && + arg->type != TEP_FILTER_ARG_BOOLEAN) + return TEP_ERRNO__INVALID_ARG_TYPE; + op->num.left = arg; + break; + default: + return TEP_ERRNO__INVALID_ARG_TYPE; + } + return 0; +} + +enum op_type { + OP_NONE, + OP_BOOL, + OP_NOT, + OP_EXP, + OP_CMP, +}; + +static enum op_type process_op(const char *token, + enum tep_filter_op_type *btype, + enum tep_filter_cmp_type *ctype, + enum tep_filter_exp_type *etype) +{ + *btype = TEP_FILTER_OP_NOT; + *etype = TEP_FILTER_EXP_NONE; + *ctype = TEP_FILTER_CMP_NONE; + + if (strcmp(token, "&&") == 0) + *btype = TEP_FILTER_OP_AND; + else if (strcmp(token, "||") == 0) + *btype = TEP_FILTER_OP_OR; + else if (strcmp(token, "!") == 0) + return OP_NOT; + + if (*btype != TEP_FILTER_OP_NOT) + return OP_BOOL; + + /* Check for value expressions */ + if (strcmp(token, "+") == 0) { + *etype = TEP_FILTER_EXP_ADD; + } else if (strcmp(token, "-") == 0) { + *etype = TEP_FILTER_EXP_SUB; + } else if (strcmp(token, "*") == 0) { + *etype = TEP_FILTER_EXP_MUL; + } else if (strcmp(token, "/") == 0) { + *etype = TEP_FILTER_EXP_DIV; + } else if (strcmp(token, "%") == 0) { + *etype = TEP_FILTER_EXP_MOD; + } else if (strcmp(token, ">>") == 0) { + *etype = TEP_FILTER_EXP_RSHIFT; + } else if (strcmp(token, "<<") == 0) { + *etype = TEP_FILTER_EXP_LSHIFT; + } else if (strcmp(token, "&") == 0) { + *etype = TEP_FILTER_EXP_AND; + } else if (strcmp(token, "|") == 0) { + *etype = TEP_FILTER_EXP_OR; + } else if (strcmp(token, "^") == 0) { + *etype = TEP_FILTER_EXP_XOR; + } else if (strcmp(token, "~") == 0) + *etype = TEP_FILTER_EXP_NOT; + + if (*etype != TEP_FILTER_EXP_NONE) + return OP_EXP; + + /* Check for compares */ + if (strcmp(token, "==") == 0) + *ctype = TEP_FILTER_CMP_EQ; + else if (strcmp(token, "!=") == 0) + *ctype = TEP_FILTER_CMP_NE; + else if (strcmp(token, "<") == 0) + *ctype = TEP_FILTER_CMP_LT; + else if (strcmp(token, ">") == 0) + *ctype = TEP_FILTER_CMP_GT; + else if (strcmp(token, "<=") == 0) + *ctype = TEP_FILTER_CMP_LE; + else if (strcmp(token, ">=") == 0) + *ctype = TEP_FILTER_CMP_GE; + else if (strcmp(token, "=~") == 0) + *ctype = TEP_FILTER_CMP_REGEX; + else if (strcmp(token, "!~") == 0) + *ctype = TEP_FILTER_CMP_NOT_REGEX; + else + return OP_NONE; + + return OP_CMP; +} + +static int check_op_done(struct tep_filter_arg *arg) +{ + switch (arg->type) { + case TEP_FILTER_ARG_EXP: + return arg->exp.right != NULL; + + case TEP_FILTER_ARG_OP: + return arg->op.right != NULL; + + case TEP_FILTER_ARG_NUM: + return arg->num.right != NULL; + + case TEP_FILTER_ARG_STR: + /* A string conversion is always done */ + return 1; + + case TEP_FILTER_ARG_BOOLEAN: + /* field not found, is ok */ + return 1; + + default: + return 0; + } +} + +enum filter_vals { + FILTER_VAL_NORM, + FILTER_VAL_FALSE, + FILTER_VAL_TRUE, +}; + +static enum tep_errno +reparent_op_arg(struct tep_filter_arg *parent, struct tep_filter_arg *old_child, + struct tep_filter_arg *arg, char *error_str) +{ + struct tep_filter_arg *other_child; + struct tep_filter_arg **ptr; + + if (parent->type != TEP_FILTER_ARG_OP && + arg->type != TEP_FILTER_ARG_OP) { + show_error(error_str, "can not reparent other than OP"); + return TEP_ERRNO__REPARENT_NOT_OP; + } + + /* Get the sibling */ + if (old_child->op.right == arg) { + ptr = &old_child->op.right; + other_child = old_child->op.left; + } else if (old_child->op.left == arg) { + ptr = &old_child->op.left; + other_child = old_child->op.right; + } else { + show_error(error_str, "Error in reparent op, find other child"); + return TEP_ERRNO__REPARENT_FAILED; + } + + /* Detach arg from old_child */ + *ptr = NULL; + + /* Check for root */ + if (parent == old_child) { + free_arg(other_child); + *parent = *arg; + /* Free arg without recussion */ + free(arg); + return 0; + } + + if (parent->op.right == old_child) + ptr = &parent->op.right; + else if (parent->op.left == old_child) + ptr = &parent->op.left; + else { + show_error(error_str, "Error in reparent op"); + return TEP_ERRNO__REPARENT_FAILED; + } + + *ptr = arg; + + free_arg(old_child); + return 0; +} + +/* Returns either filter_vals (success) or tep_errno (failfure) */ +static int test_arg(struct tep_filter_arg *parent, struct tep_filter_arg *arg, + char *error_str) +{ + int lval, rval; + + switch (arg->type) { + + /* bad case */ + case TEP_FILTER_ARG_BOOLEAN: + return FILTER_VAL_FALSE + arg->boolean.value; + + /* good cases: */ + case TEP_FILTER_ARG_STR: + case TEP_FILTER_ARG_VALUE: + case TEP_FILTER_ARG_FIELD: + return FILTER_VAL_NORM; + + case TEP_FILTER_ARG_EXP: + lval = test_arg(arg, arg->exp.left, error_str); + if (lval != FILTER_VAL_NORM) + return lval; + rval = test_arg(arg, arg->exp.right, error_str); + if (rval != FILTER_VAL_NORM) + return rval; + return FILTER_VAL_NORM; + + case TEP_FILTER_ARG_NUM: + lval = test_arg(arg, arg->num.left, error_str); + if (lval != FILTER_VAL_NORM) + return lval; + rval = test_arg(arg, arg->num.right, error_str); + if (rval != FILTER_VAL_NORM) + return rval; + return FILTER_VAL_NORM; + + case TEP_FILTER_ARG_OP: + if (arg->op.type != TEP_FILTER_OP_NOT) { + lval = test_arg(arg, arg->op.left, error_str); + switch (lval) { + case FILTER_VAL_NORM: + break; + case FILTER_VAL_TRUE: + if (arg->op.type == TEP_FILTER_OP_OR) + return FILTER_VAL_TRUE; + rval = test_arg(arg, arg->op.right, error_str); + if (rval != FILTER_VAL_NORM) + return rval; + + return reparent_op_arg(parent, arg, arg->op.right, + error_str); + + case FILTER_VAL_FALSE: + if (arg->op.type == TEP_FILTER_OP_AND) + return FILTER_VAL_FALSE; + rval = test_arg(arg, arg->op.right, error_str); + if (rval != FILTER_VAL_NORM) + return rval; + + return reparent_op_arg(parent, arg, arg->op.right, + error_str); + + default: + return lval; + } + } + + rval = test_arg(arg, arg->op.right, error_str); + switch (rval) { + case FILTER_VAL_NORM: + default: + break; + + case FILTER_VAL_TRUE: + if (arg->op.type == TEP_FILTER_OP_OR) + return FILTER_VAL_TRUE; + if (arg->op.type == TEP_FILTER_OP_NOT) + return FILTER_VAL_FALSE; + + return reparent_op_arg(parent, arg, arg->op.left, + error_str); + + case FILTER_VAL_FALSE: + if (arg->op.type == TEP_FILTER_OP_AND) + return FILTER_VAL_FALSE; + if (arg->op.type == TEP_FILTER_OP_NOT) + return FILTER_VAL_TRUE; + + return reparent_op_arg(parent, arg, arg->op.left, + error_str); + } + + return rval; + default: + show_error(error_str, "bad arg in filter tree"); + return TEP_ERRNO__BAD_FILTER_ARG; + } + return FILTER_VAL_NORM; +} + +/* Remove any unknown event fields */ +static int collapse_tree(struct tep_filter_arg *arg, + struct tep_filter_arg **arg_collapsed, char *error_str) +{ + int ret; + + ret = test_arg(arg, arg, error_str); + switch (ret) { + case FILTER_VAL_NORM: + break; + + case FILTER_VAL_TRUE: + case FILTER_VAL_FALSE: + free_arg(arg); + arg = allocate_arg(); + if (arg) { + arg->type = TEP_FILTER_ARG_BOOLEAN; + arg->boolean.value = ret == FILTER_VAL_TRUE; + } else { + show_error(error_str, "Failed to allocate filter arg"); + ret = TEP_ERRNO__MEM_ALLOC_FAILED; + } + break; + + default: + /* test_arg() already set the error_str */ + free_arg(arg); + arg = NULL; + break; + } + + *arg_collapsed = arg; + return ret; +} + +static enum tep_errno +process_filter(struct tep_event *event, struct tep_filter_arg **parg, + char *error_str, int not) +{ + enum tep_event_type type; + char *token = NULL; + struct tep_filter_arg *current_op = NULL; + struct tep_filter_arg *current_exp = NULL; + struct tep_filter_arg *left_item = NULL; + struct tep_filter_arg *arg = NULL; + enum op_type op_type; + enum tep_filter_op_type btype; + enum tep_filter_exp_type etype; + enum tep_filter_cmp_type ctype; + enum tep_errno ret; + + *parg = NULL; + + do { + free(token); + type = filter_read_token(&token); + switch (type) { + case TEP_EVENT_SQUOTE: + case TEP_EVENT_DQUOTE: + case TEP_EVENT_ITEM: + ret = create_arg_item(event, token, type, &arg, error_str); + if (ret < 0) + goto fail; + if (!left_item) + left_item = arg; + else if (current_exp) { + ret = add_right(current_exp, arg, error_str); + if (ret < 0) + goto fail; + left_item = NULL; + /* Not's only one one expression */ + if (not) { + arg = NULL; + if (current_op) + goto fail_syntax; + free(token); + *parg = current_exp; + return 0; + } + } else + goto fail_syntax; + arg = NULL; + break; + + case TEP_EVENT_DELIM: + if (*token == ',') { + show_error(error_str, "Illegal token ','"); + ret = TEP_ERRNO__ILLEGAL_TOKEN; + goto fail; + } + + if (*token == '(') { + if (left_item) { + show_error(error_str, + "Open paren can not come after item"); + ret = TEP_ERRNO__INVALID_PAREN; + goto fail; + } + if (current_exp) { + show_error(error_str, + "Open paren can not come after expression"); + ret = TEP_ERRNO__INVALID_PAREN; + goto fail; + } + + ret = process_filter(event, &arg, error_str, 0); + if (ret != TEP_ERRNO__UNBALANCED_PAREN) { + if (ret == 0) { + show_error(error_str, + "Unbalanced number of '('"); + ret = TEP_ERRNO__UNBALANCED_PAREN; + } + goto fail; + } + ret = 0; + + /* A not wants just one expression */ + if (not) { + if (current_op) + goto fail_syntax; + *parg = arg; + return 0; + } + + if (current_op) + ret = add_right(current_op, arg, error_str); + else + current_exp = arg; + + if (ret < 0) + goto fail; + + } else { /* ')' */ + if (!current_op && !current_exp) + goto fail_syntax; + + /* Make sure everything is finished at this level */ + if (current_exp && !check_op_done(current_exp)) + goto fail_syntax; + if (current_op && !check_op_done(current_op)) + goto fail_syntax; + + if (current_op) + *parg = current_op; + else + *parg = current_exp; + free(token); + return TEP_ERRNO__UNBALANCED_PAREN; + } + break; + + case TEP_EVENT_OP: + op_type = process_op(token, &btype, &ctype, &etype); + + /* All expect a left arg except for NOT */ + switch (op_type) { + case OP_BOOL: + /* Logic ops need a left expression */ + if (!current_exp && !current_op) + goto fail_syntax; + /* fall through */ + case OP_NOT: + /* logic only processes ops and exp */ + if (left_item) + goto fail_syntax; + break; + case OP_EXP: + case OP_CMP: + if (!left_item) + goto fail_syntax; + break; + case OP_NONE: + show_error(error_str, + "Unknown op token %s", token); + ret = TEP_ERRNO__UNKNOWN_TOKEN; + goto fail; + } + + ret = 0; + switch (op_type) { + case OP_BOOL: + arg = create_arg_op(btype); + if (arg == NULL) + goto fail_alloc; + if (current_op) + ret = add_left(arg, current_op); + else + ret = add_left(arg, current_exp); + current_op = arg; + current_exp = NULL; + break; + + case OP_NOT: + arg = create_arg_op(btype); + if (arg == NULL) + goto fail_alloc; + if (current_op) + ret = add_right(current_op, arg, error_str); + if (ret < 0) + goto fail; + current_exp = arg; + ret = process_filter(event, &arg, error_str, 1); + if (ret < 0) + goto fail; + ret = add_right(current_exp, arg, error_str); + if (ret < 0) + goto fail; + break; + + case OP_EXP: + case OP_CMP: + if (op_type == OP_EXP) + arg = create_arg_exp(etype); + else + arg = create_arg_cmp(ctype); + if (arg == NULL) + goto fail_alloc; + + if (current_op) + ret = add_right(current_op, arg, error_str); + if (ret < 0) + goto fail; + ret = add_left(arg, left_item); + if (ret < 0) { + arg = NULL; + goto fail_syntax; + } + current_exp = arg; + break; + default: + break; + } + arg = NULL; + if (ret < 0) + goto fail_syntax; + break; + case TEP_EVENT_NONE: + break; + case TEP_EVENT_ERROR: + goto fail_alloc; + default: + goto fail_syntax; + } + } while (type != TEP_EVENT_NONE); + + if (!current_op && !current_exp) + goto fail_syntax; + + if (!current_op) + current_op = current_exp; + + ret = collapse_tree(current_op, parg, error_str); + /* collapse_tree() may free current_op, and updates parg accordingly */ + current_op = NULL; + if (ret < 0) + goto fail; + + free(token); + return 0; + + fail_alloc: + show_error(error_str, "failed to allocate filter arg"); + ret = TEP_ERRNO__MEM_ALLOC_FAILED; + goto fail; + fail_syntax: + show_error(error_str, "Syntax error"); + ret = TEP_ERRNO__SYNTAX_ERROR; + fail: + free_arg(current_op); + free_arg(current_exp); + free_arg(arg); + free(token); + return ret; +} + +static enum tep_errno +process_event(struct tep_event *event, const char *filter_str, + struct tep_filter_arg **parg, char *error_str) +{ + int ret; + + init_input_buf(filter_str, strlen(filter_str)); + + ret = process_filter(event, parg, error_str, 0); + if (ret < 0) + return ret; + + /* If parg is NULL, then make it into FALSE */ + if (!*parg) { + *parg = allocate_arg(); + if (*parg == NULL) + return TEP_ERRNO__MEM_ALLOC_FAILED; + + (*parg)->type = TEP_FILTER_ARG_BOOLEAN; + (*parg)->boolean.value = TEP_FILTER_FALSE; + } + + return 0; +} + +static enum tep_errno +filter_event(struct tep_event_filter *filter, struct tep_event *event, + const char *filter_str, char *error_str) +{ + struct tep_filter_type *filter_type; + struct tep_filter_arg *arg; + enum tep_errno ret; + + if (filter_str) { + ret = process_event(event, filter_str, &arg, error_str); + if (ret < 0) + return ret; + + } else { + /* just add a TRUE arg */ + arg = allocate_arg(); + if (arg == NULL) + return TEP_ERRNO__MEM_ALLOC_FAILED; + + arg->type = TEP_FILTER_ARG_BOOLEAN; + arg->boolean.value = TEP_FILTER_TRUE; + } + + filter_type = add_filter_type(filter, event->id); + if (filter_type == NULL) { + free_arg(arg); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + + if (filter_type->filter) + free_arg(filter_type->filter); + filter_type->filter = arg; + + return 0; +} + +static void filter_init_error_buf(struct tep_event_filter *filter) +{ + /* clear buffer to reset show error */ + init_input_buf("", 0); + filter->error_buffer[0] = '\0'; +} + +/** + * tep_filter_add_filter_str - add a new filter + * @filter: the event filter to add to + * @filter_str: the filter string that contains the filter + * + * Returns 0 if the filter was successfully added or a + * negative error code. Use tep_filter_strerror() to see + * actual error message in case of error. + */ +enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, + const char *filter_str) +{ + struct tep_handle *tep = filter->tep; + struct event_list *event; + struct event_list *events = NULL; + const char *filter_start; + const char *next_event; + char *this_event; + char *event_name = NULL; + char *sys_name = NULL; + char *sp; + enum tep_errno rtn = 0; /* TEP_ERRNO__SUCCESS */ + int len; + int ret; + + filter_init_error_buf(filter); + + filter_start = strchr(filter_str, ':'); + if (filter_start) + len = filter_start - filter_str; + else + len = strlen(filter_str); + + do { + next_event = strchr(filter_str, ','); + if (next_event && + (!filter_start || next_event < filter_start)) + len = next_event - filter_str; + else if (filter_start) + len = filter_start - filter_str; + else + len = strlen(filter_str); + + this_event = malloc(len + 1); + if (this_event == NULL) { + /* This can only happen when events is NULL, but still */ + free_events(events); + return TEP_ERRNO__MEM_ALLOC_FAILED; + } + memcpy(this_event, filter_str, len); + this_event[len] = 0; + + if (next_event) + next_event++; + + filter_str = next_event; + + sys_name = strtok_r(this_event, "/", &sp); + event_name = strtok_r(NULL, "/", &sp); + + if (!sys_name) { + /* This can only happen when events is NULL, but still */ + free_events(events); + free(this_event); + return TEP_ERRNO__FILTER_NOT_FOUND; + } + + /* Find this event */ + ret = find_event(tep, &events, strim(sys_name), strim(event_name)); + if (ret < 0) { + free_events(events); + free(this_event); + return ret; + } + free(this_event); + } while (filter_str); + + /* Skip the ':' */ + if (filter_start) + filter_start++; + + /* filter starts here */ + for (event = events; event; event = event->next) { + ret = filter_event(filter, event->event, filter_start, + filter->error_buffer); + /* Failures are returned if a parse error happened */ + if (ret < 0) + rtn = ret; + + if (ret >= 0 && tep->test_filters) { + char *test; + test = tep_filter_make_string(filter, event->event->id); + if (test) { + printf(" '%s: %s'\n", event->event->name, test); + free(test); + } + } + } + + free_events(events); + + return rtn; +} + +static void free_filter_type(struct tep_filter_type *filter_type) +{ + free_arg(filter_type->filter); +} + +/** + * tep_filter_strerror - fill error message in a buffer + * @filter: the event filter contains error + * @err: the error code + * @buf: the buffer to be filled in + * @buflen: the size of the buffer + * + * Returns 0 if message was filled successfully, -1 if error + */ +int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err, + char *buf, size_t buflen) +{ + if (err <= __TEP_ERRNO__START || err >= __TEP_ERRNO__END) + return -1; + + if (strlen(filter->error_buffer) > 0) { + size_t len = snprintf(buf, buflen, "%s", filter->error_buffer); + + if (len > buflen) + return -1; + return 0; + } + + return tep_strerror(filter->tep, err, buf, buflen); +} + +/** + * tep_filter_remove_event - remove a filter for an event + * @filter: the event filter to remove from + * @event_id: the event to remove a filter for + * + * Removes the filter saved for an event defined by @event_id + * from the @filter. + * + * Returns 1: if an event was removed + * 0: if the event was not found + */ +int tep_filter_remove_event(struct tep_event_filter *filter, + int event_id) +{ + struct tep_filter_type *filter_type; + unsigned long len; + + if (!filter->filters) + return 0; + + filter_type = find_filter_type(filter, event_id); + + if (!filter_type) + return 0; + + free_filter_type(filter_type); + + /* The filter_type points into the event_filters array */ + len = (unsigned long)(filter->event_filters + filter->filters) - + (unsigned long)(filter_type + 1); + + memmove(filter_type, filter_type + 1, len); + filter->filters--; + + memset(&filter->event_filters[filter->filters], 0, + sizeof(*filter_type)); + + return 1; +} + +/** + * tep_filter_reset - clear all filters in a filter + * @filter: the event filter to reset + * + * Removes all filters from a filter and resets it. + */ +void tep_filter_reset(struct tep_event_filter *filter) +{ + int i; + + for (i = 0; i < filter->filters; i++) + free_filter_type(&filter->event_filters[i]); + + free(filter->event_filters); + filter->filters = 0; + filter->event_filters = NULL; +} + +void tep_filter_free(struct tep_event_filter *filter) +{ + tep_unref(filter->tep); + + tep_filter_reset(filter); + + free(filter); +} + +static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg); + +static int copy_filter_type(struct tep_event_filter *filter, + struct tep_event_filter *source, + struct tep_filter_type *filter_type) +{ + struct tep_filter_arg *arg; + struct tep_event *event; + const char *sys; + const char *name; + char *str; + + /* Can't assume that the tep's are the same */ + sys = filter_type->event->system; + name = filter_type->event->name; + event = tep_find_event_by_name(filter->tep, sys, name); + if (!event) + return -1; + + str = arg_to_str(source, filter_type->filter); + if (!str) + return -1; + + if (strcmp(str, "TRUE") == 0 || strcmp(str, "FALSE") == 0) { + /* Add trivial event */ + arg = allocate_arg(); + if (arg == NULL) { + free(str); + return -1; + } + + arg->type = TEP_FILTER_ARG_BOOLEAN; + if (strcmp(str, "TRUE") == 0) + arg->boolean.value = 1; + else + arg->boolean.value = 0; + + filter_type = add_filter_type(filter, event->id); + if (filter_type == NULL) { + free(str); + free_arg(arg); + return -1; + } + + filter_type->filter = arg; + + free(str); + return 0; + } + + filter_event(filter, event, str, NULL); + free(str); + + return 0; +} + +/** + * tep_filter_copy - copy a filter using another filter + * @dest - the filter to copy to + * @source - the filter to copy from + * + * Returns 0 on success and -1 if not all filters were copied + */ +int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source) +{ + int ret = 0; + int i; + + tep_filter_reset(dest); + + for (i = 0; i < source->filters; i++) { + if (copy_filter_type(dest, source, &source->event_filters[i])) + ret = -1; + } + return ret; +} + +static int test_filter(struct tep_event *event, struct tep_filter_arg *arg, + struct tep_record *record, enum tep_errno *err); + +static const char * +get_comm(struct tep_event *event, struct tep_record *record) +{ + const char *comm; + int pid; + + pid = tep_data_pid(event->tep, record); + comm = tep_data_comm_from_pid(event->tep, pid); + return comm; +} + +static unsigned long long +get_value(struct tep_event *event, + struct tep_format_field *field, struct tep_record *record) +{ + unsigned long long val; + + /* Handle our dummy "comm" field */ + if (field == &comm) { + const char *name; + + name = get_comm(event, record); + return (unsigned long)name; + } + + /* Handle our dummy "cpu" field */ + if (field == &cpu) + return record->cpu; + + tep_read_number_field(field, record->data, &val); + + if (!(field->flags & TEP_FIELD_IS_SIGNED)) + return val; + + switch (field->size) { + case 1: + return (char)val; + case 2: + return (short)val; + case 4: + return (int)val; + case 8: + return (long long)val; + } + return val; +} + +static unsigned long long +get_arg_value(struct tep_event *event, struct tep_filter_arg *arg, + struct tep_record *record, enum tep_errno *err); + +static unsigned long long +get_exp_value(struct tep_event *event, struct tep_filter_arg *arg, + struct tep_record *record, enum tep_errno *err) +{ + unsigned long long lval, rval; + + lval = get_arg_value(event, arg->exp.left, record, err); + rval = get_arg_value(event, arg->exp.right, record, err); + + if (*err) { + /* + * There was an error, no need to process anymore. + */ + return 0; + } + + switch (arg->exp.type) { + case TEP_FILTER_EXP_ADD: + return lval + rval; + + case TEP_FILTER_EXP_SUB: + return lval - rval; + + case TEP_FILTER_EXP_MUL: + return lval * rval; + + case TEP_FILTER_EXP_DIV: + return lval / rval; + + case TEP_FILTER_EXP_MOD: + return lval % rval; + + case TEP_FILTER_EXP_RSHIFT: + return lval >> rval; + + case TEP_FILTER_EXP_LSHIFT: + return lval << rval; + + case TEP_FILTER_EXP_AND: + return lval & rval; + + case TEP_FILTER_EXP_OR: + return lval | rval; + + case TEP_FILTER_EXP_XOR: + return lval ^ rval; + + case TEP_FILTER_EXP_NOT: + default: + if (!*err) + *err = TEP_ERRNO__INVALID_EXP_TYPE; + } + return 0; +} + +static unsigned long long +get_arg_value(struct tep_event *event, struct tep_filter_arg *arg, + struct tep_record *record, enum tep_errno *err) +{ + switch (arg->type) { + case TEP_FILTER_ARG_FIELD: + return get_value(event, arg->field.field, record); + + case TEP_FILTER_ARG_VALUE: + if (arg->value.type != TEP_FILTER_NUMBER) { + if (!*err) + *err = TEP_ERRNO__NOT_A_NUMBER; + } + return arg->value.val; + + case TEP_FILTER_ARG_EXP: + return get_exp_value(event, arg, record, err); + + default: + if (!*err) + *err = TEP_ERRNO__INVALID_ARG_TYPE; + } + return 0; +} + +static int test_num(struct tep_event *event, struct tep_filter_arg *arg, + struct tep_record *record, enum tep_errno *err) +{ + unsigned long long lval, rval; + + lval = get_arg_value(event, arg->num.left, record, err); + rval = get_arg_value(event, arg->num.right, record, err); + + if (*err) { + /* + * There was an error, no need to process anymore. + */ + return 0; + } + + switch (arg->num.type) { + case TEP_FILTER_CMP_EQ: + return lval == rval; + + case TEP_FILTER_CMP_NE: + return lval != rval; + + case TEP_FILTER_CMP_GT: + return lval > rval; + + case TEP_FILTER_CMP_LT: + return lval < rval; + + case TEP_FILTER_CMP_GE: + return lval >= rval; + + case TEP_FILTER_CMP_LE: + return lval <= rval; + + default: + if (!*err) + *err = TEP_ERRNO__ILLEGAL_INTEGER_CMP; + return 0; + } +} + +static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record) +{ + struct tep_event *event; + struct tep_handle *tep; + unsigned long long addr; + const char *val = NULL; + unsigned int size; + char hex[64]; + + /* If the field is not a string convert it */ + if (arg->str.field->flags & TEP_FIELD_IS_STRING) { + val = record->data + arg->str.field->offset; + size = arg->str.field->size; + + if (arg->str.field->flags & TEP_FIELD_IS_DYNAMIC) { + addr = *(unsigned int *)val; + size = addr >> 16; + addr &= 0xffff; + if (arg->str.field->flags & TEP_FIELD_IS_RELATIVE) + addr += arg->str.field->offset + arg->str.field->size; + val = record->data + addr; + } + + /* + * We need to copy the data since we can't be sure the field + * is null terminated. + */ + if (*(val + size - 1)) { + /* copy it */ + memcpy(arg->str.buffer, val, arg->str.field->size); + /* the buffer is already NULL terminated */ + val = arg->str.buffer; + } + + } else { + event = arg->str.field->event; + tep = event->tep; + addr = get_value(event, arg->str.field, record); + + if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG)) + /* convert to a kernel symbol */ + val = tep_find_function(tep, addr); + + if (val == NULL) { + /* just use the hex of the string name */ + snprintf(hex, 64, "0x%llx", addr); + val = hex; + } + } + + return val; +} + +static int test_str(struct tep_event *event, struct tep_filter_arg *arg, + struct tep_record *record, enum tep_errno *err) +{ + const char *val; + + if (arg->str.field == &comm) + val = get_comm(event, record); + else + val = get_field_str(arg, record); + + switch (arg->str.type) { + case TEP_FILTER_CMP_MATCH: + return strcmp(val, arg->str.val) == 0; + + case TEP_FILTER_CMP_NOT_MATCH: + return strcmp(val, arg->str.val) != 0; + + case TEP_FILTER_CMP_REGEX: + /* Returns zero on match */ + return !regexec(&arg->str.reg, val, 0, NULL, 0); + + case TEP_FILTER_CMP_NOT_REGEX: + return regexec(&arg->str.reg, val, 0, NULL, 0); + + default: + if (!*err) + *err = TEP_ERRNO__ILLEGAL_STRING_CMP; + return 0; + } +} + +static int test_op(struct tep_event *event, struct tep_filter_arg *arg, + struct tep_record *record, enum tep_errno *err) +{ + switch (arg->op.type) { + case TEP_FILTER_OP_AND: + return test_filter(event, arg->op.left, record, err) && + test_filter(event, arg->op.right, record, err); + + case TEP_FILTER_OP_OR: + return test_filter(event, arg->op.left, record, err) || + test_filter(event, arg->op.right, record, err); + + case TEP_FILTER_OP_NOT: + return !test_filter(event, arg->op.right, record, err); + + default: + if (!*err) + *err = TEP_ERRNO__INVALID_OP_TYPE; + return 0; + } +} + +static int test_filter(struct tep_event *event, struct tep_filter_arg *arg, + struct tep_record *record, enum tep_errno *err) +{ + if (*err) { + /* + * There was an error, no need to process anymore. + */ + return 0; + } + + switch (arg->type) { + case TEP_FILTER_ARG_BOOLEAN: + /* easy case */ + return arg->boolean.value; + + case TEP_FILTER_ARG_OP: + return test_op(event, arg, record, err); + + case TEP_FILTER_ARG_NUM: + return test_num(event, arg, record, err); + + case TEP_FILTER_ARG_STR: + return test_str(event, arg, record, err); + + case TEP_FILTER_ARG_EXP: + case TEP_FILTER_ARG_VALUE: + case TEP_FILTER_ARG_FIELD: + /* + * Expressions, fields and values evaluate + * to true if they return non zero + */ + return !!get_arg_value(event, arg, record, err); + + default: + if (!*err) + *err = TEP_ERRNO__INVALID_ARG_TYPE; + return 0; + } +} + +/** + * tep_event_filtered - return true if event has filter + * @filter: filter struct with filter information + * @event_id: event id to test if filter exists + * + * Returns 1 if filter found for @event_id + * otherwise 0; + */ +int tep_event_filtered(struct tep_event_filter *filter, int event_id) +{ + struct tep_filter_type *filter_type; + + if (!filter->filters) + return 0; + + filter_type = find_filter_type(filter, event_id); + + return filter_type ? 1 : 0; +} + +/** + * tep_filter_match - test if a record matches a filter + * @filter: filter struct with filter information + * @record: the record to test against the filter + * + * Returns: match result or error code (prefixed with TEP_ERRNO__) + * FILTER_MATCH - filter found for event and @record matches + * FILTER_MISS - filter found for event and @record does not match + * FILTER_NOT_FOUND - no filter found for @record's event + * NO_FILTER - if no filters exist + * otherwise - error occurred during test + */ +enum tep_errno tep_filter_match(struct tep_event_filter *filter, + struct tep_record *record) +{ + struct tep_handle *tep = filter->tep; + struct tep_filter_type *filter_type; + int event_id; + int ret; + enum tep_errno err = 0; + + filter_init_error_buf(filter); + + if (!filter->filters) + return TEP_ERRNO__NO_FILTER; + + event_id = tep_data_type(tep, record); + + filter_type = find_filter_type(filter, event_id); + if (!filter_type) + return TEP_ERRNO__FILTER_NOT_FOUND; + + ret = test_filter(filter_type->event, filter_type->filter, record, &err); + if (err) + return err; + + return ret ? TEP_ERRNO__FILTER_MATCH : TEP_ERRNO__FILTER_MISS; +} + +static char *op_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg) +{ + char *str = NULL; + char *left = NULL; + char *right = NULL; + char *op = NULL; + int left_val = -1; + int right_val = -1; + int val; + + switch (arg->op.type) { + case TEP_FILTER_OP_AND: + op = "&&"; + /* fall through */ + case TEP_FILTER_OP_OR: + if (!op) + op = "||"; + + left = arg_to_str(filter, arg->op.left); + right = arg_to_str(filter, arg->op.right); + if (!left || !right) + break; + + /* Try to consolidate boolean values */ + if (strcmp(left, "TRUE") == 0) + left_val = 1; + else if (strcmp(left, "FALSE") == 0) + left_val = 0; + + if (strcmp(right, "TRUE") == 0) + right_val = 1; + else if (strcmp(right, "FALSE") == 0) + right_val = 0; + + if (left_val >= 0) { + if ((arg->op.type == TEP_FILTER_OP_AND && !left_val) || + (arg->op.type == TEP_FILTER_OP_OR && left_val)) { + /* Just return left value */ + str = left; + left = NULL; + break; + } + if (right_val >= 0) { + /* just evaluate this. */ + val = 0; + switch (arg->op.type) { + case TEP_FILTER_OP_AND: + val = left_val && right_val; + break; + case TEP_FILTER_OP_OR: + val = left_val || right_val; + break; + default: + break; + } + if (asprintf(&str, val ? "TRUE" : "FALSE") < 0) + str = NULL; + break; + } + } + if (right_val >= 0) { + if ((arg->op.type == TEP_FILTER_OP_AND && !right_val) || + (arg->op.type == TEP_FILTER_OP_OR && right_val)) { + /* Just return right value */ + str = right; + right = NULL; + break; + } + /* The right value is meaningless */ + str = left; + left = NULL; + break; + } + + if (asprintf(&str, "(%s) %s (%s)", left, op, right) < 0) + str = NULL; + break; + + case TEP_FILTER_OP_NOT: + op = "!"; + right = arg_to_str(filter, arg->op.right); + if (!right) + break; + + /* See if we can consolidate */ + if (strcmp(right, "TRUE") == 0) + right_val = 1; + else if (strcmp(right, "FALSE") == 0) + right_val = 0; + if (right_val >= 0) { + /* just return the opposite */ + if (asprintf(&str, right_val ? "FALSE" : "TRUE") < 0) + str = NULL; + break; + } + if (asprintf(&str, "%s(%s)", op, right) < 0) + str = NULL; + break; + + default: + /* ?? */ + break; + } + free(left); + free(right); + return str; +} + +static char *val_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg) +{ + char *str = NULL; + + if (asprintf(&str, "%lld", arg->value.val) < 0) + str = NULL; + + return str; +} + +static char *field_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg) +{ + return strdup(arg->field.field->name); +} + +static char *exp_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg) +{ + char *lstr; + char *rstr; + char *op; + char *str = NULL; + + lstr = arg_to_str(filter, arg->exp.left); + rstr = arg_to_str(filter, arg->exp.right); + if (!lstr || !rstr) + goto out; + + switch (arg->exp.type) { + case TEP_FILTER_EXP_ADD: + op = "+"; + break; + case TEP_FILTER_EXP_SUB: + op = "-"; + break; + case TEP_FILTER_EXP_MUL: + op = "*"; + break; + case TEP_FILTER_EXP_DIV: + op = "/"; + break; + case TEP_FILTER_EXP_MOD: + op = "%"; + break; + case TEP_FILTER_EXP_RSHIFT: + op = ">>"; + break; + case TEP_FILTER_EXP_LSHIFT: + op = "<<"; + break; + case TEP_FILTER_EXP_AND: + op = "&"; + break; + case TEP_FILTER_EXP_OR: + op = "|"; + break; + case TEP_FILTER_EXP_XOR: + op = "^"; + break; + default: + op = "[ERROR IN EXPRESSION TYPE]"; + break; + } + + if (asprintf(&str, "%s %s %s", lstr, op, rstr) < 0) + str = NULL; +out: + free(lstr); + free(rstr); + + return str; +} + +static char *num_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg) +{ + char *lstr; + char *rstr; + char *str = NULL; + char *op = NULL; + + lstr = arg_to_str(filter, arg->num.left); + rstr = arg_to_str(filter, arg->num.right); + if (!lstr || !rstr) + goto out; + + switch (arg->num.type) { + case TEP_FILTER_CMP_EQ: + op = "=="; + /* fall through */ + case TEP_FILTER_CMP_NE: + if (!op) + op = "!="; + /* fall through */ + case TEP_FILTER_CMP_GT: + if (!op) + op = ">"; + /* fall through */ + case TEP_FILTER_CMP_LT: + if (!op) + op = "<"; + /* fall through */ + case TEP_FILTER_CMP_GE: + if (!op) + op = ">="; + /* fall through */ + case TEP_FILTER_CMP_LE: + if (!op) + op = "<="; + + if (asprintf(&str, "%s %s %s", lstr, op, rstr) < 0) + str = NULL; + break; + + default: + /* ?? */ + break; + } + +out: + free(lstr); + free(rstr); + return str; +} + +static char *str_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg) +{ + char *str = NULL; + char *op = NULL; + + switch (arg->str.type) { + case TEP_FILTER_CMP_MATCH: + op = "=="; + /* fall through */ + case TEP_FILTER_CMP_NOT_MATCH: + if (!op) + op = "!="; + /* fall through */ + case TEP_FILTER_CMP_REGEX: + if (!op) + op = "=~"; + /* fall through */ + case TEP_FILTER_CMP_NOT_REGEX: + if (!op) + op = "!~"; + + if (asprintf(&str, "%s %s \"%s\"", + arg->str.field->name, op, arg->str.val) < 0) + str = NULL; + break; + + default: + /* ?? */ + break; + } + return str; +} + +static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg) +{ + char *str = NULL; + + switch (arg->type) { + case TEP_FILTER_ARG_BOOLEAN: + if (asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE") < 0) + str = NULL; + return str; + + case TEP_FILTER_ARG_OP: + return op_to_str(filter, arg); + + case TEP_FILTER_ARG_NUM: + return num_to_str(filter, arg); + + case TEP_FILTER_ARG_STR: + return str_to_str(filter, arg); + + case TEP_FILTER_ARG_VALUE: + return val_to_str(filter, arg); + + case TEP_FILTER_ARG_FIELD: + return field_to_str(filter, arg); + + case TEP_FILTER_ARG_EXP: + return exp_to_str(filter, arg); + + default: + /* ?? */ + return NULL; + } + +} + +/** + * tep_filter_make_string - return a string showing the filter + * @filter: filter struct with filter information + * @event_id: the event id to return the filter string with + * + * Returns a string that displays the filter contents. + * This string must be freed with free(str). + * NULL is returned if no filter is found or allocation failed. + */ +char * +tep_filter_make_string(struct tep_event_filter *filter, int event_id) +{ + struct tep_filter_type *filter_type; + + if (!filter->filters) + return NULL; + + filter_type = find_filter_type(filter, event_id); + + if (!filter_type) + return NULL; + + return arg_to_str(filter, filter_type->filter); +} + +/** + * tep_filter_compare - compare two filters and return if they are the same + * @filter1: Filter to compare with @filter2 + * @filter2: Filter to compare with @filter1 + * + * Returns: + * 1 if the two filters hold the same content. + * 0 if they do not. + */ +int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2) +{ + struct tep_filter_type *filter_type1; + struct tep_filter_type *filter_type2; + char *str1, *str2; + int result; + int i; + + /* Do the easy checks first */ + if (filter1->filters != filter2->filters) + return 0; + if (!filter1->filters && !filter2->filters) + return 1; + + /* + * Now take a look at each of the events to see if they have the same + * filters to them. + */ + for (i = 0; i < filter1->filters; i++) { + filter_type1 = &filter1->event_filters[i]; + filter_type2 = find_filter_type(filter2, filter_type1->event_id); + if (!filter_type2) + break; + if (filter_type1->filter->type != filter_type2->filter->type) + break; + /* The best way to compare complex filters is with strings */ + str1 = arg_to_str(filter1, filter_type1->filter); + str2 = arg_to_str(filter2, filter_type2->filter); + if (str1 && str2) + result = strcmp(str1, str2) != 0; + else + /* bail out if allocation fails */ + result = 1; + + free(str1); + free(str2); + if (result) + break; + } + + if (i < filter1->filters) + return 0; + return 1; +} + diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c new file mode 100644 index 000000000..e99867111 --- /dev/null +++ b/tools/lib/traceevent/parse-utils.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdarg.h> +#include <errno.h> + +#define __weak __attribute__((weak)) + +void __vwarning(const char *fmt, va_list ap) +{ + if (errno) + perror("libtraceevent"); + errno = 0; + + fprintf(stderr, " "); + vfprintf(stderr, fmt, ap); + + fprintf(stderr, "\n"); +} + +void __warning(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + __vwarning(fmt, ap); + va_end(ap); +} + +void __weak warning(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + __vwarning(fmt, ap); + va_end(ap); +} + +void __vpr_stat(const char *fmt, va_list ap) +{ + vprintf(fmt, ap); + printf("\n"); +} + +void __pr_stat(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + __vpr_stat(fmt, ap); + va_end(ap); +} + +void __weak vpr_stat(const char *fmt, va_list ap) +{ + __vpr_stat(fmt, ap); +} + +void __weak pr_stat(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + __vpr_stat(fmt, ap); + va_end(ap); +} diff --git a/tools/lib/traceevent/plugins/Build b/tools/lib/traceevent/plugins/Build new file mode 100644 index 000000000..dd4da823c --- /dev/null +++ b/tools/lib/traceevent/plugins/Build @@ -0,0 +1,12 @@ +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_futex-y += plugin_futex.o +plugin_xen-y += plugin_xen.o +plugin_scsi-y += plugin_scsi.o +plugin_cfg80211-y += plugin_cfg80211.o +plugin_tlb-y += plugin_tlb.o
\ No newline at end of file diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile new file mode 100644 index 000000000..47e802553 --- /dev/null +++ b/tools/lib/traceevent/plugins/Makefile @@ -0,0 +1,225 @@ +# 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_futex.so +PLUGINS += plugin_xen.so +PLUGINS += plugin_scsi.so +PLUGINS += plugin_cfg80211.so +PLUGINS += plugin_tlb.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 [ "$$symbol_type" = "U W" ];then \ + (echo '{'; \ + $(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); 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/plugins/plugin_cfg80211.c b/tools/lib/traceevent/plugins/plugin_cfg80211.c new file mode 100644 index 000000000..3d43b56a6 --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_cfg80211.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> +#include <inttypes.h> +#include <endian.h> +#include "event-parse.h" + +/* + * From glibc endian.h, for older systems where it is not present, e.g.: RHEL5, + * Fedora6. + */ +#ifndef le16toh +# if __BYTE_ORDER == __LITTLE_ENDIAN +# define le16toh(x) (x) +# else +# define le16toh(x) __bswap_16 (x) +# endif +#endif + + +static unsigned long long +process___le16_to_cpup(struct trace_seq *s, unsigned long long *args) +{ + uint16_t *val = (uint16_t *) (unsigned long) args[0]; + return val ? (long long) le16toh(*val) : 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_print_function(tep, + process___le16_to_cpup, + TEP_FUNC_ARG_INT, + "__le16_to_cpup", + TEP_FUNC_ARG_PTR, + TEP_FUNC_ARG_VOID); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_print_function(tep, process___le16_to_cpup, + "__le16_to_cpup"); +} diff --git a/tools/lib/traceevent/plugins/plugin_function.c b/tools/lib/traceevent/plugins/plugin_function.c new file mode 100644 index 000000000..807b16e1b --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_function.c @@ -0,0 +1,282 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "event-parse.h" +#include "event-utils.h" +#include "trace-seq.h" + +static struct func_stack { + int size; + char **stack; +} *fstack; + +static int cpus = -1; + +#define STK_BLK 10 + +struct tep_plugin_option plugin_options[] = +{ + { + .name = "parent", + .plugin_alias = "ftrace", + .description = + "Print parent of functions for function events", + }, + { + .name = "indent", + .plugin_alias = "ftrace", + .description = + "Try to show function call indents, based on parents", + .set = 1, + }, + { + .name = "offset", + .plugin_alias = "ftrace", + .description = + "Show function names as well as their offsets", + .set = 0, + }, + { + .name = NULL, + } +}; + +static struct tep_plugin_option *ftrace_parent = &plugin_options[0]; +static struct tep_plugin_option *ftrace_indent = &plugin_options[1]; +static struct tep_plugin_option *ftrace_offset = &plugin_options[2]; + +static void add_child(struct func_stack *stack, const char *child, int pos) +{ + int i; + + if (!child) + return; + + if (pos < stack->size) + free(stack->stack[pos]); + else { + char **ptr; + + ptr = realloc(stack->stack, sizeof(char *) * + (stack->size + STK_BLK)); + if (!ptr) { + warning("could not allocate plugin memory\n"); + return; + } + + stack->stack = ptr; + + for (i = stack->size; i < stack->size + STK_BLK; i++) + stack->stack[i] = NULL; + stack->size += STK_BLK; + } + + stack->stack[pos] = strdup(child); +} + +static int add_and_get_index(const char *parent, const char *child, int cpu) +{ + int i; + + if (cpu < 0) + return 0; + + if (cpu > cpus) { + struct func_stack *ptr; + + ptr = realloc(fstack, sizeof(*fstack) * (cpu + 1)); + if (!ptr) { + warning("could not allocate plugin memory\n"); + return 0; + } + + fstack = ptr; + + /* Account for holes in the cpu count */ + for (i = cpus + 1; i <= cpu; i++) + memset(&fstack[i], 0, sizeof(fstack[i])); + cpus = cpu; + } + + for (i = 0; i < fstack[cpu].size && fstack[cpu].stack[i]; i++) { + if (strcmp(parent, fstack[cpu].stack[i]) == 0) { + add_child(&fstack[cpu], child, i+1); + return i; + } + } + + /* Not found */ + add_child(&fstack[cpu], parent, 0); + add_child(&fstack[cpu], child, 1); + return 0; +} + +static void show_function(struct trace_seq *s, struct tep_handle *tep, + const char *func, unsigned long long function) +{ + unsigned long long offset; + + trace_seq_printf(s, "%s", func); + if (ftrace_offset->set) { + offset = tep_find_function_address(tep, function); + trace_seq_printf(s, "+0x%x ", (int)(function - offset)); + } +} + +static int function_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct tep_handle *tep = event->tep; + unsigned long long function; + unsigned long long pfunction; + const char *func; + const char *parent; + int index = 0; + + if (tep_get_field_val(s, event, "ip", record, &function, 1)) + return trace_seq_putc(s, '!'); + + func = tep_find_function(tep, function); + + if (tep_get_field_val(s, event, "parent_ip", record, &pfunction, 1)) + return trace_seq_putc(s, '!'); + + parent = tep_find_function(tep, pfunction); + + if (parent && ftrace_indent->set) + index = add_and_get_index(parent, func, record->cpu); + + trace_seq_printf(s, "%*s", index*3, ""); + + if (func) + show_function(s, tep, func, function); + else + trace_seq_printf(s, "0x%llx", function); + + if (ftrace_parent->set) { + trace_seq_printf(s, " <-- "); + if (parent) + show_function(s, tep, parent, pfunction); + else + trace_seq_printf(s, "0x%llx", pfunction); + } + + return 0; +} + +static int +trace_stack_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct tep_format_field *field; + unsigned long long addr; + const char *func; + int long_size; + void *data = record->data; + + field = tep_find_any_field(event, "caller"); + if (!field) { + trace_seq_printf(s, "<CANT FIND FIELD %s>", "caller"); + return 0; + } + + trace_seq_puts(s, "<stack trace >\n"); + + long_size = tep_get_long_size(event->tep); + + for (data += field->offset; data < record->data + record->size; + data += long_size) { + addr = tep_read_number(event->tep, data, long_size); + + if ((long_size == 8 && addr == (unsigned long long)-1) || + ((int)addr == -1)) + break; + + func = tep_find_function(event->tep, addr); + if (func) + trace_seq_printf(s, "=> %s (%llx)\n", func, addr); + else + trace_seq_printf(s, "=> %llx\n", addr); + } + + return 0; +} + +static int +trace_raw_data_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct tep_format_field *field; + unsigned long long id; + int long_size; + void *data = record->data; + + if (tep_get_field_val(s, event, "id", record, &id, 1)) + return trace_seq_putc(s, '!'); + + trace_seq_printf(s, "# %llx", id); + + field = tep_find_any_field(event, "buf"); + if (!field) { + trace_seq_printf(s, "<CANT FIND FIELD %s>", "buf"); + return 0; + } + + long_size = tep_get_long_size(event->tep); + + for (data += field->offset; data < record->data + record->size; + data += long_size) { + int size = sizeof(long); + int left = (record->data + record->size) - data; + int i; + + if (size > left) + size = left; + + for (i = 0; i < size; i++) + trace_seq_printf(s, " %02x", *(unsigned char *)(data + i)); + } + + return 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_event_handler(tep, -1, "ftrace", "function", + function_handler, NULL); + + tep_register_event_handler(tep, -1, "ftrace", "kernel_stack", + trace_stack_handler, NULL); + + tep_register_event_handler(tep, -1, "ftrace", "raw_data", + trace_raw_data_handler, NULL); + + tep_plugin_add_options("ftrace", plugin_options); + + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + int i, x; + + tep_unregister_event_handler(tep, -1, "ftrace", "function", + function_handler, NULL); + + for (i = 0; i <= cpus; i++) { + for (x = 0; x < fstack[i].size && fstack[i].stack[x]; x++) + free(fstack[i].stack[x]); + free(fstack[i].stack); + } + + tep_plugin_remove_options(plugin_options); + + free(fstack); + fstack = NULL; + cpus = -1; +} diff --git a/tools/lib/traceevent/plugins/plugin_futex.c b/tools/lib/traceevent/plugins/plugin_futex.c new file mode 100644 index 000000000..eb7c9f8a8 --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_futex.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2017 National Instruments Corp. + * + * Author: Julia Cartwright <julia@ni.com> + * + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <linux/futex.h> + +#include "event-parse.h" + +#define ARRAY_SIZE(_a) (sizeof(_a) / sizeof((_a)[0])) + +struct futex_args { + unsigned long long uaddr; + unsigned long long op; + unsigned long long val; + unsigned long long utime; /* or val2 */ + unsigned long long uaddr2; + unsigned long long val3; +}; + +struct futex_op { + const char *name; + const char *fmt_val; + const char *fmt_utime; + const char *fmt_uaddr2; + const char *fmt_val3; +}; + +static const struct futex_op futex_op_tbl[] = { + { "FUTEX_WAIT", " val=0x%08llx", " utime=0x%08llx", NULL, NULL }, + { "FUTEX_WAKE", " val=%llu", NULL, NULL, NULL }, + { "FUTEX_FD", " val=%llu", NULL, NULL, NULL }, + { "FUTEX_REQUEUE", " val=%llu", " val2=%llu", " uaddr2=0x%08llx", NULL }, + { "FUTEX_CMP_REQUEUE", " val=%llu", " val2=%llu", " uaddr2=0x%08llx", " val3=0x%08llx" }, + { "FUTEX_WAKE_OP", " val=%llu", " val2=%llu", " uaddr2=0x%08llx", " val3=0x%08llx" }, + { "FUTEX_LOCK_PI", NULL, " utime=0x%08llx", NULL, NULL }, + { "FUTEX_UNLOCK_PI", NULL, NULL, NULL, NULL }, + { "FUTEX_TRYLOCK_PI", NULL, NULL, NULL, NULL }, + { "FUTEX_WAIT_BITSET", " val=0x%08llx", " utime=0x%08llx", NULL, " val3=0x%08llx" }, + { "FUTEX_WAKE_BITSET", " val=%llu", NULL, NULL, " val3=0x%08llx" }, + { "FUTEX_WAIT_REQUEUE_PI", " val=0x%08llx", " utime=0x%08llx", " uaddr2=0x%08llx", " val3=0x%08llx" }, + { "FUTEX_CMP_REQUEUE_PI", " val=%llu", " val2=%llu", " uaddr2=0x%08llx", " val3=0x%08llx" }, +}; + + +static void futex_print(struct trace_seq *s, const struct futex_args *args, + const struct futex_op *fop) +{ + trace_seq_printf(s, " uaddr=0x%08llx", args->uaddr); + + if (fop->fmt_val) + trace_seq_printf(s, fop->fmt_val, args->val); + + if (fop->fmt_utime) + trace_seq_printf(s,fop->fmt_utime, args->utime); + + if (fop->fmt_uaddr2) + trace_seq_printf(s, fop->fmt_uaddr2, args->uaddr2); + + if (fop->fmt_val3) + trace_seq_printf(s, fop->fmt_val3, args->val3); +} + +static int futex_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + const struct futex_op *fop; + struct futex_args args; + unsigned long long cmd; + + if (tep_get_field_val(s, event, "uaddr", record, &args.uaddr, 1)) + return 1; + + if (tep_get_field_val(s, event, "op", record, &args.op, 1)) + return 1; + + if (tep_get_field_val(s, event, "val", record, &args.val, 1)) + return 1; + + if (tep_get_field_val(s, event, "utime", record, &args.utime, 1)) + return 1; + + if (tep_get_field_val(s, event, "uaddr2", record, &args.uaddr2, 1)) + return 1; + + if (tep_get_field_val(s, event, "val3", record, &args.val3, 1)) + return 1; + + cmd = args.op & FUTEX_CMD_MASK; + if (cmd >= ARRAY_SIZE(futex_op_tbl)) + return 1; + + fop = &futex_op_tbl[cmd]; + + trace_seq_printf(s, "op=%s", fop->name); + + if (args.op & FUTEX_PRIVATE_FLAG) + trace_seq_puts(s, "|FUTEX_PRIVATE_FLAG"); + + if (args.op & FUTEX_CLOCK_REALTIME) + trace_seq_puts(s, "|FUTEX_CLOCK_REALTIME"); + + futex_print(s, &args, fop); + return 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_event_handler(tep, -1, "syscalls", "sys_enter_futex", + futex_handler, NULL); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_event_handler(tep, -1, "syscalls", "sys_enter_futex", + futex_handler, NULL); +} diff --git a/tools/lib/traceevent/plugins/plugin_hrtimer.c b/tools/lib/traceevent/plugins/plugin_hrtimer.c new file mode 100644 index 000000000..d98466788 --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_hrtimer.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2009 Johannes Berg <johannes@sipsolutions.net> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "event-parse.h" +#include "trace-seq.h" + +static int timer_expire_handler(struct trace_seq *s, + struct tep_record *record, + struct tep_event *event, void *context) +{ + trace_seq_printf(s, "hrtimer="); + + if (tep_print_num_field(s, "0x%llx", event, "timer", + record, 0) == -1) + tep_print_num_field(s, "0x%llx", event, "hrtimer", + record, 1); + + trace_seq_printf(s, " now="); + + tep_print_num_field(s, "%llu", event, "now", record, 1); + + tep_print_func_field(s, " function=%s", event, "function", + record, 0); + return 0; +} + +static int timer_start_handler(struct trace_seq *s, + struct tep_record *record, + struct tep_event *event, void *context) +{ + trace_seq_printf(s, "hrtimer="); + + if (tep_print_num_field(s, "0x%llx", event, "timer", + record, 0) == -1) + tep_print_num_field(s, "0x%llx", event, "hrtimer", + record, 1); + + tep_print_func_field(s, " function=%s", event, "function", + record, 0); + + trace_seq_printf(s, " expires="); + tep_print_num_field(s, "%llu", event, "expires", record, 1); + + trace_seq_printf(s, " softexpires="); + tep_print_num_field(s, "%llu", event, "softexpires", record, 1); + return 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_event_handler(tep, -1, + "timer", "hrtimer_expire_entry", + timer_expire_handler, NULL); + + tep_register_event_handler(tep, -1, "timer", "hrtimer_start", + timer_start_handler, NULL); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_event_handler(tep, -1, + "timer", "hrtimer_expire_entry", + timer_expire_handler, NULL); + + tep_unregister_event_handler(tep, -1, "timer", "hrtimer_start", + timer_start_handler, NULL); +} diff --git a/tools/lib/traceevent/plugins/plugin_jbd2.c b/tools/lib/traceevent/plugins/plugin_jbd2.c new file mode 100644 index 000000000..69111a68d --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_jbd2.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "event-parse.h" +#include "trace-seq.h" + +#define MINORBITS 20 +#define MINORMASK ((1U << MINORBITS) - 1) + +#define MAJOR(dev) ((unsigned int) ((dev) >> MINORBITS)) +#define MINOR(dev) ((unsigned int) ((dev) & MINORMASK)) + +static unsigned long long +process_jbd2_dev_to_name(struct trace_seq *s, unsigned long long *args) +{ + unsigned int dev = args[0]; + + trace_seq_printf(s, "%d:%d", MAJOR(dev), MINOR(dev)); + return 0; +} + +static unsigned long long +process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args) +{ + unsigned long long jiffies = args[0]; + + trace_seq_printf(s, "%lld", jiffies); + return jiffies; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_print_function(tep, + process_jbd2_dev_to_name, + TEP_FUNC_ARG_STRING, + "jbd2_dev_to_name", + TEP_FUNC_ARG_INT, + TEP_FUNC_ARG_VOID); + + tep_register_print_function(tep, + process_jiffies_to_msecs, + TEP_FUNC_ARG_LONG, + "jiffies_to_msecs", + TEP_FUNC_ARG_LONG, + TEP_FUNC_ARG_VOID); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_print_function(tep, process_jbd2_dev_to_name, + "jbd2_dev_to_name"); + + tep_unregister_print_function(tep, process_jiffies_to_msecs, + "jiffies_to_msecs"); +} diff --git a/tools/lib/traceevent/plugins/plugin_kmem.c b/tools/lib/traceevent/plugins/plugin_kmem.c new file mode 100644 index 000000000..4b4f7f961 --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_kmem.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "event-parse.h" +#include "trace-seq.h" + +static int call_site_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct tep_format_field *field; + unsigned long long val, addr; + void *data = record->data; + const char *func; + + field = tep_find_field(event, "call_site"); + if (!field) + return 1; + + if (tep_read_number_field(field, data, &val)) + return 1; + + func = tep_find_function(event->tep, val); + if (!func) + return 1; + + addr = tep_find_function_address(event->tep, val); + + trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr)); + return 1; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_event_handler(tep, -1, "kmem", "kfree", + call_site_handler, NULL); + + tep_register_event_handler(tep, -1, "kmem", "kmalloc", + call_site_handler, NULL); + + tep_register_event_handler(tep, -1, "kmem", "kmalloc_node", + call_site_handler, NULL); + + tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc", + call_site_handler, NULL); + + tep_register_event_handler(tep, -1, "kmem", + "kmem_cache_alloc_node", + call_site_handler, NULL); + + tep_register_event_handler(tep, -1, "kmem", "kmem_cache_free", + call_site_handler, NULL); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_event_handler(tep, -1, "kmem", "kfree", + call_site_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kmem", "kmalloc", + call_site_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kmem", "kmalloc_node", + call_site_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc", + call_site_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kmem", + "kmem_cache_alloc_node", + call_site_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_free", + call_site_handler, NULL); +} diff --git a/tools/lib/traceevent/plugins/plugin_kvm.c b/tools/lib/traceevent/plugins/plugin_kvm.c new file mode 100644 index 000000000..9ce7b4b68 --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_kvm.c @@ -0,0 +1,527 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdint.h> + +#include "event-parse.h" +#include "trace-seq.h" + +#ifdef HAVE_UDIS86 + +#include <udis86.h> + +static ud_t ud; + +static void init_disassembler(void) +{ + ud_init(&ud); + ud_set_syntax(&ud, UD_SYN_ATT); +} + +static const char *disassemble(unsigned char *insn, int len, uint64_t rip, + int cr0_pe, int eflags_vm, + int cs_d, int cs_l) +{ + int mode; + + if (!cr0_pe) + mode = 16; + else if (eflags_vm) + mode = 16; + else if (cs_l) + mode = 64; + else if (cs_d) + mode = 32; + else + mode = 16; + + ud_set_pc(&ud, rip); + ud_set_mode(&ud, mode); + ud_set_input_buffer(&ud, insn, len); + ud_disassemble(&ud); + return ud_insn_asm(&ud); +} + +#else + +static void init_disassembler(void) +{ +} + +static const char *disassemble(unsigned char *insn, int len, uint64_t rip, + int cr0_pe, int eflags_vm, + int cs_d, int cs_l) +{ + static char out[15*3+1]; + int i; + + for (i = 0; i < len; ++i) + sprintf(out + i * 3, "%02x ", insn[i]); + out[len*3-1] = '\0'; + return out; +} + +#endif + + +#define VMX_EXIT_REASONS \ + _ER(EXCEPTION_NMI, 0) \ + _ER(EXTERNAL_INTERRUPT, 1) \ + _ER(TRIPLE_FAULT, 2) \ + _ER(PENDING_INTERRUPT, 7) \ + _ER(NMI_WINDOW, 8) \ + _ER(TASK_SWITCH, 9) \ + _ER(CPUID, 10) \ + _ER(HLT, 12) \ + _ER(INVD, 13) \ + _ER(INVLPG, 14) \ + _ER(RDPMC, 15) \ + _ER(RDTSC, 16) \ + _ER(VMCALL, 18) \ + _ER(VMCLEAR, 19) \ + _ER(VMLAUNCH, 20) \ + _ER(VMPTRLD, 21) \ + _ER(VMPTRST, 22) \ + _ER(VMREAD, 23) \ + _ER(VMRESUME, 24) \ + _ER(VMWRITE, 25) \ + _ER(VMOFF, 26) \ + _ER(VMON, 27) \ + _ER(CR_ACCESS, 28) \ + _ER(DR_ACCESS, 29) \ + _ER(IO_INSTRUCTION, 30) \ + _ER(MSR_READ, 31) \ + _ER(MSR_WRITE, 32) \ + _ER(MWAIT_INSTRUCTION, 36) \ + _ER(MONITOR_INSTRUCTION, 39) \ + _ER(PAUSE_INSTRUCTION, 40) \ + _ER(MCE_DURING_VMENTRY, 41) \ + _ER(TPR_BELOW_THRESHOLD, 43) \ + _ER(APIC_ACCESS, 44) \ + _ER(EOI_INDUCED, 45) \ + _ER(EPT_VIOLATION, 48) \ + _ER(EPT_MISCONFIG, 49) \ + _ER(INVEPT, 50) \ + _ER(PREEMPTION_TIMER, 52) \ + _ER(WBINVD, 54) \ + _ER(XSETBV, 55) \ + _ER(APIC_WRITE, 56) \ + _ER(INVPCID, 58) \ + _ER(PML_FULL, 62) \ + _ER(XSAVES, 63) \ + _ER(XRSTORS, 64) + +#define SVM_EXIT_REASONS \ + _ER(EXIT_READ_CR0, 0x000) \ + _ER(EXIT_READ_CR3, 0x003) \ + _ER(EXIT_READ_CR4, 0x004) \ + _ER(EXIT_READ_CR8, 0x008) \ + _ER(EXIT_WRITE_CR0, 0x010) \ + _ER(EXIT_WRITE_CR3, 0x013) \ + _ER(EXIT_WRITE_CR4, 0x014) \ + _ER(EXIT_WRITE_CR8, 0x018) \ + _ER(EXIT_READ_DR0, 0x020) \ + _ER(EXIT_READ_DR1, 0x021) \ + _ER(EXIT_READ_DR2, 0x022) \ + _ER(EXIT_READ_DR3, 0x023) \ + _ER(EXIT_READ_DR4, 0x024) \ + _ER(EXIT_READ_DR5, 0x025) \ + _ER(EXIT_READ_DR6, 0x026) \ + _ER(EXIT_READ_DR7, 0x027) \ + _ER(EXIT_WRITE_DR0, 0x030) \ + _ER(EXIT_WRITE_DR1, 0x031) \ + _ER(EXIT_WRITE_DR2, 0x032) \ + _ER(EXIT_WRITE_DR3, 0x033) \ + _ER(EXIT_WRITE_DR4, 0x034) \ + _ER(EXIT_WRITE_DR5, 0x035) \ + _ER(EXIT_WRITE_DR6, 0x036) \ + _ER(EXIT_WRITE_DR7, 0x037) \ + _ER(EXIT_EXCP_DE, 0x040) \ + _ER(EXIT_EXCP_DB, 0x041) \ + _ER(EXIT_EXCP_BP, 0x043) \ + _ER(EXIT_EXCP_OF, 0x044) \ + _ER(EXIT_EXCP_BR, 0x045) \ + _ER(EXIT_EXCP_UD, 0x046) \ + _ER(EXIT_EXCP_NM, 0x047) \ + _ER(EXIT_EXCP_DF, 0x048) \ + _ER(EXIT_EXCP_TS, 0x04a) \ + _ER(EXIT_EXCP_NP, 0x04b) \ + _ER(EXIT_EXCP_SS, 0x04c) \ + _ER(EXIT_EXCP_GP, 0x04d) \ + _ER(EXIT_EXCP_PF, 0x04e) \ + _ER(EXIT_EXCP_MF, 0x050) \ + _ER(EXIT_EXCP_AC, 0x051) \ + _ER(EXIT_EXCP_MC, 0x052) \ + _ER(EXIT_EXCP_XF, 0x053) \ + _ER(EXIT_INTR, 0x060) \ + _ER(EXIT_NMI, 0x061) \ + _ER(EXIT_SMI, 0x062) \ + _ER(EXIT_INIT, 0x063) \ + _ER(EXIT_VINTR, 0x064) \ + _ER(EXIT_CR0_SEL_WRITE, 0x065) \ + _ER(EXIT_IDTR_READ, 0x066) \ + _ER(EXIT_GDTR_READ, 0x067) \ + _ER(EXIT_LDTR_READ, 0x068) \ + _ER(EXIT_TR_READ, 0x069) \ + _ER(EXIT_IDTR_WRITE, 0x06a) \ + _ER(EXIT_GDTR_WRITE, 0x06b) \ + _ER(EXIT_LDTR_WRITE, 0x06c) \ + _ER(EXIT_TR_WRITE, 0x06d) \ + _ER(EXIT_RDTSC, 0x06e) \ + _ER(EXIT_RDPMC, 0x06f) \ + _ER(EXIT_PUSHF, 0x070) \ + _ER(EXIT_POPF, 0x071) \ + _ER(EXIT_CPUID, 0x072) \ + _ER(EXIT_RSM, 0x073) \ + _ER(EXIT_IRET, 0x074) \ + _ER(EXIT_SWINT, 0x075) \ + _ER(EXIT_INVD, 0x076) \ + _ER(EXIT_PAUSE, 0x077) \ + _ER(EXIT_HLT, 0x078) \ + _ER(EXIT_INVLPG, 0x079) \ + _ER(EXIT_INVLPGA, 0x07a) \ + _ER(EXIT_IOIO, 0x07b) \ + _ER(EXIT_MSR, 0x07c) \ + _ER(EXIT_TASK_SWITCH, 0x07d) \ + _ER(EXIT_FERR_FREEZE, 0x07e) \ + _ER(EXIT_SHUTDOWN, 0x07f) \ + _ER(EXIT_VMRUN, 0x080) \ + _ER(EXIT_VMMCALL, 0x081) \ + _ER(EXIT_VMLOAD, 0x082) \ + _ER(EXIT_VMSAVE, 0x083) \ + _ER(EXIT_STGI, 0x084) \ + _ER(EXIT_CLGI, 0x085) \ + _ER(EXIT_SKINIT, 0x086) \ + _ER(EXIT_RDTSCP, 0x087) \ + _ER(EXIT_ICEBP, 0x088) \ + _ER(EXIT_WBINVD, 0x089) \ + _ER(EXIT_MONITOR, 0x08a) \ + _ER(EXIT_MWAIT, 0x08b) \ + _ER(EXIT_MWAIT_COND, 0x08c) \ + _ER(EXIT_XSETBV, 0x08d) \ + _ER(EXIT_NPF, 0x400) \ + _ER(EXIT_AVIC_INCOMPLETE_IPI, 0x401) \ + _ER(EXIT_AVIC_UNACCELERATED_ACCESS, 0x402) \ + _ER(EXIT_ERR, -1) + +#define _ER(reason, val) { #reason, val }, +struct str_values { + const char *str; + int val; +}; + +static struct str_values vmx_exit_reasons[] = { + VMX_EXIT_REASONS + { NULL, -1} +}; + +static struct str_values svm_exit_reasons[] = { + SVM_EXIT_REASONS + { NULL, -1} +}; + +static struct isa_exit_reasons { + unsigned isa; + struct str_values *strings; +} isa_exit_reasons[] = { + { .isa = 1, .strings = vmx_exit_reasons }, + { .isa = 2, .strings = svm_exit_reasons }, + { } +}; + +static const char *find_exit_reason(unsigned isa, int val) +{ + struct str_values *strings = NULL; + int i; + + for (i = 0; isa_exit_reasons[i].strings; ++i) + if (isa_exit_reasons[i].isa == isa) { + strings = isa_exit_reasons[i].strings; + break; + } + if (!strings) + return "UNKNOWN-ISA"; + for (i = 0; strings[i].str; i++) + if (strings[i].val == val) + break; + + return strings[i].str; +} + +static int print_exit_reason(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, const char *field) +{ + unsigned long long isa; + unsigned long long val; + const char *reason; + + if (tep_get_field_val(s, event, field, record, &val, 1) < 0) + return -1; + + if (tep_get_field_val(s, event, "isa", record, &isa, 0) < 0) + isa = 1; + + reason = find_exit_reason(isa, val); + if (reason) + trace_seq_printf(s, "reason %s", reason); + else + trace_seq_printf(s, "reason UNKNOWN (%llu)", val); + return 0; +} + +static int kvm_exit_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + unsigned long long info1 = 0, info2 = 0; + + if (print_exit_reason(s, record, event, "exit_reason") < 0) + return -1; + + tep_print_num_field(s, " rip 0x%lx", event, "guest_rip", record, 1); + + if (tep_get_field_val(s, event, "info1", record, &info1, 0) >= 0 + && tep_get_field_val(s, event, "info2", record, &info2, 0) >= 0) + trace_seq_printf(s, " info %llx %llx", info1, info2); + + return 0; +} + +#define KVM_EMUL_INSN_F_CR0_PE (1 << 0) +#define KVM_EMUL_INSN_F_EFL_VM (1 << 1) +#define KVM_EMUL_INSN_F_CS_D (1 << 2) +#define KVM_EMUL_INSN_F_CS_L (1 << 3) + +static int kvm_emulate_insn_handler(struct trace_seq *s, + struct tep_record *record, + struct tep_event *event, void *context) +{ + unsigned long long rip, csbase, len, flags, failed; + int llen; + uint8_t *insn; + const char *disasm; + + if (tep_get_field_val(s, event, "rip", record, &rip, 1) < 0) + return -1; + + if (tep_get_field_val(s, event, "csbase", record, &csbase, 1) < 0) + return -1; + + if (tep_get_field_val(s, event, "len", record, &len, 1) < 0) + return -1; + + if (tep_get_field_val(s, event, "flags", record, &flags, 1) < 0) + return -1; + + if (tep_get_field_val(s, event, "failed", record, &failed, 1) < 0) + return -1; + + insn = tep_get_field_raw(s, event, "insn", record, &llen, 1); + if (!insn) + return -1; + + disasm = disassemble(insn, len, rip, + flags & KVM_EMUL_INSN_F_CR0_PE, + flags & KVM_EMUL_INSN_F_EFL_VM, + flags & KVM_EMUL_INSN_F_CS_D, + flags & KVM_EMUL_INSN_F_CS_L); + + trace_seq_printf(s, "%llx:%llx: %s%s", csbase, rip, disasm, + failed ? " FAIL" : ""); + return 0; +} + + +static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + if (print_exit_reason(s, record, event, "exit_code") < 0) + return -1; + + tep_print_num_field(s, " info1 %llx", event, "exit_info1", record, 1); + tep_print_num_field(s, " info2 %llx", event, "exit_info2", record, 1); + tep_print_num_field(s, " int_info %llx", event, "exit_int_info", record, 1); + tep_print_num_field(s, " int_info_err %llx", event, "exit_int_info_err", record, 1); + + return 0; +} + +static int kvm_nested_vmexit_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + tep_print_num_field(s, "rip %llx ", event, "rip", record, 1); + + return kvm_nested_vmexit_inject_handler(s, record, event, context); +} + +union kvm_mmu_page_role { + unsigned word; + struct { + unsigned level:4; + unsigned cr4_pae:1; + unsigned quadrant:2; + unsigned direct:1; + unsigned access:3; + unsigned invalid:1; + unsigned efer_nx:1; + unsigned cr0_wp:1; + unsigned smep_and_not_wp:1; + unsigned smap_and_not_wp:1; + unsigned pad_for_nice_hex_output:8; + unsigned smm:8; + }; +}; + +static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + unsigned long long val; + static const char *access_str[] = { + "---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux" + }; + union kvm_mmu_page_role role; + + if (tep_get_field_val(s, event, "role", record, &val, 1) < 0) + return -1; + + role.word = (int)val; + + /* + * We can only use the structure if file is of the same + * endianness. + */ + if (tep_is_file_bigendian(event->tep) == + tep_is_local_bigendian(event->tep)) { + + trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s", + role.level, + role.quadrant, + role.direct ? " direct" : "", + access_str[role.access], + role.invalid ? " invalid" : "", + role.cr4_pae ? "" : "!", + role.efer_nx ? "" : "!", + role.cr0_wp ? "" : "!", + role.smep_and_not_wp ? " smep" : "", + role.smap_and_not_wp ? " smap" : "", + role.smm ? " smm" : ""); + } else + trace_seq_printf(s, "WORD: %08x", role.word); + + tep_print_num_field(s, " root %u ", event, + "root_count", record, 1); + + if (tep_get_field_val(s, event, "unsync", record, &val, 1) < 0) + return -1; + + trace_seq_printf(s, "%s%c", val ? "unsync" : "sync", 0); + return 0; +} + +static int kvm_mmu_get_page_handler(struct trace_seq *s, + struct tep_record *record, + struct tep_event *event, void *context) +{ + unsigned long long val; + + if (tep_get_field_val(s, event, "created", record, &val, 1) < 0) + return -1; + + trace_seq_printf(s, "%s ", val ? "new" : "existing"); + + if (tep_get_field_val(s, event, "gfn", record, &val, 1) < 0) + return -1; + + trace_seq_printf(s, "sp gfn %llx ", val); + return kvm_mmu_print_role(s, record, event, context); +} + +#define PT_WRITABLE_SHIFT 1 +#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT) + +static unsigned long long +process_is_writable_pte(struct trace_seq *s, unsigned long long *args) +{ + unsigned long pte = args[0]; + return pte & PT_WRITABLE_MASK; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + init_disassembler(); + + tep_register_event_handler(tep, -1, "kvm", "kvm_exit", + kvm_exit_handler, NULL); + + tep_register_event_handler(tep, -1, "kvm", "kvm_emulate_insn", + kvm_emulate_insn_handler, NULL); + + tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit", + kvm_nested_vmexit_handler, NULL); + + tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject", + kvm_nested_vmexit_inject_handler, NULL); + + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page", + kvm_mmu_get_page_handler, NULL); + + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page", + kvm_mmu_print_role, NULL); + + tep_register_event_handler(tep, -1, + "kvmmmu", "kvm_mmu_unsync_page", + kvm_mmu_print_role, NULL); + + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page", + kvm_mmu_print_role, NULL); + + tep_register_event_handler(tep, -1, "kvmmmu", + "kvm_mmu_prepare_zap_page", kvm_mmu_print_role, + NULL); + + tep_register_print_function(tep, + process_is_writable_pte, + TEP_FUNC_ARG_INT, + "is_writable_pte", + TEP_FUNC_ARG_LONG, + TEP_FUNC_ARG_VOID); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_event_handler(tep, -1, "kvm", "kvm_exit", + kvm_exit_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kvm", "kvm_emulate_insn", + kvm_emulate_insn_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit", + kvm_nested_vmexit_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject", + kvm_nested_vmexit_inject_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page", + kvm_mmu_get_page_handler, NULL); + + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page", + kvm_mmu_print_role, NULL); + + tep_unregister_event_handler(tep, -1, + "kvmmmu", "kvm_mmu_unsync_page", + kvm_mmu_print_role, NULL); + + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page", + kvm_mmu_print_role, NULL); + + tep_unregister_event_handler(tep, -1, "kvmmmu", + "kvm_mmu_prepare_zap_page", kvm_mmu_print_role, + NULL); + + tep_unregister_print_function(tep, process_is_writable_pte, + "is_writable_pte"); +} diff --git a/tools/lib/traceevent/plugins/plugin_mac80211.c b/tools/lib/traceevent/plugins/plugin_mac80211.c new file mode 100644 index 000000000..f48071e3c --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_mac80211.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009 Johannes Berg <johannes@sipsolutions.net> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "event-parse.h" +#include "trace-seq.h" + +#define INDENT 65 + +static void print_string(struct trace_seq *s, struct tep_event *event, + const char *name, const void *data) +{ + struct tep_format_field *f = tep_find_field(event, name); + int offset; + int length; + + if (!f) { + trace_seq_printf(s, "NOTFOUND:%s", name); + return; + } + + offset = f->offset; + length = f->size; + + if (!strncmp(f->type, "__data_loc", 10)) { + unsigned long long v; + if (tep_read_number_field(f, data, &v)) { + trace_seq_printf(s, "invalid_data_loc"); + return; + } + offset = v & 0xffff; + length = v >> 16; + } + + trace_seq_printf(s, "%.*s", length, (char *)data + offset); +} + +#define SF(fn) tep_print_num_field(s, fn ":%d", event, fn, record, 0) +#define SFX(fn) tep_print_num_field(s, fn ":%#x", event, fn, record, 0) +#define SP() trace_seq_putc(s, ' ') + +static int drv_bss_info_changed(struct trace_seq *s, + struct tep_record *record, + struct tep_event *event, void *context) +{ + void *data = record->data; + + print_string(s, event, "wiphy_name", data); + trace_seq_printf(s, " vif:"); + print_string(s, event, "vif_name", data); + tep_print_num_field(s, "(%d)", event, "vif_type", record, 1); + + trace_seq_printf(s, "\n%*s", INDENT, ""); + SF("assoc"); SP(); + SF("aid"); SP(); + SF("cts"); SP(); + SF("shortpre"); SP(); + SF("shortslot"); SP(); + SF("dtimper"); SP(); + trace_seq_printf(s, "\n%*s", INDENT, ""); + SF("bcnint"); SP(); + SFX("assoc_cap"); SP(); + SFX("basic_rates"); SP(); + SF("enable_beacon"); + trace_seq_printf(s, "\n%*s", INDENT, ""); + SF("ht_operation_mode"); + + return 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_event_handler(tep, -1, "mac80211", + "drv_bss_info_changed", + drv_bss_info_changed, NULL); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_event_handler(tep, -1, "mac80211", + "drv_bss_info_changed", + drv_bss_info_changed, NULL); +} diff --git a/tools/lib/traceevent/plugins/plugin_sched_switch.c b/tools/lib/traceevent/plugins/plugin_sched_switch.c new file mode 100644 index 000000000..e12fa1038 --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_sched_switch.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "event-parse.h" +#include "trace-seq.h" + +static void write_state(struct trace_seq *s, int val) +{ + const char states[] = "SDTtZXxW"; + int found = 0; + int i; + + for (i = 0; i < (sizeof(states) - 1); i++) { + if (!(val & (1 << i))) + continue; + + if (found) + trace_seq_putc(s, '|'); + + found = 1; + trace_seq_putc(s, states[i]); + } + + if (!found) + trace_seq_putc(s, 'R'); +} + +static void write_and_save_comm(struct tep_format_field *field, + struct tep_record *record, + struct trace_seq *s, int pid) +{ + const char *comm; + int len; + + comm = (char *)(record->data + field->offset); + len = s->len; + trace_seq_printf(s, "%.*s", + field->size, comm); + + /* make sure the comm has a \0 at the end. */ + trace_seq_terminate(s); + comm = &s->buffer[len]; + + /* Help out the comm to ids. This will handle dups */ + tep_register_comm(field->event->tep, comm, pid); +} + +static int sched_wakeup_handler(struct trace_seq *s, + struct tep_record *record, + struct tep_event *event, void *context) +{ + struct tep_format_field *field; + unsigned long long val; + + if (tep_get_field_val(s, event, "pid", record, &val, 1)) + return trace_seq_putc(s, '!'); + + field = tep_find_any_field(event, "comm"); + if (field) { + write_and_save_comm(field, record, s, val); + trace_seq_putc(s, ':'); + } + trace_seq_printf(s, "%lld", val); + + if (tep_get_field_val(s, event, "prio", record, &val, 0) == 0) + trace_seq_printf(s, " [%lld]", val); + + if (tep_get_field_val(s, event, "success", record, &val, 1) == 0) + trace_seq_printf(s, " success=%lld", val); + + if (tep_get_field_val(s, event, "target_cpu", record, &val, 0) == 0) + trace_seq_printf(s, " CPU:%03llu", val); + + return 0; +} + +static int sched_switch_handler(struct trace_seq *s, + struct tep_record *record, + struct tep_event *event, void *context) +{ + struct tep_format_field *field; + unsigned long long val; + + if (tep_get_field_val(s, event, "prev_pid", record, &val, 1)) + return trace_seq_putc(s, '!'); + + field = tep_find_any_field(event, "prev_comm"); + if (field) { + write_and_save_comm(field, record, s, val); + trace_seq_putc(s, ':'); + } + trace_seq_printf(s, "%lld ", val); + + if (tep_get_field_val(s, event, "prev_prio", record, &val, 0) == 0) + trace_seq_printf(s, "[%d] ", (int) val); + + if (tep_get_field_val(s, event, "prev_state", record, &val, 0) == 0) + write_state(s, val); + + trace_seq_puts(s, " ==> "); + + if (tep_get_field_val(s, event, "next_pid", record, &val, 1)) + return trace_seq_putc(s, '!'); + + field = tep_find_any_field(event, "next_comm"); + if (field) { + write_and_save_comm(field, record, s, val); + trace_seq_putc(s, ':'); + } + trace_seq_printf(s, "%lld", val); + + if (tep_get_field_val(s, event, "next_prio", record, &val, 0) == 0) + trace_seq_printf(s, " [%d]", (int) val); + + return 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_event_handler(tep, -1, "sched", "sched_switch", + sched_switch_handler, NULL); + + tep_register_event_handler(tep, -1, "sched", "sched_wakeup", + sched_wakeup_handler, NULL); + + tep_register_event_handler(tep, -1, "sched", "sched_wakeup_new", + sched_wakeup_handler, NULL); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_event_handler(tep, -1, "sched", "sched_switch", + sched_switch_handler, NULL); + + tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup", + sched_wakeup_handler, NULL); + + tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup_new", + sched_wakeup_handler, NULL); +} diff --git a/tools/lib/traceevent/plugins/plugin_scsi.c b/tools/lib/traceevent/plugins/plugin_scsi.c new file mode 100644 index 000000000..5d0387a4b --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_scsi.c @@ -0,0 +1,434 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> +#include <inttypes.h> +#include "event-parse.h" +#include "trace-seq.h" + +typedef unsigned long sector_t; +typedef uint64_t u64; +typedef unsigned int u32; + +/* + * SCSI opcodes + */ +#define TEST_UNIT_READY 0x00 +#define REZERO_UNIT 0x01 +#define REQUEST_SENSE 0x03 +#define FORMAT_UNIT 0x04 +#define READ_BLOCK_LIMITS 0x05 +#define REASSIGN_BLOCKS 0x07 +#define INITIALIZE_ELEMENT_STATUS 0x07 +#define READ_6 0x08 +#define WRITE_6 0x0a +#define SEEK_6 0x0b +#define READ_REVERSE 0x0f +#define WRITE_FILEMARKS 0x10 +#define SPACE 0x11 +#define INQUIRY 0x12 +#define RECOVER_BUFFERED_DATA 0x14 +#define MODE_SELECT 0x15 +#define RESERVE 0x16 +#define RELEASE 0x17 +#define COPY 0x18 +#define ERASE 0x19 +#define MODE_SENSE 0x1a +#define START_STOP 0x1b +#define RECEIVE_DIAGNOSTIC 0x1c +#define SEND_DIAGNOSTIC 0x1d +#define ALLOW_MEDIUM_REMOVAL 0x1e + +#define READ_FORMAT_CAPACITIES 0x23 +#define SET_WINDOW 0x24 +#define READ_CAPACITY 0x25 +#define READ_10 0x28 +#define WRITE_10 0x2a +#define SEEK_10 0x2b +#define POSITION_TO_ELEMENT 0x2b +#define WRITE_VERIFY 0x2e +#define VERIFY 0x2f +#define SEARCH_HIGH 0x30 +#define SEARCH_EQUAL 0x31 +#define SEARCH_LOW 0x32 +#define SET_LIMITS 0x33 +#define PRE_FETCH 0x34 +#define READ_POSITION 0x34 +#define SYNCHRONIZE_CACHE 0x35 +#define LOCK_UNLOCK_CACHE 0x36 +#define READ_DEFECT_DATA 0x37 +#define MEDIUM_SCAN 0x38 +#define COMPARE 0x39 +#define COPY_VERIFY 0x3a +#define WRITE_BUFFER 0x3b +#define READ_BUFFER 0x3c +#define UPDATE_BLOCK 0x3d +#define READ_LONG 0x3e +#define WRITE_LONG 0x3f +#define CHANGE_DEFINITION 0x40 +#define WRITE_SAME 0x41 +#define UNMAP 0x42 +#define READ_TOC 0x43 +#define READ_HEADER 0x44 +#define GET_EVENT_STATUS_NOTIFICATION 0x4a +#define LOG_SELECT 0x4c +#define LOG_SENSE 0x4d +#define XDWRITEREAD_10 0x53 +#define MODE_SELECT_10 0x55 +#define RESERVE_10 0x56 +#define RELEASE_10 0x57 +#define MODE_SENSE_10 0x5a +#define PERSISTENT_RESERVE_IN 0x5e +#define PERSISTENT_RESERVE_OUT 0x5f +#define VARIABLE_LENGTH_CMD 0x7f +#define REPORT_LUNS 0xa0 +#define SECURITY_PROTOCOL_IN 0xa2 +#define MAINTENANCE_IN 0xa3 +#define MAINTENANCE_OUT 0xa4 +#define MOVE_MEDIUM 0xa5 +#define EXCHANGE_MEDIUM 0xa6 +#define READ_12 0xa8 +#define SERVICE_ACTION_OUT_12 0xa9 +#define WRITE_12 0xaa +#define SERVICE_ACTION_IN_12 0xab +#define WRITE_VERIFY_12 0xae +#define VERIFY_12 0xaf +#define SEARCH_HIGH_12 0xb0 +#define SEARCH_EQUAL_12 0xb1 +#define SEARCH_LOW_12 0xb2 +#define SECURITY_PROTOCOL_OUT 0xb5 +#define READ_ELEMENT_STATUS 0xb8 +#define SEND_VOLUME_TAG 0xb6 +#define WRITE_LONG_2 0xea +#define EXTENDED_COPY 0x83 +#define RECEIVE_COPY_RESULTS 0x84 +#define ACCESS_CONTROL_IN 0x86 +#define ACCESS_CONTROL_OUT 0x87 +#define READ_16 0x88 +#define WRITE_16 0x8a +#define READ_ATTRIBUTE 0x8c +#define WRITE_ATTRIBUTE 0x8d +#define VERIFY_16 0x8f +#define SYNCHRONIZE_CACHE_16 0x91 +#define WRITE_SAME_16 0x93 +#define SERVICE_ACTION_BIDIRECTIONAL 0x9d +#define SERVICE_ACTION_IN_16 0x9e +#define SERVICE_ACTION_OUT_16 0x9f +/* values for service action in */ +#define SAI_READ_CAPACITY_16 0x10 +#define SAI_GET_LBA_STATUS 0x12 +/* values for VARIABLE_LENGTH_CMD service action codes + * see spc4r17 Section D.3.5, table D.7 and D.8 */ +#define VLC_SA_RECEIVE_CREDENTIAL 0x1800 +/* values for maintenance in */ +#define MI_REPORT_IDENTIFYING_INFORMATION 0x05 +#define MI_REPORT_TARGET_PGS 0x0a +#define MI_REPORT_ALIASES 0x0b +#define MI_REPORT_SUPPORTED_OPERATION_CODES 0x0c +#define MI_REPORT_SUPPORTED_TASK_MANAGEMENT_FUNCTIONS 0x0d +#define MI_REPORT_PRIORITY 0x0e +#define MI_REPORT_TIMESTAMP 0x0f +#define MI_MANAGEMENT_PROTOCOL_IN 0x10 +/* value for MI_REPORT_TARGET_PGS ext header */ +#define MI_EXT_HDR_PARAM_FMT 0x20 +/* values for maintenance out */ +#define MO_SET_IDENTIFYING_INFORMATION 0x06 +#define MO_SET_TARGET_PGS 0x0a +#define MO_CHANGE_ALIASES 0x0b +#define MO_SET_PRIORITY 0x0e +#define MO_SET_TIMESTAMP 0x0f +#define MO_MANAGEMENT_PROTOCOL_OUT 0x10 +/* values for variable length command */ +#define XDREAD_32 0x03 +#define XDWRITE_32 0x04 +#define XPWRITE_32 0x06 +#define XDWRITEREAD_32 0x07 +#define READ_32 0x09 +#define VERIFY_32 0x0a +#define WRITE_32 0x0b +#define WRITE_SAME_32 0x0d + +#define SERVICE_ACTION16(cdb) (cdb[1] & 0x1f) +#define SERVICE_ACTION32(cdb) ((cdb[8] << 8) | cdb[9]) + +static const char * +scsi_trace_misc(struct trace_seq *, unsigned char *, int); + +static const char * +scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = p->buffer + p->len; + sector_t lba = 0, txlen = 0; + + lba |= ((cdb[1] & 0x1F) << 16); + lba |= (cdb[2] << 8); + lba |= cdb[3]; + txlen = cdb[4]; + + trace_seq_printf(p, "lba=%llu txlen=%llu", + (unsigned long long)lba, (unsigned long long)txlen); + trace_seq_putc(p, 0); + return ret; +} + +static const char * +scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = p->buffer + p->len; + sector_t lba = 0, txlen = 0; + + lba |= (cdb[2] << 24); + lba |= (cdb[3] << 16); + lba |= (cdb[4] << 8); + lba |= cdb[5]; + txlen |= (cdb[7] << 8); + txlen |= cdb[8]; + + trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u", + (unsigned long long)lba, (unsigned long long)txlen, + cdb[1] >> 5); + + if (cdb[0] == WRITE_SAME) + trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1); + + trace_seq_putc(p, 0); + return ret; +} + +static const char * +scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = p->buffer + p->len; + sector_t lba = 0, txlen = 0; + + lba |= (cdb[2] << 24); + lba |= (cdb[3] << 16); + lba |= (cdb[4] << 8); + lba |= cdb[5]; + txlen |= (cdb[6] << 24); + txlen |= (cdb[7] << 16); + txlen |= (cdb[8] << 8); + txlen |= cdb[9]; + + trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u", + (unsigned long long)lba, (unsigned long long)txlen, + cdb[1] >> 5); + trace_seq_putc(p, 0); + return ret; +} + +static const char * +scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = p->buffer + p->len; + sector_t lba = 0, txlen = 0; + + lba |= ((u64)cdb[2] << 56); + lba |= ((u64)cdb[3] << 48); + lba |= ((u64)cdb[4] << 40); + lba |= ((u64)cdb[5] << 32); + lba |= (cdb[6] << 24); + lba |= (cdb[7] << 16); + lba |= (cdb[8] << 8); + lba |= cdb[9]; + txlen |= (cdb[10] << 24); + txlen |= (cdb[11] << 16); + txlen |= (cdb[12] << 8); + txlen |= cdb[13]; + + trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u", + (unsigned long long)lba, (unsigned long long)txlen, + cdb[1] >> 5); + + if (cdb[0] == WRITE_SAME_16) + trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1); + + trace_seq_putc(p, 0); + return ret; +} + +static const char * +scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = p->buffer + p->len, *cmd; + sector_t lba = 0, txlen = 0; + u32 ei_lbrt = 0; + + switch (SERVICE_ACTION32(cdb)) { + case READ_32: + cmd = "READ"; + break; + case VERIFY_32: + cmd = "VERIFY"; + break; + case WRITE_32: + cmd = "WRITE"; + break; + case WRITE_SAME_32: + cmd = "WRITE_SAME"; + break; + default: + trace_seq_printf(p, "UNKNOWN"); + goto out; + } + + lba |= ((u64)cdb[12] << 56); + lba |= ((u64)cdb[13] << 48); + lba |= ((u64)cdb[14] << 40); + lba |= ((u64)cdb[15] << 32); + lba |= (cdb[16] << 24); + lba |= (cdb[17] << 16); + lba |= (cdb[18] << 8); + lba |= cdb[19]; + ei_lbrt |= (cdb[20] << 24); + ei_lbrt |= (cdb[21] << 16); + ei_lbrt |= (cdb[22] << 8); + ei_lbrt |= cdb[23]; + txlen |= (cdb[28] << 24); + txlen |= (cdb[29] << 16); + txlen |= (cdb[30] << 8); + txlen |= cdb[31]; + + trace_seq_printf(p, "%s_32 lba=%llu txlen=%llu protect=%u ei_lbrt=%u", + cmd, (unsigned long long)lba, + (unsigned long long)txlen, cdb[10] >> 5, ei_lbrt); + + if (SERVICE_ACTION32(cdb) == WRITE_SAME_32) + trace_seq_printf(p, " unmap=%u", cdb[10] >> 3 & 1); + +out: + trace_seq_putc(p, 0); + return ret; +} + +static const char * +scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = p->buffer + p->len; + unsigned int regions = cdb[7] << 8 | cdb[8]; + + trace_seq_printf(p, "regions=%u", (regions - 8) / 16); + trace_seq_putc(p, 0); + return ret; +} + +static const char * +scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = p->buffer + p->len, *cmd; + sector_t lba = 0; + u32 alloc_len = 0; + + switch (SERVICE_ACTION16(cdb)) { + case SAI_READ_CAPACITY_16: + cmd = "READ_CAPACITY_16"; + break; + case SAI_GET_LBA_STATUS: + cmd = "GET_LBA_STATUS"; + break; + default: + trace_seq_printf(p, "UNKNOWN"); + goto out; + } + + lba |= ((u64)cdb[2] << 56); + lba |= ((u64)cdb[3] << 48); + lba |= ((u64)cdb[4] << 40); + lba |= ((u64)cdb[5] << 32); + lba |= (cdb[6] << 24); + lba |= (cdb[7] << 16); + lba |= (cdb[8] << 8); + lba |= cdb[9]; + alloc_len |= (cdb[10] << 24); + alloc_len |= (cdb[11] << 16); + alloc_len |= (cdb[12] << 8); + alloc_len |= cdb[13]; + + trace_seq_printf(p, "%s lba=%llu alloc_len=%u", cmd, + (unsigned long long)lba, alloc_len); + +out: + trace_seq_putc(p, 0); + return ret; +} + +static const char * +scsi_trace_varlen(struct trace_seq *p, unsigned char *cdb, int len) +{ + switch (SERVICE_ACTION32(cdb)) { + case READ_32: + case VERIFY_32: + case WRITE_32: + case WRITE_SAME_32: + return scsi_trace_rw32(p, cdb, len); + default: + return scsi_trace_misc(p, cdb, len); + } +} + +static const char * +scsi_trace_misc(struct trace_seq *p, unsigned char *cdb, int len) +{ + const char *ret = p->buffer + p->len; + + trace_seq_printf(p, "-"); + trace_seq_putc(p, 0); + return ret; +} + +const char * +scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len) +{ + switch (cdb[0]) { + case READ_6: + case WRITE_6: + return scsi_trace_rw6(p, cdb, len); + case READ_10: + case VERIFY: + case WRITE_10: + case WRITE_SAME: + return scsi_trace_rw10(p, cdb, len); + case READ_12: + case VERIFY_12: + case WRITE_12: + return scsi_trace_rw12(p, cdb, len); + case READ_16: + case VERIFY_16: + case WRITE_16: + case WRITE_SAME_16: + return scsi_trace_rw16(p, cdb, len); + case UNMAP: + return scsi_trace_unmap(p, cdb, len); + case SERVICE_ACTION_IN_16: + return scsi_trace_service_action_in(p, cdb, len); + case VARIABLE_LENGTH_CMD: + return scsi_trace_varlen(p, cdb, len); + default: + return scsi_trace_misc(p, cdb, len); + } +} + +unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s, + unsigned long long *args) +{ + scsi_trace_parse_cdb(s, (unsigned char *) (unsigned long) args[1], args[2]); + return 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_print_function(tep, + process_scsi_trace_parse_cdb, + TEP_FUNC_ARG_STRING, + "scsi_trace_parse_cdb", + TEP_FUNC_ARG_PTR, + TEP_FUNC_ARG_PTR, + TEP_FUNC_ARG_INT, + TEP_FUNC_ARG_VOID); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_print_function(tep, process_scsi_trace_parse_cdb, + "scsi_trace_parse_cdb"); +} diff --git a/tools/lib/traceevent/plugins/plugin_tlb.c b/tools/lib/traceevent/plugins/plugin_tlb.c new file mode 100644 index 000000000..43657fb60 --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_tlb.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2015 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "event-parse.h" + +enum tlb_flush_reason { + TLB_FLUSH_ON_TASK_SWITCH, + TLB_REMOTE_SHOOTDOWN, + TLB_LOCAL_SHOOTDOWN, + TLB_LOCAL_MM_SHOOTDOWN, + NR_TLB_FLUSH_REASONS, +}; + +static int tlb_flush_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + unsigned long long val; + + trace_seq_printf(s, "pages="); + + tep_print_num_field(s, "%ld", event, "pages", record, 1); + + if (tep_get_field_val(s, event, "reason", record, &val, 1) < 0) + return -1; + + trace_seq_puts(s, " reason="); + + switch (val) { + case TLB_FLUSH_ON_TASK_SWITCH: + trace_seq_puts(s, "flush on task switch"); + break; + case TLB_REMOTE_SHOOTDOWN: + trace_seq_puts(s, "remote shootdown"); + break; + case TLB_LOCAL_SHOOTDOWN: + trace_seq_puts(s, "local shootdown"); + break; + case TLB_LOCAL_MM_SHOOTDOWN: + trace_seq_puts(s, "local mm shootdown"); + break; + } + + trace_seq_printf(s, " (%lld)", val); + + return 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_event_handler(tep, -1, "tlb", "tlb_flush", + tlb_flush_handler, NULL); + + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_event_handler(tep, -1, + "tlb", "tlb_flush", + tlb_flush_handler, NULL); +} diff --git a/tools/lib/traceevent/plugins/plugin_xen.c b/tools/lib/traceevent/plugins/plugin_xen.c new file mode 100644 index 000000000..993b208d0 --- /dev/null +++ b/tools/lib/traceevent/plugins/plugin_xen.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include "event-parse.h" +#include "trace-seq.h" + +#define __HYPERVISOR_set_trap_table 0 +#define __HYPERVISOR_mmu_update 1 +#define __HYPERVISOR_set_gdt 2 +#define __HYPERVISOR_stack_switch 3 +#define __HYPERVISOR_set_callbacks 4 +#define __HYPERVISOR_fpu_taskswitch 5 +#define __HYPERVISOR_sched_op_compat 6 +#define __HYPERVISOR_dom0_op 7 +#define __HYPERVISOR_set_debugreg 8 +#define __HYPERVISOR_get_debugreg 9 +#define __HYPERVISOR_update_descriptor 10 +#define __HYPERVISOR_memory_op 12 +#define __HYPERVISOR_multicall 13 +#define __HYPERVISOR_update_va_mapping 14 +#define __HYPERVISOR_set_timer_op 15 +#define __HYPERVISOR_event_channel_op_compat 16 +#define __HYPERVISOR_xen_version 17 +#define __HYPERVISOR_console_io 18 +#define __HYPERVISOR_physdev_op_compat 19 +#define __HYPERVISOR_grant_table_op 20 +#define __HYPERVISOR_vm_assist 21 +#define __HYPERVISOR_update_va_mapping_otherdomain 22 +#define __HYPERVISOR_iret 23 /* x86 only */ +#define __HYPERVISOR_vcpu_op 24 +#define __HYPERVISOR_set_segment_base 25 /* x86/64 only */ +#define __HYPERVISOR_mmuext_op 26 +#define __HYPERVISOR_acm_op 27 +#define __HYPERVISOR_nmi_op 28 +#define __HYPERVISOR_sched_op 29 +#define __HYPERVISOR_callback_op 30 +#define __HYPERVISOR_xenoprof_op 31 +#define __HYPERVISOR_event_channel_op 32 +#define __HYPERVISOR_physdev_op 33 +#define __HYPERVISOR_hvm_op 34 +#define __HYPERVISOR_tmem_op 38 + +/* Architecture-specific hypercall definitions. */ +#define __HYPERVISOR_arch_0 48 +#define __HYPERVISOR_arch_1 49 +#define __HYPERVISOR_arch_2 50 +#define __HYPERVISOR_arch_3 51 +#define __HYPERVISOR_arch_4 52 +#define __HYPERVISOR_arch_5 53 +#define __HYPERVISOR_arch_6 54 +#define __HYPERVISOR_arch_7 55 + +#define N(x) [__HYPERVISOR_##x] = "("#x")" +static const char *xen_hypercall_names[] = { + N(set_trap_table), + N(mmu_update), + N(set_gdt), + N(stack_switch), + N(set_callbacks), + N(fpu_taskswitch), + N(sched_op_compat), + N(dom0_op), + N(set_debugreg), + N(get_debugreg), + N(update_descriptor), + N(memory_op), + N(multicall), + N(update_va_mapping), + N(set_timer_op), + N(event_channel_op_compat), + N(xen_version), + N(console_io), + N(physdev_op_compat), + N(grant_table_op), + N(vm_assist), + N(update_va_mapping_otherdomain), + N(iret), + N(vcpu_op), + N(set_segment_base), + N(mmuext_op), + N(acm_op), + N(nmi_op), + N(sched_op), + N(callback_op), + N(xenoprof_op), + N(event_channel_op), + N(physdev_op), + N(hvm_op), + +/* Architecture-specific hypercall definitions. */ + N(arch_0), + N(arch_1), + N(arch_2), + N(arch_3), + N(arch_4), + N(arch_5), + N(arch_6), + N(arch_7), +}; +#undef N + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +static const char *xen_hypercall_name(unsigned op) +{ + if (op < ARRAY_SIZE(xen_hypercall_names) && + xen_hypercall_names[op] != NULL) + return xen_hypercall_names[op]; + + return ""; +} + +unsigned long long process_xen_hypercall_name(struct trace_seq *s, + unsigned long long *args) +{ + unsigned int op = args[0]; + + trace_seq_printf(s, "%s", xen_hypercall_name(op)); + return 0; +} + +int TEP_PLUGIN_LOADER(struct tep_handle *tep) +{ + tep_register_print_function(tep, + process_xen_hypercall_name, + TEP_FUNC_ARG_STRING, + "xen_hypercall_name", + TEP_FUNC_ARG_INT, + TEP_FUNC_ARG_VOID); + return 0; +} + +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) +{ + tep_unregister_print_function(tep, process_xen_hypercall_name, + "xen_hypercall_name"); +} diff --git a/tools/lib/traceevent/tep_strerror.c b/tools/lib/traceevent/tep_strerror.c new file mode 100644 index 000000000..4ac26445b --- /dev/null +++ b/tools/lib/traceevent/tep_strerror.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: LGPL-2.1 +#undef _GNU_SOURCE +#include <string.h> +#include <stdio.h> + +#include "event-parse.h" + +#undef _PE +#define _PE(code, str) str +static const char * const tep_error_str[] = { + TEP_ERRORS +}; +#undef _PE + +/* + * The tools so far have been using the strerror_r() GNU variant, that returns + * a string, be it the buffer passed or something else. + * + * But that, besides being tricky in cases where we expect that the function + * using strerror_r() returns the error formatted in a provided buffer (we have + * to check if it returned something else and copy that instead), breaks the + * build on systems not using glibc, like Alpine Linux, where musl libc is + * used. + * + * So, introduce yet another wrapper, str_error_r(), that has the GNU + * interface, but uses the portable XSI variant of strerror_r(), so that users + * rest asured that the provided buffer is used and it is what is returned. + */ +int tep_strerror(struct tep_handle *tep __maybe_unused, + enum tep_errno errnum, char *buf, size_t buflen) +{ + const char *msg; + int idx; + + if (!buflen) + return 0; + + if (errnum >= 0) { + int err = strerror_r(errnum, buf, buflen); + buf[buflen - 1] = 0; + return err; + } + + if (errnum <= __TEP_ERRNO__START || + errnum >= __TEP_ERRNO__END) + return -1; + + idx = errnum - __TEP_ERRNO__START - 1; + msg = tep_error_str[idx]; + snprintf(buf, buflen, "%s", msg); + + return 0; +} diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c new file mode 100644 index 000000000..8d5ecd2bf --- /dev/null +++ b/tools/lib/traceevent/trace-seq.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ +#include "trace-seq.h" + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdarg.h> + +#include <asm/bug.h> +#include "event-parse.h" +#include "event-utils.h" + +/* + * The TRACE_SEQ_POISON is to catch the use of using + * a trace_seq structure after it was destroyed. + */ +#define TRACE_SEQ_POISON ((void *)0xdeadbeef) +#define TRACE_SEQ_CHECK(s) \ +do { \ + if (WARN_ONCE((s)->buffer == TRACE_SEQ_POISON, \ + "Usage of trace_seq after it was destroyed")) \ + (s)->state = TRACE_SEQ__BUFFER_POISONED; \ +} while (0) + +#define TRACE_SEQ_CHECK_RET_N(s, n) \ +do { \ + TRACE_SEQ_CHECK(s); \ + if ((s)->state != TRACE_SEQ__GOOD) \ + return n; \ +} while (0) + +#define TRACE_SEQ_CHECK_RET(s) TRACE_SEQ_CHECK_RET_N(s, ) +#define TRACE_SEQ_CHECK_RET0(s) TRACE_SEQ_CHECK_RET_N(s, 0) + +/** + * trace_seq_init - initialize the trace_seq structure + * @s: a pointer to the trace_seq structure to initialize + */ +void trace_seq_init(struct trace_seq *s) +{ + s->len = 0; + s->readpos = 0; + s->buffer_size = TRACE_SEQ_BUF_SIZE; + s->buffer = malloc(s->buffer_size); + if (s->buffer != NULL) + s->state = TRACE_SEQ__GOOD; + else + s->state = TRACE_SEQ__MEM_ALLOC_FAILED; +} + +/** + * trace_seq_reset - re-initialize the trace_seq structure + * @s: a pointer to the trace_seq structure to reset + */ +void trace_seq_reset(struct trace_seq *s) +{ + if (!s) + return; + TRACE_SEQ_CHECK(s); + s->len = 0; + s->readpos = 0; +} + +/** + * trace_seq_destroy - free up memory of a trace_seq + * @s: a pointer to the trace_seq to free the buffer + * + * Only frees the buffer, not the trace_seq struct itself. + */ +void trace_seq_destroy(struct trace_seq *s) +{ + if (!s) + return; + TRACE_SEQ_CHECK_RET(s); + free(s->buffer); + s->buffer = TRACE_SEQ_POISON; +} + +static void expand_buffer(struct trace_seq *s) +{ + char *buf; + + buf = realloc(s->buffer, s->buffer_size + TRACE_SEQ_BUF_SIZE); + if (WARN_ONCE(!buf, "Can't allocate trace_seq buffer memory")) { + s->state = TRACE_SEQ__MEM_ALLOC_FAILED; + return; + } + + s->buffer = buf; + s->buffer_size += TRACE_SEQ_BUF_SIZE; +} + +/** + * trace_seq_printf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * It returns 0 if the trace oversizes the buffer's free + * space, the number of characters printed, or a negative + * value in case of an error. + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + */ +int +trace_seq_printf(struct trace_seq *s, const char *fmt, ...) +{ + va_list ap; + int len; + int ret; + + try_again: + TRACE_SEQ_CHECK_RET0(s); + + len = (s->buffer_size - 1) - s->len; + + va_start(ap, fmt); + ret = vsnprintf(s->buffer + s->len, len, fmt, ap); + va_end(ap); + + if (ret >= len) { + expand_buffer(s); + goto try_again; + } + + if (ret > 0) + s->len += ret; + + return ret; +} + +/** + * trace_seq_vprintf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * It returns 0 if the trace oversizes the buffer's free + * space, the number of characters printed, or a negative + * value in case of an error. + * * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + */ +int +trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args) +{ + int len; + int ret; + + try_again: + TRACE_SEQ_CHECK_RET0(s); + + len = (s->buffer_size - 1) - s->len; + + ret = vsnprintf(s->buffer + s->len, len, fmt, args); + + if (ret >= len) { + expand_buffer(s); + goto try_again; + } + + if (ret > 0) + s->len += ret; + + return ret; +} + +/** + * trace_seq_puts - trace sequence printing of simple string + * @s: trace sequence descriptor + * @str: simple string to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple string + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + */ +int trace_seq_puts(struct trace_seq *s, const char *str) +{ + int len; + + TRACE_SEQ_CHECK_RET0(s); + + len = strlen(str); + + while (len > ((s->buffer_size - 1) - s->len)) + expand_buffer(s); + + TRACE_SEQ_CHECK_RET0(s); + + memcpy(s->buffer + s->len, str, len); + s->len += len; + + return len; +} + +int trace_seq_putc(struct trace_seq *s, unsigned char c) +{ + TRACE_SEQ_CHECK_RET0(s); + + while (s->len >= (s->buffer_size - 1)) + expand_buffer(s); + + TRACE_SEQ_CHECK_RET0(s); + + s->buffer[s->len++] = c; + + return 1; +} + +void trace_seq_terminate(struct trace_seq *s) +{ + TRACE_SEQ_CHECK_RET(s); + + /* There's always one character left on the buffer */ + s->buffer[s->len] = 0; +} + +int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp) +{ + TRACE_SEQ_CHECK(s); + + switch (s->state) { + case TRACE_SEQ__GOOD: + return fprintf(fp, "%.*s", s->len, s->buffer); + case TRACE_SEQ__BUFFER_POISONED: + fprintf(fp, "%s\n", "Usage of trace_seq after it was destroyed"); + break; + case TRACE_SEQ__MEM_ALLOC_FAILED: + fprintf(fp, "%s\n", "Can't allocate trace_seq buffer memory"); + break; + } + return -1; +} + +int trace_seq_do_printf(struct trace_seq *s) +{ + return trace_seq_do_fprintf(s, stdout); +} diff --git a/tools/lib/traceevent/trace-seq.h b/tools/lib/traceevent/trace-seq.h new file mode 100644 index 000000000..d68ec69f8 --- /dev/null +++ b/tools/lib/traceevent/trace-seq.h @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ + +#ifndef _TRACE_SEQ_H +#define _TRACE_SEQ_H + +#include <stdarg.h> +#include <stdio.h> + +/* ----------------------- trace_seq ----------------------- */ + +#ifndef TRACE_SEQ_BUF_SIZE +#define TRACE_SEQ_BUF_SIZE 4096 +#endif + +enum trace_seq_fail { + TRACE_SEQ__GOOD, + TRACE_SEQ__BUFFER_POISONED, + TRACE_SEQ__MEM_ALLOC_FAILED, +}; + +/* + * Trace sequences are used to allow a function to call several other functions + * to create a string of data to use (up to a max of PAGE_SIZE). + */ + +struct trace_seq { + char *buffer; + unsigned int buffer_size; + unsigned int len; + unsigned int readpos; + enum trace_seq_fail state; +}; + +void trace_seq_init(struct trace_seq *s); +void trace_seq_reset(struct trace_seq *s); +void trace_seq_destroy(struct trace_seq *s); + +extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...) + __attribute__ ((format (printf, 2, 3))); +extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args) + __attribute__ ((format (printf, 2, 0))); + +extern int trace_seq_puts(struct trace_seq *s, const char *str); +extern int trace_seq_putc(struct trace_seq *s, unsigned char c); + +extern void trace_seq_terminate(struct trace_seq *s); + +extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp); +extern int trace_seq_do_printf(struct trace_seq *s); + +#endif /* _TRACE_SEQ_H */ diff --git a/tools/lib/vsprintf.c b/tools/lib/vsprintf.c new file mode 100644 index 000000000..8780b4cda --- /dev/null +++ b/tools/lib/vsprintf.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <sys/types.h> +#include <linux/kernel.h> +#include <stdio.h> + +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) +{ + int i = vsnprintf(buf, size, fmt, args); + ssize_t ssize = size; + + return (i >= ssize) ? (ssize - 1) : i; +} + +int scnprintf(char * buf, size_t size, const char * fmt, ...) +{ + ssize_t ssize = size; + va_list args; + int i; + + va_start(args, fmt); + i = vsnprintf(buf, size, fmt, args); + va_end(args); + + return (i >= ssize) ? (ssize - 1) : i; +} + +int scnprintf_pad(char * buf, size_t size, const char * fmt, ...) +{ + ssize_t ssize = size; + va_list args; + int i; + + va_start(args, fmt); + i = vscnprintf(buf, size, fmt, args); + va_end(args); + + if (i < (int) size) { + for (; i < (int) size; i++) + buf[i] = ' '; + buf[i] = 0x0; + } + + return (i >= ssize) ? (ssize - 1) : i; +} diff --git a/tools/lib/zalloc.c b/tools/lib/zalloc.c new file mode 100644 index 000000000..9c856d59f --- /dev/null +++ b/tools/lib/zalloc.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: LGPL-2.1 + +#include <stdlib.h> +#include <linux/zalloc.h> + +void *zalloc(size_t size) +{ + return calloc(1, size); +} + +void __zfree(void **ptr) +{ + free(*ptr); + *ptr = NULL; +} |