Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2a1dbf5..b337d6f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -18,11 +18,13 @@
#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>
@@ -33,6 +35,7 @@
#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>
@@ -40,9 +43,10 @@
#include <sys/types.h>
#include <sys/vfs.h>
#include <sys/utsname.h>
-#include <tools/libc_compat.h>
+#include <sys/resource.h>
#include <libelf.h>
#include <gelf.h>
+#include <zlib.h>
#include "libbpf.h"
#include "bpf.h"
@@ -59,6 +63,8 @@
#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.
*/
@@ -66,6 +72,10 @@
#define __printf(a, b) __attribute__((format(printf, a, b)))
+static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+
static int __base_pr(enum libbpf_print_level level, const char *format,
va_list args)
{
@@ -98,15 +108,34 @@
va_end(args);
}
+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
-#define CHECK_ERR(action, err, out) do { \
- err = action; \
- if (err) \
- goto out; \
-} while(0)
-
-
/* Copied from tools/perf/util/util.h */
#ifndef zfree
# define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
@@ -121,26 +150,67 @@
___err; })
#endif
-#ifdef HAVE_LIBELF_MMAP_SUPPORT
-# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP
-#else
-# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
-#endif
-
static inline __u64 ptr_to_u64(const void *ptr)
{
return (__u64) (unsigned long) ptr;
}
-struct bpf_capabilities {
+enum kern_feature_id {
/* v4.14: kernel support for program & map names. */
- __u32 name:1;
+ FEAT_PROG_NAME,
/* v5.2: kernel support for global data sections. */
- __u32 global_data:1;
+ FEAT_GLOBAL_DATA,
+ /* BTF support */
+ FEAT_BTF,
/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
- __u32 btf_func:1;
+ FEAT_BTF_FUNC,
/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
- __u32 btf_datasec:1;
+ 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,
+ __FEAT_CNT,
+};
+
+static bool kernel_supports(enum kern_feature_id feat_id);
+
+enum reloc_type {
+ RELO_LD64,
+ RELO_CALL,
+ RELO_DATA,
+ RELO_EXTERN,
+};
+
+struct reloc_desc {
+ enum reloc_type type;
+ int insn_idx;
+ int map_idx;
+ int sym_off;
+ bool processed;
+};
+
+struct bpf_sec_def;
+
+typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec,
+ struct bpf_program *prog);
+
+struct bpf_sec_def {
+ const char *sec;
+ size_t len;
+ enum bpf_prog_type prog_type;
+ enum bpf_attach_type expected_attach_type;
+ bool is_exp_attach_type_optional;
+ bool is_attachable;
+ bool is_attach_btf;
+ bool is_sleepable;
+ attach_fn_t attach_fn;
};
/*
@@ -148,31 +218,47 @@
* linux/filter.h.
*/
struct bpf_program {
- /* Index in elf obj file, for relocation use. */
- int idx;
+ const struct bpf_sec_def *sec_def;
+ char *sec_name;
+ size_t sec_idx;
+ /* 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;
+
char *name;
- int prog_ifindex;
- char *section_name;
- /* section_name with / replaced by _; makes recursive pinning
+ /* sec_name with / replaced by _; makes recursive pinning
* in bpf_object__pin_programs easier
*/
char *pin_name;
- struct bpf_insn *insns;
- size_t insns_cnt, main_prog_cnt;
- enum bpf_prog_type type;
- struct reloc_desc {
- enum {
- RELO_LD64,
- RELO_CALL,
- RELO_DATA,
- } type;
- int insn_idx;
- union {
- int map_idx;
- int text_off;
- };
- } *reloc_desc;
+ /* 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;
int log_level;
@@ -186,50 +272,132 @@
void *priv;
bpf_program_clear_priv_t clear_priv;
+ bool load;
+ enum bpf_prog_type type;
enum bpf_attach_type expected_attach_type;
+ int prog_ifindex;
+ __u32 attach_btf_id;
+ __u32 attach_prog_fd;
void *func_info;
__u32 func_info_rec_size;
__u32 func_info_cnt;
- struct bpf_capabilities *caps;
-
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,
};
static const char * const libbpf_type_to_btf_name[] = {
- [LIBBPF_MAP_DATA] = ".data",
- [LIBBPF_MAP_BSS] = ".bss",
- [LIBBPF_MAP_RODATA] = ".rodata",
+ [LIBBPF_MAP_DATA] = DATA_SEC,
+ [LIBBPF_MAP_BSS] = BSS_SEC,
+ [LIBBPF_MAP_RODATA] = RODATA_SEC,
+ [LIBBPF_MAP_KCONFIG] = KCONFIG_SEC,
};
struct bpf_map {
- int fd;
char *name;
+ int fd;
int sec_idx;
size_t sec_offset;
int map_ifindex;
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;
void *priv;
bpf_map_clear_priv_t clear_priv;
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;
};
-struct bpf_secdata {
- void *rodata;
- void *data;
+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 vmlinux_btf_id;
+
+ /* local btf_id of the ksym extern's type. */
+ __u32 type_id;
+ } ksym;
+ };
};
static LIST_HEAD(bpf_objects_list);
@@ -244,10 +412,15 @@
struct bpf_map *maps;
size_t nr_maps;
size_t maps_cap;
- struct bpf_secdata sections;
+
+ char *kconfig;
+ struct extern_desc *externs;
+ int nr_extern;
+ int kconfig_map_idx;
+ int rodata_map_idx;
bool loaded;
- bool has_pseudo_calls;
+ bool has_subcalls;
/*
* Information when doing elf related work. Only valid if fd
@@ -255,7 +428,7 @@
*/
struct {
int fd;
- void *obj_buf;
+ const void *obj_buf;
size_t obj_buf_sz;
Elf *elf;
GElf_Ehdr ehdr;
@@ -263,18 +436,23 @@
Elf_Data *data;
Elf_Data *rodata;
Elf_Data *bss;
+ Elf_Data *st_ops_data;
+ size_t shstrndx; /* section index for section name strings */
size_t strtabidx;
struct {
GElf_Shdr shdr;
Elf_Data *data;
- } *reloc;
- int nr_reloc;
+ } *reloc_sects;
+ int nr_reloc_sects;
int maps_shndx;
int btf_maps_shndx;
+ __u32 btf_maps_sec_btf_id;
int text_shndx;
+ int symbols_shndx;
int data_shndx;
int rodata_shndx;
int bss_shndx;
+ int st_ops_shndx;
} efile;
/*
* All loaded bpf_object is linked in a list, which is
@@ -284,17 +462,29 @@
struct list_head list;
struct btf *btf;
+ /* Parse and load BTF vmlinux if any of the programs in the object need
+ * it at load time.
+ */
+ struct btf *btf_vmlinux;
struct btf_ext *btf_ext;
void *priv;
bpf_object_clear_priv_t clear_priv;
- struct bpf_capabilities caps;
-
char path[];
};
#define obj_elf_valid(o) ((o)->efile.elf)
+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 int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr);
+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 int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx,
+ size_t off, __u32 sym_type, GElf_Sym *sym);
+
void bpf_program__unload(struct bpf_program *prog)
{
int i;
@@ -310,8 +500,8 @@
for (i = 0; i < prog->instances.nr; i++)
zclose(prog->instances.fds[i]);
} else if (prog->instances.nr != -1) {
- pr_warning("Internal error: instances.nr is %d\n",
- prog->instances.nr);
+ pr_warn("Internal error: instances.nr is %d\n",
+ prog->instances.nr);
}
prog->instances.nr = -1;
@@ -334,182 +524,535 @@
bpf_program__unload(prog);
zfree(&prog->name);
- zfree(&prog->section_name);
+ zfree(&prog->sec_name);
zfree(&prog->pin_name);
zfree(&prog->insns);
zfree(&prog->reloc_desc);
prog->nr_reloc = 0;
prog->insns_cnt = 0;
- prog->idx = -1;
+ prog->sec_idx = -1;
}
static char *__bpf_program__pin_name(struct bpf_program *prog)
{
char *name, *p;
- name = p = strdup(prog->section_name);
+ name = p = strdup(prog->sec_name);
while ((p = strchr(p, '/')))
*p = '_';
return name;
}
-static int
-bpf_program__init(void *data, size_t size, char *section_name, int idx,
- struct bpf_program *prog)
+static bool insn_is_subprog_call(const struct bpf_insn *insn)
{
- const size_t bpf_insn_sz = sizeof(struct bpf_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;
+}
- if (size == 0 || size % bpf_insn_sz) {
- pr_warning("corrupted section '%s', size: %zu\n",
- section_name, size);
+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->section_name = strdup(section_name);
- if (!prog->section_name) {
- pr_warning("failed to alloc name for prog under section(%d) %s\n",
- idx, section_name);
- goto errout;
- }
+ 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->pin_name = __bpf_program__pin_name(prog);
- if (!prog->pin_name) {
- pr_warning("failed to alloc pin name for prog under section(%d) %s\n",
- idx, section_name);
- goto errout;
- }
+ prog->type = BPF_PROG_TYPE_UNSPEC;
+ prog->load = true;
- prog->insns = malloc(size);
- if (!prog->insns) {
- pr_warning("failed to alloc insns for prog under section %s\n",
- section_name);
- goto errout;
- }
- prog->insns_cnt = size / bpf_insn_sz;
- memcpy(prog->insns, data, size);
- prog->idx = idx;
prog->instances.fds = NULL;
prog->instances.nr = -1;
- prog->type = BPF_PROG_TYPE_UNSPEC;
+
+ prog->sec_name = strdup(sec_name);
+ if (!prog->sec_name)
+ goto errout;
+
+ prog->name = strdup(name);
+ if (!prog->name)
+ goto errout;
+
+ prog->pin_name = __bpf_program__pin_name(prog);
+ if (!prog->pin_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_program(struct bpf_object *obj, void *data, size_t size,
- char *section_name, int idx)
+bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
+ const char *sec_name, int sec_idx)
{
- struct bpf_program prog, *progs;
+ struct bpf_program *prog, *progs;
+ void *data = sec_data->d_buf;
+ size_t sec_sz = sec_data->d_size, sec_off, prog_sz;
int nr_progs, err;
+ const char *name;
+ GElf_Sym sym;
- err = bpf_program__init(data, size, section_name, idx, &prog);
- if (err)
- return err;
-
- prog.caps = &obj->caps;
progs = obj->programs;
nr_progs = obj->nr_programs;
+ sec_off = 0;
- progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
- if (!progs) {
- /*
- * In this case the original obj->programs
- * is still valid, so don't need special treat for
- * bpf_close_object().
- */
- pr_warning("failed to alloc a new program under section '%s'\n",
- section_name);
- bpf_program__exit(&prog);
- return -ENOMEM;
+ while (sec_off < sec_sz) {
+ if (elf_sym_by_sec_off(obj, sec_idx, sec_off, STT_FUNC, &sym)) {
+ pr_warn("sec '%s': failed to find program symbol at offset %zu\n",
+ sec_name, sec_off);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ prog_sz = sym.st_size;
+
+ 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;
+ }
+
+ 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;
+
+ nr_progs++;
+ obj->nr_programs = nr_progs;
+
+ sec_off += prog_sz;
}
- pr_debug("found program %s\n", prog.section_name);
- obj->programs = progs;
- obj->nr_programs = nr_progs + 1;
- prog.obj = obj;
- progs[nr_progs] = prog;
return 0;
}
-static int
-bpf_object__init_prog_names(struct bpf_object *obj)
+static __u32 get_kernel_version(void)
{
- Elf_Data *symbols = obj->efile.symbols;
- struct bpf_program *prog;
- size_t pi, si;
+ __u32 major, minor, patch;
+ struct utsname info;
- for (pi = 0; pi < obj->nr_programs; pi++) {
- const char *name = NULL;
+ uname(&info);
+ if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
+ return 0;
+ return KERNEL_VERSION(major, minor, patch);
+}
- prog = &obj->programs[pi];
+static const struct btf_member *
+find_member_by_offset(const struct btf_type *t, __u32 bit_offset)
+{
+ struct btf_member *m;
+ int i;
- for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
- si++) {
- GElf_Sym sym;
+ for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+ if (btf_member_bit_offset(t, i) == bit_offset)
+ return m;
+ }
- if (!gelf_getsym(symbols, si, &sym))
- continue;
- if (sym.st_shndx != prog->idx)
- continue;
- if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
- continue;
+ return NULL;
+}
- name = elf_strptr(obj->efile.elf,
- obj->efile.strtabidx,
- sym.st_name);
- if (!name) {
- pr_warning("failed to get sym name string for prog %s\n",
- prog->section_name);
- return -LIBBPF_ERRNO__LIBELF;
- }
+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;
}
- if (!name && prog->idx == obj->efile.text_shndx)
- name = ".text";
+ 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;
+ }
- if (!name) {
- pr_warning("failed to find sym for prog %s\n",
- prog->section_name);
+ 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;
}
- prog->name = strdup(name);
- if (!prog->name) {
- pr_warning("failed to allocate memory for prog sym %s\n",
- name);
- return -ENOMEM;
+ type = btf__type_by_id(obj->btf, type_id);
+ tname = btf__name_by_offset(obj->btf, type->name_off);
+ if (!tname[0]) {
+ pr_warn("struct_ops init: anonymous type is not supported\n");
+ return -ENOTSUP;
}
+ if (!btf_is_struct(type)) {
+ pr_warn("struct_ops init: %s is not a struct\n", tname);
+ return -EINVAL;
+ }
+
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ map->sec_idx = obj->efile.st_ops_shndx;
+ map->sec_offset = vsi->offset;
+ map->name = strdup(var_name);
+ if (!map->name)
+ return -ENOMEM;
+
+ map->def.type = BPF_MAP_TYPE_STRUCT_OPS;
+ map->def.key_size = sizeof(int);
+ map->def.value_size = type->size;
+ map->def.max_entries = 1;
+
+ map->st_ops = calloc(1, sizeof(*map->st_ops));
+ if (!map->st_ops)
+ return -ENOMEM;
+ st_ops = map->st_ops;
+ st_ops->data = malloc(type->size);
+ st_ops->progs = calloc(btf_vlen(type), sizeof(*st_ops->progs));
+ st_ops->kern_func_off = malloc(btf_vlen(type) *
+ sizeof(*st_ops->kern_func_off));
+ if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off)
+ return -ENOMEM;
+
+ if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) {
+ pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n",
+ var_name, STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ memcpy(st_ops->data,
+ obj->efile.st_ops_data->d_buf + vsi->offset,
+ type->size);
+ st_ops->tname = tname;
+ st_ops->type = type;
+ st_ops->type_id = type_id;
+
+ pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n",
+ tname, type_id, var_name, vsi->offset);
}
return 0;
}
static struct bpf_object *bpf_object__new(const char *path,
- void *obj_buf,
- size_t obj_buf_sz)
+ const void *obj_buf,
+ size_t obj_buf_sz,
+ const char *obj_name)
{
struct bpf_object *obj;
char *end;
obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
if (!obj) {
- pr_warning("alloc memory failed for %s\n", path);
+ pr_warn("alloc memory failed for %s\n", path);
return ERR_PTR(-ENOMEM);
}
strcpy(obj->path, path);
- /* Using basename() GNU version which doesn't modify arg. */
- strncpy(obj->name, basename((void *)path), sizeof(obj->name) - 1);
- end = strchr(obj->name, '.');
- if (end)
- *end = 0;
+ if (obj_name) {
+ strncpy(obj->name, obj_name, sizeof(obj->name) - 1);
+ obj->name[sizeof(obj->name) - 1] = 0;
+ } else {
+ /* Using basename() GNU version which doesn't modify arg. */
+ strncpy(obj->name, basename((void *)path),
+ sizeof(obj->name) - 1);
+ end = strchr(obj->name, '.');
+ if (end)
+ *end = 0;
+ }
obj->efile.fd = -1;
/*
@@ -525,7 +1068,11 @@
obj->efile.data_shndx = -1;
obj->efile.rodata_shndx = -1;
obj->efile.bss_shndx = -1;
+ obj->efile.st_ops_shndx = -1;
+ obj->kconfig_map_idx = -1;
+ obj->rodata_map_idx = -1;
+ obj->kern_version = get_kernel_version();
obj->loaded = false;
INIT_LIST_HEAD(&obj->list);
@@ -546,21 +1093,27 @@
obj->efile.data = NULL;
obj->efile.rodata = NULL;
obj->efile.bss = NULL;
+ obj->efile.st_ops_data = NULL;
- zfree(&obj->efile.reloc);
- obj->efile.nr_reloc = 0;
+ zfree(&obj->efile.reloc_sects);
+ obj->efile.nr_reloc_sects = 0;
zclose(obj->efile.fd);
obj->efile.obj_buf = NULL;
obj->efile.obj_buf_sz = 0;
}
+/* 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
+
static int bpf_object__elf_init(struct bpf_object *obj)
{
int err = 0;
GElf_Ehdr *ep;
if (obj_elf_valid(obj)) {
- pr_warning("elf init: internal error\n");
+ pr_warn("elf: init internal error\n");
return -LIBBPF_ERRNO__LIBELF;
}
@@ -569,7 +1122,7 @@
* obj_buf should have been validated by
* bpf_object__open_buffer().
*/
- obj->efile.elf = elf_memory(obj->efile.obj_buf,
+ obj->efile.elf = elf_memory((char *)obj->efile.obj_buf,
obj->efile.obj_buf_sz);
} else {
obj->efile.fd = open(obj->path, O_RDONLY);
@@ -578,31 +1131,45 @@
err = -errno;
cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
- pr_warning("failed to open %s: %s\n", obj->path, cp);
+ pr_warn("elf: failed to open %s: %s\n", obj->path, cp);
return err;
}
- obj->efile.elf = elf_begin(obj->efile.fd,
- LIBBPF_ELF_C_READ_MMAP, NULL);
+ obj->efile.elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL);
}
if (!obj->efile.elf) {
- pr_warning("failed to open %s as ELF file\n", obj->path);
+ pr_warn("elf: failed to open %s as ELF file: %s\n", obj->path, elf_errmsg(-1));
err = -LIBBPF_ERRNO__LIBELF;
goto errout;
}
if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
- pr_warning("failed to get EHDR from %s\n", obj->path);
+ pr_warn("elf: failed to get ELF header from %s: %s\n", obj->path, elf_errmsg(-1));
err = -LIBBPF_ERRNO__FORMAT;
goto errout;
}
ep = &obj->efile.ehdr;
+ if (elf_getshdrstrndx(obj->efile.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(obj->efile.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 (ep->e_type != ET_REL ||
(ep->e_machine && ep->e_machine != EM_BPF)) {
- pr_warning("%s is not an eBPF object file\n", obj->path);
+ pr_warn("elf: %s is not a valid eBPF object file\n", obj->path);
err = -LIBBPF_ERRNO__FORMAT;
goto errout;
}
@@ -624,7 +1191,7 @@
#else
# error "Unrecognized __BYTE_ORDER__"
#endif
- pr_warning("endianness mismatch.\n");
+ pr_warn("elf: endianness mismatch in %s.\n", obj->path);
return -LIBBPF_ERRNO__ENDIAN;
}
@@ -642,7 +1209,7 @@
__u32 kver;
if (size != sizeof(kver)) {
- pr_warning("invalid kver section in %s\n", obj->path);
+ pr_warn("invalid kver section in %s\n", obj->path);
return -LIBBPF_ERRNO__FORMAT;
}
memcpy(&kver, data, sizeof(kver));
@@ -651,16 +1218,6 @@
return 0;
}
-static int compare_bpf_map(const void *_a, const void *_b)
-{
- const struct bpf_map *a = _a;
- const struct bpf_map *b = _b;
-
- if (a->sec_idx != b->sec_idx)
- return a->sec_idx - b->sec_idx;
- return a->sec_offset - b->sec_offset;
-}
-
static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
{
if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
@@ -669,72 +1226,34 @@
return false;
}
-static int bpf_object_search_section_size(const struct bpf_object *obj,
- const char *name, size_t *d_size)
-{
- const GElf_Ehdr *ep = &obj->efile.ehdr;
- Elf *elf = obj->efile.elf;
- Elf_Scn *scn = NULL;
- int idx = 0;
-
- while ((scn = elf_nextscn(elf, scn)) != NULL) {
- const char *sec_name;
- Elf_Data *data;
- GElf_Shdr sh;
-
- idx++;
- if (gelf_getshdr(scn, &sh) != &sh) {
- pr_warning("failed to get section(%d) header from %s\n",
- idx, obj->path);
- return -EIO;
- }
-
- sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
- if (!sec_name) {
- pr_warning("failed to get section(%d) name from %s\n",
- idx, obj->path);
- return -EIO;
- }
-
- if (strcmp(name, sec_name))
- continue;
-
- data = elf_getdata(scn, 0);
- if (!data) {
- pr_warning("failed to get section(%d) data from %s(%s)\n",
- idx, name, obj->path);
- return -EIO;
- }
-
- *d_size = data->d_size;
- return 0;
- }
-
- return -ENOENT;
-}
-
int bpf_object__section_size(const struct bpf_object *obj, const char *name,
__u32 *size)
{
int ret = -ENOENT;
- size_t d_size;
*size = 0;
if (!name) {
return -EINVAL;
- } else if (!strcmp(name, ".data")) {
+ } else if (!strcmp(name, DATA_SEC)) {
if (obj->efile.data)
*size = obj->efile.data->d_size;
- } else if (!strcmp(name, ".bss")) {
+ } else if (!strcmp(name, BSS_SEC)) {
if (obj->efile.bss)
*size = obj->efile.bss->d_size;
- } else if (!strcmp(name, ".rodata")) {
+ } else if (!strcmp(name, RODATA_SEC)) {
if (obj->efile.rodata)
*size = obj->efile.rodata->d_size;
+ } else if (!strcmp(name, STRUCT_OPS_SEC)) {
+ if (obj->efile.st_ops_data)
+ *size = obj->efile.st_ops_data->d_size;
} else {
- ret = bpf_object_search_section_size(obj, name, &d_size);
- if (!ret)
- *size = d_size;
+ Elf_Scn *scn = elf_sec_by_name(obj, name);
+ Elf_Data *data = elf_sec_data(obj, scn);
+
+ if (data) {
+ ret = 0; /* found it */
+ *size = data->d_size;
+ }
}
return *size ? 0 : ret;
@@ -759,11 +1278,10 @@
GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
continue;
- sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
- sym.st_name);
+ sname = elf_sym_str(obj, sym.st_name);
if (!sname) {
- pr_warning("failed to get sym name string for var %s\n",
- name);
+ pr_warn("failed to get sym name string for var %s\n",
+ name);
return -EIO;
}
if (strcmp(name, sname) == 0) {
@@ -785,9 +1303,9 @@
return &obj->maps[obj->nr_maps++];
new_cap = max((size_t)4, obj->maps_cap * 3 / 2);
- new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps));
+ new_maps = libbpf_reallocarray(obj->maps, new_cap, sizeof(*obj->maps));
if (!new_maps) {
- pr_warning("alloc maps for object failed\n");
+ pr_warn("alloc maps for object failed\n");
return ERR_PTR(-ENOMEM);
}
@@ -809,13 +1327,43 @@
return &obj->maps[obj->nr_maps++];
}
+static size_t bpf_map_mmap_sz(const struct bpf_map *map)
+{
+ long page_sz = sysconf(_SC_PAGE_SIZE);
+ size_t map_sz;
+
+ map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries;
+ map_sz = roundup(map_sz, page_sz);
+ return map_sz;
+}
+
+static char *internal_map_name(struct bpf_object *obj,
+ enum libbpf_map_type type)
+{
+ char map_name[BPF_OBJ_NAME_LEN], *p;
+ const char *sfx = libbpf_type_to_btf_name[type];
+ int sfx_len = max((size_t)7, strlen(sfx));
+ int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1,
+ strlen(obj->name));
+
+ snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
+ sfx_len, libbpf_type_to_btf_name[type]);
+
+ /* 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_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
- int sec_idx, Elf_Data *data, void **data_buff)
+ int sec_idx, void *data, size_t data_sz)
{
- char map_name[BPF_OBJ_NAME_LEN];
struct bpf_map_def *def;
struct bpf_map *map;
+ int err;
map = bpf_object__add_map(obj);
if (IS_ERR(map))
@@ -824,32 +1372,38 @@
map->libbpf_type = type;
map->sec_idx = sec_idx;
map->sec_offset = 0;
- snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
- libbpf_type_to_btf_name[type]);
- map->name = strdup(map_name);
+ map->name = internal_map_name(obj, type);
if (!map->name) {
- pr_warning("failed to alloc map name\n");
+ pr_warn("failed to alloc map name\n");
return -ENOMEM;
}
- pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
- map_name, map->sec_idx, map->sec_offset);
def = &map->def;
def->type = BPF_MAP_TYPE_ARRAY;
def->key_size = sizeof(int);
- def->value_size = data->d_size;
+ def->value_size = data_sz;
def->max_entries = 1;
- def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
- if (data_buff) {
- *data_buff = malloc(data->d_size);
- if (!*data_buff) {
- zfree(&map->name);
- pr_warning("failed to alloc map content buffer\n");
- return -ENOMEM;
- }
- memcpy(*data_buff, data->d_buf, data->d_size);
+ def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG
+ ? BPF_F_RDONLY_PROG : 0;
+ def->map_flags |= BPF_F_MMAPABLE;
+
+ pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
+ map->name, map->sec_idx, map->sec_offset, def->map_flags);
+
+ map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ if (map->mmaped == MAP_FAILED) {
+ err = -errno;
+ map->mmaped = NULL;
+ pr_warn("failed to alloc map '%s' content buffer: %d\n",
+ map->name, err);
+ zfree(&map->name);
+ return err;
}
+ if (data)
+ memcpy(map->mmaped, data, data_sz);
+
pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name);
return 0;
}
@@ -858,37 +1412,338 @@
{
int err;
- if (!obj->caps.global_data)
- return 0;
/*
* Populate obj->maps with libbpf internal maps.
*/
if (obj->efile.data_shndx >= 0) {
err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
obj->efile.data_shndx,
- obj->efile.data,
- &obj->sections.data);
+ obj->efile.data->d_buf,
+ obj->efile.data->d_size);
if (err)
return err;
}
if (obj->efile.rodata_shndx >= 0) {
err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
obj->efile.rodata_shndx,
- obj->efile.rodata,
- &obj->sections.rodata);
+ obj->efile.rodata->d_buf,
+ obj->efile.rodata->d_size);
if (err)
return err;
+
+ obj->rodata_map_idx = obj->nr_maps - 1;
}
if (obj->efile.bss_shndx >= 0) {
err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
obj->efile.bss_shndx,
- obj->efile.bss, NULL);
+ NULL,
+ obj->efile.bss->d_size);
if (err)
return err;
}
return 0;
}
+
+static struct extern_desc *find_extern_by_name(const struct bpf_object *obj,
+ const void *name)
+{
+ int i;
+
+ for (i = 0; i < obj->nr_extern; i++) {
+ if (strcmp(obj->externs[i].name, name) == 0)
+ return &obj->externs[i];
+ }
+ return NULL;
+}
+
+static int set_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=%c should be tristate or char\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=%c should be bool, tristate, or char\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=%s should be char array\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 config %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) {
+ pr_warn("extern (kcfg) %s=%llu should be integer\n",
+ ext->name, (unsigned long long)value);
+ return -EINVAL;
+ }
+ if (!is_kcfg_value_in_range(ext, value)) {
+ pr_warn("extern (kcfg) %s=%llu value 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 (strncmp(buf, "CONFIG_", 7))
+ return 0;
+
+ sep = strchr(buf, '=');
+ if (!sep) {
+ pr_warn("failed to parse '%s': no separator\n", buf);
+ return -EINVAL;
+ }
+
+ /* Trim ending '\n' */
+ len = strlen(buf);
+ if (buf[len - 1] == '\n')
+ buf[len - 1] = '\0';
+ /* Split on '=' and ensure that a value is present. */
+ *sep = '\0';
+ if (!sep[1]) {
+ *sep = '=';
+ pr_warn("failed to parse '%s': no value\n", buf);
+ return -EINVAL;
+ }
+
+ ext = find_extern_by_name(obj, buf);
+ if (!ext || ext->is_set)
+ return 0;
+
+ ext_val = data + ext->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=%s should be integer\n",
+ ext->name, value);
+ return err;
+ }
+ err = set_kcfg_value_num(ext, ext_val, num);
+ break;
+ }
+ if (err)
+ return err;
+ pr_debug("extern (kcfg) %s=%s\n", ext->name, value);
+ return 0;
+}
+
+static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data)
+{
+ char buf[PATH_MAX];
+ struct utsname uts;
+ int len, err = 0;
+ gzFile file;
+
+ uname(&uts);
+ len = snprintf(buf, PATH_MAX, "/boot/config-%s", uts.release);
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ /* gzopen also accepts uncompressed files. */
+ file = gzopen(buf, "r");
+ if (!file)
+ file = gzopen("/proc/config.gz", "r");
+
+ if (!file) {
+ pr_warn("failed to open system Kconfig\n");
+ return -ENOENT;
+ }
+
+ while (gzgets(file, buf, sizeof(buf))) {
+ err = bpf_object__process_kconfig_line(obj, buf, data);
+ if (err) {
+ pr_warn("error parsing system Kconfig line '%s': %d\n",
+ buf, err);
+ goto out;
+ }
+ }
+
+out:
+ gzclose(file);
+ return err;
+}
+
+static int bpf_object__read_kconfig_mem(struct bpf_object *obj,
+ const char *config, void *data)
+{
+ char buf[PATH_MAX];
+ int err = 0;
+ FILE *file;
+
+ file = fmemopen((void *)config, strlen(config), "r");
+ if (!file) {
+ err = -errno;
+ pr_warn("failed to open in-memory Kconfig: %d\n", err);
+ return err;
+ }
+
+ while (fgets(buf, sizeof(buf), file)) {
+ err = bpf_object__process_kconfig_line(obj, buf, data);
+ if (err) {
+ pr_warn("error parsing in-memory Kconfig line '%s': %d\n",
+ buf, err);
+ break;
+ }
+ }
+
+ fclose(file);
+ return err;
+}
+
+static int bpf_object__init_kconfig_map(struct bpf_object *obj)
+{
+ struct extern_desc *last_ext = 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,
+ obj->efile.symbols_shndx,
+ NULL, map_sz);
+ if (err)
+ return err;
+
+ obj->kconfig_map_idx = obj->nr_maps - 1;
+
+ return 0;
+}
+
static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
{
Elf_Data *symbols = obj->efile.symbols;
@@ -902,12 +1757,12 @@
if (!symbols)
return -EINVAL;
- scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx);
- if (scn)
- data = elf_getdata(scn, NULL);
+
+ scn = elf_sec_by_idx(obj, obj->efile.maps_shndx);
+ data = elf_sec_data(obj, scn);
if (!scn || !data) {
- pr_warning("failed to get Elf_Data from map section %d\n",
- obj->efile.maps_shndx);
+ pr_warn("elf: failed to get legacy map definitions for %s\n",
+ obj->path);
return -EINVAL;
}
@@ -929,16 +1784,15 @@
nr_maps++;
}
/* Assume equally sized map definitions */
- pr_debug("maps in %s: %d maps in %zd bytes\n",
- obj->path, nr_maps, data->d_size);
+ pr_debug("elf: found %d legacy map definitions (%zd bytes) in %s\n",
+ nr_maps, data->d_size, obj->path);
- map_def_sz = data->d_size / nr_maps;
- if (!data->d_size || (data->d_size % nr_maps) != 0) {
- pr_warning("unable to determine map definition size "
- "section %s, %d maps in %zd bytes\n",
- obj->path, nr_maps, data->d_size);
+ if (!data->d_size || nr_maps == 0 || (data->d_size % nr_maps) != 0) {
+ pr_warn("elf: unable to determine legacy map definition size in %s\n",
+ obj->path);
return -EINVAL;
}
+ map_def_sz = data->d_size / nr_maps;
/* Fill obj->maps using data in "maps" section. */
for (i = 0; i < nr_syms; i++) {
@@ -956,11 +1810,10 @@
if (IS_ERR(map))
return PTR_ERR(map);
- map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
- sym.st_name);
+ map_name = elf_sym_str(obj, sym.st_name);
if (!map_name) {
- pr_warning("failed to get map #%d name sym string for obj %s\n",
- i, obj->path);
+ pr_warn("failed to get map #%d name sym string for obj %s\n",
+ i, obj->path);
return -LIBBPF_ERRNO__FORMAT;
}
@@ -970,14 +1823,14 @@
pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n",
map_name, map->sec_idx, map->sec_offset);
if (sym.st_value + map_def_sz > data->d_size) {
- pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
- obj->path, map_name);
+ pr_warn("corrupted maps section in %s: last map \"%s\" too small\n",
+ obj->path, map_name);
return -EINVAL;
}
map->name = strdup(map_name);
if (!map->name) {
- pr_warning("failed to alloc map name\n");
+ pr_warn("failed to alloc map name\n");
return -ENOMEM;
}
pr_debug("map %d is \"%s\"\n", i, map->name);
@@ -998,13 +1851,12 @@
* incompatible.
*/
char *b;
+
for (b = ((char *)def) + sizeof(struct bpf_map_def);
b < ((char *)def) + map_def_sz; b++) {
if (*b != 0) {
- pr_warning("maps section in %s: \"%s\" "
- "has unrecognized, non-zero "
- "options\n",
- obj->path, map_name);
+ pr_warn("maps section in %s: \"%s\" has unrecognized, non-zero options\n",
+ obj->path, map_name);
if (strict)
return -EINVAL;
}
@@ -1032,6 +1884,43 @@
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(const struct btf_type *t)
+{
+ switch (btf_kind(t)) {
+ 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";
+ default: return "unknown";
+ }
+}
+
/*
* Fetch integer attribute of BTF map definition. Such attributes are
* represented using a pointer to an array, in which dimensionality of array
@@ -1040,28 +1929,28 @@
* type definition, while using only sizeof(void *) space in ELF data section.
*/
static bool get_map_field_int(const char *map_name, const struct btf *btf,
- const struct btf_type *def,
- const struct btf_member *m, __u32 *res) {
+ const struct btf_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_warning("map '%s': attr '%s': expected PTR, got %u.\n",
- map_name, name, btf_kind(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_warning("map '%s': attr '%s': type [%u] not found.\n",
- map_name, name, t->type);
+ pr_warn("map '%s': attr '%s': type [%u] not found.\n",
+ map_name, name, t->type);
return false;
}
if (!btf_is_array(arr_t)) {
- pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n",
- map_name, name, btf_kind(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);
@@ -1069,110 +1958,75 @@
return true;
}
-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)
+static int build_map_pin_path(struct bpf_map *map, const char *path)
{
- const struct btf_type *var, *def, *t;
- const struct btf_var_secinfo *vi;
- const struct btf_var *var_extra;
+ char buf[PATH_MAX];
+ int len;
+
+ if (!path)
+ path = "/sys/fs/bpf";
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map));
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ return bpf_map__set_pin_path(map, buf);
+}
+
+
+static int parse_btf_map_def(struct bpf_object *obj,
+ struct bpf_map *map,
+ const struct btf_type *def,
+ bool strict, bool is_inner,
+ const char *pin_root_path)
+{
+ const struct btf_type *t;
const struct btf_member *m;
- const char *map_name;
- struct bpf_map *map;
int vlen, i;
- vi = btf_var_secinfos(sec) + var_idx;
- var = btf__type_by_id(obj->btf, vi->type);
- var_extra = btf_var(var);
- map_name = btf__name_by_offset(obj->btf, var->name_off);
- vlen = btf_vlen(var);
-
- if (map_name == NULL || map_name[0] == '\0') {
- pr_warning("map #%d: empty name.\n", var_idx);
- return -EINVAL;
- }
- if ((__u64)vi->offset + vi->size > data->d_size) {
- pr_warning("map '%s' BTF data is corrupted.\n", map_name);
- return -EINVAL;
- }
- if (!btf_is_var(var)) {
- pr_warning("map '%s': unexpected var kind %u.\n",
- map_name, btf_kind(var));
- return -EINVAL;
- }
- if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED &&
- var_extra->linkage != BTF_VAR_STATIC) {
- pr_warning("map '%s': unsupported var linkage %u.\n",
- map_name, var_extra->linkage);
- return -EOPNOTSUPP;
- }
-
- def = skip_mods_and_typedefs(obj->btf, var->type, NULL);
- if (!btf_is_struct(def)) {
- pr_warning("map '%s': unexpected def kind %u.\n",
- map_name, btf_kind(var));
- return -EINVAL;
- }
- if (def->size > vi->size) {
- pr_warning("map '%s': invalid def size.\n", map_name);
- 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_warning("map '%s': failed to alloc map name.\n", map_name);
- return -ENOMEM;
- }
- map->libbpf_type = LIBBPF_MAP_UNSPEC;
- map->def.type = BPF_MAP_TYPE_UNSPEC;
- map->sec_idx = sec_idx;
- map->sec_offset = vi->offset;
- pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
- map_name, map->sec_idx, map->sec_offset);
-
vlen = btf_vlen(def);
m = btf_members(def);
for (i = 0; i < vlen; i++, m++) {
const char *name = btf__name_by_offset(obj->btf, m->name_off);
if (!name) {
- pr_warning("map '%s': invalid field #%d.\n",
- map_name, i);
+ pr_warn("map '%s': invalid field #%d.\n", map->name, i);
return -EINVAL;
}
if (strcmp(name, "type") == 0) {
- if (!get_map_field_int(map_name, obj->btf, def, m,
+ if (!get_map_field_int(map->name, obj->btf, m,
&map->def.type))
return -EINVAL;
pr_debug("map '%s': found type = %u.\n",
- map_name, map->def.type);
+ map->name, map->def.type);
} else if (strcmp(name, "max_entries") == 0) {
- if (!get_map_field_int(map_name, obj->btf, def, m,
+ if (!get_map_field_int(map->name, obj->btf, m,
&map->def.max_entries))
return -EINVAL;
pr_debug("map '%s': found max_entries = %u.\n",
- map_name, map->def.max_entries);
+ map->name, map->def.max_entries);
} else if (strcmp(name, "map_flags") == 0) {
- if (!get_map_field_int(map_name, obj->btf, def, m,
+ if (!get_map_field_int(map->name, obj->btf, m,
&map->def.map_flags))
return -EINVAL;
pr_debug("map '%s': found map_flags = %u.\n",
- map_name, map->def.map_flags);
+ map->name, map->def.map_flags);
+ } else if (strcmp(name, "numa_node") == 0) {
+ if (!get_map_field_int(map->name, obj->btf, m, &map->numa_node))
+ return -EINVAL;
+ pr_debug("map '%s': found numa_node = %u.\n", map->name, map->numa_node);
} else if (strcmp(name, "key_size") == 0) {
__u32 sz;
- if (!get_map_field_int(map_name, obj->btf, def, m,
- &sz))
+ if (!get_map_field_int(map->name, obj->btf, m, &sz))
return -EINVAL;
pr_debug("map '%s': found key_size = %u.\n",
- map_name, sz);
+ map->name, sz);
if (map->def.key_size && map->def.key_size != sz) {
- pr_warning("map '%s': conflicting key size %u != %u.\n",
- map_name, map->def.key_size, sz);
+ pr_warn("map '%s': conflicting key size %u != %u.\n",
+ map->name, map->def.key_size, sz);
return -EINVAL;
}
map->def.key_size = sz;
@@ -1181,26 +2035,26 @@
t = btf__type_by_id(obj->btf, m->type);
if (!t) {
- pr_warning("map '%s': key type [%d] not found.\n",
- map_name, m->type);
+ pr_warn("map '%s': key type [%d] not found.\n",
+ map->name, m->type);
return -EINVAL;
}
if (!btf_is_ptr(t)) {
- pr_warning("map '%s': key spec is not PTR: %u.\n",
- map_name, btf_kind(t));
+ pr_warn("map '%s': key spec is not PTR: %s.\n",
+ map->name, btf_kind_str(t));
return -EINVAL;
}
sz = btf__resolve_size(obj->btf, t->type);
if (sz < 0) {
- pr_warning("map '%s': can't determine key size for type [%u]: %lld.\n",
- map_name, t->type, sz);
+ pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n",
+ map->name, t->type, (ssize_t)sz);
return sz;
}
- pr_debug("map '%s': found key [%u], sz = %lld.\n",
- map_name, t->type, sz);
+ pr_debug("map '%s': found key [%u], sz = %zd.\n",
+ map->name, t->type, (ssize_t)sz);
if (map->def.key_size && map->def.key_size != sz) {
- pr_warning("map '%s': conflicting key size %u != %lld.\n",
- map_name, map->def.key_size, sz);
+ pr_warn("map '%s': conflicting key size %u != %zd.\n",
+ map->name, map->def.key_size, (ssize_t)sz);
return -EINVAL;
}
map->def.key_size = sz;
@@ -1208,14 +2062,13 @@
} else if (strcmp(name, "value_size") == 0) {
__u32 sz;
- if (!get_map_field_int(map_name, obj->btf, def, m,
- &sz))
+ if (!get_map_field_int(map->name, obj->btf, m, &sz))
return -EINVAL;
pr_debug("map '%s': found value_size = %u.\n",
- map_name, sz);
+ map->name, sz);
if (map->def.value_size && map->def.value_size != sz) {
- pr_warning("map '%s': conflicting value size %u != %u.\n",
- map_name, map->def.value_size, sz);
+ pr_warn("map '%s': conflicting value size %u != %u.\n",
+ map->name, map->def.value_size, sz);
return -EINVAL;
}
map->def.value_size = sz;
@@ -1224,50 +2077,210 @@
t = btf__type_by_id(obj->btf, m->type);
if (!t) {
- pr_warning("map '%s': value type [%d] not found.\n",
- map_name, m->type);
+ pr_warn("map '%s': value type [%d] not found.\n",
+ map->name, m->type);
return -EINVAL;
}
if (!btf_is_ptr(t)) {
- pr_warning("map '%s': value spec is not PTR: %u.\n",
- map_name, btf_kind(t));
+ pr_warn("map '%s': value spec is not PTR: %s.\n",
+ map->name, btf_kind_str(t));
return -EINVAL;
}
sz = btf__resolve_size(obj->btf, t->type);
if (sz < 0) {
- pr_warning("map '%s': can't determine value size for type [%u]: %lld.\n",
- map_name, t->type, sz);
+ pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n",
+ map->name, t->type, (ssize_t)sz);
return sz;
}
- pr_debug("map '%s': found value [%u], sz = %lld.\n",
- map_name, t->type, sz);
+ pr_debug("map '%s': found value [%u], sz = %zd.\n",
+ map->name, t->type, (ssize_t)sz);
if (map->def.value_size && map->def.value_size != sz) {
- pr_warning("map '%s': conflicting value size %u != %lld.\n",
- map_name, map->def.value_size, sz);
+ pr_warn("map '%s': conflicting value size %u != %zd.\n",
+ map->name, map->def.value_size, (ssize_t)sz);
return -EINVAL;
}
map->def.value_size = sz;
map->btf_value_type_id = t->type;
+ }
+ else if (strcmp(name, "values") == 0) {
+ 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 (!bpf_map_type__is_map_in_map(map->def.type)) {
+ pr_warn("map '%s': should be map-in-map.\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(obj->btf, m->type);
+ if (!t) {
+ pr_warn("map '%s': map-in-map inner type [%d] not found.\n",
+ map->name, m->type);
+ return -EINVAL;
+ }
+ if (!btf_is_array(t) || btf_array(t)->nelems) {
+ pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n",
+ map->name);
+ return -EINVAL;
+ }
+ t = skip_mods_and_typedefs(obj->btf, btf_array(t)->type,
+ NULL);
+ if (!btf_is_ptr(t)) {
+ pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n",
+ map->name, btf_kind_str(t));
+ return -EINVAL;
+ }
+ t = skip_mods_and_typedefs(obj->btf, t->type, NULL);
+ 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;
+ }
+
+ map->inner_map = calloc(1, sizeof(*map->inner_map));
+ if (!map->inner_map)
+ return -ENOMEM;
+ map->inner_map->sec_idx = obj->efile.btf_maps_shndx;
+ 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);
+
+ err = parse_btf_map_def(obj, map->inner_map, t, strict,
+ true /* is_inner */, NULL);
+ if (err)
+ return err;
+ } else if (strcmp(name, "pinning") == 0) {
+ __u32 val;
+ int err;
+
+ if (is_inner) {
+ pr_debug("map '%s': inner def can't be pinned.\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (!get_map_field_int(map->name, obj->btf, m, &val))
+ return -EINVAL;
+ pr_debug("map '%s': found pinning = %u.\n",
+ map->name, val);
+
+ if (val != LIBBPF_PIN_NONE &&
+ val != LIBBPF_PIN_BY_NAME) {
+ pr_warn("map '%s': invalid pinning value %u.\n",
+ map->name, val);
+ return -EINVAL;
+ }
+ if (val == LIBBPF_PIN_BY_NAME) {
+ err = build_map_pin_path(map, pin_root_path);
+ if (err) {
+ pr_warn("map '%s': couldn't build pin path.\n",
+ map->name);
+ return err;
+ }
+ }
} else {
if (strict) {
- pr_warning("map '%s': unknown field '%s'.\n",
- map_name, name);
+ pr_warn("map '%s': unknown field '%s'.\n",
+ map->name, name);
return -ENOTSUP;
}
pr_debug("map '%s': ignoring unknown field '%s'.\n",
- map_name, name);
+ map->name, name);
}
}
if (map->def.type == BPF_MAP_TYPE_UNSPEC) {
- pr_warning("map '%s': map type isn't specified.\n", map_name);
+ pr_warn("map '%s': map type isn't specified.\n", map->name);
return -EINVAL;
}
return 0;
}
-static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
+static int bpf_object__init_user_btf_map(struct bpf_object *obj,
+ const struct btf_type *sec,
+ int var_idx, int sec_idx,
+ const Elf_Data *data, bool strict,
+ const char *pin_root_path)
+{
+ const struct btf_type *var, *def;
+ const struct btf_var_secinfo *vi;
+ const struct btf_var *var_extra;
+ const char *map_name;
+ struct bpf_map *map;
+
+ 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 &&
+ var_extra->linkage != BTF_VAR_STATIC) {
+ pr_warn("map '%s': unsupported var linkage %u.\n",
+ map_name, var_extra->linkage);
+ return -EOPNOTSUPP;
+ }
+
+ def = skip_mods_and_typedefs(obj->btf, var->type, NULL);
+ if (!btf_is_struct(def)) {
+ pr_warn("map '%s': unexpected def kind %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);
+
+ return parse_btf_map_def(obj, map, def, strict, false, pin_root_path);
+}
+
+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;
@@ -1279,12 +2292,11 @@
if (obj->efile.btf_maps_shndx < 0)
return 0;
- scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx);
- if (scn)
- data = elf_getdata(scn, NULL);
+ scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx);
+ data = elf_sec_data(obj, scn);
if (!scn || !data) {
- pr_warning("failed to get Elf_Data from map section %d (%s)\n",
- obj->efile.maps_shndx, MAPS_ELF_SEC);
+ pr_warn("elf: failed to get %s map definitions for %s\n",
+ MAPS_ELF_SEC, obj->path);
return -EINVAL;
}
@@ -1296,12 +2308,13 @@
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_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC);
+ pr_warn("DATASEC '%s' not found.\n", MAPS_ELF_SEC);
return -ENOENT;
}
@@ -1309,7 +2322,8 @@
for (i = 0; i < vlen; i++) {
err = bpf_object__init_user_btf_map(obj, sec, i,
obj->efile.btf_maps_shndx,
- data, strict);
+ data, strict,
+ pin_root_path);
if (err)
return err;
}
@@ -1317,59 +2331,54 @@
return 0;
}
-static int bpf_object__init_maps(struct bpf_object *obj, int flags)
+static int bpf_object__init_maps(struct bpf_object *obj,
+ const struct bpf_object_open_opts *opts)
{
- bool strict = !(flags & MAPS_RELAX_COMPAT);
+ const char *pin_root_path;
+ bool strict;
int err;
+ strict = !OPTS_GET(opts, relaxed_maps, false);
+ pin_root_path = OPTS_GET(opts, pin_root_path, NULL);
+
err = bpf_object__init_user_maps(obj, strict);
+ err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path);
+ err = err ?: bpf_object__init_global_data_maps(obj);
+ err = err ?: bpf_object__init_kconfig_map(obj);
+ err = err ?: bpf_object__init_struct_ops_maps(obj);
if (err)
return err;
- err = bpf_object__init_user_btf_maps(obj, strict);
- if (err)
- return err;
-
- err = bpf_object__init_global_data_maps(obj);
- if (err)
- return err;
-
- if (obj->nr_maps) {
- qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
- compare_bpf_map);
- }
return 0;
}
static bool section_have_execinstr(struct bpf_object *obj, int idx)
{
- Elf_Scn *scn;
GElf_Shdr sh;
- scn = elf_getscn(obj->efile.elf, idx);
- if (!scn)
+ if (elf_sec_hdr(obj, elf_sec_by_idx(obj, idx), &sh))
return false;
- if (gelf_getshdr(scn, &sh) != &sh)
- return false;
-
- if (sh.sh_flags & SHF_EXECINSTR)
- return true;
-
- return false;
+ return sh.sh_flags & SHF_EXECINSTR;
}
-static void bpf_object__sanitize_btf(struct bpf_object *obj)
+static bool btf_needs_sanitization(struct bpf_object *obj)
{
- bool has_datasec = obj->caps.btf_datasec;
- bool has_func = obj->caps.btf_func;
- struct btf *btf = obj->btf;
+ bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC);
+ bool has_datasec = kernel_supports(FEAT_BTF_DATASEC);
+ bool has_func = kernel_supports(FEAT_BTF_FUNC);
+
+ return !has_func || !has_datasec || !has_func_global;
+}
+
+static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
+{
+ bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC);
+ bool has_datasec = kernel_supports(FEAT_BTF_DATASEC);
+ bool has_func = kernel_supports(FEAT_BTF_FUNC);
struct btf_type *t;
int i, j, vlen;
- if (!obj->btf || (has_func && has_datasec))
- return;
-
for (i = 1; i <= btf__get_nr_types(btf); i++) {
t = (struct btf_type *)btf__type_by_id(btf, i);
@@ -1415,46 +2424,43 @@
} 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);
}
}
}
-static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
+static bool libbpf_needs_btf(const struct bpf_object *obj)
{
- if (!obj->btf_ext)
- return;
-
- if (!obj->caps.btf_func) {
- btf_ext__free(obj->btf_ext);
- obj->btf_ext = NULL;
- }
+ return obj->efile.btf_maps_shndx >= 0 ||
+ obj->efile.st_ops_shndx >= 0 ||
+ obj->nr_extern > 0;
}
-static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
+static bool kernel_needs_btf(const struct bpf_object *obj)
{
- return obj->efile.btf_maps_shndx >= 0;
+ 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)
{
- bool btf_required = bpf_object__is_btf_mandatory(obj);
- int err = 0;
+ int err = -ENOENT;
if (btf_data) {
obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
if (IS_ERR(obj->btf)) {
- pr_warning("Error loading ELF section %s: %d.\n",
- BTF_ELF_SEC, err);
+ err = PTR_ERR(obj->btf);
+ obj->btf = NULL;
+ pr_warn("Error loading ELF section %s: %d.\n",
+ BTF_ELF_SEC, err);
goto out;
}
- err = btf__finalize_data(obj, obj->btf);
- if (err) {
- pr_warning("Error finalizing %s: %d.\n",
- BTF_ELF_SEC, err);
- goto out;
- }
+ /* enforce 8-byte pointers for BPF-targeted BTFs */
+ btf__set_pointer_size(obj->btf, 8);
+ err = 0;
}
if (btf_ext_data) {
if (!obj->btf) {
@@ -1465,112 +2471,398 @@
obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
btf_ext_data->d_size);
if (IS_ERR(obj->btf_ext)) {
- pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
- BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext));
+ pr_warn("Error loading ELF section %s: %ld. Ignored and continue.\n",
+ BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext));
obj->btf_ext = NULL;
goto out;
}
}
out:
- if (err || IS_ERR(obj->btf)) {
- if (btf_required)
- err = err ? : PTR_ERR(obj->btf);
- else
- err = 0;
- if (!IS_ERR_OR_NULL(obj->btf))
- btf__free(obj->btf);
- obj->btf = NULL;
+ if (err && libbpf_needs_btf(obj)) {
+ pr_warn("BTF is required, but is missing or corrupted.\n");
+ return err;
}
- if (btf_required && !obj->btf) {
- pr_warning("BTF is required, but is missing or corrupted.\n");
- return err == 0 ? -ENOENT : err;
+ return 0;
+}
+
+static int bpf_object__finalize_btf(struct bpf_object *obj)
+{
+ int err;
+
+ if (!obj->btf)
+ return 0;
+
+ err = btf__finalize_data(obj, obj->btf);
+ if (err) {
+ pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err);
+ return err;
+ }
+
+ return 0;
+}
+
+static inline bool libbpf_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 int bpf_object__load_vmlinux_btf(struct bpf_object *obj)
+{
+ bool need_vmlinux_btf = false;
+ struct bpf_program *prog;
+ int i, err;
+
+ /* CO-RE relocations need kernel BTF */
+ if (obj->btf_ext && obj->btf_ext->core_relo_info.len)
+ need_vmlinux_btf = 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) {
+ need_vmlinux_btf = true;
+ break;
+ }
+ }
+
+ bpf_object__for_each_program(prog, obj) {
+ if (!prog->load)
+ continue;
+ if (libbpf_prog_needs_vmlinux_btf(prog)) {
+ need_vmlinux_btf = true;
+ break;
+ }
+ }
+
+ if (!need_vmlinux_btf)
+ return 0;
+
+ obj->btf_vmlinux = libbpf_find_kernel_btf();
+ if (IS_ERR(obj->btf_vmlinux)) {
+ err = PTR_ERR(obj->btf_vmlinux);
+ pr_warn("Error loading vmlinux BTF: %d\n", err);
+ obj->btf_vmlinux = NULL;
+ return err;
}
return 0;
}
static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
{
+ struct btf *kern_btf = obj->btf;
+ bool btf_mandatory, sanitize;
int err = 0;
if (!obj->btf)
return 0;
- bpf_object__sanitize_btf(obj);
- bpf_object__sanitize_btf_ext(obj);
-
- err = btf__load(obj->btf);
- if (err) {
- pr_warning("Error loading %s into kernel: %d.\n",
- BTF_ELF_SEC, err);
- btf__free(obj->btf);
- obj->btf = NULL;
- /* btf_ext can't exist without btf, so free it as well */
- if (obj->btf_ext) {
- btf_ext__free(obj->btf_ext);
- obj->btf_ext = NULL;
+ if (!kernel_supports(FEAT_BTF)) {
+ if (kernel_needs_btf(obj)) {
+ err = -EOPNOTSUPP;
+ goto report;
}
-
- if (bpf_object__is_btf_mandatory(obj))
- return err;
+ pr_debug("Kernel doesn't support BTF, skipping uploading it.\n");
+ return 0;
}
+
+ 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__get_raw_data(obj->btf, &sz);
+ kern_btf = btf__new(raw_data, sz);
+ if (IS_ERR(kern_btf))
+ return PTR_ERR(kern_btf);
+
+ /* enforce 8-byte pointers for BPF-targeted BTFs */
+ btf__set_pointer_size(obj->btf, 8);
+ bpf_object__sanitize_btf(obj, kern_btf);
+ }
+
+ err = btf__load(kern_btf);
+ 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 int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr)
+{
+ if (!scn)
+ return -EINVAL;
+
+ if (gelf_getshdr(scn, hdr) != hdr) {
+ pr_warn("elf: failed to get section(%zu) header from %s: %s\n",
+ elf_ndxscn(scn), obj->path, elf_errmsg(-1));
+ return -EINVAL;
+ }
+
return 0;
}
-static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
+static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn)
{
- Elf *elf = obj->efile.elf;
- GElf_Ehdr *ep = &obj->efile.ehdr;
- Elf_Data *btf_ext_data = NULL;
- Elf_Data *btf_data = NULL;
- Elf_Scn *scn = NULL;
- int idx = 0, err = 0;
+ const char *name;
+ GElf_Shdr sh;
- /* Elf is corrupted/truncated, avoid calling elf_strptr. */
- if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
- pr_warning("failed to get e_shstrndx from %s\n", obj->path);
- return -LIBBPF_ERRNO__FORMAT;
+ if (!scn)
+ return NULL;
+
+ if (elf_sec_hdr(obj, scn, &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 int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx,
+ size_t off, __u32 sym_type, GElf_Sym *sym)
+{
+ Elf_Data *symbols = obj->efile.symbols;
+ size_t n = symbols->d_size / sizeof(GElf_Sym);
+ int i;
+
+ for (i = 0; i < n; i++) {
+ if (!gelf_getsym(symbols, i, sym))
+ continue;
+ if (sym->st_shndx != sec_idx || sym->st_value != off)
+ continue;
+ if (GELF_ST_TYPE(sym->st_info) != sym_type)
+ continue;
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+static bool is_sec_name_dwarf(const char *name)
+{
+ /* approximation, but the actual list is too long */
+ return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0;
+}
+
+static bool ignore_elf_section(GElf_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 == 0x6FFF4C03 /* 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 (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) {
+ 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)
+{
+ 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;
+ GElf_Shdr sh;
+
+ /* 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) {
- char *name;
- GElf_Shdr sh;
- Elf_Data *data;
+ if (elf_sec_hdr(obj, scn, &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;
+
+ obj->efile.symbols = data;
+ obj->efile.symbols_shndx = elf_ndxscn(scn);
+ obj->efile.strtabidx = sh.sh_link;
+ }
+ }
+
+ scn = NULL;
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
idx++;
- if (gelf_getshdr(scn, &sh) != &sh) {
- pr_warning("failed to get section(%d) header from %s\n",
- idx, obj->path);
- return -LIBBPF_ERRNO__FORMAT;
- }
- name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
- if (!name) {
- pr_warning("failed to get section(%d) name from %s\n",
- idx, obj->path);
+ if (elf_sec_hdr(obj, scn, &sh))
return -LIBBPF_ERRNO__FORMAT;
- }
- data = elf_getdata(scn, 0);
- if (!data) {
- pr_warning("failed to get section(%d) data from %s(%s)\n",
- idx, name, obj->path);
+ name = elf_sec_str(obj, sh.sh_name);
+ if (!name)
return -LIBBPF_ERRNO__FORMAT;
- }
- pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
+
+ 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);
+ 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);
+ err = bpf_object__init_kversion(obj, data->d_buf, data->d_size);
if (err)
return err;
} else if (strcmp(name, "maps") == 0) {
@@ -1582,95 +2874,386 @@
} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
btf_ext_data = data;
} else if (sh.sh_type == SHT_SYMTAB) {
- if (obj->efile.symbols) {
- pr_warning("bpf: multiple SYMTAB in %s\n",
- obj->path);
- return -LIBBPF_ERRNO__FORMAT;
- }
- obj->efile.symbols = data;
- obj->efile.strtabidx = sh.sh_link;
+ /* 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_program(obj, data->d_buf,
- data->d_size, name, idx);
- if (err) {
- char errmsg[STRERR_BUFSIZE];
- char *cp = libbpf_strerror_r(-err, errmsg,
- sizeof(errmsg));
-
- pr_warning("failed to alloc program %s (%s): %s",
- name, obj->path, cp);
+ err = bpf_object__add_programs(obj, data, name, idx);
+ if (err)
return err;
- }
- } else if (strcmp(name, ".data") == 0) {
+ } else if (strcmp(name, DATA_SEC) == 0) {
obj->efile.data = data;
obj->efile.data_shndx = idx;
- } else if (strcmp(name, ".rodata") == 0) {
+ } else if (strcmp(name, RODATA_SEC) == 0) {
obj->efile.rodata = data;
obj->efile.rodata_shndx = idx;
+ } else if (strcmp(name, STRUCT_OPS_SEC) == 0) {
+ obj->efile.st_ops_data = data;
+ obj->efile.st_ops_shndx = idx;
} else {
- pr_debug("skip section(%d) %s\n", idx, name);
+ pr_info("elf: skipping unrecognized data section(%d) %s\n",
+ idx, name);
}
} else if (sh.sh_type == SHT_REL) {
- int nr_reloc = obj->efile.nr_reloc;
- void *reloc = obj->efile.reloc;
+ int nr_sects = obj->efile.nr_reloc_sects;
+ void *sects = obj->efile.reloc_sects;
int sec = sh.sh_info; /* points to other section */
/* Only do relo for section with exec instructions */
- if (!section_have_execinstr(obj, sec)) {
- pr_debug("skip relo %s(%d) for section(%d)\n",
- name, idx, sec);
+ if (!section_have_execinstr(obj, sec) &&
+ 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, sec,
+ elf_sec_name(obj, elf_sec_by_idx(obj, sec)) ?: "<?>");
continue;
}
- reloc = reallocarray(reloc, nr_reloc + 1,
- sizeof(*obj->efile.reloc));
- if (!reloc) {
- pr_warning("realloc failed\n");
+ sects = libbpf_reallocarray(sects, nr_sects + 1,
+ sizeof(*obj->efile.reloc_sects));
+ if (!sects)
return -ENOMEM;
- }
- obj->efile.reloc = reloc;
- obj->efile.nr_reloc++;
+ obj->efile.reloc_sects = sects;
+ obj->efile.nr_reloc_sects++;
- obj->efile.reloc[nr_reloc].shdr = sh;
- obj->efile.reloc[nr_reloc].data = data;
- } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
+ obj->efile.reloc_sects[nr_sects].shdr = sh;
+ obj->efile.reloc_sects[nr_sects].data = data;
+ } else if (sh.sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) {
obj->efile.bss = data;
obj->efile.bss_shndx = idx;
} else {
- pr_debug("skip section(%d) %s\n", idx, name);
+ 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_warning("Corrupted ELF file: index of strtab invalid\n");
+ 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;
}
- err = bpf_object__init_btf(obj, btf_data, btf_ext_data);
- if (!err)
- err = bpf_object__init_maps(obj, flags);
- if (!err)
- err = bpf_object__sanitize_and_load_btf(obj);
- if (!err)
- err = bpf_object__init_prog_names(obj);
- return err;
+
+ /* sort BPF programs by section name and in-section instruction offset
+ * for faster search */
+ qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs);
+
+ return bpf_object__init_btf(obj, btf_data, btf_ext_data);
}
-static struct bpf_program *
-bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
+static bool sym_is_extern(const GElf_Sym *sym)
{
- struct bpf_program *prog;
- size_t i;
+ int bind = GELF_ST_BIND(sym->st_info);
+ /* externs are symbols w/ type=NOTYPE, bind=GLOBAL|WEAK, section=UND */
+ return sym->st_shndx == SHN_UNDEF &&
+ (bind == STB_GLOBAL || bind == STB_WEAK) &&
+ GELF_ST_TYPE(sym->st_info) == STT_NOTYPE;
+}
- for (i = 0; i < obj->nr_programs; i++) {
- prog = &obj->programs[i];
- if (prog->idx == idx)
- return prog;
+static int find_extern_btf_id(const struct btf *btf, const char *ext_name)
+{
+ const struct btf_type *t;
+ const char *var_name;
+ int i, n;
+
+ if (!btf)
+ return -ESRCH;
+
+ n = btf__get_nr_types(btf);
+ for (i = 1; i <= n; i++) {
+ t = btf__type_by_id(btf, i);
+
+ if (!btf_is_var(t))
+ continue;
+
+ var_name = btf__name_by_offset(btf, t->name_off);
+ if (strcmp(var_name, ext_name))
+ continue;
+
+ if (btf_var(t)->linkage != BTF_VAR_GLOBAL_EXTERN)
+ return -EINVAL;
+
+ return i;
}
- return NULL;
+
+ 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__get_nr_types(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_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__get_nr_types(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 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;
+ const char *ext_name, *sec_name;
+ Elf_Scn *scn;
+ GElf_Shdr sh;
+
+ if (!obj->efile.symbols)
+ return 0;
+
+ scn = elf_sec_by_idx(obj, obj->efile.symbols_shndx);
+ if (elf_sec_hdr(obj, scn, &sh))
+ return -LIBBPF_ERRNO__FORMAT;
+
+ n = sh.sh_size / sh.sh_entsize;
+ pr_debug("looking for externs among %d symbols...\n", n);
+
+ for (i = 0; i < n; i++) {
+ GElf_Sym sym;
+
+ if (!gelf_getsym(obj->efile.symbols, i, &sym))
+ return -LIBBPF_ERRNO__FORMAT;
+ if (!sym_is_extern(&sym))
+ continue;
+ ext_name = elf_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 = GELF_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) {
+ 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 (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 var '%s'\n",
+ ext_name);
+ return -ESRCH;
+ }
+ 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;
}
struct bpf_program *
@@ -1680,12 +3263,45 @@
struct bpf_program *pos;
bpf_object__for_each_program(pos, obj) {
- if (pos->section_name && !strcmp(pos->section_name, title))
+ if (pos->sec_name && !strcmp(pos->sec_name, title))
return pos;
}
return NULL;
}
+static bool prog_is_subprog(const struct bpf_object *obj,
+ const struct bpf_program *prog)
+{
+ /* For legacy reasons, libbpf supports an entry-point BPF programs
+ * without SEC() attribute, i.e., those in the .text section. But if
+ * there are 2 or more such programs in the .text section, they all
+ * must be subprograms called from entry-point BPF programs in
+ * designated SEC()'tions, otherwise there is no way to distinguish
+ * which of those programs should be loaded vs which are a subprogram.
+ * Similarly, if there is a function/program in .text and at least one
+ * other BPF program with custom SEC() attribute, then we just assume
+ * .text programs are subprograms (even if they are not called from
+ * other programs), because libbpf never explicitly supported mixing
+ * SEC()-designated BPF programs and .text entry-point BPF programs.
+ */
+ 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 NULL;
+}
+
static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
int shndx)
{
@@ -1701,14 +3317,6 @@
shndx == obj->efile.btf_maps_shndx;
}
-static bool bpf_object__relo_in_known_section(const struct bpf_object *obj,
- int shndx)
-{
- return shndx == obj->efile.text_shndx ||
- bpf_object__shndx_is_maps(obj, shndx) ||
- bpf_object__shndx_is_data(obj, shndx);
-}
-
static enum libbpf_map_type
bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
{
@@ -1718,134 +3326,254 @@
return LIBBPF_MAP_BSS;
else if (shndx == obj->efile.rodata_shndx)
return LIBBPF_MAP_RODATA;
+ else if (shndx == obj->efile.symbols_shndx)
+ return LIBBPF_MAP_KCONFIG;
else
return LIBBPF_MAP_UNSPEC;
}
+static int bpf_program__record_reloc(struct bpf_program *prog,
+ struct reloc_desc *reloc_desc,
+ __u32 insn_idx, const char *sym_name,
+ const GElf_Sym *sym, const GElf_Rel *rel)
+{
+ struct bpf_insn *insn = &prog->insns[insn_idx];
+ size_t map_idx, nr_maps = prog->obj->nr_maps;
+ struct bpf_object *obj = prog->obj;
+ __u32 shdr_idx = sym->st_shndx;
+ enum libbpf_map_type type;
+ const char *sym_sec_name;
+ struct bpf_map *map;
+
+ reloc_desc->processed = false;
+
+ /* sub-program call relocation */
+ if (insn->code == (BPF_JMP | BPF_CALL)) {
+ 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 (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) {
+ 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 = GELF_R_SYM(rel->r_info);
+ int i, n = obj->nr_extern;
+ struct extern_desc *ext;
+
+ for (i = 0; i < n; i++) {
+ ext = &obj->externs[i];
+ if (ext->sym_idx == sym_idx)
+ break;
+ }
+ if (i >= n) {
+ pr_warn("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);
+ reloc_desc->type = RELO_EXTERN;
+ reloc_desc->insn_idx = insn_idx;
+ reloc_desc->sym_off = i; /* sym_off stores extern index */
+ 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;
+ }
+
+ 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)
+ 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;
+
+ 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_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
- Elf_Data *data, struct bpf_object *obj)
+bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data *data)
{
Elf_Data *symbols = obj->efile.symbols;
- struct bpf_map *maps = obj->maps;
- size_t nr_maps = obj->nr_maps;
- int i, nrels;
+ const char *relo_sec_name, *sec_name;
+ size_t sec_idx = shdr->sh_info;
+ struct bpf_program *prog;
+ struct reloc_desc *relos;
+ int err, i, nrels;
+ const char *sym_name;
+ __u32 insn_idx;
+ GElf_Sym sym;
+ GElf_Rel rel;
- pr_debug("collecting relocating info for: '%s'\n", prog->section_name);
+ relo_sec_name = elf_sec_str(obj, shdr->sh_name);
+ sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
+ 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;
- prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
- if (!prog->reloc_desc) {
- pr_warning("failed to alloc memory in relocation\n");
- return -ENOMEM;
- }
- prog->nr_reloc = nrels;
-
for (i = 0; i < nrels; i++) {
- struct bpf_insn *insns = prog->insns;
- enum libbpf_map_type type;
- unsigned int insn_idx;
- unsigned int shdr_idx;
- const char *name;
- size_t map_idx;
- GElf_Sym sym;
- GElf_Rel rel;
-
if (!gelf_getrel(data, i, &rel)) {
- pr_warning("relocation: failed to get %d reloc\n", i);
+ pr_warn("sec '%s': failed to get relo #%d\n", relo_sec_name, i);
return -LIBBPF_ERRNO__FORMAT;
}
-
if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
- pr_warning("relocation: symbol %"PRIx64" not found\n",
- GELF_R_SYM(rel.r_info));
+ pr_warn("sec '%s': symbol 0x%zx not found for relo #%d\n",
+ relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+ if (rel.r_offset % BPF_INSN_SZ) {
+ pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n",
+ relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
return -LIBBPF_ERRNO__FORMAT;
}
- name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
- sym.st_name) ? : "<?>";
+ 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 (GELF_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("relo for %lld value %lld name %d (\'%s\')\n",
- (long long) (rel.r_info >> 32),
- (long long) sym.st_value, sym.st_name, name);
+ pr_debug("sec '%s': relo #%d: insn #%u against '%s'\n",
+ relo_sec_name, i, insn_idx, sym_name);
- shdr_idx = sym.st_shndx;
- insn_idx = rel.r_offset / sizeof(struct bpf_insn);
- pr_debug("relocation: insn_idx=%u, shdr_idx=%u\n",
- insn_idx, shdr_idx);
-
- if (shdr_idx >= SHN_LORESERVE) {
- pr_warning("relocation: not yet supported relo for non-static global \'%s\' variable in special section (0x%x) found in insns[%d].code 0x%x\n",
- name, shdr_idx, insn_idx,
- insns[insn_idx].code);
- return -LIBBPF_ERRNO__RELOC;
- }
- if (!bpf_object__relo_in_known_section(obj, shdr_idx)) {
- pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n",
- prog->section_name, shdr_idx);
+ prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx);
+ if (!prog) {
+ pr_warn("sec '%s': relo #%d: program not found in section '%s' for insn #%u\n",
+ relo_sec_name, i, sec_name, insn_idx);
return -LIBBPF_ERRNO__RELOC;
}
- if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) {
- if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) {
- pr_warning("incorrect bpf_call opcode\n");
- return -LIBBPF_ERRNO__RELOC;
- }
- prog->reloc_desc[i].type = RELO_CALL;
- prog->reloc_desc[i].insn_idx = insn_idx;
- prog->reloc_desc[i].text_off = sym.st_value;
- obj->has_pseudo_calls = true;
- continue;
- }
+ relos = libbpf_reallocarray(prog->reloc_desc,
+ prog->nr_reloc + 1, sizeof(*relos));
+ if (!relos)
+ return -ENOMEM;
+ prog->reloc_desc = relos;
- if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
- pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
- insn_idx, insns[insn_idx].code);
- return -LIBBPF_ERRNO__RELOC;
- }
+ /* 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;
- if (bpf_object__shndx_is_maps(obj, shdr_idx) ||
- bpf_object__shndx_is_data(obj, shdr_idx)) {
- type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
- if (type != LIBBPF_MAP_UNSPEC) {
- if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
- pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
- name, insn_idx, insns[insn_idx].code);
- return -LIBBPF_ERRNO__RELOC;
- }
- if (!obj->caps.global_data) {
- pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n",
- name, insn_idx);
- return -LIBBPF_ERRNO__RELOC;
- }
- }
-
- for (map_idx = 0; map_idx < nr_maps; map_idx++) {
- if (maps[map_idx].libbpf_type != type)
- continue;
- if (type != LIBBPF_MAP_UNSPEC ||
- (maps[map_idx].sec_idx == sym.st_shndx &&
- maps[map_idx].sec_offset == sym.st_value)) {
- pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n",
- map_idx, maps[map_idx].name,
- maps[map_idx].sec_idx,
- maps[map_idx].sec_offset,
- insn_idx);
- break;
- }
- }
-
- if (map_idx >= nr_maps) {
- pr_warning("bpf relocation: map_idx %d larger than %d\n",
- (int)map_idx, (int)nr_maps - 1);
- return -LIBBPF_ERRNO__RELOC;
- }
-
- prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
- RELO_DATA : RELO_LD64;
- prog->reloc_desc[i].insn_idx = insn_idx;
- prog->reloc_desc[i].map_idx = map_idx;
- }
+ prog->nr_reloc++;
}
return 0;
}
@@ -1856,8 +3584,12 @@
__u32 key_type_id = 0, value_type_id = 0;
int ret;
- /* if it's BTF-defined map, we don't need to search for type IDs */
- if (map->sec_idx == obj->efile.btf_maps_shndx)
+ /* if it's BTF-defined map, we don't need to search for type IDs.
+ * For struct_ops map, it does not need btf_key_type_id and
+ * btf_value_type_id.
+ */
+ if (map->sec_idx == obj->efile.btf_maps_shndx ||
+ bpf_map__is_struct_ops(map))
return 0;
if (!bpf_map__is_internal(map)) {
@@ -1881,6 +3613,42 @@
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;
+}
+
int bpf_map__reuse_fd(struct bpf_map *map, int fd)
{
struct bpf_map_info info = {};
@@ -1889,6 +3657,8 @@
char *new_name;
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 err;
@@ -1924,6 +3694,7 @@
map->def.map_flags = info.map_flags;
map->btf_key_type_id = info.btf_key_type_id;
map->btf_value_type_id = info.btf_value_type_id;
+ map->reused = true;
return 0;
@@ -1934,22 +3705,29 @@
return err;
}
+__u32 bpf_map__max_entries(const struct bpf_map *map)
+{
+ return map->def.max_entries;
+}
+
+int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
+{
+ if (map->fd >= 0)
+ return -EBUSY;
+ map->def.max_entries = max_entries;
+ return 0;
+}
+
int bpf_map__resize(struct bpf_map *map, __u32 max_entries)
{
if (!map || !max_entries)
return -EINVAL;
- /* If map already created, its attributes can't be changed. */
- if (map->fd >= 0)
- return -EBUSY;
-
- map->def.max_entries = max_entries;
-
- return 0;
+ return bpf_map__set_max_entries(map, max_entries);
}
static int
-bpf_object__probe_name(struct bpf_object *obj)
+bpf_object__probe_loading(struct bpf_object *obj)
{
struct bpf_load_program_attr attr;
char *cp, errmsg[STRERR_BUFSIZE];
@@ -1969,27 +3747,48 @@
ret = bpf_load_program_xattr(&attr, NULL, 0);
if (ret < 0) {
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n",
- __func__, cp, errno);
- return -errno;
+ 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);
- /* now try the same program, but with the name */
-
- attr.name = "test";
- ret = bpf_load_program_xattr(&attr, NULL, 0);
- if (ret >= 0) {
- obj->caps.name = 1;
- close(ret);
- }
-
return 0;
}
-static int
-bpf_object__probe_global_data(struct bpf_object *obj)
+static int probe_fd(int fd)
+{
+ if (fd >= 0)
+ close(fd);
+ return fd >= 0;
+}
+
+static int probe_kern_prog_name(void)
+{
+ struct bpf_load_program_attr attr;
+ struct bpf_insn insns[] = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+ int ret;
+
+ /* make sure loading with name works */
+
+ memset(&attr, 0, sizeof(attr));
+ attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+ attr.insns = insns;
+ attr.insns_cnt = ARRAY_SIZE(insns);
+ attr.license = "GPL";
+ attr.name = "test";
+ ret = bpf_load_program_xattr(&attr, NULL, 0);
+ return probe_fd(ret);
+}
+
+static int probe_kern_global_data(void)
{
struct bpf_load_program_attr prg_attr;
struct bpf_create_map_attr map_attr;
@@ -2010,10 +3809,11 @@
map = bpf_create_map_xattr(&map_attr);
if (map < 0) {
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n",
- __func__, cp, errno);
- return -errno;
+ 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;
@@ -2025,18 +3825,25 @@
prg_attr.license = "GPL";
ret = bpf_load_program_xattr(&prg_attr, NULL, 0);
- if (ret >= 0) {
- obj->caps.global_data = 1;
- close(ret);
- }
-
close(map);
- return 0;
+ return probe_fd(ret);
}
-static int bpf_object__probe_btf_func(struct bpf_object *obj)
+static int probe_kern_btf(void)
{
- const char strs[] = "\0int\0x\0a";
+ 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 */
@@ -2047,22 +3854,32 @@
/* FUNC x */ /* [3] */
BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
};
- int btf_fd;
- btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
- strs, sizeof(strs));
- if (btf_fd >= 0) {
- obj->caps.btf_func = 1;
- close(btf_fd);
- return 1;
- }
-
- return 0;
+ return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+ strs, sizeof(strs)));
}
-static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
+static int probe_kern_btf_func_global(void)
{
- const char strs[] = "\0x\0.data";
+ 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 */
@@ -2074,232 +3891,473 @@
BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
BTF_VAR_SECINFO_ENC(2, 0, 4),
};
- int btf_fd;
- btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
- strs, sizeof(strs));
- if (btf_fd >= 0) {
- obj->caps.btf_datasec = 1;
- close(btf_fd);
- return 1;
+ return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+ strs, sizeof(strs)));
+}
+
+static int probe_kern_array_mmap(void)
+{
+ struct bpf_create_map_attr attr = {
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_flags = BPF_F_MMAPABLE,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+ };
+
+ return probe_fd(bpf_create_map_xattr(&attr));
+}
+
+static int probe_kern_exp_attach_type(void)
+{
+ struct bpf_load_program_attr attr;
+ struct bpf_insn insns[] = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+
+ memset(&attr, 0, sizeof(attr));
+ /* use any valid combination of program type and (optional)
+ * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
+ * to see if kernel supports expected_attach_type field for
+ * BPF_PROG_LOAD command
+ */
+ attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
+ attr.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE;
+ attr.insns = insns;
+ attr.insns_cnt = ARRAY_SIZE(insns);
+ attr.license = "GPL";
+
+ return probe_fd(bpf_load_program_xattr(&attr, NULL, 0));
+}
+
+static int probe_kern_probe_read_kernel(void)
+{
+ struct bpf_load_program_attr attr;
+ struct bpf_insn insns[] = {
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */
+ 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(),
+ };
+
+ memset(&attr, 0, sizeof(attr));
+ attr.prog_type = BPF_PROG_TYPE_KPROBE;
+ attr.insns = insns;
+ attr.insns_cnt = ARRAY_SIZE(insns);
+ attr.license = "GPL";
+
+ return probe_fd(bpf_load_program_xattr(&attr, NULL, 0));
+}
+
+static int probe_prog_bind_map(void)
+{
+ struct bpf_load_program_attr prg_attr;
+ struct bpf_create_map_attr map_attr;
+ char *cp, errmsg[STRERR_BUFSIZE];
+ struct bpf_insn insns[] = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+ int ret, map, prog;
+
+ memset(&map_attr, 0, sizeof(map_attr));
+ map_attr.map_type = BPF_MAP_TYPE_ARRAY;
+ map_attr.key_size = sizeof(int);
+ map_attr.value_size = 32;
+ map_attr.max_entries = 1;
+
+ map = bpf_create_map_xattr(&map_attr);
+ 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;
}
- return 0;
+ memset(&prg_attr, 0, sizeof(prg_attr));
+ prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+ prg_attr.insns = insns;
+ prg_attr.insns_cnt = ARRAY_SIZE(insns);
+ prg_attr.license = "GPL";
+
+ prog = bpf_load_program_xattr(&prg_attr, NULL, 0);
+ if (prog < 0) {
+ close(map);
+ return 0;
+ }
+
+ ret = bpf_prog_bind_map(prog, map, NULL);
+
+ close(map);
+ close(prog);
+
+ return ret >= 0;
+}
+
+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,
+ }
+};
+
+static bool kernel_supports(enum kern_feature_id feat_id)
+{
+ struct kern_feature_desc *feat = &feature_probes[feat_id];
+ int ret;
+
+ 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;
+ int err;
+
+ map_info_len = sizeof(map_info);
+
+ 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);
}
static int
-bpf_object__probe_caps(struct bpf_object *obj)
+bpf_object__reuse_map(struct bpf_map *map)
{
- int (*probe_fn[])(struct bpf_object *obj) = {
- bpf_object__probe_name,
- bpf_object__probe_global_data,
- bpf_object__probe_btf_func,
- bpf_object__probe_btf_datasec,
- };
- int i, ret;
+ char *cp, errmsg[STRERR_BUFSIZE];
+ int err, pin_fd;
- for (i = 0; i < ARRAY_SIZE(probe_fn); i++) {
- ret = probe_fn[i](obj);
- if (ret < 0)
- pr_debug("Probe #%d failed with %d.\n", i, ret);
+ pin_fd = bpf_obj_get(map->pin_path);
+ if (pin_fd < 0) {
+ err = -errno;
+ if (err == -ENOENT) {
+ pr_debug("found no pinned map to reuse at '%s'\n",
+ map->pin_path);
+ return 0;
+ }
+
+ cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
+ pr_warn("couldn't retrieve pinned map '%s': %s\n",
+ map->pin_path, cp);
+ return err;
}
+ if (!map_is_reuse_compat(map, pin_fd)) {
+ pr_warn("couldn't reuse pinned map at '%s': parameter mismatch\n",
+ map->pin_path);
+ close(pin_fd);
+ return -EINVAL;
+ }
+
+ err = bpf_map__reuse_fd(map, pin_fd);
+ if (err) {
+ close(pin_fd);
+ return err;
+ }
+ map->pinned = true;
+ pr_debug("reused pinned map at '%s'\n", map->pin_path);
+
return 0;
}
static int
bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
{
+ enum libbpf_map_type map_type = map->libbpf_type;
char *cp, errmsg[STRERR_BUFSIZE];
int err, zero = 0;
- __u8 *data;
- /* Nothing to do here since kernel already zero-initializes .bss map. */
- if (map->libbpf_type == LIBBPF_MAP_BSS)
- 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;
+ }
- data = map->libbpf_type == LIBBPF_MAP_DATA ?
- obj->sections.data : obj->sections.rodata;
-
- err = bpf_map_update_elem(map->fd, &zero, data, 0);
- /* Freeze .rodata map as read-only from syscall side. */
- if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) {
+ /* Freeze .rodata and .kconfig map as read-only from syscall side. */
+ if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG) {
err = bpf_map_freeze(map->fd);
if (err) {
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("Error freezing map(%s) as read-only: %s\n",
- map->name, cp);
- err = 0;
+ err = -errno;
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
+ pr_warn("Error freezing map(%s) as read-only: %s\n",
+ map->name, cp);
+ return err;
}
}
+ return 0;
+}
+
+static void bpf_map__destroy(struct bpf_map *map);
+
+static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
+{
+ struct bpf_create_map_attr create_attr;
+ struct bpf_map_def *def = &map->def;
+ int err = 0;
+
+ memset(&create_attr, 0, sizeof(create_attr));
+
+ if (kernel_supports(FEAT_PROG_NAME))
+ create_attr.name = map->name;
+ create_attr.map_ifindex = map->map_ifindex;
+ create_attr.map_type = def->type;
+ create_attr.map_flags = def->map_flags;
+ create_attr.key_size = def->key_size;
+ create_attr.value_size = def->value_size;
+ create_attr.numa_node = map->numa_node;
+
+ if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !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);
+ create_attr.max_entries = nr_cpus;
+ } else {
+ create_attr.max_entries = def->max_entries;
+ }
+
+ if (bpf_map__is_struct_ops(map))
+ create_attr.btf_vmlinux_value_type_id =
+ map->btf_vmlinux_value_type_id;
+
+ create_attr.btf_fd = 0;
+ create_attr.btf_key_type_id = 0;
+ create_attr.btf_value_type_id = 0;
+ if (obj->btf && btf__fd(obj->btf) >= 0 && !bpf_map_find_btf_info(obj, map)) {
+ create_attr.btf_fd = btf__fd(obj->btf);
+ create_attr.btf_key_type_id = map->btf_key_type_id;
+ 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);
+ 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;
+ }
+
+ map->fd = bpf_create_map_xattr(&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_create_map_xattr(&create_attr);
+ }
+
+ err = map->fd < 0 ? -errno : 0;
+
+ if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) {
+ bpf_map__destroy(map->inner_map);
+ zfree(&map->inner_map);
+ }
+
return err;
}
+static int init_map_slots(struct bpf_map *map)
+{
+ const struct bpf_map *targ_map;
+ unsigned int i;
+ int fd, err;
+
+ 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);
+ 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
bpf_object__create_maps(struct bpf_object *obj)
{
- struct bpf_create_map_attr create_attr = {};
- int nr_cpus = 0;
- unsigned int i;
+ 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++) {
- struct bpf_map *map = &obj->maps[i];
- struct bpf_map_def *def = &map->def;
- char *cp, errmsg[STRERR_BUFSIZE];
- int *pfd = &map->fd;
+ map = &obj->maps[i];
+
+ 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("skip map create (preset) %s: fd=%d\n",
+ pr_debug("map '%s': skipping creation (preset fd=%d)\n",
map->name, map->fd);
- continue;
- }
-
- if (obj->caps.name)
- create_attr.name = map->name;
- create_attr.map_ifindex = map->map_ifindex;
- create_attr.map_type = def->type;
- create_attr.map_flags = def->map_flags;
- create_attr.key_size = def->key_size;
- create_attr.value_size = def->value_size;
- if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
- !def->max_entries) {
- if (!nr_cpus)
- nr_cpus = libbpf_num_possible_cpus();
- if (nr_cpus < 0) {
- pr_warning("failed to determine number of system CPUs: %d\n",
- nr_cpus);
- err = nr_cpus;
- goto err_out;
- }
- pr_debug("map '%s': setting size to %d\n",
- map->name, nr_cpus);
- create_attr.max_entries = nr_cpus;
} else {
- create_attr.max_entries = def->max_entries;
- }
- create_attr.btf_fd = 0;
- create_attr.btf_key_type_id = 0;
- create_attr.btf_value_type_id = 0;
- if (bpf_map_type__is_map_in_map(def->type) &&
- map->inner_map_fd >= 0)
- create_attr.inner_map_fd = map->inner_map_fd;
-
- if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
- create_attr.btf_fd = btf__fd(obj->btf);
- create_attr.btf_key_type_id = map->btf_key_type_id;
- create_attr.btf_value_type_id = map->btf_value_type_id;
- }
-
- *pfd = bpf_create_map_xattr(&create_attr);
- if (*pfd < 0 && (create_attr.btf_key_type_id ||
- create_attr.btf_value_type_id)) {
- err = -errno;
- cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
- pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
- map->name, cp, err);
- 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;
- *pfd = bpf_create_map_xattr(&create_attr);
- }
-
- if (*pfd < 0) {
- size_t j;
-
- err = -errno;
-err_out:
- cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
- pr_warning("failed to create map (name: '%s'): %s(%d)\n",
- map->name, cp, err);
- for (j = 0; j < i; j++)
- zclose(obj->maps[j].fd);
- return err;
- }
-
- if (bpf_map__is_internal(map)) {
- err = bpf_object__populate_internal_map(obj, map);
- if (err < 0) {
- zclose(*pfd);
+ err = bpf_object__create_map(obj, map);
+ 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) {
+ err = init_map_slots(map);
+ if (err < 0) {
+ zclose(map->fd);
+ goto err_out;
+ }
}
}
- pr_debug("created map %s: fd=%d\n", map->name, *pfd);
+ 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;
-}
-static int
-check_btf_ext_reloc_err(struct bpf_program *prog, int err,
- void *btf_prog_info, const char *info_name)
-{
- if (err != -ENOENT) {
- pr_warning("Error in loading %s for sec %s.\n",
- info_name, prog->section_name);
- return err;
- }
-
- /* err == -ENOENT (i.e. prog->section_name not found in btf_ext) */
-
- if (btf_prog_info) {
- /*
- * Some info has already been found but has problem
- * in the last btf_ext reloc. Must have to error out.
- */
- pr_warning("Error in relocating %s for sec %s.\n",
- info_name, prog->section_name);
- return err;
- }
-
- /* Have problem loading the very first info. Ignore the rest. */
- pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n",
- info_name, prog->section_name, info_name);
- return 0;
-}
-
-static int
-bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
- const char *section_name, __u32 insn_offset)
-{
- int err;
-
- if (!insn_offset || prog->func_info) {
- /*
- * !insn_offset => main program
- *
- * For sub prog, the main program's func_info has to
- * be loaded first (i.e. prog->func_info != NULL)
- */
- err = btf_ext__reloc_func_info(obj->btf, obj->btf_ext,
- section_name, insn_offset,
- &prog->func_info,
- &prog->func_info_cnt);
- if (err)
- return check_btf_ext_reloc_err(prog, err,
- prog->func_info,
- "bpf_func_info");
-
- prog->func_info_rec_size = btf_ext__func_info_rec_size(obj->btf_ext);
- }
-
- if (!insn_offset || prog->line_info) {
- err = btf_ext__reloc_line_info(obj->btf, obj->btf_ext,
- section_name, insn_offset,
- &prog->line_info,
- &prog->line_info_cnt);
- if (err)
- return check_btf_ext_reloc_err(prog, err,
- prog->line_info,
- "bpf_line_info");
-
- prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
- }
-
- 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;
}
#define BPF_CORE_SPEC_MAX_LEN 64
@@ -2315,14 +4373,18 @@
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 byte offset represented by spec */
- __u32 offset;
+ /* field bit offset represented by spec */
+ __u32 bit_offset;
};
static bool str_is_empty(const char *s)
@@ -2330,11 +4392,84 @@
return !s || !s[0];
}
+static bool is_flex_arr(const struct btf *btf,
+ const struct bpf_core_accessor *acc,
+ const struct btf_array *arr)
+{
+ const struct btf_type *t;
+
+ /* not a flexible array, if not inside a struct or has non-zero size */
+ if (!acc->name || arr->nelems > 0)
+ return false;
+
+ /* has to be the last member of enclosing struct */
+ t = btf__type_by_id(btf, acc->type_id);
+ return acc->idx == btf_vlen(t) - 1;
+}
+
+static const char *core_relo_kind_str(enum bpf_core_relo_kind kind)
+{
+ switch (kind) {
+ case BPF_FIELD_BYTE_OFFSET: return "byte_off";
+ case BPF_FIELD_BYTE_SIZE: return "byte_sz";
+ case BPF_FIELD_EXISTS: return "field_exists";
+ case BPF_FIELD_SIGNED: return "signed";
+ case BPF_FIELD_LSHIFT_U64: return "lshift_u64";
+ case BPF_FIELD_RSHIFT_U64: return "rshift_u64";
+ case BPF_TYPE_ID_LOCAL: return "local_type_id";
+ case BPF_TYPE_ID_TARGET: return "target_type_id";
+ case BPF_TYPE_EXISTS: return "type_exists";
+ case BPF_TYPE_SIZE: return "type_size";
+ case BPF_ENUMVAL_EXISTS: return "enumval_exists";
+ case BPF_ENUMVAL_VALUE: return "enumval_value";
+ default: return "unknown";
+ }
+}
+
+static bool core_relo_is_field_based(enum bpf_core_relo_kind kind)
+{
+ switch (kind) {
+ case BPF_FIELD_BYTE_OFFSET:
+ case BPF_FIELD_BYTE_SIZE:
+ case BPF_FIELD_EXISTS:
+ case BPF_FIELD_SIGNED:
+ case BPF_FIELD_LSHIFT_U64:
+ case BPF_FIELD_RSHIFT_U64:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool core_relo_is_type_based(enum bpf_core_relo_kind kind)
+{
+ switch (kind) {
+ case BPF_TYPE_ID_LOCAL:
+ case BPF_TYPE_ID_TARGET:
+ case BPF_TYPE_EXISTS:
+ case BPF_TYPE_SIZE:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
+{
+ switch (kind) {
+ case BPF_ENUMVAL_EXISTS:
+ case BPF_ENUMVAL_VALUE:
+ return true;
+ default:
+ return false;
+ }
+}
+
/*
- * Turn bpf_offset_reloc into a low- and high-level spec representation,
+ * Turn bpf_core_relo into a low- and high-level spec representation,
* validating correctness along the way, as well as calculating resulting
- * field offset (in bytes), specified by accessor string. Low-level spec
- * captures every single level of nestedness, including traversing anonymous
+ * 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:
@@ -2360,13 +4495,21 @@
* - 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_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.
*/
-static int bpf_core_spec_parse(const struct btf *btf,
+static int bpf_core_parse_spec(const struct btf *btf,
__u32 type_id,
const char *spec_str,
+ enum bpf_core_relo_kind relo_kind,
struct bpf_core_spec *spec)
{
int access_idx, parsed_len, i;
+ struct bpf_core_accessor *acc;
const struct btf_type *t;
const char *name;
__u32 id;
@@ -2377,6 +4520,15 @@
memset(spec, 0, sizeof(*spec));
spec->btf = btf;
+ spec->root_type_id = 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) {
@@ -2393,20 +4545,32 @@
if (spec->raw_len == 0)
return -EINVAL;
- /* first spec value is always reloc type array index */
t = skip_mods_and_typedefs(btf, type_id, &id);
if (!t)
return -EINVAL;
access_idx = spec->raw_spec[0];
- spec->spec[0].type_id = id;
- spec->spec[0].idx = access_idx;
+ 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_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t))
+ return -EINVAL;
+
+ /* record enumerator name in a first accessor */
+ acc->name = btf__name_by_offset(btf, btf_enum(t)[access_idx].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->offset = access_idx * sz;
+ spec->bit_offset = access_idx * sz * 8;
for (i = 1; i < spec->raw_len; i++) {
t = skip_mods_and_typedefs(btf, id, &id);
@@ -2414,20 +4578,17 @@
return -EINVAL;
access_idx = spec->raw_spec[i];
+ acc = &spec->spec[spec->len];
if (btf_is_composite(t)) {
const struct btf_member *m;
- __u32 offset;
+ __u32 bit_offset;
if (access_idx >= btf_vlen(t))
return -EINVAL;
- if (btf_member_bitfield_size(t, access_idx))
- return -EINVAL;
- offset = btf_member_bit_offset(t, access_idx);
- if (offset % 8)
- return -EINVAL;
- spec->offset += offset / 8;
+ bit_offset = btf_member_bit_offset(t, access_idx);
+ spec->bit_offset += bit_offset;
m = btf_members(t) + access_idx;
if (m->name_off) {
@@ -2435,18 +4596,23 @@
if (str_is_empty(name))
return -EINVAL;
- spec->spec[spec->len].type_id = id;
- spec->spec[spec->len].idx = access_idx;
- spec->spec[spec->len].name = name;
+ 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 || access_idx >= a->nelems)
+ 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;
@@ -2456,10 +4622,10 @@
sz = btf__resolve_size(btf, id);
if (sz < 0)
return sz;
- spec->offset += access_idx * sz;
+ spec->bit_offset += access_idx * sz * 8;
} else {
- pr_warning("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n",
- type_id, spec_str, i, id, btf_kind(t));
+ pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n",
+ type_id, spec_str, i, id, btf_kind_str(t));
return -EINVAL;
}
}
@@ -2509,16 +4675,16 @@
{
size_t local_essent_len, targ_essent_len;
const char *local_name, *targ_name;
- const struct btf_type *t;
+ const struct btf_type *t, *local_t;
struct ids_vec *cand_ids;
__u32 *new_ids;
int i, err, n;
- t = btf__type_by_id(local_btf, local_type_id);
- if (!t)
+ 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, t->name_off);
+ 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);
@@ -2530,6 +4696,9 @@
n = btf__get_nr_types(targ_btf);
for (i = 1; i <= n; i++) {
t = btf__type_by_id(targ_btf, i);
+ if (btf_kind(t) != btf_kind(local_t))
+ continue;
+
targ_name = btf__name_by_offset(targ_btf, t->name_off);
if (str_is_empty(targ_name))
continue;
@@ -2539,11 +4708,12 @@
continue;
if (strncmp(local_name, targ_name, local_essent_len) == 0) {
- pr_debug("[%d] %s: found candidate [%d] %s\n",
- local_type_id, local_name, i, targ_name);
- new_ids = reallocarray(cand_ids->data,
- cand_ids->len + 1,
- sizeof(*cand_ids->data));
+ pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s\n",
+ local_type_id, btf_kind_str(local_t),
+ local_name, i, btf_kind_str(t), targ_name);
+ new_ids = libbpf_reallocarray(cand_ids->data,
+ cand_ids->len + 1,
+ sizeof(*cand_ids->data));
if (!new_ids) {
err = -ENOMEM;
goto err_out;
@@ -2558,13 +4728,16 @@
return ERR_PTR(err);
}
-/* Check two types for compatibility, skipping const/volatile/restrict and
- * typedefs, to ensure we are relocating offset to the compatible entities:
+/* 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;
+ * - 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 bitness should match, signedness is ignored;
+ * - for INT, size and signedness are ignored;
* - for ARRAY, dimensionality is ignored, element types are checked for
* compatibility recursively;
* - everything else shouldn't be ever a target of relocation.
@@ -2590,23 +4763,36 @@
return 0;
switch (btf_kind(local_type)) {
- case BTF_KIND_FWD:
case BTF_KIND_PTR:
return 1;
- case BTF_KIND_ENUM:
- return local_type->size == targ_type->size;
+ case BTF_KIND_FWD:
+ case BTF_KIND_ENUM: {
+ const char *local_name, *targ_name;
+ size_t local_len, targ_len;
+
+ local_name = btf__name_by_offset(local_btf,
+ local_type->name_off);
+ targ_name = btf__name_by_offset(targ_btf, targ_type->name_off);
+ local_len = bpf_core_essential_name_len(local_name);
+ targ_len = bpf_core_essential_name_len(targ_name);
+ /* one of them is anonymous or both w/ same flavor-less names */
+ return local_len == 0 || targ_len == 0 ||
+ (local_len == targ_len &&
+ strncmp(local_name, targ_name, local_len) == 0);
+ }
case BTF_KIND_INT:
+ /* just reject deprecated bitfield-like integers; all other
+ * integers are by default compatible between each other
+ */
return btf_int_offset(local_type) == 0 &&
- btf_int_offset(targ_type) == 0 &&
- local_type->size == targ_type->size &&
- btf_int_bits(local_type) == btf_int_bits(targ_type);
+ btf_int_offset(targ_type) == 0;
case BTF_KIND_ARRAY:
local_id = btf_array(local_type)->type;
targ_id = btf_array(targ_type)->type;
goto recur;
default:
- pr_warning("unexpected kind %d relocated, local [%d], target [%d]\n",
- btf_kind(local_type), local_id, targ_id);
+ pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n",
+ btf_kind(local_type), local_id, targ_id);
return 0;
}
}
@@ -2615,7 +4801,7 @@
* 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
- * offset.
+ * bit offset.
*
* Searching is performed through recursive exhaustive enumeration of all
* fields of a struct/union. If there are any anonymous (embedded)
@@ -2654,21 +4840,16 @@
n = btf_vlen(targ_type);
m = btf_members(targ_type);
for (i = 0; i < n; i++, m++) {
- __u32 offset;
+ __u32 bit_offset;
- /* bitfield relocations not supported */
- if (btf_member_bitfield_size(targ_type, i))
- continue;
- offset = btf_member_bit_offset(targ_type, i);
- if (offset % 8)
- continue;
+ 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->offset += offset / 8;
+ spec->bit_offset += bit_offset;
spec->raw_spec[spec->raw_len++] = i;
targ_name = btf__name_by_offset(targ_btf, m->name_off);
@@ -2697,16 +4878,110 @@
return found;
}
/* member turned out not to be what we looked for */
- spec->offset -= offset / 8;
+ spec->bit_offset -= bit_offset;
spec->raw_len--;
}
return 0;
}
+/* 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.
+ */
+static int bpf_core_types_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;
+ 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(local_type) != btf_kind(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(local_type) != btf_kind(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:
+ 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++) {
+ 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);
+ 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;
+ }
+}
+
/*
* Try to match local spec to a target type and, if successful, produce full
- * target spec (high-level, low-level + offset).
+ * 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,
@@ -2719,10 +4994,51 @@
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)) {
+ 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 struct btf_enum *e;
+ 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_enum(targ_type))
+ return 0;
+
+ local_essent_len = bpf_core_essential_name_len(local_acc->name);
+
+ for (i = 0, e = btf_enum(targ_type); i < btf_vlen(targ_type); i++, e++) {
+ targ_name = btf__name_by_offset(targ_spec->btf, e->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);
@@ -2743,12 +5059,14 @@
*/
if (i > 0) {
const struct btf_array *a;
+ bool flex;
if (!btf_is_array(targ_type))
return 0;
a = btf_array(targ_type);
- if (local_acc->idx >= a->nelems)
+ 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))
@@ -2769,144 +5087,517 @@
sz = btf__resolve_size(targ_btf, targ_id);
if (sz < 0)
return sz;
- targ_spec->offset += local_acc->idx * sz;
+ targ_spec->bit_offset += local_acc->idx * sz * 8;
}
}
return 1;
}
+static int bpf_core_calc_field_relo(const struct bpf_program *prog,
+ const struct bpf_core_relo *relo,
+ const struct bpf_core_spec *spec,
+ __u32 *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_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_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_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_FIELD_BYTE_OFFSET:
+ *val = byte_off;
+ if (!bitfield) {
+ *field_sz = byte_sz;
+ *type_id = field_type_id;
+ }
+ break;
+ case BPF_FIELD_BYTE_SIZE:
+ *val = byte_sz;
+ break;
+ case BPF_FIELD_SIGNED:
+ /* enums will be assumed unsigned */
+ *val = btf_is_enum(mt) ||
+ (btf_int_encoding(mt) & BTF_INT_SIGNED);
+ if (validate)
+ *validate = true; /* signedness is never ambiguous */
+ break;
+ case BPF_FIELD_LSHIFT_U64:
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ *val = 64 - (bit_off + bit_sz - byte_off * 8);
+#else
+ *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
+#endif
+ break;
+ case BPF_FIELD_RSHIFT_U64:
+ *val = 64 - bit_sz;
+ if (validate)
+ *validate = true; /* right shift is never ambiguous */
+ break;
+ case BPF_FIELD_EXISTS:
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
+ const struct bpf_core_spec *spec,
+ __u32 *val)
+{
+ __s64 sz;
+
+ /* type-based relos return zero when target type is not found */
+ if (!spec) {
+ *val = 0;
+ return 0;
+ }
+
+ switch (relo->kind) {
+ case BPF_TYPE_ID_TARGET:
+ *val = spec->root_type_id;
+ break;
+ case BPF_TYPE_EXISTS:
+ *val = 1;
+ break;
+ case BPF_TYPE_SIZE:
+ sz = btf__resolve_size(spec->btf, spec->root_type_id);
+ if (sz < 0)
+ return -EINVAL;
+ *val = sz;
+ break;
+ case BPF_TYPE_ID_LOCAL:
+ /* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
+ const struct bpf_core_spec *spec,
+ __u32 *val)
+{
+ const struct btf_type *t;
+ const struct btf_enum *e;
+
+ switch (relo->kind) {
+ case BPF_ENUMVAL_EXISTS:
+ *val = spec ? 1 : 0;
+ break;
+ case BPF_ENUMVAL_VALUE:
+ if (!spec)
+ return -EUCLEAN; /* request instruction poisoning */
+ t = btf__type_by_id(spec->btf, spec->spec[0].type_id);
+ e = btf_enum(t) + spec->spec[0].idx;
+ *val = e->val;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+struct bpf_core_relo_res
+{
+ /* expected value in the instruction, unless validate == false */
+ __u32 orig_val;
+ /* new value that needs to be patched up to */
+ __u32 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;
+};
+
+/* 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 struct bpf_program *prog,
+ 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, relo, local_spec,
+ &res->orig_val, &res->orig_sz,
+ &res->orig_type_id, &res->validate);
+ err = err ?: bpf_core_calc_field_relo(prog, 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);
+ err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val);
+ } 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(struct bpf_program *prog, 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 bool is_ldimm64(struct bpf_insn *insn)
+{
+ return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
+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.
- * Expected insn->imm value is provided for validation, as well as the new
- * relocated value.
*
- * Currently three kinds of BPF instructions are supported:
+ * 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) = <imm> (indirect memory assignment with immediate operand).
- *
- * If actual insn->imm value is wrong, bail out.
+ * 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}.
*/
-static int bpf_core_reloc_insn(struct bpf_program *prog, int insn_off,
- __u32 orig_off, __u32 new_off)
+static int bpf_core_patch_insn(struct bpf_program *prog,
+ const struct bpf_core_relo *relo,
+ int relo_idx,
+ const struct bpf_core_relo_res *res)
{
+ __u32 orig_val, new_val;
struct bpf_insn *insn;
int insn_idx;
__u8 class;
- if (insn_off % sizeof(struct bpf_insn))
+ if (relo->insn_off % BPF_INSN_SZ)
return -EINVAL;
- insn_idx = insn_off / sizeof(struct bpf_insn);
-
+ insn_idx = relo->insn_off / BPF_INSN_SZ;
+ /* 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;
insn = &prog->insns[insn_idx];
class = BPF_CLASS(insn->code);
- if (class == BPF_ALU || class == BPF_ALU64) {
+ if (res->poison) {
+poison:
+ /* poison second part of ldimm64 to avoid confusing error from
+ * verifier about "unknown opcode 00"
+ */
+ if (is_ldimm64(insn))
+ bpf_core_poison_insn(prog, relo_idx, insn_idx + 1, insn + 1);
+ bpf_core_poison_insn(prog, 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 (insn->imm != orig_off)
+ if (res->validate && insn->imm != orig_val) {
+ pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n",
+ prog->name, relo_idx,
+ insn_idx, insn->imm, orig_val, new_val);
return -EINVAL;
- insn->imm = new_off;
- pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n",
- bpf_program__title(prog, false),
- insn_idx, orig_off, new_off);
- } else {
- pr_warning("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n",
- bpf_program__title(prog, false),
- insn_idx, insn->code, insn->src_reg, insn->dst_reg,
- insn->off, insn->imm);
+ }
+ orig_val = insn->imm;
+ insn->imm = new_val;
+ pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n",
+ prog->name, relo_idx, insn_idx,
+ orig_val, 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 %u -> %u\n",
+ prog->name, relo_idx, insn_idx, insn->off, orig_val, new_val);
+ return -EINVAL;
+ }
+ if (new_val > SHRT_MAX) {
+ pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n",
+ prog->name, relo_idx, insn_idx, 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 %u -> %u\n",
+ prog->name, relo_idx, insn_idx, orig_val, 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[0].src_reg != 0 || insn[0].off != 0 ||
+ insn_idx + 1 >= prog->insns_cnt ||
+ 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 = 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 %u -> %u\n",
+ prog->name, relo_idx,
+ insn_idx, (unsigned long long)imm,
+ orig_val, new_val);
+ return -EINVAL;
+ }
+
+ insn[0].imm = new_val;
+ insn[1].imm = 0; /* currently only 32-bit values are supported */
+ pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %u\n",
+ prog->name, relo_idx, insn_idx,
+ (unsigned long long)imm, 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;
}
-static struct btf *btf_load_raw(const char *path)
-{
- struct btf *btf;
- size_t read_cnt;
- struct stat st;
- void *data;
- FILE *f;
-
- if (stat(path, &st))
- return ERR_PTR(-errno);
-
- data = malloc(st.st_size);
- if (!data)
- return ERR_PTR(-ENOMEM);
-
- f = fopen(path, "rb");
- if (!f) {
- btf = ERR_PTR(-errno);
- goto cleanup;
- }
-
- read_cnt = fread(data, 1, st.st_size, f);
- fclose(f);
- if (read_cnt < st.st_size) {
- btf = ERR_PTR(-EBADF);
- goto cleanup;
- }
-
- btf = btf__new(data, read_cnt);
-
-cleanup:
- free(data);
- return btf;
-}
-
-/*
- * Probe few well-known locations for vmlinux kernel image and try to load BTF
- * data out of it to use for target BTF.
- */
-static struct btf *bpf_core_find_kernel_btf(void)
-{
- struct {
- const char *path_fmt;
- bool raw_btf;
- } locations[] = {
- /* try canonical vmlinux BTF through sysfs first */
- { "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
- /* fall back to trying to find vmlinux ELF on disk otherwise */
- { "/boot/vmlinux-%1$s" },
- { "/lib/modules/%1$s/vmlinux-%1$s" },
- { "/lib/modules/%1$s/build/vmlinux" },
- { "/usr/lib/modules/%1$s/kernel/vmlinux" },
- { "/usr/lib/debug/boot/vmlinux-%1$s" },
- { "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
- { "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
- };
- char path[PATH_MAX + 1];
- struct utsname buf;
- struct btf *btf;
- int i;
-
- uname(&buf);
-
- for (i = 0; i < ARRAY_SIZE(locations); i++) {
- snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
-
- if (access(path, R_OK))
- continue;
-
- if (locations[i].raw_btf)
- btf = btf_load_raw(path);
- else
- btf = btf__parse_elf(path, NULL);
-
- pr_debug("loading kernel BTF '%s': %ld\n",
- path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
- if (IS_ERR(btf))
- continue;
-
- return btf;
- }
-
- pr_warning("failed to find valid kernel BTF\n");
- return ERR_PTR(-ESRCH);
-}
-
/* Output spec definition in the format:
* [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
* where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
@@ -2914,28 +5605,48 @@
static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
{
const struct btf_type *t;
+ const struct btf_enum *e;
const char *s;
__u32 type_id;
int i;
- type_id = spec->spec[0].type_id;
+ 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);
- libbpf_print(level, "[%u] %s + ", type_id, s);
- for (i = 0; i < spec->raw_len; i++)
- libbpf_print(level, "%d%s", spec->raw_spec[i],
- i == spec->raw_len - 1 ? " => " : ":");
+ libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s);
- libbpf_print(level, "%u @ &x", spec->offset);
+ if (core_relo_is_type_based(spec->relo_kind))
+ return;
- for (i = 0; i < spec->len; i++) {
- if (spec->spec[i].name)
- libbpf_print(level, ".%s", spec->spec[i].name);
- else
- libbpf_print(level, "[%u]", spec->spec[i].idx);
+ if (core_relo_is_enumval_based(spec->relo_kind)) {
+ t = skip_mods_and_typedefs(spec->btf, type_id, NULL);
+ e = btf_enum(t) + spec->raw_spec[0];
+ s = btf__name_by_offset(spec->btf, e->name_off);
+
+ libbpf_print(level, "::%s = %u", s, e->val);
+ return;
}
+ if (core_relo_is_field_based(spec->relo_kind)) {
+ for (i = 0; i < spec->len; i++) {
+ if (spec->spec[i].name)
+ libbpf_print(level, ".%s", spec->spec[i].name);
+ else if (i > 0 || spec->spec[i].idx > 0)
+ libbpf_print(level, "[%u]", spec->spec[i].idx);
+ }
+
+ libbpf_print(level, " (");
+ for (i = 0; i < spec->raw_len; i++)
+ libbpf_print(level, "%s%d", i == 0 ? "" : ":", spec->raw_spec[i]);
+
+ if (spec->bit_offset % 8)
+ libbpf_print(level, " @ offset %u.%u)",
+ spec->bit_offset / 8, spec->bit_offset % 8);
+ else
+ libbpf_print(level, " @ offset %u)", spec->bit_offset / 8);
+ return;
+ }
}
static size_t bpf_core_hash_fn(const void *key, void *ctx)
@@ -2984,7 +5695,7 @@
* 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 not error. If there is any
+ * offsets across all candidates, there is no error. If there is any
* ambiguity, CO-RE relocation will fail. This is necessary to accomodate
* imprefection of BTF deduplication, which can cause slight duplication of
* the same BTF type, if some directly or indirectly referenced (by
@@ -2999,22 +5710,22 @@
* 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_offset_reloc associated with it. This list is shared
+ * 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.
*/
-static int bpf_core_reloc_offset(struct bpf_program *prog,
- const struct bpf_offset_reloc *relo,
- int relo_idx,
- const struct btf *local_btf,
- const struct btf *targ_btf,
- struct hashmap *cand_cache)
+static int bpf_core_apply_relo(struct bpf_program *prog,
+ const struct bpf_core_relo *relo,
+ int relo_idx,
+ const struct btf *local_btf,
+ const struct btf *targ_btf,
+ struct hashmap *cand_cache)
{
- const char *prog_name = bpf_program__title(prog, false);
- struct bpf_core_spec local_spec, cand_spec, targ_spec;
+ struct bpf_core_spec local_spec, cand_spec, targ_spec = {};
const void *type_key = u32_as_hash_key(relo->type_id);
- const struct btf_type *local_type, *cand_type;
- const char *local_name, *cand_name;
+ struct bpf_core_relo_res cand_res, targ_res;
+ const struct btf_type *local_type;
+ const char *local_name;
struct ids_vec *cand_ids;
__u32 local_id, cand_id;
const char *spec_str;
@@ -3026,31 +5737,49 @@
return -EINVAL;
local_name = btf__name_by_offset(local_btf, local_type->name_off);
- if (str_is_empty(local_name))
+ if (!local_name)
return -EINVAL;
spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
if (str_is_empty(spec_str))
return -EINVAL;
- err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec);
+ err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec);
if (err) {
- pr_warning("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n",
- prog_name, relo_idx, local_id, local_name, spec_str,
- err);
+ pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n",
+ prog->name, relo_idx, local_id, btf_kind_str(local_type),
+ str_is_empty(local_name) ? "<anon>" : local_name,
+ spec_str, err);
return -EINVAL;
}
- pr_debug("prog '%s': relo #%d: spec is ", prog_name, relo_idx);
+ pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog->name,
+ relo_idx, core_relo_kind_str(relo->kind), relo->kind);
bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
libbpf_print(LIBBPF_DEBUG, "\n");
+ /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */
+ if (relo->kind == BPF_TYPE_ID_LOCAL) {
+ targ_res.validate = true;
+ targ_res.poison = false;
+ targ_res.orig_val = local_spec.root_type_id;
+ targ_res.new_val = local_spec.root_type_id;
+ goto patch_insn;
+ }
+
+ /* libbpf doesn't support candidate search for anonymous types */
+ if (str_is_empty(spec_str)) {
+ 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;
+ }
+
if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) {
cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf);
if (IS_ERR(cand_ids)) {
- pr_warning("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld",
- prog_name, relo_idx, local_id, local_name,
- PTR_ERR(cand_ids));
+ pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld",
+ prog->name, relo_idx, local_id, btf_kind_str(local_type),
+ local_name, PTR_ERR(cand_ids));
return PTR_ERR(cand_ids);
}
err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL);
@@ -3062,50 +5791,91 @@
for (i = 0, j = 0; i < cand_ids->len; i++) {
cand_id = cand_ids->data[i];
- cand_type = btf__type_by_id(targ_btf, cand_id);
- cand_name = btf__name_by_offset(targ_btf, cand_type->name_off);
-
- err = bpf_core_spec_match(&local_spec, targ_btf,
- cand_id, &cand_spec);
- pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ",
- prog_name, relo_idx, i, cand_name);
- bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec);
- libbpf_print(LIBBPF_DEBUG, ": %d\n", err);
+ err = bpf_core_spec_match(&local_spec, targ_btf, cand_id, &cand_spec);
if (err < 0) {
- pr_warning("prog '%s': relo #%d: matching error: %d\n",
- prog_name, relo_idx, err);
+ pr_warn("prog '%s': relo #%d: error matching candidate #%d ",
+ prog->name, relo_idx, i);
+ bpf_core_dump_spec(LIBBPF_WARN, &cand_spec);
+ libbpf_print(LIBBPF_WARN, ": %d\n", err);
return err;
}
+
+ pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog->name,
+ relo_idx, err == 0 ? "non-matching" : "matching", i);
+ bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec);
+ libbpf_print(LIBBPF_DEBUG, "\n");
+
if (err == 0)
continue;
+ err = bpf_core_calc_relo(prog, 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.offset != targ_spec.offset) {
- /* if there are many candidates, they should all
- * resolve to the same offset
+ } 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_warning("prog '%s': relo #%d: offset ambiguity: %u != %u\n",
- prog_name, relo_idx, cand_spec.offset,
- targ_spec.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 %u != %s %u\n",
+ prog->name, relo_idx,
+ cand_res.poison ? "failure" : "success", cand_res.new_val,
+ targ_res.poison ? "failure" : "success", targ_res.new_val);
return -EINVAL;
}
- cand_ids->data[j++] = cand_spec.spec[0].type_id;
+ cand_ids->data[j++] = cand_spec.root_type_id;
}
- cand_ids->len = j;
- if (cand_ids->len == 0) {
- pr_warning("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n",
- prog_name, relo_idx, local_id, local_name, spec_str);
- return -ESRCH;
+ /*
+ * For BPF_FIELD_EXISTS relo or when used BPF program has field
+ * existence checks or kernel version/config checks, it's expected
+ * that we might not find any candidates. In this case, if field
+ * wasn't found in any candidate, the list of candidates shouldn't
+ * change at all, we'll just handle relocating appropriately,
+ * depending on relo's kind.
+ */
+ if (j > 0)
+ cand_ids->len = j;
+
+ /*
+ * If no candidates were found, it might be both a programmer error,
+ * as well as expected case, depending whether instruction w/
+ * relocation is guarded in some way that makes it unreachable (dead
+ * code) if relocation can't be resolved. This is handled in
+ * bpf_core_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, relo, relo_idx, &local_spec, NULL, &targ_res);
+ if (err)
+ return err;
}
- err = bpf_core_reloc_insn(prog, relo->insn_off,
- local_spec.offset, targ_spec.offset);
+patch_insn:
+ /* bpf_core_patch_insn() should know how to handle missing targ_spec */
+ err = bpf_core_patch_insn(prog, relo, relo_idx, &targ_res);
if (err) {
- pr_warning("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n",
- prog_name, relo_idx, relo->insn_off, err);
+ pr_warn("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n",
+ prog->name, relo_idx, relo->insn_off, err);
return -EINVAL;
}
@@ -3113,25 +5883,27 @@
}
static int
-bpf_core_reloc_offsets(struct bpf_object *obj, const char *targ_btf_path)
+bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
{
const struct btf_ext_info_sec *sec;
- const struct bpf_offset_reloc *rec;
+ 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 btf *targ_btf;
const char *sec_name;
- int i, err = 0;
+ int i, err = 0, insn_idx, sec_idx;
+
+ if (obj->btf_ext->core_relo_info.len == 0)
+ return 0;
if (targ_btf_path)
- targ_btf = btf__parse_elf(targ_btf_path, NULL);
+ targ_btf = btf__parse(targ_btf_path, NULL);
else
- targ_btf = bpf_core_find_kernel_btf();
- if (IS_ERR(targ_btf)) {
- pr_warning("failed to get target BTF: %ld\n",
- PTR_ERR(targ_btf));
+ targ_btf = obj->btf_vmlinux;
+ if (IS_ERR_OR_NULL(targ_btf)) {
+ pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf));
return PTR_ERR(targ_btf);
}
@@ -3141,37 +5913,63 @@
goto out;
}
- seg = &obj->btf_ext->offset_reloc_info;
+ seg = &obj->btf_ext->core_relo_info;
for_each_btf_ext_sec(seg, sec) {
sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off);
if (str_is_empty(sec_name)) {
err = -EINVAL;
goto out;
}
- prog = bpf_object__find_program_by_title(obj, sec_name);
- if (!prog) {
- pr_warning("failed to find program '%s' for CO-RE offset relocation\n",
- sec_name);
- err = -EINVAL;
- goto out;
+ /* bpf_object's ELF is gone by now so it's not easy to find
+ * section index by section name, but we can find *any*
+ * bpf_program within desired section name and use it's
+ * prog->sec_idx to do a proper search by section index and
+ * instruction offset
+ */
+ prog = NULL;
+ for (i = 0; i < obj->nr_programs; i++) {
+ prog = &obj->programs[i];
+ if (strcmp(prog->sec_name, sec_name) == 0)
+ break;
}
+ if (!prog) {
+ pr_warn("sec '%s': failed to find a BPF program\n", sec_name);
+ return -ENOENT;
+ }
+ sec_idx = prog->sec_idx;
- pr_debug("prog '%s': performing %d CO-RE offset relocs\n",
+ pr_debug("sec '%s': found %d CO-RE relocations\n",
sec_name, sec->num_info);
for_each_btf_ext_rec(seg, sec, i, rec) {
- err = bpf_core_reloc_offset(prog, rec, i, obj->btf,
- targ_btf, cand_cache);
+ insn_idx = rec->insn_off / BPF_INSN_SZ;
+ prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx);
+ if (!prog) {
+ pr_warn("sec '%s': failed to find program at insn #%d for CO-RE offset relocation #%d\n",
+ sec_name, insn_idx, i);
+ err = -EINVAL;
+ goto out;
+ }
+ /* no need to apply CO-RE relocation if the program is
+ * not going to be loaded
+ */
+ if (!prog->load)
+ continue;
+
+ err = bpf_core_apply_relo(prog, rec, i, obj->btf,
+ targ_btf, cand_cache);
if (err) {
- pr_warning("prog '%s': relo #%d: failed to relocate: %d\n",
- sec_name, i, err);
+ pr_warn("prog '%s': relo #%d: failed to relocate: %d\n",
+ prog->name, i, err);
goto out;
}
}
}
out:
- btf__free(targ_btf);
+ /* obj->btf_vmlinux is freed at the end of object load phase */
+ if (targ_btf != obj->btf_vmlinux)
+ btf__free(targ_btf);
if (!IS_ERR_OR_NULL(cand_cache)) {
hashmap__for_each_entry(cand_cache, entry, i) {
bpf_core_free_cands(entry->value);
@@ -3181,121 +5979,432 @@
return err;
}
+/* Relocate data references within program code:
+ * - map references;
+ * - global variable references;
+ * - extern references.
+ */
static int
-bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
+bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
{
- int err = 0;
+ int i;
- if (obj->btf_ext->offset_reloc_info.len)
- err = bpf_core_reloc_offsets(obj, targ_btf_path);
+ 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];
+ struct extern_desc *ext;
- return err;
-}
-
-static int
-bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
- struct reloc_desc *relo)
-{
- struct bpf_insn *insn, *new_insn;
- struct bpf_program *text;
- size_t new_cnt;
- int err;
-
- if (relo->type != RELO_CALL)
- return -LIBBPF_ERRNO__RELOC;
-
- if (prog->idx == obj->efile.text_shndx) {
- pr_warning("relo in .text insn %d into off %d\n",
- relo->insn_idx, relo->text_off);
- return -LIBBPF_ERRNO__RELOC;
+ switch (relo->type) {
+ case RELO_LD64:
+ insn[0].src_reg = BPF_PSEUDO_MAP_FD;
+ insn[0].imm = obj->maps[relo->map_idx].fd;
+ relo->processed = true;
+ break;
+ case RELO_DATA:
+ insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
+ insn[1].imm = insn[0].imm + relo->sym_off;
+ insn[0].imm = obj->maps[relo->map_idx].fd;
+ relo->processed = true;
+ break;
+ case RELO_EXTERN:
+ ext = &obj->externs[relo->sym_off];
+ if (ext->type == EXT_KCFG) {
+ 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) { /* typed ksyms */
+ insn[0].src_reg = BPF_PSEUDO_BTF_ID;
+ insn[0].imm = ext->ksym.vmlinux_btf_id;
+ } else { /* typeless ksyms */
+ insn[0].imm = (__u32)ext->ksym.addr;
+ insn[1].imm = ext->ksym.addr >> 32;
+ }
+ }
+ relo->processed = true;
+ break;
+ case RELO_CALL:
+ /* will be handled as a follow up pass */
+ break;
+ default:
+ pr_warn("prog '%s': relo #%d: bad relo type %d\n",
+ prog->name, i, relo->type);
+ return -EINVAL;
+ }
}
- if (prog->main_prog_cnt == 0) {
- text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx);
- if (!text) {
- pr_warning("no .text section found yet relo into text exist\n");
- return -LIBBPF_ERRNO__RELOC;
- }
- new_cnt = prog->insns_cnt + text->insns_cnt;
- new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
- if (!new_insn) {
- pr_warning("oom in prog realloc\n");
- return -ENOMEM;
- }
- prog->insns = new_insn;
-
- if (obj->btf_ext) {
- err = bpf_program_reloc_btf_ext(prog, obj,
- text->section_name,
- prog->insns_cnt);
- if (err)
- return err;
- }
-
- memcpy(new_insn + prog->insns_cnt, text->insns,
- text->insns_cnt * sizeof(*insn));
- prog->main_prog_cnt = prog->insns_cnt;
- prog->insns_cnt = new_cnt;
- pr_debug("added %zd insn from %s to prog %s\n",
- text->insns_cnt, text->section_name,
- prog->section_name);
- }
- insn = &prog->insns[relo->insn_idx];
- insn->imm += prog->main_prog_cnt - relo->insn_idx;
return 0;
}
-static int
-bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
+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)
{
- int i, err;
+ 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;
+ const char *sec_name;
+ int i, off_adj;
- if (!prog)
+ for_each_btf_ext_sec(ext_info, sec) {
+ sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off);
+ if (!sec_name)
+ return -EINVAL;
+ if (strcmp(sec_name, prog->sec_name) != 0)
+ 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;
-
- if (obj->btf_ext) {
- err = bpf_program_reloc_btf_ext(prog, obj,
- prog->section_name, 0);
- if (err)
- return err;
}
- if (!prog->reloc_desc)
+ 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(FEAT_BTF_FUNC))
return 0;
- for (i = 0; i < prog->nr_reloc; i++) {
- if (prog->reloc_desc[i].type == RELO_LD64 ||
- prog->reloc_desc[i].type == RELO_DATA) {
- bool relo_data = prog->reloc_desc[i].type == RELO_DATA;
- struct bpf_insn *insns = prog->insns;
- int insn_idx, map_idx;
+ /* 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;
- insn_idx = prog->reloc_desc[i].insn_idx;
- map_idx = prog->reloc_desc[i].map_idx;
+ 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);
+ }
- if (insn_idx + 1 >= (int)prog->insns_cnt) {
- pr_warning("relocation out of range: '%s'\n",
- prog->section_name);
- return -LIBBPF_ERRNO__RELOC;
+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)
+{
+ return bsearch(&insn_idx, prog->reloc_desc, prog->nr_reloc,
+ sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx);
+}
+
+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))
+ continue;
+
+ relo = find_prog_insn_relo(prog, insn_idx);
+ if (relo && relo->type != RELO_CALL) {
+ 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
+ */
+ sub_insn_idx = relo->sym_off / BPF_INSN_SZ + insn->imm + 1;
+ } 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;
- if (!relo_data) {
- insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
- } else {
- insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE;
- insns[insn_idx + 1].imm = insns[insn_idx].imm;
- }
- insns[insn_idx].imm = obj->maps[map_idx].fd;
- } else if (prog->reloc_desc[i].type == RELO_CALL) {
- err = bpf_program__reloc_text(prog, obj,
- &prog->reloc_desc[i]);
+ 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);
+
+ 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;
+
+ if (relo)
+ relo->processed = true;
+
+ 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);
}
- zfree(&prog->reloc_desc);
- prog->nr_reloc = 0;
+ 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, j, 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;
+ for (j = 0; j < subprog->nr_reloc; j++)
+ if (subprog->reloc_desc[j].type == RELO_CALL)
+ subprog->reloc_desc[j].processed = false;
+ }
+
+ err = bpf_object__reloc_code(obj, prog, prog);
+ if (err)
+ return err;
+
+
return 0;
}
@@ -3309,54 +6418,261 @@
if (obj->btf_ext) {
err = bpf_object__relocate_core(obj, targ_btf_path);
if (err) {
- pr_warning("failed to perform CO-RE relocations: %d\n",
- err);
+ pr_warn("failed to perform CO-RE relocations: %d\n",
+ err);
return err;
}
}
+ /* relocate data references first for all programs and sub-programs,
+ * as they don't change relative to code locations, so subsequent
+ * subprogram processing won't need to re-calculate any of them
+ */
for (i = 0; i < obj->nr_programs; i++) {
prog = &obj->programs[i];
-
- err = bpf_program__relocate(prog, obj);
+ err = bpf_object__relocate_data(obj, prog);
if (err) {
- pr_warning("failed to relocate '%s'\n",
- prog->section_name);
+ pr_warn("prog '%s': failed to relocate data references: %d\n",
+ prog->name, err);
return err;
}
}
+ /* now 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
+ */
+ 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;
+
+ err = bpf_object__relocate_calls(obj, prog);
+ if (err) {
+ pr_warn("prog '%s': failed to relocate calls: %d\n",
+ prog->name, err);
+ return err;
+ }
+ }
+ /* free up relocation descriptors */
+ for (i = 0; i < obj->nr_programs; i++) {
+ prog = &obj->programs[i];
+ zfree(&prog->reloc_desc);
+ prog->nr_reloc = 0;
+ }
return 0;
}
-static int bpf_object__collect_reloc(struct bpf_object *obj)
+static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
+ GElf_Shdr *shdr, Elf_Data *data);
+
+static int bpf_object__collect_map_relos(struct bpf_object *obj,
+ GElf_Shdr *shdr, Elf_Data *data)
{
- int i, err;
+ 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;
+ const struct btf_member *member;
+ const char *name, *mname;
+ Elf_Data *symbols;
+ unsigned int moff;
+ GElf_Sym sym;
+ GElf_Rel rel;
+ void *tmp;
- if (!obj_elf_valid(obj)) {
- pr_warning("Internal error: elf object is closed\n");
- return -LIBBPF_ERRNO__INTERNAL;
- }
+ 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;
- for (i = 0; i < obj->efile.nr_reloc; i++) {
- GElf_Shdr *shdr = &obj->efile.reloc[i].shdr;
- Elf_Data *data = obj->efile.reloc[i].data;
- int idx = shdr->sh_info;
- struct bpf_program *prog;
-
- if (shdr->sh_type != SHT_REL) {
- pr_warning("internal error at %d\n", __LINE__);
- return -LIBBPF_ERRNO__INTERNAL;
+ symbols = obj->efile.symbols;
+ nrels = shdr->sh_size / shdr->sh_entsize;
+ for (i = 0; i < nrels; i++) {
+ if (!gelf_getrel(data, i, &rel)) {
+ pr_warn(".maps relo #%d: failed to get ELF relo\n", i);
+ return -LIBBPF_ERRNO__FORMAT;
}
-
- prog = bpf_object__find_prog_by_idx(obj, idx);
- if (!prog) {
- pr_warning("relocation failed: no section(%d)\n", idx);
+ if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+ pr_warn(".maps relo #%d: symbol %zx not found\n",
+ i, (size_t)GELF_R_SYM(rel.r_info));
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+ name = elf_sym_str(obj, sym.st_name) ?: "<?>";
+ if (sym.st_shndx != obj->efile.btf_maps_shndx) {
+ pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n",
+ i, name);
return -LIBBPF_ERRNO__RELOC;
}
- err = bpf_program__collect_reloc(prog, shdr, data, obj);
+ 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;
+ }
+
+ if (!bpf_map_type__is_map_in_map(map->def.type))
+ return -EINVAL;
+ if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS &&
+ map->def.key_size != sizeof(int)) {
+ pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n",
+ i, map->name, sizeof(int));
+ return -EINVAL;
+ }
+
+ targ_map = bpf_object__find_map_by_name(obj, name);
+ if (!targ_map)
+ return -ESRCH;
+
+ var = btf__type_by_id(obj->btf, vi->type);
+ def = skip_mods_and_typedefs(obj->btf, var->type, NULL);
+ if (btf_vlen(def) == 0)
+ 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] = targ_map;
+
+ pr_debug(".maps relo #%d: map '%s' slot [%d] points to map '%s'\n",
+ i, map->name, moff, name);
+ }
+
+ return 0;
+}
+
+static int cmp_relocs(const void *_a, const void *_b)
+{
+ const struct reloc_desc *a = _a;
+ const struct reloc_desc *b = _b;
+
+ if (a->insn_idx != b->insn_idx)
+ return a->insn_idx < b->insn_idx ? -1 : 1;
+
+ /* no two relocations should have the same insn_idx, but ... */
+ if (a->type != b->type)
+ return a->type < b->type ? -1 : 1;
+
+ return 0;
+}
+
+static int bpf_object__collect_relos(struct bpf_object *obj)
+{
+ int i, err;
+
+ for (i = 0; i < obj->efile.nr_reloc_sects; i++) {
+ GElf_Shdr *shdr = &obj->efile.reloc_sects[i].shdr;
+ Elf_Data *data = obj->efile.reloc_sects[i].data;
+ int idx = shdr->sh_info;
+
+ 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;
}
+
+ 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);
+ }
+ 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;
+
+ 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(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(FEAT_PROBE_READ_KERN))
+ insn->imm = BPF_FUNC_probe_read_str;
+ break;
+ default:
+ break;
+ }
+ }
return 0;
}
@@ -3366,8 +6682,8 @@
{
struct bpf_load_program_attr load_attr;
char *cp, errmsg[STRERR_BUFSIZE];
- int log_buf_size = BPF_LOG_BUF_SIZE;
- char *log_buf;
+ size_t log_buf_size = 0;
+ char *log_buf = NULL;
int btf_fd, ret;
if (!insns || !insns_cnt)
@@ -3375,79 +6691,108 @@
memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
load_attr.prog_type = prog->type;
- load_attr.expected_attach_type = prog->expected_attach_type;
- if (prog->caps->name)
+ /* old kernels might not support specifying expected_attach_type */
+ if (!kernel_supports(FEAT_EXP_ATTACH_TYPE) && prog->sec_def &&
+ prog->sec_def->is_exp_attach_type_optional)
+ load_attr.expected_attach_type = 0;
+ else
+ load_attr.expected_attach_type = prog->expected_attach_type;
+ if (kernel_supports(FEAT_PROG_NAME))
load_attr.name = prog->name;
load_attr.insns = insns;
load_attr.insns_cnt = insns_cnt;
load_attr.license = license;
- load_attr.kern_version = kern_version;
- load_attr.prog_ifindex = prog->prog_ifindex;
- /* if .BTF.ext was loaded, kernel supports associated BTF for prog */
- if (prog->obj->btf_ext)
- btf_fd = bpf_object__btf_fd(prog->obj);
- else
- btf_fd = -1;
- load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0;
- load_attr.func_info = prog->func_info;
- load_attr.func_info_rec_size = prog->func_info_rec_size;
- load_attr.func_info_cnt = prog->func_info_cnt;
- load_attr.line_info = prog->line_info;
- load_attr.line_info_rec_size = prog->line_info_rec_size;
- load_attr.line_info_cnt = prog->line_info_cnt;
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
+ prog->type == BPF_PROG_TYPE_LSM) {
+ load_attr.attach_btf_id = prog->attach_btf_id;
+ } else if (prog->type == BPF_PROG_TYPE_TRACING ||
+ prog->type == BPF_PROG_TYPE_EXT) {
+ load_attr.attach_prog_fd = prog->attach_prog_fd;
+ load_attr.attach_btf_id = prog->attach_btf_id;
+ } else {
+ load_attr.kern_version = kern_version;
+ load_attr.prog_ifindex = prog->prog_ifindex;
+ }
+ /* specify func_info/line_info only if kernel supports them */
+ btf_fd = bpf_object__btf_fd(prog->obj);
+ if (btf_fd >= 0 && kernel_supports(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 = prog->log_level;
load_attr.prog_flags = prog->prog_flags;
retry_load:
- log_buf = malloc(log_buf_size);
- if (!log_buf)
- pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
+ if (log_buf_size) {
+ log_buf = malloc(log_buf_size);
+ if (!log_buf)
+ return -ENOMEM;
+
+ *log_buf = 0;
+ }
ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
if (ret >= 0) {
- if (load_attr.log_level)
+ if (log_buf && load_attr.log_level)
pr_debug("verifier log:\n%s", log_buf);
+
+ if (prog->obj->rodata_map_idx >= 0 &&
+ kernel_supports(FEAT_PROG_BIND_MAP)) {
+ struct bpf_map *rodata_map =
+ &prog->obj->maps[prog->obj->rodata_map_idx];
+
+ if (bpf_prog_bind_map(ret, bpf_map__fd(rodata_map), NULL)) {
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ pr_warn("prog '%s': failed to bind .rodata map: %s\n",
+ prog->name, cp);
+ /* Don't fail hard if can't bind rodata. */
+ }
+ }
+
*pfd = ret;
ret = 0;
goto out;
}
- if (errno == ENOSPC) {
- log_buf_size <<= 1;
+ if (!log_buf || errno == ENOSPC) {
+ log_buf_size = max((size_t)BPF_LOG_BUF_SIZE,
+ log_buf_size << 1);
+
free(log_buf);
goto retry_load;
}
- ret = -LIBBPF_ERRNO__LOAD;
+ ret = errno ? -errno : -LIBBPF_ERRNO__LOAD;
cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("load bpf program failed: %s\n", cp);
+ pr_warn("load bpf program failed: %s\n", cp);
+ pr_perm_msg(ret);
if (log_buf && log_buf[0] != '\0') {
ret = -LIBBPF_ERRNO__VERIFY;
- pr_warning("-- BEGIN DUMP LOG ---\n");
- pr_warning("\n%s\n", log_buf);
- pr_warning("-- END LOG --\n");
+ pr_warn("-- BEGIN DUMP LOG ---\n");
+ pr_warn("\n%s\n", log_buf);
+ pr_warn("-- END LOG --\n");
} else if (load_attr.insns_cnt >= BPF_MAXINSNS) {
- pr_warning("Program too large (%zu insns), at most %d insns\n",
- load_attr.insns_cnt, BPF_MAXINSNS);
+ pr_warn("Program too large (%zu insns), at most %d insns\n",
+ load_attr.insns_cnt, BPF_MAXINSNS);
ret = -LIBBPF_ERRNO__PROG2BIG;
- } else {
+ } else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
/* Wrong program type? */
- if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
- int fd;
+ int fd;
- load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
- load_attr.expected_attach_type = 0;
- fd = bpf_load_program_xattr(&load_attr, NULL, 0);
- if (fd >= 0) {
- close(fd);
- ret = -LIBBPF_ERRNO__PROGTYPE;
- goto out;
- }
+ load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
+ load_attr.expected_attach_type = 0;
+ fd = bpf_load_program_xattr(&load_attr, NULL, 0);
+ if (fd >= 0) {
+ close(fd);
+ ret = -LIBBPF_ERRNO__PROGTYPE;
+ goto out;
}
-
- if (log_buf)
- ret = -LIBBPF_ERRNO__KVER;
}
out:
@@ -3455,22 +6800,36 @@
return ret;
}
-int
-bpf_program__load(struct bpf_program *prog,
- char *license, __u32 kern_version)
+static int libbpf_find_attach_btf_id(struct bpf_program *prog);
+
+int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
{
- int err = 0, fd, i;
+ int err = 0, fd, i, btf_id;
+
+ if (prog->obj->loaded) {
+ pr_warn("prog '%s': can't load after object was loaded\n", prog->name);
+ return -EINVAL;
+ }
+
+ if ((prog->type == BPF_PROG_TYPE_TRACING ||
+ prog->type == BPF_PROG_TYPE_LSM ||
+ prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
+ btf_id = libbpf_find_attach_btf_id(prog);
+ if (btf_id <= 0)
+ return btf_id;
+ prog->attach_btf_id = btf_id;
+ }
if (prog->instances.nr < 0 || !prog->instances.fds) {
if (prog->preprocessor) {
- pr_warning("Internal error: can't load program '%s'\n",
- prog->section_name);
+ pr_warn("Internal error: can't load program '%s'\n",
+ prog->name);
return -LIBBPF_ERRNO__INTERNAL;
}
prog->instances.fds = malloc(sizeof(int));
if (!prog->instances.fds) {
- pr_warning("Not enough memory for BPF fds\n");
+ pr_warn("Not enough memory for BPF fds\n");
return -ENOMEM;
}
prog->instances.nr = 1;
@@ -3479,11 +6838,11 @@
if (!prog->preprocessor) {
if (prog->instances.nr != 1) {
- pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
- prog->section_name, prog->instances.nr);
+ pr_warn("prog '%s': inconsistent nr(%d) != 1\n",
+ prog->name, prog->instances.nr);
}
err = load_program(prog, prog->insns, prog->insns_cnt,
- license, kern_version, &fd);
+ license, kern_ver, &fd);
if (!err)
prog->instances.fds[0] = fd;
goto out;
@@ -3497,14 +6856,14 @@
err = preprocessor(prog, i, prog->insns,
prog->insns_cnt, &result);
if (err) {
- pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
- i, prog->section_name);
+ pr_warn("Preprocessing the %dth instance of program '%s' failed\n",
+ i, prog->name);
goto out;
}
if (!result.new_insn_ptr || !result.new_insn_cnt) {
pr_debug("Skip loading the %dth instance of program '%s'\n",
- i, prog->section_name);
+ i, prog->name);
prog->instances.fds[i] = -1;
if (result.pfd)
*result.pfd = -1;
@@ -3512,12 +6871,10 @@
}
err = load_program(prog, result.new_insn_ptr,
- result.new_insn_cnt,
- license, kern_version, &fd);
-
+ result.new_insn_cnt, license, kern_ver, &fd);
if (err) {
- pr_warning("Loading the %dth instance of program '%s' failed\n",
- i, prog->section_name);
+ pr_warn("Loading the %dth instance of program '%s' failed\n",
+ i, prog->name);
goto out;
}
@@ -3527,125 +6884,135 @@
}
out:
if (err)
- pr_warning("failed to load program '%s'\n",
- prog->section_name);
+ pr_warn("failed to load program '%s'\n", prog->name);
zfree(&prog->insns);
prog->insns_cnt = 0;
return err;
}
-static bool bpf_program__is_function_storage(const struct bpf_program *prog,
- const struct bpf_object *obj)
-{
- return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls;
-}
-
static int
bpf_object__load_progs(struct bpf_object *obj, int log_level)
{
+ struct bpf_program *prog;
size_t i;
int err;
for (i = 0; i < obj->nr_programs; i++) {
- if (bpf_program__is_function_storage(&obj->programs[i], obj))
+ 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;
- obj->programs[i].log_level |= log_level;
- err = bpf_program__load(&obj->programs[i],
- obj->license,
- obj->kern_version);
+ if (!prog->load) {
+ pr_debug("prog '%s': skipped loading\n", prog->name);
+ continue;
+ }
+ prog->log_level |= log_level;
+ err = bpf_program__load(prog, obj->license, obj->kern_version);
if (err)
return err;
}
return 0;
}
-static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
-{
- switch (type) {
- case BPF_PROG_TYPE_SOCKET_FILTER:
- case BPF_PROG_TYPE_SCHED_CLS:
- case BPF_PROG_TYPE_SCHED_ACT:
- case BPF_PROG_TYPE_XDP:
- case BPF_PROG_TYPE_CGROUP_SKB:
- case BPF_PROG_TYPE_CGROUP_SOCK:
- case BPF_PROG_TYPE_LWT_IN:
- case BPF_PROG_TYPE_LWT_OUT:
- case BPF_PROG_TYPE_LWT_XMIT:
- case BPF_PROG_TYPE_LWT_SEG6LOCAL:
- case BPF_PROG_TYPE_SOCK_OPS:
- case BPF_PROG_TYPE_SK_SKB:
- case BPF_PROG_TYPE_CGROUP_DEVICE:
- case BPF_PROG_TYPE_SK_MSG:
- case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
- case BPF_PROG_TYPE_LIRC_MODE2:
- case BPF_PROG_TYPE_SK_REUSEPORT:
- case BPF_PROG_TYPE_FLOW_DISSECTOR:
- case BPF_PROG_TYPE_UNSPEC:
- case BPF_PROG_TYPE_TRACEPOINT:
- case BPF_PROG_TYPE_RAW_TRACEPOINT:
- case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
- case BPF_PROG_TYPE_PERF_EVENT:
- case BPF_PROG_TYPE_CGROUP_SYSCTL:
- case BPF_PROG_TYPE_CGROUP_SOCKOPT:
- return false;
- case BPF_PROG_TYPE_KPROBE:
- default:
- return true;
- }
-}
-
-static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
-{
- if (needs_kver && obj->kern_version == 0) {
- pr_warning("%s doesn't provide kernel version\n",
- obj->path);
- return -LIBBPF_ERRNO__KVERSION;
- }
- return 0;
-}
+static const struct bpf_sec_def *find_sec_def(const char *sec_name);
static struct bpf_object *
-__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
- bool needs_kver, int flags)
+__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
+ const struct bpf_object_open_opts *opts)
{
+ const char *obj_name, *kconfig;
+ struct bpf_program *prog;
struct bpf_object *obj;
+ char tmp_name[64];
int err;
if (elf_version(EV_CURRENT) == EV_NONE) {
- pr_warning("failed to init libelf for %s\n", path);
+ pr_warn("failed to init libelf for %s\n",
+ path ? : "(mem buf)");
return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
}
- obj = bpf_object__new(path, obj_buf, obj_buf_sz);
+ if (!OPTS_VALID(opts, bpf_object_open_opts))
+ return ERR_PTR(-EINVAL);
+
+ obj_name = OPTS_GET(opts, object_name, NULL);
+ if (obj_buf) {
+ if (!obj_name) {
+ snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
+ (unsigned long)obj_buf,
+ (unsigned long)obj_buf_sz);
+ obj_name = tmp_name;
+ }
+ path = obj_name;
+ pr_debug("loading object '%s' from buffer\n", obj_name);
+ }
+
+ obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name);
if (IS_ERR(obj))
return obj;
- CHECK_ERR(bpf_object__elf_init(obj), err, out);
- CHECK_ERR(bpf_object__check_endianness(obj), err, out);
- CHECK_ERR(bpf_object__probe_caps(obj), err, out);
- CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
- CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
- CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
+ kconfig = OPTS_GET(opts, kconfig, NULL);
+ if (kconfig) {
+ obj->kconfig = strdup(kconfig);
+ if (!obj->kconfig) {
+ 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__collect_relos(obj);
+ if (err)
+ goto out;
bpf_object__elf_finish(obj);
+
+ 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 */
+ continue;
+
+ if (prog->sec_def->is_sleepable)
+ prog->prog_flags |= BPF_F_SLEEPABLE;
+ bpf_program__set_type(prog, prog->sec_def->prog_type);
+ bpf_program__set_expected_attach_type(prog,
+ prog->sec_def->expected_attach_type);
+
+ if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING ||
+ prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
+ prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
+ }
+
return obj;
out:
bpf_object__close(obj);
return ERR_PTR(err);
}
-struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
- int flags)
+static struct bpf_object *
+__bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags)
{
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
+ .relaxed_maps = flags & MAPS_RELAX_COMPAT,
+ );
+
/* param validation */
if (!attr->file)
return NULL;
pr_debug("loading %s\n", attr->file);
-
- return __bpf_object__open(attr->file, NULL, 0,
- bpf_prog_type__needs_kver(attr->prog_type),
- flags);
+ return __bpf_object__open(attr->file, NULL, 0, &opts);
}
struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
@@ -3663,25 +7030,42 @@
return bpf_object__open_xattr(&attr);
}
-struct bpf_object *bpf_object__open_buffer(void *obj_buf,
- size_t obj_buf_sz,
- const char *name)
+struct bpf_object *
+bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts)
{
- char tmp_name[64];
+ if (!path)
+ return ERR_PTR(-EINVAL);
- /* param validation */
- if (!obj_buf || obj_buf_sz <= 0)
+ pr_debug("loading %s\n", path);
+
+ return __bpf_object__open(path, NULL, 0, opts);
+}
+
+struct bpf_object *
+bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
+ const struct bpf_object_open_opts *opts)
+{
+ if (!obj_buf || obj_buf_sz == 0)
+ return ERR_PTR(-EINVAL);
+
+ return __bpf_object__open(NULL, obj_buf, obj_buf_sz, opts);
+}
+
+struct bpf_object *
+bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz,
+ const char *name)
+{
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
+ .object_name = name,
+ /* wrong default, but backwards-compatible */
+ .relaxed_maps = true,
+ );
+
+ /* returning NULL is wrong, but backwards-compatible */
+ if (!obj_buf || obj_buf_sz == 0)
return NULL;
- if (!name) {
- snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
- (unsigned long)obj_buf,
- (unsigned long)obj_buf_sz);
- name = tmp_name;
- }
- pr_debug("loading object '%s' from buffer\n", name);
-
- return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
+ return bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
}
int bpf_object__unload(struct bpf_object *obj)
@@ -3691,8 +7075,11 @@
if (!obj)
return -EINVAL;
- for (i = 0; i < obj->nr_maps; i++)
+ for (i = 0; i < obj->nr_maps; i++) {
zclose(obj->maps[i].fd);
+ if (obj->maps[i].st_ops)
+ zfree(&obj->maps[i].st_ops->kern_vdata);
+ }
for (i = 0; i < obj->nr_programs; i++)
bpf_program__unload(&obj->programs[i]);
@@ -3700,10 +7087,224 @@
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(FEAT_GLOBAL_DATA)) {
+ pr_warn("kernel doesn't support global data\n");
+ return -ENOTSUP;
+ }
+ if (!kernel_supports(FEAT_ARRAY_MMAP))
+ m->def.map_flags ^= BPF_F_MMAPABLE;
+ }
+
+ return 0;
+}
+
+static int bpf_object__read_kallsyms_file(struct bpf_object *obj)
+{
+ char sym_type, sym_name[500];
+ unsigned long long sym_addr;
+ struct extern_desc *ext;
+ 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;
+ goto out;
+ }
+
+ ext = find_extern_by_name(obj, sym_name);
+ if (!ext || ext->type != EXT_KSYM)
+ continue;
+
+ 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);
+ err = -EINVAL;
+ goto out;
+ }
+ if (!ext->is_set) {
+ ext->is_set = true;
+ ext->ksym.addr = sym_addr;
+ pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr);
+ }
+ }
+
+out:
+ fclose(f);
+ return err;
+}
+
+static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
+{
+ struct extern_desc *ext;
+ int i, id;
+
+ for (i = 0; i < obj->nr_extern; i++) {
+ const struct btf_type *targ_var, *targ_type;
+ __u32 targ_type_id, local_type_id;
+ const char *targ_var_name;
+ int ret;
+
+ ext = &obj->externs[i];
+ if (ext->type != EXT_KSYM || !ext->ksym.type_id)
+ continue;
+
+ id = btf__find_by_name_kind(obj->btf_vmlinux, ext->name,
+ BTF_KIND_VAR);
+ if (id <= 0) {
+ pr_warn("extern (ksym) '%s': failed to find BTF ID in vmlinux BTF.\n",
+ ext->name);
+ return -ESRCH;
+ }
+
+ /* find local type_id */
+ local_type_id = ext->ksym.type_id;
+
+ /* find target type_id */
+ targ_var = btf__type_by_id(obj->btf_vmlinux, id);
+ targ_var_name = btf__name_by_offset(obj->btf_vmlinux,
+ targ_var->name_off);
+ targ_type = skip_mods_and_typedefs(obj->btf_vmlinux,
+ targ_var->type,
+ &targ_type_id);
+
+ ret = bpf_core_types_are_compat(obj->btf, local_type_id,
+ obj->btf_vmlinux, targ_type_id);
+ if (ret <= 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(obj->btf_vmlinux,
+ targ_type->name_off);
+
+ pr_warn("extern (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.vmlinux_btf_id = id;
+ pr_debug("extern (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_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_KCFG &&
+ strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) {
+ void *ext_val = kcfg_data + ext->kcfg.data_off;
+ __u32 kver = get_kernel_version();
+
+ if (!kver) {
+ pr_warn("failed to get kernel version\n");
+ return -EINVAL;
+ }
+ err = set_kcfg_value_num(ext, ext_val, kver);
+ if (err)
+ return err;
+ pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver);
+ } else if (ext->type == EXT_KCFG &&
+ strncmp(ext->name, "CONFIG_", 7) == 0) {
+ need_config = true;
+ } else if (ext->type == EXT_KSYM) {
+ if (ext->ksym.type_id)
+ need_vmlinux_btf = true;
+ else
+ need_kallsyms = true;
+ } else {
+ pr_warn("unrecognized extern '%s'\n", ext->name);
+ return -EINVAL;
+ }
+ }
+ if (need_config && extra_kconfig) {
+ err = bpf_object__read_kconfig_mem(obj, extra_kconfig, 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;
+}
+
int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
{
struct bpf_object *obj;
- int err;
+ int err, i;
if (!attr)
return -EINVAL;
@@ -3712,20 +7313,37 @@
return -EINVAL;
if (obj->loaded) {
- pr_warning("object should not be loaded twice\n");
+ pr_warn("object '%s': load can't be attempted twice\n", obj->name);
return -EINVAL;
}
- obj->loaded = true;
+ err = bpf_object__probe_loading(obj);
+ err = err ? : bpf_object__load_vmlinux_btf(obj);
+ err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
+ err = err ? : bpf_object__sanitize_and_load_btf(obj);
+ err = err ? : bpf_object__sanitize_maps(obj);
+ err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
+ err = err ? : bpf_object__create_maps(obj);
+ err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
+ err = err ? : bpf_object__load_progs(obj, attr->log_level);
- CHECK_ERR(bpf_object__create_maps(obj), err, out);
- CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out);
- CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out);
+ 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_warning("failed to load object '%s'\n", obj->path);
+ pr_warn("failed to load object '%s'\n", obj->path);
return err;
}
@@ -3738,6 +7356,28 @@
return bpf_object__load_xattr(&attr);
}
+static int make_parent_dir(const char *path)
+{
+ char *cp, errmsg[STRERR_BUFSIZE];
+ char *dname, *dir;
+ int err = 0;
+
+ dname = strdup(path);
+ if (dname == NULL)
+ return -ENOMEM;
+
+ dir = dirname(dname);
+ if (mkdir(dir, 0700) && errno != EEXIST)
+ err = -errno;
+
+ free(dname);
+ if (err) {
+ cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
+ pr_warn("failed to mkdir %s: %s\n", path, cp);
+ }
+ return err;
+}
+
static int check_path(const char *path)
{
char *cp, errmsg[STRERR_BUFSIZE];
@@ -3755,13 +7395,13 @@
dir = dirname(dname);
if (statfs(dir, &st_fs)) {
cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("failed to statfs %s: %s\n", dir, cp);
+ pr_warn("failed to statfs %s: %s\n", dir, cp);
err = -errno;
}
free(dname);
if (!err && st_fs.f_type != BPF_FS_MAGIC) {
- pr_warning("specified path %s is not on BPF FS\n", path);
+ pr_warn("specified path %s is not on BPF FS\n", path);
err = -EINVAL;
}
@@ -3774,25 +7414,30 @@
char *cp, errmsg[STRERR_BUFSIZE];
int err;
+ err = make_parent_dir(path);
+ if (err)
+ return err;
+
err = check_path(path);
if (err)
return err;
if (prog == NULL) {
- pr_warning("invalid program pointer\n");
+ pr_warn("invalid program pointer\n");
return -EINVAL;
}
if (instance < 0 || instance >= prog->instances.nr) {
- pr_warning("invalid prog instance %d of prog %s (max %d)\n",
- instance, prog->section_name, prog->instances.nr);
+ pr_warn("invalid prog instance %d of prog %s (max %d)\n",
+ instance, prog->name, prog->instances.nr);
return -EINVAL;
}
if (bpf_obj_pin(prog->instances.fds[instance], path)) {
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("failed to pin program: %s\n", cp);
- return -errno;
+ err = -errno;
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
+ pr_warn("failed to pin program: %s\n", cp);
+ return err;
}
pr_debug("pinned program '%s'\n", path);
@@ -3809,13 +7454,13 @@
return err;
if (prog == NULL) {
- pr_warning("invalid program pointer\n");
+ pr_warn("invalid program pointer\n");
return -EINVAL;
}
if (instance < 0 || instance >= prog->instances.nr) {
- pr_warning("invalid prog instance %d of prog %s (max %d)\n",
- instance, prog->section_name, prog->instances.nr);
+ pr_warn("invalid prog instance %d of prog %s (max %d)\n",
+ instance, prog->name, prog->instances.nr);
return -EINVAL;
}
@@ -3827,37 +7472,25 @@
return 0;
}
-static int make_dir(const char *path)
-{
- char *cp, errmsg[STRERR_BUFSIZE];
- int err = 0;
-
- if (mkdir(path, 0700) && errno != EEXIST)
- err = -errno;
-
- if (err) {
- cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
- pr_warning("failed to mkdir %s: %s\n", path, cp);
- }
- return err;
-}
-
int bpf_program__pin(struct bpf_program *prog, const char *path)
{
int i, err;
+ err = make_parent_dir(path);
+ if (err)
+ return err;
+
err = check_path(path);
if (err)
return err;
if (prog == NULL) {
- pr_warning("invalid program pointer\n");
+ pr_warn("invalid program pointer\n");
return -EINVAL;
}
if (prog->instances.nr <= 0) {
- pr_warning("no instances of prog %s to pin\n",
- prog->section_name);
+ pr_warn("no instances of prog %s to pin\n", prog->name);
return -EINVAL;
}
@@ -3866,10 +7499,6 @@
return bpf_program__pin_instance(prog, path, 0);
}
- err = make_dir(path);
- if (err)
- return err;
-
for (i = 0; i < prog->instances.nr; i++) {
char buf[PATH_MAX];
int len;
@@ -3918,13 +7547,12 @@
return err;
if (prog == NULL) {
- pr_warning("invalid program pointer\n");
+ pr_warn("invalid program pointer\n");
return -EINVAL;
}
if (prog->instances.nr <= 0) {
- pr_warning("no instances of prog %s to pin\n",
- prog->section_name);
+ pr_warn("no instances of prog %s to pin\n", prog->name);
return -EINVAL;
}
@@ -3960,47 +7588,133 @@
char *cp, errmsg[STRERR_BUFSIZE];
int err;
- err = check_path(path);
- if (err)
- return err;
-
if (map == NULL) {
- pr_warning("invalid map pointer\n");
+ pr_warn("invalid map pointer\n");
return -EINVAL;
}
- if (bpf_obj_pin(map->fd, path)) {
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("failed to pin map: %s\n", cp);
- return -errno;
+ if (map->pin_path) {
+ if (path && strcmp(path, map->pin_path)) {
+ pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
+ bpf_map__name(map), map->pin_path, path);
+ return -EINVAL;
+ } else if (map->pinned) {
+ pr_debug("map '%s' already pinned at '%s'; not re-pinning\n",
+ bpf_map__name(map), map->pin_path);
+ return 0;
+ }
+ } else {
+ if (!path) {
+ pr_warn("missing a path to pin map '%s' at\n",
+ bpf_map__name(map));
+ return -EINVAL;
+ } else if (map->pinned) {
+ pr_warn("map '%s' already pinned\n", bpf_map__name(map));
+ return -EEXIST;
+ }
+
+ map->pin_path = strdup(path);
+ if (!map->pin_path) {
+ err = -errno;
+ goto out_err;
+ }
}
- pr_debug("pinned map '%s'\n", path);
+ err = make_parent_dir(map->pin_path);
+ if (err)
+ return err;
+
+ err = check_path(map->pin_path);
+ if (err)
+ return err;
+
+ if (bpf_obj_pin(map->fd, map->pin_path)) {
+ err = -errno;
+ goto out_err;
+ }
+
+ map->pinned = true;
+ pr_debug("pinned map '%s'\n", map->pin_path);
return 0;
+
+out_err:
+ cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
+ pr_warn("failed to pin map: %s\n", cp);
+ return err;
}
int bpf_map__unpin(struct bpf_map *map, const char *path)
{
int err;
+ if (map == NULL) {
+ pr_warn("invalid map pointer\n");
+ return -EINVAL;
+ }
+
+ if (map->pin_path) {
+ if (path && strcmp(path, map->pin_path)) {
+ pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
+ bpf_map__name(map), map->pin_path, path);
+ return -EINVAL;
+ }
+ path = map->pin_path;
+ } else if (!path) {
+ pr_warn("no path to unpin map '%s' from\n",
+ bpf_map__name(map));
+ return -EINVAL;
+ }
+
err = check_path(path);
if (err)
return err;
- if (map == NULL) {
- pr_warning("invalid map pointer\n");
- return -EINVAL;
- }
-
err = unlink(path);
if (err != 0)
return -errno;
- pr_debug("unpinned map '%s'\n", path);
+
+ map->pinned = false;
+ pr_debug("unpinned map '%s' from '%s'\n", bpf_map__name(map), path);
return 0;
}
+int bpf_map__set_pin_path(struct bpf_map *map, const char *path)
+{
+ char *new = NULL;
+
+ if (path) {
+ new = strdup(path);
+ if (!new)
+ return -errno;
+ }
+
+ free(map->pin_path);
+ map->pin_path = new;
+ return 0;
+}
+
+const char *bpf_map__get_pin_path(const struct bpf_map *map)
+{
+ return map->pin_path;
+}
+
+bool bpf_map__is_pinned(const struct bpf_map *map)
+{
+ return map->pinned;
+}
+
+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;
@@ -4010,29 +7724,33 @@
return -ENOENT;
if (!obj->loaded) {
- pr_warning("object not yet loaded; load it first\n");
+ pr_warn("object not yet loaded; load it first\n");
return -ENOENT;
}
- err = make_dir(path);
- if (err)
- return err;
-
bpf_object__for_each_map(map, obj) {
+ char *pin_path = NULL;
char buf[PATH_MAX];
- int len;
- len = snprintf(buf, PATH_MAX, "%s/%s", path,
- bpf_map__name(map));
- if (len < 0) {
- err = -EINVAL;
- goto err_unpin_maps;
- } else if (len >= PATH_MAX) {
- err = -ENAMETOOLONG;
- goto err_unpin_maps;
+ if (path) {
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0) {
+ err = -EINVAL;
+ goto err_unpin_maps;
+ } else if (len >= PATH_MAX) {
+ err = -ENAMETOOLONG;
+ goto err_unpin_maps;
+ }
+ sanitize_pin_path(buf);
+ pin_path = buf;
+ } else if (!map->pin_path) {
+ continue;
}
- err = bpf_map__pin(map, buf);
+ err = bpf_map__pin(map, pin_path);
if (err)
goto err_unpin_maps;
}
@@ -4041,17 +7759,10 @@
err_unpin_maps:
while ((map = bpf_map__prev(map, obj))) {
- char buf[PATH_MAX];
- int len;
-
- len = snprintf(buf, PATH_MAX, "%s/%s", path,
- bpf_map__name(map));
- if (len < 0)
- continue;
- else if (len >= PATH_MAX)
+ if (!map->pin_path)
continue;
- bpf_map__unpin(map, buf);
+ bpf_map__unpin(map, NULL);
}
return err;
@@ -4066,17 +7777,25 @@
return -ENOENT;
bpf_object__for_each_map(map, obj) {
+ char *pin_path = NULL;
char buf[PATH_MAX];
- int len;
- len = snprintf(buf, PATH_MAX, "%s/%s", path,
- bpf_map__name(map));
- if (len < 0)
- return -EINVAL;
- else if (len >= PATH_MAX)
- return -ENAMETOOLONG;
+ if (path) {
+ int len;
- err = bpf_map__unpin(map, buf);
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+ sanitize_pin_path(buf);
+ pin_path = buf;
+ } else if (!map->pin_path) {
+ continue;
+ }
+
+ err = bpf_map__unpin(map, pin_path);
if (err)
return err;
}
@@ -4093,14 +7812,10 @@
return -ENOENT;
if (!obj->loaded) {
- pr_warning("object not yet loaded; load it first\n");
+ pr_warn("object not yet loaded; load it first\n");
return -ENOENT;
}
- err = make_dir(path);
- if (err)
- return err;
-
bpf_object__for_each_program(prog, obj) {
char buf[PATH_MAX];
int len;
@@ -4184,11 +7899,45 @@
return 0;
}
+static void bpf_map__destroy(struct bpf_map *map)
+{
+ if (map->clear_priv)
+ map->clear_priv(map, map->priv);
+ map->priv = NULL;
+ map->clear_priv = NULL;
+
+ 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->pin_path);
+
+ if (map->fd >= 0)
+ zclose(map->fd);
+}
+
void bpf_object__close(struct bpf_object *obj)
{
size_t i;
- if (!obj)
+ if (IS_ERR_OR_NULL(obj))
return;
if (obj->clear_priv)
@@ -4199,17 +7948,13 @@
btf__free(obj->btf);
btf_ext__free(obj->btf_ext);
- for (i = 0; i < obj->nr_maps; i++) {
- zfree(&obj->maps[i].name);
- if (obj->maps[i].clear_priv)
- obj->maps[i].clear_priv(&obj->maps[i],
- obj->maps[i].priv);
- obj->maps[i].priv = NULL;
- obj->maps[i].clear_priv = NULL;
- }
+ for (i = 0; i < obj->nr_maps; i++)
+ bpf_map__destroy(&obj->maps[i]);
- zfree(&obj->sections.rodata);
- zfree(&obj->sections.data);
+ zfree(&obj->kconfig);
+ zfree(&obj->externs);
+ obj->nr_extern = 0;
+
zfree(&obj->maps);
obj->nr_maps = 0;
@@ -4244,7 +7989,7 @@
const char *bpf_object__name(const struct bpf_object *obj)
{
- return obj ? obj->path : ERR_PTR(-EINVAL);
+ return obj ? obj->name : ERR_PTR(-EINVAL);
}
unsigned int bpf_object__kversion(const struct bpf_object *obj)
@@ -4294,7 +8039,7 @@
&obj->programs[nr_programs - 1];
if (p->obj != obj) {
- pr_warning("error: program handler doesn't match object\n");
+ pr_warn("error: program handler doesn't match object\n");
return NULL;
}
@@ -4311,7 +8056,7 @@
do {
prog = __bpf_program__iter(prog, obj, true);
- } while (prog && bpf_program__is_function_storage(prog, obj));
+ } while (prog && prog_is_subprog(obj, prog));
return prog;
}
@@ -4323,7 +8068,7 @@
do {
prog = __bpf_program__iter(prog, obj, false);
- } while (prog && bpf_program__is_function_storage(prog, obj));
+ } while (prog && prog_is_subprog(obj, prog));
return prog;
}
@@ -4349,15 +8094,25 @@
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;
+}
+
const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy)
{
const char *title;
- title = prog->section_name;
+ title = prog->sec_name;
if (needs_copy) {
title = strdup(title);
if (!title) {
- pr_warning("failed to strdup program title\n");
+ pr_warn("failed to strdup program title\n");
return ERR_PTR(-ENOMEM);
}
}
@@ -4365,11 +8120,30 @@
return title;
}
+bool bpf_program__autoload(const struct bpf_program *prog)
+{
+ return prog->load;
+}
+
+int bpf_program__set_autoload(struct bpf_program *prog, bool autoload)
+{
+ if (prog->obj->loaded)
+ return -EINVAL;
+
+ prog->load = autoload;
+ return 0;
+}
+
int bpf_program__fd(const struct bpf_program *prog)
{
return bpf_program__nth_fd(prog, 0);
}
+size_t bpf_program__size(const struct bpf_program *prog)
+{
+ return prog->insns_cnt * BPF_INSN_SZ;
+}
+
int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
bpf_program_prep_t prep)
{
@@ -4379,13 +8153,13 @@
return -EINVAL;
if (prog->instances.nr > 0 || prog->instances.fds) {
- pr_warning("Can't set pre-processor after loading\n");
+ pr_warn("Can't set pre-processor after loading\n");
return -EINVAL;
}
instances_fds = malloc(sizeof(int) * nr_instances);
if (!instances_fds) {
- pr_warning("alloc memory failed for fds\n");
+ pr_warn("alloc memory failed for fds\n");
return -ENOMEM;
}
@@ -4406,21 +8180,26 @@
return -EINVAL;
if (n >= prog->instances.nr || n < 0) {
- pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
- n, prog->section_name, prog->instances.nr);
+ pr_warn("Can't get the %dth fd from program %s: only %d instances\n",
+ n, prog->name, prog->instances.nr);
return -EINVAL;
}
fd = prog->instances.fds[n];
if (fd < 0) {
- pr_warning("%dth instance of program '%s' is invalid\n",
- n, prog->section_name);
+ pr_warn("%dth instance of program '%s' is invalid\n",
+ n, prog->name);
return -ENOENT;
}
return fd;
}
+enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog)
+{
+ return prog->type;
+}
+
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
{
prog->type = type;
@@ -4447,6 +8226,7 @@
} \
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(lsm, BPF_PROG_TYPE_LSM);
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
@@ -4454,6 +8234,16 @@
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
+BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING);
+BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS);
+BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT);
+BPF_PROG_TYPE_FNS(sk_lookup, BPF_PROG_TYPE_SK_LOOKUP);
+
+enum bpf_attach_type
+bpf_program__get_expected_attach_type(struct bpf_program *prog)
+{
+ return prog->expected_attach_type;
+}
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
enum bpf_attach_type type)
@@ -4461,41 +8251,130 @@
prog->expected_attach_type = type;
}
-#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
- { string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional, \
+ attachable, attach_btf) \
+ { \
+ .sec = string, \
+ .len = sizeof(string) - 1, \
+ .prog_type = ptype, \
+ .expected_attach_type = eatype, \
+ .is_exp_attach_type_optional = eatype_optional, \
+ .is_attachable = attachable, \
+ .is_attach_btf = attach_btf, \
+ }
/* Programs that can NOT be attached. */
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
+#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0)
/* Programs that can be attached. */
#define BPF_APROG_SEC(string, ptype, atype) \
- BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
+ BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0)
/* Programs that must specify expected attach type at load time. */
#define BPF_EAPROG_SEC(string, ptype, eatype) \
- BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
+ BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0)
+
+/* Programs that use BTF to identify attach point */
+#define BPF_PROG_BTF(string, ptype, eatype) \
+ BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1)
/* Programs that can be attached but attach type can't be identified by section
* name. Kept for backward compatibility.
*/
#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype)
-static const struct {
- const char *sec;
- size_t len;
- enum bpf_prog_type prog_type;
- enum bpf_attach_type expected_attach_type;
- int is_attachable;
- enum bpf_attach_type attach_type;
-} section_names[] = {
+#define SEC_DEF(sec_pfx, ptype, ...) { \
+ .sec = sec_pfx, \
+ .len = sizeof(sec_pfx) - 1, \
+ .prog_type = BPF_PROG_TYPE_##ptype, \
+ __VA_ARGS__ \
+}
+
+static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
+ struct bpf_program *prog);
+static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
+ struct bpf_program *prog);
+static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
+ struct bpf_program *prog);
+static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
+ struct bpf_program *prog);
+static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
+ struct bpf_program *prog);
+static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
+ struct bpf_program *prog);
+
+static const struct bpf_sec_def section_defs[] = {
BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER),
- BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE),
- BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE),
+ BPF_PROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT),
+ SEC_DEF("kprobe/", KPROBE,
+ .attach_fn = attach_kprobe),
+ BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE),
+ SEC_DEF("kretprobe/", KPROBE,
+ .attach_fn = attach_kprobe),
+ BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE),
BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS),
BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT),
- BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT),
- BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT),
- BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
+ SEC_DEF("tracepoint/", TRACEPOINT,
+ .attach_fn = attach_tp),
+ SEC_DEF("tp/", TRACEPOINT,
+ .attach_fn = attach_tp),
+ SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT,
+ .attach_fn = attach_raw_tp),
+ SEC_DEF("raw_tp/", RAW_TRACEPOINT,
+ .attach_fn = attach_raw_tp),
+ SEC_DEF("tp_btf/", TRACING,
+ .expected_attach_type = BPF_TRACE_RAW_TP,
+ .is_attach_btf = true,
+ .attach_fn = attach_trace),
+ SEC_DEF("fentry/", TRACING,
+ .expected_attach_type = BPF_TRACE_FENTRY,
+ .is_attach_btf = true,
+ .attach_fn = attach_trace),
+ SEC_DEF("fmod_ret/", TRACING,
+ .expected_attach_type = BPF_MODIFY_RETURN,
+ .is_attach_btf = true,
+ .attach_fn = attach_trace),
+ SEC_DEF("fexit/", TRACING,
+ .expected_attach_type = BPF_TRACE_FEXIT,
+ .is_attach_btf = true,
+ .attach_fn = attach_trace),
+ SEC_DEF("fentry.s/", TRACING,
+ .expected_attach_type = BPF_TRACE_FENTRY,
+ .is_attach_btf = true,
+ .is_sleepable = true,
+ .attach_fn = attach_trace),
+ SEC_DEF("fmod_ret.s/", TRACING,
+ .expected_attach_type = BPF_MODIFY_RETURN,
+ .is_attach_btf = true,
+ .is_sleepable = true,
+ .attach_fn = attach_trace),
+ SEC_DEF("fexit.s/", TRACING,
+ .expected_attach_type = BPF_TRACE_FEXIT,
+ .is_attach_btf = true,
+ .is_sleepable = true,
+ .attach_fn = attach_trace),
+ SEC_DEF("freplace/", EXT,
+ .is_attach_btf = true,
+ .attach_fn = attach_trace),
+ SEC_DEF("lsm/", LSM,
+ .is_attach_btf = true,
+ .expected_attach_type = BPF_LSM_MAC,
+ .attach_fn = attach_lsm),
+ SEC_DEF("lsm.s/", LSM,
+ .is_attach_btf = true,
+ .is_sleepable = true,
+ .expected_attach_type = BPF_LSM_MAC,
+ .attach_fn = attach_lsm),
+ SEC_DEF("iter/", TRACING,
+ .expected_attach_type = BPF_TRACE_ITER,
+ .is_attach_btf = true,
+ .attach_fn = attach_iter),
+ BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP,
+ BPF_XDP_DEVMAP),
+ BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP,
+ BPF_XDP_CPUMAP),
+ BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP,
+ BPF_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT),
@@ -4506,6 +8385,10 @@
BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB,
BPF_CGROUP_INET_EGRESS),
BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB),
+ BPF_EAPROG_SEC("cgroup/sock_create", BPF_PROG_TYPE_CGROUP_SOCK,
+ BPF_CGROUP_INET_SOCK_CREATE),
+ BPF_EAPROG_SEC("cgroup/sock_release", BPF_PROG_TYPE_CGROUP_SOCK,
+ BPF_CGROUP_INET_SOCK_RELEASE),
BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK,
BPF_CGROUP_INET_SOCK_CREATE),
BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK,
@@ -4543,12 +8426,23 @@
BPF_CGROUP_UDP4_RECVMSG),
BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
BPF_CGROUP_UDP6_RECVMSG),
+ BPF_EAPROG_SEC("cgroup/getpeername4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_INET4_GETPEERNAME),
+ BPF_EAPROG_SEC("cgroup/getpeername6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_INET6_GETPEERNAME),
+ BPF_EAPROG_SEC("cgroup/getsockname4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_INET4_GETSOCKNAME),
+ BPF_EAPROG_SEC("cgroup/getsockname6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_INET6_GETSOCKNAME),
BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_CGROUP_SYSCTL),
BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_CGROUP_GETSOCKOPT),
BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_CGROUP_SETSOCKOPT),
+ BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS),
+ BPF_EAPROG_SEC("sk_lookup/", BPF_PROG_TYPE_SK_LOOKUP,
+ BPF_SK_LOOKUP),
};
#undef BPF_PROG_SEC_IMPL
@@ -4556,12 +8450,26 @@
#undef BPF_APROG_SEC
#undef BPF_EAPROG_SEC
#undef BPF_APROG_COMPAT
+#undef SEC_DEF
#define MAX_TYPE_NAME_SIZE 32
+static const struct bpf_sec_def *find_sec_def(const char *sec_name)
+{
+ int i, n = ARRAY_SIZE(section_defs);
+
+ for (i = 0; i < n; i++) {
+ if (strncmp(sec_name,
+ section_defs[i].sec, section_defs[i].len))
+ continue;
+ return §ion_defs[i];
+ }
+ return NULL;
+}
+
static char *libbpf_get_type_names(bool attach_type)
{
- int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE;
+ int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE;
char *buf;
buf = malloc(len);
@@ -4570,16 +8478,16 @@
buf[0] = '\0';
/* Forge string buf with all available names */
- for (i = 0; i < ARRAY_SIZE(section_names); i++) {
- if (attach_type && !section_names[i].is_attachable)
+ for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
+ if (attach_type && !section_defs[i].is_attachable)
continue;
- if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) {
+ if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) {
free(buf);
return NULL;
}
strcat(buf, " ");
- strcat(buf, section_names[i].sec);
+ strcat(buf, section_defs[i].sec);
}
return buf;
@@ -4588,29 +8496,286 @@
int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
enum bpf_attach_type *expected_attach_type)
{
+ const struct bpf_sec_def *sec_def;
char *type_names;
- int i;
if (!name)
return -EINVAL;
- for (i = 0; i < ARRAY_SIZE(section_names); i++) {
- if (strncmp(name, section_names[i].sec, section_names[i].len))
- continue;
- *prog_type = section_names[i].prog_type;
- *expected_attach_type = section_names[i].expected_attach_type;
+ sec_def = find_sec_def(name);
+ if (sec_def) {
+ *prog_type = sec_def->prog_type;
+ *expected_attach_type = sec_def->expected_attach_type;
return 0;
}
- pr_warning("failed to guess program type based on ELF section name '%s'\n", name);
+
+ pr_debug("failed to guess program type from ELF section '%s'\n", name);
type_names = libbpf_get_type_names(false);
if (type_names != NULL) {
- pr_info("supported section(type) names are:%s\n", type_names);
+ pr_debug("supported section(type) names are:%s\n", type_names);
free(type_names);
}
+ return -ESRCH;
+}
+
+static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
+ size_t offset)
+{
+ struct bpf_map *map;
+ size_t i;
+
+ for (i = 0; i < obj->nr_maps; i++) {
+ map = &obj->maps[i];
+ if (!bpf_map__is_struct_ops(map))
+ continue;
+ if (map->sec_offset <= offset &&
+ offset - map->sec_offset < map->def.value_size)
+ return map;
+ }
+
+ return NULL;
+}
+
+/* Collect the reloc from ELF and populate the st_ops->progs[] */
+static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
+ GElf_Shdr *shdr, Elf_Data *data)
+{
+ const struct btf_member *member;
+ struct bpf_struct_ops *st_ops;
+ struct bpf_program *prog;
+ unsigned int shdr_idx;
+ const struct btf *btf;
+ struct bpf_map *map;
+ Elf_Data *symbols;
+ unsigned int moff, insn_idx;
+ const char *name;
+ __u32 member_idx;
+ GElf_Sym sym;
+ GElf_Rel rel;
+ int i, nrels;
+
+ symbols = obj->efile.symbols;
+ btf = obj->btf;
+ nrels = shdr->sh_size / shdr->sh_entsize;
+ for (i = 0; i < nrels; i++) {
+ if (!gelf_getrel(data, i, &rel)) {
+ pr_warn("struct_ops reloc: failed to get %d reloc\n", i);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+ pr_warn("struct_ops reloc: symbol %zx not found\n",
+ (size_t)GELF_R_SYM(rel.r_info));
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ name = elf_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;
+ }
+
+ if (prog->type == BPF_PROG_TYPE_UNSPEC) {
+ const struct bpf_sec_def *sec_def;
+
+ sec_def = find_sec_def(prog->sec_name);
+ if (sec_def &&
+ sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) {
+ /* for pr_warn */
+ prog->type = sec_def->prog_type;
+ goto invalid_prog;
+ }
+
+ prog->type = BPF_PROG_TYPE_STRUCT_OPS;
+ prog->attach_btf_id = st_ops->type_id;
+ prog->expected_attach_type = member_idx;
+ } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
+ prog->attach_btf_id != st_ops->type_id ||
+ prog->expected_attach_type != member_idx) {
+ goto invalid_prog;
+ }
+ st_ops->progs[member_idx] = prog;
+ }
+
+ return 0;
+
+invalid_prog:
+ pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
+ map->name, prog->name, prog->sec_name, prog->type,
+ prog->attach_btf_id, prog->expected_attach_type, name);
return -EINVAL;
}
+#define BTF_TRACE_PREFIX "btf_trace_"
+#define BTF_LSM_PREFIX "bpf_lsm_"
+#define BTF_ITER_PREFIX "bpf_iter_"
+#define BTF_MAX_NAME_SIZE 128
+
+static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
+ const char *name, __u32 kind)
+{
+ char btf_type_name[BTF_MAX_NAME_SIZE];
+ int ret;
+
+ ret = snprintf(btf_type_name, sizeof(btf_type_name),
+ "%s%s", prefix, name);
+ /* snprintf returns the number of characters written excluding the
+ * the terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it
+ * indicates truncation.
+ */
+ if (ret < 0 || ret >= sizeof(btf_type_name))
+ return -ENAMETOOLONG;
+ return btf__find_by_name_kind(btf, btf_type_name, kind);
+}
+
+static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name,
+ enum bpf_attach_type attach_type)
+{
+ int err;
+
+ if (attach_type == BPF_TRACE_RAW_TP)
+ err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name,
+ BTF_KIND_TYPEDEF);
+ else if (attach_type == BPF_LSM_MAC)
+ err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name,
+ BTF_KIND_FUNC);
+ else if (attach_type == BPF_TRACE_ITER)
+ err = find_btf_by_prefix_kind(btf, BTF_ITER_PREFIX, name,
+ BTF_KIND_FUNC);
+ else
+ err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+
+ if (err <= 0)
+ pr_warn("%s is not found in vmlinux BTF\n", name);
+
+ return err;
+}
+
+int libbpf_find_vmlinux_btf_id(const char *name,
+ enum bpf_attach_type attach_type)
+{
+ struct btf *btf;
+ int err;
+
+ btf = libbpf_find_kernel_btf();
+ if (IS_ERR(btf)) {
+ pr_warn("vmlinux BTF is not found\n");
+ return -EINVAL;
+ }
+
+ err = __find_vmlinux_btf_id(btf, name, attach_type);
+ btf__free(btf);
+ return err;
+}
+
+static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
+{
+ struct bpf_prog_info_linear *info_linear;
+ struct bpf_prog_info *info;
+ struct btf *btf = NULL;
+ int err = -EINVAL;
+
+ info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0);
+ if (IS_ERR_OR_NULL(info_linear)) {
+ pr_warn("failed get_prog_info_linear for FD %d\n",
+ attach_prog_fd);
+ return -EINVAL;
+ }
+ info = &info_linear->info;
+ if (!info->btf_id) {
+ pr_warn("The target program doesn't have BTF\n");
+ goto out;
+ }
+ if (btf__get_from_id(info->btf_id, &btf)) {
+ pr_warn("Failed to get BTF of the program\n");
+ goto out;
+ }
+ err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+ btf__free(btf);
+ if (err <= 0) {
+ pr_warn("%s is not found in prog's BTF\n", name);
+ goto out;
+ }
+out:
+ free(info_linear);
+ return err;
+}
+
+static int libbpf_find_attach_btf_id(struct bpf_program *prog)
+{
+ enum bpf_attach_type attach_type = prog->expected_attach_type;
+ __u32 attach_prog_fd = prog->attach_prog_fd;
+ const char *name = prog->sec_name;
+ int i, err;
+
+ if (!name)
+ return -EINVAL;
+
+ for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
+ if (!section_defs[i].is_attach_btf)
+ continue;
+ if (strncmp(name, section_defs[i].sec, section_defs[i].len))
+ continue;
+ if (attach_prog_fd)
+ err = libbpf_find_prog_btf_id(name + section_defs[i].len,
+ attach_prog_fd);
+ else
+ err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
+ name + section_defs[i].len,
+ attach_type);
+ return err;
+ }
+ pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name);
+ return -ESRCH;
+}
+
int libbpf_attach_type_by_name(const char *name,
enum bpf_attach_type *attach_type)
{
@@ -4620,33 +8785,24 @@
if (!name)
return -EINVAL;
- for (i = 0; i < ARRAY_SIZE(section_names); i++) {
- if (strncmp(name, section_names[i].sec, section_names[i].len))
+ for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
+ if (strncmp(name, section_defs[i].sec, section_defs[i].len))
continue;
- if (!section_names[i].is_attachable)
+ if (!section_defs[i].is_attachable)
return -EINVAL;
- *attach_type = section_names[i].attach_type;
+ *attach_type = section_defs[i].expected_attach_type;
return 0;
}
- pr_warning("failed to guess attach type based on ELF section name '%s'\n", name);
+ pr_debug("failed to guess attach type based on ELF section name '%s'\n", name);
type_names = libbpf_get_type_names(true);
if (type_names != NULL) {
- pr_info("attachable section(type) names are:%s\n", type_names);
+ pr_debug("attachable section(type) names are:%s\n", type_names);
free(type_names);
}
return -EINVAL;
}
-static int
-bpf_program__identify_section(struct bpf_program *prog,
- enum bpf_prog_type *prog_type,
- enum bpf_attach_type *expected_attach_type)
-{
- return libbpf_prog_type_by_name(prog->section_name, prog_type,
- expected_attach_type);
-}
-
int bpf_map__fd(const struct bpf_map *map)
{
return map ? map->fd : -EINVAL;
@@ -4662,6 +8818,71 @@
return map ? map->name : NULL;
}
+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 -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 -EBUSY;
+ map->def.map_flags = flags;
+ 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 -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 -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 -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;
@@ -4693,6 +8914,17 @@
return map ? map->priv : ERR_PTR(-EINVAL);
}
+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 -EINVAL;
+
+ memcpy(map->mmaped, data, size);
+ return 0;
+}
+
bool bpf_map__is_offload_neutral(const struct bpf_map *map)
{
return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
@@ -4703,19 +8935,27 @@
return map->libbpf_type != LIBBPF_MAP_UNSPEC;
}
-void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
+__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 -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_warning("error: unsupported map type\n");
+ pr_warn("error: unsupported map type\n");
return -EINVAL;
}
if (map->inner_map_fd != -1) {
- pr_warning("error: inner_map_fd already specified\n");
+ pr_warn("error: inner_map_fd already specified\n");
return -EINVAL;
}
map->inner_map_fd = fd;
@@ -4735,8 +8975,8 @@
e = obj->maps + obj->nr_maps;
if ((m < s) || (m >= e)) {
- pr_warning("error in %s: map handler doesn't belong to object\n",
- __func__);
+ pr_warn("error in %s: map handler doesn't belong to object\n",
+ __func__);
return NULL;
}
@@ -4814,8 +9054,6 @@
{
struct bpf_object_open_attr open_attr = {};
struct bpf_program *prog, *first_prog = NULL;
- enum bpf_attach_type expected_attach_type;
- enum bpf_prog_type prog_type;
struct bpf_object *obj;
struct bpf_map *map;
int err;
@@ -4833,28 +9071,29 @@
return -ENOENT;
bpf_object__for_each_program(prog, obj) {
+ enum bpf_attach_type attach_type = attr->expected_attach_type;
/*
- * If type is not specified, try to guess it based on
- * section name.
+ * to preserve backwards compatibility, bpf_prog_load treats
+ * attr->prog_type, if specified, as an override to whatever
+ * bpf_object__open guessed
*/
- prog_type = attr->prog_type;
- prog->prog_ifindex = attr->ifindex;
- expected_attach_type = attr->expected_attach_type;
- if (prog_type == BPF_PROG_TYPE_UNSPEC) {
- err = bpf_program__identify_section(prog, &prog_type,
- &expected_attach_type);
- if (err < 0) {
- bpf_object__close(obj);
- return -EINVAL;
- }
+ if (attr->prog_type != BPF_PROG_TYPE_UNSPEC) {
+ bpf_program__set_type(prog, attr->prog_type);
+ bpf_program__set_expected_attach_type(prog,
+ attach_type);
+ }
+ if (bpf_program__get_type(prog) == BPF_PROG_TYPE_UNSPEC) {
+ /*
+ * we haven't guessed from section name and user
+ * didn't provide a fallback type, too bad...
+ */
+ bpf_object__close(obj);
+ return -EINVAL;
}
- bpf_program__set_type(prog, prog_type);
- bpf_program__set_expected_attach_type(prog,
- expected_attach_type);
-
+ prog->prog_ifindex = attr->ifindex;
prog->log_level = attr->log_level;
- prog->prog_flags = attr->prog_flags;
+ prog->prog_flags |= attr->prog_flags;
if (!first_prog)
first_prog = prog;
}
@@ -4865,7 +9104,7 @@
}
if (!first_prog) {
- pr_warning("object file doesn't contain bpf program\n");
+ pr_warn("object file doesn't contain bpf program\n");
bpf_object__close(obj);
return -ENOENT;
}
@@ -4873,7 +9112,7 @@
err = bpf_object__load(obj);
if (err) {
bpf_object__close(obj);
- return -EINVAL;
+ return err;
}
*pobj = obj;
@@ -4882,37 +9121,153 @@
}
struct bpf_link {
+ int (*detach)(struct bpf_link *link);
int (*destroy)(struct bpf_link *link);
+ char *pin_path; /* NULL, if not pinned */
+ int fd; /* hook FD, -1 if not applicable */
+ bool disconnected;
};
+/* Replace link's underlying BPF program with the new one */
+int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog)
+{
+ return bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+}
+
+/* Release "ownership" of underlying BPF resource (typically, BPF program
+ * attached to some BPF hook, e.g., tracepoint, kprobe, etc). Disconnected
+ * link, when destructed through bpf_link__destroy() call won't attempt to
+ * detach/unregisted that BPF resource. This is useful in situations where,
+ * say, attached BPF program has to outlive userspace program that attached it
+ * in the system. Depending on type of BPF program, though, there might be
+ * additional steps (like pinning BPF program in BPF FS) necessary to ensure
+ * exit of userspace program doesn't trigger automatic detachment and clean up
+ * inside the kernel.
+ */
+void bpf_link__disconnect(struct bpf_link *link)
+{
+ link->disconnected = true;
+}
+
int bpf_link__destroy(struct bpf_link *link)
{
- int err;
+ int err = 0;
- if (!link)
+ if (IS_ERR_OR_NULL(link))
return 0;
- err = link->destroy(link);
+ if (!link->disconnected && link->detach)
+ err = link->detach(link);
+ if (link->destroy)
+ link->destroy(link);
+ if (link->pin_path)
+ free(link->pin_path);
free(link);
return err;
}
-struct bpf_link_fd {
- struct bpf_link link; /* has to be at the top of struct */
- int fd; /* hook FD */
-};
-
-static int bpf_link__destroy_perf_event(struct bpf_link *link)
+int bpf_link__fd(const struct bpf_link *link)
{
- struct bpf_link_fd *l = (void *)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 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 ERR_PTR(fd);
+ }
+
+ link = calloc(1, sizeof(*link));
+ if (!link) {
+ close(fd);
+ return 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 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;
- err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0);
+ if (link->pin_path)
+ return -EBUSY;
+ err = make_parent_dir(path);
+ if (err)
+ return err;
+ err = check_path(path);
+ if (err)
+ return err;
+
+ link->pin_path = strdup(path);
+ if (!link->pin_path)
+ return -ENOMEM;
+
+ if (bpf_obj_pin(link->fd, link->pin_path)) {
+ err = -errno;
+ zfree(&link->pin_path);
+ return 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 -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;
+}
+
+static int bpf_link__detach_perf_event(struct bpf_link *link)
+{
+ int err;
+
+ err = ioctl(link->fd, PERF_EVENT_IOC_DISABLE, 0);
if (err)
err = -errno;
- close(l->fd);
+ close(link->fd);
return err;
}
@@ -4920,44 +9275,45 @@
int pfd)
{
char errmsg[STRERR_BUFSIZE];
- struct bpf_link_fd *link;
+ struct bpf_link *link;
int prog_fd, err;
if (pfd < 0) {
- pr_warning("program '%s': invalid perf event FD %d\n",
- bpf_program__title(prog, false), pfd);
+ pr_warn("prog '%s': invalid perf event FD %d\n",
+ prog->name, pfd);
return ERR_PTR(-EINVAL);
}
prog_fd = bpf_program__fd(prog);
if (prog_fd < 0) {
- pr_warning("program '%s': can't attach BPF program w/o FD (did you load it?)\n",
- bpf_program__title(prog, false));
+ pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n",
+ prog->name);
return ERR_PTR(-EINVAL);
}
- link = malloc(sizeof(*link));
+ link = calloc(1, sizeof(*link));
if (!link)
return ERR_PTR(-ENOMEM);
- link->link.destroy = &bpf_link__destroy_perf_event;
+ link->detach = &bpf_link__detach_perf_event;
link->fd = pfd;
if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
err = -errno;
free(link);
- pr_warning("program '%s': failed to attach to pfd %d: %s\n",
- bpf_program__title(prog, false), pfd,
- libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ pr_warn("prog '%s': failed to attach to pfd %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);
return ERR_PTR(err);
}
if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
err = -errno;
free(link);
- pr_warning("program '%s': failed to enable pfd %d: %s\n",
- bpf_program__title(prog, false), pfd,
- libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ pr_warn("prog '%s': failed to enable pfd %d: %s\n",
+ prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
return ERR_PTR(err);
}
- return (struct bpf_link *)link;
+ return link;
}
/*
@@ -5028,9 +9384,9 @@
type = uprobe ? determine_uprobe_perf_type()
: determine_kprobe_perf_type();
if (type < 0) {
- pr_warning("failed to determine %s perf type: %s\n",
- uprobe ? "uprobe" : "kprobe",
- libbpf_strerror_r(type, errmsg, sizeof(errmsg)));
+ pr_warn("failed to determine %s perf type: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(type, errmsg, sizeof(errmsg)));
return type;
}
if (retprobe) {
@@ -5038,10 +9394,9 @@
: determine_kprobe_retprobe_bit();
if (bit < 0) {
- pr_warning("failed to determine %s retprobe bit: %s\n",
- uprobe ? "uprobe" : "kprobe",
- libbpf_strerror_r(bit, errmsg,
- sizeof(errmsg)));
+ pr_warn("failed to determine %s retprobe bit: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(bit, errmsg, sizeof(errmsg)));
return bit;
}
attr.config |= 1 << bit;
@@ -5058,9 +9413,9 @@
-1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
if (pfd < 0) {
err = -errno;
- pr_warning("%s perf_event_open() failed: %s\n",
- uprobe ? "uprobe" : "kprobe",
- libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ pr_warn("%s perf_event_open() failed: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
return err;
}
return pfd;
@@ -5077,25 +9432,35 @@
pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
0 /* offset */, -1 /* pid */);
if (pfd < 0) {
- pr_warning("program '%s': failed to create %s '%s' perf event: %s\n",
- bpf_program__title(prog, false),
- retprobe ? "kretprobe" : "kprobe", func_name,
- libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
+ prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
return ERR_PTR(pfd);
}
link = bpf_program__attach_perf_event(prog, pfd);
if (IS_ERR(link)) {
close(pfd);
err = PTR_ERR(link);
- pr_warning("program '%s': failed to attach to %s '%s': %s\n",
- bpf_program__title(prog, false),
- retprobe ? "kretprobe" : "kprobe", func_name,
- libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
+ prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
return link;
}
return link;
}
+static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
+ struct bpf_program *prog)
+{
+ const char *func_name;
+ bool retprobe;
+
+ func_name = prog->sec_name + sec->len;
+ retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+
+ return bpf_program__attach_kprobe(prog, retprobe, func_name);
+}
+
struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
bool retprobe, pid_t pid,
const char *binary_path,
@@ -5108,22 +9473,20 @@
pfd = perf_event_open_probe(true /* uprobe */, retprobe,
binary_path, func_offset, pid);
if (pfd < 0) {
- pr_warning("program '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
- bpf_program__title(prog, false),
- retprobe ? "uretprobe" : "uprobe",
- binary_path, func_offset,
- libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ pr_warn("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(pfd, errmsg, sizeof(errmsg)));
return ERR_PTR(pfd);
}
link = bpf_program__attach_perf_event(prog, pfd);
if (IS_ERR(link)) {
close(pfd);
err = PTR_ERR(link);
- pr_warning("program '%s': failed to attach to %s '%s:0x%zx': %s\n",
- bpf_program__title(prog, false),
- retprobe ? "uretprobe" : "uprobe",
- binary_path, func_offset,
- libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ pr_warn("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)));
return link;
}
return link;
@@ -5157,9 +9520,9 @@
tp_id = determine_tracepoint_id(tp_category, tp_name);
if (tp_id < 0) {
- pr_warning("failed to determine tracepoint '%s/%s' perf event ID: %s\n",
- tp_category, tp_name,
- libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg)));
+ pr_warn("failed to determine tracepoint '%s/%s' perf event ID: %s\n",
+ tp_category, tp_name,
+ libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg)));
return tp_id;
}
@@ -5171,9 +9534,9 @@
-1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
if (pfd < 0) {
err = -errno;
- pr_warning("tracepoint '%s/%s' perf_event_open() failed: %s\n",
- tp_category, tp_name,
- libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ pr_warn("tracepoint '%s/%s' perf_event_open() failed: %s\n",
+ tp_category, tp_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
return err;
}
return pfd;
@@ -5189,64 +9552,333 @@
pfd = perf_event_open_tracepoint(tp_category, tp_name);
if (pfd < 0) {
- pr_warning("program '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
- bpf_program__title(prog, false),
- tp_category, tp_name,
- libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ pr_warn("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 ERR_PTR(pfd);
}
link = bpf_program__attach_perf_event(prog, pfd);
if (IS_ERR(link)) {
close(pfd);
err = PTR_ERR(link);
- pr_warning("program '%s': failed to attach to tracepoint '%s/%s': %s\n",
- bpf_program__title(prog, false),
- tp_category, tp_name,
- libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ pr_warn("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 link;
}
return link;
}
-static int bpf_link__destroy_fd(struct bpf_link *link)
+static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
+ struct bpf_program *prog)
{
- struct bpf_link_fd *l = (void *)link;
+ char *sec_name, *tp_cat, *tp_name;
+ struct bpf_link *link;
- return close(l->fd);
+ sec_name = strdup(prog->sec_name);
+ if (!sec_name)
+ return ERR_PTR(-ENOMEM);
+
+ /* extract "tp/<category>/<name>" */
+ tp_cat = sec_name + sec->len;
+ tp_name = strchr(tp_cat, '/');
+ if (!tp_name) {
+ link = ERR_PTR(-EINVAL);
+ goto out;
+ }
+ *tp_name = '\0';
+ tp_name++;
+
+ link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name);
+out:
+ free(sec_name);
+ return link;
}
struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
const char *tp_name)
{
char errmsg[STRERR_BUFSIZE];
- struct bpf_link_fd *link;
+ struct bpf_link *link;
int prog_fd, pfd;
prog_fd = bpf_program__fd(prog);
if (prog_fd < 0) {
- pr_warning("program '%s': can't attach before loaded\n",
- bpf_program__title(prog, false));
+ pr_warn("prog '%s': can't attach before loaded\n", prog->name);
return ERR_PTR(-EINVAL);
}
- link = malloc(sizeof(*link));
+ link = calloc(1, sizeof(*link));
if (!link)
return ERR_PTR(-ENOMEM);
- link->link.destroy = &bpf_link__destroy_fd;
+ link->detach = &bpf_link__detach_fd;
pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
if (pfd < 0) {
pfd = -errno;
free(link);
- pr_warning("program '%s': failed to attach to raw tracepoint '%s': %s\n",
- bpf_program__title(prog, false), tp_name,
- libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ pr_warn("prog '%s': failed to attach to raw tracepoint '%s': %s\n",
+ prog->name, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link->fd = pfd;
+ return link;
+}
+
+static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
+ struct bpf_program *prog)
+{
+ const char *tp_name = prog->sec_name + sec->len;
+
+ return bpf_program__attach_raw_tracepoint(prog, tp_name);
+}
+
+/* Common logic for all BPF program types that attach to a btf_id */
+static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
+{
+ 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 ERR_PTR(-EINVAL);
+ }
+
+ link = calloc(1, sizeof(*link));
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ link->detach = &bpf_link__detach_fd;
+
+ pfd = bpf_raw_tracepoint_open(NULL, prog_fd);
+ 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 ERR_PTR(pfd);
}
link->fd = pfd;
return (struct bpf_link *)link;
}
+struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+{
+ return bpf_program__attach_btf_id(prog);
+}
+
+struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog)
+{
+ return bpf_program__attach_btf_id(prog);
+}
+
+static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
+ struct bpf_program *prog)
+{
+ return bpf_program__attach_trace(prog);
+}
+
+static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
+ struct bpf_program *prog)
+{
+ return bpf_program__attach_lsm(prog);
+}
+
+static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
+ struct bpf_program *prog)
+{
+ return bpf_program__attach_iter(prog, NULL);
+}
+
+static struct bpf_link *
+bpf_program__attach_fd(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 ERR_PTR(-EINVAL);
+ }
+
+ link = calloc(1, sizeof(*link));
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ link->detach = &bpf_link__detach_fd;
+
+ attach_type = bpf_program__get_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 ERR_PTR(link_fd);
+ }
+ link->fd = link_fd;
+ return link;
+}
+
+struct bpf_link *
+bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
+{
+ return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup");
+}
+
+struct bpf_link *
+bpf_program__attach_netns(struct bpf_program *prog, int netns_fd)
+{
+ return bpf_program__attach_fd(prog, netns_fd, 0, "netns");
+}
+
+struct bpf_link *bpf_program__attach_xdp(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(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 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 ERR_PTR(-EINVAL);
+ }
+
+ if (target_fd) {
+ btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd);
+ if (btf_id < 0)
+ return 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(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 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 ERR_PTR(-EINVAL);
+ }
+
+ link = calloc(1, sizeof(*link));
+ if (!link)
+ return 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 ERR_PTR(link_fd);
+ }
+ link->fd = link_fd;
+ return link;
+}
+
+struct bpf_link *bpf_program__attach(struct bpf_program *prog)
+{
+ const struct bpf_sec_def *sec_def;
+
+ sec_def = find_sec_def(prog->sec_name);
+ if (!sec_def || !sec_def->attach_fn)
+ return ERR_PTR(-ESRCH);
+
+ return sec_def->attach_fn(sec_def, prog);
+}
+
+static int bpf_link__detach_struct_ops(struct bpf_link *link)
+{
+ __u32 zero = 0;
+
+ if (bpf_map_delete_elem(link->fd, &zero))
+ return -errno;
+
+ return 0;
+}
+
+struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
+{
+ struct bpf_struct_ops *st_ops;
+ struct bpf_link *link;
+ __u32 i, zero = 0;
+ int err;
+
+ if (!bpf_map__is_struct_ops(map) || map->fd == -1)
+ return ERR_PTR(-EINVAL);
+
+ link = calloc(1, sizeof(*link));
+ if (!link)
+ return ERR_PTR(-EINVAL);
+
+ st_ops = map->st_ops;
+ for (i = 0; i < btf_vlen(st_ops->type); i++) {
+ struct bpf_program *prog = st_ops->progs[i];
+ void *kern_data;
+ int prog_fd;
+
+ if (!prog)
+ continue;
+
+ prog_fd = bpf_program__fd(prog);
+ kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i];
+ *(unsigned long *)kern_data = prog_fd;
+ }
+
+ err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0);
+ if (err) {
+ err = -errno;
+ free(link);
+ return ERR_PTR(err);
+ }
+
+ link->detach = bpf_link__detach_struct_ops;
+ link->fd = map->fd;
+
+ return link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
@@ -5330,7 +9962,7 @@
size_t mmap_size;
struct perf_cpu_buf **cpu_bufs;
struct epoll_event *events;
- int cpu_cnt;
+ int cpu_cnt; /* number of allocated CPU buffers */
int epoll_fd; /* perf event FD */
int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */
};
@@ -5342,7 +9974,7 @@
return;
if (cpu_buf->base &&
munmap(cpu_buf->base, pb->mmap_size + pb->page_size))
- pr_warning("failed to munmap cpu_buf #%d\n", cpu_buf->cpu);
+ pr_warn("failed to munmap cpu_buf #%d\n", cpu_buf->cpu);
if (cpu_buf->fd >= 0) {
ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0);
close(cpu_buf->fd);
@@ -5355,7 +9987,7 @@
{
int i;
- if (!pb)
+ if (IS_ERR_OR_NULL(pb))
return;
if (pb->cpu_bufs) {
for (i = 0; i < pb->cpu_cnt; i++) {
@@ -5395,8 +10027,8 @@
-1, PERF_FLAG_FD_CLOEXEC);
if (cpu_buf->fd < 0) {
err = -errno;
- pr_warning("failed to open perf buffer event on cpu #%d: %s\n",
- cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ pr_warn("failed to open perf buffer event on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
goto error;
}
@@ -5406,15 +10038,15 @@
if (cpu_buf->base == MAP_FAILED) {
cpu_buf->base = NULL;
err = -errno;
- pr_warning("failed to mmap perf buffer on cpu #%d: %s\n",
- cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ pr_warn("failed to mmap perf buffer on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
goto error;
}
if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
err = -errno;
- pr_warning("failed to enable perf buffer event on cpu #%d: %s\n",
- cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ pr_warn("failed to enable perf buffer event on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
goto error;
}
@@ -5434,7 +10066,7 @@
struct perf_buffer_params p = {};
struct perf_event_attr attr = { 0, };
- attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+ attr.config = PERF_COUNT_SW_BPF_OUTPUT;
attr.type = PERF_TYPE_SOFTWARE;
attr.sample_type = PERF_SAMPLE_RAW;
attr.sample_period = 1;
@@ -5467,31 +10099,42 @@
static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
struct perf_buffer_params *p)
{
- struct bpf_map_info map = {};
+ const char *online_cpus_file = "/sys/devices/system/cpu/online";
+ struct bpf_map_info map;
char msg[STRERR_BUFSIZE];
struct perf_buffer *pb;
+ bool *online = NULL;
__u32 map_info_len;
- int err, i;
+ int err, i, j, n;
if (page_cnt & (page_cnt - 1)) {
- pr_warning("page count should be power of two, but is %zu\n",
- page_cnt);
+ pr_warn("page count should be power of two, but is %zu\n",
+ page_cnt);
return ERR_PTR(-EINVAL);
}
+ /* 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;
- pr_warning("failed to get map info for map FD %d: %s\n",
- map_fd, libbpf_strerror_r(err, msg, sizeof(msg)));
- return ERR_PTR(err);
- }
-
- if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
- pr_warning("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
- map.name);
- return ERR_PTR(-EINVAL);
+ /* 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));
@@ -5510,8 +10153,8 @@
pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
if (pb->epoll_fd < 0) {
err = -errno;
- pr_warning("failed to create epoll instance: %s\n",
- libbpf_strerror_r(err, msg, sizeof(msg)));
+ pr_warn("failed to create epoll instance: %s\n",
+ libbpf_strerror_r(err, msg, sizeof(msg)));
goto error;
}
@@ -5523,63 +10166,79 @@
err = pb->cpu_cnt;
goto error;
}
- if (map.max_entries < pb->cpu_cnt)
+ 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_warning("failed to allocate events: out of memory\n");
+ pr_warn("failed to allocate events: out of memory\n");
goto error;
}
pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs));
if (!pb->cpu_bufs) {
err = -ENOMEM;
- pr_warning("failed to allocate buffers: out of memory\n");
+ pr_warn("failed to allocate buffers: out of memory\n");
goto error;
}
- for (i = 0; i < pb->cpu_cnt; i++) {
+ err = parse_cpu_mask_file(online_cpus_file, &online, &n);
+ if (err) {
+ pr_warn("failed to get online CPU mask: %d\n", err);
+ goto error;
+ }
+
+ for (i = 0, j = 0; i < pb->cpu_cnt; i++) {
struct perf_cpu_buf *cpu_buf;
int cpu, map_key;
cpu = p->cpu_cnt > 0 ? p->cpus[i] : i;
map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i;
+ /* in case user didn't explicitly requested particular CPUs to
+ * be attached to, skip offline/not present CPUs
+ */
+ if (p->cpu_cnt <= 0 && (cpu >= n || !online[cpu]))
+ continue;
+
cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key);
if (IS_ERR(cpu_buf)) {
err = PTR_ERR(cpu_buf);
goto error;
}
- pb->cpu_bufs[i] = cpu_buf;
+ pb->cpu_bufs[j] = cpu_buf;
err = bpf_map_update_elem(pb->map_fd, &map_key,
&cpu_buf->fd, 0);
if (err) {
err = -errno;
- pr_warning("failed to set cpu #%d, key %d -> perf FD %d: %s\n",
- cpu, map_key, cpu_buf->fd,
- libbpf_strerror_r(err, msg, sizeof(msg)));
+ pr_warn("failed to set cpu #%d, key %d -> perf FD %d: %s\n",
+ cpu, map_key, cpu_buf->fd,
+ libbpf_strerror_r(err, msg, sizeof(msg)));
goto error;
}
- pb->events[i].events = EPOLLIN;
- pb->events[i].data.ptr = cpu_buf;
+ pb->events[j].events = EPOLLIN;
+ pb->events[j].data.ptr = cpu_buf;
if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd,
- &pb->events[i]) < 0) {
+ &pb->events[j]) < 0) {
err = -errno;
- pr_warning("failed to epoll_ctl cpu #%d perf FD %d: %s\n",
- cpu, cpu_buf->fd,
- libbpf_strerror_r(err, msg, sizeof(msg)));
+ pr_warn("failed to epoll_ctl cpu #%d perf FD %d: %s\n",
+ cpu, cpu_buf->fd,
+ libbpf_strerror_r(err, msg, sizeof(msg)));
goto error;
}
+ j++;
}
+ pb->cpu_cnt = j;
+ free(online);
return pb;
error:
+ free(online);
if (pb)
perf_buffer__free(pb);
return ERR_PTR(err);
@@ -5588,7 +10247,7 @@
struct perf_sample_raw {
struct perf_event_header header;
uint32_t size;
- char data[0];
+ char data[];
};
struct perf_sample_lost {
@@ -5625,7 +10284,7 @@
break;
}
default:
- pr_warning("unknown perf sample type %d\n", e->type);
+ pr_warn("unknown perf sample type %d\n", e->type);
return LIBBPF_PERF_EVENT_ERROR;
}
return LIBBPF_PERF_EVENT_CONT;
@@ -5645,6 +10304,11 @@
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;
@@ -5655,13 +10319,81 @@
err = perf_buffer__process_records(pb, cpu_buf);
if (err) {
- pr_warning("error while processing records: %d\n", err);
+ pr_warn("error while processing records: %d\n", err);
return err;
}
}
return cnt < 0 ? -errno : 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 -EINVAL;
+
+ cpu_buf = pb->cpu_bufs[buf_idx];
+ if (!cpu_buf)
+ return -ENOENT;
+
+ return cpu_buf->fd;
+}
+
+/*
+ * 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 -EINVAL;
+
+ cpu_buf = pb->cpu_bufs[buf_idx];
+ if (!cpu_buf)
+ return -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 err;
+ }
+ }
+ return 0;
+}
+
struct bpf_prog_info_array_desc {
int array_offset; /* e.g. offset of jited_prog_insns */
int count_offset; /* e.g. offset of jited_prog_len */
@@ -5719,7 +10451,8 @@
};
-static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offset)
+static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info,
+ int offset)
{
__u32 *array = (__u32 *)info;
@@ -5728,7 +10461,8 @@
return -(int)offset;
}
-static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, int offset)
+static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info,
+ int offset)
{
__u64 *array = (__u64 *)info;
@@ -5852,13 +10586,13 @@
v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
desc->count_offset);
if (v1 != v2)
- pr_warning("%s: mismatch in element count\n", __func__);
+ pr_warn("%s: mismatch in element count\n", __func__);
v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
desc->size_offset);
if (v1 != v2)
- pr_warning("%s: mismatch in rec size\n", __func__);
+ pr_warn("%s: mismatch in rec size\n", __func__);
}
/* step 7: update info_len and data_len */
@@ -5908,6 +10642,30 @@
}
}
+int bpf_program__set_attach_target(struct bpf_program *prog,
+ int attach_prog_fd,
+ const char *attach_func_name)
+{
+ int btf_id;
+
+ if (!prog || attach_prog_fd < 0 || !attach_func_name)
+ return -EINVAL;
+
+ if (attach_prog_fd)
+ btf_id = libbpf_find_prog_btf_id(attach_func_name,
+ attach_prog_fd);
+ else
+ btf_id = libbpf_find_vmlinux_btf_id(attach_func_name,
+ prog->expected_attach_type);
+
+ if (btf_id < 0)
+ return btf_id;
+
+ prog->attach_btf_id = btf_id;
+ 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;
@@ -5924,15 +10682,15 @@
}
n = sscanf(s, "%d%n-%d%n", &start, &len, &end, &len);
if (n <= 0 || n > 2) {
- pr_warning("Failed to get CPU range %s: %d\n", s, n);
+ 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_warning("Invalid CPU range [%d,%d] in %s\n",
- start, end, s);
+ pr_warn("Invalid CPU range [%d,%d] in %s\n",
+ start, end, s);
err = -EINVAL;
goto cleanup;
}
@@ -5948,7 +10706,7 @@
s += len;
}
if (!*mask_sz) {
- pr_warning("Empty CPU range\n");
+ pr_warn("Empty CPU range\n");
return -EINVAL;
}
return 0;
@@ -5966,18 +10724,18 @@
fd = open(fcpu, O_RDONLY);
if (fd < 0) {
err = -errno;
- pr_warning("Failed to open cpu mask file %s: %d\n", fcpu, err);
+ 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_warning("Failed to read cpu mask from %s: %d\n", fcpu, err);
+ pr_warn("Failed to read cpu mask from %s: %d\n", fcpu, err);
return err;
}
if (len >= sizeof(buf)) {
- pr_warning("CPU mask is too big in file %s\n", fcpu);
+ pr_warn("CPU mask is too big in file %s\n", fcpu);
return -E2BIG;
}
buf[len] = '\0';
@@ -6010,3 +10768,166 @@
WRITE_ONCE(cpus, tmp_cpus);
return tmp_cpus;
}
+
+int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
+ const struct bpf_object_open_opts *opts)
+{
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts,
+ .object_name = s->name,
+ );
+ struct bpf_object *obj;
+ int i;
+
+ /* Attempt to preserve opts->object_name, unless overriden by user
+ * explicitly. Overwriting object name for skeletons is discouraged,
+ * as it breaks global data maps, because they contain object name
+ * prefix as their own map name prefix. When skeleton is generated,
+ * bpftool is making an assumption that this name will stay the same.
+ */
+ if (opts) {
+ memcpy(&skel_opts, opts, sizeof(*opts));
+ if (!opts->object_name)
+ skel_opts.object_name = s->name;
+ }
+
+ obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts);
+ if (IS_ERR(obj)) {
+ pr_warn("failed to initialize skeleton BPF object '%s': %ld\n",
+ s->name, PTR_ERR(obj));
+ return PTR_ERR(obj);
+ }
+
+ *s->obj = obj;
+
+ for (i = 0; i < s->map_cnt; i++) {
+ struct bpf_map **map = s->maps[i].map;
+ const char *name = s->maps[i].name;
+ void **mmaped = s->maps[i].mmaped;
+
+ *map = bpf_object__find_map_by_name(obj, name);
+ if (!*map) {
+ pr_warn("failed to find skeleton map '%s'\n", name);
+ return -ESRCH;
+ }
+
+ /* externs shouldn't be pre-setup from user code */
+ if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG)
+ *mmaped = (*map)->mmaped;
+ }
+
+ for (i = 0; i < s->prog_cnt; i++) {
+ struct bpf_program **prog = s->progs[i].prog;
+ const char *name = s->progs[i].name;
+
+ *prog = bpf_object__find_program_by_name(obj, name);
+ if (!*prog) {
+ pr_warn("failed to find skeleton program '%s'\n", name);
+ return -ESRCH;
+ }
+ }
+
+ return 0;
+}
+
+int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
+{
+ int i, err;
+
+ err = bpf_object__load(*s->obj);
+ if (err) {
+ pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err);
+ return err;
+ }
+
+ for (i = 0; i < s->map_cnt; i++) {
+ struct bpf_map *map = *s->maps[i].map;
+ size_t mmap_sz = bpf_map_mmap_sz(map);
+ int prot, map_fd = bpf_map__fd(map);
+ void **mmaped = s->maps[i].mmaped;
+
+ if (!mmaped)
+ continue;
+
+ if (!(map->def.map_flags & BPF_F_MMAPABLE)) {
+ *mmaped = NULL;
+ continue;
+ }
+
+ if (map->def.map_flags & BPF_F_RDONLY_PROG)
+ prot = PROT_READ;
+ else
+ prot = PROT_READ | PROT_WRITE;
+
+ /* Remap anonymous mmap()-ed "map initialization image" as
+ * a BPF map-backed mmap()-ed memory, but preserving the same
+ * memory address. This will cause kernel to change process'
+ * page table to point to a different piece of kernel memory,
+ * but from userspace point of view memory address (and its
+ * contents, being identical at this point) will stay the
+ * same. This mapping will be released by bpf_object__close()
+ * as per normal clean up procedure, so we don't need to worry
+ * about it from skeleton's clean up perspective.
+ */
+ *mmaped = mmap(map->mmaped, mmap_sz, prot,
+ MAP_SHARED | MAP_FIXED, map_fd, 0);
+ if (*mmaped == MAP_FAILED) {
+ err = -errno;
+ *mmaped = NULL;
+ pr_warn("failed to re-mmap() map '%s': %d\n",
+ bpf_map__name(map), err);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
+{
+ int i;
+
+ for (i = 0; i < s->prog_cnt; i++) {
+ struct bpf_program *prog = *s->progs[i].prog;
+ struct bpf_link **link = s->progs[i].link;
+ const struct bpf_sec_def *sec_def;
+
+ if (!prog->load)
+ continue;
+
+ sec_def = find_sec_def(prog->sec_name);
+ if (!sec_def || !sec_def->attach_fn)
+ continue;
+
+ *link = sec_def->attach_fn(sec_def, prog);
+ if (IS_ERR(*link)) {
+ pr_warn("failed to auto-attach program '%s': %ld\n",
+ bpf_program__name(prog), PTR_ERR(*link));
+ return PTR_ERR(*link);
+ }
+ }
+
+ return 0;
+}
+
+void bpf_object__detach_skeleton(struct bpf_object_skeleton *s)
+{
+ int i;
+
+ for (i = 0; i < s->prog_cnt; i++) {
+ struct bpf_link **link = s->progs[i].link;
+
+ bpf_link__destroy(*link);
+ *link = NULL;
+ }
+}
+
+void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s)
+{
+ if (s->progs)
+ bpf_object__detach_skeleton(s);
+ if (s->obj)
+ bpf_object__close(*s->obj);
+ free(s->maps);
+ free(s->progs);
+ free(s);
+}