summaryrefslogtreecommitdiff
path: root/tools/lib/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/lib/bpf')
-rw-r--r--tools/lib/bpf/Build2
-rw-r--r--tools/lib/bpf/bpf.c70
-rw-r--r--tools/lib/bpf/bpf.h31
-rw-r--r--tools/lib/bpf/bpf_gen_internal.h2
-rw-r--r--tools/lib/bpf/bpf_helpers.h17
-rw-r--r--tools/lib/bpf/btf.c1
-rw-r--r--tools/lib/bpf/btf.h3
-rw-r--r--tools/lib/bpf/btf_dump.c56
-rw-r--r--tools/lib/bpf/elf.c1
-rw-r--r--tools/lib/bpf/features.c1
-rw-r--r--tools/lib/bpf/gen_loader.c50
-rw-r--r--tools/lib/bpf/libbpf.c168
-rw-r--r--tools/lib/bpf/libbpf.h71
-rw-r--r--tools/lib/bpf/libbpf.map8
-rw-r--r--tools/lib/bpf/libbpf_errno.c75
-rw-r--r--tools/lib/bpf/libbpf_internal.h19
-rw-r--r--tools/lib/bpf/libbpf_utils.c252
-rw-r--r--tools/lib/bpf/libbpf_version.h2
-rw-r--r--tools/lib/bpf/linker.c1
-rw-r--r--tools/lib/bpf/relo_core.c1
-rw-r--r--tools/lib/bpf/ringbuf.c1
-rw-r--r--tools/lib/bpf/skel_internal.h76
-rw-r--r--tools/lib/bpf/str_error.c104
-rw-r--r--tools/lib/bpf/str_error.h19
-rw-r--r--tools/lib/bpf/usdt.bpf.h44
-rw-r--r--tools/lib/bpf/usdt.c83
26 files changed, 889 insertions, 269 deletions
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index e2cd558ca0b4..c80204bb72a2 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,4 +1,4 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_utils.o \
netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \
btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \
usdt.o zip.o elf.o features.o btf_iter.o btf_relocate.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a9c3e33d0f8a..339b19797237 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -172,7 +172,7 @@ int bpf_map_create(enum bpf_map_type map_type,
__u32 max_entries,
const struct bpf_map_create_opts *opts)
{
- const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd);
+ const size_t attr_sz = offsetofend(union bpf_attr, excl_prog_hash_size);
union bpf_attr attr;
int fd;
@@ -203,6 +203,8 @@ int bpf_map_create(enum bpf_map_type map_type,
attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
attr.map_token_fd = OPTS_GET(opts, token_fd, 0);
+ attr.excl_prog_hash = ptr_to_u64(OPTS_GET(opts, excl_prog_hash, NULL));
+ attr.excl_prog_hash_size = OPTS_GET(opts, excl_prog_hash_size, 0);
fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
return libbpf_err_errno(fd);
@@ -238,7 +240,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, size_t insn_cnt,
struct bpf_prog_load_opts *opts)
{
- const size_t attr_sz = offsetofend(union bpf_attr, fd_array_cnt);
+ const size_t attr_sz = offsetofend(union bpf_attr, keyring_id);
void *finfo = NULL, *linfo = NULL;
const char *func_info, *line_info;
__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -837,6 +839,50 @@ int bpf_link_create(int prog_fd, int target_fd,
if (!OPTS_ZEROED(opts, netkit))
return libbpf_err(-EINVAL);
break;
+ case BPF_CGROUP_INET_INGRESS:
+ case BPF_CGROUP_INET_EGRESS:
+ case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_INET_SOCK_RELEASE:
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ case BPF_CGROUP_INET4_POST_BIND:
+ case BPF_CGROUP_INET6_POST_BIND:
+ case BPF_CGROUP_INET4_CONNECT:
+ case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
+ case BPF_CGROUP_INET4_GETPEERNAME:
+ case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
+ case BPF_CGROUP_INET4_GETSOCKNAME:
+ case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
+ case BPF_CGROUP_UDP4_SENDMSG:
+ case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
+ case BPF_CGROUP_UDP4_RECVMSG:
+ case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
+ case BPF_CGROUP_SOCK_OPS:
+ case BPF_CGROUP_DEVICE:
+ case BPF_CGROUP_SYSCTL:
+ case BPF_CGROUP_GETSOCKOPT:
+ case BPF_CGROUP_SETSOCKOPT:
+ case BPF_LSM_CGROUP:
+ relative_fd = OPTS_GET(opts, cgroup.relative_fd, 0);
+ relative_id = OPTS_GET(opts, cgroup.relative_id, 0);
+ if (relative_fd && relative_id)
+ return libbpf_err(-EINVAL);
+ if (relative_id) {
+ attr.link_create.cgroup.relative_id = relative_id;
+ attr.link_create.flags |= BPF_F_ID;
+ } else {
+ attr.link_create.cgroup.relative_fd = relative_fd;
+ }
+ attr.link_create.cgroup.expected_revision =
+ OPTS_GET(opts, cgroup.expected_revision, 0);
+ if (!OPTS_ZEROED(opts, cgroup))
+ return libbpf_err(-EINVAL);
+ break;
default:
if (!OPTS_ZEROED(opts, flags))
return libbpf_err(-EINVAL);
@@ -1331,3 +1377,23 @@ int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts)
fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz);
return libbpf_err_errno(fd);
}
+
+int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len,
+ struct bpf_prog_stream_read_opts *opts)
+{
+ const size_t attr_sz = offsetofend(union bpf_attr, prog_stream_read);
+ union bpf_attr attr;
+ int err;
+
+ if (!OPTS_VALID(opts, bpf_prog_stream_read_opts))
+ return libbpf_err(-EINVAL);
+
+ memset(&attr, 0, attr_sz);
+ attr.prog_stream_read.stream_buf = ptr_to_u64(buf);
+ attr.prog_stream_read.stream_buf_len = buf_len;
+ attr.prog_stream_read.stream_id = stream_id;
+ attr.prog_stream_read.prog_fd = prog_fd;
+
+ err = sys_bpf(BPF_PROG_STREAM_READ_BY_FD, &attr, attr_sz);
+ return libbpf_err_errno(err);
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 777627d33d25..e983a3e40d61 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -54,9 +54,12 @@ struct bpf_map_create_opts {
__s32 value_type_btf_obj_fd;
__u32 token_fd;
+
+ const void *excl_prog_hash;
+ __u32 excl_prog_hash_size;
size_t :0;
};
-#define bpf_map_create_opts__last_field token_fd
+#define bpf_map_create_opts__last_field excl_prog_hash_size
LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
const char *map_name,
@@ -438,6 +441,11 @@ struct bpf_link_create_opts {
__u32 relative_id;
__u64 expected_revision;
} netkit;
+ struct {
+ __u32 relative_fd;
+ __u32 relative_id;
+ __u64 expected_revision;
+ } cgroup;
};
size_t :0;
};
@@ -704,6 +712,27 @@ struct bpf_token_create_opts {
LIBBPF_API int bpf_token_create(int bpffs_fd,
struct bpf_token_create_opts *opts);
+struct bpf_prog_stream_read_opts {
+ size_t sz;
+ size_t :0;
+};
+#define bpf_prog_stream_read_opts__last_field sz
+/**
+ * @brief **bpf_prog_stream_read** reads data from the BPF stream of a given BPF
+ * program.
+ *
+ * @param prog_fd FD for the BPF program whose BPF stream is to be read.
+ * @param stream_id ID of the BPF stream to be read.
+ * @param buf Buffer to read data into from the BPF stream.
+ * @param buf_len Maximum number of bytes to read from the BPF stream.
+ * @param opts optional options, can be NULL
+ *
+ * @return The number of bytes read, on success; negative error code, otherwise
+ * (errno is also set to the error code)
+ */
+LIBBPF_API int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len,
+ struct bpf_prog_stream_read_opts *opts);
+
#ifdef __cplusplus
} /* extern "C" */
#endif
diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index 6ff963a491d9..49af4260b8e6 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -4,6 +4,7 @@
#define __BPF_GEN_INTERNAL_H
#include "bpf.h"
+#include "libbpf_internal.h"
struct ksym_relo_desc {
const char *name;
@@ -50,6 +51,7 @@ struct bpf_gen {
__u32 nr_ksyms;
int fd_array;
int nr_fd_array;
+ int hash_insn_offset[SHA256_DWORD_SIZE];
};
void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index a50773d4616e..80c028540656 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -215,6 +215,7 @@ enum libbpf_tristate {
#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull")))
#define __arg_nullable __attribute((btf_decl_tag("arg:nullable")))
#define __arg_trusted __attribute((btf_decl_tag("arg:trusted")))
+#define __arg_untrusted __attribute((btf_decl_tag("arg:untrusted")))
#define __arg_arena __attribute((btf_decl_tag("arg:arena")))
#ifndef ___bpf_concat
@@ -314,6 +315,22 @@ enum libbpf_tristate {
___param, sizeof(___param)); \
})
+extern int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args,
+ __u32 len__sz, void *aux__prog) __weak __ksym;
+
+#define bpf_stream_printk(stream_id, fmt, args...) \
+({ \
+ static const char ___fmt[] = fmt; \
+ unsigned long long ___param[___bpf_narg(args)]; \
+ \
+ _Pragma("GCC diagnostic push") \
+ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
+ ___bpf_fill(___param, args); \
+ _Pragma("GCC diagnostic pop") \
+ \
+ bpf_stream_vprintk(stream_id, ___fmt, ___param, sizeof(___param), NULL);\
+})
+
/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args
* Otherwise use __bpf_vprintk
*/
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 37682908cb0f..18907f0fcf9f 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -23,7 +23,6 @@
#include "libbpf_internal.h"
#include "hashmap.h"
#include "strset.h"
-#include "str_error.h"
#define BTF_MAX_NR_TYPES 0x7fffffffU
#define BTF_MAX_STR_OFFSET 0x7fffffffU
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4392451d634b..ccfd905f03df 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -326,9 +326,10 @@ struct btf_dump_type_data_opts {
bool compact; /* no newlines/indentation */
bool skip_names; /* skip member/type names */
bool emit_zeroes; /* show 0-valued fields */
+ bool emit_strings; /* print char arrays as strings */
size_t :0;
};
-#define btf_dump_type_data_opts__last_field emit_zeroes
+#define btf_dump_type_data_opts__last_field emit_strings
LIBBPF_API int
btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 0381f209920a..6388392f49a0 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -21,7 +21,6 @@
#include "hashmap.h"
#include "libbpf.h"
#include "libbpf_internal.h"
-#include "str_error.h"
static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
@@ -68,6 +67,7 @@ struct btf_dump_data {
bool compact;
bool skip_names;
bool emit_zeroes;
+ bool emit_strings;
__u8 indent_lvl; /* base indent level */
char indent_str[BTF_DATA_INDENT_STR_LEN];
/* below are used during iteration */
@@ -2031,6 +2031,52 @@ static int btf_dump_var_data(struct btf_dump *d,
return btf_dump_dump_type_data(d, NULL, t, type_id, data, 0, 0);
}
+static int btf_dump_string_data(struct btf_dump *d,
+ const struct btf_type *t,
+ __u32 id,
+ const void *data)
+{
+ const struct btf_array *array = btf_array(t);
+ const char *chars = data;
+ __u32 i;
+
+ /* Make sure it is a NUL-terminated string. */
+ for (i = 0; i < array->nelems; i++) {
+ if ((void *)(chars + i) >= d->typed_dump->data_end)
+ return -E2BIG;
+ if (chars[i] == '\0')
+ break;
+ }
+ if (i == array->nelems) {
+ /* The caller will print this as a regular array. */
+ return -EINVAL;
+ }
+
+ btf_dump_data_pfx(d);
+ btf_dump_printf(d, "\"");
+
+ for (i = 0; i < array->nelems; i++) {
+ char c = chars[i];
+
+ if (c == '\0') {
+ /*
+ * When printing character arrays as strings, NUL bytes
+ * are always treated as string terminators; they are
+ * never printed.
+ */
+ break;
+ }
+ if (isprint(c))
+ btf_dump_printf(d, "%c", c);
+ else
+ btf_dump_printf(d, "\\x%02x", (__u8)c);
+ }
+
+ btf_dump_printf(d, "\"");
+
+ return 0;
+}
+
static int btf_dump_array_data(struct btf_dump *d,
const struct btf_type *t,
__u32 id,
@@ -2058,8 +2104,13 @@ static int btf_dump_array_data(struct btf_dump *d,
* char arrays, so if size is 1 and element is
* printable as a char, we'll do that.
*/
- if (elem_size == 1)
+ if (elem_size == 1) {
+ if (d->typed_dump->emit_strings &&
+ btf_dump_string_data(d, t, id, data) == 0) {
+ return 0;
+ }
d->typed_dump->is_array_char = true;
+ }
}
/* note that we increment depth before calling btf_dump_print() below;
@@ -2547,6 +2598,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
d->typed_dump->compact = OPTS_GET(opts, compact, false);
d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false);
d->typed_dump->emit_zeroes = OPTS_GET(opts, emit_zeroes, false);
+ d->typed_dump->emit_strings = OPTS_GET(opts, emit_strings, false);
ret = btf_dump_dump_type_data(d, NULL, t, id, data, 0, 0);
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 823f83ad819c..295dbda24580 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -9,7 +9,6 @@
#include <linux/kernel.h>
#include "libbpf_internal.h"
-#include "str_error.h"
/* A SHT_GNU_versym section holds 16-bit words. This bit is set if
* the symbol is hidden and can only be seen when referenced using an
diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index 760657f5224c..b842b83e2480 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -6,7 +6,6 @@
#include "libbpf.h"
#include "libbpf_common.h"
#include "libbpf_internal.h"
-#include "str_error.h"
static inline __u64 ptr_to_u64(const void *ptr)
{
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 113ae4abd345..cd5c2543f54d 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -4,6 +4,7 @@
#include <stdlib.h>
#include <string.h>
#include <errno.h>
+#include <asm/byteorder.h>
#include <linux/filter.h>
#include <sys/param.h>
#include "btf.h"
@@ -13,8 +14,6 @@
#include "hashmap.h"
#include "bpf_gen_internal.h"
#include "skel_internal.h"
-#include <asm/byteorder.h>
-#include "str_error.h"
#define MAX_USED_MAPS 64
#define MAX_USED_PROGS 32
@@ -110,6 +109,7 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in
static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
+static void emit_signature_match(struct bpf_gen *gen);
void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
{
@@ -152,6 +152,8 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps
/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
emit(gen, BPF_EXIT_INSN());
+ if (OPTS_GET(gen->opts, gen_hash, false))
+ emit_signature_match(gen);
}
static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
@@ -368,6 +370,8 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
__emit_sys_close(gen);
}
+static void compute_sha_update_offsets(struct bpf_gen *gen);
+
int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
{
int i;
@@ -394,6 +398,9 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
blob_fd_array_off(gen, i));
emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
emit(gen, BPF_EXIT_INSN());
+ if (OPTS_GET(gen->opts, gen_hash, false))
+ compute_sha_update_offsets(gen);
+
pr_debug("gen: finish %s\n", errstr(gen->error));
if (!gen->error) {
struct gen_loader_opts *opts = gen->opts;
@@ -446,6 +453,22 @@ void bpf_gen__free(struct bpf_gen *gen)
_val; \
})
+static void compute_sha_update_offsets(struct bpf_gen *gen)
+{
+ __u64 sha[SHA256_DWORD_SIZE];
+ __u64 sha_dw;
+ int i;
+
+ libbpf_sha256(gen->data_start, gen->data_cur - gen->data_start, (__u8 *)sha);
+ for (i = 0; i < SHA256_DWORD_SIZE; i++) {
+ struct bpf_insn *insn =
+ (struct bpf_insn *)(gen->insn_start + gen->hash_insn_offset[i]);
+ sha_dw = tgt_endian(sha[i]);
+ insn[0].imm = (__u32)sha_dw;
+ insn[1].imm = sha_dw >> 32;
+ }
+}
+
void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
__u32 btf_raw_size)
{
@@ -557,6 +580,29 @@ void bpf_gen__map_create(struct bpf_gen *gen,
emit_sys_close_stack(gen, stack_off(inner_map_fd));
}
+static void emit_signature_match(struct bpf_gen *gen)
+{
+ __s64 off;
+ int i;
+
+ for (i = 0; i < SHA256_DWORD_SIZE; i++) {
+ emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX,
+ 0, 0, 0, 0));
+ emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, i * sizeof(__u64)));
+ gen->hash_insn_offset[i] = gen->insn_cur - gen->insn_start;
+ emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_3, 0, 0, 0, 0, 0));
+
+ off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1;
+ if (is_simm16(off)) {
+ emit(gen, BPF_MOV64_IMM(BPF_REG_7, -EINVAL));
+ emit(gen, BPF_JMP_REG(BPF_JNE, BPF_REG_2, BPF_REG_3, off));
+ } else {
+ gen->error = -ERANGE;
+ emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1));
+ }
+ }
+}
+
void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name,
enum bpf_attach_type type)
{
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d41ee26b9443..dd3b2f57082d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -50,7 +50,6 @@
#include "libbpf.h"
#include "bpf.h"
#include "btf.h"
-#include "str_error.h"
#include "libbpf_internal.h"
#include "hashmap.h"
#include "bpf_gen_internal.h"
@@ -318,8 +317,6 @@ static void pr_perm_msg(int err)
buf);
}
-#define STRERR_BUFSIZE 128
-
/* Copied from tools/perf/util/util.h */
#ifndef zfree
# define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
@@ -496,6 +493,7 @@ struct bpf_program {
__u32 line_info_rec_size;
__u32 line_info_cnt;
__u32 prog_flags;
+ __u8 hash[SHA256_DIGEST_LENGTH];
};
struct bpf_struct_ops {
@@ -575,6 +573,7 @@ struct bpf_map {
bool autocreate;
bool autoattach;
__u64 map_extra;
+ struct bpf_program *excl_prog;
};
enum extern_type {
@@ -1013,35 +1012,33 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw,
const struct btf_member *kern_data_member;
struct btf *btf = NULL;
__s32 kern_vtype_id, kern_type_id;
- char tname[256];
+ char tname[192], stname[256];
__u32 i;
snprintf(tname, sizeof(tname), "%.*s",
(int)bpf_core_essential_name_len(tname_raw), tname_raw);
- kern_type_id = find_ksym_btf_id(obj, tname, BTF_KIND_STRUCT,
- &btf, mod_btf);
- if (kern_type_id < 0) {
- pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n",
- tname);
- return kern_type_id;
- }
- kern_type = btf__type_by_id(btf, kern_type_id);
+ snprintf(stname, sizeof(stname), "%s%s", STRUCT_OPS_VALUE_PREFIX, tname);
- /* Find the corresponding "map_value" type that will be used
- * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example,
- * find "struct bpf_struct_ops_tcp_congestion_ops" from the
- * btf_vmlinux.
+ /* Look for the corresponding "map_value" type that will be used
+ * in map_update(BPF_MAP_TYPE_STRUCT_OPS) first, figure out the btf
+ * and the mod_btf.
+ * For example, find "struct bpf_struct_ops_tcp_congestion_ops".
*/
- kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX,
- tname, BTF_KIND_STRUCT);
+ kern_vtype_id = find_ksym_btf_id(obj, stname, BTF_KIND_STRUCT, &btf, mod_btf);
if (kern_vtype_id < 0) {
- pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n",
- STRUCT_OPS_VALUE_PREFIX, tname);
+ pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", stname);
return kern_vtype_id;
}
kern_vtype = btf__type_by_id(btf, kern_vtype_id);
+ kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+ if (kern_type_id < 0) {
+ pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", tname);
+ return kern_type_id;
+ }
+ kern_type = btf__type_by_id(btf, kern_type_id);
+
/* Find "struct tcp_congestion_ops" from
* struct bpf_struct_ops_tcp_congestion_ops {
* [ ... ]
@@ -1054,8 +1051,8 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw,
break;
}
if (i == btf_vlen(kern_vtype)) {
- pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n",
- tname, STRUCT_OPS_VALUE_PREFIX, tname);
+ pr_warn("struct_ops init_kern: struct %s data is not found in struct %s\n",
+ tname, stname);
return -EINVAL;
}
@@ -4485,6 +4482,44 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
}
}
+static int bpf_prog_compute_hash(struct bpf_program *prog)
+{
+ struct bpf_insn *purged;
+ int i, err = 0;
+
+ purged = calloc(prog->insns_cnt, BPF_INSN_SZ);
+ if (!purged)
+ return -ENOMEM;
+
+ /* If relocations have been done, the map_fd needs to be
+ * discarded for the digest calculation.
+ */
+ for (i = 0; i < prog->insns_cnt; i++) {
+ purged[i] = prog->insns[i];
+ if (purged[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
+ (purged[i].src_reg == BPF_PSEUDO_MAP_FD ||
+ purged[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
+ purged[i].imm = 0;
+ i++;
+ if (i >= prog->insns_cnt ||
+ prog->insns[i].code != 0 ||
+ prog->insns[i].dst_reg != 0 ||
+ prog->insns[i].src_reg != 0 ||
+ prog->insns[i].off != 0) {
+ err = -EINVAL;
+ goto out;
+ }
+ purged[i] = prog->insns[i];
+ purged[i].imm = 0;
+ }
+ }
+ libbpf_sha256(purged, prog->insns_cnt * sizeof(struct bpf_insn),
+ prog->hash);
+out:
+ free(purged);
+ return err;
+}
+
static int bpf_program__record_reloc(struct bpf_program *prog,
struct reloc_desc *reloc_desc,
__u32 insn_idx, const char *sym_name,
@@ -4582,6 +4617,11 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
/* arena data relocation */
if (shdr_idx == obj->efile.arena_data_shndx) {
+ if (obj->arena_map_idx < 0) {
+ pr_warn("prog '%s': bad arena data relocation at insn %u, no arena maps defined\n",
+ prog->name, insn_idx);
+ return -LIBBPF_ERRNO__RELOC;
+ }
reloc_desc->type = RELO_DATA;
reloc_desc->insn_idx = insn_idx;
reloc_desc->map_idx = obj->arena_map_idx;
@@ -5088,6 +5128,16 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
return false;
}
+ /*
+ * bpf_get_map_info_by_fd() for DEVMAP will always return flags with
+ * BPF_F_RDONLY_PROG set, but it generally is not set at map creation time.
+ * Thus, ignore the BPF_F_RDONLY_PROG flag in the flags returned from
+ * bpf_get_map_info_by_fd() when checking for compatibility with an
+ * existing DEVMAP.
+ */
+ if (map->def.type == BPF_MAP_TYPE_DEVMAP || map->def.type == BPF_MAP_TYPE_DEVMAP_HASH)
+ map_info.map_flags &= ~BPF_F_RDONLY_PROG;
+
return (map_info.type == map->def.type &&
map_info.key_size == map->def.key_size &&
map_info.value_size == map->def.value_size &&
@@ -5219,6 +5269,14 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
create_attr.token_fd = obj->token_fd;
if (obj->token_fd)
create_attr.map_flags |= BPF_F_TOKEN_FD;
+ if (map->excl_prog) {
+ err = bpf_prog_compute_hash(map->excl_prog);
+ if (err)
+ return err;
+
+ create_attr.excl_prog_hash = map->excl_prog->hash;
+ create_attr.excl_prog_hash_size = SHA256_DIGEST_LENGTH;
+ }
if (bpf_map__is_struct_ops(map)) {
create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
@@ -9216,7 +9274,7 @@ int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts)
return libbpf_err(-EFAULT);
if (!OPTS_VALID(opts, gen_loader_opts))
return libbpf_err(-EINVAL);
- gen = calloc(sizeof(*gen), 1);
+ gen = calloc(1, sizeof(*gen));
if (!gen)
return libbpf_err(-ENOMEM);
gen->opts = opts;
@@ -10091,7 +10149,7 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name,
enum bpf_attach_type attach_type,
int *btf_obj_fd, int *btf_type_id)
{
- int ret, i, mod_len;
+ int ret, i, mod_len = 0;
const char *fn_name, *mod_name = NULL;
fn_name = strchr(attach_name, ':');
@@ -10509,6 +10567,27 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
return 0;
}
+int bpf_map__set_exclusive_program(struct bpf_map *map, struct bpf_program *prog)
+{
+ if (map_is_created(map)) {
+ pr_warn("exclusive programs must be set before map creation\n");
+ return libbpf_err(-EINVAL);
+ }
+
+ if (map->obj != prog->obj) {
+ pr_warn("excl_prog and map must be from the same bpf object\n");
+ return libbpf_err(-EINVAL);
+ }
+
+ map->excl_prog = prog;
+ return 0;
+}
+
+struct bpf_program *bpf_map__exclusive_program(struct bpf_map *map)
+{
+ return map->excl_prog;
+}
+
static struct bpf_map *
__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
{
@@ -10960,11 +11039,14 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p
}
link->link.fd = pfd;
}
- if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
- err = -errno;
- pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n",
- prog->name, pfd, errstr(err));
- goto err_out;
+
+ if (!OPTS_GET(opts, dont_enable, false)) {
+ if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ err = -errno;
+ pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n",
+ prog->name, pfd, errstr(err));
+ goto err_out;
+ }
}
return &link->link;
@@ -12848,6 +12930,34 @@ struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifi
}
struct bpf_link *
+bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd,
+ const struct bpf_cgroup_opts *opts)
+{
+ LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
+ __u32 relative_id;
+ int relative_fd;
+
+ if (!OPTS_VALID(opts, bpf_cgroup_opts))
+ return libbpf_err_ptr(-EINVAL);
+
+ relative_id = OPTS_GET(opts, relative_id, 0);
+ relative_fd = OPTS_GET(opts, relative_fd, 0);
+
+ if (relative_fd && relative_id) {
+ pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n",
+ prog->name);
+ return libbpf_err_ptr(-EINVAL);
+ }
+
+ link_create_opts.cgroup.expected_revision = OPTS_GET(opts, expected_revision, 0);
+ link_create_opts.cgroup.relative_fd = relative_fd;
+ link_create_opts.cgroup.relative_id = relative_id;
+ link_create_opts.flags = OPTS_GET(opts, flags, 0);
+
+ return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", &link_create_opts);
+}
+
+struct bpf_link *
bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
const struct bpf_tcx_opts *opts)
{
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1137e7d2e1b5..5118d0a90e24 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -24,8 +24,25 @@
extern "C" {
#endif
+/**
+ * @brief **libbpf_major_version()** provides the major version of libbpf.
+ * @return An integer, the major version number
+ */
LIBBPF_API __u32 libbpf_major_version(void);
+
+/**
+ * @brief **libbpf_minor_version()** provides the minor version of libbpf.
+ * @return An integer, the minor version number
+ */
LIBBPF_API __u32 libbpf_minor_version(void);
+
+/**
+ * @brief **libbpf_version_string()** provides the version of libbpf in a
+ * human-readable form, e.g., "v1.7".
+ * @return Pointer to a static string containing the version
+ *
+ * The format is *not* a part of a stable API and may change in the future.
+ */
LIBBPF_API const char *libbpf_version_string(void);
enum libbpf_errno {
@@ -49,6 +66,14 @@ enum libbpf_errno {
__LIBBPF_ERRNO__END,
};
+/**
+ * @brief **libbpf_strerror()** converts the provided error code into a
+ * human-readable string.
+ * @param err The error code to convert
+ * @param buf Pointer to a buffer where the error message will be stored
+ * @param size The number of bytes in the buffer
+ * @return 0, on success; negative error code, otherwise
+ */
LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size);
/**
@@ -252,7 +277,7 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
* @return 0, on success; negative error code, otherwise, error code is
* stored in errno
*/
-int bpf_object__prepare(struct bpf_object *obj);
+LIBBPF_API int bpf_object__prepare(struct bpf_object *obj);
/**
* @brief **bpf_object__load()** loads BPF object into kernel.
@@ -499,9 +524,11 @@ struct bpf_perf_event_opts {
__u64 bpf_cookie;
/* don't use BPF link when attach BPF program */
bool force_ioctl_attach;
+ /* don't automatically enable the event */
+ bool dont_enable;
size_t :0;
};
-#define bpf_perf_event_opts__last_field force_ioctl_attach
+#define bpf_perf_event_opts__last_field dont_enable
LIBBPF_API struct bpf_link *
bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd);
@@ -877,6 +904,21 @@ LIBBPF_API struct bpf_link *
bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
const struct bpf_netkit_opts *opts);
+struct bpf_cgroup_opts {
+ /* size of this struct, for forward/backward compatibility */
+ size_t sz;
+ __u32 flags;
+ __u32 relative_fd;
+ __u32 relative_id;
+ __u64 expected_revision;
+ size_t :0;
+};
+#define bpf_cgroup_opts__last_field expected_revision
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd,
+ const struct bpf_cgroup_opts *opts);
+
struct bpf_map;
LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
@@ -1249,6 +1291,28 @@ LIBBPF_API int bpf_map__lookup_and_delete_elem(const struct bpf_map *map,
*/
LIBBPF_API int bpf_map__get_next_key(const struct bpf_map *map,
const void *cur_key, void *next_key, size_t key_sz);
+/**
+ * @brief **bpf_map__set_exclusive_program()** sets a map to be exclusive to the
+ * specified program. This must be called *before* the map is created.
+ *
+ * @param map BPF map to make exclusive.
+ * @param prog BPF program to be the exclusive user of the map. Must belong
+ * to the same bpf_object as the map.
+ * @return 0 on success; a negative error code otherwise.
+ *
+ * This function must be called after the BPF object is opened but before
+ * it is loaded. Once the object is loaded, only the specified program
+ * will be able to access the map's contents.
+ */
+LIBBPF_API int bpf_map__set_exclusive_program(struct bpf_map *map, struct bpf_program *prog);
+
+/**
+ * @brief **bpf_map__exclusive_program()** returns the exclusive program
+ * that is registered with the map (if any).
+ * @param map BPF map to which the exclusive program is registered.
+ * @return the registered exclusive program.
+ */
+LIBBPF_API struct bpf_program *bpf_map__exclusive_program(struct bpf_map *map);
struct bpf_xdp_set_link_opts {
size_t sz;
@@ -1793,9 +1857,10 @@ struct gen_loader_opts {
const char *insns;
__u32 data_sz;
__u32 insns_sz;
+ bool gen_hash;
};
-#define gen_loader_opts__last_field insns_sz
+#define gen_loader_opts__last_field gen_hash
LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj,
struct gen_loader_opts *opts);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 1205f9a4fe04..8ed8749907d4 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -437,6 +437,8 @@ LIBBPF_1.6.0 {
bpf_linker__add_fd;
bpf_linker__new_fd;
bpf_object__prepare;
+ bpf_prog_stream_read;
+ bpf_program__attach_cgroup_opts;
bpf_program__func_info;
bpf_program__func_info_cnt;
bpf_program__line_info;
@@ -444,3 +446,9 @@ LIBBPF_1.6.0 {
btf__add_decl_attr;
btf__add_type_attr;
} LIBBPF_1.5.0;
+
+LIBBPF_1.7.0 {
+ global:
+ bpf_map__set_exclusive_program;
+ bpf_map__exclusive_program;
+} LIBBPF_1.6.0;
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
deleted file mode 100644
index 6b180172ec6b..000000000000
--- a/tools/lib/bpf/libbpf_errno.c
+++ /dev/null
@@ -1,75 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-
-/*
- * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
- * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015 Huawei Inc.
- * Copyright (C) 2017 Nicira, Inc.
- */
-
-#undef _GNU_SOURCE
-#include <stdio.h>
-#include <string.h>
-
-#include "libbpf.h"
-#include "libbpf_internal.h"
-
-/* make sure libbpf doesn't use kernel-only integer typedefs */
-#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
-
-#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
-#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
-#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
-
-static const char *libbpf_strerror_table[NR_ERRNO] = {
- [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf",
- [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid",
- [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost",
- [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch",
- [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf",
- [ERRCODE_OFFSET(RELOC)] = "Relocation failed",
- [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading",
- [ERRCODE_OFFSET(PROG2BIG)] = "Program too big",
- [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version",
- [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type",
- [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message",
- [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence",
- [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing",
-};
-
-int libbpf_strerror(int err, char *buf, size_t size)
-{
- int ret;
-
- if (!buf || !size)
- return libbpf_err(-EINVAL);
-
- err = err > 0 ? err : -err;
-
- if (err < __LIBBPF_ERRNO__START) {
- ret = strerror_r(err, buf, size);
- buf[size - 1] = '\0';
- return libbpf_err_errno(ret);
- }
-
- if (err < __LIBBPF_ERRNO__END) {
- const char *msg;
-
- msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
- ret = snprintf(buf, size, "%s", msg);
- buf[size - 1] = '\0';
- /* The length of the buf and msg is positive.
- * A negative number may be returned only when the
- * size exceeds INT_MAX. Not likely to appear.
- */
- if (ret >= size)
- return libbpf_err(-ERANGE);
- return 0;
- }
-
- ret = snprintf(buf, size, "Unknown libbpf error %d", err);
- buf[size - 1] = '\0';
- if (ret >= size)
- return libbpf_err(-ERANGE);
- return libbpf_err(-ENOENT);
-}
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 477a3b3389a0..35b2527bedec 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -172,6 +172,16 @@ do { \
#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
+/**
+ * @brief **libbpf_errstr()** returns string corresponding to numeric errno
+ * @param err negative numeric errno
+ * @return pointer to string representation of the errno, that is invalidated
+ * upon the next call.
+ */
+const char *libbpf_errstr(int err);
+
+#define errstr(err) libbpf_errstr(err)
+
#ifndef __has_builtin
#define __has_builtin(x) 0
#endif
@@ -712,6 +722,11 @@ static inline bool is_pow_of_2(size_t x)
return x && (x & (x - 1)) == 0;
}
+static inline __u32 ror32(__u32 v, int bits)
+{
+ return (v >> bits) | (v << (32 - bits));
+}
+
#define PROG_LOAD_ATTEMPTS 5
int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
@@ -736,4 +751,8 @@ int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
int probe_fd(int fd);
+#define SHA256_DIGEST_LENGTH 32
+#define SHA256_DWORD_SIZE SHA256_DIGEST_LENGTH / sizeof(__u64)
+
+void libbpf_sha256(const void *data, size_t len, __u8 out[SHA256_DIGEST_LENGTH]);
#endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/libbpf_utils.c b/tools/lib/bpf/libbpf_utils.c
new file mode 100644
index 000000000000..5d66bc6ff098
--- /dev/null
+++ b/tools/lib/bpf/libbpf_utils.c
@@ -0,0 +1,252 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
+ */
+
+#undef _GNU_SOURCE
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
+
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+ [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf",
+ [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid",
+ [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost",
+ [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch",
+ [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf",
+ [ERRCODE_OFFSET(RELOC)] = "Relocation failed",
+ [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading",
+ [ERRCODE_OFFSET(PROG2BIG)] = "Program too big",
+ [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version",
+ [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type",
+ [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message",
+ [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence",
+ [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+ int ret;
+
+ if (!buf || !size)
+ return libbpf_err(-EINVAL);
+
+ err = err > 0 ? err : -err;
+
+ if (err < __LIBBPF_ERRNO__START) {
+ ret = strerror_r(err, buf, size);
+ buf[size - 1] = '\0';
+ return libbpf_err_errno(ret);
+ }
+
+ if (err < __LIBBPF_ERRNO__END) {
+ const char *msg;
+
+ msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+ ret = snprintf(buf, size, "%s", msg);
+ buf[size - 1] = '\0';
+ /* The length of the buf and msg is positive.
+ * A negative number may be returned only when the
+ * size exceeds INT_MAX. Not likely to appear.
+ */
+ if (ret >= size)
+ return libbpf_err(-ERANGE);
+ return 0;
+ }
+
+ ret = snprintf(buf, size, "Unknown libbpf error %d", err);
+ buf[size - 1] = '\0';
+ if (ret >= size)
+ return libbpf_err(-ERANGE);
+ return libbpf_err(-ENOENT);
+}
+
+const char *libbpf_errstr(int err)
+{
+ static __thread char buf[12];
+
+ if (err > 0)
+ err = -err;
+
+ switch (err) {
+ case -E2BIG: return "-E2BIG";
+ case -EACCES: return "-EACCES";
+ case -EADDRINUSE: return "-EADDRINUSE";
+ case -EADDRNOTAVAIL: return "-EADDRNOTAVAIL";
+ case -EAGAIN: return "-EAGAIN";
+ case -EALREADY: return "-EALREADY";
+ case -EBADF: return "-EBADF";
+ case -EBADFD: return "-EBADFD";
+ case -EBUSY: return "-EBUSY";
+ case -ECANCELED: return "-ECANCELED";
+ case -ECHILD: return "-ECHILD";
+ case -EDEADLK: return "-EDEADLK";
+ case -EDOM: return "-EDOM";
+ case -EEXIST: return "-EEXIST";
+ case -EFAULT: return "-EFAULT";
+ case -EFBIG: return "-EFBIG";
+ case -EILSEQ: return "-EILSEQ";
+ case -EINPROGRESS: return "-EINPROGRESS";
+ case -EINTR: return "-EINTR";
+ case -EINVAL: return "-EINVAL";
+ case -EIO: return "-EIO";
+ case -EISDIR: return "-EISDIR";
+ case -ELOOP: return "-ELOOP";
+ case -EMFILE: return "-EMFILE";
+ case -EMLINK: return "-EMLINK";
+ case -EMSGSIZE: return "-EMSGSIZE";
+ case -ENAMETOOLONG: return "-ENAMETOOLONG";
+ case -ENFILE: return "-ENFILE";
+ case -ENODATA: return "-ENODATA";
+ case -ENODEV: return "-ENODEV";
+ case -ENOENT: return "-ENOENT";
+ case -ENOEXEC: return "-ENOEXEC";
+ case -ENOLINK: return "-ENOLINK";
+ case -ENOMEM: return "-ENOMEM";
+ case -ENOSPC: return "-ENOSPC";
+ case -ENOTBLK: return "-ENOTBLK";
+ case -ENOTDIR: return "-ENOTDIR";
+ case -ENOTSUPP: return "-ENOTSUPP";
+ case -ENOTTY: return "-ENOTTY";
+ case -ENXIO: return "-ENXIO";
+ case -EOPNOTSUPP: return "-EOPNOTSUPP";
+ case -EOVERFLOW: return "-EOVERFLOW";
+ case -EPERM: return "-EPERM";
+ case -EPIPE: return "-EPIPE";
+ case -EPROTO: return "-EPROTO";
+ case -EPROTONOSUPPORT: return "-EPROTONOSUPPORT";
+ case -ERANGE: return "-ERANGE";
+ case -EROFS: return "-EROFS";
+ case -ESPIPE: return "-ESPIPE";
+ case -ESRCH: return "-ESRCH";
+ case -ETXTBSY: return "-ETXTBSY";
+ case -EUCLEAN: return "-EUCLEAN";
+ case -EXDEV: return "-EXDEV";
+ default:
+ snprintf(buf, sizeof(buf), "%d", err);
+ return buf;
+ }
+}
+
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
+struct __packed_u32 { __u32 __val; } __attribute__((packed));
+#pragma GCC diagnostic pop
+
+#define get_unaligned_be32(p) be32_to_cpu((((struct __packed_u32 *)(p))->__val))
+#define put_unaligned_be32(v, p) do { \
+ ((struct __packed_u32 *)(p))->__val = cpu_to_be32(v); \
+} while (0)
+
+#define SHA256_BLOCK_LENGTH 64
+#define Ch(x, y, z) (((x) & (y)) ^ (~(x) & (z)))
+#define Maj(x, y, z) (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))
+#define Sigma_0(x) (ror32((x), 2) ^ ror32((x), 13) ^ ror32((x), 22))
+#define Sigma_1(x) (ror32((x), 6) ^ ror32((x), 11) ^ ror32((x), 25))
+#define sigma_0(x) (ror32((x), 7) ^ ror32((x), 18) ^ ((x) >> 3))
+#define sigma_1(x) (ror32((x), 17) ^ ror32((x), 19) ^ ((x) >> 10))
+
+static const __u32 sha256_K[64] = {
+ 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1,
+ 0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
+ 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174, 0xe49b69c1, 0xefbe4786,
+ 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+ 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147,
+ 0x06ca6351, 0x14292967, 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
+ 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85, 0xa2bfe8a1, 0xa81a664b,
+ 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+ 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a,
+ 0x5b9cca4f, 0x682e6ff3, 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
+ 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2,
+};
+
+#define SHA256_ROUND(i, a, b, c, d, e, f, g, h) \
+ { \
+ __u32 tmp = h + Sigma_1(e) + Ch(e, f, g) + sha256_K[i] + w[i]; \
+ d += tmp; \
+ h = tmp + Sigma_0(a) + Maj(a, b, c); \
+ }
+
+static void sha256_blocks(__u32 state[8], const __u8 *data, size_t nblocks)
+{
+ while (nblocks--) {
+ __u32 a = state[0];
+ __u32 b = state[1];
+ __u32 c = state[2];
+ __u32 d = state[3];
+ __u32 e = state[4];
+ __u32 f = state[5];
+ __u32 g = state[6];
+ __u32 h = state[7];
+ __u32 w[64];
+ int i;
+
+ for (i = 0; i < 16; i++)
+ w[i] = get_unaligned_be32(&data[4 * i]);
+ for (; i < ARRAY_SIZE(w); i++)
+ w[i] = sigma_1(w[i - 2]) + w[i - 7] +
+ sigma_0(w[i - 15]) + w[i - 16];
+ for (i = 0; i < ARRAY_SIZE(w); i += 8) {
+ SHA256_ROUND(i + 0, a, b, c, d, e, f, g, h);
+ SHA256_ROUND(i + 1, h, a, b, c, d, e, f, g);
+ SHA256_ROUND(i + 2, g, h, a, b, c, d, e, f);
+ SHA256_ROUND(i + 3, f, g, h, a, b, c, d, e);
+ SHA256_ROUND(i + 4, e, f, g, h, a, b, c, d);
+ SHA256_ROUND(i + 5, d, e, f, g, h, a, b, c);
+ SHA256_ROUND(i + 6, c, d, e, f, g, h, a, b);
+ SHA256_ROUND(i + 7, b, c, d, e, f, g, h, a);
+ }
+ state[0] += a;
+ state[1] += b;
+ state[2] += c;
+ state[3] += d;
+ state[4] += e;
+ state[5] += f;
+ state[6] += g;
+ state[7] += h;
+ data += SHA256_BLOCK_LENGTH;
+ }
+}
+
+void libbpf_sha256(const void *data, size_t len, __u8 out[SHA256_DIGEST_LENGTH])
+{
+ __u32 state[8] = { 0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a,
+ 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19 };
+ const __be64 bitcount = cpu_to_be64((__u64)len * 8);
+ __u8 final_data[2 * SHA256_BLOCK_LENGTH] = { 0 };
+ size_t final_len = len % SHA256_BLOCK_LENGTH;
+ int i;
+
+ sha256_blocks(state, data, len / SHA256_BLOCK_LENGTH);
+
+ memcpy(final_data, data + len - final_len, final_len);
+ final_data[final_len] = 0x80;
+ final_len = roundup(final_len + 9, SHA256_BLOCK_LENGTH);
+ memcpy(&final_data[final_len - 8], &bitcount, 8);
+
+ sha256_blocks(state, final_data, final_len / SHA256_BLOCK_LENGTH);
+
+ for (i = 0; i < ARRAY_SIZE(state); i++)
+ put_unaligned_be32(state[i], &out[4 * i]);
+}
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
index 28c58fb17250..99331e317dee 100644
--- a/tools/lib/bpf/libbpf_version.h
+++ b/tools/lib/bpf/libbpf_version.h
@@ -4,6 +4,6 @@
#define __LIBBPF_VERSION_H
#define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 6
+#define LIBBPF_MINOR_VERSION 7
#endif /* __LIBBPF_VERSION_H */
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index a469e5d4fee7..56ae77047bc3 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -25,7 +25,6 @@
#include "btf.h"
#include "libbpf_internal.h"
#include "strset.h"
-#include "str_error.h"
#define BTF_EXTERN_SEC ".extern"
diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 2b83c98a1137..6eea5edba58a 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -64,7 +64,6 @@ enum libbpf_print_level {
#include "libbpf.h"
#include "bpf.h"
#include "btf.h"
-#include "str_error.h"
#include "libbpf_internal.h"
#endif
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 9702b70da444..00ec4837a06d 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -21,7 +21,6 @@
#include "libbpf.h"
#include "libbpf_internal.h"
#include "bpf.h"
-#include "str_error.h"
struct ring {
ring_buffer_sample_fn sample_cb;
diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
index 4d5fa079b5d6..6a8f5c7a02eb 100644
--- a/tools/lib/bpf/skel_internal.h
+++ b/tools/lib/bpf/skel_internal.h
@@ -13,10 +13,15 @@
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/mman.h>
+#include <linux/keyctl.h>
#include <stdlib.h>
#include "bpf.h"
#endif
+#ifndef SHA256_DIGEST_LENGTH
+#define SHA256_DIGEST_LENGTH 32
+#endif
+
#ifndef __NR_bpf
# if defined(__mips__) && defined(_ABIO32)
# define __NR_bpf 4355
@@ -64,6 +69,11 @@ struct bpf_load_and_run_opts {
__u32 data_sz;
__u32 insns_sz;
const char *errstr;
+ void *signature;
+ __u32 signature_sz;
+ __s32 keyring_id;
+ void *excl_prog_hash;
+ __u32 excl_prog_hash_sz;
};
long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
@@ -220,14 +230,19 @@ static inline int skel_map_create(enum bpf_map_type map_type,
const char *map_name,
__u32 key_size,
__u32 value_size,
- __u32 max_entries)
+ __u32 max_entries,
+ const void *excl_prog_hash,
+ __u32 excl_prog_hash_sz)
{
- const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
+ const size_t attr_sz = offsetofend(union bpf_attr, excl_prog_hash_size);
union bpf_attr attr;
memset(&attr, 0, attr_sz);
attr.map_type = map_type;
+ attr.excl_prog_hash = (unsigned long) excl_prog_hash;
+ attr.excl_prog_hash_size = excl_prog_hash_sz;
+
strncpy(attr.map_name, map_name, sizeof(attr.map_name));
attr.key_size = key_size;
attr.value_size = value_size;
@@ -300,6 +315,35 @@ static inline int skel_link_create(int prog_fd, int target_fd,
return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz);
}
+static inline int skel_obj_get_info_by_fd(int fd)
+{
+ const size_t attr_sz = offsetofend(union bpf_attr, info);
+ __u8 sha[SHA256_DIGEST_LENGTH];
+ struct bpf_map_info info;
+ __u32 info_len = sizeof(info);
+ union bpf_attr attr;
+
+ memset(&info, 0, sizeof(info));
+ info.hash = (long) &sha;
+ info.hash_size = SHA256_DIGEST_LENGTH;
+
+ memset(&attr, 0, attr_sz);
+ attr.info.bpf_fd = fd;
+ attr.info.info = (long) &info;
+ attr.info.info_len = info_len;
+ return skel_sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz);
+}
+
+static inline int skel_map_freeze(int fd)
+{
+ const size_t attr_sz = offsetofend(union bpf_attr, map_fd);
+ union bpf_attr attr;
+
+ memset(&attr, 0, attr_sz);
+ attr.map_fd = fd;
+
+ return skel_sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz);
+}
#ifdef __KERNEL__
#define set_err
#else
@@ -308,12 +352,13 @@ static inline int skel_link_create(int prog_fd, int target_fd,
static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
{
- const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array);
+ const size_t prog_load_attr_sz = offsetofend(union bpf_attr, keyring_id);
const size_t test_run_attr_sz = offsetofend(union bpf_attr, test);
int map_fd = -1, prog_fd = -1, key = 0, err;
union bpf_attr attr;
- err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
+ err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1,
+ opts->excl_prog_hash, opts->excl_prog_hash_sz);
if (map_fd < 0) {
opts->errstr = "failed to create loader map";
set_err;
@@ -327,11 +372,34 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
goto out;
}
+#ifndef __KERNEL__
+ err = skel_map_freeze(map_fd);
+ if (err < 0) {
+ opts->errstr = "failed to freeze map";
+ set_err;
+ goto out;
+ }
+ err = skel_obj_get_info_by_fd(map_fd);
+ if (err < 0) {
+ opts->errstr = "failed to fetch obj info";
+ set_err;
+ goto out;
+ }
+#endif
+
memset(&attr, 0, prog_load_attr_sz);
attr.prog_type = BPF_PROG_TYPE_SYSCALL;
attr.insns = (long) opts->insns;
attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
attr.license = (long) "Dual BSD/GPL";
+#ifndef __KERNEL__
+ attr.signature = (long) opts->signature;
+ attr.signature_size = opts->signature_sz;
+#else
+ if (opts->signature || opts->signature_sz)
+ pr_warn("signatures are not supported from bpf_preload\n");
+#endif
+ attr.keyring_id = opts->keyring_id;
memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog"));
attr.fd_array = (long) &map_fd;
attr.log_level = opts->ctx->log_level;
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
deleted file mode 100644
index 9a541762f54c..000000000000
--- a/tools/lib/bpf/str_error.c
+++ /dev/null
@@ -1,104 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-#undef _GNU_SOURCE
-#include <string.h>
-#include <stdio.h>
-#include <errno.h>
-#include "str_error.h"
-
-#ifndef ENOTSUPP
-#define ENOTSUPP 524
-#endif
-
-/* make sure libbpf doesn't use kernel-only integer typedefs */
-#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
-
-/*
- * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl
- * libc, while checking strerror_r() return to avoid having to check this in
- * all places calling it.
- */
-char *libbpf_strerror_r(int err, char *dst, int len)
-{
- int ret = strerror_r(err < 0 ? -err : err, dst, len);
- /* on glibc <2.13, ret == -1 and errno is set, if strerror_r() can't
- * handle the error, on glibc >=2.13 *positive* (errno-like) error
- * code is returned directly
- */
- if (ret == -1)
- ret = errno;
- if (ret) {
- if (ret == EINVAL)
- /* strerror_r() doesn't recognize this specific error */
- snprintf(dst, len, "unknown error (%d)", err < 0 ? err : -err);
- else
- snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
- }
- return dst;
-}
-
-const char *libbpf_errstr(int err)
-{
- static __thread char buf[12];
-
- if (err > 0)
- err = -err;
-
- switch (err) {
- case -E2BIG: return "-E2BIG";
- case -EACCES: return "-EACCES";
- case -EADDRINUSE: return "-EADDRINUSE";
- case -EADDRNOTAVAIL: return "-EADDRNOTAVAIL";
- case -EAGAIN: return "-EAGAIN";
- case -EALREADY: return "-EALREADY";
- case -EBADF: return "-EBADF";
- case -EBADFD: return "-EBADFD";
- case -EBUSY: return "-EBUSY";
- case -ECANCELED: return "-ECANCELED";
- case -ECHILD: return "-ECHILD";
- case -EDEADLK: return "-EDEADLK";
- case -EDOM: return "-EDOM";
- case -EEXIST: return "-EEXIST";
- case -EFAULT: return "-EFAULT";
- case -EFBIG: return "-EFBIG";
- case -EILSEQ: return "-EILSEQ";
- case -EINPROGRESS: return "-EINPROGRESS";
- case -EINTR: return "-EINTR";
- case -EINVAL: return "-EINVAL";
- case -EIO: return "-EIO";
- case -EISDIR: return "-EISDIR";
- case -ELOOP: return "-ELOOP";
- case -EMFILE: return "-EMFILE";
- case -EMLINK: return "-EMLINK";
- case -EMSGSIZE: return "-EMSGSIZE";
- case -ENAMETOOLONG: return "-ENAMETOOLONG";
- case -ENFILE: return "-ENFILE";
- case -ENODATA: return "-ENODATA";
- case -ENODEV: return "-ENODEV";
- case -ENOENT: return "-ENOENT";
- case -ENOEXEC: return "-ENOEXEC";
- case -ENOLINK: return "-ENOLINK";
- case -ENOMEM: return "-ENOMEM";
- case -ENOSPC: return "-ENOSPC";
- case -ENOTBLK: return "-ENOTBLK";
- case -ENOTDIR: return "-ENOTDIR";
- case -ENOTSUPP: return "-ENOTSUPP";
- case -ENOTTY: return "-ENOTTY";
- case -ENXIO: return "-ENXIO";
- case -EOPNOTSUPP: return "-EOPNOTSUPP";
- case -EOVERFLOW: return "-EOVERFLOW";
- case -EPERM: return "-EPERM";
- case -EPIPE: return "-EPIPE";
- case -EPROTO: return "-EPROTO";
- case -EPROTONOSUPPORT: return "-EPROTONOSUPPORT";
- case -ERANGE: return "-ERANGE";
- case -EROFS: return "-EROFS";
- case -ESPIPE: return "-ESPIPE";
- case -ESRCH: return "-ESRCH";
- case -ETXTBSY: return "-ETXTBSY";
- case -EUCLEAN: return "-EUCLEAN";
- case -EXDEV: return "-EXDEV";
- default:
- snprintf(buf, sizeof(buf), "%d", err);
- return buf;
- }
-}
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
deleted file mode 100644
index 53e7fbffc13e..000000000000
--- a/tools/lib/bpf/str_error.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-#ifndef __LIBBPF_STR_ERROR_H
-#define __LIBBPF_STR_ERROR_H
-
-#define STRERR_BUFSIZE 128
-
-char *libbpf_strerror_r(int err, char *dst, int len);
-
-/**
- * @brief **libbpf_errstr()** returns string corresponding to numeric errno
- * @param err negative numeric errno
- * @return pointer to string representation of the errno, that is invalidated
- * upon the next call.
- */
-const char *libbpf_errstr(int err);
-
-#define errstr(err) libbpf_errstr(err)
-
-#endif /* __LIBBPF_STR_ERROR_H */
diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h
index 2a7865c8e3fe..43deb05a5197 100644
--- a/tools/lib/bpf/usdt.bpf.h
+++ b/tools/lib/bpf/usdt.bpf.h
@@ -34,13 +34,32 @@ enum __bpf_usdt_arg_type {
BPF_USDT_ARG_CONST,
BPF_USDT_ARG_REG,
BPF_USDT_ARG_REG_DEREF,
+ BPF_USDT_ARG_SIB,
};
+/*
+ * This struct layout is designed specifically to be backwards/forward
+ * compatible between libbpf versions for ARG_CONST, ARG_REG, and
+ * ARG_REG_DEREF modes. ARG_SIB requires libbpf v1.7+.
+ */
struct __bpf_usdt_arg_spec {
/* u64 scalar interpreted depending on arg_type, see below */
__u64 val_off;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
/* arg location case, see bpf_usdt_arg() for details */
- enum __bpf_usdt_arg_type arg_type;
+ enum __bpf_usdt_arg_type arg_type: 8;
+ /* index register offset within struct pt_regs */
+ __u16 idx_reg_off: 12;
+ /* scale factor for index register (1, 2, 4, or 8) */
+ __u16 scale_bitshift: 4;
+ /* reserved for future use, keeps reg_off offset stable */
+ __u8 __reserved: 8;
+#else
+ __u8 __reserved: 8;
+ __u16 idx_reg_off: 12;
+ __u16 scale_bitshift: 4;
+ enum __bpf_usdt_arg_type arg_type: 8;
+#endif
/* offset of referenced register within struct pt_regs */
short reg_off;
/* whether arg should be interpreted as signed value */
@@ -149,7 +168,7 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res)
{
struct __bpf_usdt_spec *spec;
struct __bpf_usdt_arg_spec *arg_spec;
- unsigned long val;
+ unsigned long val, idx;
int err, spec_id;
*res = 0;
@@ -204,6 +223,27 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res)
val >>= arg_spec->arg_bitshift;
#endif
break;
+ case BPF_USDT_ARG_SIB:
+ /* Arg is in memory addressed by SIB (Scale-Index-Base) mode
+ * (e.g., "-1@-96(%rbp,%rax,8)" in USDT arg spec). We first
+ * fetch the base register contents and the index register
+ * contents from pt_regs. Then we calculate the final address
+ * as base + (index * scale) + offset, and do a user-space
+ * probe read to fetch the argument value.
+ */
+ err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off);
+ if (err)
+ return err;
+ err = bpf_probe_read_kernel(&idx, sizeof(idx), (void *)ctx + arg_spec->idx_reg_off);
+ if (err)
+ return err;
+ err = bpf_probe_read_user(&val, sizeof(val), (void *)(val + (idx << arg_spec->scale_bitshift) + arg_spec->val_off));
+ if (err)
+ return err;
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ val >>= arg_spec->arg_bitshift;
+#endif
+ break;
default:
return -EINVAL;
}
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index 4e4a52742b01..c174b4086673 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -20,7 +20,6 @@
#include "libbpf_common.h"
#include "libbpf_internal.h"
#include "hashmap.h"
-#include "str_error.h"
/* libbpf's USDT support consists of BPF-side state/code and user-space
* state/code working together in concert. BPF-side parts are defined in
@@ -59,7 +58,7 @@
*
* STAP_PROBE3(my_usdt_provider, my_usdt_probe_name, 123, x, &y);
*
- * USDT is identified by it's <provider-name>:<probe-name> pair of names. Each
+ * USDT is identified by its <provider-name>:<probe-name> pair of names. Each
* individual USDT has a fixed number of arguments (3 in the above example)
* and specifies values of each argument as if it was a function call.
*
@@ -81,7 +80,7 @@
* NOP instruction that kernel can replace with an interrupt instruction to
* trigger instrumentation code (BPF program for all that we care about).
*
- * Semaphore above is and optional feature. It records an address of a 2-byte
+ * Semaphore above is an optional feature. It records an address of a 2-byte
* refcount variable (normally in '.probes' ELF section) used for signaling if
* there is anything that is attached to USDT. This is useful for user
* applications if, for example, they need to prepare some arguments that are
@@ -121,7 +120,7 @@
* a uprobe BPF program (which for kernel, at least currently, is just a kprobe
* program, so BPF_PROG_TYPE_KPROBE program type). With the only difference
* that uprobe is usually attached at the function entry, while USDT will
- * normally will be somewhere inside the function. But it should always be
+ * normally be somewhere inside the function. But it should always be
* pointing to NOP instruction, which makes such uprobes the fastest uprobe
* kind.
*
@@ -151,7 +150,7 @@
* libbpf sets to spec ID during attach time, or, if kernel is too old to
* support BPF cookie, through IP-to-spec-ID map that libbpf maintains in such
* case. The latter means that some modes of operation can't be supported
- * without BPF cookie. Such mode is attaching to shared library "generically",
+ * without BPF cookie. Such a mode is attaching to shared library "generically",
* without specifying target process. In such case, it's impossible to
* calculate absolute IP addresses for IP-to-spec-ID map, and thus such mode
* is not supported without BPF cookie support.
@@ -185,7 +184,7 @@
* as even if USDT spec string is the same, USDT cookie value can be
* different. It was deemed excessive to try to deduplicate across independent
* USDT attachments by taking into account USDT spec string *and* USDT cookie
- * value, which would complicated spec ID accounting significantly for little
+ * value, which would complicate spec ID accounting significantly for little
* gain.
*/
@@ -200,12 +199,23 @@ enum usdt_arg_type {
USDT_ARG_CONST,
USDT_ARG_REG,
USDT_ARG_REG_DEREF,
+ USDT_ARG_SIB,
};
/* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */
struct usdt_arg_spec {
__u64 val_off;
- enum usdt_arg_type arg_type;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ enum usdt_arg_type arg_type: 8;
+ __u16 idx_reg_off: 12;
+ __u16 scale_bitshift: 4;
+ __u8 __reserved: 8; /* keep reg_off offset stable */
+#else
+ __u8 __reserved: 8; /* keep reg_off offset stable */
+ __u16 idx_reg_off: 12;
+ __u16 scale_bitshift: 4;
+ enum usdt_arg_type arg_type: 8;
+#endif
short reg_off;
bool arg_signed;
char arg_bitshift;
@@ -570,9 +580,8 @@ static struct elf_seg *find_vma_seg(struct elf_seg *segs, size_t seg_cnt, long o
return NULL;
}
-static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr,
- const char *data, size_t name_off, size_t desc_off,
- struct usdt_note *usdt_note);
+static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off,
+ size_t desc_off, struct usdt_note *usdt_note);
static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie);
@@ -626,7 +635,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *
struct elf_seg *seg = NULL;
void *tmp;
- err = parse_usdt_note(elf, path, &nhdr, data->d_buf, name_off, desc_off, &note);
+ err = parse_usdt_note(&nhdr, data->d_buf, name_off, desc_off, &note);
if (err)
goto err_out;
@@ -1132,8 +1141,7 @@ err_out:
/* Parse out USDT ELF note from '.note.stapsdt' section.
* Logic inspired by perf's code.
*/
-static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr,
- const char *data, size_t name_off, size_t desc_off,
+static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off,
struct usdt_note *note)
{
const char *provider, *name, *args;
@@ -1283,11 +1291,51 @@ static int calc_pt_regs_off(const char *reg_name)
static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
{
- char reg_name[16];
- int len, reg_off;
- long off;
+ char reg_name[16] = {0}, idx_reg_name[16] = {0};
+ int len, reg_off, idx_reg_off, scale = 1;
+ long off = 0;
+
+ if (sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^,] , %d ) %n",
+ arg_sz, &off, reg_name, idx_reg_name, &scale, &len) == 5 ||
+ sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^,] , %d ) %n",
+ arg_sz, reg_name, idx_reg_name, &scale, &len) == 4 ||
+ sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^)] ) %n",
+ arg_sz, &off, reg_name, idx_reg_name, &len) == 4 ||
+ sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^)] ) %n",
+ arg_sz, reg_name, idx_reg_name, &len) == 3
+ ) {
+ /*
+ * Scale Index Base case:
+ * 1@-96(%rbp,%rax,8)
+ * 1@(%rbp,%rax,8)
+ * 1@-96(%rbp,%rax)
+ * 1@(%rbp,%rax)
+ */
+ arg->arg_type = USDT_ARG_SIB;
+ arg->val_off = off;
- if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", arg_sz, &off, reg_name, &len) == 3) {
+ reg_off = calc_pt_regs_off(reg_name);
+ if (reg_off < 0)
+ return reg_off;
+ arg->reg_off = reg_off;
+
+ idx_reg_off = calc_pt_regs_off(idx_reg_name);
+ if (idx_reg_off < 0)
+ return idx_reg_off;
+ arg->idx_reg_off = idx_reg_off;
+
+ /* validate scale factor and set fields directly */
+ switch (scale) {
+ case 1: arg->scale_bitshift = 0; break;
+ case 2: arg->scale_bitshift = 1; break;
+ case 4: arg->scale_bitshift = 2; break;
+ case 8: arg->scale_bitshift = 3; break;
+ default:
+ pr_warn("usdt: invalid SIB scale %d, expected 1, 2, 4, 8\n", scale);
+ return -EINVAL;
+ }
+ } else if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n",
+ arg_sz, &off, reg_name, &len) == 3) {
/* Memory dereference case, e.g., -4@-20(%rbp) */
arg->arg_type = USDT_ARG_REG_DEREF;
arg->val_off = off;
@@ -1306,6 +1354,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
} else if (sscanf(arg_str, " %d @ %%%15s %n", arg_sz, reg_name, &len) == 2) {
/* Register read case, e.g., -4@%eax */
arg->arg_type = USDT_ARG_REG;
+ /* register read has no memory offset */
arg->val_off = 0;
reg_off = calc_pt_regs_off(reg_name);
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-26 15:55:14 +0000