summaryrefslogtreecommitdiff
path: root/tools/lib/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/lib/bpf')
-rw-r--r--tools/lib/bpf/Build3
-rw-r--r--tools/lib/bpf/Makefile10
-rw-r--r--tools/lib/bpf/bpf.c158
-rw-r--r--tools/lib/bpf/bpf.h66
-rw-r--r--tools/lib/bpf/bpf_core_read.h37
-rw-r--r--tools/lib/bpf/bpf_helpers.h28
-rw-r--r--tools/lib/bpf/bpf_tracing.h126
-rw-r--r--tools/lib/bpf/btf.c46
-rw-r--r--tools/lib/bpf/btf.h34
-rw-r--r--tools/lib/bpf/btf_dump.c11
-rw-r--r--tools/lib/bpf/gen_loader.c15
-rw-r--r--tools/lib/bpf/hashmap.c3
-rw-r--r--tools/lib/bpf/libbpf.c2183
-rw-r--r--tools/lib/bpf/libbpf.h513
-rw-r--r--tools/lib/bpf/libbpf.map31
-rw-r--r--tools/lib/bpf/libbpf_internal.h54
-rw-r--r--tools/lib/bpf/libbpf_legacy.h26
-rw-r--r--tools/lib/bpf/libbpf_version.h4
-rw-r--r--tools/lib/bpf/netlink.c180
-rw-r--r--tools/lib/bpf/relo_core.c183
-rw-r--r--tools/lib/bpf/relo_core.h48
-rw-r--r--tools/lib/bpf/skel_internal.h253
-rw-r--r--tools/lib/bpf/usdt.bpf.h259
-rw-r--r--tools/lib/bpf/usdt.c1518
-rw-r--r--tools/lib/bpf/xsk.c15
25 files changed, 5065 insertions, 739 deletions
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 94f0a146bb7b..31a1a9015902 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,3 +1,4 @@
libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \
- btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o
+ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \
+ usdt.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index f947b61b2107..a1265b152027 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -60,7 +60,7 @@ ifndef VERBOSE
VERBOSE = 0
endif
-INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.) \
+INCLUDES = -I$(or $(OUTPUT),.) \
-I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
export prefix libdir src obj
@@ -127,11 +127,11 @@ TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags)
GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
sed 's/\[.*\]//' | \
- awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
+ awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \
sort -u | wc -l)
VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
sed 's/\[.*\]//' | \
- awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
+ awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
@@ -194,7 +194,7 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
sort -u > $(OUTPUT)libbpf_global_syms.tmp; \
readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
sed 's/\[.*\]//' | \
- awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \
+ awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}'| \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \
sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \
diff -u $(OUTPUT)libbpf_global_syms.tmp \
@@ -239,7 +239,7 @@ install_lib: all_cmd
SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
bpf_helpers.h bpf_tracing.h bpf_endian.h bpf_core_read.h \
- skel_internal.h libbpf_version.h
+ skel_internal.h libbpf_version.h usdt.bpf.h
GEN_HDRS := $(BPF_GENERATED)
INSTALL_PFX := $(DESTDIR)$(prefix)/include/bpf
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 550b4cbb6c99..240186aac8e6 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -29,6 +29,7 @@
#include <errno.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/kernel.h>
#include <limits.h>
#include <sys/resource.h>
#include "bpf.h"
@@ -111,7 +112,7 @@ int probe_memcg_account(void)
BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
BPF_EXIT_INSN(),
};
- size_t insn_cnt = sizeof(insns) / sizeof(insns[0]);
+ size_t insn_cnt = ARRAY_SIZE(insns);
union bpf_attr attr;
int prog_fd;
@@ -207,86 +208,6 @@ int bpf_map_create(enum bpf_map_type map_type,
return libbpf_err_errno(fd);
}
-int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
-{
- LIBBPF_OPTS(bpf_map_create_opts, p);
-
- p.map_flags = create_attr->map_flags;
- p.numa_node = create_attr->numa_node;
- p.btf_fd = create_attr->btf_fd;
- p.btf_key_type_id = create_attr->btf_key_type_id;
- p.btf_value_type_id = create_attr->btf_value_type_id;
- p.map_ifindex = create_attr->map_ifindex;
- if (create_attr->map_type == BPF_MAP_TYPE_STRUCT_OPS)
- p.btf_vmlinux_value_type_id = create_attr->btf_vmlinux_value_type_id;
- else
- p.inner_map_fd = create_attr->inner_map_fd;
-
- return bpf_map_create(create_attr->map_type, create_attr->name,
- create_attr->key_size, create_attr->value_size,
- create_attr->max_entries, &p);
-}
-
-int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
- int key_size, int value_size, int max_entries,
- __u32 map_flags, int node)
-{
- LIBBPF_OPTS(bpf_map_create_opts, opts);
-
- opts.map_flags = map_flags;
- if (node >= 0) {
- opts.numa_node = node;
- opts.map_flags |= BPF_F_NUMA_NODE;
- }
-
- return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts);
-}
-
-int bpf_create_map(enum bpf_map_type map_type, int key_size,
- int value_size, int max_entries, __u32 map_flags)
-{
- LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags);
-
- return bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
-}
-
-int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
- int key_size, int value_size, int max_entries,
- __u32 map_flags)
-{
- LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags);
-
- return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts);
-}
-
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
- int key_size, int inner_map_fd, int max_entries,
- __u32 map_flags, int node)
-{
- LIBBPF_OPTS(bpf_map_create_opts, opts);
-
- opts.inner_map_fd = inner_map_fd;
- opts.map_flags = map_flags;
- if (node >= 0) {
- opts.map_flags |= BPF_F_NUMA_NODE;
- opts.numa_node = node;
- }
-
- return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts);
-}
-
-int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
- int key_size, int inner_map_fd, int max_entries,
- __u32 map_flags)
-{
- LIBBPF_OPTS(bpf_map_create_opts, opts,
- .inner_map_fd = inner_map_fd,
- .map_flags = map_flags,
- );
-
- return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts);
-}
-
static void *
alloc_zero_tailing_info(const void *orecord, __u32 cnt,
__u32 actual_rec_size, __u32 expected_rec_size)
@@ -638,6 +559,20 @@ int bpf_map_delete_elem(int fd, const void *key)
return libbpf_err_errno(ret);
}
+int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags)
+{
+ union bpf_attr attr;
+ int ret;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.map_fd = fd;
+ attr.key = ptr_to_u64(key);
+ attr.flags = flags;
+
+ ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+ return libbpf_err_errno(ret);
+}
+
int bpf_map_get_next_key(int fd, const void *key, void *next_key)
{
union bpf_attr attr;
@@ -754,10 +689,10 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
.flags = flags,
);
- return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts);
+ return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts);
}
-int bpf_prog_attach_xattr(int prog_fd, int target_fd,
+int bpf_prog_attach_opts(int prog_fd, int target_fd,
enum bpf_attach_type type,
const struct bpf_prog_attach_opts *opts)
{
@@ -778,6 +713,11 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd,
return libbpf_err_errno(ret);
}
+__attribute__((alias("bpf_prog_attach_opts")))
+int bpf_prog_attach_xattr(int prog_fd, int target_fd,
+ enum bpf_attach_type type,
+ const struct bpf_prog_attach_opts *opts);
+
int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
{
union bpf_attr attr;
@@ -811,7 +751,7 @@ int bpf_link_create(int prog_fd, int target_fd,
{
__u32 target_btf_id, iter_info_len;
union bpf_attr attr;
- int fd;
+ int fd, err;
if (!OPTS_VALID(opts, bpf_link_create_opts))
return libbpf_err(-EINVAL);
@@ -848,6 +788,23 @@ int bpf_link_create(int prog_fd, int target_fd,
if (!OPTS_ZEROED(opts, perf_event))
return libbpf_err(-EINVAL);
break;
+ case BPF_TRACE_KPROBE_MULTI:
+ attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0);
+ attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0);
+ attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0));
+ attr.link_create.kprobe_multi.addrs = ptr_to_u64(OPTS_GET(opts, kprobe_multi.addrs, 0));
+ attr.link_create.kprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, kprobe_multi.cookies, 0));
+ if (!OPTS_ZEROED(opts, kprobe_multi))
+ return libbpf_err(-EINVAL);
+ break;
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ case BPF_MODIFY_RETURN:
+ case BPF_LSM_MAC:
+ attr.link_create.tracing.cookie = OPTS_GET(opts, tracing.cookie, 0);
+ if (!OPTS_ZEROED(opts, tracing))
+ return libbpf_err(-EINVAL);
+ break;
default:
if (!OPTS_ZEROED(opts, flags))
return libbpf_err(-EINVAL);
@@ -855,7 +812,37 @@ int bpf_link_create(int prog_fd, int target_fd,
}
proceed:
fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr));
- return libbpf_err_errno(fd);
+ if (fd >= 0)
+ return fd;
+ /* we'll get EINVAL if LINK_CREATE doesn't support attaching fentry
+ * and other similar programs
+ */
+ err = -errno;
+ if (err != -EINVAL)
+ return libbpf_err(err);
+
+ /* if user used features not supported by
+ * BPF_RAW_TRACEPOINT_OPEN command, then just give up immediately
+ */
+ if (attr.link_create.target_fd || attr.link_create.target_btf_id)
+ return libbpf_err(err);
+ if (!OPTS_ZEROED(opts, sz))
+ return libbpf_err(err);
+
+ /* otherwise, for few select kinds of programs that can be
+ * attached using BPF_RAW_TRACEPOINT_OPEN command, try that as
+ * a fallback for older kernels
+ */
+ switch (attach_type) {
+ case BPF_TRACE_RAW_TP:
+ case BPF_LSM_MAC:
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ case BPF_MODIFY_RETURN:
+ return bpf_raw_tracepoint_open(NULL, prog_fd);
+ default:
+ return libbpf_err(err);
+ }
}
int bpf_link_detach(int link_fd)
@@ -989,6 +976,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
memset(&attr, 0, sizeof(attr));
attr.test.prog_fd = prog_fd;
+ attr.test.batch_size = OPTS_GET(opts, batch_size, 0);
attr.test.cpu = OPTS_GET(opts, cpu, 0);
attr.test.flags = OPTS_GET(opts, flags, 0);
attr.test.repeat = OPTS_GET(opts, repeat, 0);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 14e0d97ad2cf..cabc03703e29 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -61,48 +61,6 @@ LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
__u32 max_entries,
const struct bpf_map_create_opts *opts);
-struct bpf_create_map_attr {
- const char *name;
- enum bpf_map_type map_type;
- __u32 map_flags;
- __u32 key_size;
- __u32 value_size;
- __u32 max_entries;
- __u32 numa_node;
- __u32 btf_fd;
- __u32 btf_key_type_id;
- __u32 btf_value_type_id;
- __u32 map_ifindex;
- union {
- __u32 inner_map_fd;
- __u32 btf_vmlinux_value_type_id;
- };
-};
-
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
- int key_size, int value_size,
- int max_entries, __u32 map_flags, int node);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
- int key_size, int value_size,
- int max_entries, __u32 map_flags);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
- int value_size, int max_entries, __u32 map_flags);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type,
- const char *name, int key_size,
- int inner_map_fd, int max_entries,
- __u32 map_flags, int node);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type,
- const char *name, int key_size,
- int inner_map_fd, int max_entries,
- __u32 map_flags);
-
struct bpf_prog_load_opts {
size_t sz; /* size of this struct for forward/backward compatibility */
@@ -244,6 +202,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key,
void *value, __u64 flags);
LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
+LIBBPF_API int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags);
LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
LIBBPF_API int bpf_map_freeze(int fd);
@@ -391,6 +350,10 @@ struct bpf_prog_attach_opts {
LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
+ enum bpf_attach_type type,
+ const struct bpf_prog_attach_opts *opts);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead")
LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd,
enum bpf_attach_type type,
const struct bpf_prog_attach_opts *opts);
@@ -409,10 +372,20 @@ struct bpf_link_create_opts {
struct {
__u64 bpf_cookie;
} perf_event;
+ struct {
+ __u32 flags;
+ __u32 cnt;
+ const char **syms;
+ const unsigned long *addrs;
+ const __u64 *cookies;
+ } kprobe_multi;
+ struct {
+ __u64 cookie;
+ } tracing;
};
size_t :0;
};
-#define bpf_link_create_opts__last_field perf_event
+#define bpf_link_create_opts__last_field kprobe_multi.cookies
LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
enum bpf_attach_type attach_type,
@@ -449,12 +422,14 @@ struct bpf_prog_test_run_attr {
* out: length of cxt_out */
};
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead")
LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
/*
* bpf_prog_test_run does not check that data_out is large enough. Consider
- * using bpf_prog_test_run_xattr instead.
+ * using bpf_prog_test_run_opts instead.
*/
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead")
LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
__u32 size, void *data_out, __u32 *size_out,
__u32 *retval, __u32 *duration);
@@ -506,8 +481,9 @@ struct bpf_test_run_opts {
__u32 duration; /* out: average per repetition in ns */
__u32 flags;
__u32 cpu;
+ __u32 batch_size;
};
-#define bpf_test_run_opts__last_field cpu
+#define bpf_test_run_opts__last_field batch_size
LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
struct bpf_test_run_opts *opts);
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index e4aa9996a550..fd48b1ff59ca 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -110,21 +110,50 @@ enum bpf_enum_value_kind {
val; \
})
+#define ___bpf_field_ref1(field) (field)
+#define ___bpf_field_ref2(type, field) (((typeof(type) *)0)->field)
+#define ___bpf_field_ref(args...) \
+ ___bpf_apply(___bpf_field_ref, ___bpf_narg(args))(args)
+
/*
* Convenience macro to check that field actually exists in target kernel's.
* Returns:
* 1, if matching field is present in target kernel;
* 0, if no matching field found.
+ *
+ * Supports two forms:
+ * - field reference through variable access:
+ * bpf_core_field_exists(p->my_field);
+ * - field reference through type and field names:
+ * bpf_core_field_exists(struct my_type, my_field).
*/
-#define bpf_core_field_exists(field) \
- __builtin_preserve_field_info(field, BPF_FIELD_EXISTS)
+#define bpf_core_field_exists(field...) \
+ __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_EXISTS)
/*
* Convenience macro to get the byte size of a field. Works for integers,
* struct/unions, pointers, arrays, and enums.
+ *
+ * Supports two forms:
+ * - field reference through variable access:
+ * bpf_core_field_size(p->my_field);
+ * - field reference through type and field names:
+ * bpf_core_field_size(struct my_type, my_field).
+ */
+#define bpf_core_field_size(field...) \
+ __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_SIZE)
+
+/*
+ * Convenience macro to get field's byte offset.
+ *
+ * Supports two forms:
+ * - field reference through variable access:
+ * bpf_core_field_offset(p->my_field);
+ * - field reference through type and field names:
+ * bpf_core_field_offset(struct my_type, my_field).
*/
-#define bpf_core_field_size(field) \
- __builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE)
+#define bpf_core_field_offset(field...) \
+ __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_OFFSET)
/*
* Convenience macro to get BTF type ID of a specified type, using a local BTF
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 963b1060d944..fb04eaf367f1 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -76,6 +76,30 @@
#endif
/*
+ * Compiler (optimization) barrier.
+ */
+#ifndef barrier
+#define barrier() asm volatile("" ::: "memory")
+#endif
+
+/* Variable-specific compiler (optimization) barrier. It's a no-op which makes
+ * compiler believe that there is some black box modification of a given
+ * variable and thus prevents compiler from making extra assumption about its
+ * value and potential simplifications and optimizations on this variable.
+ *
+ * E.g., compiler might often delay or even omit 32-bit to 64-bit casting of
+ * a variable, making some code patterns unverifiable. Putting barrier_var()
+ * in place will ensure that cast is performed before the barrier_var()
+ * invocation, because compiler has to pessimistically assume that embedded
+ * asm section might perform some extra operations on that variable.
+ *
+ * This is a variable-specific variant of more global barrier().
+ */
+#ifndef barrier_var
+#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var))
+#endif
+
+/*
* Helper macro to throw a compilation error if __bpf_unreachable() gets
* built into the resulting code. This works given BPF back end does not
* implement __builtin_trap(). This is useful to assert that certain paths
@@ -133,7 +157,7 @@ struct bpf_map_def {
unsigned int value_size;
unsigned int max_entries;
unsigned int map_flags;
-};
+} __attribute__((deprecated("use BTF-defined maps in .maps section")));
enum libbpf_pin_type {
LIBBPF_PIN_NONE,
@@ -149,6 +173,8 @@ enum libbpf_tristate {
#define __kconfig __attribute__((section(".kconfig")))
#define __ksym __attribute__((section(".ksyms")))
+#define __kptr __attribute__((btf_type_tag("kptr")))
+#define __kptr_ref __attribute__((btf_type_tag("kptr_ref")))
#ifndef ___bpf_concat
#define ___bpf_concat(a, b) a ## b
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 90f56b0f585f..01ce121c302d 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -27,6 +27,9 @@
#elif defined(__TARGET_ARCH_riscv)
#define bpf_target_riscv
#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arc)
+ #define bpf_target_arc
+ #define bpf_target_defined
#else
/* Fall back to what the compiler says */
@@ -54,6 +57,9 @@
#elif defined(__riscv) && __riscv_xlen == 64
#define bpf_target_riscv
#define bpf_target_defined
+#elif defined(__arc__)
+ #define bpf_target_arc
+ #define bpf_target_defined
#endif /* no compiler target */
#endif
@@ -76,6 +82,9 @@
#define __PT_RC_REG ax
#define __PT_SP_REG sp
#define __PT_IP_REG ip
+/* syscall uses r10 for PARM4 */
+#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
#else
@@ -105,6 +114,9 @@
#define __PT_RC_REG rax
#define __PT_SP_REG rsp
#define __PT_IP_REG rip
+/* syscall uses r10 for PARM4 */
+#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
#endif /* __i386__ */
@@ -112,6 +124,10 @@
#elif defined(bpf_target_s390)
+struct pt_regs___s390 {
+ unsigned long orig_gpr2;
+};
+
/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
#define __PT_PARM1_REG gprs[2]
@@ -124,6 +140,8 @@
#define __PT_RC_REG gprs[2]
#define __PT_SP_REG gprs[15]
#define __PT_IP_REG psw.addr
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)
#elif defined(bpf_target_arm)
@@ -140,6 +158,10 @@
#elif defined(bpf_target_arm64)
+struct pt_regs___arm64 {
+ unsigned long orig_x0;
+};
+
/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
#define __PT_PARM1_REG regs[0]
@@ -152,6 +174,8 @@
#define __PT_RC_REG regs[0]
#define __PT_SP_REG sp
#define __PT_IP_REG pc
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)
#elif defined(bpf_target_mips)
@@ -178,6 +202,8 @@
#define __PT_RC_REG gpr[3]
#define __PT_SP_REG sp
#define __PT_IP_REG nip
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
#elif defined(bpf_target_sparc)
@@ -206,10 +232,29 @@
#define __PT_PARM4_REG a3
#define __PT_PARM5_REG a4
#define __PT_RET_REG ra
-#define __PT_FP_REG fp
+#define __PT_FP_REG s0
#define __PT_RC_REG a5
#define __PT_SP_REG sp
-#define __PT_IP_REG epc
+#define __PT_IP_REG pc
+/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+
+#elif defined(bpf_target_arc)
+
+/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG scratch.r0
+#define __PT_PARM2_REG scratch.r1
+#define __PT_PARM3_REG scratch.r2
+#define __PT_PARM4_REG scratch.r3
+#define __PT_PARM5_REG scratch.r4
+#define __PT_RET_REG scratch.blink
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG scratch.r0
+#define __PT_SP_REG scratch.sp
+#define __PT_IP_REG scratch.ret
+/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
#endif
@@ -263,6 +308,26 @@ struct pt_regs;
#endif
+#ifndef PT_REGS_PARM1_SYSCALL
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x)
+#endif
+#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x)
+#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x)
+#ifndef PT_REGS_PARM4_SYSCALL
+#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x)
+#endif
+#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x)
+
+#ifndef PT_REGS_PARM1_CORE_SYSCALL
+#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x)
+#endif
+#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x)
+#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x)
+#ifndef PT_REGS_PARM4_CORE_SYSCALL
+#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x)
+#endif
+#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x)
+
#else /* defined(bpf_target_defined) */
#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -290,8 +355,30 @@ struct pt_regs;
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
#endif /* defined(bpf_target_defined) */
+/*
+ * When invoked from a syscall handler kprobe, returns a pointer to a
+ * struct pt_regs containing syscall arguments and suitable for passing to
+ * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL().
+ */
+#ifndef PT_REGS_SYSCALL_REGS
+/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx))
+#endif
+
#ifndef ___bpf_concat
#define ___bpf_concat(a, b) a ## b
#endif
@@ -406,4 +493,39 @@ typeof(name(0)) name(struct pt_regs *ctx) \
} \
static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
+#define ___bpf_syscall_args0() ctx
+#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KPROBE_SYSCALL is a variant of BPF_KPROBE, which is intended for
+ * tracing syscall functions, like __x64_sys_close. It hides the underlying
+ * platform-specific low-level way of getting syscall input arguments from
+ * struct pt_regs, and provides a familiar typed and named function arguments
+ * syntax and semantics of accessing syscall input parameters.
+ *
+ * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ *
+ * This macro relies on BPF CO-RE support.
+ */
+#define BPF_KPROBE_SYSCALL(name, args...) \
+name(struct pt_regs *ctx); \
+static __attribute__((always_inline)) typeof(name(0)) \
+____##name(struct pt_regs *ctx, ##args); \
+typeof(name(0)) name(struct pt_regs *ctx) \
+{ \
+ struct pt_regs *regs = PT_REGS_SYSCALL_REGS(ctx); \
+ _Pragma("GCC diagnostic push") \
+ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
+ return ____##name(___bpf_syscall_args(args)); \
+ _Pragma("GCC diagnostic pop") \
+} \
+static __attribute__((always_inline)) typeof(name(0)) \
+____##name(struct pt_regs *ctx, ##args)
+
#endif
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 9aa19c89f758..bb1e06eb1eca 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1620,20 +1620,37 @@ static int btf_commit_type(struct btf *btf, int data_sz)
struct btf_pipe {
const struct btf *src;
struct btf *dst;
+ struct hashmap *str_off_map; /* map string offsets from src to dst */
};
static int btf_rewrite_str(__u32 *str_off, void *ctx)
{
struct btf_pipe *p = ctx;
- int off;
+ void *mapped_off;
+ int off, err;
if (!*str_off) /* nothing to do for empty strings */
return 0;
+ if (p->str_off_map &&
+ hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) {
+ *str_off = (__u32)(long)mapped_off;
+ return 0;
+ }
+
off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off));
if (off < 0)
return off;
+ /* Remember string mapping from src to dst. It avoids
+ * performing expensive string comparisons.
+ */
+ if (p->str_off_map) {
+ err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off);
+ if (err)
+ return err;
+ }
+
*str_off = off;
return 0;
}
@@ -1680,6 +1697,9 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
return 0;
}
+static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx);
+static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx);
+
int btf__add_btf(struct btf *btf, const struct btf *src_btf)
{
struct btf_pipe p = { .src = src_btf, .dst = btf };
@@ -1713,6 +1733,11 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
if (!off)
return libbpf_err(-ENOMEM);
+ /* Map the string offsets from src_btf to the offsets from btf to improve performance */
+ p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL);
+ if (IS_ERR(p.str_off_map))
+ return libbpf_err(-ENOMEM);
+
/* bulk copy types data for all types from src_btf */
memcpy(t, src_btf->types_data, data_sz);
@@ -1754,6 +1779,8 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
btf->hdr->str_off += data_sz;
btf->nr_types += cnt;
+ hashmap__free(p.str_off_map);
+
/* return type ID of the first added BTF type */
return btf->start_id + btf->nr_types - cnt;
err_out:
@@ -1767,6 +1794,8 @@ err_out:
* wasn't modified, so doesn't need restoring, see big comment above */
btf->hdr->str_len = old_strs_len;
+ hashmap__free(p.str_off_map);
+
return libbpf_err(err);
}
@@ -2597,6 +2626,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext,
const struct btf_ext_info_sec *sinfo;
struct btf_ext_info *ext_info;
__u32 info_left, record_size;
+ size_t sec_cnt = 0;
/* The sta