aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-gen.rst78
-rw-r--r--tools/bpf/bpftool/bash-completion/bpftool17
-rw-r--r--tools/bpf/bpftool/btf.c3
-rw-r--r--tools/bpf/bpftool/common.c1
-rw-r--r--tools/bpf/bpftool/gen.c72
-rw-r--r--tools/bpf/bpftool/main.c3
-rw-r--r--tools/bpf/bpftool/map.c2
-rw-r--r--tools/bpf/bpftool/prog.c1
-rw-r--r--tools/bpf/resolve_btfids/main.c11
-rw-r--r--tools/include/uapi/linux/bpf.h5
-rw-r--r--tools/include/uapi/linux/kvm.h13
-rw-r--r--tools/kvm/kvm_stat/kvm_stat.service1
-rw-r--r--tools/lib/bpf/Build2
-rw-r--r--tools/lib/bpf/Makefile3
-rw-r--r--tools/lib/bpf/bpf_helpers.h21
-rw-r--r--tools/lib/bpf/btf.c714
-rw-r--r--tools/lib/bpf/btf.h3
-rw-r--r--tools/lib/bpf/btf_dump.c10
-rw-r--r--tools/lib/bpf/libbpf.c421
-rw-r--r--tools/lib/bpf/libbpf.h19
-rw-r--r--tools/lib/bpf/libbpf.map6
-rw-r--r--tools/lib/bpf/libbpf_internal.h38
-rw-r--r--tools/lib/bpf/libbpf_util.h75
-rw-r--r--tools/lib/bpf/linker.c1963
-rw-r--r--tools/lib/bpf/netlink.c2
-rw-r--r--tools/lib/bpf/ringbuf.c2
-rw-r--r--tools/lib/bpf/strset.c176
-rw-r--r--tools/lib/bpf/strset.h21
-rw-r--r--tools/lib/bpf/xsk.c315
-rw-r--r--tools/lib/bpf/xsk.h70
-rw-r--r--tools/objtool/check.c3
-rw-r--r--tools/perf/builtin-daemon.c57
-rw-r--r--tools/perf/tests/bpf.c9
-rwxr-xr-xtools/perf/tests/shell/daemon.sh2
-rw-r--r--tools/perf/util/auxtrace.c4
-rw-r--r--tools/perf/util/bpf-event.c13
-rw-r--r--tools/perf/util/parse-events.c3
-rw-r--r--tools/perf/util/pmu.c33
-rw-r--r--tools/perf/util/pmu.h3
-rw-r--r--tools/perf/util/synthetic-events.c11
-rw-r--r--tools/perf/util/vdso.c2
-rw-r--r--tools/testing/kunit/configs/broken_on_uml.config2
-rw-r--r--tools/testing/kunit/kunit_config.py2
-rw-r--r--tools/testing/radix-tree/idr-test.c21
-rw-r--r--tools/testing/radix-tree/linux/compiler_types.h0
-rw-r--r--tools/testing/radix-tree/multiorder.c2
-rw-r--r--tools/testing/radix-tree/xarray.c2
-rw-r--r--tools/testing/selftests/arm64/fp/sve-ptrace.c2
-rw-r--r--tools/testing/selftests/arm64/fp/sve-test.S22
-rw-r--r--tools/testing/selftests/bpf/Makefile34
-rw-r--r--tools/testing/selftests/bpf/README.rst14
-rw-r--r--tools/testing/selftests/bpf/bpf_tcp_helpers.h29
-rw-r--r--tools/testing/selftests/bpf/get_cgroup_id_user.c6
-rw-r--r--tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c5
-rw-r--r--tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c158
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c44
-rw-r--r--tools/testing/selftests/bpf/prog_tests/check_mtu.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_sleep.c82
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kfunc_call.c59
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_basic.c40
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_listen.c136
-rw-r--r--tools/testing/selftests/bpf/prog_tests/static_linked.c40
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_ima.c6
-rw-r--r--tools/testing/selftests/bpf/progs/bind4_prog.c25
-rw-r--r--tools/testing/selftests/bpf/progs/bind6_prog.c25
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_cubic.c36
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_dctcp.c22
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c19
-rw-r--r--tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c8
-rw-r--r--tools/testing/selftests/bpf/progs/fentry_test.c2
-rw-r--r--tools/testing/selftests/bpf/progs/fexit_sleep.c31
-rw-r--r--tools/testing/selftests/bpf/progs/fexit_test.c4
-rw-r--r--tools/testing/selftests/bpf/progs/kfunc_call_test.c47
-rw-r--r--tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c42
-rw-r--r--tools/testing/selftests/bpf/progs/skb_pkt_end.c1
-rw-r--r--tools/testing/selftests/bpf/progs/test_check_mtu.c92
-rw-r--r--tools/testing/selftests/bpf/progs/test_global_func10.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_listen.c22
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c18
-rw-r--r--tools/testing/selftests/bpf/progs/test_static_linked1.c30
-rw-r--r--tools/testing/selftests/bpf/progs/test_static_linked2.c31
-rw-r--r--tools/testing/selftests/bpf/progs/test_tunnel_kern.c6
-rwxr-xr-xtools/testing/selftests/bpf/test_xsk.sh3
-rw-r--r--tools/testing/selftests/bpf/verifier/bounds_deduction.c27
-rw-r--r--tools/testing/selftests/bpf/verifier/calls.c12
-rw-r--r--tools/testing/selftests/bpf/verifier/dead_code.c10
-rw-r--r--tools/testing/selftests/bpf/verifier/map_ptr.c4
-rw-r--r--tools/testing/selftests/bpf/verifier/unpriv.c15
-rw-r--r--tools/testing/selftests/bpf/verifier/value_ptr_arith.c23
-rwxr-xr-xtools/testing/selftests/bpf/vmtest.sh39
-rw-r--r--tools/testing/selftests/bpf/xdpxceiver.c704
-rw-r--r--tools/testing/selftests/bpf/xdpxceiver.h49
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh31
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh82
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh77
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh21
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/tc_sample.sh165
-rw-r--r--tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh5
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh110
-rw-r--r--tools/testing/selftests/kvm/.gitignore3
-rw-r--r--tools/testing/selftests/kvm/Makefile3
-rw-r--r--tools/testing/selftests/kvm/hardware_disable_test.c10
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h2
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c7
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util_internal.h2
-rw-r--r--tools/testing/selftests/kvm/x86_64/get_msr_index_features.c134
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_clock.c269
-rw-r--r--tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c166
-rw-r--r--tools/testing/selftests/net/Makefile2
-rwxr-xr-xtools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh366
-rw-r--r--tools/testing/selftests/net/forwarding/fib_offload_lib.sh2
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh14
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_police.sh56
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh13
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh55
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c10
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh22
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh196
-rwxr-xr-xtools/testing/selftests/net/mptcp/pm_netlink.sh6
-rw-r--r--tools/testing/selftests/net/mptcp/pm_nl_ctl.c34
-rwxr-xr-xtools/testing/selftests/net/mptcp/simult_flows.sh13
-rw-r--r--tools/testing/selftests/net/reuseaddr_ports_exhausted.c32
-rw-r--r--tools/testing/selftests/net/so_txtime.c247
-rwxr-xr-xtools/testing/selftests/net/so_txtime.sh97
-rwxr-xr-xtools/testing/selftests/net/udpgro_fwd.sh251
-rwxr-xr-xtools/testing/selftests/net/veth.sh177
-rwxr-xr-xtools/testing/selftests/netfilter/nft_flowtable.sh82
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/police.json48
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/simple.json83
-rw-r--r--tools/testing/selftests/vm/Makefile4
130 files changed, 7638 insertions, 1526 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index 84cf0639696f..7cd6681137f3 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -14,16 +14,37 @@ SYNOPSIS
*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
- *COMMAND* := { **skeleton** | **help** }
+ *COMMAND* := { **object** | **skeleton** | **help** }
GEN COMMANDS
=============
-| **bpftool** **gen skeleton** *FILE*
+| **bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...]
+| **bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*]
| **bpftool** **gen help**
DESCRIPTION
===========
+ **bpftool gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...]
+ Statically link (combine) together one or more *INPUT_FILE*'s
+ into a single resulting *OUTPUT_FILE*. All the files involved
+ are BPF ELF object files.
+
+ The rules of BPF static linking are mostly the same as for
+ user-space object files, but in addition to combining data
+ and instruction sections, .BTF and .BTF.ext (if present in
+ any of the input files) data are combined together. .BTF
+ data is deduplicated, so all the common types across
+ *INPUT_FILE*'s will only be represented once in the resulting
+ BTF information.
+
+ BPF static linking allows to partition BPF source code into
+ individually compiled files that are then linked into
+ a single resulting BPF object file, which can be used to
+ generated BPF skeleton (with **gen skeleton** command) or
+ passed directly into **libbpf** (using **bpf_object__open()**
+ family of APIs).
+
**bpftool gen skeleton** *FILE*
Generate BPF skeleton C header file for a given *FILE*.
@@ -75,10 +96,13 @@ DESCRIPTION
specific maps, programs, etc.
As part of skeleton, few custom functions are generated.
- Each of them is prefixed with object name, derived from
- object file name. I.e., if BPF object file name is
- **example.o**, BPF object name will be **example**. The
- following custom functions are provided in such case:
+ Each of them is prefixed with object name. Object name can
+ either be derived from object file name, i.e., if BPF object
+ file name is **example.o**, BPF object name will be
+ **example**. Object name can be also specified explicitly
+ through **name** *OBJECT_NAME* parameter. The following
+ custom functions are provided (assuming **example** as
+ the object name):
- **example__open** and **example__open_opts**.
These functions are used to instantiate skeleton. It
@@ -130,26 +154,19 @@ OPTIONS
EXAMPLES
========
-**$ cat example.c**
+**$ cat example1.bpf.c**
::
#include <stdbool.h>
#include <linux/ptrace.h>
#include <linux/bpf.h>
- #include "bpf_helpers.h"
+ #include <bpf/bpf_helpers.h>
const volatile int param1 = 42;
bool global_flag = true;
struct { int x; } data = {};
- struct {
- __uint(type, BPF_MAP_TYPE_HASH);
- __uint(max_entries, 128);
- __type(key, int);
- __type(value, long);
- } my_map SEC(".maps");
-
SEC("raw_tp/sys_enter")
int handle_sys_enter(struct pt_regs *ctx)
{
@@ -161,6 +178,21 @@ EXAMPLES
return 0;
}
+**$ cat example2.bpf.c**
+
+::
+
+ #include <linux/ptrace.h>
+ #include <linux/bpf.h>
+ #include <bpf/bpf_helpers.h>
+
+ struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 128);
+ __type(key, int);
+ __type(value, long);
+ } my_map SEC(".maps");
+
SEC("raw_tp/sys_exit")
int handle_sys_exit(struct pt_regs *ctx)
{
@@ -170,9 +202,17 @@ EXAMPLES
}
This is example BPF application with two BPF programs and a mix of BPF maps
-and global variables.
+and global variables. Source code is split across two source code files.
-**$ bpftool gen skeleton example.o**
+**$ clang -target bpf -g example1.bpf.c -o example1.bpf.o**
+**$ clang -target bpf -g example2.bpf.c -o example2.bpf.o**
+**$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o**
+
+This set of commands compiles *example1.bpf.c* and *example2.bpf.c*
+individually and then statically links respective object files into the final
+BPF ELF object file *example.bpf.o*.
+
+**$ bpftool gen skeleton example.bpf.o name example | tee example.skel.h**
::
@@ -227,7 +267,7 @@ and global variables.
#endif /* __EXAMPLE_SKEL_H__ */
-**$ cat example_user.c**
+**$ cat example.c**
::
@@ -270,7 +310,7 @@ and global variables.
return err;
}
-**# ./example_user**
+**# ./example**
::
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index fdffbc64c65c..d67518bcbd44 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -981,12 +981,25 @@ _bpftool()
;;
gen)
case $command in
- skeleton)
+ object)
_filedir
+ return 0
+ ;;
+ skeleton)
+ case $prev in
+ $command)
+ _filedir
+ return 0
+ ;;
+ *)
+ _bpftool_once_attr 'name'
+ return 0
+ ;;
+ esac
;;
*)
[[ $prev == $object ]] && \
- COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) )
+ COMPREPLY=( $( compgen -W 'object skeleton help' -- "$cur" ) )
;;
esac
;;
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 985610c3f193..62953bbf68b4 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -546,6 +546,7 @@ static int do_dump(int argc, char **argv)
NEXT_ARG();
if (argc < 1) {
p_err("expecting value for 'format' option\n");
+ err = -EINVAL;
goto done;
}
if (strcmp(*argv, "c") == 0) {
@@ -555,11 +556,13 @@ static int do_dump(int argc, char **argv)
} else {
p_err("unrecognized format specifier: '%s', possible values: raw, c",
*argv);
+ err = -EINVAL;
goto done;
}
NEXT_ARG();
} else {
p_err("unrecognized option: '%s'", *argv);
+ err = -EINVAL;
goto done;
}
}
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 65303664417e..1828bba19020 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -57,6 +57,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = {
[BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser",
[BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict",
+ [BPF_SK_SKB_VERDICT] = "sk_skb_verdict",
[BPF_SK_MSG_VERDICT] = "sk_msg_verdict",
[BPF_LIRC_MODE2] = "lirc_mode2",
[BPF_FLOW_DISSECTOR] = "flow_dissector",
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 4033c46d83e7..31ade77f5ef8 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -273,7 +273,7 @@ static int do_skeleton(int argc, char **argv)
char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")];
size_t i, map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz;
DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
- char obj_name[MAX_OBJ_NAME_LEN], *obj_data;
+ char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data;
struct bpf_object *obj = NULL;
const char *file, *ident;
struct bpf_program *prog;
@@ -288,6 +288,28 @@ static int do_skeleton(int argc, char **argv)
}
file = GET_ARG();
+ while (argc) {
+ if (!REQ_ARGS(2))
+ return -1;
+
+ if (is_prefix(*argv, "name")) {
+ NEXT_ARG();
+
+ if (obj_name[0] != '\0') {
+ p_err("object name already specified");
+ return -1;
+ }
+
+ strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1);
+ obj_name[MAX_OBJ_NAME_LEN - 1] = '\0';
+ } else {
+ p_err("unknown arg %s", *argv);
+ return -1;
+ }
+
+ NEXT_ARG();
+ }
+
if (argc) {
p_err("extra unknown arguments");
return -1;
@@ -310,7 +332,8 @@ static int do_skeleton(int argc, char **argv)
p_err("failed to mmap() %s: %s", file, strerror(errno));
goto out;
}
- get_obj_name(obj_name, file);
+ if (obj_name[0] == '\0')
+ get_obj_name(obj_name, file);
opts.object_name = obj_name;
obj = bpf_object__open_mem(obj_data, file_sz, &opts);
if (IS_ERR(obj)) {
@@ -591,6 +614,47 @@ out:
return err;
}
+static int do_object(int argc, char **argv)
+{
+ struct bpf_linker *linker;
+ const char *output_file, *file;
+ int err = 0;
+
+ if (!REQ_ARGS(2)) {
+ usage();
+ return -1;
+ }
+
+ output_file = GET_ARG();
+
+ linker = bpf_linker__new(output_file, NULL);
+ if (!linker) {
+ p_err("failed to create BPF linker instance");
+ return -1;
+ }
+
+ while (argc) {
+ file = GET_ARG();
+
+ err = bpf_linker__add_file(linker, file);
+ if (err) {
+ p_err("failed to link '%s': %s (%d)", file, strerror(err), err);
+ goto out;
+ }
+ }
+
+ err = bpf_linker__finalize(linker);
+ if (err) {
+ p_err("failed to finalize ELF file: %s (%d)", strerror(err), err);
+ goto out;
+ }
+
+ err = 0;
+out:
+ bpf_linker__free(linker);
+ return err;
+}
+
static int do_help(int argc, char **argv)
{
if (json_output) {
@@ -599,7 +663,8 @@ static int do_help(int argc, char **argv)
}
fprintf(stderr,
- "Usage: %1$s %2$s skeleton FILE\n"
+ "Usage: %1$s %2$s object OUTPUT_FILE INPUT_FILE [INPUT_FILE...]\n"
+ " %1$s %2$s skeleton FILE [name OBJECT_NAME]\n"
" %1$s %2$s help\n"
"\n"
" " HELP_SPEC_OPTIONS "\n"
@@ -610,6 +675,7 @@ static int do_help(int argc, char **argv)
}
static const struct cmd cmds[] = {
+ { "object", do_object },
{ "skeleton", do_skeleton },
{ "help", do_help },
{ 0 }
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index b86f450e6fce..d9afb730136a 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -276,7 +276,7 @@ static int do_batch(int argc, char **argv)
int n_argc;
FILE *fp;
char *cp;
- int err;
+ int err = 0;
int i;
if (argc < 2) {
@@ -370,7 +370,6 @@ static int do_batch(int argc, char **argv)
} else {
if (!json_output)
printf("processed %d commands\n", lines);
- err = 0;
}
err_close:
if (fp != stdin)
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index b400364ee054..09ae0381205b 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -100,7 +100,7 @@ static int do_dump_btf(const struct btf_dumper *d,
void *value)
{
__u32 value_id;
- int ret;
+ int ret = 0;
/* start of key-value pair */
jsonw_start_object(d->jw);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index f2b915b20546..3f067d2d7584 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -76,6 +76,7 @@ enum dump_mode {
static const char * const attach_type_strings[] = {
[BPF_SK_SKB_STREAM_PARSER] = "stream_parser",
[BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict",
+ [BPF_SK_SKB_VERDICT] = "skb_verdict",
[BPF_SK_MSG_VERDICT] = "msg_verdict",
[BPF_FLOW_DISSECTOR] = "flow_dissector",
[__MAX_BPF_ATTACH_TYPE] = NULL,
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 80d966cfcaa1..7550fd9c3188 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -115,10 +115,10 @@ struct object {
static int verbose;
-int eprintf(int level, int var, const char *fmt, ...)
+static int eprintf(int level, int var, const char *fmt, ...)
{
va_list args;
- int ret;
+ int ret = 0;
if (var >= level) {
va_start(args, fmt);
@@ -385,7 +385,7 @@ static int elf_collect(struct object *obj)
static int symbols_collect(struct object *obj)
{
Elf_Scn *scn = NULL;
- int n, i, err = 0;
+ int n, i;
GElf_Shdr sh;
char *name;
@@ -402,11 +402,10 @@ static int symbols_collect(struct object *obj)
* Scan symbols and look for the ones starting with
* __BTF_ID__* over .BTF_ids section.
*/
- for (i = 0; !err && i < n; i++) {
- char *tmp, *prefix;
+ for (i = 0; i < n; i++) {
+ char *prefix;
struct btf_id *id;
GElf_Sym sym;
- int err = -1;
if (!gelf_getsym(obj->efile.symbols, i, &sym))
return -1;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2d3036e292a9..69902603012c 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -957,6 +957,7 @@ enum bpf_attach_type {
BPF_XDP_CPUMAP,
BPF_SK_LOOKUP,
BPF_XDP,
+ BPF_SK_SKB_VERDICT,
__MAX_BPF_ATTACH_TYPE
};
@@ -1117,6 +1118,10 @@ enum bpf_link_type {
* offset to another bpf function
*/
#define BPF_PSEUDO_CALL 1
+/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL,
+ * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel
+ */
+#define BPF_PSEUDO_KFUNC_CALL 2
/* flags for BPF_MAP_UPDATE_ELEM command */
enum {
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 8b281f722e5b..f6afee209620 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1154,6 +1154,7 @@ struct kvm_x86_mce {
#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
struct kvm_xen_hvm_config {
__u32 flags;
@@ -1621,12 +1622,24 @@ struct kvm_xen_vcpu_attr {
union {
__u64 gpa;
__u64 pad[8];
+ struct {
+ __u64 state;
+ __u64 state_entry_time;
+ __u64 time_running;
+ __u64 time_runnable;
+ __u64 time_blocked;
+ __u64 time_offline;
+ } runstate;
} u;
};
/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0
#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
diff --git a/tools/kvm/kvm_stat/kvm_stat.service b/tools/kvm/kvm_stat/kvm_stat.service
index 71aabaffe779..8f13b843d5b4 100644
--- a/tools/kvm/kvm_stat/kvm_stat.service
+++ b/tools/kvm/kvm_stat/kvm_stat.service
@@ -9,6 +9,7 @@ Type=simple
ExecStart=/usr/bin/kvm_stat -dtcz -s 10 -L /var/log/kvm_stat.csv
ExecReload=/bin/kill -HUP $MAINPID
Restart=always
+RestartSec=60s
SyslogIdentifier=kvm_stat
SyslogLevel=debug
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 190366d05588..9b057cc7650a 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,3 +1,3 @@
libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \
- btf_dump.o ringbuf.o
+ btf_dump.o ringbuf.o strset.o linker.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 8170f88e8ea6..e43e1896cb4b 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -215,7 +215,7 @@ define do_install
if [ ! -d '$(DESTDIR_SQ)$2' ]; then \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \
fi; \
- $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
+ $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
endef
install_lib: all_cmd
@@ -228,7 +228,6 @@ install_headers: $(BPF_HELPER_DEFS)
$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
$(call do_install,btf.h,$(prefix)/include/bpf,644); \
- $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \
$(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \
$(call do_install,xsk.h,$(prefix)/include/bpf,644); \
$(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index ae6c975e0b87..cc2e51c64a54 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -29,9 +29,10 @@
*/
#define SEC(NAME) __attribute__((section(NAME), used))
-#ifndef __always_inline
+/* Avoid 'linux/stddef.h' definition of '__always_inline'. */
+#undef __always_inline
#define __always_inline inline __attribute__((always_inline))
-#endif
+
#ifndef __noinline
#define __noinline __attribute__((noinline))
#endif
@@ -39,8 +40,22 @@
#define __weak __attribute__((weak))
#endif
+/* When utilizing vmlinux.h with BPF CO-RE, user BPF programs can't include
+ * any system-level headers (such as stddef.h, linux/version.h, etc), and
+ * commonly-used macros like NULL and KERNEL_VERSION aren't available through
+ * vmlinux.h. This just adds unnecessary hurdles and forces users to re-define
+ * them on their own. So as a convenience, provide such definitions here.
+ */
+#ifndef NULL
+#define NULL ((void *)0)
+#endif
+
+#ifndef KERNEL_VERSION
+#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c))
+#endif
+
/*
- * Helper macro to manipulate data structures
+ * Helper macros to manipulate data structures
*/
#ifndef offsetof
#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER)
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 3aa58f2ac183..d30e67e7e1e5 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -21,6 +21,7 @@
#include "libbpf.h"
#include "libbpf_internal.h"
#include "hashmap.h"
+#include "strset.h"
#define BTF_MAX_NR_TYPES 0x7fffffffU
#define BTF_MAX_STR_OFFSET 0x7fffffffU
@@ -67,7 +68,7 @@ struct btf {
* | | |
* hdr | |
* types_data----+ |
- * strs_data------------------+
+ * strset__data(strs_set)-----+
*
* +----------+---------+-----------+
* | Header | Types | Strings |
@@ -105,20 +106,15 @@ struct btf {
*/
int start_str_off;
+ /* only one of strs_data or strs_set can be non-NULL, depending on
+ * whether BTF is in a modifiable state (strs_set is used) or not
+ * (strs_data points inside raw_data)
+ */
void *strs_data;
- size_t strs_data_cap; /* used size stored in hdr->str_len */
-
- /* lookup index for each unique string in strings section */
- struct hashmap *strs_hash;
+ /* a set of unique strings */
+ struct strset *strs_set;
/* whether strings are already deduplicated */
bool strs_deduped;
- /* extra indirection layer to make strings hashmap work with stable
- * string offsets and ability to transparently choose between
- * btf->strs_data or btf_dedup->strs_data as a source of strings.
- * This is used for BTF strings dedup to transfer deduplicated strings
- * data back to struct btf without re-building strings index.
- */
- void **strs_data_ptr;
/* BTF object FD, if loaded into kernel */
int fd;
@@ -142,8 +138,8 @@ static inline __u64 ptr_to_u64(const void *ptr)
* On success, memory pointer to the beginning of unused memory is returned.
* On error, NULL is returned.
*/
-void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
- size_t cur_cnt, size_t max_cnt, size_t add_cnt)
+void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
+ size_t cur_cnt, size_t max_cnt, size_t add_cnt)
{
size_t new_cnt;
void *new_data;
@@ -179,14 +175,14 @@ void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
/* Ensure given dynamically allocated memory region has enough allocated space
* to accommodate *need_cnt* elements of size *elem_sz* bytes each
*/
-int btf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt)
+int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt)
{
void *p;
if (need_cnt <= *cap_cnt)
return 0;
- p = btf_add_mem(data, cap_cnt, elem_sz, *cap_cnt, SIZE_MAX, need_cnt - *cap_cnt);
+ p = libbpf_add_mem(data, cap_cnt, elem_sz, *cap_cnt, SIZE_MAX, need_cnt - *cap_cnt);
if (!p)
return -ENOMEM;
@@ -197,8 +193,8 @@ static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off)
{
__u32 *p;
- p = btf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
- btf->nr_types, BTF_MAX_NR_TYPES, 1);
+ p = libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
+ btf->nr_types, BTF_MAX_NR_TYPES, 1);
if (!p)
return -ENOMEM;
@@ -435,7 +431,7 @@ const struct btf *btf__base_btf(const struct btf *btf)
}
/* internal helper returning non-const pointer to a type */
-static struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
+struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
{
if (type_id == 0)
return &btf_void;
@@ -738,7 +734,7 @@ void btf__free(struct btf *btf)
*/
free(btf->hdr);
free(btf->types_data);
- free(btf->strs_data);
+ strset__free(btf->strs_set);
}
free(btf->raw_data);
free(btf->raw_data_swapped);
@@ -1246,6 +1242,11 @@ void btf__set_fd(struct btf *btf, int fd)
btf->fd = fd;
}
+static const void *btf_strs_data(const struct btf *btf)
+{
+ return btf->strs_data ? btf->strs_data : strset__data(btf->strs_set);
+}
+
static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian)
{
struct btf_header *hdr = btf->hdr;
@@ -1286,7 +1287,7 @@ static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endi
}
p += hdr->type_len;
- memcpy(p, btf->strs_data, hdr->str_len);
+ memcpy(p, btf_strs_data(btf), hdr->str_len);
p += hdr->str_len;
*size = data_sz;
@@ -1320,7 +1321,7 @@ const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
if (offset < btf->start_str_off)
return btf__str_by_offset(btf->base_btf, offset);
else if (offset - btf->start_str_off < btf->hdr->str_len)
- return btf->strs_data + (offset - btf->start_str_off);
+ return btf_strs_data(btf) + (offset - btf->start_str_off);
else
return NULL;
}
@@ -1474,25 +1475,6 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
return 0;
}
-static size_t strs_hash_fn(const void *key, void *ctx)
-{
- const struct btf *btf = ctx;
- const char *strs = *btf->strs_data_ptr;
- const char *str = strs + (long)key;
-
- return str_hash(str);
-}
-
-static bool strs_hash_equal_fn(const void *key1, const void *key2, void *ctx)
-{
- const struct btf *btf = ctx;
- const char *strs = *btf->strs_data_ptr;
- const char *str1 = strs + (long)key1;
- const char *str2 = strs + (long)key2;
-
- return strcmp(str1, str2) == 0;
-}
-
static void btf_invalidate_raw_data(struct btf *btf)
{
if (btf->raw_data) {
@@ -1511,10 +1493,9 @@ static void btf_invalidate_raw_data(struct btf *btf)
*/
static int btf_ensure_modifiable(struct btf *btf)
{
- void *hdr, *types, *strs, *strs_end, *s;
- struct hashmap *hash = NULL;
- long off;
- int err;
+ void *hdr, *types;
+ struct strset *set = NULL;
+ int err = -ENOMEM;
if (btf_is_modifiable(btf)) {
/* any BTF modification invalidates raw_data */
@@ -1525,44 +1506,25 @@ static int btf_ensure_modifiable(struct btf *btf)
/* split raw data into three memory regions */
hdr = malloc(btf->hdr->hdr_len);
types = malloc(btf->hdr->type_len);
- strs = malloc(btf->hdr->str_len);
- if (!hdr || !types || !strs)
+ if (!hdr || !types)
goto err_out;
memcpy(hdr, btf->hdr, btf->hdr->hdr_len);
memcpy(types, btf->types_data, btf->hdr->type_len);
- memcpy(strs, btf->strs_data, btf->hdr->str_len);
-
- /* make hashmap below use btf->strs_data as a source of strings */
- btf->strs_data_ptr = &btf->strs_data;
/* build lookup index for all strings */
- hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, btf);
- if (IS_ERR(hash)) {
- err = PTR_ERR(hash);
- hash = NULL;
+ set = strset__new(BTF_MAX_STR_OFFSET, btf->strs_data, btf->hdr->str_len);
+ if (IS_ERR(set)) {
+ err = PTR_ERR(set);
goto err_out;
}
- strs_end = strs + btf->hdr->str_len;
- for (off = 0, s = strs; s < strs_end; off += strlen(s) + 1, s = strs + off) {
- /* hashmap__add() returns EEXIST if string with the same
- * content already is in the hash map
- */
- err = hashmap__add(hash, (void *)off, (void *)off);
- if (err == -EEXIST)
- continue; /* duplicate */
- if (err)
- goto err_out;
- }
-
/* only when everything was successful, update internal state */
btf->hdr = hdr;
btf->types_data = types;
btf->types_data_cap = btf->hdr->type_len;
- btf->strs_data = strs;
- btf->strs_data_cap = btf->hdr->str_len;
- btf->strs_hash = hash;
+ btf->strs_data = NULL;
+ btf->strs_set = set;
/* if BTF was created from scratch, all strings are guaranteed to be
* unique and deduplicated
*/
@@ -1577,17 +1539,10 @@ static int btf_ensure_modifiable(struct btf *btf)
return 0;
err_out:
- hashmap__free(hash);
+ strset__free(set);
free(hdr);
free(types);
- free(strs);
- return -ENOMEM;
-}
-
-static void *btf_add_str_mem(struct btf *btf, size_t add_sz)
-{
- return btf_add_mem(&btf->strs_data, &btf->strs_data_cap, 1,
- btf->hdr->str_len, BTF_MAX_STR_OFFSET, add_sz);
+ return err;
}
/* Find an offset in BTF string section that corresponds to a given string *s*.
@@ -1598,34 +1553,23 @@ static void *btf_add_str_mem(struct btf *btf, size_t add_sz)
*/
int btf__find_str(struct btf *btf, const char *s)
{
- long old_off, new_off, len;
- void *p;
+ int off;
if (btf->base_btf) {
- int ret;
-
- ret = btf__find_str(btf->base_btf, s);
- if (ret != -ENOENT)
- return ret;
+ off = btf__find_str(btf->base_btf, s);
+ if (off != -ENOENT)
+ return off;
}
/* BTF needs to be in a modifiable state to build string lookup index */
if (btf_ensure_modifiable(btf))
return -ENOMEM;
- /* see btf__add_str() for why we do this */
- len = strlen(s) + 1;
- p = btf_add_str_mem(btf, len);
- if (!p)
- return -ENOMEM;
-
- new_off = btf->hdr->str_len;
- memcpy(p, s, len);
+ off = strset__find_str(btf->strs_set, s);
+ if (off < 0)
+ return off;
- if (hashmap__find(btf->strs_hash, (void *)new_off, (void **)&old_off))
- return btf->start_str_off + old_off;
-
- return -ENOENT;
+ return btf->start_str_off + off;
}
/* Add a string s to the BTF string section.
@@ -1635,56 +1579,30 @@ int btf__find_str(struct btf *btf, const char *s)
*/
int btf__add_str(struct btf *btf, const char *s)
{
- long old_off, new_off, len;
- void *p;
- int err;
+ int off;
if (btf->base_btf) {
- int ret;
-
- ret = btf__find_str(btf->base_btf, s);
- if (ret != -ENOENT)
- return ret;
+ off = btf__find_str(btf->base_btf, s);
+ if (off != -ENOENT)
+ return off;
}
if (btf_ensure_modifiable(btf))
return -ENOMEM;
- /* Hashmap keys are always offsets within btf->strs_data, so to even
- * look up some string from the "outside", we need to first append it
- * at the end, so that it can be addressed with an offset. Luckily,
- * until btf->hdr->str_len is incremented, that string is just a piece
- * of garbage for the rest of BTF code, so no harm, no foul. On the
- * other hand, if the string is unique, it's already appended and
- * ready to be used, only a simple btf->hdr->str_len increment away.
- */
- len = strlen(s) + 1;
- p = btf_add_str_mem(btf, len);
- if (!p)
- return -ENOMEM;
+ off = strset__add_str(btf->strs_set, s);
+ if (off < 0)
+ return off;
- new_off = btf->hdr->str_len;
- memcpy(p, s, len);
+ btf->hdr->str_len = strset__data_size(btf->strs_set);
- /* Now attempt to add the string, but only if the string with the same
- * contents doesn't exist already (HASHMAP_ADD strategy). If such
- * string exists, we'll get its offset in old_off (that's old_key).
- */
- err = hashmap__insert(btf->strs_hash, (void *)new_off, (void *)new_off,
- HASHMAP_ADD, (const void **)&old_off, NULL);
- if (err == -EEXIST)
- return btf->start_str_off + old_off; /* duplicated string, return existing offset */
- if (err)
- return err;
-
- btf->hdr->str_len += len; /* new unique string, adjust data length */
- return btf->start_str_off + new_off;
+ return btf->start_str_off + off;
}
static void *btf_add_type_mem(struct btf *btf, size_t add_sz)
{
- return btf_add_mem(&btf->types_data, &btf->types_data_cap, 1,
- btf->hdr->type_len, UINT_MAX, add_sz);
+ return libbpf_add_mem(&btf->types_data, &btf->types_data_cap, 1,
+ btf->hdr->type_len, UINT_MAX, add_sz);
}
static __u32 btf_type_info(int kind, int vlen, int kflag)
@@ -1711,6 +1629,54 @@ static int btf_commit_type(struct btf *btf, int data_sz)
return btf->start_id + btf->nr_types - 1;
}
+struct btf_pipe {
+ const struct btf *src;
+ struct btf *dst;
+};
+
+static int btf_rewrite_str(__u32 *str_off, void *ctx)
+{
+ struct btf_pipe *p = ctx;
+ int off;
+
+ if (!*str_off) /* nothing to do for empty strings */
+ return 0;
+
+ off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off));
+ if (off < 0)
+ return off;
+
+ *str_off = off;
+ return 0;
+}
+
+int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type)
+{
+ struct btf_pipe p = { .src = src_btf, .dst = btf };
+ struct btf_type *t;
+ int sz, err;
+
+ sz = btf_type_size(src_type);
+ if (sz < 0)
+ return sz;
+
+ /* deconstruct BTF, if necessary, and invalidate raw_data */
+ if (btf_ensure_modifiable(btf))
+ return -ENOMEM;
+
+ t = btf_add_type_mem(btf, sz);
+ if (!t)
+ return -ENOMEM;
+
+ memcpy(t, src_type, sz);
+
+ err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
+ if (err)
+ return err;
+
+ return btf_commit_type(btf, sz);
+}
+
/*
* Append new BTF_KIND_INT type with:
* - *name* - non-empty, non-NULL type name;
@@ -3016,10 +2982,7 @@ struct btf_dedup {
/* Various option modifying behavior of algorithm */
struct btf_dedup_opts opts;
/* temporary strings deduplication state */
- void *strs_data;
- size_t strs_cap;
- size_t strs_len;
- struct hashmap* strs_hash;
+ struct strset *strs_set;
};
static long hash_combine(long h, long value)
@@ -3155,95 +3118,28 @@ done:
return d;
}
-typedef int (*str_off_fn_t)(__u32 *str_off_ptr, void *ctx);
-
/*
* Iterate over all possible places in .BTF and .BTF.ext that can reference
* string and pass pointer to it to a provided callback `fn`.
*/
-static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
+static int btf_for_each_str_off(struct btf_dedup *d, str_off_visit_fn fn, void *ctx)
{
- void *line_data_cur, *line_data_end;
- int i, j, r, rec_size;
- struct btf_type *t;
+ int i, r;
for (i = 0; i < d->btf->nr_types; i++) {
- t = btf_type_by_id(d->btf, d->btf->start_id + i);
- r = fn(&t->name_off, ctx);
+ struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i);
+
+ r = btf_type_visit_str_offs(t, fn, ctx);
if (r)
return r;
-
- switch (btf_kind(t)) {
- case BTF_KIND_STRUCT:
- case BTF_KIND_UNION: {
- struct btf_member *m = btf_members(t);
- __u16 vlen = btf_vlen(t);
-
- for (j = 0; j < vlen; j++) {
- r = fn(&m->name_off, ctx);
- if (r)
- return r;
- m++;
- }
- break;
- }
- case BTF_KIND_ENUM: {
- struct btf_enum *m = btf_enum(t);
- __u16 vlen = btf_vlen(t);
-
- for (j = 0; j < vlen; j++) {
- r = fn(&m->name_off, ctx);
- if (r)
- return r;
- m++;
- }
- break;
- }
- case BTF_KIND_FUNC_PROTO: {
- struct btf_param *m = btf_params(t);
- __u16 vlen = btf_vlen(t);
-
- for (j = 0; j < vlen; j++) {
- r = fn(&m->name_off, ctx);
- if (r)
- return r;
- m++;
- }
- break;
- }
- default:
- break;
- }
}
if (!d->btf_ext)
return 0;
- line_data_cur = d->btf_ext->line_info.info;
- line_data_end = d->btf_ext->line_info.info + d->btf_ext->line_info.len;
- rec_size = d->btf_ext->line_info.rec_size;
-
- while (line_data_cur < line_data_end) {
- struct btf_ext_info_sec *sec = line_data_cur;
- struct bpf_line_info_min *line_info;
- __u32 num_info = sec->num_info;
-
- r = fn(&sec->sec_name_off, ctx);
- if (r)
- return r;
-
- line_data_cur += sizeof(struct btf_ext_info_sec);
- for (i = 0; i < num_info; i++) {
- line_info = line_data_cur;
- r = fn(&line_info->file_name_off, ctx);
- if (r)
- return r;
- r = fn(&line_info->line_off, ctx);
- if (r)
- return r;
- line_data_cur += rec_size;
- }
- }
+ r = btf_ext_visit_str_offs(d->btf_ext, fn, ctx);
+ if (r)
+ return r;
return 0;
}
@@ -3252,10 +3148,8 @@ static int strs_dedup_remap_str_off(__u32 *str_off_ptr, void *ctx)
{
struct btf_dedup *d = ctx;
__u32 str_off = *str_off_ptr;
- long old_off, new_off, len;
const char *s;
- void *p;
- int err;
+ int off, err;
/* don't touch empty string or string in main BTF */
if (str_off == 0 || str_off < d->btf->start_str_off)
@@ -3272,29 +3166,11 @@ static int strs_dedup_remap_str_off(__u32 *str_off_ptr, void *ctx)
return err;
}
- len = strlen(s) + 1;
-
- new_off = d->strs_len;
- p = btf_add_mem(&d->strs_data, &d->strs_cap, 1, new_off, BTF_MAX_STR_OFFSET, len);
- if (!p)
- return -ENOMEM;
-
- memcpy(p, s, len);
+ off = strset__add_str(d->strs_set, s);
+ if (off < 0)
+ return off;
- /* Now attempt to add the string, but only if the string with the same
- * contents doesn't exist already (HASHMAP_ADD strategy). If such
- * string exists, we'll get its offset in old_off (that's old_key).
- */
- err = hashmap__insert(d->strs_hash, (void *)new_off, (void *)new_off,
- HASHMAP_ADD, (const void **)&old_off, NULL);
- if (err == -EEXIST) {
- *str_off_ptr = d->btf->start_str_off + old_off;
- } else if (err) {
- return err;
- } else {
- *str_off_ptr = d->btf->start_str_off + new_off;
- d->strs_len += len;
- }
+ *str_off_ptr = d->btf->start_str_off + off;
return 0;
}
@@ -3311,39 +3187,23 @@ static int strs_dedup_remap_str_off(__u32 *str_off_ptr, void *ctx)
*/
static int btf_dedup_strings(struct btf_dedup *d)
{
- char *s;
int err;
if (d->btf->strs_deduped)
return 0;
- /* temporarily switch to use btf_dedup's strs_data for strings for hash
- * functions; later we'll just transfer hashmap to struct btf as is,
- * along the strs_data
- */
- d->btf->strs_data_ptr = &d->strs_data;
-
- d->strs_hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, d->btf);
- if (IS_ERR(d->strs_hash)) {
- err = PTR_ERR(d->strs_hash);
- d->strs_hash = NULL;
+ d->strs_set = strset__new(BTF_MAX_STR_OFFSET, NULL, 0);
+ if (IS_ERR(d->strs_set)) {
+ err = PTR_ERR(d->strs_set);
goto err_out;
}
if (!d->btf->base_btf) {
- s = btf_add_mem(&d->strs_data, &d->strs_cap, 1, d->strs_len, BTF_MAX_STR_OFFSET, 1);
- if (!s)
- return -ENOMEM;
- /* initial empty string */
- s[0] = 0;
- d->strs_len = 1;
-
/* insert empty string; we won't be looking it up during strings
* dedup, but it's good to have it for generic BTF string lookups
*/
- err = hashmap__insert(d->strs_hash, (void *)0, (void *)0,
- HASHMAP_ADD, NULL, NULL);
- if (err)
+ err = strset__add_str(d->strs_set, "");
+ if (err < 0)
goto err_out;
}
@@ -3353,28 +3213,16 @@ static int btf_dedup_strings(struct btf_dedup *d)
goto err_out;
/* replace BTF string data and hash with deduped ones */
- free(d->btf->strs_data);
- hashmap__free(d->btf->strs_hash);
- d->btf->strs_data = d->strs_data;
- d->btf->strs_data_cap = d->strs_cap;
- d->btf->hdr->str_len = d->strs_len;
- d->btf->strs_hash = d->strs_hash;
- /* now point strs_data_ptr back to btf->strs_data */
- d->btf->strs_data_ptr = &d->btf->strs_data;
-
- d->strs_data = d->strs_hash = NULL;
- d->strs_len = d->strs_cap = 0;
+ strset__free(d->btf->strs_set);
+ d->btf->hdr->str_len = strset__data_size(d->strs_set);
+ d->btf->strs_set = d->strs_set;
+ d->strs_set = NULL;
d->btf->strs_deduped = true;
return 0;
err_out:
- free(d->strs_data);
- hashmap__free(d->strs_hash);
- d->strs_data = d->strs_hash = NULL;
- d->strs_len = d->strs_cap = 0;
-
- /* restore strings pointer for existing d->btf->strs_hash back */
- d->btf->strs_data_ptr = &d->strs_data;
+ strset__free(d->strs_set);
+ d->strs_set = NULL;
return err;
}
@@ -4498,15 +4346,18 @@ static int btf_dedup_compact_types(struct btf_dedup *d)
* then mapping it to a deduplicated type ID, stored in btf_dedup->hypot_map,
* which is populated during compaction phase.
*/
-static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id)
+static int btf_dedup_remap_type_id(__u32 *type_id, void *ctx)
{
+ struct btf_dedup *d = ctx;
__u32 resolved_type_id, new_type_id;
- resolved_type_id = resolve_type_id(d, type_id);
+ resolved_type_id = resolve_type_id(d, *type_id);
new_type_id = d->hypot_map[resolved_type_id];
if (new_type_id > BTF_MAX_NR_TYPES)
return -EINVAL;
- return new_type_id;
+
+ *type_id = new_type_id;
+ return 0;
}
/*
@@ -4519,109 +4370,25 @@ static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id)
* referenced from any BTF type (e.g., struct fields, func proto args, etc) to
* their final deduped type IDs.
*/
-static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
+static int btf_dedup_remap_types(struct btf_dedup *d)
{
- struct btf_type *t = btf_type_by_id(d->btf, type_id);
int i, r;
- switch (btf_kind(t)) {
- case BTF_KIND_INT:
- case BTF_KIND_ENUM:
- case BTF_KIND_FLOAT:
- break;
-
- case BTF_KIND_FWD:
- case BTF_KIND_CONST:
- case BTF_KIND_VOLATILE:
- case BTF_KIND_RESTRICT:
- case BTF_KIND_PTR:
- case BTF_KIND_TYPEDEF:
- case BTF_KIND_FUNC:
- case BTF_KIND_VAR:
- r = btf_dedup_remap_type_id(d, t->type);
- if (r < 0)
- return r;
- t->type = r;
- break;
-
- case BTF_KIND_ARRAY: {
- struct btf_array *arr_info = btf_array(t);
-
- r = btf_dedup_remap_type_id(d, arr_info->type);
- if (r < 0)
- return r;
- arr_info->type = r;
- r = btf_dedup_remap_type_id(d, arr_info->index_type);
- if (r < 0)
- return r;
- arr_info->index_type = r;
- break;
- }
-
- case BTF_KIND_STRUCT:
- case BTF_KIND_UNION: {
- struct btf_member *member = btf_members(t);
- __u16 vlen = btf_vlen(t);
-
- for (i = 0; i < vlen; i++) {
- r = btf_dedup_remap_type_id(d, member->type);
- if (r < 0)
- return r;
- member->type = r;
- member++;
- }
- break;
- }
-
- case BTF_KIND_FUNC_PROTO: {
- struct btf_param *param = btf_params(t);
- __u16 vlen = btf_vlen(t);
+ for (i = 0; i < d->btf->nr_types; i++) {
+ struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i);
- r = btf_dedup_remap_type_id(d, t->type);
- if (r < 0)
+ r = btf_type_visit_type_ids(t, btf_dedup_remap_type_id, d);
+ if (r)
return r;
- t->type = r;
-
- for (i = 0; i < vlen; i++) {
- r = btf_dedup_remap_type_id(d, param->type);
- if (r < 0)
- return r;
- param->type = r;
- param++;
- }
- break;
- }
-
- case BTF_KIND_DATASEC: {
- struct btf_var_secinfo *var = btf_var_secinfos(t);
- __u16 vlen = btf_vlen(t);
-
- for (i = 0; i < vlen; i++) {
- r = btf_dedup_remap_type_id(d, var->type);
- if (r < 0)
- return r;
- var->type = r;
- var++;
- }
- break;
- }
-
- default:
- return -EINVAL;
}
- return 0;
-}
+ if (!d->btf_ext)
+ return 0;
-static int btf_dedup_remap_types(struct btf_dedup *d)
-{
- int i, r;
+ r = btf_ext_visit_type_ids(d->btf_ext, btf_dedup_remap_type_id, d);
+ if (r)
+ return r;
- for (i = 0; i < d->btf->nr_types; i++) {
- r = btf_dedup_remap_type(d, d->btf->start_id + i);
- if (r < 0)
- return r;
- }
return 0;
}
@@ -4675,3 +4442,200 @@ struct btf *libbpf_find_kernel_btf(void)
pr_warn("failed to find valid kernel BTF\n");
return ERR_PTR(-ESRCH);
}
+
+int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx)
+{
+ int i, n, err;
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_INT:
+ case BTF_KIND_FLOAT:
+ case BTF_KIND_ENUM:
+ return 0;
+
+ case BTF_KIND_FWD:
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_PTR:
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_FUNC:
+ case BTF_KIND_VAR:
+ return visit(&t->type, ctx);
+
+ case BTF_KIND_ARRAY: {
+ struct btf_array *a = btf_array(t);
+
+ err = visit(&a->type, ctx);
+ err = err ?: visit(&a->index_type, ctx);
+ return err;
+ }
+
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ struct btf_member *m = btf_members(t);
+
+ for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
+ err = visit(&m->type, ctx);
+ if (err)
+ return err;
+ }
+ return 0;
+ }
+
+ case BTF_KIND_FUNC_PROTO: {
+ struct btf_param *m = btf_params(t);
+
+ err = visit(&t->type, ctx);
+ if (err)
+ return err;
+ for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
+ err = visit(&m->type, ctx);
+ if (err)
+ return err;
+ }
+ return 0;
+ }
+
+ case BTF_KIND_DATASEC: {
+ struct btf_var_secinfo *m = btf_var_secinfos(t);
+
+ for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
+ err = visit(&m->type, ctx);
+ if (err)
+ return err;
+ }
+ return 0;
+ }
+
+ default:
+ return -EINVAL;
+ }
+}
+
+int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx)
+{
+ int i, n, err;
+
+ err = visit(&t->name_off, ctx);
+ if (err)
+ return err;
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ struct btf_member *m = btf_members(t);
+
+ for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
+ err = visit(&m->name_off, ctx);
+ if (err)
+ return err;
+ }
+ break;
+ }
+ case BTF_KIND_ENUM: {
+ struct btf_enum *m = btf_enum(t);
+
+ for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
+ err = visit(&m->name_off, ctx);
+ if (err)
+ return err;
+ }
+ break;
+ }
+ case BTF_KIND_FUNC_PROTO: {
+ struct btf_param *m = btf_params(t);
+
+ for (i = 0, n = btf_vlen(t); i < n; i++, m++) {
+ err = visit(&m->name_off, ctx);
+ if (err)
+ return err;
+ }
+ break;
+ }
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx)
+{
+ const struct btf_ext_info *seg;
+ struct btf_ext_info_sec *sec;
+ int i, err;
+
+ seg = &btf_ext->func_info;
+ for_each_btf_ext_sec(seg, sec) {
+ struct bpf_func_info_min *rec;
+
+ for_each_btf_ext_rec(seg, sec, i, rec) {
+ err = visit(&rec->type_id, ctx);
+ if (err < 0)
+ return err;
+ }
+ }
+
+ seg = &btf_ext->core_relo_info;
+ for_each_btf_ext_sec(seg, sec) {
+ struct bpf_core_relo *rec;
+
+ for_each_btf_ext_rec(seg, sec, i, rec) {
+ err = visit(&rec->type_id, ctx);
+ if (err < 0)
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx)
+{
+ const struct btf_ext_info *seg;
+ struct btf_ext_info_sec *sec;
+ int i, err;
+
+ seg = &btf_ext->func_info;
+ for_each_btf_ext_sec(seg, sec) {
+ err = visit(&sec->sec_name_off, ctx);
+ if (err)
+ return err;
+ }
+
+ seg = &btf_ext->line_info;
+ for_each_btf_ext_sec(seg, sec) {
+ struct bpf_line_info_min *rec;
+
+ err = visit(&sec->sec_name_off, ctx);
+ if (err)
+ return err;
+
+ for_each_btf_ext_rec(seg, sec, i, rec) {
+ err = visit(&rec->file_name_off, ctx);
+ if (err)
+ return err;
+ err = visit(&rec->line_off, ctx);
+ if (err)
+ return err;
+ }
+ }
+
+ seg = &btf_ext->core_relo_info;
+ for_each_btf_ext_sec(seg, sec) {
+ struct bpf_core_relo *rec;
+
+ err = visit(&sec->sec_name_off, ctx);
+ if (err)
+ return err;
+
+ for_each_btf_ext_rec(seg, sec, i, rec) {
+ err = visit(&rec->access_str_off, ctx);
+ if (err)
+ return err;
+ }
+ }
+
+ return 0;
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 029a9cfc8c2d..b54f1c3ebd57 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -93,6 +93,8 @@ LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
+LIBBPF_API int btf__add_type(struct btf *btf, const struct btf *src_btf,
+ const struct btf_type *src_type);
LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding);
LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz);
@@ -174,6 +176,7 @@ struct btf_dump_emit_type_decl_opts {
int indent_level;
/* strip all the const/volatile/restrict mods */
bool strip_mods;
+ size_t :0;
};
#define btf_dump_emit_type_decl_opts__last_field strip_mods
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 5e957fcceee6..5e2809d685bf 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -166,11 +166,11 @@ static int btf_dump_resize(struct btf_dump *d)
if (last_id <= d->last_id)
return 0;
- if (btf_ensure_mem((void **)&d->type_states, &d->type_states_cap,
- sizeof(*d->type_states), last_id + 1))
+ if (libbpf_ensure_mem((void **)&d->type_states, &d->type_states_cap,
+ sizeof(*d->type_states), last_id + 1))
return -ENOMEM;
- if (btf_ensure_mem((void **)&d->cached_names, &d->cached_names_cap,
- sizeof(*d->cached_names), last_id + 1))
+ if (libbpf_ensure_mem((void **)&d->cached_names, &d->cached_names_cap,
+ sizeof(*d->cached_names), last_id + 1))
return -ENOMEM;
if (d->last_id == 0) {
@@ -464,7 +464,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
return err;
case BTF_KIND_ARRAY:
- return btf_dump_order_type(d, btf_array(t)->type, through_ptr);
+ return btf_dump_order_type(d, btf_array(t)->type, false);
case BTF_KIND_STRUCT:
case BTF_KIND_UNION: {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2f351d3ad3e7..7aad78dbb4b4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -55,10 +55,6 @@
#include "libbpf_internal.h"
#include "hashmap.h"
-#ifndef EM_BPF
-#define EM_BPF 247
-#endif
-
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC 0xcafe4a11
#endif
@@ -189,7 +185,8 @@ enum reloc_type {
RELO_LD64,
RELO_CALL,
RELO_DATA,
- RELO_EXTERN,
+ RELO_EXTERN_VAR,
+ RELO_EXTERN_FUNC,
RELO_SUBPROG_ADDR,
};
@@ -577,14 +574,19 @@ static bool insn_is_subprog_call(const struct bpf_insn *insn)
insn->off == 0;
}
-static bool is_ldimm64(struct bpf_insn *insn)
+static bool is_ldimm64_insn(struct bpf_insn *insn)
{
return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
}
+static bool is_call_insn(const struct bpf_insn *insn)
+{
+ return insn->code == (BPF_JMP | BPF_CALL);
+}
+
static bool insn_is_pseudo_func(struct bpf_insn *insn)
{
- return is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
+ return is_ldimm64_insn(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
}
static int
@@ -1134,11 +1136,6 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
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;
@@ -1194,7 +1191,8 @@ static int bpf_object__elf_init(struct bpf_object *obj)
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));
- return -LIBBPF_ERRNO__FORMAT;
+ err = -LIBBPF_ERRNO__FORMAT;
+ goto errout;
}
/* Old LLVM set e_machine to EM_NONE */
@@ -1929,9 +1927,9 @@ resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id)
return btf_is_func_proto(t) ? t : NULL;
}
-static const char *btf_kind_str(const struct btf_type *t)
+static const char *__btf_kind_str(__u16 kind)
{
- switch (btf_kind(t)) {
+ switch (kind) {
case BTF_KIND_UNKN: return "void";
case BTF_KIND_INT: return "int";
case BTF_KIND_PTR: return "ptr";
@@ -1953,6 +1951,16 @@ static const char *btf_kind_str(const struct btf_type *t)
}
}
+static const char *btf_kind_str(const struct btf_type *t)
+{
+ return __btf_kind_str(btf_kind(t));
+}
+
+static enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
+{
+ return (enum btf_func_linkage)BTF_INFO_VLEN(t->info);
+}
+
/*
* Fetch integer attribute of BTF map definition. Such attributes are
* represented using a pointer to an array, in which dimensionality of array
@@ -2807,7 +2815,7 @@ static bool ignore_elf_section(GElf_Shdr *hdr, const char *name)
return true;
/* ignore .llvm_addrsig section as well */
- if (hdr->sh_type == 0x6FFF4C03 /* SHT_LLVM_ADDRSIG */)
+ if (hdr->sh_type == SHT_LLVM_ADDRSIG)
return true;
/* no subprograms will lead to an empty .text section, ignore it */
@@ -3017,7 +3025,7 @@ static bool sym_is_subprog(const GElf_Sym *sym, int text_shndx)
static int find_extern_btf_id(const struct btf *btf, const char *ext_name)
{
const struct btf_type *t;
- const char *var_name;
+ const char *tname;
int i, n;
if (!btf)
@@ -3027,14 +3035,18 @@ static int find_extern_btf_id(const struct btf *btf, const char *ext_name)
for (i = 1; i <= n; i++) {
t = btf__type_by_id(btf, i);
- if (!btf_is_var(t))
+ if (!btf_is_var(t) && !btf_is_func(t))
continue;
- var_name = btf__name_by_offset(btf, t->name_off);
- if (strcmp(var_name, ext_name))
+ tname = btf__name_by_offset(btf, t->name_off);
+ if (strcmp(tname, ext_name))
continue;
- if (btf_var(t)->linkage != BTF_VAR_GLOBAL_EXTERN)
+ if (btf_is_var(t) &&
+ btf_var(t)->linkage != BTF_VAR_GLOBAL_EXTERN)
+ return -EINVAL;
+
+ if (btf_is_func(t) && btf_func_linkage(t) != BTF_FUNC_EXTERN)
return -EINVAL;
return i;
@@ -3147,12 +3159,48 @@ static int find_int_btf_id(const struct btf *btf)
return 0;
}
+static int add_dummy_ksym_var(struct btf *btf)
+{
+ int i, int_btf_id, sec_btf_id, dummy_var_btf_id;
+ const struct btf_var_secinfo *vs;
+ const struct btf_type *sec;
+
+ sec_btf_id = btf__find_by_name_kind(btf, KSYMS_SEC,
+ BTF_KIND_DATASEC);
+ if (sec_btf_id < 0)
+ return 0;
+
+ sec = btf__type_by_id(btf, sec_btf_id);
+ vs = btf_var_secinfos(sec);
+ for (i = 0; i < btf_vlen(sec); i++, vs++) {
+ const struct btf_type *vt;
+
+ vt = btf__type_by_id(btf, vs->type);
+ if (btf_is_func(vt))
+ break;
+ }
+
+ /* No func in ksyms sec. No need to add dummy var. */
+ if (i == btf_vlen(sec))
+ return 0;
+
+ int_btf_id = find_int_btf_id(btf);
+ dummy_var_btf_id = btf__add_var(btf,
+ "dummy_ksym",
+ BTF_VAR_GLOBAL_ALLOCATED,
+ int_btf_id);
+ if (dummy_var_btf_id < 0)
+ pr_warn("cannot create a dummy_ksym var\n");
+
+ return dummy_var_btf_id;
+}
+
static int bpf_object__collect_externs(struct bpf_object *obj)
{
struct btf_type *sec, *kcfg_sec = NULL, *ksym_sec = NULL;
const struct btf_type *t;
struct extern_desc *ext;
- int i, n, off;
+ int i, n, off, dummy_var_btf_id;
const char *ext_name, *sec_name;
Elf_Scn *scn;
GElf_Shdr sh;
@@ -3164,6 +3212,10 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
if (elf_sec_hdr(obj, scn, &sh))
return -LIBBPF_ERRNO__FORMAT;
+ dummy_var_btf_id = add_dummy_ksym_var(obj->btf);
+ if (dummy_var_btf_id < 0)
+ return dummy_var_btf_id;
+
n = sh.sh_size / sh.sh_entsize;
pr_debug("looking for externs among %d symbols...\n", n);
@@ -3208,6 +3260,11 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
sec_name = btf__name_by_offset(obj->btf, sec->name_off);
if (strcmp(sec_name, KCONFIG_SEC) == 0) {
+ if (btf_is_func(t)) {
+ pr_warn("extern function %s is unsupported under %s section\n",
+ ext->name, KCONFIG_SEC);
+ return -ENOTSUP;
+ }
kcfg_sec = sec;
ext->type = EXT_KCFG;
ext->kcfg.sz = btf__resolve_size(obj->btf, t->type);
@@ -3229,6 +3286,11 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
return -ENOTSUP;
}
} else if (strcmp(sec_name, KSYMS_SEC) == 0) {
+ if (btf_is_func(t) && ext->is_weak) {
+ pr_warn("extern weak function %s is unsupported\n",
+ ext->name);
+ return -ENOTSUP;
+ }
ksym_sec = sec;
ext->type = EXT_KSYM;
skip_mods_and_typedefs(obj->btf, t->type,
@@ -3255,7 +3317,14 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
* extern variables in DATASEC
*/
int int_btf_id = find_int_btf_id(obj->btf);
+ /* For extern function, a dummy_var added earlier
+ * will be used to replace the vs->type and
+ * its name string will be used to refill
+ * the missing param's name.
+ */
+ const struct btf_type *dummy_var;
+ dummy_var = btf__type_by_id(obj->btf, dummy_var_btf_id);
for (i = 0; i < obj->nr_extern; i++) {
ext = &obj->externs[i];
if (ext->type != EXT_KSYM)
@@ -3274,12 +3343,32 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
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);
+ pr_warn("failed to find extern definition for BTF %s '%s'\n",
+ btf_kind_str(vt), ext_name);
return -ESRCH;
}
- btf_var(vt)->linkage = BTF_VAR_GLOBAL_ALLOCATED;
- vt->type = int_btf_id;
+ if (btf_is_func(vt)) {
+ const struct btf_type *func_proto;
+ struct btf_param *param;
+ int j;
+
+ func_proto = btf__type_by_id(obj->btf,
+ vt->type);
+ param = btf_params(func_proto);
+ /* Reuse the dummy_var string if the
+ * func proto does not have param name.
+ */
+ for (j = 0; j < btf_vlen(func_proto); j++)
+ if (param[j].type && !param[j].name_off)
+ param[j].name_off =
+ dummy_var->name_off;
+ vs->type = dummy_var_btf_id;
+ vt->info &= ~0xffff;
+ vt->info |= BTF_FUNC_GLOBAL;
+ } else {
+ btf_var(vt)->linkage = BTF_VAR_GLOBAL_ALLOCATED;
+ vt->type = int_btf_id;
+ }
vs->offset = off;
vs->size = sizeof(int);
}
@@ -3411,31 +3500,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
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 (!is_ldimm64(insn)) {
+ if (!is_call_insn(insn) && !is_ldimm64_insn(insn)) {
pr_warn("prog '%s': invalid relo against '%s' for insns[%d].code 0x%x\n",
prog->name, sym_name, insn_idx, insn->code);
return -LIBBPF_ERRNO__RELOC;
@@ -3458,12 +3523,39 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
}
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;
+ if (insn->code == (BPF_JMP | BPF_CALL))
+ reloc_desc->type = RELO_EXTERN_FUNC;
+ else
+ reloc_desc->type = RELO_EXTERN_VAR;
reloc_desc->insn_idx = insn_idx;
reloc_desc->sym_off = i; /* sym_off stores extern index */
return 0;
}
+ /* sub-program call relocation */
+ if (is_call_insn(insn)) {
+ if (insn->src_reg != BPF_PSEUDO_CALL) {
+ pr_warn("prog '%s': incorrect bpf_call opcode\n", prog->name);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+ /* text_shndx can be 0, if no default "main" program exists */
+ if (!shdr_idx || shdr_idx != obj->efile.text_shndx) {
+ sym_sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, shdr_idx));
+ pr_warn("prog '%s': bad call relo against '%s' in section '%s'\n",
+ prog->name, sym_name, sym_sec_name);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+ if (sym->st_value % BPF_INSN_SZ) {
+ pr_warn("prog '%s': bad call relo against '%s' at offset %zu\n",
+ prog->name, sym_name, (size_t)sym->st_value);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+ reloc_desc->type = RELO_CALL;
+ reloc_desc->insn_idx = insn_idx;
+ reloc_desc->sym_off = sym->st_value;
+ return 0;
+ }
+
if (!shdr_idx || shdr_idx >= SHN_LORESERVE) {
pr_warn("prog '%s': invalid relo against '%s' in special section 0x%x; forgot to initialize global var?..\n",
prog->name, sym_name, shdr_idx);
@@ -4867,8 +4959,8 @@ static int load_module_btfs(struct bpf_object *obj)
goto err_out;
}
- err = btf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap,
- sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
+ err = libbpf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap,
+ sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
if (err)
goto err_out;
@@ -5703,7 +5795,7 @@ poison:
/* poison second part of ldimm64 to avoid confusing error from
* verifier about "unknown opcode 00"
*/
- if (is_ldimm64(insn))
+ if (is_ldimm64_insn(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;
@@ -5779,7 +5871,7 @@ poison:
case BPF_LD: {
__u64 imm;
- if (!is_ldimm64(insn) ||
+ if (!is_ldimm64_insn(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 ||
@@ -6221,7 +6313,7 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
insn[0].imm = obj->maps[relo->map_idx].fd;
relo->processed = true;
break;
- case RELO_EXTERN:
+ case RELO_EXTERN_VAR:
ext = &obj->externs[relo->sym_off];
if (ext->type == EXT_KCFG) {
insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
@@ -6239,6 +6331,12 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
}
relo->processed = true;
break;
+ case RELO_EXTERN_FUNC:
+ ext = &obj->externs[relo->sym_off];
+ insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL;
+ insn[0].imm = ext->ksym.kernel_btf_id;
+ relo->processed = true;
+ break;
case RELO_SUBPROG_ADDR:
insn[0].src_reg = BPF_PSEUDO_FUNC;
/* will be handled as a follow up pass */
@@ -7359,6 +7457,7 @@ static int bpf_object__read_kallsyms_file(struct bpf_object *obj)
{
char sym_type, sym_name[500];
unsigned long long sym_addr;
+ const struct btf_type *t;
struct extern_desc *ext;
int ret, err = 0;
FILE *f;
@@ -7385,6 +7484,10 @@ static int bpf_object__read_kallsyms_file(struct bpf_object *obj)
if (!ext || ext->type != EXT_KSYM)
continue;
+ t = btf__type_by_id(obj->btf, ext->btf_id);
+ if (!btf_is_var(t))
+ 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);
@@ -7403,75 +7506,151 @@ out:
return err;
}
-static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
+static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
+ __u16 kind, struct btf **res_btf,
+ int *res_btf_fd)
{
- struct extern_desc *ext;
+ int i, id, btf_fd, err;
struct btf *btf;
- int i, j, id, btf_fd, err;
- 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;
+ btf = obj->btf_vmlinux;
+ btf_fd = 0;
+ id = btf__find_by_name_kind(btf, ksym_name, kind);
- btf = obj->btf_vmlinux;
- btf_fd = 0;
- id = btf__find_by_name_kind(btf, ext->name, BTF_KIND_VAR);
- if (id == -ENOENT) {
- err = load_module_btfs(obj);
- if (err)
- return err;
+ if (id == -ENOENT) {
+ err = load_module_btfs(obj);
+ if (err)
+ return err;
- for (j = 0; j < obj->btf_module_cnt; j++) {
- btf = obj->btf_modules[j].btf;
- /* we assume module BTF FD is always >0 */
- btf_fd = obj->btf_modules[j].fd;
- id = btf__find_by_name_kind(btf, ext->name, BTF_KIND_VAR);
- if (id != -ENOENT)
- break;
- }
- }
- if (id <= 0) {
- pr_warn("extern (ksym) '%s': failed to find BTF ID in kernel BTF(s).\n",
- ext->name);
- return -ESRCH;
+ for (i = 0; i < obj->btf_module_cnt; i++) {
+ btf = obj->btf_modules[i].btf;
+ /* we assume module BTF FD is always >0 */
+ btf_fd = obj->btf_modules[i].fd;
+ id = btf__find_by_name_kind(btf, ksym_name, kind);
+ if (id != -ENOENT)
+ break;
}
+ }
+ if (id <= 0) {
+ pr_warn("extern (%s ksym) '%s': failed to find BTF ID in kernel BTF(s).\n",
+ __btf_kind_str(kind), ksym_name);
+ return -ESRCH;
+ }
- /* find local type_id */
- local_type_id = ext->ksym.type_id;
+ *res_btf = btf;
+ *res_btf_fd = btf_fd;
+ return id;
+}
- /* find target type_id */
- targ_var = btf__type_by_id(btf, id);
- targ_var_name = btf__name_by_offset(btf, targ_var->name_off);
- targ_type = skip_mods_and_typedefs(btf, targ_var->type, &targ_type_id);
+static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj,
+ struct extern_desc *ext)
+{
+ const struct btf_type *targ_var, *targ_type;
+ __u32 targ_type_id, local_type_id;
+ const char *targ_var_name;
+ int id, btf_fd = 0, err;
+ struct btf *btf = NULL;
- ret = bpf_core_types_are_compat(obj->btf, local_type_id,
- btf, targ_type_id);
- if (ret <= 0) {
- const struct btf_type *local_type;
- const char *targ_name, *local_name;
+ id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &btf_fd);
+ if (id < 0)
+ return id;
- local_type = btf__type_by_id(obj->btf, local_type_id);
- local_name = btf__name_by_offset(obj->btf, local_type->name_off);
- targ_name = btf__name_by_offset(btf, targ_type->name_off);
+ /* find local type_id */
+ local_type_id = ext->ksym.type_id;
- 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;
- }
+ /* find target type_id */
+ targ_var = btf__type_by_id(btf, id);
+ targ_var_name = btf__name_by_offset(btf, targ_var->name_off);
+ targ_type = skip_mods_and_typedefs(btf, targ_var->type, &targ_type_id);
- ext->is_set = true;
- ext->ksym.kernel_btf_obj_fd = btf_fd;
- ext->ksym.kernel_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);
+ err = bpf_core_types_are_compat(obj->btf, local_type_id,
+ btf, targ_type_id);
+ if (err <= 0) {
+ const struct btf_type *local_type;
+ const char *targ_name, *local_name;
+
+ local_type = btf__type_by_id(obj->btf, local_type_id);
+ local_name = btf__name_by_offset(obj->btf, local_type->name_off);
+ targ_name = btf__name_by_offset(btf, targ_type->name_off);
+
+ pr_warn("extern (var ksym) '%s': incompatible types, expected [%d] %s %s, but kernel has [%d] %s %s\n",
+ ext->name, local_type_id,
+ btf_kind_str(local_type), local_name, targ_type_id,
+ btf_kind_str(targ_type), targ_name);
+ return -EINVAL;
+ }
+
+ ext->is_set = true;
+ ext->ksym.kernel_btf_obj_fd = btf_fd;
+ ext->ksym.kernel_btf_id = id;
+ pr_debug("extern (var ksym) '%s': resolved to [%d] %s %s\n",
+ ext->name, id, btf_kind_str(targ_var), targ_var_name);
+
+ return 0;
+}
+
+static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
+ struct extern_desc *ext)
+{
+ int local_func_proto_id, kfunc_proto_id, kfunc_id;
+ const struct btf_type *kern_func;
+ struct btf *kern_btf = NULL;
+ int ret, kern_btf_fd = 0;
+
+ local_func_proto_id = ext->ksym.type_id;
+
+ kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC,
+ &kern_btf, &kern_btf_fd);
+ if (kfunc_id < 0) {
+ pr_warn("extern (func ksym) '%s': not found in kernel BTF\n",
+ ext->name);
+ return kfunc_id;
+ }
+
+ if (kern_btf != obj->btf_vmlinux) {
+ pr_warn("extern (func ksym) '%s': function in kernel module is not supported\n",
+ ext->name);
+ return -ENOTSUP;
+ }
+
+ kern_func = btf__type_by_id(kern_btf, kfunc_id);
+ kfunc_proto_id = kern_func->type;
+
+ ret = bpf_core_types_are_compat(obj->btf, local_func_proto_id,
+ kern_btf, kfunc_proto_id);
+ if (ret <= 0) {
+ pr_warn("extern (func ksym) '%s': func_proto [%d] incompatible with kernel [%d]\n",
+ ext->name, local_func_proto_id, kfunc_proto_id);
+ return -EINVAL;
+ }
+
+ ext->is_set = true;
+ ext->ksym.kernel_btf_obj_fd = kern_btf_fd;
+ ext->ksym.kernel_btf_id = kfunc_id;
+ pr_debug("extern (func ksym) '%s': resolved to kernel [%d]\n",
+ ext->name, kfunc_id);
+
+ return 0;
+}
+
+static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
+{
+ const struct btf_type *t;
+ struct extern_desc *ext;
+ int i, err;
+
+ for (i = 0; i < obj->nr_extern; i++) {
+ ext = &obj->externs[i];
+ if (ext->type != EXT_KSYM || !ext->ksym.type_id)
+ continue;
+
+ t = btf__type_by_id(obj->btf, ext->btf_id);
+ if (btf_is_var(t))
+ err = bpf_object__resolve_ksym_var_btf_id(obj, ext);
+ else
+ err = bpf_object__resolve_ksym_func_btf_id(obj, ext);
+ if (err)
+ return err;
}
return 0;
}
@@ -8278,6 +8457,16 @@ int bpf_object__btf_fd(const struct bpf_object *obj)
return obj->btf ? btf__fd(obj->btf) : -1;
}
+int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version)
+{
+ if (obj->loaded)
+ return -EINVAL;
+
+ obj->kern_version = kern_version;
+
+ return 0;
+}
+
int bpf_object__set_priv(struct bpf_object *obj, void *priv,
bpf_object_clear_priv_t clear_priv)
{
@@ -8466,7 +8655,7 @@ int bpf_program__nth_fd(const struct bpf_program *prog, int n)
return fd;
}
-enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog)
+enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog)
{
return prog->type;
}
@@ -8511,7 +8700,7 @@ 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)
+bpf_program__get_expected_attach_type(const struct bpf_program *prog)
{
return prog->expected_attach_type;
}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 3c35eb401931..f500621d28e5 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -143,6 +143,7 @@ LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
+LIBBPF_API int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version);
struct btf;
LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
@@ -361,12 +362,12 @@ LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_sk_lookup(struct bpf_program *prog);
-LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog);
+LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog);
LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
enum bpf_prog_type type);
LIBBPF_API enum bpf_attach_type
-bpf_program__get_expected_attach_type(struct bpf_program *prog);
+bpf_program__get_expected_attach_type(const struct bpf_program *prog);
LIBBPF_API void
bpf_program__set_expected_attach_type(struct bpf_program *prog,
enum bpf_attach_type type);
@@ -507,6 +508,7 @@ struct xdp_link_info {
struct bpf_xdp_set_link_opts {
size_t sz;
int old_fd;
+ size_t :0;
};
#define bpf_xdp_set_link_opts__last_field old_fd
@@ -759,6 +761,19 @@ enum libbpf_tristate {
TRI_MODULE = 2,
};
+struct bpf_linker_opts {
+ /* size of this struct, for forward/backward compatiblity */
+ size_t sz;
+};
+#define bpf_linker_opts__last_field sz
+
+struct bpf_linker;
+
+LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts);
+LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, const char *filename);
+LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker);
+LIBBPF_API void bpf_linker__free(struct bpf_linker *linker);
+
#ifdef __cplusplus
} /* extern "C" */
#endif
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index ec898f464ab9..f5990f7208ce 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -354,4 +354,10 @@ LIBBPF_0.3.0 {
LIBBPF_0.4.0 {
global:
btf__add_float;
+ btf__add_type;
+ bpf_linker__add_file;
+ bpf_linker__finalize;
+ bpf_linker__free;
+ bpf_linker__new;
+ bpf_object__set_kversion;
} LIBBPF_0.3.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 343f6eb05637..6017902c687e 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -20,6 +20,26 @@
#include "libbpf.h"
+#ifndef EM_BPF
+#define EM_BPF 247
+#endif
+
+#ifndef R_BPF_64_64
+#define R_BPF_64_64 1
+#endif
+#ifndef R_BPF_64_32
+#define R_BPF_64_32 10
+#endif
+
+#ifndef SHT_LLVM_ADDRSIG
+#define SHT_LLVM_ADDRSIG 0x6FFF4C03
+#endif
+
+/* if libelf is old and doesn't support mmap(), fall back to read() */
+#ifndef ELF_C_READ_MMAP
+#define ELF_C_READ_MMAP ELF_C_READ
+#endif
+
#define BTF_INFO_ENC(kind, kind_flag, vlen) \
((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
@@ -107,9 +127,14 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
return realloc(ptr, total);
}
-void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
- size_t cur_cnt, size_t max_cnt, size_t add_cnt);
-int btf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt);
+struct btf;
+struct btf_type;
+
+struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id);
+
+void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
+ size_t cur_cnt, size_t max_cnt, size_t add_cnt);
+int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt);
static inline bool libbpf_validate_opts(const char *opts,
size_t opts_sz, size_t user_sz,
@@ -351,4 +376,11 @@ struct bpf_core_relo {
enum bpf_core_relo_kind kind;
};
+typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx);
+typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx);
+int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx);
+int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
+int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
+int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
+
#endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h
deleted file mode 100644
index cfbcfc063c81..000000000000
--- a/tools/lib/bpf/libbpf_util.h
+++ /dev/null
@@ -1,75 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-/* Copyright (c) 2019 Facebook */
-
-#ifndef __LIBBPF_LIBBPF_UTIL_H
-#define __LIBBPF_LIBBPF_UTIL_H
-
-#include <stdbool.h>
-#include <linux/compiler.h>
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* Use these barrier functions instead of smp_[rw]mb() when they are
- * used in a libbpf header file. That way they can be built into the
- * application that uses libbpf.
- */
-#if defined(__i386__) || defined(__x86_64__)
-# define libbpf_smp_store_release(p, v) \
- do { \
- asm volatile("" : : : "memory"); \
- WRITE_ONCE(*p, v); \
- } while (0)
-# define libbpf_smp_load_acquire(p) \
- ({ \
- typeof(*p) ___p1 = READ_ONCE(*p); \
- asm volatile("" : : : "memory"); \
- ___p1; \
- })
-#elif defined(__aarch64__)
-# define libbpf_smp_store_release(p, v) \
- asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory")
-# define libbpf_smp_load_acquire(p) \
- ({ \
- typeof(*p) ___p1; \
- asm volatile ("ldar %w0, %1" \
- : "=r" (___p1) : "Q" (*p) : "memory"); \
- ___p1; \
- })
-#elif defined(__riscv)
-# define libbpf_smp_store_release(p, v) \
- do { \
- asm volatile ("fence rw,w" : : : "memory"); \
- WRITE_ONCE(*p, v); \
- } while (0)
-# define libbpf_smp_load_acquire(p) \
- ({ \
- typeof(*p) ___p1 = READ_ONCE(*p); \
- asm volatile ("fence r,rw" : : : "memory"); \
- ___p1; \
- })
-#endif
-
-#ifndef libbpf_smp_store_release
-#define libbpf_smp_store_release(p, v) \
- do { \
- __sync_synchronize(); \
- WRITE_ONCE(*p, v); \
- } while (0)
-#endif
-
-#ifndef libbpf_smp_load_acquire
-#define libbpf_smp_load_acquire(p) \
- ({ \
- typeof(*p) ___p1 = READ_ONCE(*p); \
- __sync_synchronize(); \
- ___p1; \
- })
-#endif
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-#endif
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
new file mode 100644
index 000000000000..46b16cbdcda3
--- /dev/null
+++ b/tools/lib/bpf/linker.c
@@ -0,0 +1,1963 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/*
+ * BPF static linker
+ *
+ * Copyright (c) 2021 Facebook
+ */
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <linux/err.h>
+#include <linux/btf.h>
+#include <elf.h>
+#include <libelf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include "libbpf.h"
+#include "btf.h"
+#include "libbpf_internal.h"
+#include "strset.h"
+
+struct src_sec {
+ const char *sec_name;
+ /* positional (not necessarily ELF) index in an array of sections */
+ int id;
+ /* positional (not necessarily ELF) index of a matching section in a final object file */
+ int dst_id;
+ /* section data offset in a matching output section */
+ int dst_off;
+ /* whether section is omitted from the final ELF file */
+ bool skipped;
+ /* whether section is an ephemeral section, not mapped to an ELF section */
+ bool ephemeral;
+
+ /* ELF info */
+ size_t sec_idx;
+ Elf_Scn *scn;
+ Elf64_Shdr *shdr;
+ Elf_Data *data;
+
+ /* corresponding BTF DATASEC type ID */
+ int sec_type_id;
+};
+
+struct src_obj {
+ const char *filename;
+ int fd;
+ Elf *elf;
+ /* Section header strings section index */
+ size_t shstrs_sec_idx;
+ /* SYMTAB section index */
+ size_t symtab_sec_idx;
+
+ struct btf *btf;
+ struct btf_ext *btf_ext;
+
+ /* List of sections (including ephemeral). Slot zero is unused. */
+ struct src_sec *secs;
+ int sec_cnt;
+
+ /* mapping of symbol indices from src to dst ELF */
+ int *sym_map;
+ /* mapping from the src BTF type IDs to dst ones */
+ int *btf_type_map;
+};
+
+/* single .BTF.ext data section */
+struct btf_ext_sec_data {
+ size_t rec_cnt;
+ __u32 rec_sz;
+ void *recs;
+};
+
+struct dst_sec {
+ char *sec_name;
+ /* positional (not necessarily ELF) index in an array of sections */
+ int id;
+
+ /* ELF info */
+ size_t sec_idx;
+ Elf_Scn *scn;
+ Elf64_Shdr *shdr;
+ Elf_Data *data;
+
+ /* final output section size */
+ int sec_sz;
+ /* final output contents of the section */
+ void *raw_data;
+
+ /* corresponding STT_SECTION symbol index in SYMTAB */
+ int sec_sym_idx;
+
+ /* section's DATASEC variable info, emitted on BTF finalization */
+ bool has_btf;
+ int sec_var_cnt;
+ struct btf_var_secinfo *sec_vars;
+
+ /* section's .BTF.ext data */
+ struct btf_ext_sec_data func_info;
+ struct btf_ext_sec_data line_info;
+ struct btf_ext_sec_data core_relo_info;
+};
+
+struct bpf_linker {
+ char *filename;
+ int fd;
+ Elf *elf;
+ Elf64_Ehdr *elf_hdr;
+
+ /* Output sections metadata */
+ struct dst_sec *secs;
+ int sec_cnt;
+
+ struct strset *strtab_strs; /* STRTAB unique strings */
+ size_t strtab_sec_idx; /* STRTAB section index */
+ size_t symtab_sec_idx; /* SYMTAB section index */
+
+ struct btf *btf;
+ struct btf_ext *btf_ext;
+};
+
+#define pr_warn_elf(fmt, ...) \
+do { \
+ libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1)); \
+} while (0)
+
+static int init_output_elf(struct bpf_linker *linker, const char *file);
+
+static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj);
+static int linker_sanity_check_elf(struct src_obj *obj);
+static int linker_sanity_check_btf(struct src_obj *obj);
+static int linker_sanity_check_btf_ext(struct src_obj *obj);
+static int linker_fixup_btf(struct src_obj *obj);
+static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj);
+static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj);
+static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj);
+static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj);
+static int linker_append_btf_ext(struct bpf_linker *linker, struct src_obj *obj);
+
+static int finalize_btf(struct bpf_linker *linker);
+static int finalize_btf_ext(struct bpf_linker *linker);
+
+void bpf_linker__free(struct bpf_linker *linker)
+{
+ int i;
+
+ if (!linker)
+ return;
+
+ free(linker->filename);
+
+ if (linker->elf)
+ elf_end(linker->elf);
+
+ if (linker->fd >= 0)
+ close(linker->fd);
+
+ strset__free(linker->strtab_strs);
+
+ btf__free(linker->btf);
+ btf_ext__free(linker->btf_ext);
+
+ for (i = 1; i < linker->sec_cnt; i++) {
+ struct dst_sec *sec = &linker->secs[i];
+
+ free(sec->sec_name);
+ free(sec->raw_data);
+ free(sec->sec_vars);
+
+ free(sec->func_info.recs);
+ free(sec->line_info.recs);
+ free(sec->core_relo_info.recs);
+ }
+ free(linker->secs);
+
+ free(linker);
+}
+
+struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts)
+{
+ struct bpf_linker *linker;
+ int err;
+
+ if (!OPTS_VALID(opts, bpf_linker_opts))
+ return NULL;
+
+ if (elf_version(EV_CURRENT) == EV_NONE) {
+ pr_warn_elf("libelf initialization failed");
+ return NULL;
+ }
+
+ linker = calloc(1, sizeof(*linker));
+ if (!linker)
+ return NULL;
+
+ linker->fd = -1;
+
+ err = init_output_elf(linker, filename);
+ if (err)
+ goto err_out;
+
+ return linker;
+
+err_out:
+ bpf_linker__free(linker);
+ return NULL;
+}
+
+static struct dst_sec *add_dst_sec(struct bpf_linker *linker, const char *sec_name)
+{
+ struct dst_sec *secs = linker->secs, *sec;
+ size_t new_cnt = linker->sec_cnt ? linker->sec_cnt + 1 : 2;
+
+ secs = libbpf_reallocarray(secs, new_cnt, sizeof(*secs));
+ if (!secs)
+ return NULL;
+
+ /* zero out newly allocated memory */
+ memset(secs + linker->sec_cnt, 0, (new_cnt - linker->sec_cnt) * sizeof(*secs));
+
+ linker->secs = secs;
+ linker->sec_cnt = new_cnt;
+
+ sec = &linker->secs[new_cnt - 1];
+ sec->id = new_cnt - 1;
+ sec->sec_name = strdup(sec_name);
+ if (!sec->sec_name)
+ return NULL;
+
+ return sec;
+}
+
+static Elf64_Sym *add_new_sym(struct bpf_linker *linker, size_t *sym_idx)
+{
+ struct dst_sec *symtab = &linker->secs[linker->symtab_sec_idx];
+ Elf64_Sym *syms, *sym;
+ size_t sym_cnt = symtab->sec_sz / sizeof(*sym);
+
+ syms = libbpf_reallocarray(symtab->raw_data, sym_cnt + 1, sizeof(*sym));
+ if (!syms)
+ return NULL;
+
+ sym = &syms[sym_cnt];
+ memset(sym, 0, sizeof(*sym));
+
+ symtab->raw_data = syms;
+ symtab->sec_sz += sizeof(*sym);
+ symtab->shdr->sh_size += sizeof(*sym);
+ symtab->data->d_size += sizeof(*sym);
+
+ if (sym_idx)
+ *sym_idx = sym_cnt;
+
+ return sym;
+}
+
+static int init_output_elf(struct bpf_linker *linker, const char *file)
+{
+ int err, str_off;
+ Elf64_Sym *init_sym;
+ struct dst_sec *sec;
+
+ linker->filename = strdup(file);
+ if (!linker->filename)
+ return -ENOMEM;
+
+ linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC, 0644);
+ if (linker->fd < 0) {
+ err = -errno;
+ pr_warn("failed to create '%s': %d\n", file, err);
+ return err;
+ }
+
+ linker->elf = elf_begin(linker->fd, ELF_C_WRITE, NULL);
+ if (!linker->elf) {
+ pr_warn_elf("failed to create ELF object");
+ return -EINVAL;
+ }
+
+ /* ELF header */
+ linker->elf_hdr = elf64_newehdr(linker->elf);
+ if (!linker->elf_hdr){
+ pr_warn_elf("failed to create ELF header");
+ return -EINVAL;
+ }
+
+ linker->elf_hdr->e_machine = EM_BPF;
+ linker->elf_hdr->e_type = ET_REL;
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB;
+#elif __BYTE_ORDER == __BIG_ENDIAN
+ linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB;
+#else
+#error "Unknown __BYTE_ORDER"
+#endif
+
+ /* STRTAB */
+ /* initialize strset with an empty string to conform to ELF */
+ linker->strtab_strs = strset__new(INT_MAX, "", sizeof(""));
+ if (libbpf_get_error(linker->strtab_strs))
+ return libbpf_get_error(linker->strtab_strs);
+
+ sec = add_dst_sec(linker, ".strtab");
+ if (!sec)
+ return -ENOMEM;
+
+ sec->scn = elf_newscn(linker->elf);
+ if (!sec->scn) {
+ pr_warn_elf("failed to create STRTAB section");
+ return -EINVAL;
+ }
+
+ sec->shdr = elf64_getshdr(sec->scn);
+ if (!sec->shdr)
+ return -EINVAL;
+
+ sec->data = elf_newdata(sec->scn);
+ if (!sec->data) {
+ pr_warn_elf("failed to create STRTAB data");
+ return -EINVAL;
+ }
+
+ str_off = strset__add_str(linker->strtab_strs, sec->sec_name);
+ if (str_off < 0)
+ return str_off;
+
+ sec->sec_idx = elf_ndxscn(sec->scn);
+ linker->elf_hdr->e_shstrndx = sec->sec_idx;
+ linker->strtab_sec_idx = sec->sec_idx;
+
+ sec->shdr->sh_name = str_off;
+ sec->shdr->sh_type = SHT_STRTAB;
+ sec->shdr->sh_flags = SHF_STRINGS;
+ sec->shdr->sh_offset = 0;
+ sec->shdr->sh_link = 0;
+ sec->shdr->sh_info = 0;
+ sec->shdr->sh_addralign = 1;
+ sec->shdr->sh_size = sec->sec_sz = 0;
+ sec->shdr->sh_entsize = 0;
+
+ /* SYMTAB */
+ sec = add_dst_sec(linker, ".symtab");
+ if (!sec)
+ return -ENOMEM;
+
+ sec->scn = elf_newscn(linker->elf);
+ if (!sec->scn) {
+ pr_warn_elf("failed to create SYMTAB section");
+ return -EINVAL;
+ }
+
+ sec->shdr = elf64_getshdr(sec->scn);
+ if (!sec->shdr)
+ return -EINVAL;
+
+ sec->data = elf_newdata(sec->scn);
+ if (!sec->data) {
+ pr_warn_elf("failed to create SYMTAB data");
+ return -EINVAL;
+ }
+
+ str_off = strset__add_str(linker->strtab_strs, sec->sec_name);
+ if (str_off < 0)
+ return str_off;
+
+ sec->sec_idx = elf_ndxscn(sec->scn);
+ linker->symtab_sec_idx = sec->sec_idx;
+
+ sec->shdr->sh_name = str_off;
+ sec->shdr->sh_type = SHT_SYMTAB;
+ sec->shdr->sh_flags = 0;
+ sec->shdr->sh_offset = 0;
+ sec->shdr->sh_link = linker->strtab_sec_idx;
+ /* sh_info should be one greater than the index of the last local
+ * symbol (i.e., binding is STB_LOCAL). But why and who cares?
+ */
+ sec->shdr->sh_info = 0;
+ sec->shdr->sh_addralign = 8;
+ sec->shdr->sh_entsize = sizeof(Elf64_Sym);
+
+ /* .BTF */
+ linker->btf = btf__new_empty();
+ err = libbpf_get_error(linker->btf);
+ if (err)
+ return err;
+
+ /* add the special all-zero symbol */
+ init_sym = add_new_sym(linker, NULL);
+ if (!init_sym)
+ return -EINVAL;
+
+ init_sym->st_name = 0;
+ init_sym->st_info = 0;
+ init_sym->st_other = 0;
+ init_sym->st_shndx = SHN_UNDEF;
+ init_sym->st_value = 0;
+ init_sym->st_size = 0;
+
+ return 0;
+}
+
+int bpf_linker__add_file(struct bpf_linker *linker, const char *filename)
+{
+ struct src_obj obj = {};
+ int err = 0;
+
+ if (!linker->elf)
+ return -EINVAL;
+
+ err = err ?: linker_load_obj_file(linker, filename, &obj);
+ err = err ?: linker_append_sec_data(linker, &obj);
+ err = err ?: linker_append_elf_syms(linker, &obj);
+ err = err ?: linker_append_elf_relos(linker, &obj);
+ err = err ?: linker_append_btf(linker, &obj);
+ err = err ?: linker_append_btf_ext(linker, &obj);
+
+ /* free up src_obj resources */
+ free(obj.btf_type_map);
+ btf__free(obj.btf);
+ btf_ext__free(obj.btf_ext);
+ free(obj.secs);
+ free(obj.sym_map);
+ if (obj.elf)
+ elf_end(obj.elf);
+ if (obj.fd >= 0)
+ close(obj.fd);
+
+ return err;
+}
+
+static bool is_dwarf_sec_name(const char *name)
+{
+ /* approximation, but the actual list is too long */
+ return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0;
+}
+
+static bool is_ignored_sec(struct src_sec *sec)
+{
+ Elf64_Shdr *shdr = sec->shdr;
+ const char *name = sec->sec_name;
+
+ /* no special handling of .strtab */
+ if (shdr->sh_type == SHT_STRTAB)
+ return true;
+
+ /* ignore .llvm_addrsig section as well */
+ if (shdr->sh_type == SHT_LLVM_ADDRSIG)
+ return true;
+
+ /* no subprograms will lead to an empty .text section, ignore it */
+ if (shdr->sh_type == SHT_PROGBITS && shdr->sh_size == 0 &&
+ strcmp(sec->sec_name, ".text") == 0)
+ return true;
+
+ /* DWARF sections */
+ if (is_dwarf_sec_name(sec->sec_name))
+ return true;
+
+ if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) {
+ name += sizeof(".rel") - 1;
+ /* DWARF section relocations */
+ if (is_dwarf_sec_name(name))
+ return true;
+
+ /* .BTF and .BTF.ext don't need relocations */
+ if (strcmp(name, BTF_ELF_SEC) == 0 ||
+ strcmp(name, BTF_EXT_ELF_SEC) == 0)
+ return true;
+ }
+
+ return false;
+}
+
+static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name)
+{
+ struct src_sec *secs = obj->secs, *sec;
+ size_t new_cnt = obj->sec_cnt ? obj->sec_cnt + 1 : 2;
+
+ secs = libbpf_reallocarray(secs, new_cnt, sizeof(*secs));
+ if (!secs)
+ return NULL;
+
+ /* zero out newly allocated memory */
+ memset(secs + obj->sec_cnt, 0, (new_cnt - obj->sec_cnt) * sizeof(*secs));
+
+ obj->secs = secs;
+ obj->sec_cnt = new_cnt;
+
+ sec = &obj->secs[new_cnt - 1];
+ sec->id = new_cnt - 1;
+ sec->sec_name = sec_name;
+
+ return sec;
+}
+
+static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj)
+{
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ const int host_endianness = ELFDATA2LSB;
+#elif __BYTE_ORDER == __BIG_ENDIAN
+ const int host_endianness = ELFDATA2MSB;
+#else
+#error "Unknown __BYTE_ORDER"
+#endif
+ int err = 0;
+ Elf_Scn *scn;
+ Elf_Data *data;
+ Elf64_Ehdr *ehdr;
+ Elf64_Shdr *shdr;
+ struct src_sec *sec;
+
+ pr_debug("linker: adding object file '%s'...\n", filename);
+
+ obj->filename = filename;
+
+ obj->fd = open(filename, O_RDONLY);
+ if (obj->fd < 0) {
+ err = -errno;
+ pr_warn("failed to open file '%s': %d\n", filename, err);
+ return err;
+ }
+ obj->elf = elf_begin(obj->fd, ELF_C_READ_MMAP, NULL);
+ if (!obj->elf) {
+ err = -errno;
+ pr_warn_elf("failed to parse ELF file '%s'", filename);
+ return err;
+ }
+
+ /* Sanity check ELF file high-level properties */
+ ehdr = elf64_getehdr(obj->elf);
+ if (!ehdr) {
+ err = -errno;
+ pr_warn_elf("failed to get ELF header for %s", filename);
+ return err;
+ }
+ if (ehdr->e_ident[EI_DATA] != host_endianness) {
+ err = -EOPNOTSUPP;
+ pr_warn_elf("unsupported byte order of ELF file %s", filename);
+ return err;
+ }
+ if (ehdr->e_type != ET_REL
+ || ehdr->e_machine != EM_BPF
+ || ehdr->e_ident[EI_CLASS] != ELFCLASS64) {
+ err = -EOPNOTSUPP;
+ pr_warn_elf("unsupported kind of ELF file %s", filename);
+ return err;
+ }
+
+ if (elf_getshdrstrndx(obj->elf, &obj->shstrs_sec_idx)) {
+ err = -errno;
+ pr_warn_elf("failed to get SHSTRTAB section index for %s", filename);
+ return err;
+ }
+
+ scn = NULL;
+ while ((scn = elf_nextscn(obj->elf, scn)) != NULL) {
+ size_t sec_idx = elf_ndxscn(scn);
+ const char *sec_name;
+
+ shdr = elf64_getshdr(scn);
+ if (!shdr) {
+ err = -errno;
+ pr_warn_elf("failed to get section #%zu header for %s",
+ sec_idx, filename);
+ return err;
+ }
+
+ sec_name = elf_strptr(obj->elf, obj->shstrs_sec_idx, shdr->sh_name);
+ if (!sec_name) {
+ err = -errno;
+ pr_warn_elf("failed to get section #%zu name for %s",
+ sec_idx, filename);
+ return err;
+ }
+
+ data = elf_getdata(scn, 0);
+ if (!data) {
+ err = -errno;
+ pr_warn_elf("failed to get section #%zu (%s) data from %s",
+ sec_idx, sec_name, filename);
+ return err;
+ }
+
+ sec = add_src_sec(obj, sec_name);
+ if (!sec)
+ return -ENOMEM;
+
+ sec->scn = scn;
+ sec->shdr = shdr;
+ sec->data = data;
+ sec->sec_idx = elf_ndxscn(scn);
+
+ if (is_ignored_sec(sec)) {
+ sec->skipped = true;
+ continue;
+ }
+
+ switch (shdr->sh_type) {
+ case SHT_SYMTAB:
+ if (obj->symtab_sec_idx) {
+ err = -EOPNOTSUPP;
+ pr_warn("multiple SYMTAB sections found, not supported\n");
+ return err;
+ }
+ obj->symtab_sec_idx = sec_idx;
+ break;
+ case SHT_STRTAB:
+ /* we'll construct our own string table */
+ break;
+ case SHT_PROGBITS:
+ if (strcmp(sec_name, BTF_ELF_SEC) == 0) {
+ obj->btf = btf__new(data->d_buf, shdr->sh_size);
+ err = libbpf_get_error(obj->btf);
+ if (err) {
+ pr_warn("failed to parse .BTF from %s: %d\n", filename, err);
+ return err;
+ }
+ sec->skipped = true;
+ continue;
+ }
+ if (strcmp(sec_name, BTF_EXT_ELF_SEC) == 0) {
+ obj->btf_ext = btf_ext__new(data->d_buf, shdr->sh_size);
+ err = libbpf_get_error(obj->btf_ext);
+ if (err) {
+ pr_warn("failed to parse .BTF.ext from '%s': %d\n", filename, err);
+ return err;
+ }
+ sec->skipped = true;
+ continue;
+ }
+
+ /* data & code */
+ break;
+ case SHT_NOBITS:
+ /* BSS */
+ break;
+ case SHT_REL:
+ /* relocations */
+ break;
+ default:
+ pr_warn("unrecognized section #%zu (%s) in %s\n",
+ sec_idx, sec_name, filename);
+ err = -EINVAL;
+ return err;
+ }
+ }
+
+ err = err ?: linker_sanity_check_elf(obj);
+ err = err ?: linker_sanity_check_btf(obj);
+ err = err ?: linker_sanity_check_btf_ext(obj);
+ err = err ?: linker_fixup_btf(obj);
+
+ return err;
+}
+
+static bool is_pow_of_2(size_t x)
+{
+ return x && (x & (x - 1)) == 0;
+}
+
+static int linker_sanity_check_elf(struct src_obj *obj)
+{
+ struct src_sec *sec, *link_sec;
+ int i, j, n;
+
+ if (!obj->symtab_sec_idx) {
+ pr_warn("ELF is missing SYMTAB section in %s\n", obj->filename);
+ return -EINVAL;
+ }
+ if (!obj->shstrs_sec_idx) {
+ pr_warn("ELF is missing section headers STRTAB section in %s\n", obj->filename);
+ return -EINVAL;
+ }
+
+ for (i = 1; i < obj->sec_cnt; i++) {
+ sec = &obj->secs[i];
+
+ if (sec->sec_name[0] == '\0') {
+ pr_warn("ELF section #%zu has empty name in %s\n", sec->sec_idx, obj->filename);
+ return -EINVAL;
+ }
+
+ if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign))
+ return -EINVAL;
+ if (sec->shdr->sh_addralign != sec->data->d_align)
+ return -EINVAL;
+
+ if (sec->shdr->sh_size != sec->data->d_size)
+ return -EINVAL;
+
+ switch (sec->shdr->sh_type) {
+ case SHT_SYMTAB: {
+ Elf64_Sym *sym;
+
+ if (sec->shdr->sh_entsize != sizeof(Elf64_Sym))
+ return -EINVAL;
+ if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0)
+ return -EINVAL;
+
+ if (!sec->shdr->sh_link || sec->shdr->sh_link >= obj->sec_cnt) {
+ pr_warn("ELF SYMTAB section #%zu points to missing STRTAB section #%zu in %s\n",
+ sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
+ return -EINVAL;
+ }
+ link_sec = &obj->secs[sec->shdr->sh_link];
+ if (link_sec->shdr->sh_type != SHT_STRTAB) {
+ pr_warn("ELF SYMTAB section #%zu points to invalid STRTAB section #%zu in %s\n",
+ sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
+ return -EINVAL;
+ }
+
+ n = sec->shdr->sh_size / sec->shdr->sh_entsize;
+ sym = sec->data->d_buf;
+ for (j = 0; j < n; j++, sym++) {
+ if (sym->st_shndx
+ && sym->st_shndx < SHN_LORESERVE
+ && sym->st_shndx >= obj->sec_cnt) {
+ pr_warn("ELF sym #%d in section #%zu points to missing section #%zu in %s\n",
+ j, sec->sec_idx, (size_t)sym->st_shndx, obj->filename);
+ return -EINVAL;
+ }
+ if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) {
+ if (sym->st_value != 0)
+ return -EINVAL;
+ }
+ }
+ break;
+ }
+ case SHT_STRTAB:
+ break;
+ case SHT_PROGBITS:
+ if (sec->shdr->sh_flags & SHF_EXECINSTR) {
+ if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0)
+ return -EINVAL;
+ }
+ break;
+ case SHT_NOBITS:
+ break;
+ case SHT_REL: {
+ Elf64_Rel *relo;
+ struct src_sec *sym_sec;
+
+ if (sec->shdr->sh_entsize != sizeof(Elf64_Rel))
+ return -EINVAL;
+ if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0)
+ return -EINVAL;
+
+ /* SHT_REL's sh_link should point to SYMTAB */
+ if (sec->shdr->sh_link != obj->symtab_sec_idx) {
+ pr_warn("ELF relo section #%zu points to invalid SYMTAB section #%zu in %s\n",
+ sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
+ return -EINVAL;
+ }
+
+ /* SHT_REL's sh_info points to relocated section */
+ if (!sec->shdr->sh_info || sec->shdr->sh_info >= obj->sec_cnt) {
+ pr_warn("ELF relo section #%zu points to missing section #%zu in %s\n",
+ sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename);
+ return -EINVAL;
+ }
+ link_sec = &obj->secs[sec->shdr->sh_info];
+
+ /* .rel<secname> -> <secname> pattern is followed */
+ if (strncmp(sec->sec_name, ".rel", sizeof(".rel") - 1) != 0
+ || strcmp(sec->sec_name + sizeof(".rel") - 1, link_sec->sec_name) != 0) {
+ pr_warn("ELF relo section #%zu name has invalid name in %s\n",
+ sec->sec_idx, obj->filename);
+ return -EINVAL;
+ }
+
+ /* don't further validate relocations for ignored sections */
+ if (link_sec->skipped)
+ break;
+
+ /* relocatable section is data or instructions */
+ if (link_sec->shdr->sh_type != SHT_PROGBITS
+ && link_sec->shdr->sh_type != SHT_NOBITS) {
+ pr_warn("ELF relo section #%zu points to invalid section #%zu in %s\n",
+ sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename);
+ return -EINVAL;
+ }
+
+ /* check sanity of each relocation */
+ n = sec->shdr->sh_size / sec->shdr->sh_entsize;
+ relo = sec->data->d_buf;
+ sym_sec = &obj->secs[obj->symtab_sec_idx];
+ for (j = 0; j < n; j++, relo++) {
+ size_t sym_idx = ELF64_R_SYM(relo->r_info);
+ size_t sym_type = ELF64_R_TYPE(relo->r_info);
+
+ if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32) {
+ pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n",
+ j, sec->sec_idx, sym_type, obj->filename);
+ return -EINVAL;
+ }
+
+ if (!sym_idx || sym_idx * sizeof(Elf64_Sym) >= sym_sec->shdr->sh_size) {
+ pr_warn("ELF relo #%d in section #%zu points to invalid symbol #%zu in %s\n",
+ j, sec->sec_idx, sym_idx, obj->filename);
+ return -EINVAL;
+ }
+
+ if (link_sec->shdr->sh_flags & SHF_EXECINSTR) {
+ if (relo->r_offset % sizeof(struct bpf_insn) != 0) {
+ pr_warn("ELF relo #%d in section #%zu points to missing symbol #%zu in %s\n",
+ j, sec->sec_idx, sym_idx, obj->filename);
+ return -EINVAL;
+ }
+ }
+ }
+ break;
+ }
+ case SHT_LLVM_ADDRSIG:
+ break;
+ default:
+ pr_warn("ELF section #%zu (%s) has unrecognized type %zu in %s\n",
+ sec->sec_idx, sec->sec_name, (size_t)sec->shdr->sh_type, obj->filename);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static int check_btf_type_id(__u32 *type_id, void *ctx)
+{
+ struct btf *btf = ctx;
+
+ if (*type_id > btf__get_nr_types(btf))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int check_btf_str_off(__u32 *str_off, void *ctx)
+{
+ struct btf *btf = ctx;
+ const char *s;
+
+ s = btf__str_by_offset(btf, *str_off);
+
+ if (!s)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int linker_sanity_check_btf(struct src_obj *obj)
+{
+ struct btf_type *t;
+ int i, n, err = 0;
+
+ if (!obj->btf)
+ return 0;
+
+ n = btf__get_nr_types(obj->btf);
+ for (i = 1; i <= n; i++) {
+ t = btf_type_by_id(obj->btf, i);
+
+ err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf);
+ err = err ?: btf_type_visit_str_offs(t, check_btf_str_off, obj->btf);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int linker_sanity_check_btf_ext(struct src_obj *obj)
+{
+ int err = 0;
+
+ if (!obj->btf_ext)
+ return 0;
+
+ /* can't use .BTF.ext without .BTF */
+ if (!obj->btf)
+ return -EINVAL;
+
+ err = err ?: btf_ext_visit_type_ids(obj->btf_ext, check_btf_type_id, obj->btf);
+ err = err ?: btf_ext_visit_str_offs(obj->btf_ext, check_btf_str_off, obj->btf);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static int init_sec(struct bpf_linker *linker, struct dst_sec *dst_sec, struct src_sec *src_sec)
+{
+ Elf_Scn *scn;
+ Elf_Data *data;
+ Elf64_Shdr *shdr;
+ int name_off;
+
+ dst_sec->sec_sz = 0;
+ dst_sec->sec_idx = 0;
+
+ /* ephemeral sections are just thin section shells lacking most parts */
+ if (src_sec->ephemeral)
+ return 0;
+
+ scn = elf_newscn(linker->elf);
+ if (!scn)
+ return -1;
+ data = elf_newdata(scn);
+ if (!data)
+ return -1;
+ shdr = elf64_getshdr(scn);
+ if (!shdr)
+ return -1;
+
+ dst_sec->scn = scn;
+ dst_sec->shdr = shdr;
+ dst_sec->data = data;
+ dst_sec->sec_idx = elf_ndxscn(scn);
+
+ name_off = strset__add_str(linker->strtab_strs, src_sec->sec_name);
+ if (name_off < 0)
+ return name_off;
+
+ shdr->sh_name = name_off;
+ shdr->sh_type = src_sec->shdr->sh_type;
+ shdr->sh_flags = src_sec->shdr->sh_flags;
+ shdr->sh_size = 0;
+ /* sh_link and sh_info have different meaning for different types of
+ * sections, so we leave it up to the caller code to fill them in, if
+ * necessary
+ */
+ shdr->sh_link = 0;
+ shdr->sh_info = 0;
+ shdr->sh_addralign = src_sec->shdr->sh_addralign;
+ shdr->sh_entsize = src_sec->shdr->sh_entsize;
+
+ data->d_type = src_sec->data->d_type;
+ data->d_size = 0;
+ data->d_buf = NULL;
+ data->d_align = src_sec->data->d_align;
+ data->d_off = 0;
+
+ return 0;
+}
+
+static struct dst_sec *find_dst_sec_by_name(struct bpf_linker *linker, const char *sec_name)
+{
+ struct dst_sec *sec;
+ int i;
+
+ for (i = 1; i < linker->sec_cnt; i++) {
+ sec = &linker->secs[i];
+
+ if (strcmp(sec->sec_name, sec_name) == 0)
+ return sec;
+ }
+
+ return NULL;
+}
+
+static bool secs_match(struct dst_sec *dst, struct src_sec *src)
+{
+ if (dst->shdr->sh_type != src->shdr->sh_type) {
+ pr_warn("sec %s types mismatch\n", dst->sec_name);
+ return false;
+ }
+ if (dst->shdr->sh_flags != src->shdr->sh_flags) {
+ pr_warn("sec %s flags mismatch\n", dst->sec_name);
+ return false;
+ }
+ if (dst->shdr->sh_entsize != src->shdr->sh_entsize) {
+ pr_warn("sec %s entsize mismatch\n", dst->sec_name);
+ return false;
+ }
+
+ return true;
+}
+
+static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec)
+{
+ if (dst_sec->sec_sz != src_sec->shdr->sh_size)
+ return false;
+ if (memcmp(dst_sec->raw_data, src_sec->data->d_buf, dst_sec->sec_sz) != 0)
+ return false;
+ return true;
+}
+
+static int extend_sec(struct dst_sec *dst, struct src_sec *src)
+{
+ void *tmp;
+ size_t dst_align = dst->shdr->sh_addralign;
+ size_t src_align = src->shdr->sh_addralign;
+ size_t dst_align_sz, dst_final_sz;
+
+ if (dst_align == 0)
+ dst_align = 1;
+ if (dst_align < src_align)
+ dst_align = src_align;
+
+ dst_align_sz = (dst->sec_sz + dst_align - 1) / dst_align * dst_align;
+
+ /* no need to re-align final size */
+ dst_final_sz = dst_align_sz + src->shdr->sh_size;
+
+ if (src->shdr->sh_type != SHT_NOBITS) {
+ tmp = realloc(dst->raw_data, dst_final_sz);
+ if (!tmp)
+ return -ENOMEM;
+ dst->raw_data = tmp;
+
+ /* pad dst section, if it's alignment forced size increase */
+ memset(dst->raw_data + dst->sec_sz, 0, dst_align_sz - dst->sec_sz);
+ /* now copy src data at a properly aligned offset */
+ memcpy(dst->raw_data + dst_align_sz, src->data->d_buf, src->shdr->sh_size);
+ }
+
+ dst->sec_sz = dst_final_sz;
+ dst->shdr->sh_size = dst_final_sz;
+ dst->data->d_size = dst_final_sz;
+
+ dst->shdr->sh_addralign = dst_align;
+ dst->data->d_align = dst_align;
+
+ src->dst_off = dst_align_sz;
+
+ return 0;
+}
+
+static bool is_data_sec(struct src_sec *sec)
+{
+ if (!sec || sec->skipped)
+ return false;
+ /* ephemeral sections are data sections, e.g., .kconfig, .ksyms */
+ if (sec->ephemeral)
+ return true;
+ return sec->shdr->sh_type == SHT_PROGBITS || sec->shdr->sh_type == SHT_NOBITS;
+}
+
+static bool is_relo_sec(struct src_sec *sec)
+{
+ if (!sec || sec->skipped || sec->ephemeral)
+ return false;
+ return sec->shdr->sh_type == SHT_REL;
+}
+
+static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj)
+{
+ int i, err;
+
+ for (i = 1; i < obj->sec_cnt; i++) {
+ struct src_sec *src_sec;
+ struct dst_sec *dst_sec;
+
+ src_sec = &obj->secs[i];
+ if (!is_data_sec(src_sec))
+ continue;
+
+ dst_sec = find_dst_sec_by_name(linker, src_sec->sec_name);
+ if (!dst_sec) {
+ dst_sec = add_dst_sec(linker, src_sec->sec_name);
+ if (!dst_sec)
+ return -ENOMEM;
+ err = init_sec(linker, dst_sec, src_sec);
+ if (err) {
+ pr_warn("failed to init section '%s'\n", src_sec->sec_name);
+ return err;
+ }
+ } else {
+ if (!secs_match(dst_sec, src_sec)) {
+ pr_warn("ELF sections %s are incompatible\n", src_sec->sec_name);
+ return -1;
+ }
+
+ /* "license" and "version" sections are deduped */
+ if (strcmp(src_sec->sec_name, "license") == 0
+ || strcmp(src_sec->sec_name, "version") == 0) {
+ if (!sec_content_is_same(dst_sec, src_sec)) {
+ pr_warn("non-identical contents of section '%s' are not supported\n", src_sec->sec_name);
+ return -EINVAL;
+ }
+ src_sec->skipped = true;
+ src_sec->dst_id = dst_sec->id;
+ continue;
+ }
+ }
+
+ /* record mapped section index */
+ src_sec->dst_id = dst_sec->id;
+
+ if (src_sec->ephemeral)
+ continue;
+
+ err = extend_sec(dst_sec, src_sec);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj)
+{
+ struct src_sec *symtab = &obj->secs[obj->symtab_sec_idx];
+ Elf64_Sym *sym = symtab->data->d_buf, *dst_sym;
+ int i, n = symtab->shdr->sh_size / symtab->shdr->sh_entsize;
+ int str_sec_idx = symtab->shdr->sh_link;
+
+ obj->sym_map = calloc(n + 1, sizeof(*obj->sym_map));
+ if (!obj->sym_map)
+ return -ENOMEM;
+
+ for (i = 0; i < n; i++, sym++) {
+ struct src_sec *src_sec = NULL;
+ struct dst_sec *dst_sec = NULL;
+ const char *sym_name;
+ size_t dst_sym_idx;
+ int name_off;
+
+ /* we already have all-zero initial symbol */
+ if (sym->st_name == 0 && sym->st_info == 0 &&
+ sym->st_other == 0 && sym->st_shndx == SHN_UNDEF &&
+ sym->st_value == 0 && sym->st_size ==0)
+ continue;
+
+ sym_name = elf_strptr(obj->elf, str_sec_idx, sym->st_name);
+ if (!sym_name) {
+ pr_warn("can't fetch symbol name for symbol #%d in '%s'\n", i, obj->filename);
+ return -1;
+ }
+
+ if (sym->st_shndx && sym->st_shndx < SHN_LORESERVE) {
+ src_sec = &obj->secs[sym->st_shndx];
+ if (src_sec->skipped)
+ continue;
+ dst_sec = &linker->secs[src_sec->dst_id];
+
+ /* allow only one STT_SECTION symbol per section */
+ if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && dst_sec->sec_sym_idx) {
+ obj->sym_map[i] = dst_sec->sec_sym_idx;
+ continue;
+ }
+ }
+
+ name_off = strset__add_str(linker->strtab_strs, sym_name);
+ if (name_off < 0)
+ return name_off;
+
+ dst_sym = add_new_sym(linker, &dst_sym_idx);
+ if (!dst_sym)
+ return -ENOMEM;
+
+ dst_sym->st_name = name_off;
+ dst_sym->st_info = sym->st_info;
+ dst_sym->st_other = sym->st_other;
+ dst_sym->st_shndx = src_sec ? dst_sec->sec_idx : sym->st_shndx;
+ dst_sym->st_value = (src_sec ? src_sec->dst_off : 0) + sym->st_value;
+ dst_sym->st_size = sym->st_size;
+
+ obj->sym_map[i] = dst_sym_idx;
+
+ if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && dst_sym) {
+ dst_sec->sec_sym_idx = dst_sym_idx;
+ dst_sym->st_value = 0;
+ }
+
+ }
+
+ return 0;
+}
+
+static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj)
+{
+ struct src_sec *src_symtab = &obj->secs[obj->symtab_sec_idx];
+ struct dst_sec *dst_symtab = &linker->secs[linker->symtab_sec_idx];
+ int i, err;
+
+ for (i = 1; i < obj->sec_cnt; i++) {
+ struct src_sec *src_sec, *src_linked_sec;
+ struct dst_sec *dst_sec, *dst_linked_sec;
+ Elf64_Rel *src_rel, *dst_rel;
+ int j, n;
+
+ src_sec = &obj->secs[i];
+ if (!is_relo_sec(src_sec))
+ continue;
+
+ /* shdr->sh_info points to relocatable section */
+ src_linked_sec = &obj->secs[src_sec->shdr->sh_info];
+ if (src_linked_sec->skipped)
+ continue;
+
+ dst_sec = find_dst_sec_by_name(linker, src_sec->sec_name);
+ if (!dst_sec) {
+ dst_sec = add_dst_sec(linker, src_sec->sec_name);
+ if (!dst_sec)
+ return -ENOMEM;
+ err = init_sec(linker, dst_sec, src_sec);
+ if (err) {
+ pr_warn("failed to init section '%s'\n", src_sec->sec_name);
+ return err;
+ }
+ } else if (!secs_match(dst_sec, src_sec)) {
+ pr_warn("Secs %s are not compatible\n", src_sec->sec_name);
+ return -1;
+ }
+
+ /* shdr->sh_link points to SYMTAB */
+ dst_sec->shdr->sh_link = linker->symtab_sec_idx;
+
+ /* shdr->sh_info points to relocated section */
+ dst_linked_sec = &linker->secs[src_linked_sec->dst_id];
+ dst_sec->shdr->sh_info = dst_linked_sec->sec_idx;
+
+ src_sec->dst_id = dst_sec->id;
+ err = extend_sec(dst_sec, src_sec);
+ if (err)
+ return err;
+
+ src_rel = src_sec->data->d_buf;
+ dst_rel = dst_sec->raw_data + src_sec->dst_off;
+ n = src_sec->shdr->sh_size / src_sec->shdr->sh_entsize;
+ for (j = 0; j < n; j++, src_rel++, dst_rel++) {
+ size_t src_sym_idx = ELF64_R_SYM(src_rel->r_info);
+ size_t sym_type = ELF64_R_TYPE(src_rel->r_info);
+ Elf64_Sym *src_sym, *dst_sym;
+ size_t dst_sym_idx;
+
+ src_sym_idx = ELF64_R_SYM(src_rel->r_info);
+ src_sym = src_symtab->data->d_buf + sizeof(*src_sym) * src_sym_idx;
+
+ dst_sym_idx = obj->sym_map[src_sym_idx];
+ dst_sym = dst_symtab->raw_data + sizeof(*dst_sym) * dst_sym_idx;
+ dst_rel->r_offset += src_linked_sec->dst_off;
+ sym_type = ELF64_R_TYPE(src_rel->r_info);
+ dst_rel->r_info = ELF64_R_INFO(dst_sym_idx, sym_type);
+
+ if (ELF64_ST_TYPE(src_sym->st_info) == STT_SECTION) {
+ struct src_sec *sec = &obj->secs[src_sym->st_shndx];
+ struct bpf_insn *insn;
+
+ if (src_linked_sec->shdr->sh_flags & SHF_EXECINSTR) {
+ /* calls to the very first static function inside
+ * .text section at offset 0 will
+ * reference section symbol, not the
+ * function symbol. Fix that up,
+ * otherwise it won't be possible to
+ * relocate calls to two different
+ * static functions with the same name
+ * (rom two different object files)
+ */
+ insn = dst_linked_sec->raw_data + dst_rel->r_offset;
+ if (insn->code == (BPF_JMP | BPF_CALL))
+ insn->imm += sec->dst_off / sizeof(struct bpf_insn);
+ else
+ insn->imm += sec->dst_off;
+ } else {
+ pr_warn("relocation against STT_SECTION in non-exec section is not supported!\n");
+ return -EINVAL;
+ }
+ }
+
+ }
+ }
+
+ return 0;
+}
+
+static struct src_sec *find_src_sec_by_name(struct src_obj *obj, const char *sec_name)
+{
+ struct src_sec *sec;
+ int i;
+
+ for (i = 1; i < obj->sec_cnt; i++) {
+ sec = &obj->secs[i];
+
+ if (strcmp(sec->sec_name, sec_name) == 0)
+ return sec;
+ }
+
+ return NULL;
+}
+
+static Elf64_Sym *find_sym_by_name(struct src_obj *obj, size_t sec_idx,
+ int sym_type, const char *sym_name)
+{
+ struct src_sec *symtab = &obj->secs[obj->symtab_sec_idx];
+ Elf64_Sym *sym = symtab->data->d_buf;
+ int i, n = symtab->shdr->sh_size / symtab->shdr->sh_entsize;
+ int str_sec_idx = symtab->shdr->sh_link;
+ const char *name;
+
+ for (i = 0; i < n; i++, sym++) {
+ if (sym->st_shndx != sec_idx)
+ continue;
+ if (ELF64_ST_TYPE(sym->st_info) != sym_type)
+ continue;
+
+ name = elf_strptr(obj->elf, str_sec_idx, sym->st_name);
+ if (!name)
+ return NULL;
+
+ if (strcmp(sym_name, name) != 0)
+ continue;
+
+ return sym;
+ }
+
+ return NULL;
+}
+
+static int linker_fixup_btf(struct src_obj *obj)
+{
+ const char *sec_name;
+ struct src_sec *sec;
+ int i, j, n, m;
+
+ if (!obj->btf)
+ return 0;
+
+ n = btf__get_nr_types(obj->btf);
+ for (i = 1; i <= n; i++) {
+ struct btf_var_secinfo *vi;
+ struct btf_type *t;
+
+ t = btf_type_by_id(obj->btf, i);
+ if (btf_kind(t) != BTF_KIND_DATASEC)
+ continue;
+
+ sec_name = btf__str_by_offset(obj->btf, t->name_off);
+ sec = find_src_sec_by_name(obj, sec_name);
+ if (sec) {
+ /* record actual section size, unless ephemeral */
+ if (sec->shdr)
+ t->size = sec->shdr->sh_size;
+ } else {
+ /* BTF can have some sections that are not represented
+ * in ELF, e.g., .kconfig and .ksyms, which are used
+ * for special extern variables. Here we'll
+ * pre-create "section shells" for them to be able to
+ * keep track of extra per-section metadata later
+ * (e.g., BTF variables).
+ */
+ sec = add_src_sec(obj, sec_name);
+ if (!sec)
+ return -ENOMEM;
+
+ sec->ephemeral = true;
+ sec->sec_idx = 0; /* will match UNDEF shndx in ELF */
+ }
+
+ /* remember ELF section and its BTF type ID match */
+ sec->sec_type_id = i;
+
+ /* fix up variable offsets */
+ vi = btf_var_secinfos(t);
+ for (j = 0, m = btf_vlen(t); j < m; j++, vi++) {
+ const struct btf_type *vt = btf__type_by_id(obj->btf, vi->type);
+ const char *var_name = btf__str_by_offset(obj->btf, vt->name_off);
+ int var_linkage = btf_var(vt)->linkage;
+ Elf64_Sym *sym;
+
+ /* no need to patch up static or extern vars */
+ if (var_linkage != BTF_VAR_GLOBAL_ALLOCATED)
+ continue;
+
+ sym = find_sym_by_name(obj, sec->sec_idx, STT_OBJECT, var_name);
+ if (!sym) {
+ pr_warn("failed to find symbol for variable '%s' in section '%s'\n", var_name, sec_name);
+ return -ENOENT;
+ }
+
+ vi->offset = sym->st_value;
+ }
+ }
+
+ return 0;
+}
+
+static int remap_type_id(__u32 *type_id, void *ctx)
+{
+ int *id_map = ctx;
+
+ *type_id = id_map[*type_id];
+
+ return 0;
+}
+
+static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
+{
+ const struct btf_type *t;
+ int i, j, n, start_id, id;
+
+ if (!obj->btf)
+ return 0;
+
+ start_id = btf__get_nr_types(linker->btf) + 1;
+ n = btf__get_nr_types(obj->btf);
+
+ obj->btf_type_map = calloc(n + 1, sizeof(int));
+ if (!obj->btf_type_map)
+ return -ENOMEM;
+
+ for (i = 1; i <= n; i++) {
+ t = btf__type_by_id(obj->btf, i);
+
+ /* DATASECs are handled specially below */
+ if (btf_kind(t) == BTF_KIND_DATASEC)
+ continue;
+
+ id = btf__add_type(linker->btf, obj->btf, t);
+ if (id < 0) {
+ pr_warn("failed to append BTF type #%d from file '%s'\n", i, obj->filename);
+ return id;
+ }
+
+ obj->btf_type_map[i] = id;
+ }
+
+ /* remap all the types except DATASECs */
+ n = btf__get_nr_types(linker->btf);
+ for (i = start_id; i <= n; i++) {
+ struct btf_type *dst_t = btf_type_by_id(linker->btf, i);
+
+ if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map))
+ return -EINVAL;
+ }
+
+ /* append DATASEC info */
+ for (i = 1; i < obj->sec_cnt; i++) {
+ struct src_sec *src_sec;
+ struct dst_sec *dst_sec;
+ const struct btf_var_secinfo *src_var;
+ struct btf_var_secinfo *dst_var;
+
+ src_sec = &obj->secs[i];
+ if (!src_sec->sec_type_id || src_sec->skipped)
+ continue;
+ dst_sec = &linker->secs[src_sec->dst_id];
+
+ /* Mark section as having BTF regardless of the presence of
+ * variables. In some cases compiler might generate empty BTF
+ * with no variables information. E.g., when promoting local
+ * array/structure variable initial values and BPF object
+ * file otherwise has no read-only static variables in
+ * .rodata. We need to preserve such empty BTF and just set
+ * correct section size.
+ */
+ dst_sec->has_btf = true;
+
+ t = btf__type_by_id(obj->btf, src_sec->sec_type_id);
+ src_var = btf_var_secinfos(t);
+ n = btf_vlen(t);
+ for (j = 0; j < n; j++, src_var++) {
+ void *sec_vars = dst_sec->sec_vars;
+
+ sec_vars = libbpf_reallocarray(sec_vars,
+ dst_sec->sec_var_cnt + 1,
+ sizeof(*dst_sec->sec_vars));
+ if (!sec_vars)
+ return -ENOMEM;
+
+ dst_sec->sec_vars = sec_vars;
+ dst_sec->sec_var_cnt++;
+
+ dst_var = &dst_sec->sec_vars[dst_sec->sec_var_cnt - 1];
+ dst_var->type = obj->btf_type_map[src_var->type];
+ dst_var->size = src_var->size;
+ dst_var->offset = src_sec->dst_off + src_var->offset;
+ }
+ }
+
+ return 0;
+}
+
+static void *add_btf_ext_rec(struct btf_ext_sec_data *ext_data, const void *src_rec)
+{
+ void *tmp;
+
+ tmp = libbpf_reallocarray(ext_data->recs, ext_data->rec_cnt + 1, ext_data->rec_sz);
+ if (!tmp)
+ return NULL;
+ ext_data->recs = tmp;
+
+ tmp += ext_data->rec_cnt * ext_data->rec_sz;
+ memcpy(tmp, src_rec, ext_data->rec_sz);
+
+ ext_data->rec_cnt++;
+
+ return tmp;
+}
+
+static int linker_append_btf_ext(struct bpf_linker *linker, struct src_obj *obj)
+{
+ const struct btf_ext_info_sec *ext_sec;
+ const char *sec_name, *s;
+ struct src_sec *src_sec;
+ struct dst_sec *dst_sec;
+ int rec_sz, str_off, i;
+
+ if (!obj->btf_ext)
+ return 0;
+
+ rec_sz = obj->btf_ext->func_info.rec_size;
+ for_each_btf_ext_sec(&obj->btf_ext->func_info, ext_sec) {
+ struct bpf_func_info_min *src_rec, *dst_rec;
+
+ sec_name = btf__name_by_offset(obj->btf, ext_sec->sec_name_off);
+ src_sec = find_src_sec_by_name(obj, sec_name);
+ if (!src_sec) {
+ pr_warn("can't find section '%s' referenced from .BTF.ext\n", sec_name);
+ return -EINVAL;
+ }
+ dst_sec = &linker->secs[src_sec->dst_id];
+
+ if (dst_sec->func_info.rec_sz == 0)
+ dst_sec->func_info.rec_sz = rec_sz;
+ if (dst_sec->func_info.rec_sz != rec_sz) {
+ pr_warn("incompatible .BTF.ext record sizes for section '%s'\n", sec_name);
+ return -EINVAL;
+ }
+
+ for_each_btf_ext_rec(&obj->btf_ext->func_info, ext_sec, i, src_rec) {
+ dst_rec = add_btf_ext_rec(&dst_sec->func_info, src_rec);
+ if (!dst_rec)
+ return -ENOMEM;
+
+ dst_rec->insn_off += src_sec->dst_off;
+ dst_rec->type_id = obj->btf_type_map[dst_rec->type_id];
+ }
+ }
+
+ rec_sz = obj->btf_ext->line_info.rec_size;
+ for_each_btf_ext_sec(&obj->btf_ext->line_info, ext_sec) {
+ struct bpf_line_info_min *src_rec, *dst_rec;
+
+ sec_name = btf__name_by_offset(obj->btf, ext_sec->sec_name_off);
+ src_sec = find_src_sec_by_name(obj, sec_name);
+ if (!src_sec) {
+ pr_warn("can't find section '%s' referenced from .BTF.ext\n", sec_name);
+ return -EINVAL;
+ }
+ dst_sec = &linker->secs[src_sec->dst_id];
+
+ if (dst_sec->line_info.rec_sz == 0)
+ dst_sec->line_info.rec_sz = rec_sz;
+ if (dst_sec->line_info.rec_sz != rec_sz) {
+ pr_warn("incompatible .BTF.ext record sizes for section '%s'\n", sec_name);
+ return -EINVAL;
+ }
+
+ for_each_btf_ext_rec(&obj->btf_ext->line_info, ext_sec, i, src_rec) {
+ dst_rec = add_btf_ext_rec(&dst_sec->line_info, src_rec);
+ if (!dst_rec)
+ return -ENOMEM;
+
+ dst_rec->insn_off += src_sec->dst_off;
+
+ s = btf__str_by_offset(obj->btf, src_rec->file_name_off);
+ str_off = btf__add_str(linker->btf, s);
+ if (str_off < 0)
+ return -ENOMEM;
+ dst_rec->file_name_off = str_off;
+
+ s = btf__str_by_offset(obj->btf, src_rec->line_off);
+ str_off = btf__add_str(linker->btf, s);
+ if (str_off < 0)
+ return -ENOMEM;
+ dst_rec->line_off = str_off;
+
+ /* dst_rec->line_col is fine */
+ }
+ }
+
+ rec_sz = obj->btf_ext->core_relo_info.rec_size;
+ for_each_btf_ext_sec(&obj->btf_ext->core_relo_info, ext_sec) {
+ struct bpf_core_relo *src_rec, *dst_rec;
+
+ sec_name = btf__name_by_offset(obj->btf, ext_sec->sec_name_off);
+ src_sec = find_src_sec_by_name(obj, sec_name);
+ if (!src_sec) {
+ pr_warn("can't find section '%s' referenced from .BTF.ext\n", sec_name);
+ return -EINVAL;
+ }
+ dst_sec = &linker->secs[src_sec->dst_id];
+
+ if (dst_sec->core_relo_info.rec_sz == 0)
+ dst_sec->core_relo_info.rec_sz = rec_sz;
+ if (dst_sec->core_relo_info.rec_sz != rec_sz) {
+ pr_warn("incompatible .BTF.ext record sizes for section '%s'\n", sec_name);
+ return -EINVAL;
+ }
+
+ for_each_btf_ext_rec(&obj->btf_ext->core_relo_info, ext_sec, i, src_rec) {
+ dst_rec = add_btf_ext_rec(&dst_sec->core_relo_info, src_rec);
+ if (!dst_rec)
+ return -ENOMEM;
+
+ dst_rec->insn_off += src_sec->dst_off;
+ dst_rec->type_id = obj->btf_type_map[dst_rec->type_id];
+
+ s = btf__str_by_offset(obj->btf, src_rec->access_str_off);
+ str_off = btf__add_str(linker->btf, s);
+ if (str_off < 0)
+ return -ENOMEM;
+ dst_rec->access_str_off = str_off;
+
+ /* dst_rec->kind is fine */
+ }
+ }
+
+ return 0;
+}
+
+int bpf_linker__finalize(struct bpf_linker *linker)
+{
+ struct dst_sec *sec;
+ size_t strs_sz;
+ const void *strs;
+ int err, i;
+
+ if (!linker->elf)
+ return -EINVAL;
+
+ err = finalize_btf(linker);
+ if (err)
+ return err;
+
+ /* Finalize strings */
+ strs_sz = strset__data_size(linker->strtab_strs);
+ strs = strset__data(linker->strtab_strs);
+
+ sec = &linker->secs[linker->strtab_sec_idx];
+ sec->data->d_align = 1;
+ sec->data->d_off = 0LL;
+ sec->data->d_buf = (void *)strs;
+ sec->data->d_type = ELF_T_BYTE;
+ sec->data->d_size = strs_sz;
+ sec->shdr->sh_size = strs_sz;
+
+ for (i = 1; i < linker->sec_cnt; i++) {
+ sec = &linker->secs[i];
+
+ /* STRTAB is handled specially above */
+ if (sec->sec_idx == linker->strtab_sec_idx)
+ continue;
+
+ /* special ephemeral sections (.ksyms, .kconfig, etc) */
+ if (!sec->scn)
+ continue;
+
+ sec->data->d_buf = sec->raw_data;
+ }
+
+ /* Finalize ELF layout */
+ if (elf_update(linker->elf, ELF_C_NULL) < 0) {
+ err = -errno;
+ pr_warn_elf("failed to finalize ELF layout");
+ return err;
+ }
+
+ /* Write out final ELF contents */
+ if (elf_update(linker->elf, ELF_C_WRITE) < 0) {
+ err = -errno;
+ pr_warn_elf("failed to write ELF contents");
+ return err;
+ }
+
+ elf_end(linker->elf);
+ close(linker->fd);
+
+ linker->elf = NULL;
+ linker->fd = -1;
+
+ return 0;
+}
+
+static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name,
+ size_t align, const void *raw_data, size_t raw_sz)
+{
+ Elf_Scn *scn;
+ Elf_Data *data;
+ Elf64_Shdr *shdr;
+ int name_off;
+
+ name_off = strset__add_str(linker->strtab_strs, sec_name);
+ if (name_off < 0)
+ return name_off;
+
+ scn = elf_newscn(linker->elf);
+ if (!scn)
+ return -ENOMEM;
+ data = elf_newdata(scn);
+ if (!data)
+ return -ENOMEM;
+ shdr = elf64_getshdr(scn);
+ if (!shdr)
+ return -EINVAL;
+
+ shdr->sh_name = name_off;
+ shdr->sh_type = SHT_PROGBITS;
+ shdr->sh_flags = 0;
+ shdr->sh_size = raw_sz;
+ shdr->sh_link = 0;
+ shdr->sh_info = 0;
+ shdr->sh_addralign = align;
+ shdr->sh_entsize = 0;
+
+ data->d_type = ELF_T_BYTE;
+ data->d_size = raw_sz;
+ data->d_buf = (void *)raw_data;
+ data->d_align = align;
+ data->d_off = 0;
+
+ return 0;
+}
+
+static int finalize_btf(struct bpf_linker *linker)
+{
+ struct btf *btf = linker->btf;
+ const void *raw_data;
+ int i, j, id, err;
+ __u32 raw_sz;
+
+ /* bail out if no BTF data was produced */
+ if (btf__get_nr_types(linker->btf) == 0)
+ return 0;
+
+ for (i = 1; i < linker->sec_cnt; i++) {
+ struct dst_sec *sec = &linker->secs[i];
+
+ if (!sec->has_btf)
+ continue;
+
+ id = btf__add_datasec(btf, sec->sec_name, sec->sec_sz);
+ if (id < 0) {
+ pr_warn("failed to add consolidated BTF type for datasec '%s': %d\n",
+ sec->sec_name, id);
+ return id;
+ }
+
+ for (j = 0; j < sec->sec_var_cnt; j++) {
+ struct btf_var_secinfo *vi = &sec->sec_vars[j];
+
+ if (btf__add_datasec_var_info(btf, vi->type, vi->offset, vi->size))
+ return -EINVAL;
+ }
+ }
+
+ err = finalize_btf_ext(linker);
+ if (err) {
+ pr_warn(".BTF.ext generation failed: %d\n", err);
+ return err;
+ }
+
+ err = btf__dedup(linker->btf, linker->btf_ext, NULL);
+ if (err) {
+ pr_warn("BTF dedup failed: %d\n", err);
+ return err;
+ }
+
+ /* Emit .BTF section */
+ raw_data = btf__get_raw_data(linker->btf, &raw_sz);
+ if (!raw_data)
+ return -ENOMEM;
+
+ err = emit_elf_data_sec(linker, BTF_ELF_SEC, 8, raw_data, raw_sz);
+ if (err) {
+ pr_warn("failed to write out .BTF ELF section: %d\n", err);
+ return err;
+ }
+
+ /* Emit .BTF.ext section */
+ if (linker->btf_ext) {
+ raw_data = btf_ext__get_raw_data(linker->btf_ext, &raw_sz);
+ if (!raw_data)
+ return -ENOMEM;
+
+ err = emit_elf_data_sec(linker, BTF_EXT_ELF_SEC, 8, raw_data, raw_sz);
+ if (err) {
+ pr_warn("failed to write out .BTF.ext ELF section: %d\n", err);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+static int emit_btf_ext_data(struct bpf_linker *linker, void *output,
+ const char *sec_name, struct btf_ext_sec_data *sec_data)
+{
+ struct btf_ext_info_sec *sec_info;
+ void *cur = output;
+ int str_off;
+ size_t sz;
+
+ if (!sec_data->rec_cnt)
+ return 0;
+
+ str_off = btf__add_str(linker->btf, sec_name);
+ if (str_off < 0)
+ return -ENOMEM;
+
+ sec_info = cur;
+ sec_info->sec_name_off = str_off;
+ sec_info->num_info = sec_data->rec_cnt;
+ cur += sizeof(struct btf_ext_info_sec);
+
+ sz = sec_data->rec_cnt * sec_data->rec_sz;
+ memcpy(cur, sec_data->recs, sz);
+ cur += sz;
+
+ return cur - output;
+}
+
+static int finalize_btf_ext(struct bpf_linker *linker)
+{
+ size_t funcs_sz = 0, lines_sz = 0, core_relos_sz = 0, total_sz = 0;
+ size_t func_rec_sz = 0, line_rec_sz = 0, core_relo_rec_sz = 0;
+ struct btf_ext_header *hdr;
+ void *data, *cur;
+ int i, err, sz;
+
+ /* validate that all sections have the same .BTF.ext record sizes
+ * and calculate total data size for each type of data (func info,
+ * line info, core relos)
+ */
+ for (i = 1; i < linker->sec_cnt; i++) {
+ struct dst_sec *sec = &linker->secs[i];
+
+ if (sec->func_info.rec_cnt) {
+ if (func_rec_sz == 0)
+ func_rec_sz = sec->func_info.rec_sz;
+ if (func_rec_sz != sec->func_info.rec_sz) {
+ pr_warn("mismatch in func_info record size %zu != %u\n",
+ func_rec_sz, sec->func_info.rec_sz);
+ return -EINVAL;
+ }
+
+ funcs_sz += sizeof(struct btf_ext_info_sec) + func_rec_sz * sec->func_info.rec_cnt;
+ }
+ if (sec->line_info.rec_cnt) {
+ if (line_rec_sz == 0)
+ line_rec_sz = sec->line_info.rec_sz;
+ if (line_rec_sz != sec->line_info.rec_sz) {
+ pr_warn("mismatch in line_info record size %zu != %u\n",
+ line_rec_sz, sec->line_info.rec_sz);
+ return -EINVAL;
+ }
+
+ lines_sz += sizeof(struct btf_ext_info_sec) + line_rec_sz * sec->line_info.rec_cnt;
+ }
+ if (sec->core_relo_info.rec_cnt) {
+ if (core_relo_rec_sz == 0)
+ core_relo_rec_sz = sec->core_relo_info.rec_sz;
+ if (core_relo_rec_sz != sec->core_relo_info.rec_sz) {
+ pr_warn("mismatch in core_relo_info record size %zu != %u\n",
+ core_relo_rec_sz, sec->core_relo_info.rec_sz);
+ return -EINVAL;
+ }
+
+ core_relos_sz += sizeof(struct btf_ext_info_sec) + core_relo_rec_sz * sec->core_relo_info.rec_cnt;
+ }
+ }
+
+ if (!funcs_sz && !lines_sz && !core_relos_sz)
+ return 0;
+
+ total_sz += sizeof(struct btf_ext_header);
+ if (funcs_sz) {
+ funcs_sz += sizeof(__u32); /* record size prefix */
+ total_sz += funcs_sz;
+ }
+ if (lines_sz) {
+ lines_sz += sizeof(__u32); /* record size prefix */
+ total_sz += lines_sz;
+ }
+ if (core_relos_sz) {
+ core_relos_sz += sizeof(__u32); /* record size prefix */
+ total_sz += core_relos_sz;
+ }
+
+ cur = data = calloc(1, total_sz);
+ if (!data)
+ return -ENOMEM;
+
+ hdr = cur;
+ hdr->magic = BTF_MAGIC;
+ hdr->version = BTF_VERSION;
+ hdr->flags = 0;
+ hdr->hdr_len = sizeof(struct btf_ext_header);
+ cur += sizeof(struct btf_ext_header);
+
+ /* All offsets are in bytes relative to the end of this header */
+ hdr->func_info_off = 0;
+ hdr->func_info_len = funcs_sz;
+ hdr->line_info_off = funcs_sz;
+ hdr->line_info_len = lines_sz;
+ hdr->core_relo_off = funcs_sz + lines_sz;;
+ hdr->core_relo_len = core_relos_sz;
+
+ if (funcs_sz) {
+ *(__u32 *)cur = func_rec_sz;
+ cur += sizeof(__u32);
+
+ for (i = 1; i < linker->sec_cnt; i++) {
+ struct dst_sec *sec = &linker->secs[i];
+
+ sz = emit_btf_ext_data(linker, cur, sec->sec_name, &sec->func_info);
+ if (sz < 0) {
+ err = sz;
+ goto out;
+ }
+
+ cur += sz;
+ }
+ }
+
+ if (lines_sz) {
+ *(__u32 *)cur = line_rec_sz;
+ cur += sizeof(__u32);
+
+ for (i = 1; i < linker->sec_cnt; i++) {
+ struct dst_sec *sec = &linker->secs[i];
+
+ sz = emit_btf_ext_data(linker, cur, sec->sec_name, &sec->line_info);
+ if (sz < 0) {
+ err = sz;
+ goto out;
+ }
+
+ cur += sz;
+ }
+ }
+
+ if (core_relos_sz) {
+ *(__u32 *)cur = core_relo_rec_sz;
+ cur += sizeof(__u32);
+
+ for (i = 1; i < linker->sec_cnt; i++) {
+ struct dst_sec *sec = &linker->secs[i];
+
+ sz = emit_btf_ext_data(linker, cur, sec->sec_name, &sec->core_relo_info);
+ if (sz < 0) {
+ err = sz;
+ goto out;
+ }
+
+ cur += sz;
+ }
+ }
+
+ linker->btf_ext = btf_ext__new(data, total_sz);
+ err = libbpf_get_error(linker->btf_ext);
+ if (err) {
+ linker->btf_ext = NULL;
+ pr_warn("failed to parse final .BTF.ext data: %d\n", err);
+ goto out;
+ }
+
+out:
+ free(data);
+ return err;
+}
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 4dd73de00b6f..d2cb28e9ef52 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -40,7 +40,7 @@ static int libbpf_netlink_open(__u32 *nl_pid)
memset(&sa, 0, sizeof(sa));
sa.nl_family = AF_NETLINK;
- sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
if (sock < 0)
return -errno;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 8caaafe7e312..e7a8d847161f 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -227,7 +227,7 @@ static int ringbuf_process_ring(struct ring* r)
if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) {
sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ;
err = r->sample_cb(r->ctx, sample, len);
- if (err) {
+ if (err < 0) {
/* update consumer pos and bail out */
smp_store_release(r->consumer_pos,
cons_pos);
diff --git a/tools/lib/bpf/strset.c b/tools/lib/bpf/strset.c
new file mode 100644
index 000000000000..1fb8b49de1d6
--- /dev/null
+++ b/tools/lib/bpf/strset.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2021 Facebook */
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "hashmap.h"
+#include "libbpf_internal.h"
+#include "strset.h"
+
+struct strset {
+ void *strs_data;
+ size_t strs_data_len;
+ size_t strs_data_cap;
+ size_t strs_data_max_len;
+
+ /* lookup index for each unique string in strings set */
+ struct hashmap *strs_hash;
+};
+
+static size_t strset_hash_fn(const void *key, void *ctx)
+{
+ const struct strset *s = ctx;
+ const char *str = s->strs_data + (long)key;
+
+ return str_hash(str);
+}
+
+static bool strset_equal_fn(const void *key1, const void *key2, void *ctx)
+{
+ const struct strset *s = ctx;
+ const char *str1 = s->strs_data + (long)key1;
+ const char *str2 = s->strs_data + (long)key2;
+
+ return strcmp(str1, str2) == 0;
+}
+
+struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t init_data_sz)
+{
+ struct strset *set = calloc(1, sizeof(*set));
+ struct hashmap *hash;
+ int err = -ENOMEM;
+
+ if (!set)
+ return ERR_PTR(-ENOMEM);
+
+ hash = hashmap__new(strset_hash_fn, strset_equal_fn, set);
+ if (IS_ERR(hash))
+ goto err_out;
+
+ set->strs_data_max_len = max_data_sz;
+ set->strs_hash = hash;
+
+ if (init_data) {
+ long off;
+
+ set->strs_data = malloc(init_data_sz);
+ if (!set->strs_data)
+ goto err_out;
+
+ memcpy(set->strs_data, init_data, init_data_sz);
+ set->strs_data_len = init_data_sz;
+ set->strs_data_cap = init_data_sz;
+
+ for (off = 0; off < set->strs_data_len; off += strlen(set->strs_data + off) + 1) {
+ /* hashmap__add() returns EEXIST if string with the same
+ * content already is in the hash map
+ */
+ err = hashmap__add(hash, (void *)off, (void *)off);
+ if (err == -EEXIST)
+ continue; /* duplicate */
+ if (err)
+ goto err_out;
+ }
+ }
+
+ return set;
+err_out:
+ strset__free(set);
+ return ERR_PTR(err);
+}
+
+void strset__free(struct strset *set)
+{
+ if (IS_ERR_OR_NULL(set))
+ return;
+
+ hashmap__free(set->strs_hash);
+ free(set->strs_data);
+}
+
+size_t strset__data_size(const struct strset *set)
+{
+ return set->strs_data_len;
+}
+
+const char *strset__data(const struct strset *set)
+{
+ return set->strs_data;
+}
+
+static void *strset_add_str_mem(struct strset *set, size_t add_sz)
+{
+ return libbpf_add_mem(&set->strs_data, &set->strs_data_cap, 1,
+ set->strs_data_len, set->strs_data_max_len, add_sz);
+}
+
+/* Find string offset that corresponds to a given string *s*.
+ * Returns:
+ * - >0 offset into string data, if string is found;
+ * - -ENOENT, if string is not in the string data;
+ * - <0, on any other error.
+ */
+int strset__find_str(struct strset *set, const char *s)
+{
+ long old_off, new_off, len;
+ void *p;
+
+ /* see strset__add_str() for why we do this */
+ len = strlen(s) + 1;
+ p = strset_add_str_mem(set, len);
+ if (!p)
+ return -ENOMEM;
+
+ new_off = set->strs_data_len;
+ memcpy(p, s, len);
+
+ if (hashmap__find(set->strs_hash, (void *)new_off, (void **)&old_off))
+ return old_off;
+
+ return -ENOENT;
+}
+
+/* Add a string s to the string data. If the string already exists, return its
+ * offset within string data.
+ * Returns:
+ * - > 0 offset into string data, on success;
+ * - < 0, on error.
+ */
+int strset__add_str(struct strset *set, const char *s)
+{
+ long old_off, new_off, len;
+ void *p;
+ int err;
+
+ /* Hashmap keys are always offsets within set->strs_data, so to even
+ * look up some string from the "outside", we need to first append it
+ * at the end, so that it can be addressed with an offset. Luckily,
+ * until set->strs_data_len is incremented, that string is just a piece
+ * of garbage for the rest of the code, so no harm, no foul. On the
+ * other hand, if the string is unique, it's already appended and
+ * ready to be used, only a simple set->strs_data_len increment away.
+ */
+ len = strlen(s) + 1;
+ p = strset_add_str_mem(set, len);
+ if (!p)
+ return -ENOMEM;
+
+ new_off = set->strs_data_len;
+ memcpy(p, s, len);
+
+ /* Now attempt to add the string, but only if the string with the same
+ * contents doesn't exist already (HASHMAP_ADD strategy). If such
+ * string exists, we'll get its offset in old_off (that's old_key).
+ */
+ err = hashmap__insert(set->strs_hash, (void *)new_off, (void *)new_off,
+ HASHMAP_ADD, (const void **)&old_off, NULL);
+ if (err == -EEXIST)
+ return old_off; /* duplicated string, return existing offset */
+ if (err)
+ return err;
+
+ set->strs_data_len += len; /* new unique string, adjust data length */
+ return new_off;
+}
diff --git a/tools/lib/bpf/strset.h b/tools/lib/bpf/strset.h
new file mode 100644
index 000000000000..b6ddf77a83c2
--- /dev/null
+++ b/tools/lib/bpf/strset.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/* Copyright (c) 2021 Facebook */
+#ifndef __LIBBPF_STRSET_H
+#define __LIBBPF_STRSET_H
+
+#include <stdbool.h>
+#include <stddef.h>
+
+struct strset;
+
+struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t init_data_sz);
+void strset__free(struct strset *set);
+
+const char *strset__data(const struct strset *set);
+size_t strset__data_size(const struct strset *set);
+
+int strset__find_str(struct strset *set, const char *s);
+int strset__add_str(struct strset *set, const char *s);
+
+#endif /* __LIBBPF_STRSET_H */
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 526fc35c0b23..cea62cc3e456 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -28,6 +28,7 @@
#include <sys/mman.h>
#include <sys/socket.h>
#include <sys/types.h>
+#include <linux/if_link.h>
#include "bpf.h"
#include "libbpf.h"
@@ -59,6 +60,8 @@ struct xsk_umem {
int fd;
int refcount;
struct list_head ctx_list;
+ bool rx_ring_setup_done;
+ bool tx_ring_setup_done;
};
struct xsk_ctx {
@@ -70,8 +73,10 @@ struct xsk_ctx {
int ifindex;
struct list_head list;
int prog_fd;
+ int link_fd;
int xsks_map_fd;
char ifname[IFNAMSIZ];
+ bool has_bpf_link;
};
struct xsk_socket {
@@ -409,7 +414,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
static const int log_buf_size = 16 * 1024;
struct xsk_ctx *ctx = xsk->ctx;
char log_buf[log_buf_size];
- int err, prog_fd;
+ int prog_fd;
/* This is the fallback C-program:
* SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
@@ -499,14 +504,41 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
return prog_fd;
}
- err = bpf_set_link_xdp_fd(xsk->ctx->ifindex, prog_fd,
- xsk->config.xdp_flags);
+ ctx->prog_fd = prog_fd;
+ return 0;
+}
+
+static int xsk_create_bpf_link(struct xsk_socket *xsk)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+ struct xsk_ctx *ctx = xsk->ctx;
+ __u32 prog_id = 0;
+ int link_fd;
+ int err;
+
+ err = bpf_get_link_xdp_id(ctx->ifindex, &prog_id, xsk->config.xdp_flags);
if (err) {
- close(prog_fd);
+ pr_warn("getting XDP prog id failed\n");
return err;
}
- ctx->prog_fd = prog_fd;
+ /* if there's a netlink-based XDP prog loaded on interface, bail out
+ * and ask user to do the removal by himself
+ */
+ if (prog_id) {
+ pr_warn("Netlink-based XDP prog detected, please unload it in order to launch AF_XDP prog\n");
+ return -EINVAL;
+ }
+
+ opts.flags = xsk->config.xdp_flags & ~(XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_REPLACE);
+
+ link_fd = bpf_link_create(ctx->prog_fd, ctx->ifindex, BPF_XDP, &opts);
+ if (link_fd < 0) {
+ pr_warn("bpf_link_create failed: %s\n", strerror(errno));
+ return link_fd;
+ }
+
+ ctx->link_fd = link_fd;
return 0;
}
@@ -625,7 +657,6 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
close(fd);
}
- err = 0;
if (ctx->xsks_map_fd == -1)
err = -ENOENT;
@@ -642,6 +673,98 @@ static int xsk_set_bpf_maps(struct xsk_socket *xsk)
&xsk->fd, 0);
}
+static int xsk_link_lookup(int ifindex, __u32 *prog_id, int *link_fd)
+{
+ struct bpf_link_info link_info;
+ __u32 link_len;
+ __u32 id = 0;
+ int err;
+ int fd;
+
+ while (true) {
+ err = bpf_link_get_next_id(id, &id);
+ if (err) {
+ if (errno == ENOENT) {
+ err = 0;
+ break;
+ }
+ pr_warn("can't get next link: %s\n", strerror(errno));
+ break;
+ }
+
+ fd = bpf_link_get_fd_by_id(id);
+ if (fd < 0) {
+ if (errno == ENOENT)
+ continue;
+ pr_warn("can't get link by id (%u): %s\n", id, strerror(errno));
+ err = -errno;
+ break;
+ }
+
+ link_len = sizeof(struct bpf_link_info);
+ memset(&link_info, 0, link_len);
+ err = bpf_obj_get_info_by_fd(fd, &link_info, &link_len);
+ if (err) {
+ pr_warn("can't get link info: %s\n", strerror(errno));
+ close(fd);
+ break;
+ }
+ if (link_info.type == BPF_LINK_TYPE_XDP) {
+ if (link_info.xdp.ifindex == ifindex) {
+ *link_fd = fd;
+ if (prog_id)
+ *prog_id = link_info.prog_id;
+ break;
+ }
+ }
+ close(fd);
+ }
+
+ return err;
+}
+
+static bool xsk_probe_bpf_link(void)
+{
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
+ .flags = XDP_FLAGS_SKB_MODE);
+ struct bpf_load_program_attr prog_attr;
+ struct bpf_insn insns[2] = {
+ BPF_MOV64_IMM(BPF_REG_0, XDP_PASS),
+ BPF_EXIT_INSN()
+ };
+ int prog_fd, link_fd = -1;
+ int ifindex_lo = 1;
+ bool ret = false;
+ int err;
+
+ err = xsk_link_lookup(ifindex_lo, NULL, &link_fd);
+ if (err)
+ return ret;
+
+ if (link_fd >= 0)
+ return true;
+
+ memset(&prog_attr, 0, sizeof(prog_attr));
+ prog_attr.prog_type = BPF_PROG_TYPE_XDP;
+ prog_attr.insns = insns;
+ prog_attr.insns_cnt = ARRAY_SIZE(insns);
+ prog_attr.license = "GPL";
+
+ prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0);
+ if (prog_fd < 0)
+ return ret;
+
+ link_fd = bpf_link_create(prog_fd, ifindex_lo, BPF_XDP, &opts);
+ close(prog_fd);
+
+ if (link_fd >= 0) {
+ ret = true;
+ close(link_fd);
+ }
+
+ return ret;
+}
+
static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
{
char ifname[IFNAMSIZ];
@@ -663,64 +786,108 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
ctx->ifname[IFNAMSIZ - 1] = 0;
xsk->ctx = ctx;
+ xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
return 0;
}
-static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp,
- int *xsks_map_fd)
+static int xsk_init_xdp_res(struct xsk_socket *xsk,
+ int *xsks_map_fd)
{
- struct xsk_socket *xsk = _xdp;
struct xsk_ctx *ctx = xsk->ctx;
- __u32 prog_id = 0;
int err;
- err = bpf_get_link_xdp_id(ctx->ifindex, &prog_id,
- xsk->config.xdp_flags);
+ err = xsk_create_bpf_maps(xsk);
if (err)
return err;
- if (!prog_id) {
- err = xsk_create_bpf_maps(xsk);
- if (err)
- return err;
+ err = xsk_load_xdp_prog(xsk);
+ if (err)
+ goto err_load_xdp_prog;
- err = xsk_load_xdp_prog(xsk);
- if (err) {
- goto err_load_xdp_prog;
- }
- } else {
- ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id);
- if (ctx->prog_fd < 0)
- return -errno;
- err = xsk_lookup_bpf_maps(xsk);
- if (err) {
- close(ctx->prog_fd);
- return err;
- }
- }
+ if (ctx->has_bpf_link)
+ err = xsk_create_bpf_link(xsk);
+ else
+ err = bpf_set_link_xdp_fd(xsk->ctx->ifindex, ctx->prog_fd,
+ xsk->config.xdp_flags);
- if (xsk->rx) {
- err = xsk_set_bpf_maps(xsk);
- if (err) {
- if (!prog_id) {
- goto err_set_bpf_maps;
- } else {
- close(ctx->prog_fd);
- return err;
- }
- }
- }
- if (xsks_map_fd)
- *xsks_map_fd = ctx->xsks_map_fd;
+ if (err)
+ goto err_attach_xdp_prog;
- return 0;
+ if (!xsk->rx)
+ return err;
+
+ err = xsk_set_bpf_maps(xsk);
+ if (err)
+ goto err_set_bpf_maps;
+
+ return err;
err_set_bpf_maps:
+ if (ctx->has_bpf_link)
+ close(ctx->link_fd);
+ else
+ bpf_set_link_xdp_fd(ctx->ifindex, -1, 0);
+err_attach_xdp_prog:
close(ctx->prog_fd);
- bpf_set_link_xdp_fd(ctx->ifindex, -1, 0);
err_load_xdp_prog:
xsk_delete_bpf_maps(xsk);
+ return err;
+}
+
+static int xsk_lookup_xdp_res(struct xsk_socket *xsk, int *xsks_map_fd, int prog_id)
+{
+ struct xsk_ctx *ctx = xsk->ctx;
+ int err;
+
+ ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id);
+ if (ctx->prog_fd < 0) {
+ err = -errno;
+ goto err_prog_fd;
+ }
+ err = xsk_lookup_bpf_maps(xsk);
+ if (err)
+ goto err_lookup_maps;
+
+ if (!xsk->rx)
+ return err;
+
+ err = xsk_set_bpf_maps(xsk);
+ if (err)
+ goto err_set_maps;
+
+ return err;
+
+err_set_maps:
+ close(ctx->xsks_map_fd);
+err_lookup_maps:
+ close(ctx->prog_fd);
+err_prog_fd:
+ if (ctx->has_bpf_link)
+ close(ctx->link_fd);
+ return err;
+}
+
+static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp, int *xsks_map_fd)
+{
+ struct xsk_socket *xsk = _xdp;
+ struct xsk_ctx *ctx = xsk->ctx;
+ __u32 prog_id = 0;
+ int err;
+
+ if (ctx->has_bpf_link)
+ err = xsk_link_lookup(ctx->ifindex, &prog_id, &ctx->link_fd);
+ else
+ err = bpf_get_link_xdp_id(ctx->ifindex, &prog_id, xsk->config.xdp_flags);
+
+ if (err)
+ return err;
+
+ err = !prog_id ? xsk_init_xdp_res(xsk, xsks_map_fd) :
+ xsk_lookup_xdp_res(xsk, xsks_map_fd, prog_id);
+
+ if (!err && xsks_map_fd)
+ *xsks_map_fd = ctx->xsks_map_fd;
return err;
}
@@ -743,26 +910,30 @@ static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
return NULL;
}
-static void xsk_put_ctx(struct xsk_ctx *ctx)
+static void xsk_put_ctx(struct xsk_ctx *ctx, bool unmap)
{
struct xsk_umem *umem = ctx->umem;
struct xdp_mmap_offsets off;
int err;
- if (--ctx->refcount == 0) {
- err = xsk_get_mmap_offsets(umem->fd, &off);
- if (!err) {
- munmap(ctx->fill->ring - off.fr.desc,
- off.fr.desc + umem->config.fill_size *
- sizeof(__u64));
- munmap(ctx->comp->ring - off.cr.desc,
- off.cr.desc + umem->config.comp_size *
- sizeof(__u64));
- }
+ if (--ctx->refcount)
+ return;
- list_del(&ctx->list);
- free(ctx);
- }
+ if (!unmap)
+ goto out_free;
+
+ err = xsk_get_mmap_offsets(umem->fd, &off);
+ if (err)
+ goto out_free;
+
+ munmap(ctx->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size *
+ sizeof(__u64));
+ munmap(ctx->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size *
+ sizeof(__u64));
+
+out_free:
+ list_del(&ctx->list);
+ free(ctx);
}
static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
@@ -797,8 +968,6 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
memcpy(ctx->ifname, ifname, IFNAMSIZ - 1);
ctx->ifname[IFNAMSIZ - 1] = '\0';
- umem->fill_save = NULL;
- umem->comp_save = NULL;
ctx->fill = fill;
ctx->comp = comp;
list_add(&ctx->list, &umem->ctx_list);
@@ -854,6 +1023,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
struct xsk_socket *xsk;
struct xsk_ctx *ctx;
int err, ifindex;
+ bool unmap = umem->fill_save != fill;
+ bool rx_setup_done = false, tx_setup_done = false;
if (!umem || !xsk_ptr || !(rx || tx))
return -EFAULT;
@@ -881,6 +1052,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
}
} else {
xsk->fd = umem->fd;
+ rx_setup_done = umem->rx_ring_setup_done;
+ tx_setup_done = umem->tx_ring_setup_done;
}
ctx = xsk_get_ctx(umem, ifindex, queue_id);
@@ -898,8 +1071,9 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
}
}
xsk->ctx = ctx;
+ xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
- if (rx) {
+ if (rx && !rx_setup_done) {
err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
&xsk->config.rx_size,
sizeof(xsk->config.rx_size));
@@ -907,8 +1081,10 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
err = -errno;
goto out_put_ctx;
}
+ if (xsk->fd == umem->fd)
+ umem->rx_ring_setup_done = true;
}
- if (tx) {
+ if (tx && !tx_setup_done) {
err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING,
&xsk->config.tx_size,
sizeof(xsk->config.tx_size));
@@ -916,6 +1092,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
err = -errno;
goto out_put_ctx;
}
+ if (xsk->fd == umem->fd)
+ umem->rx_ring_setup_done = true;
}
err = xsk_get_mmap_offsets(xsk->fd, &off);
@@ -994,6 +1172,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
}
*xsk_ptr = xsk;
+ umem->fill_save = NULL;
+ umem->comp_save = NULL;
return 0;
out_mmap_tx:
@@ -1005,7 +1185,7 @@ out_mmap_rx:
munmap(rx_map, off.rx.desc +
xsk->config.rx_size * sizeof(struct xdp_desc));
out_put_ctx:
- xsk_put_ctx(ctx);
+ xsk_put_ctx(ctx, unmap);
out_socket:
if (--umem->refcount)
close(xsk->fd);
@@ -1019,6 +1199,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
const struct xsk_socket_config *usr_config)
{
+ if (!umem)
+ return -EFAULT;
+
return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem,
rx, tx, umem->fill_save,
umem->comp_save, usr_config);
@@ -1054,6 +1237,8 @@ void xsk_socket__delete(struct xsk_socket *xsk)
if (ctx->prog_fd != -1) {
xsk_delete_bpf_maps(xsk);
close(ctx->prog_fd);
+ if (ctx->has_bpf_link)
+ close(ctx->link_fd);
}
err = xsk_get_mmap_offsets(xsk->fd, &off);
@@ -1068,7 +1253,7 @@ void xsk_socket__delete(struct xsk_socket *xsk)
}
}
- xsk_put_ctx(ctx);
+ xsk_put_ctx(ctx, true);
umem->refcount--;
/* Do not close an fd that also has an associated umem connected
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index a9fdea87b5cd..01c12dca9c10 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -3,7 +3,8 @@
/*
* AF_XDP user-space access library.
*
- * Copyright(c) 2018 - 2019 Intel Corporation.
+ * Copyright (c) 2018 - 2019 Intel Corporation.
+ * Copyright (c) 2019 Facebook
*
* Author(s): Magnus Karlsson <magnus.karlsson@intel.com>
*/
@@ -13,15 +14,80 @@
#include <stdio.h>
#include <stdint.h>
+#include <stdbool.h>
#include <linux/if_xdp.h>
#include "libbpf.h"
-#include "libbpf_util.h"
#ifdef __cplusplus
extern "C" {
#endif
+/* Load-Acquire Store-Release barriers used by the XDP socket
+ * library. The following macros should *NOT* be considered part of
+ * the xsk.h API, and is subject to change anytime.
+ *
+ * LIBRARY INTERNAL
+ */
+
+#define __XSK_READ_ONCE(x) (*(volatile typeof(x) *)&x)
+#define __XSK_WRITE_ONCE(x, v) (*(volatile typeof(x) *)&x) = (v)
+
+#if defined(__i386__) || defined(__x86_64__)
+# define libbpf_smp_store_release(p, v) \
+ do { \
+ asm volatile("" : : : "memory"); \
+ __XSK_WRITE_ONCE(*p, v); \
+ } while (0)
+# define libbpf_smp_load_acquire(p) \
+ ({ \
+ typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \
+ asm volatile("" : : : "memory"); \
+ ___p1; \
+ })
+#elif defined(__aarch64__)
+# define libbpf_smp_store_release(p, v) \
+ asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory")
+# define libbpf_smp_load_acquire(p) \
+ ({ \
+ typeof(*p) ___p1; \
+ asm volatile ("ldar %w0, %1" \
+ : "=r" (___p1) : "Q" (*p) : "memory"); \
+ ___p1; \
+ })
+#elif defined(__riscv)
+# define libbpf_smp_store_release(p, v) \
+ do { \
+ asm volatile ("fence rw,w" : : : "memory"); \
+ __XSK_WRITE_ONCE(*p, v); \
+ } while (0)
+# define libbpf_smp_load_acquire(p) \
+ ({ \
+ typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \
+ asm volatile ("fence r,rw" : : : "memory"); \
+ ___p1; \
+ })
+#endif
+
+#ifndef libbpf_smp_store_release
+#define libbpf_smp_store_release(p, v) \
+ do { \
+ __sync_synchronize(); \
+ __XSK_WRITE_ONCE(*p, v); \
+ } while (0)
+#endif
+
+#ifndef libbpf_smp_load_acquire
+#define libbpf_smp_load_acquire(p) \
+ ({ \
+ typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \
+ __sync_synchronize(); \
+ ___p1; \
+ })
+#endif
+
+/* LIBRARY INTERNAL -- END */
+
/* Do not access these members directly. Use the functions below. */
#define DEFINE_XSK_RING(name) \
struct name { \
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 068cdb41f76f..5e5388a38e2a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2442,6 +2442,9 @@ static int handle_insn_ops(struct instruction *insn, struct insn_state *state)
if (update_cfi_state(insn, &state->cfi, op))
return 1;
+ if (!insn->alt_group)
+ continue;
+
if (op->dest.type == OP_DEST_PUSHF) {
if (!state->uaccess_stack) {
state->uaccess_stack = 1;
diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index ace8772a4f03..7c4a9d424a64 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -402,35 +402,42 @@ static pid_t handle_signalfd(struct daemon *daemon)
int status;
pid_t pid;
+ /*
+ * Take signal fd data as pure signal notification and check all
+ * the sessions state. The reason is that multiple signals can get
+ * coalesced in kernel and we can receive only single signal even
+ * if multiple SIGCHLD were generated.
+ */
err = read(daemon->signal_fd, &si, sizeof(struct signalfd_siginfo));
- if (err != sizeof(struct signalfd_siginfo))
+ if (err != sizeof(struct signalfd_siginfo)) {
+ pr_err("failed to read signal fd\n");
return -1;
+ }
list_for_each_entry(session, &daemon->sessions, list) {
+ if (session->pid == -1)
+ continue;
- if (session->pid != (int) si.ssi_pid)
+ pid = waitpid(session->pid, &status, WNOHANG);
+ if (pid <= 0)
continue;
- pid = waitpid(session->pid, &status, 0);
- if (pid == session->pid) {
- if (WIFEXITED(status)) {
- pr_info("session '%s' exited, status=%d\n",
- session->name, WEXITSTATUS(status));
- } else if (WIFSIGNALED(status)) {
- pr_info("session '%s' killed (signal %d)\n",
- session->name, WTERMSIG(status));
- } else if (WIFSTOPPED(status)) {
- pr_info("session '%s' stopped (signal %d)\n",
- session->name, WSTOPSIG(status));
- } else {
- pr_info("session '%s' Unexpected status (0x%x)\n",
- session->name, status);
- }
+ if (WIFEXITED(status)) {
+ pr_info("session '%s' exited, status=%d\n",
+ session->name, WEXITSTATUS(status));
+ } else if (WIFSIGNALED(status)) {
+ pr_info("session '%s' killed (signal %d)\n",
+ session->name, WTERMSIG(status));
+ } else if (WIFSTOPPED(status)) {
+ pr_info("session '%s' stopped (signal %d)\n",
+ session->name, WSTOPSIG(status));
+ } else {
+ pr_info("session '%s' Unexpected status (0x%x)\n",
+ session->name, status);
}
session->state = KILL;
session->pid = -1;
- return pid;
}
return 0;
@@ -443,7 +450,6 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
.fd = daemon->signal_fd,
.events = POLLIN,
};
- pid_t wpid = 0, pid = session->pid;
time_t start;
start = time(NULL);
@@ -452,7 +458,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
int err = poll(&pollfd, 1, 1000);
if (err > 0) {
- wpid = handle_signalfd(daemon);
+ handle_signalfd(daemon);
} else if (err < 0) {
perror("failed: poll\n");
return -1;
@@ -460,7 +466,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
if (start + secs < time(NULL))
return -1;
- } while (wpid != pid);
+ } while (session->pid != -1);
return 0;
}
@@ -902,7 +908,9 @@ static void daemon_session__kill(struct daemon_session *session,
daemon_session__signal(session, SIGKILL);
break;
default:
- break;
+ pr_err("failed to wait for session %s\n",
+ session->name);
+ return;
}
how++;
@@ -955,7 +963,8 @@ static void daemon__kill(struct daemon *daemon)
daemon__signal(daemon, SIGKILL);
break;
default:
- break;
+ pr_err("failed to wait for sessions\n");
+ return;
}
how++;
@@ -1344,7 +1353,7 @@ out:
close(sock_fd);
if (conf_fd != -1)
close(conf_fd);
- if (conf_fd != -1)
+ if (signal_fd != -1)
close(signal_fd);
pr_info("daemon exited\n");
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index f57e075b0ed2..c72adbd67386 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -86,7 +86,7 @@ static struct {
.msg_load_fail = "check your vmlinux setting?",
.target_func = &epoll_pwait_loop,
.expect_result = (NR_ITERS + 1) / 2,
- .pin = true,
+ .pin = true,
},
#ifdef HAVE_BPF_PROLOGUE
{
@@ -99,13 +99,6 @@ static struct {
.expect_result = (NR_ITERS + 1) / 4,
},
#endif
- {
- .prog_id = LLVM_TESTCASE_BPF_RELOCATION,
- .desc = "BPF relocation checker",
- .name = "[bpf_relocation_test]",
- .msg_compile_fail = "fix 'perf test LLVM' first",
- .msg_load_fail = "libbpf error when dealing with relocation",
- },
};
static int do_test(struct bpf_object *obj, int (*func)(void),
diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index 5ad3ca8d681b..58984380b211 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
# daemon operations
# SPDX-License-Identifier: GPL-2.0
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 953f4afacd3b..5b6ccb90b397 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -298,10 +298,6 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
queue->set = true;
queue->tid = buffer->tid;
queue->cpu = buffer->cpu;
- } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
- pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
- queue->cpu, queue->tid, buffer->cpu, buffer->tid);
- return -EINVAL;
}
buffer->buffer_nr = queues->next_buffer_nr++;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 57d58c81a5f8..cdecda1ddd36 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -196,25 +196,32 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
}
if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+ free(info_linear);
pr_debug("%s: the kernel is too old, aborting\n", __func__);
return -2;
}
info = &info_linear->info;
+ if (!info->jited_ksyms) {
+ free(info_linear);
+ return -1;
+ }
/* number of ksyms, func_lengths, and tags should match */
sub_prog_cnt = info->nr_jited_ksyms;
if (sub_prog_cnt != info->nr_prog_tags ||
- sub_prog_cnt != info->nr_jited_func_lens)
+ sub_prog_cnt != info->nr_jited_func_lens) {
+ free(info_linear);
return -1;
+ }
/* check BTF func info support */
if (info->btf_id && info->nr_func_info && info->func_info_rec_size) {
/* btf func info number should be same as sub_prog_cnt */
if (sub_prog_cnt != info->nr_func_info) {
pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
- err = -1;
- goto out;
+ free(info_linear);
+ return -1;
}
if (btf__get_from_id(info->btf_id, &btf)) {
pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 42c84adeb2fb..c0c0fab22cb8 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -356,6 +356,9 @@ __add_event(struct list_head *list, int *idx,
struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
+ if (pmu && attr->type == PERF_TYPE_RAW)
+ perf_pmu__warn_invalid_config(pmu, attr->config, name);
+
if (init_attr)
event_attr_init(attr);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 44ef28302fc7..46fd0f998484 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1812,3 +1812,36 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu)
return nr_caps;
}
+
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+ char *name)
+{
+ struct perf_pmu_format *format;
+ __u64 masks = 0, bits;
+ char buf[100];
+ unsigned int i;
+
+ list_for_each_entry(format, &pmu->format, list) {
+ if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG)
+ continue;
+
+ for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS)
+ masks |= 1ULL << i;
+ }
+
+ /*
+ * Kernel doesn't export any valid format bits.
+ */
+ if (masks == 0)
+ return;
+
+ bits = config & ~masks;
+ if (bits == 0)
+ return;
+
+ bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf));
+
+ pr_warning("WARNING: event '%s' not valid (bits %s of config "
+ "'%llx' not supported by kernel)!\n",
+ name ?: "N/A", buf, config);
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 8164388478c6..160b0f561771 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -123,4 +123,7 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
int perf_pmu__caps_parse(struct perf_pmu *pmu);
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+ char *name);
+
#endif /* __PMU_H */
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index b698046ec2db..dff178103ce5 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -424,7 +424,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
while (!io.eof) {
static const char anonstr[] = "//anon";
- size_t size;
+ size_t size, aligned_size;
/* ensure null termination since stack will be reused. */
event->mmap2.filename[0] = '\0';
@@ -484,11 +484,12 @@ out:
}
size = strlen(event->mmap2.filename) + 1;
- size = PERF_ALIGN(size, sizeof(u64));
+ aligned_size = PERF_ALIGN(size, sizeof(u64));
event->mmap2.len -= event->mmap.start;
event->mmap2.header.size = (sizeof(event->mmap2) -
- (sizeof(event->mmap2.filename) - size));
- memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+ (sizeof(event->mmap2.filename) - aligned_size));
+ memset(event->mmap2.filename + size, 0, machine->id_hdr_size +
+ (aligned_size - size));
event->mmap2.header.size += machine->id_hdr_size;
event->mmap2.pid = tgid;
event->mmap2.tid = pid;
@@ -758,7 +759,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
for (i = 0; i < n; i++) {
char *end;
pid_t _pid;
- bool kernel_thread;
+ bool kernel_thread = false;
_pid = strtol(dirent[i]->d_name, &end, 10);
if (*end)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 3cc91ad048ea..43beb169631d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -133,6 +133,8 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
if (dso != NULL) {
__dsos__add(&machine->dsos, dso);
dso__set_long_name(dso, long_name, false);
+ /* Put dso here because __dsos_add already got it */
+ dso__put(dso);
}
return dso;
diff --git a/tools/testing/kunit/configs/broken_on_uml.config b/tools/testing/kunit/configs/broken_on_uml.config
index a7f0603d33f6..690870043ac0 100644
--- a/tools/testing/kunit/configs/broken_on_uml.config
+++ b/tools/testing/kunit/configs/broken_on_uml.config
@@ -40,3 +40,5 @@
# CONFIG_RESET_BRCMSTB_RESCAL is not set
# CONFIG_RESET_INTEL_GW is not set
# CONFIG_ADI_AXI_ADC is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_PAGE_POISONING is not set
diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py
index 0b550cbd667d..1e2683dcc0e7 100644
--- a/tools/testing/kunit/kunit_config.py
+++ b/tools/testing/kunit/kunit_config.py
@@ -13,7 +13,7 @@ from typing import List, Set
CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$'
CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$'
-KconfigEntryBase = collections.namedtuple('KconfigEntry', ['name', 'value'])
+KconfigEntryBase = collections.namedtuple('KconfigEntryBase', ['name', 'value'])
class KconfigEntry(KconfigEntryBase):
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 3b796dd5e577..ca24f6839d50 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -296,21 +296,34 @@ static void *idr_throbber(void *arg)
return NULL;
}
+/*
+ * There are always either 1 or 2 objects in the IDR. If we find nothing,
+ * or we find something at an ID we didn't expect, that's a bug.
+ */
void idr_find_test_1(int anchor_id, int throbber_id)
{
pthread_t throbber;
time_t start = time(NULL);
- pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
-
BUG_ON(idr_alloc(&find_idr, xa_mk_value(anchor_id), anchor_id,
anchor_id + 1, GFP_KERNEL) != anchor_id);
+ pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
+
+ rcu_read_lock();
do {
int id = 0;
void *entry = idr_get_next(&find_idr, &id);
- BUG_ON(entry != xa_mk_value(id));
+ rcu_read_unlock();
+ if ((id != anchor_id && id != throbber_id) ||
+ entry != xa_mk_value(id)) {
+ printf("%s(%d, %d): %p at %d\n", __func__, anchor_id,
+ throbber_id, entry, id);
+ abort();
+ }
+ rcu_read_lock();
} while (time(NULL) < start + 11);
+ rcu_read_unlock();
pthread_join(throbber, NULL);
@@ -577,6 +590,7 @@ void ida_tests(void)
int __weak main(void)
{
+ rcu_register_thread();
radix_tree_init();
idr_checks();
ida_tests();
@@ -584,5 +598,6 @@ int __weak main(void)
rcu_barrier();
if (nr_allocated)
printf("nr_allocated = %d\n", nr_allocated);
+ rcu_unregister_thread();
return 0;
}
diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/tools/testing/radix-tree/linux/compiler_types.h
+++ /dev/null
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 9eae0fb5a67d..e00520cc6349 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -224,7 +224,9 @@ void multiorder_checks(void)
int __weak main(void)
{
+ rcu_register_thread();
radix_tree_init();
multiorder_checks();
+ rcu_unregister_thread();
return 0;
}
diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c
index e61e43efe463..f20e12cbbfd4 100644
--- a/tools/testing/radix-tree/xarray.c
+++ b/tools/testing/radix-tree/xarray.c
@@ -25,11 +25,13 @@ void xarray_tests(void)
int __weak main(void)
{
+ rcu_register_thread();
radix_tree_init();
xarray_tests();
radix_tree_cpu_dead(1);
rcu_barrier();
if (nr_allocated)
printf("nr_allocated = %d\n", nr_allocated);
+ rcu_unregister_thread();
return 0;
}
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index b2282be6f938..612d3899614a 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -332,5 +332,5 @@ int main(void)
ksft_print_cnts();
- return 0;
+ return ret;
}
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 9210691aa998..e3e08d9c7020 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -284,16 +284,28 @@ endfunction
// Set up test pattern in the FFR
// x0: pid
// x2: generation
+//
+// We need to generate a canonical FFR value, which consists of a number of
+// low "1" bits, followed by a number of zeros. This gives us 17 unique values
+// per 16 bits of FFR, so we create a 4 bit signature out of the PID and
+// generation, and use that as the initial number of ones in the pattern.
+// We fill the upper lanes of FFR with zeros.
// Beware: corrupts P0.
function setup_ffr
mov x4, x30
- bl pattern
+ and w0, w0, #0x3
+ bfi w0, w2, #2, #2
+ mov w1, #1
+ lsl w1, w1, w0
+ sub w1, w1, #1
+
ldr x0, =ffrref
- ldr x1, =scratch
- rdvl x2, #1
- lsr x2, x2, #3
- bl memcpy
+ strh w1, [x0], 2
+ rdvl x1, #1
+ lsr x1, x1, #3
+ sub x1, x1, #2
+ bl memclr
mov x0, #0
ldr x1, =ffrref
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c3999587bc23..6448c626498f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -21,7 +21,7 @@ endif
BPF_GCC ?= $(shell command -v bpf-gcc;)
SAN_CFLAGS ?=
-CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) $(SAN_CFLAGS) \
+CFLAGS += -g -Og -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \
-I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \
-I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) \
-Dbpf_prog_load=bpf_prog_test_load \
@@ -201,6 +201,7 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \
$(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
$(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
CC=$(HOSTCC) LD=$(HOSTLD) \
+ EXTRA_CFLAGS='-g -Og' \
OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \
prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
@@ -218,6 +219,7 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
../../../include/uapi/linux/bpf.h \
| $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
+ EXTRA_CFLAGS='-g -Og' \
DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
@@ -225,11 +227,12 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
../../../include/uapi/linux/bpf.h \
| $(INCLUDE_DIR) $(HOST_BUILD_DIR)/libbpf
$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \
- OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
+ EXTRA_CFLAGS='-g -Og' \
+ OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
endif
-$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR)
+$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
ifeq ($(VMLINUX_H),)
$(call msg,GEN,,$@)
$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
@@ -300,6 +303,10 @@ endef
SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
+LINKED_SKELS := test_static_linked.skel.h
+
+test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
+
# Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
# $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
# Parameters:
@@ -320,6 +327,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)
TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \
$$(filter-out $(SKEL_BLACKLIST), \
$$(TRUNNER_BPF_SRCS)))
+TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
# Evaluate rules now with extra TRUNNER_XXX variables above already defined
@@ -352,11 +360,22 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \
$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \
$(TRUNNER_BPF_CFLAGS))
-$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h: \
- $(TRUNNER_OUTPUT)/%.o \
- | $(BPFTOOL) $(TRUNNER_OUTPUT)
+$(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
+ $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
+ $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked1.o) $$<
+ $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked1.o)
+ $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o)
+ $(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
+ $(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@
+
+$(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
+ $$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.o))
+ $(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked1.o) $$(addprefix $(TRUNNER_OUTPUT)/,$$($$(@F)-deps))
+ $(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked1.o)
+ $(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked3.o) $$(@:.skel.h=.linked2.o)
+ $(Q)diff $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked3.o)
$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
- $(Q)$$(BPFTOOL) gen skeleton $$< > $$@
+ $(Q)$$(BPFTOOL) gen skeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$@
endif
# ensure we set up tests.h header generation rule just once
@@ -378,6 +397,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \
$(TRUNNER_EXTRA_HDRS) \
$(TRUNNER_BPF_OBJS) \
$(TRUNNER_BPF_SKELS) \
+ $(TRUNNER_BPF_SKELS_LINKED) \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
$(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 3464161c8eea..65fe318d1e71 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -179,3 +179,17 @@ types, which was introduced in `Clang 13`__. The older Clang versions will
either crash when compiling these tests, or generate an incorrect BTF.
__ https://reviews.llvm.org/D83289
+
+Kernel function call test and Clang version
+===========================================
+
+Some selftests (e.g. kfunc_call and bpf_tcp_ca) require a LLVM support
+to generate extern function in BTF. It was introduced in `Clang 13`__.
+
+Without it, the error from compiling bpf selftests looks like:
+
+.. code-block:: console
+
+ libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2
+
+__ https://reviews.llvm.org/D93563
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 91f0fac632f4..029589c008c9 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -187,16 +187,6 @@ struct tcp_congestion_ops {
typeof(y) __y = (y); \
__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
-static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked)
-{
- __u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh);
-
- acked -= cwnd - tp->snd_cwnd;
- tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
-
- return acked;
-}
-
static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp)
{
return tp->snd_cwnd < tp->snd_ssthresh;
@@ -213,22 +203,7 @@ static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
}
-static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked)
-{
- /* If credits accumulated at a higher w, apply them gently now. */
- if (tp->snd_cwnd_cnt >= w) {
- tp->snd_cwnd_cnt = 0;
- tp->snd_cwnd++;
- }
-
- tp->snd_cwnd_cnt += acked;
- if (tp->snd_cwnd_cnt >= w) {
- __u32 delta = tp->snd_cwnd_cnt / w;
-
- tp->snd_cwnd_cnt -= delta * w;
- tp->snd_cwnd += delta;
- }
- tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
-}
+extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym;
+extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym;
#endif
diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c
index b8d6aef99db4..99628e1a1e58 100644
--- a/tools/testing/selftests/bpf/get_cgroup_id_user.c
+++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c
@@ -57,6 +57,10 @@ int main(int argc, char **argv)
__u32 key = 0, pid;
int exit_code = 1;
char buf[256];
+ const struct timespec req = {
+ .tv_sec = 1,
+ .tv_nsec = 0,
+ };
cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
if (CHECK(cgroup_fd < 0, "cgroup_setup_and_join", "err %d errno %d\n", cgroup_fd, errno))
@@ -115,7 +119,7 @@ int main(int argc, char **argv)
goto close_pmu;
/* trigger some syscalls */
- sleep(1);
+ syscall(__NR_nanosleep, &req, NULL);
err = bpf_map_lookup_elem(cgidmap_fd, &key, &kcgid);
if (CHECK(err, "bpf_map_lookup_elem", "err %d errno %d\n", err, errno))
diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
index f0a64d8ac59a..e42ea1195d18 100644
--- a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
@@ -55,7 +55,6 @@ void test_array_map_batch_ops(void)
int map_fd, *keys, *values, *visited;
__u32 count, total, total_success;
const __u32 max_entries = 10;
- bool nospace_err;
__u64 batch = 0;
int err, step;
DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
@@ -90,7 +89,6 @@ void test_array_map_batch_ops(void)
* elements each.
*/
count = step;
- nospace_err = false;
while (true) {
err = bpf_map_lookup_batch(map_fd,
total ? &batch : NULL, &batch,
@@ -107,9 +105,6 @@ void test_array_map_batch_ops(void)
}
- if (nospace_err == true)
- continue;
-
CHECK(total != max_entries, "lookup with steps",
"total = %u, max_entries = %u\n", total, max_entries);
diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
new file mode 100644
index 000000000000..2e986e5e4cac
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <arpa/inet.h>
+#include <linux/bpf.h>
+#include <netinet/in.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_maps.h>
+
+struct test_lpm_key {
+ __u32 prefix;
+ struct in_addr ipv4;
+};
+
+static void map_batch_update(int map_fd, __u32 max_entries,
+ struct test_lpm_key *keys, int *values)
+{
+ __u32 i;
+ int err;
+ char buff[16] = { 0 };
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ for (i = 0; i < max_entries; i++) {
+ keys[i].prefix = 32;
+ snprintf(buff, 16, "192.168.1.%d", i + 1);
+ inet_pton(AF_INET, buff, &keys[i].ipv4);
+ values[i] = i + 1;
+ }
+
+ err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+ CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+ struct test_lpm_key *keys, int *values)
+{
+ char buff[16] = { 0 };
+ int lower_byte = 0;
+ __u32 i;
+
+ memset(visited, 0, max_entries * sizeof(*visited));
+ for (i = 0; i < max_entries; i++) {
+ inet_ntop(AF_INET, &keys[i].ipv4, buff, 32);
+ CHECK(sscanf(buff, "192.168.1.%d", &lower_byte) == EOF,
+ "sscanf()", "error: i %d\n", i);
+ CHECK(lower_byte != values[i], "key/value checking",
+ "error: i %d key %s value %d\n", i, buff, values[i]);
+ visited[i] = 1;
+ }
+ for (i = 0; i < max_entries; i++) {
+ CHECK(visited[i] != 1, "visited checking",
+ "error: keys array at index %d missing\n", i);
+ }
+}
+
+void test_lpm_trie_map_batch_ops(void)
+{
+ struct bpf_create_map_attr xattr = {
+ .name = "lpm_trie_map",
+ .map_type = BPF_MAP_TYPE_LPM_TRIE,
+ .key_size = sizeof(struct test_lpm_key),
+ .value_size = sizeof(int),
+ .map_flags = BPF_F_NO_PREALLOC,
+ };
+ struct test_lpm_key *keys, key;
+ int map_fd, *values, *visited;
+ __u32 step, count, total, total_success;
+ const __u32 max_entries = 10;
+ __u64 batch = 0;
+ int err;
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ xattr.max_entries = max_entries;
+ map_fd = bpf_create_map_xattr(&xattr);
+ CHECK(map_fd == -1, "bpf_create_map_xattr()", "error:%s\n",
+ strerror(errno));
+
+ keys = malloc(max_entries * sizeof(struct test_lpm_key));
+ values = malloc(max_entries * sizeof(int));
+ visited = malloc(max_entries * sizeof(int));
+ CHECK(!keys || !values || !visited, "malloc()", "error:%s\n",
+ strerror(errno));
+
+ total_success = 0;
+ for (step = 1; step < max_entries; step++) {
+ map_batch_update(map_fd, max_entries, keys, values);
+ map_batch_verify(visited, max_entries, keys, values);
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * sizeof(*values));
+ batch = 0;
+ total = 0;
+ /* iteratively lookup/delete elements with 'step'
+ * elements each.
+ */
+ count = step;
+ while (true) {
+ err = bpf_map_lookup_batch(map_fd,
+ total ? &batch : NULL, &batch,
+ keys + total, values + total, &count, &opts);
+
+ CHECK((err && errno != ENOENT), "lookup with steps",
+ "error: %s\n", strerror(errno));
+
+ total += count;
+ if (err)
+ break;
+ }
+
+ CHECK(total != max_entries, "lookup with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+
+ map_batch_verify(visited, max_entries, keys, values);
+
+ total = 0;
+ count = step;
+ while (total < max_entries) {
+ if (max_entries - total < step)
+ count = max_entries - total;
+ err = bpf_map_delete_batch(map_fd, keys + total, &count,
+ &opts);
+ CHECK((err && errno != ENOENT), "delete batch",
+ "error: %s\n", strerror(errno));
+ total += count;
+ if (err)
+ break;
+ }
+ CHECK(total != max_entries, "delete with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+
+ /* check map is empty, errono == ENOENT */
+ err = bpf_map_get_next_key(map_fd, NULL, &key);
+ CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
+ "error: %s\n", strerror(errno));
+
+ total_success++;
+ }
+
+ CHECK(total_success == 0, "check total_success",
+ "unexpected failure\n");
+
+ printf("%s:PASS\n", __func__);
+
+ free(keys);
+ free(values);
+ free(visited);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 37c5494a0381..e25917f04602 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -6,6 +6,7 @@
#include <test_progs.h>
#include "bpf_dctcp.skel.h"
#include "bpf_cubic.skel.h"
+#include "bpf_tcp_nogpl.skel.h"
#define min(a, b) ((a) < (b) ? (a) : (b))
@@ -227,10 +228,53 @@ static void test_dctcp(void)
bpf_dctcp__destroy(dctcp_skel);
}
+static char *err_str;
+static bool found;
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ char *log_buf;
+
+ if (level != LIBBPF_WARN ||
+ strcmp(format, "libbpf: \n%s\n")) {
+ vprintf(format, args);
+ return 0;
+ }
+
+ log_buf = va_arg(args, char *);
+ if (!log_buf)
+ goto out;
+ if (err_str && strstr(log_buf, err_str) != NULL)
+ found = true;
+out:
+ printf(format, log_buf);
+ return 0;
+}
+
+static void test_invalid_license(void)
+{
+ libbpf_print_fn_t old_print_fn;
+ struct bpf_tcp_nogpl *skel;
+
+ err_str = "struct ops programs must have a GPL compatible license";
+ found = false;
+ old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+ skel = bpf_tcp_nogpl__open_and_load();
+ ASSERT_NULL(skel, "bpf_tcp_nogpl");
+ ASSERT_EQ(found, true, "expected_err_msg");
+
+ bpf_tcp_nogpl__destroy(skel);
+ libbpf_set_print(old_print_fn);
+}
+
void test_bpf_tcp_ca(void)
{
if (test__start_subtest("dctcp"))
test_dctcp();
if (test__start_subtest("cubic"))
test_cubic();
+ if (test__start_subtest("invalid_license"))
+ test_invalid_license();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
index 36af1c138faf..b62a39315336 100644
--- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c
+++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
@@ -128,6 +128,8 @@ static void test_check_mtu_xdp(__u32 mtu, __u32 ifindex)
test_check_mtu_run_xdp(skel, skel->progs.xdp_use_helper, mtu);
test_check_mtu_run_xdp(skel, skel->progs.xdp_exceed_mtu, mtu);
test_check_mtu_run_xdp(skel, skel->progs.xdp_minus_delta, mtu);
+ test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len, mtu);
+ test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len_exceed, mtu);
cleanup:
test_check_mtu__destroy(skel);
@@ -187,6 +189,8 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex)
test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu, mtu);
test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu_da, mtu);
test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu);
+ test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu);
+ test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu);
cleanup:
test_check_mtu__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
new file mode 100644
index 000000000000..6c4d42a2386f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <test_progs.h>
+#include <time.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include "fexit_sleep.skel.h"
+
+static int do_sleep(void *skel)
+{
+ struct fexit_sleep *fexit_skel = skel;
+ struct timespec ts1 = { .tv_nsec = 1 };
+ struct timespec ts2 = { .tv_sec = 10 };
+
+ fexit_skel->bss->pid = getpid();
+ (void)syscall(__NR_nanosleep, &ts1, NULL);
+ (void)syscall(__NR_nanosleep, &ts2, NULL);
+ return 0;
+}
+
+#define STACK_SIZE (1024 * 1024)
+static char child_stack[STACK_SIZE];
+
+void test_fexit_sleep(void)
+{
+ struct fexit_sleep *fexit_skel = NULL;
+ int wstatus, duration = 0;
+ pid_t cpid;
+ int err, fexit_cnt;
+
+ fexit_skel = fexit_sleep__open_and_load();
+ if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
+ goto cleanup;
+
+ err = fexit_sleep__attach(fexit_skel);
+ if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
+ goto cleanup;
+
+ cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
+ if (CHECK(cpid == -1, "clone", strerror(errno)))
+ goto cleanup;
+
+ /* wait until first sys_nanosleep ends and second sys_nanosleep starts */
+ while (READ_ONCE(fexit_skel->bss->fentry_cnt) != 2);
+ fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt);
+ if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt))
+ goto cleanup;
+
+ /* close progs and detach them. That will trigger two nop5->jmp5 rewrites
+ * in the trampolines to skip nanosleep_fexit prog.
+ * The nanosleep_fentry prog will get detached first.
+ * The nanosleep_fexit prog will get detached second.
+ * Detaching will trigger freeing of both progs JITed images.
+ * There will be two dying bpf_tramp_image-s, but only the initial
+ * bpf_tramp_image (with both _fentry and _fexit progs will be stuck
+ * waiting for percpu_ref_kill to confirm). The other one
+ * will be freed quickly.
+ */
+ close(bpf_program__fd(fexit_skel->progs.nanosleep_fentry));
+ close(bpf_program__fd(fexit_skel->progs.nanosleep_fexit));
+ fexit_sleep__detach(fexit_skel);
+
+ /* kill the thread to unwind sys_nanosleep stack through the trampoline */
+ kill(cpid, 9);
+
+ if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
+ goto cleanup;
+ if (CHECK(WEXITSTATUS(wstatus) != 0, "exitstatus", "failed"))
+ goto cleanup;
+
+ /* The bypassed nanosleep_fexit prog shouldn't have executed.
+ * Unlike progs the maps were not freed and directly accessible.
+ */
+ fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt);
+ if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt))
+ goto cleanup;
+
+cleanup:
+ fexit_sleep__destroy(fexit_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
new file mode 100644
index 000000000000..7fc0951ee75f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "kfunc_call_test.skel.h"
+#include "kfunc_call_test_subprog.skel.h"
+
+static void test_main(void)
+{
+ struct kfunc_call_test *skel;
+ int prog_fd, retval, err;
+
+ skel = kfunc_call_test__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel"))
+ return;
+
+ prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1);
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, (__u32 *)&retval, NULL);
+ ASSERT_OK(err, "bpf_prog_test_run(test1)");
+ ASSERT_EQ(retval, 12, "test1-retval");
+
+ prog_fd = bpf_program__fd(skel->progs.kfunc_call_test2);
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, (__u32 *)&retval, NULL);
+ ASSERT_OK(err, "bpf_prog_test_run(test2)");
+ ASSERT_EQ(retval, 3, "test2-retval");
+
+ kfunc_call_test__destroy(skel);
+}
+
+static void test_subprog(void)
+{
+ struct kfunc_call_test_subprog *skel;
+ int prog_fd, retval, err;
+
+ skel = kfunc_call_test_subprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel"))
+ return;
+
+ prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1);
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, (__u32 *)&retval, NULL);
+ ASSERT_OK(err, "bpf_prog_test_run(test1)");
+ ASSERT_EQ(retval, 10, "test1-retval");
+ ASSERT_NEQ(skel->data->active_res, -1, "active_res");
+ ASSERT_EQ(skel->data->sk_state, BPF_TCP_CLOSE, "sk_state");
+
+ kfunc_call_test_subprog__destroy(skel);
+}
+
+void test_kfunc_call(void)
+{
+ if (test__start_subtest("main"))
+ test_main();
+
+ if (test__start_subtest("subprog"))
+ test_subprog();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index b8b48cac2ac3..ab77596b64e3 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -7,6 +7,7 @@
#include "test_skmsg_load_helpers.skel.h"
#include "test_sockmap_update.skel.h"
#include "test_sockmap_invalid_update.skel.h"
+#include "test_sockmap_skb_verdict_attach.skel.h"
#include "bpf_iter_sockmap.skel.h"
#define TCP_REPAIR 19 /* TCP sock is under repair right now */
@@ -281,6 +282,39 @@ out:
bpf_iter_sockmap__destroy(skel);
}
+static void test_sockmap_skb_verdict_attach(enum bpf_attach_type first,
+ enum bpf_attach_type second)
+{
+ struct test_sockmap_skb_verdict_attach *skel;
+ int err, map, verdict;
+
+ skel = test_sockmap_skb_verdict_attach__open_and_load();
+ if (CHECK_FAIL(!skel)) {
+ perror("test_sockmap_skb_verdict_attach__open_and_load");
+ return;
+ }
+
+ verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ map = bpf_map__fd(skel->maps.sock_map);
+
+ err = bpf_prog_attach(verdict, map, first, 0);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_prog_attach");
+ goto out;
+ }
+
+ err = bpf_prog_attach(verdict, map, second, 0);
+ assert(err == -1 && errno == EBUSY);
+
+ err = bpf_prog_detach2(verdict, map, first);
+ if (CHECK_FAIL(err)) {
+ perror("bpf_prog_detach2");
+ goto out;
+ }
+out:
+ test_sockmap_skb_verdict_attach__destroy(skel);
+}
+
void test_sockmap_basic(void)
{
if (test__start_subtest("sockmap create_update_free"))
@@ -301,4 +335,10 @@ void test_sockmap_basic(void)
test_sockmap_copy(BPF_MAP_TYPE_SOCKMAP);
if (test__start_subtest("sockhash copy"))
test_sockmap_copy(BPF_MAP_TYPE_SOCKHASH);
+ if (test__start_subtest("sockmap skb_verdict attach")) {
+ test_sockmap_skb_verdict_attach(BPF_SK_SKB_VERDICT,
+ BPF_SK_SKB_STREAM_VERDICT);
+ test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT,
+ BPF_SK_SKB_VERDICT);
+ }
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index c26e6bf05e49..648d9ae898d2 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1603,6 +1603,141 @@ static void test_reuseport(struct test_sockmap_listen *skel,
}
}
+static void udp_redir_to_connected(int family, int sotype, int sock_mapfd,
+ int verd_mapfd, enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ struct sockaddr_storage addr;
+ int c0, c1, p0, p1;
+ unsigned int pass;
+ socklen_t len;
+ int err, n;
+ u64 value;
+ u32 key;
+ char b;
+
+ zero_verdict_count(verd_mapfd);
+
+ p0 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (p0 < 0)
+ return;
+ len = sizeof(addr);
+ err = xgetsockname(p0, sockaddr(&addr), &len);
+ if (err)
+ goto close_peer0;
+
+ c0 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
+ if (c0 < 0)
+ goto close_peer0;
+ err = xconnect(c0, sockaddr(&addr), len);
+ if (err)
+ goto close_cli0;
+ err = xgetsockname(c0, sockaddr(&addr), &len);
+ if (err)
+ goto close_cli0;
+ err = xconnect(p0, sockaddr(&addr), len);
+ if (err)
+ goto close_cli0;
+
+ p1 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (p1 < 0)
+ goto close_cli0;
+ err = xgetsockname(p1, sockaddr(&addr), &len);
+ if (err)
+ goto close_cli0;
+
+ c1 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
+ if (c1 < 0)
+ goto close_peer1;
+ err = xconnect(c1, sockaddr(&addr), len);
+ if (err)
+ goto close_cli1;
+ err = xgetsockname(c1, sockaddr(&addr), &len);
+ if (err)
+ goto close_cli1;
+ err = xconnect(p1, sockaddr(&addr), len);
+ if (err)
+ goto close_cli1;
+
+ key = 0;
+ value = p0;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_cli1;
+
+ key = 1;
+ value = p1;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_cli1;
+
+ n = write(c1, "a", 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: write", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete write", log_prefix);
+ if (n < 1)
+ goto close_cli1;
+
+ key = SK_PASS;
+ err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
+ if (err)
+ goto close_cli1;
+ if (pass != 1)
+ FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+
+ n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: read", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete read", log_prefix);
+
+close_cli1:
+ xclose(c1);
+close_peer1:
+ xclose(p1);
+close_cli0:
+ xclose(c0);
+close_peer0:
+ xclose(p0);
+}
+
+static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int family)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
+ if (err)
+ return;
+
+ skel->bss->test_ingress = false;
+ udp_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+ REDIR_EGRESS);
+ skel->bss->test_ingress = true;
+ udp_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+ REDIR_INGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
+}
+
+static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
+ int family)
+{
+ const char *family_name, *map_name;
+ char s[MAX_TEST_NAME];
+
+ family_name = family_str(family);
+ map_name = map_type_str(map);
+ snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
+ if (!test__start_subtest(s))
+ return;
+ udp_skb_redir_to_connected(skel, map, family);
+}
+
static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
int family)
{
@@ -1611,6 +1746,7 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
test_redir(skel, map, family, SOCK_STREAM);
test_reuseport(skel, map, family, SOCK_STREAM);
test_reuseport(skel, map, family, SOCK_DGRAM);
+ test_udp_redir(skel, map, family);
}
void test_sockmap_listen(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/static_linked.c b/tools/testing/selftests/bpf/prog_tests/static_linked.c
new file mode 100644
index 000000000000..46556976dccc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/static_linked.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <test_progs.h>
+#include "test_static_linked.skel.h"
+
+void test_static_linked(void)
+{
+ int err;
+ struct test_static_linked* skel;
+
+ skel = test_static_linked__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->rodata->rovar1 = 1;
+ skel->bss->static_var1 = 2;
+ skel->bss->static_var11 = 3;
+
+ skel->rodata->rovar2 = 4;
+ skel->bss->static_var2 = 5;
+ skel->bss->static_var22 = 6;
+
+ err = test_static_linked__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ err = test_static_linked__attach(skel);
+ if (!ASSERT_OK(err, "skel_attach"))
+ goto cleanup;
+
+ /* trigger */
+ usleep(1);
+
+ ASSERT_EQ(skel->bss->var1, 1 * 2 + 2 + 3, "var1");
+ ASSERT_EQ(skel->bss->var2, 4 * 3 + 5 + 6, "var2");
+
+cleanup:
+ test_static_linked__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
index b54bc0c351b7..0252f61d611a 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_ima.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -68,7 +68,8 @@ void test_test_ima(void)
goto close_prog;
snprintf(cmd, sizeof(cmd), "./ima_setup.sh setup %s", measured_dir);
- if (CHECK_FAIL(system(cmd)))
+ err = system(cmd);
+ if (CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno))
goto close_clean;
err = run_measured_process(measured_dir, &skel->bss->monitored_pid);
@@ -81,7 +82,8 @@ void test_test_ima(void)
close_clean:
snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir);
- CHECK_FAIL(system(cmd));
+ err = system(cmd);
+ CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno);
close_prog:
ima__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c
index 115a3b0ad984..474c6a62078a 100644
--- a/tools/testing/selftests/bpf/progs/bind4_prog.c
+++ b/tools/testing/selftests/bpf/progs/bind4_prog.c
@@ -57,6 +57,27 @@ static __inline int bind_to_device(struct bpf_sock_addr *ctx)
return 0;
}
+static __inline int bind_reuseport(struct bpf_sock_addr *ctx)
+{
+ int val = 1;
+
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+ &val, sizeof(val)))
+ return 1;
+ if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+ &val, sizeof(val)) || !val)
+ return 1;
+ val = 0;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+ &val, sizeof(val)))
+ return 1;
+ if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+ &val, sizeof(val)) || val)
+ return 1;
+
+ return 0;
+}
+
static __inline int misc_opts(struct bpf_sock_addr *ctx, int opt)
{
int old, tmp, new = 0xeb9f;
@@ -127,6 +148,10 @@ int bind_v4_prog(struct bpf_sock_addr *ctx)
if (misc_opts(ctx, SO_MARK) || misc_opts(ctx, SO_PRIORITY))
return 0;
+ /* Set reuseport and unset */
+ if (bind_reuseport(ctx))
+ return 0;
+
ctx->user_ip4 = bpf_htonl(SERV4_REWRITE_IP);
ctx->user_port = bpf_htons(SERV4_REWRITE_PORT);
diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c
index 4c0d348034b9..c19cfa869f30 100644
--- a/tools/testing/selftests/bpf/progs/bind6_prog.c
+++ b/tools/testing/selftests/bpf/progs/bind6_prog.c
@@ -63,6 +63,27 @@ static __inline int bind_to_device(struct bpf_sock_addr *ctx)
return 0;
}
+static __inline int bind_reuseport(struct bpf_sock_addr *ctx)
+{
+ int val = 1;
+
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+ &val, sizeof(val)))
+ return 1;
+ if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+ &val, sizeof(val)) || !val)
+ return 1;
+ val = 0;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+ &val, sizeof(val)))
+ return 1;
+ if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+ &val, sizeof(val)) || val)
+ return 1;
+
+ return 0;
+}
+
static __inline int misc_opts(struct bpf_sock_addr *ctx, int opt)
{
int old, tmp, new = 0xeb9f;
@@ -141,6 +162,10 @@ int bind_v6_prog(struct bpf_sock_addr *ctx)
if (misc_opts(ctx, SO_MARK) || misc_opts(ctx, SO_PRIORITY))
return 0;
+ /* Set reuseport and unset */
+ if (bind_reuseport(ctx))
+ return 0;
+
ctx->user_ip6[0] = bpf_htonl(SERV6_REWRITE_IP_0);
ctx->user_ip6[1] = bpf_htonl(SERV6_REWRITE_IP_1);
ctx->user_ip6[2] = bpf_htonl(SERV6_REWRITE_IP_2);
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index 6939bfd8690f..f62df4d023f9 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -174,8 +174,8 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk)
* as long as it is used in one of the func ptr
* under SEC(".struct_ops").
*/
-SEC("struct_ops/bictcp_init")
-void BPF_PROG(bictcp_init, struct sock *sk)
+SEC("struct_ops/bpf_cubic_init")
+void BPF_PROG(bpf_cubic_init, struct sock *sk)
{
struct bictcp *ca = inet_csk_ca(sk);
@@ -192,7 +192,7 @@ void BPF_PROG(bictcp_init, struct sock *sk)
* The remaining tcp-cubic functions have an easier way.
*/
SEC("no-sec-prefix-bictcp_cwnd_event")
-void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event)
+void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event)
{
if (event == CA_EVENT_TX_START) {
struct bictcp *ca = inet_csk_ca(sk);
@@ -384,7 +384,7 @@ tcp_friendliness:
}
/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */
-void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+void BPF_STRUCT_OPS(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bictcp *ca = inet_csk_ca(sk);
@@ -403,7 +403,7 @@ void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
tcp_cong_avoid_ai(tp, ca->cnt, acked);
}
-__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
+__u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct bictcp *ca = inet_csk_ca(sk);
@@ -420,7 +420,7 @@ __u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
}
-void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state)
+void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state)
{
if (new_state == TCP_CA_Loss) {
bictcp_reset(inet_csk_ca(sk));
@@ -496,7 +496,7 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay)
}
}
-void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
+void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk,
const struct ack_sample *sample)
{
const struct tcp_sock *tp = tcp_sk(sk);
@@ -525,21 +525,21 @@ void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
hystart_update(sk, delay);
}
-__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
+extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym;
- return max(tp->snd_cwnd, tp->prior_cwnd);
+__u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk)
+{
+ return tcp_reno_undo_cwnd(sk);
}
SEC(".struct_ops")
struct tcp_congestion_ops cubic = {
- .init = (void *)bictcp_init,
- .ssthresh = (void *)bictcp_recalc_ssthresh,
- .cong_avoid = (void *)bictcp_cong_avoid,
- .set_state = (void *)bictcp_state,
- .undo_cwnd = (void *)tcp_reno_undo_cwnd,
- .cwnd_event = (void *)bictcp_cwnd_event,
- .pkts_acked = (void *)bictcp_acked,
+ .init = (void *)bpf_cubic_init,
+ .ssthresh = (void *)bpf_cubic_recalc_ssthresh,
+ .cong_avoid = (void *)bpf_cubic_cong_avoid,
+ .set_state = (void *)bpf_cubic_state,
+ .undo_cwnd = (void *)bpf_cubic_undo_cwnd,
+ .cwnd_event = (void *)bpf_cubic_cwnd_event,
+ .pkts_acked = (void *)bpf_cubic_acked,
.name = "bpf_cubic",
};
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index 4dc1a967776a..fd42247da8b4 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -194,22 +194,12 @@ __u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
}
-SEC("struct_ops/tcp_reno_cong_avoid")
-void BPF_PROG(tcp_reno_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
-{
- struct tcp_sock *tp = tcp_sk(sk);
-
- if (!tcp_is_cwnd_limited(sk))
- return;
+extern void tcp_reno_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym;
- /* In "safe" area, increase. */
- if (tcp_in_slow_start(tp)) {
- acked = tcp_slow_start(tp, acked);
- if (!acked)
- return;
- }
- /* In dangerous area, increase slowly. */
- tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
+SEC("struct_ops/dctcp_reno_cong_avoid")
+void BPF_PROG(dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+ tcp_reno_cong_avoid(sk, ack, acked);
}
SEC(".struct_ops")
@@ -226,7 +216,7 @@ struct tcp_congestion_ops dctcp = {
.in_ack_event = (void *)dctcp_update_alpha,
.cwnd_event = (void *)dctcp_cwnd_event,
.ssthresh = (void *)dctcp_ssthresh,
- .cong_avoid = (void *)tcp_reno_cong_avoid,
+ .cong_avoid = (void *)dctcp_cong_avoid,
.undo_cwnd = (void *)dctcp_cwnd_undo,
.set_state = (void *)dctcp_state,
.flags = TCP_CONG_NEEDS_ECN,
diff --git a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
new file mode 100644
index 000000000000..2ecd833dcd41
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "X";
+
+void BPF_STRUCT_OPS(nogpltcp_init, struct sock *sk)
+{
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops bpf_nogpltcp = {
+ .init = (void *)nogpltcp_init,
+ .name = "bpf_nogpltcp",
+};
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index 12b40dc81e14..8aaa24a00322 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -174,6 +174,12 @@ struct struct_in_struct {
};
};
+struct struct_in_array {};
+
+struct struct_in_array_typed {};
+
+typedef struct struct_in_array_typed struct_in_array_t[2];
+
struct struct_with_embedded_stuff {
int a;
struct {
@@ -203,6 +209,8 @@ struct struct_with_embedded_stuff {
} r[5];
struct struct_in_struct s[10];
int t[11];
+ struct struct_in_array (*u)[2];
+ struct_in_array_t *v;
};
struct float_struct {
diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
index 5f645fdaba6f..52a550d281d9 100644
--- a/tools/testing/selftests/bpf/progs/fentry_test.c
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -64,7 +64,7 @@ __u64 test7_result = 0;
SEC("fentry/bpf_fentry_test7")
int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
{
- if (arg == 0)
+ if (!arg)
test7_result = 1;
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c
new file mode 100644
index 000000000000..03a672d76353
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+int pid = 0;
+int fentry_cnt = 0;
+int fexit_cnt = 0;
+
+SEC("fentry/__x64_sys_nanosleep")
+int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs)
+{
+ if ((int)bpf_get_current_pid_tgid() != pid)
+ return 0;
+
+ fentry_cnt++;
+ return 0;
+}
+
+SEC("fexit/__x64_sys_nanosleep")
+int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret)
+{
+ if ((int)bpf_get_current_pid_tgid() != pid)
+ return 0;
+
+ fexit_cnt++;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c
index 0952affb22a6..8f1ccb7302e1 100644
--- a/tools/testing/selftests/bpf/progs/fexit_test.c
+++ b/tools/testing/selftests/bpf/progs/fexit_test.c
@@ -65,7 +65,7 @@ __u64 test7_result = 0;
SEC("fexit/bpf_fentry_test7")
int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
{
- if (arg == 0)
+ if (!arg)
test7_result = 1;
return 0;
}
@@ -74,7 +74,7 @@ __u64 test8_result = 0;
SEC("fexit/bpf_fentry_test8")
int BPF_PROG(test8, struct bpf_fentry_test_t *arg)
{
- if (arg->a == 0)
+ if (!arg->a)
test8_result = 1;
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
new file mode 100644
index 000000000000..470f8723e463
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym;
+extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
+ __u32 c, __u64 d) __ksym;
+
+SEC("classifier")
+int kfunc_call_test2(struct __sk_buff *skb)
+{
+ struct bpf_sock *sk = skb->sk;
+
+ if (!sk)
+ return -1;
+
+ sk = bpf_sk_fullsock(sk);
+ if (!sk)
+ return -1;
+
+ return bpf_kfunc_call_test2((struct sock *)sk, 1, 2);
+}
+
+SEC("classifier")
+int kfunc_call_test1(struct __sk_buff *skb)
+{
+ struct bpf_sock *sk = skb->sk;
+ __u64 a = 1ULL << 32;
+ __u32 ret;
+
+ if (!sk)
+ return -1;
+
+ sk = bpf_sk_fullsock(sk);
+ if (!sk)
+ return -1;
+
+ a = bpf_kfunc_call_test1((struct sock *)sk, 1, a | 2, 3, a | 4);
+ ret = a >> 32; /* ret should be 2 */
+ ret += (__u32)a; /* ret should be 12 */
+
+ return ret;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
new file mode 100644
index 000000000000..b2dcb7d9cb03
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+extern const int bpf_prog_active __ksym;
+extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
+ __u32 c, __u64 d) __ksym;
+extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym;
+int active_res = -1;
+int sk_state = -1;
+
+int __noinline f1(struct __sk_buff *skb)
+{
+ struct bpf_sock *sk = skb->sk;
+ int *active;
+
+ if (!sk)
+ return -1;
+
+ sk = bpf_sk_fullsock(sk);
+ if (!sk)
+ return -1;
+
+ active = (int *)bpf_per_cpu_ptr(&bpf_prog_active,
+ bpf_get_smp_processor_id());
+ if (active)
+ active_res = *active;
+
+ sk_state = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state;
+
+ return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4);
+}
+
+SEC("classifier")
+int kfunc_call_test1(struct __sk_buff *skb)
+{
+ return f1(skb);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
index cf6823f42e80..7f2eaa2f89f8 100644
--- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c
+++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
@@ -4,7 +4,6 @@
#include <bpf/bpf_core_read.h>
#include <bpf/bpf_helpers.h>
-#define NULL 0
#define INLINE __always_inline
#define skb_shorter(skb, len) ((void *)(long)(skb)->data + (len) > (void *)(long)skb->data_end)
diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c
index b7787b43f9db..c4a9bae96e75 100644
--- a/tools/testing/selftests/bpf/progs/test_check_mtu.c
+++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c
@@ -105,6 +105,54 @@ int xdp_minus_delta(struct xdp_md *ctx)
return retval;
}
+SEC("xdp")
+int xdp_input_len(struct xdp_md *ctx)
+{
+ int retval = XDP_PASS; /* Expected retval on successful test */
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ __u32 ifindex = GLOBAL_USER_IFINDEX;
+ __u32 data_len = data_end - data;
+
+ /* API allow user give length to check as input via mtu_len param,
+ * resulting MTU value is still output in mtu_len param after call.
+ *
+ * Input len is L3, like MTU and iph->tot_len.
+ * Remember XDP data_len is L2.
+ */
+ __u32 mtu_len = data_len - ETH_HLEN;
+
+ if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+ retval = XDP_ABORTED;
+
+ global_bpf_mtu_xdp = mtu_len;
+ return retval;
+}
+
+SEC("xdp")
+int xdp_input_len_exceed(struct xdp_md *ctx)
+{
+ int retval = XDP_ABORTED; /* Fail */
+ __u32 ifindex = GLOBAL_USER_IFINDEX;
+ int err;
+
+ /* API allow user give length to check as input via mtu_len param,
+ * resulting MTU value is still output in mtu_len param after call.
+ *
+ * Input length value is L3 size like MTU.
+ */
+ __u32 mtu_len = GLOBAL_USER_MTU;
+
+ mtu_len += 1; /* Exceed with 1 */
+
+ err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+ if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+ retval = XDP_PASS ; /* Success in exceeding MTU check */
+
+ global_bpf_mtu_xdp = mtu_len;
+ return retval;
+}
+
SEC("classifier")
int tc_use_helper(struct __sk_buff *ctx)
{
@@ -196,3 +244,47 @@ int tc_minus_delta(struct __sk_buff *ctx)
global_bpf_mtu_xdp = mtu_len;
return retval;
}
+
+SEC("classifier")
+int tc_input_len(struct __sk_buff *ctx)
+{
+ int retval = BPF_OK; /* Expected retval on successful test */
+ __u32 ifindex = GLOBAL_USER_IFINDEX;
+
+ /* API allow user give length to check as input via mtu_len param,
+ * resulting MTU value is still output in mtu_len param after call.
+ *
+ * Input length value is L3 size.
+ */
+ __u32 mtu_len = GLOBAL_USER_MTU;
+
+ if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+ retval = BPF_DROP;
+
+ global_bpf_mtu_xdp = mtu_len;
+ return retval;
+}
+
+SEC("classifier")
+int tc_input_len_exceed(struct __sk_buff *ctx)
+{
+ int retval = BPF_DROP; /* Fail */
+ __u32 ifindex = GLOBAL_USER_IFINDEX;
+ int err;
+
+ /* API allow user give length to check as input via mtu_len param,
+ * resulting MTU value is still output in mtu_len param after call.
+ *
+ * Input length value is L3 size like MTU.
+ */
+ __u32 mtu_len = GLOBAL_USER_MTU;
+
+ mtu_len += 1; /* Exceed with 1 */
+
+ err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+ if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+ retval = BPF_OK; /* Success in exceeding MTU check */
+
+ global_bpf_mtu_xdp = mtu_len;
+ return retval;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c
index 61c2ae92ce41..97b7031d0e22 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func10.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func10.c
@@ -14,7 +14,7 @@ struct Big {
__noinline int foo(const struct Big *big)
{
- if (big == 0)
+ if (!big)
return 0;
return bpf_get_prandom_u32() < big->y;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index fa221141e9c1..a39eba9f5201 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -29,6 +29,7 @@ struct {
} verdict_map SEC(".maps");
static volatile bool test_sockmap; /* toggled by user-space */
+static volatile bool test_ingress; /* toggled by user-space */
SEC("sk_skb/stream_parser")
int prog_stream_parser(struct __sk_buff *skb)
@@ -55,6 +56,27 @@ int prog_stream_verdict(struct __sk_buff *skb)
return verdict;
}
+SEC("sk_skb/skb_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+ unsigned int *count;
+ __u32 zero = 0;
+ int verdict;
+
+ if (test_sockmap)
+ verdict = bpf_sk_redirect_map(skb, &sock_map, zero,
+ test_ingress ? BPF_F_INGRESS : 0);
+ else
+ verdict = bpf_sk_redirect_hash(skb, &sock_hash, &zero,
+ test_ingress ? BPF_F_INGRESS : 0);
+
+ count = bpf_map_lookup_elem(&verdict_map, &verdict);
+ if (count)
+ (*count)++;
+
+ return verdict;
+}
+
SEC("sk_msg")
int prog_msg_verdict(struct sk_msg_md *msg)
{
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
new file mode 100644
index 000000000000..2d31f66e4f23
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __uint(max_entries, 2);
+ __type(key, __u32);
+ __type(value, __u64);
+} sock_map SEC(".maps");
+
+SEC("sk_skb/skb_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+ return SK_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_static_linked1.c b/tools/testing/selftests/bpf/progs/test_static_linked1.c
new file mode 100644
index 000000000000..ea1a6c4c7172
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_static_linked1.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+/* 8-byte aligned .bss */
+static volatile long static_var1;
+static volatile int static_var11;
+int var1 = 0;
+/* 4-byte aligned .rodata */
+const volatile int rovar1;
+
+/* same "subprog" name in both files */
+static __noinline int subprog(int x)
+{
+ /* but different formula */
+ return x * 2;
+}
+
+SEC("raw_tp/sys_enter")
+int handler1(const void *ctx)
+{
+ var1 = subprog(rovar1) + static_var1 + static_var11;
+
+ return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
+int VERSION SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_static_linked2.c b/tools/testing/selftests/bpf/progs/test_static_linked2.c
new file mode 100644
index 000000000000..54d8d1ab577c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_static_linked2.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+/* 4-byte aligned .bss */
+static volatile int static_var2;
+static volatile int static_var22;
+int var2 = 0;
+/* 8-byte aligned .rodata */
+const volatile long rovar2;
+
+/* same "subprog" name in both files */
+static __noinline int subprog(int x)
+{
+ /* but different formula */
+ return x * 3;
+}
+
+SEC("raw_tp/sys_enter")
+int handler2(const void *ctx)
+{
+ var2 = subprog(rovar2) + static_var2 + static_var22;
+
+ return 0;
+}
+
+/* different name and/or type of the variable doesn't matter */
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 9afe947cfae9..ba6eadfec565 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -508,10 +508,8 @@ int _ip6geneve_get_tunnel(struct __sk_buff *skb)
}
ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
+ if (ret < 0)
+ gopt.opt_class = 0;
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, gopt.opt_class);
diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 56d4474e2c83..46633a3bfb0b 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -107,7 +107,7 @@ setup_vethPairs() {
echo "setting up ${VETH0}: namespace: ${NS0}"
fi
ip netns add ${NS1}
- ip link add ${VETH0} type veth peer name ${VETH1}
+ ip link add ${VETH0} numtxqueues 4 numrxqueues 4 type veth peer name ${VETH1} numtxqueues 4 numrxqueues 4
if [ -f /proc/net/if_inet6 ]; then
echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6
fi
@@ -118,6 +118,7 @@ setup_vethPairs() {
ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}
ip link set ${VETH0} mtu ${MTU}
ip netns exec ${NS1} ip link set ${VETH1} up
+ ip netns exec ${NS1} ip link set dev lo up
ip link set ${VETH0} up
}
diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
index 1fd07a4f27ac..c162498a64fc 100644
--- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c
+++ b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
@@ -6,8 +6,9 @@
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 2",
@@ -20,6 +21,8 @@
BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 1,
},
@@ -31,8 +34,9 @@
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 4",
@@ -45,6 +49,8 @@
BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -55,8 +61,9 @@
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 6",
@@ -67,8 +74,9 @@
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 7",
@@ -80,8 +88,9 @@
offsetof(struct __sk_buff, mark)),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
.errstr = "dereference of modified ctx ptr",
+ .result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
@@ -94,8 +103,9 @@
offsetof(struct __sk_buff, mark)),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
.errstr = "dereference of modified ctx ptr",
+ .result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
@@ -106,8 +116,9 @@
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 10",
@@ -119,6 +130,6 @@
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
.errstr = "math between ctx pointer and register with unbounded min value is not allowed",
+ .result = REJECT,
},
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index eb888c8479c3..336a749673d1 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -19,7 +19,7 @@
BPF_MOV64_IMM(BPF_REG_0, 2),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 1,
@@ -136,7 +136,7 @@
{
"calls: wrong src reg",
.insns = {
- BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 2, 0, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 3, 0, 0),
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
@@ -397,7 +397,7 @@
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.fixup_map_hash_48b = { 3 },
.result_unpriv = REJECT,
.result = ACCEPT,
@@ -1977,7 +1977,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
},
@@ -2003,7 +2003,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.errstr = "!read_ok",
.result = REJECT,
},
@@ -2028,7 +2028,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.errstr = "!read_ok",
.result = REJECT,
},
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 5cf361d8eb1c..17fe33a75034 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -85,7 +85,7 @@
BPF_MOV64_IMM(BPF_REG_0, 12),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
@@ -103,7 +103,7 @@
BPF_MOV64_IMM(BPF_REG_0, 12),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
@@ -121,7 +121,7 @@
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
@@ -137,7 +137,7 @@
BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
@@ -152,7 +152,7 @@
BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "function calls to other bpf functions are allowed for",
+ .errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
.result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
index b117bdd3806d..6f610cfddae5 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr.c
@@ -75,6 +75,8 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_16b = { 4 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
.result = ACCEPT,
},
{
@@ -91,5 +93,7 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_16b = { 4 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
.result = ACCEPT,
},
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index b018ad71e0a8..3e32400c4b44 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -497,7 +497,7 @@
.result = ACCEPT,
},
{
- "unpriv: adding of fp",
+ "unpriv: adding of fp, reg",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_1, 0),
@@ -505,6 +505,19 @@
BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+},
+{
+ "unpriv: adding of fp, imm",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
+ BPF_EXIT_INSN(),
+ },
.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
.result_unpriv = REJECT,
.result = ACCEPT,
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index ed4e76b24649..feb91266db39 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -169,7 +169,7 @@
.fixup_map_array_48b = { 1 },
.result = ACCEPT,
.result_unpriv = REJECT,
- .errstr_unpriv = "R2 tried to add from different maps or paths",
+ .errstr_unpriv = "R2 tried to add from different maps, paths, or prohibited types",
.retval = 0,
},
{
@@ -517,6 +517,27 @@
.retval = 0xabcdef12,
},
{
+ "map access: value_ptr += N, value_ptr -= N known scalar",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV32_IMM(BPF_REG_1, 0x12345678),
+ BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 2),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 0x12345678,
+},
+{
"map access: unknown scalar += value_ptr, 1",
.insns = {
BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 22554894db99..8889b3f55236 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -24,15 +24,15 @@ EXIT_STATUS_FILE="${LOG_FILE_BASE}.exit_status"
usage()
{
cat <<EOF
-Usage: $0 [-i] [-d <output_dir>] -- [<command>]
+Usage: $0 [-i] [-s] [-d <output_dir>] -- [<command>]
<command> is the command you would normally run when you are in
tools/testing/selftests/bpf. e.g:
$0 -- ./test_progs -t test_lsm
-If no command is specified, "${DEFAULT_COMMAND}" will be run by
-default.
+If no command is specified and a debug shell (-s) is not requested,
+"${DEFAULT_COMMAND}" will be run by default.
If you build your kernel using KBUILD_OUTPUT= or O= options, these
can be passed as environment variables to the script:
@@ -49,6 +49,9 @@ Options:
-d) Update the output directory (default: ${OUTPUT_DIR})
-j) Number of jobs for compilation, similar to -j in make
(default: ${NUM_COMPILE_JOBS})
+ -s) Instead of powering off the VM, start an interactive
+ shell. If <command> is specified, the shell runs after
+ the command finishes executing
EOF
}
@@ -149,6 +152,7 @@ update_init_script()
local init_script_dir="${OUTPUT_DIR}/${MOUNT_DIR}/etc/rcS.d"
local init_script="${init_script_dir}/S50-startup"
local command="$1"
+ local exit_command="$2"
mount_image
@@ -162,9 +166,10 @@ EOF
fi
- sudo bash -c "cat >${init_script}" <<EOF
-#!/bin/bash
+ sudo bash -c "echo '#!/bin/bash' > ${init_script}"
+ if [[ "${command}" != "" ]]; then
+ sudo bash -c "cat >>${init_script}" <<EOF
# Have a default value in the exit status file
# incase the VM is forcefully stopped.
echo "130" > "/root/${EXIT_STATUS_FILE}"
@@ -175,9 +180,12 @@ echo "130" > "/root/${EXIT_STATUS_FILE}"
stdbuf -oL -eL ${command}
echo "\$?" > "/root/${EXIT_STATUS_FILE}"
} 2>&1 | tee "/root/${LOG_FILE}"
-poweroff -f
+# Ensure that the logs are written to disk
+sync
EOF
+ fi
+ sudo bash -c "echo ${exit_command} >> ${init_script}"
sudo chmod a+x "${init_script}"
unmount_image
}
@@ -277,8 +285,10 @@ main()
local kernel_bzimage="${kernel_checkout}/${X86_BZIMAGE}"
local command="${DEFAULT_COMMAND}"
local update_image="no"
+ local exit_command="poweroff -f"
+ local debug_shell="no"
- while getopts 'hkid:j:' opt; do
+ while getopts 'hskid:j:' opt; do
case ${opt} in
i)
update_image="yes"
@@ -289,6 +299,11 @@ main()
j)
NUM_COMPILE_JOBS="$OPTARG"
;;
+ s)
+ command=""
+ debug_shell="yes"
+ exit_command="bash"
+ ;;
h)
usage
exit 0
@@ -307,7 +322,7 @@ main()
done
shift $((OPTIND -1))
- if [[ $# -eq 0 ]]; then
+ if [[ $# -eq 0 && "${debug_shell}" == "no" ]]; then
echo "No command specified, will run ${DEFAULT_COMMAND} in the vm"
else
command="$@"
@@ -355,10 +370,12 @@ main()
fi
update_selftests "${kernel_checkout}" "${make_command}"
- update_init_script "${command}"
+ update_init_script "${command}" "${exit_command}"
run_vm "${kernel_bzimage}"
- copy_logs
- echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}"
+ if [[ "${command}" != "" ]]; then
+ copy_logs
+ echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}"
+ fi
}
catch()
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 8b0f7fdd9003..1135fb980814 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -41,8 +41,12 @@
* Reduce the size of the RX ring to a fraction of the fill ring size.
* iv. fill queue empty
* Do not populate the fill queue and then try to receive pkts.
+ * f. bpf_link resource persistence
+ * Configure sockets at indexes 0 and 1, run a traffic on queue ids 0,
+ * then remove xsk sockets from queue 0 on both veth interfaces and
+ * finally run a traffic on queues ids 1
*
- * Total tests: 10
+ * Total tests: 12
*
* Flow:
* -----
@@ -93,6 +97,13 @@ typedef __u16 __sum16;
#include "xdpxceiver.h"
#include "../kselftest.h"
+static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
+static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
+static const char *IP1 = "192.168.100.162";
+static const char *IP2 = "192.168.100.161";
+static const u16 UDP_PORT1 = 2020;
+static const u16 UDP_PORT2 = 2121;
+
static void __exit_with_error(int error, const char *file, const char *func, int line)
{
if (configured_mode == TEST_MODE_UNCONFIGURED) {
@@ -108,27 +119,12 @@ static void __exit_with_error(int error, const char *file, const char *func, int
#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
#define print_ksft_result(void)\
- (ksft_test_result_pass("PASS: %s %s %s%s%s\n", configured_mode ? "DRV" : "SKB",\
+ (ksft_test_result_pass("PASS: %s %s %s%s%s%s\n", configured_mode ? "DRV" : "SKB",\
test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\
test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\
test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\
- test_type == TEST_TYPE_STATS ? "Stats" : ""))
-
-static void pthread_init_mutex(void)
-{
- pthread_mutex_init(&sync_mutex, NULL);
- pthread_mutex_init(&sync_mutex_tx, NULL);
- pthread_cond_init(&signal_rx_condition, NULL);
- pthread_cond_init(&signal_tx_condition, NULL);
-}
-
-static void pthread_destroy_mutex(void)
-{
- pthread_mutex_destroy(&sync_mutex);
- pthread_mutex_destroy(&sync_mutex_tx);
- pthread_cond_destroy(&signal_rx_condition);
- pthread_cond_destroy(&signal_tx_condition);
-}
+ test_type == TEST_TYPE_STATS ? "Stats" : "",\
+ test_type == TEST_TYPE_BPF_RES ? "BPF RES" : ""))
static void *memset32_htonl(void *dest, u32 val, u32 size)
{
@@ -147,24 +143,11 @@ static void *memset32_htonl(void *dest, u32 val, u32 size)
}
/*
- * This function code has been taken from
- * Linux kernel lib/checksum.c
- */
-static inline unsigned short from32to16(unsigned int x)
-{
- /* add up 16-bit and 16-bit for 16+c bit */
- x = (x & 0xffff) + (x >> 16);
- /* add up carry.. */
- x = (x & 0xffff) + (x >> 16);
- return x;
-}
-
-/*
* Fold a partial checksum
* This function code has been taken from
* Linux kernel include/asm-generic/checksum.h
*/
-static inline __u16 csum_fold(__u32 csum)
+static __u16 csum_fold(__u32 csum)
{
u32 sum = (__force u32)csum;
@@ -177,7 +160,7 @@ static inline __u16 csum_fold(__u32 csum)
* This function code has been taken from
* Linux kernel lib/checksum.c
*/
-static inline u32 from64to32(u64 x)
+static u32 from64to32(u64 x)
{
/* add up 32-bit and 32-bit for 32+c bit */
x = (x & 0xffffffff) + (x >> 32);
@@ -186,13 +169,11 @@ static inline u32 from64to32(u64 x)
return (u32)x;
}
-__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum);
-
/*
* This function code has been taken from
* Linux kernel lib/checksum.c
*/
-__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+static __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
{
unsigned long long s = (__force u32)sum;
@@ -210,13 +191,12 @@ __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u3
* This function has been taken from
* Linux kernel include/asm-generic/checksum.h
*/
-static inline __u16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+static __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
{
return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
}
-static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
+static u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
{
u32 csum = 0;
u32 cnt = 0;
@@ -271,9 +251,8 @@ static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data, PKT_SIZE);
}
-static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
+static void xsk_configure_umem(struct ifobject *data, void *buffer, int idx)
{
- int ret;
struct xsk_umem_config cfg = {
.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
@@ -281,23 +260,28 @@ static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
.frame_headroom = frame_headroom,
.flags = XSK_UMEM__DEFAULT_FLAGS
};
+ int size = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
+ struct xsk_umem_info *umem;
+ int ret;
- data->umem = calloc(1, sizeof(struct xsk_umem_info));
- if (!data->umem)
+ umem = calloc(1, sizeof(struct xsk_umem_info));
+ if (!umem)
exit_with_error(errno);
- ret = xsk_umem__create(&data->umem->umem, buffer, size,
- &data->umem->fq, &data->umem->cq, &cfg);
+ ret = xsk_umem__create(&umem->umem, buffer, size,
+ &umem->fq, &umem->cq, &cfg);
if (ret)
exit_with_error(ret);
- data->umem->buffer = buffer;
+ umem->buffer = buffer;
+
+ data->umem_arr[idx] = umem;
}
static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
{
int ret, i;
- u32 idx;
+ u32 idx = 0;
ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
@@ -307,18 +291,19 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
}
-static int xsk_configure_socket(struct ifobject *ifobject)
+static int xsk_configure_socket(struct ifobject *ifobject, int idx)
{
struct xsk_socket_config cfg;
+ struct xsk_socket_info *xsk;
struct xsk_ring_cons *rxr;
struct xsk_ring_prod *txr;
int ret;
- ifobject->xsk = calloc(1, sizeof(struct xsk_socket_info));
- if (!ifobject->xsk)
+ xsk = calloc(1, sizeof(struct xsk_socket_info));
+ if (!xsk)
exit_with_error(errno);
- ifobject->xsk->umem = ifobject->umem;
+ xsk->umem = ifobject->umem;
cfg.rx_size = rxqsize;
cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
cfg.libbpf_flags = 0;
@@ -326,19 +311,20 @@ static int xsk_configure_socket(struct ifobject *ifobject)
cfg.bind_flags = xdp_bind_flags;
if (test_type != TEST_TYPE_BIDI) {
- rxr = (ifobject->fv.vector == rx) ? &ifobject->xsk->rx : NULL;
- txr = (ifobject->fv.vector == tx) ? &ifobject->xsk->tx : NULL;
+ rxr = (ifobject->fv.vector == rx) ? &xsk->rx : NULL;
+ txr = (ifobject->fv.vector == tx) ? &xsk->tx : NULL;
} else {
- rxr = &ifobject->xsk->rx;
- txr = &ifobject->xsk->tx;
+ rxr = &xsk->rx;
+ txr = &xsk->tx;
}
- ret = xsk_socket__create(&ifobject->xsk->xsk, ifobject->ifname,
- opt_queue, ifobject->umem->umem, rxr, txr, &cfg);
-
+ ret = xsk_socket__create(&xsk->xsk, ifobject->ifname, idx,
+ ifobject->umem->umem, rxr, txr, &cfg);
if (ret)
return 1;
+ ifobject->xsk_arr[idx] = xsk;
+
return 0;
}
@@ -364,12 +350,15 @@ static void usage(const char *prog)
ksft_print_msg(str, prog);
}
-static bool switch_namespace(int idx)
+static int switch_namespace(const char *nsname)
{
char fqns[26] = "/var/run/netns/";
int nsfd;
- strncat(fqns, ifdict[idx]->nsname, sizeof(fqns) - strlen(fqns) - 1);
+ if (!nsname || strlen(nsname) == 0)
+ return -1;
+
+ strncat(fqns, nsname, sizeof(fqns) - strlen(fqns) - 1);
nsfd = open(fqns, O_RDONLY);
if (nsfd == -1)
@@ -378,26 +367,9 @@ static bool switch_namespace(int idx)
if (setns(nsfd, 0) == -1)
exit_with_error(errno);
- return true;
-}
-
-static void *nsswitchthread(void *args)
-{
- struct targs *targs = args;
+ print_verbose("NS switched: %s\n", nsname);
- targs->retptr = false;
-
- if (switch_namespace(targs->idx)) {
- ifdict[targs->idx]->ifindex = if_nametoindex(ifdict[targs->idx]->ifname);
- if (!ifdict[targs->idx]->ifindex) {
- ksft_test_result_fail("ERROR: [%s] interface \"%s\" does not exist\n",
- __func__, ifdict[targs->idx]->ifname);
- } else {
- print_verbose("Interface found: %s\n", ifdict[targs->idx]->ifname);
- targs->retptr = true;
- }
- }
- pthread_exit(NULL);
+ return nsfd;
}
static int validate_interfaces(void)
@@ -409,33 +381,6 @@ static int validate_interfaces(void)
ret = false;
ksft_test_result_fail("ERROR: interfaces: -i <int>,<ns> -i <int>,<ns>.");
}
- if (strcmp(ifdict[i]->nsname, "")) {
- struct targs *targs;
-
- targs = malloc(sizeof(*targs));
- if (!targs)
- exit_with_error(errno);
-
- targs->idx = i;
- if (pthread_create(&ns_thread, NULL, nsswitchthread, targs))
- exit_with_error(errno);
-
- pthread_join(ns_thread, NULL);
-
- if (targs->retptr)
- print_verbose("NS switched: %s\n", ifdict[i]->nsname);
-
- free(targs);
- } else {
- ifdict[i]->ifindex = if_nametoindex(ifdict[i]->ifname);
- if (!ifdict[i]->ifindex) {
- ksft_test_result_fail
- ("ERROR: interface \"%s\" does not exist\n", ifdict[i]->ifname);
- ret = false;
- } else {
- print_verbose("Interface found: %s\n", ifdict[i]->ifname);
- }
- }
}
return ret;
}
@@ -447,7 +392,7 @@ static void parse_command_line(int argc, char **argv)
opterr = 0;
for (;;) {
- c = getopt_long(argc, argv, "i:q:DC:v", long_options, &option_index);
+ c = getopt_long(argc, argv, "i:DC:v", long_options, &option_index);
if (c == -1)
break;
@@ -467,9 +412,6 @@ static void parse_command_line(int argc, char **argv)
MAX_INTERFACES_NAMESPACE_CHARS);
interface_index++;
break;
- case 'q':
- opt_queue = atoi(optarg);
- break;
case 'D':
debug_pkt_dump = 1;
break;
@@ -506,7 +448,7 @@ static void kick_tx(struct xsk_socket_info *xsk)
exit_with_error(errno);
}
-static inline void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
+static void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
{
unsigned int rcvd;
u32 idx;
@@ -514,7 +456,7 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
if (!xsk->outstanding_tx)
return;
- if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
+ if (xsk_ring_prod__needs_wakeup(&xsk->tx))
kick_tx(xsk);
rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
@@ -584,7 +526,7 @@ static void rx_pkt(struct xsk_socket_info *xsk, struct pollfd *fds)
static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
{
- u32 idx;
+ u32 idx = 0;
unsigned int i;
bool tx_invalid_test = stat_test_type == STAT_TEST_TX_INVALID;
u32 len = tx_invalid_test ? XSK_UMEM__DEFAULT_FRAME_SIZE + 1 : PKT_SIZE;
@@ -602,16 +544,15 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
xsk_ring_prod__submit(&xsk->tx, batch_size);
if (!tx_invalid_test) {
xsk->outstanding_tx += batch_size;
- } else {
- if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
- kick_tx(xsk);
+ } else if (xsk_ring_prod__needs_wakeup(&xsk->tx)) {
+ kick_tx(xsk);
}
*frameptr += batch_size;
*frameptr %= num_frames;
complete_tx_only(xsk, batch_size);
}
-static inline int get_batch_size(int pkt_cnt)
+static int get_batch_size(int pkt_cnt)
{
if (!opt_pkt_count)
return BATCH_SIZE;
@@ -667,45 +608,40 @@ static void tx_only_all(struct ifobject *ifobject)
static void worker_pkt_dump(void)
{
- struct in_addr ipaddr;
+ struct ethhdr *ethhdr;
+ struct iphdr *iphdr;
+ struct udphdr *udphdr;
+ char s[128];
+ int payload;
+ void *ptr;
fprintf(stdout, "---------------------------------------\n");
for (int iter = 0; iter < num_frames - 1; iter++) {
+ ptr = pkt_buf[iter]->payload;
+ ethhdr = ptr;
+ iphdr = ptr + sizeof(*ethhdr);
+ udphdr = ptr + sizeof(*ethhdr) + sizeof(*iphdr);
+
/*extract L2 frame */
fprintf(stdout, "DEBUG>> L2: dst mac: ");
for (int i = 0; i < ETH_ALEN; i++)
- fprintf(stdout, "%02X", ((struct ethhdr *)
- pkt_buf[iter]->payload)->h_dest[i]);
+ fprintf(stdout, "%02X", ethhdr->h_dest[i]);
fprintf(stdout, "\nDEBUG>> L2: src mac: ");
for (int i = 0; i < ETH_ALEN; i++)
- fprintf(stdout, "%02X", ((struct ethhdr *)
- pkt_buf[iter]->payload)->h_source[i]);
+ fprintf(stdout, "%02X", ethhdr->h_source[i]);
/*extract L3 frame */
- fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n",
- ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->ihl);
-
- ipaddr.s_addr =
- ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->saddr;
- fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", inet_ntoa(ipaddr));
-
- ipaddr.s_addr =
- ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->daddr;
- fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", inet_ntoa(ipaddr));
-
+ fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl);
+ fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n",
+ inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s)));
+ fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n",
+ inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s)));
/*extract L4 frame */
- fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n",
- ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
- sizeof(struct ethhdr) +
- sizeof(struct iphdr)))->source));
-
- fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n",
- ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
- sizeof(struct ethhdr) +
- sizeof(struct iphdr)))->dest));
+ fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source));
+ fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest));
/*extract L5 frame */
- int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
+ payload = *((uint32_t *)(ptr + PKT_HDR_SIZE));
if (payload == EOT) {
print_verbose("End-of-transmission frame received\n");
@@ -809,37 +745,69 @@ static void worker_pkt_validate(void)
}
}
-static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mutex_t *mutexptr,
- atomic_int *spinningptr)
+static void thread_common_ops(struct ifobject *ifobject, void *bufs)
{
+ int umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
int ctr = 0;
int ret;
- xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
- ret = xsk_configure_socket(ifobject);
+ ifobject->ns_fd = switch_namespace(ifobject->nsname);
+
+ if (test_type == TEST_TYPE_BPF_RES)
+ umem_sz *= 2;
+
+ bufs = mmap(NULL, umem_sz,
+ PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (bufs == MAP_FAILED)
+ exit_with_error(errno);
+
+ xsk_configure_umem(ifobject, bufs, 0);
+ ifobject->umem = ifobject->umem_arr[0];
+ ret = xsk_configure_socket(ifobject, 0);
/* Retry Create Socket if it fails as xsk_socket__create()
* is asynchronous
- *
- * Essential to lock Mutex here to prevent Tx thread from
- * entering before Rx and causing a deadlock
*/
- pthread_mutex_lock(mutexptr);
while (ret && ctr < SOCK_RECONF_CTR) {
- atomic_store(spinningptr, 1);
- xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
- ret = xsk_configure_socket(ifobject);
+ xsk_configure_umem(ifobject, bufs, 0);
+ ifobject->umem = ifobject->umem_arr[0];
+ ret = xsk_configure_socket(ifobject, 0);
usleep(USLEEP_MAX);
ctr++;
}
- atomic_store(spinningptr, 0);
- pthread_mutex_unlock(mutexptr);
if (ctr >= SOCK_RECONF_CTR)
exit_with_error(ret);
+
+ ifobject->umem = ifobject->umem_arr[0];
+ ifobject->xsk = ifobject->xsk_arr[0];
+
+ if (test_type == TEST_TYPE_BPF_RES) {
+ xsk_configure_umem(ifobject, (u8 *)bufs + (umem_sz / 2), 1);
+ ifobject->umem = ifobject->umem_arr[1];
+ ret = xsk_configure_socket(ifobject, 1);
+ }
+
+ ifobject->umem = ifobject->umem_arr[0];
+ ifobject->xsk = ifobject->xsk_arr[0];
+ print_verbose("Interface [%s] vector [%s]\n",
+ ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx");
}
-static void *worker_testapp_validate(void *arg)
+static bool testapp_is_test_two_stepped(void)
+{
+ return (test_type != TEST_TYPE_BIDI && test_type != TEST_TYPE_BPF_RES) || second_step;
+}
+
+static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
+{
+ if (testapp_is_test_two_stepped()) {
+ xsk_socket__delete(ifobj->xsk->xsk);
+ (void)xsk_umem__delete(ifobj->umem->umem);
+ }
+}
+
+static void *worker_testapp_validate_tx(void *arg)
{
struct udphdr *udp_hdr =
(struct udphdr *)(pkt_data + sizeof(struct ethhdr) + sizeof(struct iphdr));
@@ -849,157 +817,97 @@ static void *worker_testapp_validate(void *arg)
struct generic_data data;
void *bufs = NULL;
- pthread_attr_setstacksize(&attr, THREAD_STACK);
-
- if (!bidi_pass) {
- bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
- PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (bufs == MAP_FAILED)
- exit_with_error(errno);
-
- if (strcmp(ifobject->nsname, ""))
- switch_namespace(ifobject->ifdict_index);
+ if (!second_step)
+ thread_common_ops(ifobject, bufs);
+
+ for (int i = 0; i < num_frames; i++) {
+ /*send EOT frame */
+ if (i == (num_frames - 1))
+ data.seqnum = -1;
+ else
+ data.seqnum = i;
+ gen_udp_hdr(&data, ifobject, udp_hdr);
+ gen_ip_hdr(ifobject, ip_hdr);
+ gen_udp_csum(udp_hdr, ip_hdr);
+ gen_eth_hdr(ifobject, eth_hdr);
+ gen_eth_frame(ifobject->umem, i * XSK_UMEM__DEFAULT_FRAME_SIZE);
}
- if (ifobject->fv.vector == tx) {
- int spinningrxctr = 0;
-
- if (!bidi_pass)
- thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_tx);
+ print_verbose("Sending %d packets on interface %s\n",
+ (opt_pkt_count - 1), ifobject->ifname);
+ tx_only_all(ifobject);
- while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
- spinningrxctr++;
- usleep(USLEEP_MAX);
- }
+ testapp_cleanup_xsk_res(ifobject);
+ pthread_exit(NULL);
+}
- print_verbose("Interface [%s] vector [Tx]\n", ifobject->ifname);
- for (int i = 0; i < num_frames; i++) {
- /*send EOT frame */
- if (i == (num_frames - 1))
- data.seqnum = -1;
- else
- data.seqnum = i;
- gen_udp_hdr(&data, ifobject, udp_hdr);
- gen_ip_hdr(ifobject, ip_hdr);
- gen_udp_csum(udp_hdr, ip_hdr);
- gen_eth_hdr(ifobject, eth_hdr);
- gen_eth_frame(ifobject->umem, i * XSK_UMEM__DEFAULT_FRAME_SIZE);
- }
+static void *worker_testapp_validate_rx(void *arg)
+{
+ struct ifobject *ifobject = (struct ifobject *)arg;
+ struct pollfd fds[MAX_SOCKS] = { };
+ void *bufs = NULL;
- print_verbose("Sending %d packets on interface %s\n",
- (opt_pkt_count - 1), ifobject->ifname);
- tx_only_all(ifobject);
- } else if (ifobject->fv.vector == rx) {
- struct pollfd fds[MAX_SOCKS] = { };
- int ret;
-
- if (!bidi_pass)
- thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
-
- print_verbose("Interface [%s] vector [Rx]\n", ifobject->ifname);
- if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
- xsk_populate_fill_ring(ifobject->umem);
-
- TAILQ_INIT(&head);
- if (debug_pkt_dump) {
- pkt_buf = calloc(num_frames, sizeof(*pkt_buf));
- if (!pkt_buf)
- exit_with_error(errno);
- }
+ if (!second_step)
+ thread_common_ops(ifobject, bufs);
- fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
- fds[0].events = POLLIN;
+ if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
+ xsk_populate_fill_ring(ifobject->umem);
- pthread_mutex_lock(&sync_mutex);
- pthread_cond_signal(&signal_rx_condition);
- pthread_mutex_unlock(&sync_mutex);
+ TAILQ_INIT(&head);
+ if (debug_pkt_dump) {
+ pkt_buf = calloc(num_frames, sizeof(*pkt_buf));
+ if (!pkt_buf)
+ exit_with_error(errno);
+ }
- while (1) {
- if (test_type == TEST_TYPE_POLL) {
- ret = poll(fds, 1, POLL_TMOUT);
- if (ret <= 0)
- continue;
- }
+ fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
+ fds[0].events = POLLIN;
- if (test_type != TEST_TYPE_STATS) {
- rx_pkt(ifobject->xsk, fds);
- worker_pkt_validate();
- } else {
- worker_stats_validate(ifobject);
- }
+ pthread_barrier_wait(&barr);
- if (sigvar)
- break;
+ while (1) {
+ if (test_type != TEST_TYPE_STATS) {
+ rx_pkt(ifobject->xsk, fds);
+ worker_pkt_validate();
+ } else {
+ worker_stats_validate(ifobject);
}
+ if (sigvar)
+ break;
+ }
- if (test_type != TEST_TYPE_STATS)
- print_verbose("Received %d packets on interface %s\n",
- pkt_counter, ifobject->ifname);
+ print_verbose("Received %d packets on interface %s\n",
+ pkt_counter, ifobject->ifname);
- if (test_type == TEST_TYPE_TEARDOWN)
- print_verbose("Destroying socket\n");
- }
+ if (test_type == TEST_TYPE_TEARDOWN)
+ print_verbose("Destroying socket\n");
- if ((test_type != TEST_TYPE_BIDI) || bidi_pass) {
- xsk_socket__delete(ifobject->xsk->xsk);
- (void)xsk_umem__delete(ifobject->umem->umem);
- }
+ testapp_cleanup_xsk_res(ifobject);
pthread_exit(NULL);
}
static void testapp_validate(void)
{
- struct timespec max_wait = { 0, 0 };
bool bidi = test_type == TEST_TYPE_BIDI;
+ bool bpf = test_type == TEST_TYPE_BPF_RES;
- pthread_attr_init(&attr);
- pthread_attr_setstacksize(&attr, THREAD_STACK);
-
- if ((test_type == TEST_TYPE_BIDI) && bidi_pass) {
- pthread_init_mutex();
- if (!switching_notify) {
- print_verbose("Switching Tx/Rx vectors\n");
- switching_notify++;
- }
- }
-
- pthread_mutex_lock(&sync_mutex);
+ if (pthread_barrier_init(&barr, NULL, 2))
+ exit_with_error(errno);
/*Spawn RX thread */
- if (!bidi || !bidi_pass) {
- if (pthread_create(&t0, &attr, worker_testapp_validate, ifdict[1]))
- exit_with_error(errno);
- } else if (bidi && bidi_pass) {
- /*switch Tx/Rx vectors */
- ifdict[0]->fv.vector = rx;
- if (pthread_create(&t0, &attr, worker_testapp_validate, ifdict[0]))
- exit_with_error(errno);
- }
+ pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx);
- if (clock_gettime(CLOCK_REALTIME, &max_wait))
+ pthread_barrier_wait(&barr);
+ if (pthread_barrier_destroy(&barr))
exit_with_error(errno);
- max_wait.tv_sec += TMOUT_SEC;
-
- if (pthread_cond_timedwait(&signal_rx_condition, &sync_mutex, &max_wait) == ETIMEDOUT)
- exit_with_error(errno);
-
- pthread_mutex_unlock(&sync_mutex);
/*Spawn TX thread */
- if (!bidi || !bidi_pass) {
- if (pthread_create(&t1, &attr, worker_testapp_validate, ifdict[0]))
- exit_with_error(errno);
- } else if (bidi && bidi_pass) {
- /*switch Tx/Rx vectors */
- ifdict[1]->fv.vector = tx;
- if (pthread_create(&t1, &attr, worker_testapp_validate, ifdict[1]))
- exit_with_error(errno);
- }
+ pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx);
pthread_join(t1, NULL);
pthread_join(t0, NULL);
- if (debug_pkt_dump) {
+ if (debug_pkt_dump && test_type != TEST_TYPE_STATS) {
worker_pkt_dump();
for (int iter = 0; iter < num_frames - 1; iter++) {
free(pkt_buf[iter]->payload);
@@ -1008,20 +916,85 @@ static void testapp_validate(void)
free(pkt_buf);
}
- if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !(test_type == TEST_TYPE_STATS))
+ if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !bpf && !(test_type == TEST_TYPE_STATS))
print_ksft_result();
}
-static void testapp_sockets(void)
+static void testapp_teardown(void)
+{
+ int i;
+
+ for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
+ pkt_counter = 0;
+ prev_pkt = -1;
+ sigvar = 0;
+ print_verbose("Creating socket\n");
+ testapp_validate();
+ }
+
+ print_ksft_result();
+}
+
+static void swap_vectors(struct ifobject *ifobj1, struct ifobject *ifobj2)
+{
+ void *(*tmp_func_ptr)(void *) = ifobj1->func_ptr;
+ enum fvector tmp_vector = ifobj1->fv.vector;
+
+ ifobj1->func_ptr = ifobj2->func_ptr;
+ ifobj1->fv.vector = ifobj2->fv.vector;
+
+ ifobj2->func_ptr = tmp_func_ptr;
+ ifobj2->fv.vector = tmp_vector;
+
+ ifdict_tx = ifobj1;
+ ifdict_rx = ifobj2;
+}
+
+static void testapp_bidi(void)
+{
+ for (int i = 0; i < MAX_BIDI_ITER; i++) {
+ pkt_counter = 0;
+ prev_pkt = -1;
+ sigvar = 0;
+ print_verbose("Creating socket\n");
+ testapp_validate();
+ if (!second_step) {
+ print_verbose("Switching Tx/Rx vectors\n");
+ swap_vectors(ifdict[1], ifdict[0]);
+ }
+ second_step = true;
+ }
+
+ swap_vectors(ifdict[0], ifdict[1]);
+
+ print_ksft_result();
+}
+
+static void swap_xsk_res(void)
+{
+ xsk_socket__delete(ifdict_tx->xsk->xsk);
+ xsk_umem__delete(ifdict_tx->umem->umem);
+ xsk_socket__delete(ifdict_rx->xsk->xsk);
+ xsk_umem__delete(ifdict_rx->umem->umem);
+ ifdict_tx->umem = ifdict_tx->umem_arr[1];
+ ifdict_tx->xsk = ifdict_tx->xsk_arr[1];
+ ifdict_rx->umem = ifdict_rx->umem_arr[1];
+ ifdict_rx->xsk = ifdict_rx->xsk_arr[1];
+}
+
+static void testapp_bpf_res(void)
{
- for (int i = 0; i < ((test_type == TEST_TYPE_TEARDOWN) ? MAX_TEARDOWN_ITER : MAX_BIDI_ITER);
- i++) {
+ int i;
+
+ for (i = 0; i < MAX_BPF_ITER; i++) {
pkt_counter = 0;
prev_pkt = -1;
sigvar = 0;
print_verbose("Creating socket\n");
testapp_validate();
- test_type == TEST_TYPE_BIDI ? bidi_pass++ : bidi_pass;
+ if (!second_step)
+ swap_xsk_res();
+ second_step = true;
}
print_ksft_result();
@@ -1053,78 +1026,33 @@ static void testapp_stats(void)
print_ksft_result();
}
-static void init_iface_config(struct ifaceconfigobj *ifaceconfig)
+static void init_iface(struct ifobject *ifobj, const char *dst_mac,
+ const char *src_mac, const char *dst_ip,
+ const char *src_ip, const u16 dst_port,
+ const u16 src_port, enum fvector vector)
{
- /*Init interface0 */
- ifdict[0]->fv.vector = tx;
- memcpy(ifdict[0]->dst_mac, ifaceconfig->dst_mac, ETH_ALEN);
- memcpy(ifdict[0]->src_mac, ifaceconfig->src_mac, ETH_ALEN);
- ifdict[0]->dst_ip = ifaceconfig->dst_ip.s_addr;
- ifdict[0]->src_ip = ifaceconfig->src_ip.s_addr;
- ifdict[0]->dst_port = ifaceconfig->dst_port;
- ifdict[0]->src_port = ifaceconfig->src_port;
-
- /*Init interface1 */
- ifdict[1]->fv.vector = rx;
- memcpy(ifdict[1]->dst_mac, ifaceconfig->src_mac, ETH_ALEN);
- memcpy(ifdict[1]->src_mac, ifaceconfig->dst_mac, ETH_ALEN);
- ifdict[1]->dst_ip = ifaceconfig->src_ip.s_addr;
- ifdict[1]->src_ip = ifaceconfig->dst_ip.s_addr;
- ifdict[1]->dst_port = ifaceconfig->src_port;
- ifdict[1]->src_port = ifaceconfig->dst_port;
-}
+ struct in_addr ip;
-static void *nsdisablemodethread(void *args)
-{
- struct targs *targs = args;
+ memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN);
+ memcpy(ifobj->src_mac, src_mac, ETH_ALEN);
- targs->retptr = false;
+ inet_aton(dst_ip, &ip);
+ ifobj->dst_ip = ip.s_addr;
- if (switch_namespace(targs->idx)) {
- targs->retptr = bpf_set_link_xdp_fd(ifdict[targs->idx]->ifindex, -1, targs->flags);
- } else {
- targs->retptr = errno;
- print_verbose("Failed to switch namespace to %s\n", ifdict[targs->idx]->nsname);
- }
-
- pthread_exit(NULL);
-}
-
-static void disable_xdp_mode(int mode)
-{
- int err = 0;
- __u32 flags = XDP_FLAGS_UPDATE_IF_NOEXIST | mode;
- char *mode_str = mode & XDP_FLAGS_SKB_MODE ? "skb" : "drv";
+ inet_aton(src_ip, &ip);
+ ifobj->src_ip = ip.s_addr;
- for (int i = 0; i < MAX_INTERFACES; i++) {
- if (strcmp(ifdict[i]->nsname, "")) {
- struct targs *targs;
-
- targs = malloc(sizeof(*targs));
- memset(targs, 0, sizeof(*targs));
- if (!targs)
- exit_with_error(errno);
-
- targs->idx = i;
- targs->flags = flags;
- if (pthread_create(&ns_thread, NULL, nsdisablemodethread, targs))
- exit_with_error(errno);
-
- pthread_join(ns_thread, NULL);
- err = targs->retptr;
- free(targs);
- } else {
- err = bpf_set_link_xdp_fd(ifdict[i]->ifindex, -1, flags);
- }
-
- if (err) {
- print_verbose("Failed to disable %s mode on interface %s\n",
- mode_str, ifdict[i]->ifname);
- exit_with_error(err);
- }
+ ifobj->dst_port = dst_port;
+ ifobj->src_port = src_port;
- print_verbose("Disabled %s mode for interface: %s\n", mode_str, ifdict[i]->ifname);
- configured_mode = mode & XDP_FLAGS_SKB_MODE ? TEST_MODE_DRV : TEST_MODE_SKB;
+ if (vector == tx) {
+ ifobj->fv.vector = tx;
+ ifobj->func_ptr = worker_testapp_validate_tx;
+ ifdict_tx = ifobj;
+ } else {
+ ifobj->fv.vector = rx;
+ ifobj->func_ptr = worker_testapp_validate_rx;
+ ifdict_rx = ifobj;
}
}
@@ -1135,72 +1063,70 @@ static void run_pkt_test(int mode, int type)
/* reset defaults after potential previous test */
xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
pkt_counter = 0;
- switching_notify = 0;
- bidi_pass = 0;
+ second_step = 0;
prev_pkt = -1;
- ifdict[0]->fv.vector = tx;
- ifdict[1]->fv.vector = rx;
sigvar = 0;
stat_test_type = -1;
rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
+ configured_mode = mode;
+
switch (mode) {
case (TEST_MODE_SKB):
- if (configured_mode == TEST_MODE_DRV)
- disable_xdp_mode(XDP_FLAGS_DRV_MODE);
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
case (TEST_MODE_DRV):
- if (configured_mode == TEST_MODE_SKB)
- disable_xdp_mode(XDP_FLAGS_SKB_MODE);
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
default:
break;
}
- pthread_init_mutex();
-
- if (test_type == TEST_TYPE_STATS)
+ switch (test_type) {
+ case TEST_TYPE_STATS:
testapp_stats();
- else if ((test_type != TEST_TYPE_TEARDOWN) && (test_type != TEST_TYPE_BIDI))
+ break;
+ case TEST_TYPE_TEARDOWN:
+ testapp_teardown();
+ break;
+ case TEST_TYPE_BIDI:
+ testapp_bidi();
+ break;
+ case TEST_TYPE_BPF_RES:
+ testapp_bpf_res();
+ break;
+ default:
testapp_validate();
- else
- testapp_sockets();
-
- pthread_destroy_mutex();
+ break;
+ }
}
int main(int argc, char **argv)
{
struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
+ bool failure = false;
+ int i, j;
if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
exit_with_error(errno);
- const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
- const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
- const char *IP1 = "192.168.100.162";
- const char *IP2 = "192.168.100.161";
- u16 UDP_DST_PORT = 2020;
- u16 UDP_SRC_PORT = 2121;
- int i, j;
-
- ifaceconfig = malloc(sizeof(struct ifaceconfigobj));
- memcpy(ifaceconfig->dst_mac, MAC1, ETH_ALEN);
- memcpy(ifaceconfig->src_mac, MAC2, ETH_ALEN);
- inet_aton(IP1, &ifaceconfig->dst_ip);
- inet_aton(IP2, &ifaceconfig->src_ip);
- ifaceconfig->dst_port = UDP_DST_PORT;
- ifaceconfig->src_port = UDP_SRC_PORT;
-
for (int i = 0; i < MAX_INTERFACES; i++) {
ifdict[i] = malloc(sizeof(struct ifobject));
if (!ifdict[i])
exit_with_error(errno);
ifdict[i]->ifdict_index = i;
+ ifdict[i]->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *));
+ if (!ifdict[i]->xsk_arr) {
+ failure = true;
+ goto cleanup;
+ }
+ ifdict[i]->umem_arr = calloc(2, sizeof(struct xsk_umem_info *));
+ if (!ifdict[i]->umem_arr) {
+ failure = true;
+ goto cleanup;
+ }
}
setlocale(LC_ALL, "");
@@ -1209,9 +1135,8 @@ int main(int argc, char **argv)
num_frames = ++opt_pkt_count;
- init_iface_config(ifaceconfig);
-
- disable_xdp_mode(XDP_FLAGS_DRV_MODE);
+ init_iface(ifdict[0], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx);
+ init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx);
ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
@@ -1220,8 +1145,17 @@ int main(int argc, char **argv)
run_pkt_test(i, j);
}
- for (int i = 0; i < MAX_INTERFACES; i++)
+cleanup:
+ for (int i = 0; i < MAX_INTERFACES; i++) {
+ if (ifdict[i]->ns_fd != -1)
+ close(ifdict[i]->ns_fd);
+ free(ifdict[i]->xsk_arr);
+ free(ifdict[i]->umem_arr);
free(ifdict[i]);
+ }
+
+ if (failure)
+ exit_with_error(errno);
ksft_exit_pass();
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 30314ef305c2..6c428b276ab6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -23,6 +23,7 @@
#define MAX_SOCKS 1
#define MAX_TEARDOWN_ITER 10
#define MAX_BIDI_ITER 2
+#define MAX_BPF_ITER 2
#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
sizeof(struct udphdr))
#define MIN_PKT_SIZE 64
@@ -33,14 +34,11 @@
#define IP_PKT_TOS 0x9
#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr))
#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))
-#define TMOUT_SEC (3)
#define EOT (-1)
#define USLEEP_MAX 200000
-#define THREAD_STACK 60000000
#define SOCK_RECONF_CTR 10
#define BATCH_SIZE 64
#define POLL_TMOUT 1000
-#define NEED_WAKEUP true
#define DEFAULT_PKT_CNT 10000
#define RX_FULL_RXQSIZE 32
@@ -63,6 +61,7 @@ enum TEST_TYPES {
TEST_TYPE_TEARDOWN,
TEST_TYPE_BIDI,
TEST_TYPE_STATS,
+ TEST_TYPE_BPF_RES,
TEST_TYPE_MAX
};
@@ -77,11 +76,9 @@ enum STAT_TEST_TYPES {
static int configured_mode = TEST_MODE_UNCONFIGURED;
static u8 debug_pkt_dump;
static u32 num_frames;
-static u8 switching_notify;
-static u8 bidi_pass;
+static bool second_step;
static int test_type;
-static int opt_queue;
static int opt_pkt_count;
static u8 opt_verbose;
@@ -125,48 +122,32 @@ struct generic_data {
u32 seqnum;
};
-struct ifaceconfigobj {
- u8 dst_mac[ETH_ALEN];
- u8 src_mac[ETH_ALEN];
- struct in_addr dst_ip;
- struct in_addr src_ip;
- u16 src_port;
- u16 dst_port;
-} *ifaceconfig;
-
struct ifobject {
- int ifindex;
- int ifdict_index;
char ifname[MAX_INTERFACE_NAME_CHARS];
char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
- struct flow_vector fv;
struct xsk_socket_info *xsk;
+ struct xsk_socket_info **xsk_arr;
+ struct xsk_umem_info **umem_arr;
struct xsk_umem_info *umem;
- u8 dst_mac[ETH_ALEN];
- u8 src_mac[ETH_ALEN];
+ void *(*func_ptr)(void *arg);
+ struct flow_vector fv;
+ int ns_fd;
+ int ifdict_index;
u32 dst_ip;
u32 src_ip;
u16 src_port;
u16 dst_port;
+ u8 dst_mac[ETH_ALEN];
+ u8 src_mac[ETH_ALEN];
};
static struct ifobject *ifdict[MAX_INTERFACES];
+static struct ifobject *ifdict_rx;
+static struct ifobject *ifdict_tx;
/*threads*/
-atomic_int spinning_tx;
-atomic_int spinning_rx;
-pthread_mutex_t sync_mutex;
-pthread_mutex_t sync_mutex_tx;
-pthread_cond_t signal_rx_condition;
-pthread_cond_t signal_tx_condition;
-pthread_t t0, t1, ns_thread;
-pthread_attr_t attr;
-
-struct targs {
- u8 retptr;
- int idx;
- u32 flags;
-};
+pthread_barrier_t barr;
+pthread_t t0, t1;
TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
struct head_s *head_p;
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
index 1fedfc9da434..42d44e27802c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
@@ -446,6 +446,35 @@ __invalid_nexthop_test()
log_test "Unresolved neigh: nexthop does not exist: $desc"
}
+__invalid_nexthop_bucket_test()
+{
+ local desc=$1; shift
+ local dip=$1; shift
+ local via_add=$1; shift
+ local trap_name="unresolved_neigh"
+
+ RET=0
+
+ # Check that route to nexthop that does not exist triggers
+ # unresolved_neigh
+ ip nexthop add id 1 via $via_add dev $rp2
+ ip nexthop add id 10 group 1 type resilient buckets 32
+ ip route add $dip nhid 10
+
+ t0_packets=$(devlink_trap_rx_packets_get $trap_name)
+ ping_do $h1 $dip
+ t1_packets=$(devlink_trap_rx_packets_get $trap_name)
+
+ if [[ $t0_packets -eq $t1_packets ]]; then
+ check_err 1 "Trap counter did not increase"
+ fi
+
+ ip route del $dip nhid 10
+ ip nexthop del id 10
+ ip nexthop del id 1
+ log_test "Unresolved neigh: nexthop bucket does not exist: $desc"
+}
+
unresolved_neigh_test()
{
__host_miss_test "IPv4" 198.51.100.1
@@ -453,6 +482,8 @@ unresolved_neigh_test()
__invalid_nexthop_test "IPv4" 198.51.100.1 198.51.100.3 24 198.51.100.4
__invalid_nexthop_test "IPv6" 2001:db8:2::1 2001:db8:2::3 64 \
2001:db8:2::4
+ __invalid_nexthop_bucket_test "IPv4" 198.51.100.1 198.51.100.4
+ __invalid_nexthop_bucket_test "IPv6" 2001:db8:2::1 2001:db8:2::4
}
vrf_without_routes_create()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index ed346da5d3cb..a217f9f6775b 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -33,6 +33,7 @@ ALL_TESTS="
nexthop_obj_invalid_test
nexthop_obj_offload_test
nexthop_obj_group_offload_test
+ nexthop_obj_bucket_offload_test
nexthop_obj_blackhole_offload_test
nexthop_obj_route_offload_test
devlink_reload_test
@@ -739,11 +740,28 @@ nexthop_obj_invalid_test()
ip nexthop add id 1 dev $swp1
ip nexthop add id 2 dev $swp1
+ ip nexthop add id 3 via 192.0.2.3 dev $swp1
ip nexthop add id 10 group 1/2
check_fail $? "managed to configure a nexthop group with device-only nexthops when should not"
+ ip nexthop add id 10 group 3 type resilient buckets 7
+ check_fail $? "managed to configure a too small resilient nexthop group when should not"
+
+ ip nexthop add id 10 group 3 type resilient buckets 129
+ check_fail $? "managed to configure a resilient nexthop group with invalid number of buckets when should not"
+
+ ip nexthop add id 10 group 1/2 type resilient buckets 32
+ check_fail $? "managed to configure a resilient nexthop group with device-only nexthops when should not"
+
+ ip nexthop add id 10 group 3 type resilient buckets 32
+ check_err $? "failed to configure a valid resilient nexthop group"
+ ip nexthop replace id 3 dev $swp1
+ check_fail $? "managed to populate a nexthop bucket with a device-only nexthop when should not"
+
log_test "nexthop objects - invalid configurations"
+ ip nexthop del id 10
+ ip nexthop del id 3
ip nexthop del id 2
ip nexthop del id 1
@@ -858,6 +876,70 @@ nexthop_obj_group_offload_test()
simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
}
+nexthop_obj_bucket_offload_test()
+{
+ # Test offload indication of nexthop buckets
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.2 dev $swp1
+ ip nexthop add id 2 via 2001:db8:1::2 dev $swp1
+ ip nexthop add id 10 group 1/2 type resilient buckets 32 idle_timer 0
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop bucket show nhid 1
+ check_err $? "IPv4 nexthop buckets not marked as offloaded when should"
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop bucket show nhid 2
+ check_err $? "IPv6 nexthop buckets not marked as offloaded when should"
+
+ # Invalidate nexthop id 1
+ ip neigh replace 192.0.2.2 nud failed dev $swp1
+ busywait "$TIMEOUT" wait_for_trap \
+ ip nexthop bucket show nhid 1
+ check_err $? "IPv4 nexthop buckets not marked with trap when should"
+
+ # Invalidate nexthop id 2
+ ip neigh replace 2001:db8:1::2 nud failed dev $swp1
+ busywait "$TIMEOUT" wait_for_trap \
+ ip nexthop bucket show nhid 2
+ check_err $? "IPv6 nexthop buckets not marked with trap when should"
+
+ # Revalidate nexthop id 1 by changing its configuration
+ ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop bucket show nhid 1
+ check_err $? "nexthop bucket not marked as offloaded after revalidating nexthop"
+
+ # Revalidate nexthop id 2 by changing its neighbour
+ ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop bucket show nhid 2
+ check_err $? "nexthop bucket not marked as offloaded after revalidating neighbour"
+
+ log_test "nexthop bucket offload indication"
+
+ ip neigh del 2001:db8:1::2 dev $swp1
+ ip neigh del 192.0.2.3 dev $swp1
+ ip neigh del 192.0.2.2 dev $swp1
+ ip nexthop del id 10
+ ip nexthop del id 2
+ ip nexthop del id 1
+
+ simple_if_fini $swp2
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
nexthop_obj_blackhole_offload_test()
{
# Test offload indication of blackhole nexthop objects
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh
deleted file mode 100755
index 0231205a7147..000000000000
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh
+++ /dev/null
@@ -1,77 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-lib_dir=$(dirname $0)/../../../../net/forwarding
-
-VXPORT=4789
-
-ALL_TESTS="
- create_dot1d_and_dot1ad_vxlans
-"
-NUM_NETIFS=2
-source $lib_dir/lib.sh
-
-setup_prepare()
-{
- swp1=${NETIFS[p1]}
- swp2=${NETIFS[p2]}
-
- ip link set dev $swp1 up
- ip link set dev $swp2 up
-}
-
-cleanup()
-{
- pre_cleanup
-
- ip link set dev $swp2 down
- ip link set dev $swp1 down
-}
-
-create_dot1d_and_dot1ad_vxlans()
-{
- RET=0
-
- ip link add dev br0 type bridge vlan_filtering 1 vlan_protocol 802.1ad \
- vlan_default_pvid 0 mcast_snooping 0
- ip link set dev br0 up
-
- ip link add name vx100 type vxlan id 1000 local 192.0.2.17 dstport \
- "$VXPORT" nolearning noudpcsum tos inherit ttl 100
- ip link set dev vx100 up
-
- ip link set dev $swp1 master br0
- ip link set dev vx100 master br0
- bridge vlan add vid 100 dev vx100 pvid untagged
-
- ip link add dev br1 type bridge vlan_filtering 0 mcast_snooping 0
- ip link set dev br1 up
-
- ip link add name vx200 type vxlan id 2000 local 192.0.2.17 dstport \
- "$VXPORT" nolearning noudpcsum tos inherit ttl 100
- ip link set dev vx200 up
-
- ip link set dev $swp2 master br1
- ip link set dev vx200 master br1 2>/dev/null
- check_fail $? "802.1d and 802.1ad VxLANs at the same time not rejected"
-
- ip link set dev vx200 master br1 2>&1 >/dev/null \
- | grep -q mlxsw_spectrum
- check_err $? "802.1d and 802.1ad VxLANs at the same time rejected without extack"
-
- log_test "create 802.1d and 802.1ad VxLANs"
-
- ip link del dev vx200
- ip link del dev br1
- ip link del dev vx100
- ip link del dev br0
-}
-
-trap cleanup EXIT
-
-setup_prepare
-setup_wait
-
-tests_run
-
-exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
index 553cb9fad508..5ec3beb637c8 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
@@ -11,6 +11,7 @@ ALL_TESTS="
matchall_mirror_behind_flower_ingress_test
matchall_sample_behind_flower_ingress_test
matchall_mirror_behind_flower_egress_test
+ matchall_proto_match_test
police_limits_test
multi_police_test
"
@@ -18,6 +19,7 @@ NUM_NETIFS=2
source $lib_dir/tc_common.sh
source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
switch_create()
{
@@ -166,7 +168,8 @@ matchall_sample_egress_test()
RET=0
# It is forbidden in mlxsw driver to have matchall with sample action
- # bound on egress
+ # bound on egress. Spectrum-1 specific restriction
+ [[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return
tc qdisc add dev $swp1 clsact
@@ -289,6 +292,22 @@ matchall_mirror_behind_flower_egress_test()
matchall_behind_flower_egress_test "mirror" "mirred egress mirror dev $swp2"
}
+matchall_proto_match_test()
+{
+ RET=0
+
+ tc qdisc add dev $swp1 clsact
+
+ tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
+ matchall skip_sw \
+ action sample group 1 rate 100
+ check_fail $? "Incorrect success to add matchall rule with protocol match"
+
+ tc qdisc del dev $swp1 clsact
+
+ log_test "matchall protocol match"
+}
+
police_limits_test()
{
RET=0
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
index 75d00104f291..093bed088ad0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
@@ -34,6 +34,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding
ALL_TESTS="
tc_sample_rate_test
tc_sample_max_rate_test
+ tc_sample_conflict_test
tc_sample_group_conflict_test
tc_sample_md_iif_test
tc_sample_md_lag_iif_test
@@ -41,6 +42,10 @@ ALL_TESTS="
tc_sample_md_lag_oif_test
tc_sample_md_out_tc_test
tc_sample_md_out_tc_occ_test
+ tc_sample_md_latency_test
+ tc_sample_acl_group_conflict_test
+ tc_sample_acl_rate_test
+ tc_sample_acl_max_rate_test
"
NUM_NETIFS=8
CAPTURE_FILE=$(mktemp)
@@ -268,6 +273,35 @@ tc_sample_max_rate_test()
log_test "tc sample maximum rate"
}
+tc_sample_conflict_test()
+{
+ RET=0
+
+ # Test that two sampling rules cannot be configured on the same port,
+ # even when they share the same parameters.
+
+ tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+ skip_sw action sample rate 1024 group 1
+ check_err $? "Failed to configure sampling rule"
+
+ tc filter add dev $rp1 ingress protocol all pref 2 handle 102 matchall \
+ skip_sw action sample rate 1024 group 1 &> /dev/null
+ check_fail $? "Managed to configure second sampling rule"
+
+ # Delete the first rule and make sure the second rule can now be
+ # configured.
+
+ tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+
+ tc filter add dev $rp1 ingress protocol all pref 2 handle 102 matchall \
+ skip_sw action sample rate 1024 group 1
+ check_err $? "Failed to configure sampling rule after deletion"
+
+ log_test "tc sample conflict test"
+
+ tc filter del dev $rp1 ingress protocol all pref 2 handle 102 matchall
+}
+
tc_sample_group_conflict_test()
{
RET=0
@@ -482,6 +516,137 @@ tc_sample_md_out_tc_occ_test()
tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
}
+tc_sample_md_latency_test()
+{
+ RET=0
+
+ # Egress sampling not supported on Spectrum-1.
+ [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+ tc filter add dev $rp2 egress protocol all pref 1 handle 101 matchall \
+ skip_sw action sample rate 5 group 1
+ check_err $? "Failed to configure sampling rule"
+
+ psample_capture_start
+
+ ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+ -B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+ psample_capture_stop
+
+ grep -q -e "latency " $CAPTURE_FILE
+ check_err $? "Sampled packets do not have latency attribute"
+
+ log_test "tc sample latency"
+
+ tc filter del dev $rp2 egress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_acl_group_conflict_test()
+{
+ RET=0
+
+ # Test that two flower sampling rules cannot be configured on the same
+ # port with different groups.
+
+ # Policy-based sampling is not supported on Spectrum-1.
+ [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+ tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+ skip_sw action sample rate 1024 group 1
+ check_err $? "Failed to configure sampling rule"
+
+ tc filter add dev $rp1 ingress protocol ip pref 2 handle 102 flower \
+ skip_sw action sample rate 1024 group 1
+ check_err $? "Failed to configure sampling rule with same group"
+
+ tc filter add dev $rp1 ingress protocol ip pref 3 handle 103 flower \
+ skip_sw action sample rate 1024 group 2 &> /dev/null
+ check_fail $? "Managed to configure sampling rule with conflicting group"
+
+ log_test "tc sample (w/ flower) group conflict test"
+
+ tc filter del dev $rp1 ingress protocol ip pref 2 handle 102 flower
+ tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+}
+
+__tc_sample_acl_rate_test()
+{
+ local bind=$1; shift
+ local port=$1; shift
+ local pkts pct
+
+ RET=0
+
+ # Policy-based sampling is not supported on Spectrum-1.
+ [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+ tc filter add dev $port $bind protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 198.51.100.1 action sample rate 32 group 1
+ check_err $? "Failed to configure sampling rule"
+
+ psample_capture_start
+
+ ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+ -B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+ psample_capture_stop
+
+ pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l)
+ pct=$((100 * (pkts - 100) / 100))
+ (( -25 <= pct && pct <= 25))
+ check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%"
+
+ # Setup a filter that should not match any packet and make sure packets
+ # are not sampled.
+ tc filter del dev $port $bind protocol ip pref 1 handle 101 flower
+
+ tc filter add dev $port $bind protocol ip pref 1 handle 101 flower \
+ skip_sw dst_ip 198.51.100.10 action sample rate 32 group 1
+ check_err $? "Failed to configure sampling rule"
+
+ psample_capture_start
+
+ ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+ -B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+ psample_capture_stop
+
+ grep -q -e "group 1 " $CAPTURE_FILE
+ check_fail $? "Sampled packets when should not"
+
+ log_test "tc sample (w/ flower) rate ($bind)"
+
+ tc filter del dev $port $bind protocol ip pref 1 handle 101 flower
+}
+
+tc_sample_acl_rate_test()
+{
+ __tc_sample_acl_rate_test ingress $rp1
+ __tc_sample_acl_rate_test egress $rp2
+}
+
+tc_sample_acl_max_rate_test()
+{
+ RET=0
+
+ # Policy-based sampling is not supported on Spectrum-1.
+ [[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+ tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+ skip_sw action sample rate $((2 ** 24 - 1)) group 1
+ check_err $? "Failed to configure sampling rule with max rate"
+
+ tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+
+ tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+ skip_sw action sample rate $((2 ** 24)) \
+ group 1 &> /dev/null
+ check_fail $? "Managed to configure sampling rate above maximum"
+
+ log_test "tc sample (w/ flower) maximum rate"
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
index 9f64d5c7107b..7ca1f030d209 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
@@ -24,8 +24,11 @@ function check {
local code=$1
local str=$2
local exp_str=$3
+ local exp_fail=$4
- if [ $code -ne 0 ]; then
+ [ -z "$exp_fail" ] && cop="-ne" || cop="-eq"
+
+ if [ $code $cop 0 ]; then
((num_errors++))
return
fi
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
new file mode 100755
index 000000000000..0c56746e9ce0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
@@ -0,0 +1,110 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+NSIM_NETDEV=$(make_netdev)
+[ a$ETHTOOL == a ] && ETHTOOL=ethtool
+
+set -o pipefail
+
+# netdevsim starts out with None/None
+s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+check $? "$s" "Configured FEC encodings: None
+Active FEC encoding: None"
+
+# Test Auto
+$ETHTOOL --set-fec $NSIM_NETDEV encoding auto
+check $?
+s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+check $? "$s" "Configured FEC encodings: Auto
+Active FEC encoding: Off"
+
+# Test case in-sensitivity
+for o in off Off OFF; do
+ $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
+ check $?
+ s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+ check $? "$s" "Configured FEC encodings: Off
+Active FEC encoding: Off"
+done
+
+for o in BaseR baser BAser; do
+ $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
+ check $?
+ s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+ check $? "$s" "Configured FEC encodings: BaseR
+Active FEC encoding: BaseR"
+done
+
+for o in llrs rs; do
+ $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
+ check $?
+ s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+ check $? "$s" "Configured FEC encodings: ${o^^}
+Active FEC encoding: ${o^^}"
+done
+
+# Test mutliple bits
+$ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs
+check $?
+s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+check $? "$s" "Configured FEC encodings: RS LLRS
+Active FEC encoding: LLRS"
+
+$ETHTOOL --set-fec $NSIM_NETDEV encoding rs off auto
+check $?
+s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+check $? "$s" "Configured FEC encodings: Auto Off RS
+Active FEC encoding: RS"
+
+# Make sure other link modes are rejected
+$ETHTOOL --set-fec $NSIM_NETDEV encoding FIBRE 2>/dev/null
+check $? '' '' 1
+
+$ETHTOOL --set-fec $NSIM_NETDEV encoding bla-bla-bla 2>/dev/null
+check $? '' '' 1
+
+# Try JSON
+$ETHTOOL --json --show-fec $NSIM_NETDEV | jq empty >>/dev/null 2>&1
+if [ $? -eq 0 ]; then
+ $ETHTOOL --set-fec $NSIM_NETDEV encoding auto
+ check $?
+
+ s=$($ETHTOOL --json --show-fec $NSIM_NETDEV | jq '.[].config[]')
+ check $? "$s" '"Auto"'
+ s=$($ETHTOOL --json --show-fec $NSIM_NETDEV | jq '.[].active[]')
+ check $? "$s" '"Off"'
+
+ $ETHTOOL --set-fec $NSIM_NETDEV encoding auto RS
+ check $?
+
+ s=$($ETHTOOL --json --show-fec $NSIM_NETDEV | jq '.[].config[]')
+ check $? "$s" '"Auto"
+"RS"'
+ s=$($ETHTOOL --json --show-fec $NSIM_NETDEV | jq '.[].active[]')
+ check $? "$s" '"RS"'
+fi
+
+# Test error injection
+echo 11 > $NSIM_DEV_DFS/ethtool/get_err
+
+$ETHTOOL --show-fec $NSIM_NETDEV >>/dev/null 2>&1
+check $? '' '' 1
+
+echo 0 > $NSIM_DEV_DFS/ethtool/get_err
+echo 11 > $NSIM_DEV_DFS/ethtool/set_err
+
+$ETHTOOL --show-fec $NSIM_NETDEV >>/dev/null 2>&1
+check $?
+
+$ETHTOOL --set-fec $NSIM_NETDEV encoding RS 2>/dev/null
+check $? '' '' 1
+
+if [ $num_errors -eq 0 ]; then
+ echo "PASSED all $((num_passes)) checks"
+ exit 0
+else
+ echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+ exit 1
+fi
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 32b87cc77c8e..7bd7e776c266 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -8,10 +8,13 @@
/x86_64/debug_regs
/x86_64/evmcs_test
/x86_64/get_cpuid_test
+/x86_64/get_msr_index_features
/x86_64/kvm_pv_test
+/x86_64/hyperv_clock
/x86_64/hyperv_cpuid
/x86_64/mmio_warning_test
/x86_64/platform_info_test
+/x86_64/set_boot_cpu_id
/x86_64/set_sregs_test
/x86_64/smm_test
/x86_64/state_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index a6d61f451f88..67eebb53235f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -39,12 +39,15 @@ LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
TEST_GEN_PROGS_x86_64 += x86_64/smm_test
TEST_GEN_PROGS_x86_64 += x86_64/state_test
diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
index 2f2eeb8a1d86..5aadf84c91c0 100644
--- a/tools/testing/selftests/kvm/hardware_disable_test.c
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -108,7 +108,7 @@ static void run_test(uint32_t run)
kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
vm_create_irqchip(vm);
- fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run);
+ pr_debug("%s: [%d] start vcpus\n", __func__, run);
for (i = 0; i < VCPU_NUM; ++i) {
vm_vcpu_add_default(vm, i, guest_code);
payloads[i].vm = vm;
@@ -124,7 +124,7 @@ static void run_test(uint32_t run)
check_set_affinity(throw_away, &cpu_set);
}
}
- fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run);
+ pr_debug("%s: [%d] all threads launched\n", __func__, run);
sem_post(sem);
for (i = 0; i < VCPU_NUM; ++i)
check_join(threads[i], &b);
@@ -147,16 +147,16 @@ int main(int argc, char **argv)
if (pid == 0)
run_test(i); /* This function always exits */
- fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i);
+ pr_debug("%s: [%d] waiting semaphore\n", __func__, i);
sem_wait(sem);
r = (rand() % DELAY_US_MAX) + 1;
- fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r);
+ pr_debug("%s: [%d] waiting %dus\n", __func__, i, r);
usleep(r);
r = waitpid(pid, &s, WNOHANG);
TEST_ASSERT(r != pid,
"%s: [%d] child exited unexpectedly status: [%d]",
__func__, i, s);
- fprintf(stderr, "%s: [%d] killing child\n", __func__, i);
+ pr_debug("%s: [%d] killing child\n", __func__, i);
kill(pid, SIGKILL);
}
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 2d7eb6989e83..0f4258eaa629 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -16,6 +16,7 @@
#include "sparsebit.h"
+#define KVM_DEV_PATH "/dev/kvm"
#define KVM_MAX_VCPUS 512
/*
@@ -133,6 +134,7 @@ void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
void *arg);
void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg);
void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index e5fbf16f725b..b8849a1aca79 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1697,11 +1697,16 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
{
int ret;
- ret = ioctl(vm->fd, cmd, arg);
+ ret = _vm_ioctl(vm, cmd, arg);
TEST_ASSERT(ret == 0, "vm ioctl %lu failed, rc: %i errno: %i (%s)",
cmd, ret, errno, strerror(errno));
}
+int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+ return ioctl(vm->fd, cmd, arg);
+}
+
/*
* KVM system ioctl
*
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 34465dc562d8..91ce1b5d480b 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -10,8 +10,6 @@
#include "sparsebit.h"
-#define KVM_DEV_PATH "/dev/kvm"
-
struct userspace_mem_region {
struct kvm_userspace_memory_region region;
struct sparsebit *unused_phy_pages;
diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
new file mode 100644
index 000000000000..cb953df4d7d0
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that KVM_GET_MSR_INDEX_LIST and
+ * KVM_GET_MSR_FEATURE_INDEX_LIST work as intended
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+static int kvm_num_index_msrs(int kvm_fd, int nmsrs)
+{
+ struct kvm_msr_list *list;
+ int r;
+
+ list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+ list->nmsrs = nmsrs;
+ r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+ TEST_ASSERT(r == -1 && errno == E2BIG,
+ "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
+ r);
+
+ r = list->nmsrs;
+ free(list);
+ return r;
+}
+
+static void test_get_msr_index(void)
+{
+ int old_res, res, kvm_fd, r;
+ struct kvm_msr_list *list;
+
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ old_res = kvm_num_index_msrs(kvm_fd, 0);
+ TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
+
+ if (old_res != 1) {
+ res = kvm_num_index_msrs(kvm_fd, 1);
+ TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1");
+ TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical");
+ }
+
+ list = malloc(sizeof(*list) + old_res * sizeof(list->indices[0]));
+ list->nmsrs = old_res;
+ r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+
+ TEST_ASSERT(r == 0,
+ "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i",
+ r);
+ TEST_ASSERT(list->nmsrs == old_res, "Expecting nmsrs to be identical");
+ free(list);
+
+ close(kvm_fd);
+}
+
+static int kvm_num_feature_msrs(int kvm_fd, int nmsrs)
+{
+ struct kvm_msr_list *list;
+ int r;
+
+ list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+ list->nmsrs = nmsrs;
+ r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list);
+ TEST_ASSERT(r == -1 && errno == E2BIG,
+ "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST probe, r: %i",
+ r);
+
+ r = list->nmsrs;
+ free(list);
+ return r;
+}
+
+struct kvm_msr_list *kvm_get_msr_feature_list(int kvm_fd, int nmsrs)
+{
+ struct kvm_msr_list *list;
+ int r;
+
+ list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+ list->nmsrs = nmsrs;
+ r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list);
+
+ TEST_ASSERT(r == 0,
+ "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i",
+ r);
+
+ return list;
+}
+
+static void test_get_msr_feature(void)
+{
+ int res, old_res, i, kvm_fd;
+ struct kvm_msr_list *feature_list;
+
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ old_res = kvm_num_feature_msrs(kvm_fd, 0);
+ TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
+
+ if (old_res != 1) {
+ res = kvm_num_feature_msrs(kvm_fd, 1);
+ TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1");
+ TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical");
+ }
+
+ feature_list = kvm_get_msr_feature_list(kvm_fd, old_res);
+ TEST_ASSERT(old_res == feature_list->nmsrs,
+ "Unmatching number of msr indexes");
+
+ for (i = 0; i < feature_list->nmsrs; i++)
+ kvm_get_feature_msr(feature_list->indices[i]);
+
+ free(feature_list);
+ close(kvm_fd);
+}
+
+int main(int argc, char *argv[])
+{
+ if (kvm_check_cap(KVM_CAP_GET_MSR_FEATURES))
+ test_get_msr_feature();
+
+ test_get_msr_index();
+}
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
new file mode 100644
index 000000000000..7f1d2765572c
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -0,0 +1,269 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021, Red Hat, Inc.
+ *
+ * Tests for Hyper-V clocksources
+ */
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+struct ms_hyperv_tsc_page {
+ volatile u32 tsc_sequence;
+ u32 reserved1;
+ volatile u64 tsc_scale;
+ volatile s64 tsc_offset;
+} __packed;
+
+#define HV_X64_MSR_GUEST_OS_ID 0x40000000
+#define HV_X64_MSR_TIME_REF_COUNT 0x40000020
+#define HV_X64_MSR_REFERENCE_TSC 0x40000021
+#define HV_X64_MSR_TSC_FREQUENCY 0x40000022
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106
+#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107
+
+/* Simplified mul_u64_u64_shr() */
+static inline u64 mul_u64_u64_shr64(u64 a, u64 b)
+{
+ union {
+ u64 ll;
+ struct {
+ u32 low, high;
+ } l;
+ } rm, rn, rh, a0, b0;
+ u64 c;
+
+ a0.ll = a;
+ b0.ll = b;
+
+ rm.ll = (u64)a0.l.low * b0.l.high;
+ rn.ll = (u64)a0.l.high * b0.l.low;
+ rh.ll = (u64)a0.l.high * b0.l.high;
+
+ rh.l.low = c = rm.l.high + rn.l.high + rh.l.low;
+ rh.l.high = (c >> 32) + rh.l.high;
+
+ return rh.ll;
+}
+
+static inline void nop_loop(void)
+{
+ int i;
+
+ for (i = 0; i < 1000000; i++)
+ asm volatile("nop");
+}
+
+static inline void check_tsc_msr_rdtsc(void)
+{
+ u64 tsc_freq, r1, r2, t1, t2;
+ s64 delta_ns;
+
+ tsc_freq = rdmsr(HV_X64_MSR_TSC_FREQUENCY);
+ GUEST_ASSERT(tsc_freq > 0);
+
+ /* First, check MSR-based clocksource */
+ r1 = rdtsc();
+ t1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+ nop_loop();
+ r2 = rdtsc();
+ t2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+
+ GUEST_ASSERT(r2 > r1 && t2 > t1);
+
+ /* HV_X64_MSR_TIME_REF_COUNT is in 100ns */
+ delta_ns = ((t2 - t1) * 100) - ((r2 - r1) * 1000000000 / tsc_freq);
+ if (delta_ns < 0)
+ delta_ns = -delta_ns;
+
+ /* 1% tolerance */
+ GUEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100);
+}
+
+static inline u64 get_tscpage_ts(struct ms_hyperv_tsc_page *tsc_page)
+{
+ return mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+}
+
+static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page)
+{
+ u64 r1, r2, t1, t2;
+
+ /* Compare TSC page clocksource with HV_X64_MSR_TIME_REF_COUNT */
+ t1 = get_tscpage_ts(tsc_page);
+ r1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+
+ /* 10 ms tolerance */
+ GUEST_ASSERT(r1 >= t1 && r1 - t1 < 100000);
+ nop_loop();
+
+ t2 = get_tscpage_ts(tsc_page);
+ r2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+ GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000);
+}
+
+static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_gpa)
+{
+ u64 tsc_scale, tsc_offset;
+
+ /* Set Guest OS id to enable Hyper-V emulation */
+ GUEST_SYNC(1);
+ wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48);
+ GUEST_SYNC(2);
+
+ check_tsc_msr_rdtsc();
+
+ GUEST_SYNC(3);
+
+ /* Set up TSC page is disabled state, check that it's clean */
+ wrmsr(HV_X64_MSR_REFERENCE_TSC, tsc_page_gpa);
+ GUEST_ASSERT(tsc_page->tsc_sequence == 0);
+ GUEST_ASSERT(tsc_page->tsc_scale == 0);
+ GUEST_ASSERT(tsc_page->tsc_offset == 0);
+
+ GUEST_SYNC(4);
+
+ /* Set up TSC page is enabled state */
+ wrmsr(HV_X64_MSR_REFERENCE_TSC, tsc_page_gpa | 0x1);
+ GUEST_ASSERT(tsc_page->tsc_sequence != 0);
+
+ GUEST_SYNC(5);
+
+ check_tsc_msr_tsc_page(tsc_page);
+
+ GUEST_SYNC(6);
+
+ tsc_offset = tsc_page->tsc_offset;
+ /* Call KVM_SET_CLOCK from userspace, check that TSC page was updated */
+
+ GUEST_SYNC(7);
+ /* Sanity check TSC page timestamp, it should be close to 0 */
+ GUEST_ASSERT(get_tscpage_ts(tsc_page) < 100000);
+
+ GUEST_ASSERT(tsc_page->tsc_offset != tsc_offset);
+
+ nop_loop();
+
+ /*
+ * Enable Re-enlightenment and check that TSC page stays constant across
+ * KVM_SET_CLOCK.
+ */
+ wrmsr(HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0x1 << 16 | 0xff);
+ wrmsr(HV_X64_MSR_TSC_EMULATION_CONTROL, 0x1);
+ tsc_offset = tsc_page->tsc_offset;
+ tsc_scale = tsc_page->tsc_scale;
+ GUEST_SYNC(8);
+ GUEST_ASSERT(tsc_page->tsc_offset == tsc_offset);
+ GUEST_ASSERT(tsc_page->tsc_scale == tsc_scale);
+
+ GUEST_SYNC(9);
+
+ check_tsc_msr_tsc_page(tsc_page);
+
+ /*
+ * Disable re-enlightenment and TSC page, check that KVM doesn't update
+ * it anymore.
+ */
+ wrmsr(HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0);
+ wrmsr(HV_X64_MSR_TSC_EMULATION_CONTROL, 0);
+ wrmsr(HV_X64_MSR_REFERENCE_TSC, 0);
+ memset(tsc_page, 0, sizeof(*tsc_page));
+
+ GUEST_SYNC(10);
+ GUEST_ASSERT(tsc_page->tsc_sequence == 0);
+ GUEST_ASSERT(tsc_page->tsc_offset == 0);
+ GUEST_ASSERT(tsc_page->tsc_scale == 0);
+
+ GUEST_DONE();
+}
+
+#define VCPU_ID 0
+
+static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm)
+{
+ u64 tsc_freq, r1, r2, t1, t2;
+ s64 delta_ns;
+
+ tsc_freq = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TSC_FREQUENCY);
+ TEST_ASSERT(tsc_freq > 0, "TSC frequency must be nonzero");
+
+ /* First, check MSR-based clocksource */
+ r1 = rdtsc();
+ t1 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+ nop_loop();
+ r2 = rdtsc();
+ t2 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+
+ TEST_ASSERT(t2 > t1, "Time reference MSR is not monotonic (%ld <= %ld)", t1, t2);
+
+ /* HV_X64_MSR_TIME_REF_COUNT is in 100ns */
+ delta_ns = ((t2 - t1) * 100) - ((r2 - r1) * 1000000000 / tsc_freq);
+ if (delta_ns < 0)
+ delta_ns = -delta_ns;
+
+ /* 1% tolerance */
+ TEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100,
+ "Elapsed time does not match (MSR=%ld, TSC=%ld)",
+ (t2 - t1) * 100, (r2 - r1) * 1000000000 / tsc_freq);
+}
+
+int main(void)
+{
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct ucall uc;
+ vm_vaddr_t tsc_page_gva;
+ int stage;
+
+ vm = vm_create_default(VCPU_ID, 0, guest_main);
+ run = vcpu_state(vm, VCPU_ID);
+
+ vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+ tsc_page_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize());
+ TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
+ "TSC page has to be page aligned\n");
+ vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));
+
+ host_check_tsc_msr_rdtsc(vm);
+
+ for (stage = 1;; stage++) {
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ break;
+ case UCALL_DONE:
+ /* Keep in sync with guest_main() */
+ TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d\n",
+ stage);
+ goto out;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+
+ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+ uc.args[1] == stage,
+ "Stage %d: Unexpected register values vmexit, got %lx",
+ stage, (ulong)uc.args[1]);
+
+ /* Reset kvmclock triggering TSC page update */
+ if (stage == 7 || stage == 8 || stage == 10) {
+ struct kvm_clock_data clock = {0};
+
+ vm_ioctl(vm, KVM_SET_CLOCK, &clock);
+ }
+ }
+
+out:
+ kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
new file mode 100644
index 000000000000..12c558fc8074
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that KVM_SET_BOOT_CPU_ID works as intended
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#define _GNU_SOURCE /* for program_invocation_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define N_VCPU 2
+#define VCPU_ID0 0
+#define VCPU_ID1 1
+
+static uint32_t get_bsp_flag(void)
+{
+ return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP;
+}
+
+static void guest_bsp_vcpu(void *arg)
+{
+ GUEST_SYNC(1);
+
+ GUEST_ASSERT(get_bsp_flag() != 0);
+
+ GUEST_DONE();
+}
+
+static void guest_not_bsp_vcpu(void *arg)
+{
+ GUEST_SYNC(1);
+
+ GUEST_ASSERT(get_bsp_flag() == 0);
+
+ GUEST_DONE();
+}
+
+static void test_set_boot_busy(struct kvm_vm *vm)
+{
+ int res;
+
+ res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID0);
+ TEST_ASSERT(res == -1 && errno == EBUSY,
+ "KVM_SET_BOOT_CPU_ID set while running vm");
+}
+
+static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct ucall uc;
+ int stage;
+
+ for (stage = 0; stage < 2; stage++) {
+
+ vcpu_run(vm, vcpuid);
+
+ switch (get_ucall(vm, vcpuid, &uc)) {
+ case UCALL_SYNC:
+ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+ uc.args[1] == stage + 1,
+ "Stage %d: Unexpected register values vmexit, got %lx",
+ stage + 1, (ulong)uc.args[1]);
+ test_set_boot_busy(vm);
+ break;
+ case UCALL_DONE:
+ TEST_ASSERT(stage == 1,
+ "Expected GUEST_DONE in stage 2, got stage %d",
+ stage);
+ break;
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "%s at %s:%ld\n\tvalues: %#lx, %#lx",
+ (const char *)uc.args[0], __FILE__,
+ uc.args[1], uc.args[2], uc.args[3]);
+ default:
+ TEST_ASSERT(false, "Unexpected exit: %s",
+ exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason));
+ }
+ }
+}
+
+static struct kvm_vm *create_vm(void)
+{
+ struct kvm_vm *vm;
+ uint64_t vcpu_pages = (DEFAULT_STACK_PGS) * 2;
+ uint64_t extra_pg_pages = vcpu_pages / PTES_PER_MIN_PAGE * N_VCPU;
+ uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
+
+ pages = vm_adjust_num_guest_pages(VM_MODE_DEFAULT, pages);
+ vm = vm_create(VM_MODE_DEFAULT, pages, O_RDWR);
+
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+ vm_create_irqchip(vm);
+
+ return vm;
+}
+
+static void add_x86_vcpu(struct kvm_vm *vm, uint32_t vcpuid, bool bsp_code)
+{
+ if (bsp_code)
+ vm_vcpu_add_default(vm, vcpuid, guest_bsp_vcpu);
+ else
+ vm_vcpu_add_default(vm, vcpuid, guest_not_bsp_vcpu);
+
+ vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+}
+
+static void run_vm_bsp(uint32_t bsp_vcpu)
+{
+ struct kvm_vm *vm;
+ bool is_bsp_vcpu1 = bsp_vcpu == VCPU_ID1;
+
+ vm = create_vm();
+
+ if (is_bsp_vcpu1)
+ vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+
+ add_x86_vcpu(vm, VCPU_ID0, !is_bsp_vcpu1);
+ add_x86_vcpu(vm, VCPU_ID1, is_bsp_vcpu1);
+
+ run_vcpu(vm, VCPU_ID0);
+ run_vcpu(vm, VCPU_ID1);
+
+ kvm_vm_free(vm);
+}
+
+static void check_set_bsp_busy(void)
+{
+ struct kvm_vm *vm;
+ int res;
+
+ vm = create_vm();
+
+ add_x86_vcpu(vm, VCPU_ID0, true);
+ add_x86_vcpu(vm, VCPU_ID1, false);
+
+ res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+ TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set after adding vcpu");
+
+ run_vcpu(vm, VCPU_ID0);
+ run_vcpu(vm, VCPU_ID1);
+
+ res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+ TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set to a terminated vcpu");
+
+ kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+ if (!kvm_check_cap(KVM_CAP_SET_BOOT_CPU_ID)) {
+ print_skip("set_boot_cpu_id not available");
+ return 0;
+ }
+
+ run_vm_bsp(VCPU_ID0);
+ run_vm_bsp(VCPU_ID1);
+ run_vm_bsp(VCPU_ID0);
+
+ check_set_bsp_busy();
+}
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 25f198bec0b2..f4242a961088 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -23,6 +23,8 @@ TEST_PROGS += drop_monitor_tests.sh
TEST_PROGS += vrf_route_leaking.sh
TEST_PROGS += bareudp.sh
TEST_PROGS += unicast_extensions.sh
+TEST_PROGS += udpgro_fwd.sh
+TEST_PROGS += veth.sh
TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket nettest
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
diff --git a/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh b/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh
new file mode 100755
index 000000000000..5148d97a5df8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh
@@ -0,0 +1,366 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +--------------------+ +----------------------+
+# | H1 (vrf) | | H2 (vrf) |
+# | + h1.10 | | + h2.20 |
+# | | 192.0.2.1/28 | | | 192.0.2.2/28 |
+# | | | | | |
+# | + $h1 | | + $h2 |
+# | | | | | |
+# +----|---------------+ +--|-------------------+
+# | |
+# +----|--------------------------------------------------|--------------------+
+# | SW | | |
+# | +--|-------------------------------+ +----------------|------------------+ |
+# | | + $swp1 BR1 (802.1ad) | | BR2 (802.1d) + $swp2 | |
+# | | vid 100 pvid untagged | | | | |
+# | | | | + $swp2.20 | |
+# | | | | | |
+# | | + vx100 (vxlan) | | + vx200 (vxlan) | |
+# | | local 192.0.2.17 | | local 192.0.2.17 | |
+# | | remote 192.0.2.34 | | remote 192.0.2.50 | |
+# | | id 1000 dstport $VXPORT | | id 2000 dstport $VXPORT | |
+# | | vid 100 pvid untagged | | | |
+# | +--------------------------------- + +-----------------------------------+ |
+# | |
+# | 192.0.2.32/28 via 192.0.2.18 |
+# | 192.0.2.48/28 via 192.0.2.18 |
+# | |
+# | + $rp1 |
+# | | 192.0.2.17/28 |
+# +----|-----------------------------------------------------------------------+
+# |
+# +----|--------------------------------------------------------+
+# | | VRP2 (vrf) |
+# | + $rp2 |
+# | 192.0.2.18/28 |
+# | | (maybe) HW
+# =============================================================================
+# | | (likely) SW
+# | + v1 (veth) + v3 (veth) |
+# | | 192.0.2.33/28 | 192.0.2.49/28 |
+# +----|---------------------------------------|----------------+
+# | |
+# +----|------------------------------+ +----|------------------------------+
+# | + v2 (veth) NS1 (netns) | | + v4 (veth) NS2 (netns) |
+# | 192.0.2.34/28 | | 192.0.2.50/28 |
+# | | | |
+# | 192.0.2.16/28 via 192.0.2.33 | | 192.0.2.16/28 via 192.0.2.49 |
+# | 192.0.2.50/32 via 192.0.2.33 | | 192.0.2.34/32 via 192.0.2.49 |
+# | | | |
+# | +-------------------------------+ | | +-------------------------------+ |
+# | | BR3 (802.1ad) | | | | BR3 (802.1d) | |
+# | | + vx100 (vxlan) | | | | + vx200 (vxlan) | |
+# | | local 192.0.2.34 | | | | local 192.0.2.50 | |
+# | | remote 192.0.2.17 | | | | remote 192.0.2.17 | |
+# | | remote 192.0.2.50 | | | | remote 192.0.2.34 | |
+# | | id 1000 dstport $VXPORT | | | | id 2000 dstport $VXPORT | |
+# | | vid 100 pvid untagged | | | | | |
+# | | | | | | + w1.20 | |
+# | | | | | | | | |
+# | | + w1 (veth) | | | | + w1 (veth) | |
+# | | | vid 100 pvid untagged | | | | | | |
+# | +--|----------------------------+ | | +--|----------------------------+ |
+# | | | | | |
+# | +--|----------------------------+ | | +--|----------------------------+ |
+# | | | VW2 (vrf) | | | | | VW2 (vrf) | |
+# | | + w2 (veth) | | | | + w2 (veth) | |
+# | | | | | | | | | |
+# | | | | | | | | | |
+# | | + w2.10 | | | | + w2.20 | |
+# | | 192.0.2.3/28 | | | | 192.0.2.4/28 | |
+# | +-------------------------------+ | | +-------------------------------+ |
+# +-----------------------------------+ +-----------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+ ping_ipv4
+ "}
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1
+ tc qdisc add dev $h1 clsact
+ vlan_create $h1 10 v$h1 192.0.2.1/28
+}
+
+h1_destroy()
+{
+ vlan_destroy $h1 10
+ tc qdisc del dev $h1 clsact
+ simple_if_fini $h1
+}
+
+h2_create()
+{
+ simple_if_init $h2
+ tc qdisc add dev $h2 clsact
+ vlan_create $h2 20 v$h2 192.0.2.2/28
+}
+
+h2_destroy()
+{
+ vlan_destroy $h2 20
+ tc qdisc del dev $h2 clsact
+ simple_if_fini $h2
+}
+
+rp1_set_addr()
+{
+ ip address add dev $rp1 192.0.2.17/28
+
+ ip route add 192.0.2.32/28 nexthop via 192.0.2.18
+ ip route add 192.0.2.48/28 nexthop via 192.0.2.18
+}
+
+rp1_unset_addr()
+{
+ ip route del 192.0.2.48/28 nexthop via 192.0.2.18
+ ip route del 192.0.2.32/28 nexthop via 192.0.2.18
+
+ ip address del dev $rp1 192.0.2.17/28
+}
+
+switch_create()
+{
+ #### BR1 ####
+ ip link add name br1 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ # Make sure the bridge uses the MAC address of the local port and not
+ # that of the VxLAN's device.
+ ip link set dev br1 address $(mac_get $swp1)
+ ip link set dev br1 up
+
+ #### BR2 ####
+ ip link add name br2 type bridge vlan_filtering 0 mcast_snooping 0
+ # Make sure the bridge uses the MAC address of the local port and not
+ # that of the VxLAN's device.
+ ip link set dev br2 address $(mac_get $swp2)
+ ip link set dev br2 up
+
+ ip link set dev $rp1 up
+ rp1_set_addr
+
+ #### VX100 ####
+ ip link add name vx100 type vxlan id 1000 local 192.0.2.17 \
+ dstport "$VXPORT" nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx100 up
+
+ ip link set dev vx100 master br1
+ bridge vlan add vid 100 dev vx100 pvid untagged
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+ bridge vlan add vid 100 dev $swp1 pvid untagged
+
+ #### VX200 ####
+ ip link add name vx200 type vxlan id 2000 local 192.0.2.17 \
+ dstport "$VXPORT" nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx200 up
+
+ ip link set dev vx200 master br2
+
+ ip link set dev $swp2 up
+ ip link add name $swp2.20 link $swp2 type vlan id 20
+ ip link set dev $swp2.20 master br2
+ ip link set dev $swp2.20 up
+
+ bridge fdb append dev vx100 00:00:00:00:00:00 dst 192.0.2.34 self
+ bridge fdb append dev vx200 00:00:00:00:00:00 dst 192.0.2.50 self
+}
+
+switch_destroy()
+{
+ bridge fdb del dev vx200 00:00:00:00:00:00 dst 192.0.2.50 self
+ bridge fdb del dev vx100 00:00:00:00:00:00 dst 192.0.2.34 self
+
+ ip link set dev vx200 nomaster
+ ip link set dev vx200 down
+ ip link del dev vx200
+
+ ip link del dev $swp2.20
+ ip link set dev $swp2 down
+ ip link set dev $swp2 nomaster
+
+ bridge vlan del vid 100 dev $swp1
+ ip link set dev $swp1 down
+ ip link set dev $swp1 nomaster
+
+ ip link set dev vx100 nomaster
+ ip link set dev vx100 down
+ ip link del dev vx100
+
+ rp1_unset_addr
+ ip link set dev $rp1 down
+
+ ip link set dev br2 down
+ ip link del dev br2
+
+ ip link set dev br1 down
+ ip link del dev br1
+}
+
+vrp2_create()
+{
+ simple_if_init $rp2 192.0.2.18/28
+ __simple_if_init v1 v$rp2 192.0.2.33/28
+ __simple_if_init v3 v$rp2 192.0.2.49/28
+ tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+ tc qdisc del dev v1 clsact
+ __simple_if_fini v3 192.0.2.49/28
+ __simple_if_fini v1 192.0.2.33/28
+ simple_if_fini $rp2 192.0.2.18/28
+}
+
+ns_init_common()
+{
+ local in_if=$1; shift
+ local in_addr=$1; shift
+ local other_in_addr=$1; shift
+ local vxlan_name=$1; shift
+ local vxlan_id=$1; shift
+ local vlan_id=$1; shift
+ local host_addr=$1; shift
+ local nh_addr=$1; shift
+
+ ip link set dev $in_if up
+ ip address add dev $in_if $in_addr/28
+ tc qdisc add dev $in_if clsact
+
+ ip link add name br3 type bridge vlan_filtering 0
+ ip link set dev br3 up
+
+ ip link add name w1 type veth peer name w2
+
+ ip link set dev w1 master br3
+ ip link set dev w1 up
+
+ ip link add name $vxlan_name type vxlan id $vxlan_id local $in_addr \
+ dstport "$VXPORT"
+ ip link set dev $vxlan_name up
+ bridge fdb append dev $vxlan_name 00:00:00:00:00:00 dst 192.0.2.17 self
+ bridge fdb append dev $vxlan_name 00:00:00:00:00:00 dst $other_in_addr self
+
+ ip link set dev $vxlan_name master br3
+ tc qdisc add dev $vxlan_name clsact
+
+ simple_if_init w2
+ vlan_create w2 $vlan_id vw2 $host_addr/28
+
+ ip route add 192.0.2.16/28 nexthop via $nh_addr
+ ip route add $other_in_addr/32 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+ ip netns add ns1
+ ip link set dev v2 netns ns1
+ in_ns ns1 \
+ ns_init_common v2 192.0.2.34 192.0.2.50 vx100 1000 10 192.0.2.3 \
+ 192.0.2.33
+
+ in_ns ns1 bridge vlan add vid 100 dev vx100 pvid untagged
+}
+
+ns1_destroy()
+{
+ ip netns exec ns1 ip link set dev v2 netns 1
+ ip netns del ns1
+}
+
+ns2_create()
+{
+ ip netns add ns2
+ ip link set dev v4 netns ns2
+ in_ns ns2 \
+ ns_init_common v4 192.0.2.50 192.0.2.34 vx200 2000 20 192.0.2.4 \
+ 192.0.2.49
+
+ in_ns ns2 ip link add name w1.20 link w1 type vlan id 20
+ in_ns ns2 ip link set dev w1.20 master br3
+ in_ns ns2 ip link set dev w1.20 up
+}
+
+ns2_destroy()
+{
+ ip netns exec ns2 ip link set dev v4 netns 1
+ ip netns del ns2
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ rp1=${NETIFS[p5]}
+ rp2=${NETIFS[p6]}
+
+ vrf_prepare
+ forwarding_enable
+
+ h1_create
+ h2_create
+ switch_create
+
+ ip link add name v1 type veth peer name v2
+ ip link add name v3 type veth peer name v4
+ vrp2_create
+ ns1_create
+ ns2_create
+
+ r1_mac=$(in_ns ns1 mac_get w2)
+ r2_mac=$(in_ns ns2 mac_get w2)
+ h2_mac=$(mac_get $h2)
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ns2_destroy
+ ns1_destroy
+ vrp2_destroy
+ ip link del dev v3
+ ip link del dev v1
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ forwarding_restore
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.3 ": local->remote 1 through VxLAN with an 802.1ad bridge"
+ ping_test $h2 192.0.2.4 ": local->remote 2 through VxLAN with an 802.1d bridge"
+}
+
+test_all()
+{
+ echo "Running tests with UDP port $VXPORT"
+ tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
index 66496659bea7..e134a5f529c9 100644
--- a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
+++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
@@ -224,7 +224,7 @@ fib_ipv4_plen_test()
ip -n $ns link set dev dummy1 up
# Add two routes with the same key and different prefix length and
- # make sure both are in hardware. It can be verfied that both are
+ # make sure both are in hardware. It can be verified that both are
# sharing the same leaf by checking the /proc/net/fib_trie
ip -n $ns route add 192.0.2.0/24 dev dummy1
ip -n $ns route add 192.0.2.0/25 dev dummy1
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index be71012b8fc5..42e28c983d41 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -353,6 +353,11 @@ wait_for_offload()
"$@" | grep -q offload
}
+wait_for_trap()
+{
+ "$@" | grep -q trap
+}
+
until_counter_is()
{
local expr=$1; shift
@@ -767,6 +772,15 @@ rate()
echo $((8 * (t1 - t0) / interval))
}
+packets_rate()
+{
+ local t0=$1; shift
+ local t1=$1; shift
+ local interval=$1; shift
+
+ echo $(((t1 - t0) / interval))
+}
+
mac_get()
{
local if_name=$1
diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh
index 160f9cccdfb7..4f9f17cb45d6 100755
--- a/tools/testing/selftests/net/forwarding/tc_police.sh
+++ b/tools/testing/selftests/net/forwarding/tc_police.sh
@@ -35,6 +35,8 @@ ALL_TESTS="
police_shared_test
police_rx_mirror_test
police_tx_mirror_test
+ police_pps_rx_test
+ police_pps_tx_test
"
NUM_NETIFS=6
source tc_common.sh
@@ -290,6 +292,60 @@ police_tx_mirror_test()
police_mirror_common_test $rp2 egress "police tx and mirror"
}
+police_pps_common_test()
+{
+ local test_name=$1; shift
+
+ RET=0
+
+ # Rule to measure bandwidth on ingress of $h2
+ tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+ dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+ action drop
+
+ mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \
+ -t udp sp=12345,dp=54321 -p 1000 -c 0 -q &
+
+ local t0=$(tc_rule_stats_get $h2 1 ingress .packets)
+ sleep 10
+ local t1=$(tc_rule_stats_get $h2 1 ingress .packets)
+
+ local er=$((2000))
+ local nr=$(packets_rate $t0 $t1 10)
+ local nr_pct=$((100 * (nr - er) / er))
+ ((-10 <= nr_pct && nr_pct <= 10))
+ check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%."
+
+ log_test "$test_name"
+
+ { kill %% && wait %%; } 2>/dev/null
+ tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+}
+
+police_pps_rx_test()
+{
+ # Rule to police traffic destined to $h2 on ingress of $rp1
+ tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+ dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+ action police pkts_rate 2000 pkts_burst 400 conform-exceed drop/ok
+
+ police_pps_common_test "police pps on rx"
+
+ tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+}
+
+police_pps_tx_test()
+{
+ # Rule to police traffic destined to $h2 on egress of $rp2
+ tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \
+ dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+ action police pkts_rate 2000 pkts_burst 400 conform-exceed drop/ok
+
+ police_pps_common_test "police pps on tx"
+
+ tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+}
+
setup_prepare()
{
h1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index ce6bea9675c0..eb307ca37bfa 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -657,10 +657,21 @@ test_ecn_decap()
{
# In accordance with INET_ECN_decapsulate()
__test_ecn_decap 00 00 0x00
+ __test_ecn_decap 00 01 0x00
+ __test_ecn_decap 00 02 0x00
+ # 00 03 is tested in test_ecn_decap_error()
+ __test_ecn_decap 01 00 0x01
__test_ecn_decap 01 01 0x01
- __test_ecn_decap 02 01 0x02
+ __test_ecn_decap 01 02 0x01
__test_ecn_decap 01 03 0x03
+ __test_ecn_decap 02 00 0x02
+ __test_ecn_decap 02 01 0x01
+ __test_ecn_decap 02 02 0x02
__test_ecn_decap 02 03 0x03
+ __test_ecn_decap 03 00 0x03
+ __test_ecn_decap 03 01 0x03
+ __test_ecn_decap 03 02 0x03
+ __test_ecn_decap 03 03 0x03
test_ecn_decap_error
}
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 39edce4f541c..2674ba20d524 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -5,8 +5,9 @@ rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
ns="ns1-$rndh"
ksft_skip=4
test_cnt=1
+timeout_poll=100
+timeout_test=$((timeout_poll * 2 + 1))
ret=0
-pids=()
flush_pids()
{
@@ -14,18 +15,14 @@ flush_pids()
# give it some time
sleep 1.1
- for pid in ${pids[@]}; do
- [ -d /proc/$pid ] && kill -SIGUSR1 $pid >/dev/null 2>&1
- done
- pids=()
+ ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null
}
cleanup()
{
+ ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null
+
ip netns del $ns
- for pid in ${pids[@]}; do
- [ -d /proc/$pid ] && kill -9 $pid >/dev/null 2>&1
- done
}
ip -Version > /dev/null 2>&1
@@ -79,39 +76,57 @@ trap cleanup EXIT
ip netns add $ns
ip -n $ns link set dev lo up
-echo "a" | ip netns exec $ns ./mptcp_connect -p 10000 -l 0.0.0.0 -t 100 >/dev/null &
+echo "a" | \
+ timeout ${timeout_test} \
+ ip netns exec $ns \
+ ./mptcp_connect -p 10000 -l -t ${timeout_poll} \
+ 0.0.0.0 >/dev/null &
sleep 0.1
-pids[0]=$!
chk_msk_nr 0 "no msk on netns creation"
-echo "b" | ip netns exec $ns ./mptcp_connect -p 10000 127.0.0.1 -j -t 100 >/dev/null &
+echo "b" | \
+ timeout ${timeout_test} \
+ ip netns exec $ns \
+ ./mptcp_connect -p 10000 -j -t ${timeout_poll} \
+ 127.0.0.1 >/dev/null &
sleep 0.1
-pids[1]=$!
chk_msk_nr 2 "after MPC handshake "
chk_msk_remote_key_nr 2 "....chk remote_key"
chk_msk_fallback_nr 0 "....chk no fallback"
flush_pids
-echo "a" | ip netns exec $ns ./mptcp_connect -p 10001 -s TCP -l 0.0.0.0 -t 100 >/dev/null &
-pids[0]=$!
+echo "a" | \
+ timeout ${timeout_test} \
+ ip netns exec $ns \
+ ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
+ 0.0.0.0 >/dev/null &
sleep 0.1
-echo "b" | ip netns exec $ns ./mptcp_connect -p 10001 127.0.0.1 -j -t 100 >/dev/null &
-pids[1]=$!
+echo "b" | \
+ timeout ${timeout_test} \
+ ip netns exec $ns \
+ ./mptcp_connect -p 10001 -j -t ${timeout_poll} \
+ 127.0.0.1 >/dev/null &
sleep 0.1
chk_msk_fallback_nr 1 "check fallback"
flush_pids
NR_CLIENTS=100
for I in `seq 1 $NR_CLIENTS`; do
- echo "a" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) -l 0.0.0.0 -t 100 -w 10 >/dev/null &
- pids[$((I*2))]=$!
+ echo "a" | \
+ timeout ${timeout_test} \
+ ip netns exec $ns \
+ ./mptcp_connect -p $((I+10001)) -l -w 10 \
+ -t ${timeout_poll} 0.0.0.0 >/dev/null &
done
sleep 0.1
for I in `seq 1 $NR_CLIENTS`; do
- echo "b" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) 127.0.0.1 -t 100 -w 10 >/dev/null &
- pids[$((I*2 + 1))]=$!
+ echo "b" | \
+ timeout ${timeout_test} \
+ ip netns exec $ns \
+ ./mptcp_connect -p $((I+10001)) -w 10 \
+ -t ${timeout_poll} 127.0.0.1 >/dev/null &
done
sleep 1.5
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 77bb62feb872..69d89b5d666f 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -55,6 +55,7 @@ static int cfg_sndbuf;
static int cfg_rcvbuf;
static bool cfg_join;
static bool cfg_remove;
+static unsigned int cfg_do_w;
static int cfg_wait;
static void die_usage(void)
@@ -272,8 +273,8 @@ static size_t do_rnd_write(const int fd, char *buf, const size_t len)
if (cfg_join && first && do_w > 100)
do_w = 100;
- if (cfg_remove && do_w > 50)
- do_w = 50;
+ if (cfg_remove && do_w > cfg_do_w)
+ do_w = cfg_do_w;
bw = write(fd, buf, do_w);
if (bw < 0)
@@ -829,7 +830,7 @@ static void parse_opts(int argc, char **argv)
{
int c;
- while ((c = getopt(argc, argv, "6jrlp:s:hut:m:S:R:w:")) != -1) {
+ while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:")) != -1) {
switch (c) {
case 'j':
cfg_join = true;
@@ -840,6 +841,9 @@ static void parse_opts(int argc, char **argv)
cfg_remove = true;
cfg_mode = CFG_MODE_POLL;
cfg_wait = 400000;
+ cfg_do_w = atoi(optarg);
+ if (cfg_do_w <= 0)
+ cfg_do_w = 50;
break;
case 'l':
listen_mode = true;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 10a030b53b23..385cdc98aed8 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -11,7 +11,8 @@ cin=""
cout=""
ksft_skip=4
capture=false
-timeout=30
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
ipv6=true
ethtool_random_on=true
tc_delay="$((RANDOM%50))"
@@ -273,7 +274,7 @@ check_mptcp_disabled()
ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0
local err=0
- LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -t $timeout -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \
+ LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \
grep -q "^socket: Protocol not available$" && err=1
ip netns delete ${disabled_ns}
@@ -425,19 +426,32 @@ do_transfer()
sleep 1
fi
+ NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \
+ nstat -n
+ if [ ${listener_ns} != ${connector_ns} ]; then
+ NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \
+ nstat -n
+ fi
+
local stat_synrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent")
local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv")
- ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" &
+ timeout ${timeout_test} \
+ ip netns exec ${listener_ns} \
+ ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \
+ $extra_args $local_addr < "$sin" > "$sout" &
local spid=$!
wait_local_port_listen "${listener_ns}" "${port}"
local start
start=$(date +%s%3N)
- ip netns exec ${connector_ns} ./mptcp_connect -t $timeout -p $port -s ${cl_proto} $extra_args $connect_addr < "$cin" > "$cout" &
+ timeout ${timeout_test} \
+ ip netns exec ${connector_ns} \
+ ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \
+ $extra_args $connect_addr < "$cin" > "$cout" &
local cpid=$!
wait $cpid
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 191303b652a6..fd99485cf2a4 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -8,9 +8,11 @@ cin=""
cinsent=""
cout=""
ksft_skip=4
-timeout=30
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
mptcp_connect=""
capture=0
+do_all_tests=1
TEST_COUNT=0
@@ -76,6 +78,7 @@ cleanup_partial()
for netns in "$ns1" "$ns2"; do
ip netns del $netns
+ rm -f /tmp/$netns.{nstat,out}
done
}
@@ -121,12 +124,6 @@ reset_with_add_addr_timeout()
-j DROP
}
-for arg in "$@"; do
- if [ "$arg" = "-c" ]; then
- capture=1
- fi
-done
-
ip -Version > /dev/null 2>&1
if [ $? -ne 0 ];then
echo "SKIP: Could not run test without ip tool"
@@ -237,10 +234,17 @@ do_transfer()
sleep 1
fi
+ NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \
+ nstat -n
+ NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \
+ nstat -n
+
if [ $speed = "fast" ]; then
mptcp_connect="./mptcp_connect -j"
- else
- mptcp_connect="./mptcp_connect -r"
+ elif [ $speed = "slow" ]; then
+ mptcp_connect="./mptcp_connect -r 50"
+ elif [ $speed = "least" ]; then
+ mptcp_connect="./mptcp_connect -r 10"
fi
local local_addr
@@ -250,17 +254,26 @@ do_transfer()
local_addr="0.0.0.0"
fi
- ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port \
- -s ${srv_proto} ${local_addr} < "$sin" > "$sout" &
+ timeout ${timeout_test} \
+ ip netns exec ${listener_ns} \
+ $mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \
+ ${local_addr} < "$sin" > "$sout" &
spid=$!
sleep 1
if [ "$test_link_fail" -eq 0 ];then
- ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+ timeout ${timeout_test} \
+ ip netns exec ${connector_ns} \
+ $mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \
+ $connect_addr < "$cin" > "$cout" &
else
- ( cat "$cin" ; sleep 2; link_failure $listener_ns ; cat "$cin" ) | tee "$cinsent" | \
- ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr > "$cout" &
+ ( cat "$cin" ; sleep 2; link_failure $listener_ns ; cat "$cin" ) | \
+ tee "$cinsent" | \
+ timeout ${timeout_test} \
+ ip netns exec ${connector_ns} \
+ $mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \
+ $connect_addr > "$cout" &
fi
cpid=$!
@@ -297,9 +310,12 @@ do_transfer()
let id+=1
done
fi
- else
+ elif [ $rm_nr_ns1 -eq 8 ]; then
sleep 1
ip netns exec ${listener_ns} ./pm_nl_ctl flush
+ elif [ $rm_nr_ns1 -eq 9 ]; then
+ sleep 1
+ ip netns exec ${listener_ns} ./pm_nl_ctl del 0 ${connect_addr}
fi
fi
@@ -336,9 +352,18 @@ do_transfer()
let id+=1
done
fi
- else
+ elif [ $rm_nr_ns2 -eq 8 ]; then
sleep 1
ip netns exec ${connector_ns} ./pm_nl_ctl flush
+ elif [ $rm_nr_ns2 -eq 9 ]; then
+ local addr
+ if is_v6 "${connect_addr}"; then
+ addr="dead:beef:1::2"
+ else
+ addr="10.0.1.2"
+ fi
+ sleep 1
+ ip netns exec ${connector_ns} ./pm_nl_ctl del 0 $addr
fi
fi
@@ -364,12 +389,19 @@ do_transfer()
kill $cappid
fi
+ NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \
+ nstat | grep Tcp > /tmp/${listener_ns}.out
+ NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \
+ nstat | grep Tcp > /tmp/${connector_ns}.out
+
if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
echo " client exit code $retc, server $rets" 1>&2
echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2
- ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port"
+ ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port"
+ cat /tmp/${listener_ns}.out
echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2
- ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
+ ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port"
+ cat /tmp/${connector_ns}.out
cat "$capout"
ret=1
@@ -745,6 +777,14 @@ subflows_tests()
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr "multiple subflows, limited by server" 2 2 1
+
+ # single subflow, dev
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow dev ns2eth3
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr "single subflow, dev" 1 1 1
}
signal_address_tests()
@@ -788,6 +828,28 @@ signal_address_tests()
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr "multiple subflows and signal" 3 3 3
chk_add_nr 1 1
+
+ # signal addresses
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal
+ ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr "signal addresses" 3 3 3
+ chk_add_nr 3 3
+
+ # signal invalid addresses
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal
+ ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr "signal invalid addresses" 1 1 1
+ chk_add_nr 3 3
}
link_failure_tests()
@@ -823,6 +885,26 @@ add_addr_timeout_tests()
run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1
chk_add_nr 4 0
+
+ # signal addresses timeout
+ reset_with_add_addr_timeout
+ ip netns exec $ns1 ./pm_nl_ctl limits 2 2
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+ ip netns exec $ns2 ./pm_nl_ctl limits 2 2
+ run_tests $ns1 $ns2 10.0.1.1 0 0 0 least
+ chk_join_nr "signal addresses, ADD_ADDR timeout" 2 2 2
+ chk_add_nr 8 0
+
+ # signal invalid addresses timeout
+ reset_with_add_addr_timeout
+ ip netns exec $ns1 ./pm_nl_ctl limits 2 2
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+ ip netns exec $ns2 ./pm_nl_ctl limits 2 2
+ run_tests $ns1 $ns2 10.0.1.1 0 0 0 least
+ chk_join_nr "invalid address, ADD_ADDR timeout" 1 1 1
+ chk_add_nr 8 0
}
remove_tests()
@@ -879,6 +961,30 @@ remove_tests()
chk_add_nr 1 1
chk_rm_nr 2 2
+ # addresses remove
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal
+ ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+ run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow
+ chk_join_nr "remove addresses" 3 3 3
+ chk_add_nr 3 3
+ chk_rm_nr 3 3 invert
+
+ # invalid addresses remove
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal
+ ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+ run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow
+ chk_join_nr "remove invalid addresses" 1 1 1
+ chk_add_nr 3 3
+ chk_rm_nr 3 1 invert
+
# subflows and signal, flush
reset
ip netns exec $ns1 ./pm_nl_ctl limits 0 3
@@ -913,6 +1019,37 @@ remove_tests()
chk_join_nr "flush addresses" 3 3 3
chk_add_nr 3 3
chk_rm_nr 3 3 invert
+
+ # invalid addresses flush
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal
+ ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+ run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow
+ chk_join_nr "flush invalid addresses" 1 1 1
+ chk_add_nr 3 3
+ chk_rm_nr 3 1 invert
+
+ # remove id 0 subflow
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow
+ chk_join_nr "remove id 0 subflow" 1 1 1
+ chk_rm_nr 1 1
+
+ # remove id 0 address
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow
+ chk_join_nr "remove id 0 address" 1 1 1
+ chk_add_nr 1 1
+ chk_rm_nr 1 1 invert
}
add_tests()
@@ -1265,7 +1402,8 @@ usage()
echo " -4 v4mapped_tests"
echo " -b backup_tests"
echo " -p add_addr_ports_tests"
- echo " -c syncookies_tests"
+ echo " -k syncookies_tests"
+ echo " -c capture pcap files"
echo " -h help"
}
@@ -1279,12 +1417,24 @@ make_file "$cin" "client" 1
make_file "$sin" "server" 1
trap cleanup EXIT
-if [ -z $1 ]; then
+for arg in "$@"; do
+ # check for "capture" arg before launching tests
+ if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then
+ capture=1
+ fi
+
+ # exception for the capture option, the rest means: a part of the tests
+ if [ "${arg}" != "-c" ]; then
+ do_all_tests=0
+ fi
+done
+
+if [ $do_all_tests -eq 1 ]; then
all_tests
exit $ret
fi
-while getopts 'fsltra64bpch' opt; do
+while getopts 'fsltra64bpkch' opt; do
case $opt in
f)
subflows_tests
@@ -1316,9 +1466,11 @@ while getopts 'fsltra64bpch' opt; do
p)
add_addr_ports_tests
;;
- c)
+ k)
syncookies_tests
;;
+ c)
+ ;;
h | *)
usage
;;
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index a617e293734c..3c741abe034e 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -100,12 +100,12 @@ done
check "ip netns exec $ns1 ./pm_nl_ctl get 9" "id 9 flags signal 10.0.1.9" "hard addr limit"
check "ip netns exec $ns1 ./pm_nl_ctl get 10" "" "above hard addr limit"
-for i in `seq 9 256`; do
+ip netns exec $ns1 ./pm_nl_ctl del 9
+for i in `seq 10 255`; do
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9 id $i
ip netns exec $ns1 ./pm_nl_ctl del $i
- ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9 id $((i+1))
done
check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags 10.0.1.1
-id 2 flags 10.0.0.9
id 3 flags signal,backup 10.0.1.3
id 4 flags signal 10.0.1.4
id 5 flags signal 10.0.1.5
diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
index 7b4167f3f9a2..115decfdc1ef 100644
--- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -26,7 +26,7 @@ static void syntax(char *argv[])
{
fprintf(stderr, "%s add|get|set|del|flush|dump|accept [<args>]\n", argv[0]);
fprintf(stderr, "\tadd [flags signal|subflow|backup] [id <nr>] [dev <name>] <ip>\n");
- fprintf(stderr, "\tdel <id>\n");
+ fprintf(stderr, "\tdel <id> [<ip>]\n");
fprintf(stderr, "\tget <id>\n");
fprintf(stderr, "\tset <ip> [flags backup|nobackup]\n");
fprintf(stderr, "\tflush\n");
@@ -301,6 +301,7 @@ int del_addr(int fd, int pm_family, int argc, char *argv[])
1024];
struct rtattr *rta, *nest;
struct nlmsghdr *nh;
+ u_int16_t family;
int nest_start;
u_int8_t id;
int off = 0;
@@ -310,11 +311,14 @@ int del_addr(int fd, int pm_family, int argc, char *argv[])
off = init_genl_req(data, pm_family, MPTCP_PM_CMD_DEL_ADDR,
MPTCP_PM_VER);
- /* the only argument is the address id */
- if (argc != 3)
+ /* the only argument is the address id (nonzero) */
+ if (argc != 3 && argc != 4)
syntax(argv);
id = atoi(argv[2]);
+ /* zero id with the IP address */
+ if (!id && argc != 4)
+ syntax(argv);
nest_start = off;
nest = (void *)(data + off);
@@ -328,6 +332,30 @@ int del_addr(int fd, int pm_family, int argc, char *argv[])
rta->rta_len = RTA_LENGTH(1);
memcpy(RTA_DATA(rta), &id, 1);
off += NLMSG_ALIGN(rta->rta_len);
+
+ if (!id) {
+ /* addr data */
+ rta = (void *)(data + off);
+ if (inet_pton(AF_INET, argv[3], RTA_DATA(rta))) {
+ family = AF_INET;
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4;
+ rta->rta_len = RTA_LENGTH(4);
+ } else if (inet_pton(AF_INET6, argv[3], RTA_DATA(rta))) {
+ family = AF_INET6;
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6;
+ rta->rta_len = RTA_LENGTH(16);
+ } else {
+ error(1, errno, "can't parse ip %s", argv[3]);
+ }
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* family */
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY;
+ rta->rta_len = RTA_LENGTH(2);
+ memcpy(RTA_DATA(rta), &family, 2);
+ off += NLMSG_ALIGN(rta->rta_len);
+ }
nest->rta_len = off - nest_start;
do_nl_req(fd, nh, off, 0);
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index f039ee57eb3c..3aeef3bcb101 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -7,7 +7,8 @@ ns2="ns2-$rndh"
ns3="ns3-$rndh"
capture=false
ksft_skip=4
-timeout=30
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
test_cnt=1
ret=0
bail=0
@@ -157,14 +158,20 @@ do_transfer()
sleep 1
fi
- ip netns exec ${ns3} ./mptcp_connect -jt $timeout -l -p $port 0.0.0.0 < "$sin" > "$sout" &
+ timeout ${timeout_test} \
+ ip netns exec ${ns3} \
+ ./mptcp_connect -jt ${timeout_poll} -l -p $port \
+ 0.0.0.0 < "$sin" > "$sout" &
local spid=$!
wait_local_port_listen "${ns3}" "${port}"
local start
start=$(date +%s%3N)
- ip netns exec ${ns1} ./mptcp_connect -jt $timeout -p $port 10.0.3.3 < "$cin" > "$cout" &
+ timeout ${timeout_test} \
+ ip netns exec ${ns1} \
+ ./mptcp_connect -jt ${timeout_poll} -p $port \
+ 10.0.3.3 < "$cin" > "$cout" &
local cpid=$!
wait $cpid
diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
index 7b01b7c2ec10..066efd30e294 100644
--- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
+++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
@@ -30,25 +30,25 @@ struct reuse_opts {
};
struct reuse_opts unreusable_opts[12] = {
- {0, 0, 0, 0},
- {0, 0, 0, 1},
- {0, 0, 1, 0},
- {0, 0, 1, 1},
- {0, 1, 0, 0},
- {0, 1, 0, 1},
- {0, 1, 1, 0},
- {0, 1, 1, 1},
- {1, 0, 0, 0},
- {1, 0, 0, 1},
- {1, 0, 1, 0},
- {1, 0, 1, 1},
+ {{0, 0}, {0, 0}},
+ {{0, 0}, {0, 1}},
+ {{0, 0}, {1, 0}},
+ {{0, 0}, {1, 1}},
+ {{0, 1}, {0, 0}},
+ {{0, 1}, {0, 1}},
+ {{0, 1}, {1, 0}},
+ {{0, 1}, {1, 1}},
+ {{1, 0}, {0, 0}},
+ {{1, 0}, {0, 1}},
+ {{1, 0}, {1, 0}},
+ {{1, 0}, {1, 1}},
};
struct reuse_opts reusable_opts[4] = {
- {1, 1, 0, 0},
- {1, 1, 0, 1},
- {1, 1, 1, 0},
- {1, 1, 1, 1},
+ {{1, 1}, {0, 0}},
+ {{1, 1}, {0, 1}},
+ {{1, 1}, {1, 0}},
+ {{1, 1}, {1, 1}},
};
int bind_port(struct __test_metadata *_metadata, int reuseaddr, int reuseport)
diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c
index b4cca382d125..59067f64b775 100644
--- a/tools/testing/selftests/net/so_txtime.c
+++ b/tools/testing/selftests/net/so_txtime.c
@@ -2,9 +2,12 @@
/*
* Test the SO_TXTIME API
*
- * Takes two streams of { payload, delivery time }[], one input and one output.
- * Sends the input stream and verifies arrival matches the output stream.
- * The two streams can differ due to out-of-order delivery and drops.
+ * Takes a stream of { payload, delivery time }[], to be sent across two
+ * processes. Start this program on two separate network namespaces or
+ * connected hosts, one instance in transmit mode and the other in receive
+ * mode using the '-r' option. Receiver will compare arrival timestamps to
+ * the expected stream. Sender will read transmit timestamps from the error
+ * queue. The streams can differ due to out-of-order delivery and drops.
*/
#define _GNU_SOURCE
@@ -28,14 +31,17 @@
#include <sys/types.h>
#include <time.h>
#include <unistd.h>
+#include <poll.h>
static int cfg_clockid = CLOCK_TAI;
-static bool cfg_do_ipv4;
-static bool cfg_do_ipv6;
static uint16_t cfg_port = 8000;
static int cfg_variance_us = 4000;
+static uint64_t cfg_start_time_ns;
+static int cfg_mark;
+static bool cfg_rx;
static uint64_t glob_tstart;
+static uint64_t tdeliver_max;
/* encode one timed transmission (of a 1B payload) */
struct timed_send {
@@ -44,18 +50,21 @@ struct timed_send {
};
#define MAX_NUM_PKT 8
-static struct timed_send cfg_in[MAX_NUM_PKT];
-static struct timed_send cfg_out[MAX_NUM_PKT];
+static struct timed_send cfg_buf[MAX_NUM_PKT];
static int cfg_num_pkt;
static int cfg_errq_level;
static int cfg_errq_type;
-static uint64_t gettime_ns(void)
+static struct sockaddr_storage cfg_dst_addr;
+static struct sockaddr_storage cfg_src_addr;
+static socklen_t cfg_alen;
+
+static uint64_t gettime_ns(clockid_t clock)
{
struct timespec ts;
- if (clock_gettime(cfg_clockid, &ts))
+ if (clock_gettime(clock, &ts))
error(1, errno, "gettime");
return ts.tv_sec * (1000ULL * 1000 * 1000) + ts.tv_nsec;
@@ -75,6 +84,8 @@ static void do_send_one(int fdt, struct timed_send *ts)
msg.msg_iov = &iov;
msg.msg_iovlen = 1;
+ msg.msg_name = (struct sockaddr *)&cfg_dst_addr;
+ msg.msg_namelen = cfg_alen;
if (ts->delay_us >= 0) {
memset(control, 0, sizeof(control));
@@ -82,6 +93,8 @@ static void do_send_one(int fdt, struct timed_send *ts)
msg.msg_controllen = sizeof(control);
tdeliver = glob_tstart + ts->delay_us * 1000;
+ tdeliver_max = tdeliver_max > tdeliver ?
+ tdeliver_max : tdeliver;
cm = CMSG_FIRSTHDR(&msg);
cm->cmsg_level = SOL_SOCKET;
@@ -98,7 +111,7 @@ static void do_send_one(int fdt, struct timed_send *ts)
}
-static bool do_recv_one(int fdr, struct timed_send *ts)
+static void do_recv_one(int fdr, struct timed_send *ts)
{
int64_t tstop, texpect;
char rbuf[2];
@@ -106,13 +119,13 @@ static bool do_recv_one(int fdr, struct timed_send *ts)
ret = recv(fdr, rbuf, sizeof(rbuf), 0);
if (ret == -1 && errno == EAGAIN)
- return true;
+ error(1, EAGAIN, "recv: timeout");
if (ret == -1)
error(1, errno, "read");
if (ret != 1)
error(1, 0, "read: %dB", ret);
- tstop = (gettime_ns() - glob_tstart) / 1000;
+ tstop = (gettime_ns(cfg_clockid) - glob_tstart) / 1000;
texpect = ts->delay_us >= 0 ? ts->delay_us : 0;
fprintf(stderr, "payload:%c delay:%lld expected:%lld (us)\n",
@@ -123,8 +136,6 @@ static bool do_recv_one(int fdr, struct timed_send *ts)
if (llabs(tstop - texpect) > cfg_variance_us)
error(1, 0, "exceeds variance (%d us)", cfg_variance_us);
-
- return false;
}
static void do_recv_verify_empty(int fdr)
@@ -137,18 +148,18 @@ static void do_recv_verify_empty(int fdr)
error(1, 0, "recv: not empty as expected (%d, %d)", ret, errno);
}
-static void do_recv_errqueue_timeout(int fdt)
+static int do_recv_errqueue_timeout(int fdt)
{
char control[CMSG_SPACE(sizeof(struct sock_extended_err)) +
CMSG_SPACE(sizeof(struct sockaddr_in6))] = {0};
char data[sizeof(struct ethhdr) + sizeof(struct ipv6hdr) +
sizeof(struct udphdr) + 1];
struct sock_extended_err *err;
+ int ret, num_tstamp = 0;
struct msghdr msg = {0};
struct iovec iov = {0};
struct cmsghdr *cm;
int64_t tstamp = 0;
- int ret;
iov.iov_base = data;
iov.iov_len = sizeof(data);
@@ -206,9 +217,47 @@ static void do_recv_errqueue_timeout(int fdt)
msg.msg_flags = 0;
msg.msg_controllen = sizeof(control);
+ num_tstamp++;
}
- error(1, 0, "recv: timeout");
+ return num_tstamp;
+}
+
+static void recv_errqueue_msgs(int fdt)
+{
+ struct pollfd pfd = { .fd = fdt, .events = POLLERR };
+ const int timeout_ms = 10;
+ int ret, num_tstamp = 0;
+
+ do {
+ ret = poll(&pfd, 1, timeout_ms);
+ if (ret == -1)
+ error(1, errno, "poll");
+
+ if (ret && (pfd.revents & POLLERR))
+ num_tstamp += do_recv_errqueue_timeout(fdt);
+
+ if (num_tstamp == cfg_num_pkt)
+ break;
+
+ } while (gettime_ns(cfg_clockid) < tdeliver_max);
+}
+
+static void start_time_wait(void)
+{
+ uint64_t now;
+ int err;
+
+ if (!cfg_start_time_ns)
+ return;
+
+ now = gettime_ns(CLOCK_REALTIME);
+ if (cfg_start_time_ns < now)
+ return;
+
+ err = usleep((cfg_start_time_ns - now) / 1000);
+ if (err)
+ error(1, errno, "usleep");
}
static void setsockopt_txtime(int fd)
@@ -245,6 +294,10 @@ static int setup_tx(struct sockaddr *addr, socklen_t alen)
setsockopt_txtime(fd);
+ if (cfg_mark &&
+ setsockopt(fd, SOL_SOCKET, SO_MARK, &cfg_mark, sizeof(cfg_mark)))
+ error(1, errno, "setsockopt mark");
+
return fd;
}
@@ -266,31 +319,70 @@ static int setup_rx(struct sockaddr *addr, socklen_t alen)
return fd;
}
-static void do_test(struct sockaddr *addr, socklen_t alen)
+static void do_test_tx(struct sockaddr *addr, socklen_t alen)
{
- int fdt, fdr, i;
+ int fdt, i;
fprintf(stderr, "\nSO_TXTIME ipv%c clock %s\n",
addr->sa_family == PF_INET ? '4' : '6',
cfg_clockid == CLOCK_TAI ? "tai" : "monotonic");
fdt = setup_tx(addr, alen);
- fdr = setup_rx(addr, alen);
- glob_tstart = gettime_ns();
+ start_time_wait();
+ glob_tstart = gettime_ns(cfg_clockid);
for (i = 0; i < cfg_num_pkt; i++)
- do_send_one(fdt, &cfg_in[i]);
+ do_send_one(fdt, &cfg_buf[i]);
+
+ recv_errqueue_msgs(fdt);
+
+ if (close(fdt))
+ error(1, errno, "close t");
+}
+
+static void do_test_rx(struct sockaddr *addr, socklen_t alen)
+{
+ int fdr, i;
+
+ fdr = setup_rx(addr, alen);
+
+ start_time_wait();
+ glob_tstart = gettime_ns(cfg_clockid);
+
for (i = 0; i < cfg_num_pkt; i++)
- if (do_recv_one(fdr, &cfg_out[i]))
- do_recv_errqueue_timeout(fdt);
+ do_recv_one(fdr, &cfg_buf[i]);
do_recv_verify_empty(fdr);
if (close(fdr))
error(1, errno, "close r");
- if (close(fdt))
- error(1, errno, "close t");
+}
+
+static void setup_sockaddr(int domain, const char *str_addr,
+ struct sockaddr_storage *sockaddr)
+{
+ struct sockaddr_in6 *addr6 = (void *) sockaddr;
+ struct sockaddr_in *addr4 = (void *) sockaddr;
+
+ switch (domain) {
+ case PF_INET:
+ memset(addr4, 0, sizeof(*addr4));
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = htons(cfg_port);
+ if (str_addr &&
+ inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+ error(1, 0, "ipv4 parse error: %s", str_addr);
+ break;
+ case PF_INET6:
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ if (str_addr &&
+ inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+ error(1, 0, "ipv6 parse error: %s", str_addr);
+ break;
+ }
}
static int parse_io(const char *optarg, struct timed_send *array)
@@ -323,17 +415,46 @@ static int parse_io(const char *optarg, struct timed_send *array)
return aoff / 2;
}
+static void usage(const char *progname)
+{
+ fprintf(stderr, "\nUsage: %s [options] <payload>\n"
+ "Options:\n"
+ " -4 only IPv4\n"
+ " -6 only IPv6\n"
+ " -c <clock> monotonic (default) or tai\n"
+ " -D <addr> destination IP address (server)\n"
+ " -S <addr> source IP address (client)\n"
+ " -r run rx mode\n"
+ " -t <nsec> start time (UTC nanoseconds)\n"
+ " -m <mark> socket mark\n"
+ "\n",
+ progname);
+ exit(1);
+}
+
static void parse_opts(int argc, char **argv)
{
- int c, ilen, olen;
+ char *daddr = NULL, *saddr = NULL;
+ int domain = PF_UNSPEC;
+ int c;
- while ((c = getopt(argc, argv, "46c:")) != -1) {
+ while ((c = getopt(argc, argv, "46c:S:D:rt:m:")) != -1) {
switch (c) {
case '4':
- cfg_do_ipv4 = true;
+ if (domain != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ domain = PF_INET;
+ cfg_alen = sizeof(struct sockaddr_in);
+ cfg_errq_level = SOL_IP;
+ cfg_errq_type = IP_RECVERR;
break;
case '6':
- cfg_do_ipv6 = true;
+ if (domain != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ domain = PF_INET6;
+ cfg_alen = sizeof(struct sockaddr_in6);
+ cfg_errq_level = SOL_IPV6;
+ cfg_errq_type = IPV6_RECVERR;
break;
case 'c':
if (!strcmp(optarg, "tai"))
@@ -344,50 +465,50 @@ static void parse_opts(int argc, char **argv)
else
error(1, 0, "unknown clock id %s", optarg);
break;
+ case 'S':
+ saddr = optarg;
+ break;
+ case 'D':
+ daddr = optarg;
+ break;
+ case 'r':
+ cfg_rx = true;
+ break;
+ case 't':
+ cfg_start_time_ns = strtol(optarg, NULL, 0);
+ break;
+ case 'm':
+ cfg_mark = strtol(optarg, NULL, 0);
+ break;
default:
- error(1, 0, "parse error at %d", optind);
+ usage(argv[0]);
}
}
- if (argc - optind != 2)
- error(1, 0, "Usage: %s [-46] -c <clock> <in> <out>", argv[0]);
+ if (argc - optind != 1)
+ usage(argv[0]);
+
+ if (domain == PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ if (!daddr)
+ error(1, 0, "-D <server addr> required\n");
+ if (!cfg_rx && !saddr)
+ error(1, 0, "-S <client addr> required\n");
- ilen = parse_io(argv[optind], cfg_in);
- olen = parse_io(argv[optind + 1], cfg_out);
- if (ilen != olen)
- error(1, 0, "i/o streams len mismatch (%d, %d)\n", ilen, olen);
- cfg_num_pkt = ilen;
+ setup_sockaddr(domain, daddr, &cfg_dst_addr);
+ setup_sockaddr(domain, saddr, &cfg_src_addr);
+
+ cfg_num_pkt = parse_io(argv[optind], cfg_buf);
}
int main(int argc, char **argv)
{
parse_opts(argc, argv);
- if (cfg_do_ipv6) {
- struct sockaddr_in6 addr6 = {0};
-
- addr6.sin6_family = AF_INET6;
- addr6.sin6_port = htons(cfg_port);
- addr6.sin6_addr = in6addr_loopback;
-
- cfg_errq_level = SOL_IPV6;
- cfg_errq_type = IPV6_RECVERR;
-
- do_test((void *)&addr6, sizeof(addr6));
- }
-
- if (cfg_do_ipv4) {
- struct sockaddr_in addr4 = {0};
-
- addr4.sin_family = AF_INET;
- addr4.sin_port = htons(cfg_port);
- addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-
- cfg_errq_level = SOL_IP;
- cfg_errq_type = IP_RECVERR;
-
- do_test((void *)&addr4, sizeof(addr4));
- }
+ if (cfg_rx)
+ do_test_rx((void *)&cfg_dst_addr, cfg_alen);
+ else
+ do_test_tx((void *)&cfg_src_addr, cfg_alen);
return 0;
}
diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh
index 3f7800eaecb1..3f06f4d286a9 100755
--- a/tools/testing/selftests/net/so_txtime.sh
+++ b/tools/testing/selftests/net/so_txtime.sh
@@ -3,32 +3,85 @@
#
# Regression tests for the SO_TXTIME interface
-# Run in network namespace
-if [[ $# -eq 0 ]]; then
- if ! ./in_netns.sh $0 __subprocess; then
- # test is time sensitive, can be flaky
- echo "test failed: retry once"
- ./in_netns.sh $0 __subprocess
+set -e
+
+readonly DEV="veth0"
+readonly BIN="./so_txtime"
+
+readonly RAND="$(mktemp -u XXXXXX)"
+readonly NSPREFIX="ns-${RAND}"
+readonly NS1="${NSPREFIX}1"
+readonly NS2="${NSPREFIX}2"
+
+readonly SADDR4='192.168.1.1'
+readonly DADDR4='192.168.1.2'
+readonly SADDR6='fd::1'
+readonly DADDR6='fd::2'
+
+cleanup() {
+ ip netns del "${NS2}"
+ ip netns del "${NS1}"
+}
+
+trap cleanup EXIT
+
+# Create virtual ethernet pair between network namespaces
+ip netns add "${NS1}"
+ip netns add "${NS2}"
+
+ip link add "${DEV}" netns "${NS1}" type veth \
+ peer name "${DEV}" netns "${NS2}"
+
+# Bring the devices up
+ip -netns "${NS1}" link set "${DEV}" up
+ip -netns "${NS2}" link set "${DEV}" up
+
+# Set fixed MAC addresses on the devices
+ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02
+ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06
+
+# Add fixed IP addresses to the devices
+ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}"
+ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}"
+ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad
+ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad
+
+do_test() {
+ local readonly IP="$1"
+ local readonly CLOCK="$2"
+ local readonly TXARGS="$3"
+ local readonly RXARGS="$4"
+
+ if [[ "${IP}" == "4" ]]; then
+ local readonly SADDR="${SADDR4}"
+ local readonly DADDR="${DADDR4}"
+ elif [[ "${IP}" == "6" ]]; then
+ local readonly SADDR="${SADDR6}"
+ local readonly DADDR="${DADDR6}"
+ else
+ echo "Invalid IP version ${IP}"
+ exit 1
fi
- exit $?
-fi
+ local readonly START="$(date +%s%N --date="+ 0.1 seconds")"
+ ip netns exec "${NS2}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${RXARGS}" -r &
+ ip netns exec "${NS1}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${TXARGS}"
+ wait "$!"
+}
-set -e
+ip netns exec "${NS1}" tc qdisc add dev "${DEV}" root fq
+do_test 4 mono a,-1 a,-1
+do_test 6 mono a,0 a,0
+do_test 6 mono a,10 a,10
+do_test 4 mono a,10,b,20 a,10,b,20
+do_test 6 mono a,20,b,10 b,20,a,20
-tc qdisc add dev lo root fq
-./so_txtime -4 -6 -c mono a,-1 a,-1
-./so_txtime -4 -6 -c mono a,0 a,0
-./so_txtime -4 -6 -c mono a,10 a,10
-./so_txtime -4 -6 -c mono a,10,b,20 a,10,b,20
-./so_txtime -4 -6 -c mono a,20,b,10 b,20,a,20
-
-if tc qdisc replace dev lo root etf clockid CLOCK_TAI delta 400000; then
- ! ./so_txtime -4 -6 -c tai a,-1 a,-1
- ! ./so_txtime -4 -6 -c tai a,0 a,0
- ./so_txtime -4 -6 -c tai a,10 a,10
- ./so_txtime -4 -6 -c tai a,10,b,20 a,10,b,20
- ./so_txtime -4 -6 -c tai a,20,b,10 b,10,a,20
+if ip netns exec "${NS1}" tc qdisc replace dev "${DEV}" root etf clockid CLOCK_TAI delta 400000; then
+ ! do_test 4 tai a,-1 a,-1
+ ! do_test 6 tai a,0 a,0
+ do_test 6 tai a,10 a,10
+ do_test 4 tai a,10,b,20 a,10,b,20
+ do_test 6 tai a,20,b,10 b,10,a,20
else
echo "tc ($(tc -V)) does not support qdisc etf. skipping"
fi
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
new file mode 100755
index 000000000000..a8fa64136282
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -0,0 +1,251 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+readonly BASE="ns-$(mktemp -u XXXXXX)"
+readonly SRC=2
+readonly DST=1
+readonly DST_NAT=100
+readonly NS_SRC=$BASE$SRC
+readonly NS_DST=$BASE$DST
+
+# "baremetal" network used for raw UDP traffic
+readonly BM_NET_V4=192.168.1.
+readonly BM_NET_V6=2001:db8::
+
+# "overlay" network used for UDP over UDP tunnel traffic
+readonly OL_NET_V4=172.16.1.
+readonly OL_NET_V6=2001:db8:1::
+readonly NPROCS=`nproc`
+
+cleanup() {
+ local ns
+ local -r jobs="$(jobs -p)"
+ [ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+
+ for ns in $NS_SRC $NS_DST; do
+ ip netns del $ns 2>/dev/null
+ done
+}
+
+trap cleanup EXIT
+
+create_ns() {
+ local net
+ local ns
+
+ for ns in $NS_SRC $NS_DST; do
+ ip netns add $ns
+ ip -n $ns link set dev lo up
+ done
+
+ ip link add name veth$SRC type veth peer name veth$DST
+
+ for ns in $SRC $DST; do
+ ip link set dev veth$ns netns $BASE$ns
+ ip -n $BASE$ns link set dev veth$ns up
+ ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24
+ ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad
+ done
+ ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+}
+
+create_vxlan_endpoint() {
+ local -r netns=$1
+ local -r bm_dev=$2
+ local -r bm_rem_addr=$3
+ local -r vxlan_dev=$4
+ local -r vxlan_id=$5
+ local -r vxlan_port=4789
+
+ ip -n $netns link set dev $bm_dev up
+ ip -n $netns link add dev $vxlan_dev type vxlan id $vxlan_id \
+ dstport $vxlan_port remote $bm_rem_addr
+ ip -n $netns link set dev $vxlan_dev up
+}
+
+create_vxlan_pair() {
+ local ns
+
+ create_ns
+
+ for ns in $SRC $DST; do
+ # note that 3 - $SRC == $DST and 3 - $DST == $SRC
+ create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V4$((3 - $ns)) vxlan$ns 4
+ ip -n $BASE$ns addr add dev vxlan$ns $OL_NET_V4$ns/24
+ done
+ for ns in $SRC $DST; do
+ create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6
+ ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad
+ done
+}
+
+is_ipv6() {
+ if [[ $1 =~ .*:.* ]]; then
+ return 0
+ fi
+ return 1
+}
+
+run_test() {
+ local -r msg=$1
+ local -r dst=$2
+ local -r pkts=$3
+ local -r vxpkts=$4
+ local bind=$5
+ local rx_args=""
+ local rx_family="-4"
+ local family=-4
+ local filter=IpInReceives
+ local ipt=iptables
+
+ printf "%-40s" "$msg"
+
+ if is_ipv6 $dst; then
+ # rx program does not support '-6' and implies ipv6 usage by default
+ rx_family=""
+ family=-6
+ filter=Ip6InReceives
+ ipt=ip6tables
+ fi
+
+ rx_args="$rx_family"
+ [ -n "$bind" ] && rx_args="$rx_args -b $bind"
+
+ # send a single GSO packet, segmented in 10 UDP frames.
+ # Always expect 10 UDP frames on RX side as rx socket does
+ # not enable GRO
+ ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789
+ ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
+ ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
+ local spid=$!
+ sleep 0.1
+ ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
+ local retc=$?
+ wait $spid
+ local rets=$?
+ if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+ echo " fail client exit code $retc, server $rets"
+ ret=1
+ return
+ fi
+
+ local rcv=`ip netns exec $NS_DST $ipt"-save" -c | grep 'dport 8000' | \
+ sed -e 's/\[//' -e 's/:.*//'`
+ if [ $rcv != $pkts ]; then
+ echo " fail - received $rvs packets, expected $pkts"
+ ret=1
+ return
+ fi
+
+ local vxrcv=`ip netns exec $NS_DST $ipt"-save" -c | grep 'dport 4789' | \
+ sed -e 's/\[//' -e 's/:.*//'`
+
+ # upper net can generate a little noise, allow some tolerance
+ if [ $vxrcv -lt $vxpkts -o $vxrcv -gt $((vxpkts + 3)) ]; then
+ echo " fail - received $vxrcv vxlan packets, expected $vxpkts"
+ ret=1
+ return
+ fi
+ echo " ok"
+}
+
+run_bench() {
+ local -r msg=$1
+ local -r dst=$2
+ local family=-4
+
+ printf "%-40s" "$msg"
+ if [ $NPROCS -lt 2 ]; then
+ echo " skip - needed 2 CPUs found $NPROCS"
+ return
+ fi
+
+ is_ipv6 $dst && family=-6
+
+ # bind the sender and the receiver to different CPUs to try
+ # get reproducible results
+ ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
+ ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10 &
+ local spid=$!
+ sleep 0.1
+ ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
+ local retc=$?
+ wait $spid
+ local rets=$?
+ if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+ echo " fail client exit code $retc, server $rets"
+ ret=1
+ return
+ fi
+}
+
+for family in 4 6; do
+ BM_NET=$BM_NET_V4
+ OL_NET=$OL_NET_V4
+ IPT=iptables
+ SUFFIX=24
+ VXDEV=vxlan
+
+ if [ $family = 6 ]; then
+ BM_NET=$BM_NET_V6
+ OL_NET=$OL_NET_V6
+ SUFFIX="64 nodad"
+ VXDEV=vxlan6
+ IPT=ip6tables
+ fi
+
+ echo "IPv$family"
+
+ create_ns
+ run_test "No GRO" $BM_NET$DST 10 0
+ cleanup
+
+ create_ns
+ ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on
+ run_test "GRO frag list" $BM_NET$DST 1 0
+ cleanup
+
+ # UDP GRO fwd skips aggregation when find an udp socket with the GRO option
+ # if there is an UDP tunnel in the running system, such lookup happen
+ # take place.
+ # use NAT to circumvent GRO FWD check
+ create_ns
+ ip -n $NS_DST addr add dev veth$DST $BM_NET$DST_NAT/$SUFFIX
+ ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+ ip netns exec $NS_DST $IPT -t nat -I PREROUTING -d $BM_NET$DST_NAT \
+ -j DNAT --to-destination $BM_NET$DST
+ run_test "GRO fwd" $BM_NET$DST_NAT 1 0 $BM_NET$DST
+ cleanup
+
+ create_ns
+ run_bench "UDP fwd perf" $BM_NET$DST
+ ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+ run_bench "UDP GRO fwd perf" $BM_NET$DST
+ cleanup
+
+ create_vxlan_pair
+ ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on
+ run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1
+ cleanup
+
+ # use NAT to circumvent GRO FWD check
+ create_vxlan_pair
+ ip -n $NS_DST addr add dev $VXDEV$DST $OL_NET$DST_NAT/$SUFFIX
+ ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+ ip netns exec $NS_DST $IPT -t nat -I PREROUTING -d $OL_NET$DST_NAT \
+ -j DNAT --to-destination $OL_NET$DST
+
+ # load arp cache before running the test to reduce the amount of
+ # stray traffic on top of the UDP tunnel
+ ip netns exec $NS_SRC ping -q -c 1 $OL_NET$DST_NAT >/dev/null
+ run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST
+ cleanup
+
+ create_vxlan_pair
+ run_bench "UDP tunnel fwd perf" $OL_NET$DST
+ ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+ run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST
+ cleanup
+done
+
+exit $ret
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
new file mode 100755
index 000000000000..2fedc0781ce8
--- /dev/null
+++ b/tools/testing/selftests/net/veth.sh
@@ -0,0 +1,177 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
+readonly BASE=`basename $STATS`
+readonly SRC=2
+readonly DST=1
+readonly DST_NAT=100
+readonly NS_SRC=$BASE$SRC
+readonly NS_DST=$BASE$DST
+
+# "baremetal" network used for raw UDP traffic
+readonly BM_NET_V4=192.168.1.
+readonly BM_NET_V6=2001:db8::
+
+readonly NPROCS=`nproc`
+ret=0
+
+cleanup() {
+ local ns
+ local -r jobs="$(jobs -p)"
+ [ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+ rm -f $STATS
+
+ for ns in $NS_SRC $NS_DST; do
+ ip netns del $ns 2>/dev/null
+ done
+}
+
+trap cleanup EXIT
+
+create_ns() {
+ local ns
+
+ for ns in $NS_SRC $NS_DST; do
+ ip netns add $ns
+ ip -n $ns link set dev lo up
+ done
+
+ ip link add name veth$SRC type veth peer name veth$DST
+
+ for ns in $SRC $DST; do
+ ip link set dev veth$ns netns $BASE$ns up
+ ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24
+ ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad
+ done
+ echo "#kernel" > $BASE
+ chmod go-rw $BASE
+}
+
+__chk_flag() {
+ local msg="$1"
+ local target=$2
+ local expected=$3
+ local flagname=$4
+
+ local flag=`ip netns exec $BASE$target ethtool -k veth$target |\
+ grep $flagname | awk '{print $2}'`
+
+ printf "%-60s" "$msg"
+ if [ "$flag" = "$expected" ]; then
+ echo " ok "
+ else
+ echo " fail - expected $expected found $flag"
+ ret=1
+ fi
+}
+
+chk_gro_flag() {
+ __chk_flag "$1" $2 $3 generic-receive-offload
+}
+
+chk_tso_flag() {
+ __chk_flag "$1" $2 $3 tcp-segmentation-offload
+}
+
+chk_gro() {
+ local msg="$1"
+ local expected=$2
+
+ ip netns exec $BASE$SRC ping -qc 1 $BM_NET_V4$DST >/dev/null
+ NSTAT_HISTORY=$STATS ip netns exec $NS_DST nstat -n
+
+ printf "%-60s" "$msg"
+ ip netns exec $BASE$DST ./udpgso_bench_rx -C 1000 -R 10 &
+ local spid=$!
+ sleep 0.1
+
+ ip netns exec $NS_SRC ./udpgso_bench_tx -4 -s 13000 -S 1300 -M 1 -D $BM_NET_V4$DST
+ local retc=$?
+ wait $spid
+ local rets=$?
+ if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+ echo " fail client exit code $retc, server $rets"
+ ret=1
+ return
+ fi
+
+ local pkts=`NSTAT_HISTORY=$STATS ip netns exec $NS_DST nstat IpInReceives | \
+ awk '{print $2}' | tail -n 1`
+ if [ "$pkts" = "$expected" ]; then
+ echo " ok "
+ else
+ echo " fail - got $pkts packets, expected $expected "
+ ret=1
+ fi
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+ echo "Missing xdp_dummy helper. Build bpf selftest first"
+ exit -1
+fi
+
+create_ns
+chk_gro_flag "default - gro flag" $SRC off
+chk_gro_flag " - peer gro flag" $DST off
+chk_tso_flag " - tso flag" $SRC on
+chk_tso_flag " - peer tso flag" $DST on
+chk_gro " - aggregation" 1
+ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
+chk_gro " - aggregation with TSO off" 10
+cleanup
+
+create_ns
+ip netns exec $NS_DST ethtool -K veth$DST gro on
+chk_gro_flag "with gro on - gro flag" $DST on
+chk_gro_flag " - peer gro flag" $SRC off
+chk_tso_flag " - tso flag" $SRC on
+chk_tso_flag " - peer tso flag" $DST on
+ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
+ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+chk_gro " - aggregation with TSO off" 1
+cleanup
+
+create_ns
+ip -n $NS_DST link set dev veth$DST down
+ip netns exec $NS_DST ethtool -K veth$DST gro on
+chk_gro_flag "with gro enabled on link down - gro flag" $DST on
+chk_gro_flag " - peer gro flag" $SRC off
+chk_tso_flag " - tso flag" $SRC on
+chk_tso_flag " - peer tso flag" $DST on
+ip -n $NS_DST link set dev veth$DST up
+ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
+ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+chk_gro " - aggregation with TSO off" 1
+cleanup
+
+create_ns
+ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+chk_gro_flag "with xdp attached - gro flag" $DST on
+chk_gro_flag " - peer gro flag" $SRC off
+chk_tso_flag " - tso flag" $SRC off
+chk_tso_flag " - peer tso flag" $DST on
+ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+chk_gro " - aggregation" 1
+
+
+ip -n $NS_DST link set dev veth$DST down
+ip -n $NS_SRC link set dev veth$SRC down
+chk_gro_flag " - after dev off, flag" $DST on
+chk_gro_flag " - peer flag" $SRC off
+
+ip netns exec $NS_DST ethtool -K veth$DST gro on
+ip -n $NS_DST link set dev veth$DST xdp off
+chk_gro_flag " - after gro on xdp off, gro flag" $DST on
+chk_gro_flag " - peer gro flag" $SRC off
+chk_tso_flag " - tso flag" $SRC on
+chk_tso_flag " - peer tso flag" $DST on
+ip -n $NS_DST link set dev veth$DST up
+ip -n $NS_SRC link set dev veth$SRC up
+chk_gro " - aggregation" 1
+
+ip netns exec $NS_DST ethtool -K veth$DST gro off
+ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
+chk_gro "aggregation again with default and TSO off" 10
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index 431296c0f91c..427d94816f2d 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -371,6 +371,88 @@ else
ip netns exec nsr1 nft list ruleset
fi
+# Another test:
+# Add bridge interface br0 to Router1, with NAT enabled.
+ip -net nsr1 link add name br0 type bridge
+ip -net nsr1 addr flush dev veth0
+ip -net nsr1 link set up dev veth0
+ip -net nsr1 link set veth0 master br0
+ip -net nsr1 addr add 10.0.1.1/24 dev br0
+ip -net nsr1 addr add dead:1::1/64 dev br0
+ip -net nsr1 link set up dev br0
+
+ip netns exec nsr1 sysctl net.ipv4.conf.br0.forwarding=1 > /dev/null
+
+# br0 with NAT enabled.
+ip netns exec nsr1 nft -f - <<EOF
+flush table ip nat
+table ip nat {
+ chain prerouting {
+ type nat hook prerouting priority 0; policy accept;
+ meta iif "br0" ip daddr 10.6.6.6 tcp dport 1666 counter dnat ip to 10.0.2.99:12345
+ }
+
+ chain postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ meta oifname "veth1" counter masquerade
+ }
+}
+EOF
+
+if test_tcp_forwarding_nat ns1 ns2; then
+ echo "PASS: flow offloaded for ns1/ns2 with bridge NAT"
+else
+ echo "FAIL: flow offload for ns1/ns2 with bridge NAT" 1>&2
+ ip netns exec nsr1 nft list ruleset
+ ret=1
+fi
+
+# Another test:
+# Add bridge interface br0 to Router1, with NAT and VLAN.
+ip -net nsr1 link set veth0 nomaster
+ip -net nsr1 link set down dev veth0
+ip -net nsr1 link add link veth0 name veth0.10 type vlan id 10
+ip -net nsr1 link set up dev veth0
+ip -net nsr1 link set up dev veth0.10
+ip -net nsr1 link set veth0.10 master br0
+
+ip -net ns1 addr flush dev eth0
+ip -net ns1 link add link eth0 name eth0.10 type vlan id 10
+ip -net ns1 link set eth0 up
+ip -net ns1 link set eth0.10 up
+ip -net ns1 addr add 10.0.1.99/24 dev eth0.10
+ip -net ns1 route add default via 10.0.1.1
+ip -net ns1 addr add dead:1::99/64 dev eth0.10
+
+if test_tcp_forwarding_nat ns1 ns2; then
+ echo "PASS: flow offloaded for ns1/ns2 with bridge NAT and VLAN"
+else
+ echo "FAIL: flow offload for ns1/ns2 with bridge NAT and VLAN" 1>&2
+ ip netns exec nsr1 nft list ruleset
+ ret=1
+fi
+
+# restore test topology (remove bridge and VLAN)
+ip -net nsr1 link set veth0 nomaster
+ip -net nsr1 link set veth0 down
+ip -net nsr1 link set veth0.10 down
+ip -net nsr1 link delete veth0.10 type vlan
+ip -net nsr1 link delete br0 type bridge
+ip -net ns1 addr flush dev eth0.10
+ip -net ns1 link set eth0.10 down
+ip -net ns1 link set eth0 down
+ip -net ns1 link delete eth0.10 type vlan
+
+# restore address in ns1 and nsr1
+ip -net ns1 link set eth0 up
+ip -net ns1 addr add 10.0.1.99/24 dev eth0
+ip -net ns1 route add default via 10.0.1.1
+ip -net ns1 addr add dead:1::99/64 dev eth0
+ip -net ns1 route add default via dead:1::1
+ip -net nsr1 addr add 10.0.1.1/24 dev veth0
+ip -net nsr1 addr add dead:1::1/64 dev veth0
+ip -net nsr1 link set up dev veth0
+
KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
SPI1=$RANDOM
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index b8268da5adaa..8e45792703ed 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -764,5 +764,53 @@
"teardown": [
"$TC actions flush action police"
]
+ },
+ {
+ "id": "cdd7",
+ "name": "Add valid police action with packets per second rate limit",
+ "category": [
+ "actions",
+ "police"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action police",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action police pkts_rate 1000 pkts_burst 200 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions ls action police",
+ "matchPattern": "action order [0-9]*: police 0x1 rate 0bit burst 0b mtu 4096Mb pkts_rate 1000 pkts_burst 200",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action police"
+ ]
+ },
+ {
+ "id": "f5bc",
+ "name": "Add invalid police action with both bps and pps",
+ "category": [
+ "actions",
+ "police"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action police",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action police rate 1kbit burst 10k pkts_rate 1000 pkts_burst 200 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions ls action police",
+ "matchPattern": "action order [0-9]*: police 0x1 ",
+ "matchCount": "0",
+ "teardown": [
+ "$TC actions flush action police"
+ ]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
index 8e8c1ae12260..e0c5f060ccb9 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -24,6 +24,30 @@
]
},
{
+ "id": "4297",
+ "name": "Add simple action with change command",
+ "category": [
+ "actions",
+ "simple"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action simple",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions change action simple sdata \"Not changed\" index 60",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action simple",
+ "matchPattern": "action order [0-9]*: Simple <Not changed>.*index 60 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action simple"
+ ]
+ },
+ {
"id": "6d4c",
"name": "Add simple action with duplicate index",
"category": [
@@ -151,5 +175,64 @@
"teardown": [
"$TC actions flush action simple"
]
+ },
+ {
+ "id": "8d07",
+ "name": "Verify cleanup of failed actions batch add",
+ "category": [
+ "actions",
+ "simple"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action simple",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action simple sdata \"2\" index 2",
+ [
+ "$TC actions add action simple sdata \"1\" index 1 action simple sdata \"2\" index 2",
+ 255
+ ],
+ "$TC actions flush action simple"
+ ],
+ "cmdUnderTest": "$TC actions add action simple sdata \"2\" index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action simple",
+ "matchPattern": "action order [0-9]*: Simple <2>.*index 2 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action simple"
+ ]
+ },
+ {
+ "id": "a68a",
+ "name": "Verify cleanup of failed actions batch change",
+ "category": [
+ "actions",
+ "simple"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action simple",
+ 0,
+ 1,
+ 255
+ ],
+ [
+ "$TC actions change action simple sdata \"1\" index 1 action simple sdata \"2\" goto chain 42 index 2",
+ 255
+ ],
+ "$TC actions flush action simple"
+ ],
+ "cmdUnderTest": "$TC actions add action simple sdata \"1\" index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action simple",
+ "matchPattern": "action order [0-9]*: Simple <1>.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action simple"
+ ]
}
]
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d42115e4284d..8b0cd421ebd3 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -101,7 +101,7 @@ endef
ifeq ($(CAN_BUILD_I386),1)
$(BINARIES_32): CFLAGS += -m32
$(BINARIES_32): LDLIBS += -lrt -ldl -lm
-$(BINARIES_32): %_32: %.c
+$(BINARIES_32): $(OUTPUT)/%_32: %.c
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t))))
endif
@@ -109,7 +109,7 @@ endif
ifeq ($(CAN_BUILD_X86_64),1)
$(BINARIES_64): CFLAGS += -m64
$(BINARIES_64): LDLIBS += -lrt -ldl
-$(BINARIES_64): %_64: %.c
+$(BINARIES_64): $(OUTPUT)/%_64: %.c
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t))))
endif