aboutsummaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rw-r--r--tools/testing/selftests/bpf/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/Makefile28
-rw-r--r--tools/testing/selftests/bpf/bench.c2
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c96
-rwxr-xr-xtools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh11
-rw-r--r--tools/testing/selftests/bpf/btf_helpers.c25
-rw-r--r--tools/testing/selftests/bpf/prog_tests/attach_probe.c49
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_cookie.c78
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf.c153
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_write.c126
-rw-r--r--tools/testing/selftests/bpf/prog_tests/core_reloc.c65
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_stress.c32
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c3
-rw-r--r--tools/testing/selftests/bpf/prog_tests/libbpf_str.c207
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tailcalls.c55
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tc_redirect.c8
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c183
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_hashmap_full_update_bench.c40
-rw-r--r--tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val.c3
-rw-r--r--tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___diff.c3
-rw-r--r--tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___err_missing.c3
-rw-r--r--tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___val3_missing.c3
-rw-r--r--tools/testing/selftests/bpf/progs/core_reloc_types.h78
-rw-r--r--tools/testing/selftests/bpf/progs/kprobe_multi.c24
-rw-r--r--tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c42
-rw-r--r--tools/testing/selftests/bpf/progs/test_attach_probe.c60
-rw-r--r--tools/testing/selftests/bpf/progs/test_core_reloc_enum64val.c70
-rw-r--r--tools/testing/selftests/bpf/progs/test_tc_dtime.c53
-rw-r--r--tools/testing/selftests/bpf/progs/test_varlen.c8
-rw-r--r--tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c833
-rwxr-xr-xtools/testing/selftests/bpf/test_bpftool_synctypes.py166
-rw-r--r--tools/testing/selftests/bpf/test_btf.h1
-rwxr-xr-xtools/testing/selftests/bpf/test_xdping.sh4
-rw-r--r--tools/testing/selftests/bpf/xdp_synproxy.c466
-rw-r--r--tools/testing/selftests/dma/Makefile1
-rw-r--r--tools/testing/selftests/dma/dma_map_benchmark.c2
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/rif_counter_scale.sh107
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh31
l---------tools/testing/selftests/drivers/net/mlxsw/spectrum-2/rif_counter_scale.sh1
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh15
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh29
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/spectrum/rif_counter_scale.sh34
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh17
-rw-r--r--tools/testing/selftests/kvm/Makefile49
-rw-r--r--tools/testing/selftests/kvm/dirty_log_perf_test.c10
-rw-r--r--tools/testing/selftests/kvm/include/perf_test_util.h9
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h25
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/vmx.h6
-rw-r--r--tools/testing/selftests/kvm/lib/perf_test_util.c53
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c112
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c31
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/vmx.c149
-rw-r--r--tools/testing/selftests/kvm/max_guest_memory_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/mmu_role_test.c2
-rw-r--r--tools/testing/selftests/lib.mk25
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/Makefile2
-rw-r--r--tools/testing/selftests/net/bind_bhash_test.c119
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh61
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh7
-rwxr-xr-xtools/testing/selftests/netfilter/nft_concat_range.sh2
-rw-r--r--tools/testing/selftests/tc-testing/.gitignore1
-rw-r--r--tools/testing/selftests/vm/gup_test.c4
-rw-r--r--tools/testing/selftests/vm/ksm_tests.c2
-rw-r--r--tools/testing/selftests/wireguard/qemu/Makefile28
-rw-r--r--tools/testing/selftests/wireguard/qemu/init.c3
-rw-r--r--tools/testing/selftests/wireguard/qemu/kernel.config3
67 files changed, 3400 insertions, 522 deletions
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 595565eb68c0..ca2f47f45670 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -43,3 +43,4 @@ test_cpp
*.tmp
xdpxceiver
xdp_redirect_multi
+xdp_synproxy
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 2d3c8c8f558a..cb8e552e1418 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -82,7 +82,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
- xdpxceiver xdp_redirect_multi
+ xdpxceiver xdp_redirect_multi xdp_synproxy
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
@@ -168,17 +168,26 @@ $(OUTPUT)/%:%.c
$(call msg,BINARY,,$@)
$(Q)$(LINK.c) $^ $(LDLIBS) -o $@
+# LLVM's ld.lld doesn't support all the architectures, so use it only on x86
+ifeq ($(SRCARCH),x86)
+LLD := lld
+else
+LLD := ld
+endif
+
# Filter out -static for liburandom_read.so and its dependent targets so that static builds
# do not fail. Static builds leave urandom_read relying on system-wide shared libraries.
$(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c
$(call msg,LIB,,$@)
- $(Q)$(CC) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $^ $(LDLIBS) -fPIC -shared -o $@
+ $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $^ $(LDLIBS) \
+ -fuse-ld=$(LLD) -Wl,-znoseparate-code -fPIC -shared -o $@
$(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so
$(call msg,BINARY,,$@)
- $(Q)$(CC) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \
- liburandom_read.so $(LDLIBS) \
- -Wl,-rpath=. -Wl,--build-id=sha1 -o $@
+ $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \
+ liburandom_read.so $(LDLIBS) \
+ -fuse-ld=$(LLD) -Wl,-znoseparate-code \
+ -Wl,-rpath=. -Wl,--build-id=sha1 -o $@
$(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
$(call msg,MOD,,$@)
@@ -502,6 +511,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \
cap_helpers.c
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \
$(OUTPUT)/liburandom_read.so \
+ $(OUTPUT)/xdp_synproxy \
ima_setup.sh \
$(wildcard progs/btf_dump_test_case_*.c)
TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
@@ -560,6 +570,7 @@ $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
$(OUTPUT)/bench_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h
$(OUTPUT)/bench_bpf_loop.o: $(OUTPUT)/bpf_loop_bench.skel.h
$(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h
+$(OUTPUT)/bench_bpf_hashmap_full_update.o: $(OUTPUT)/bpf_hashmap_full_update_bench.skel.h
$(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
$(OUTPUT)/bench: LDLIBS += -lm
$(OUTPUT)/bench: $(OUTPUT)/bench.o \
@@ -571,13 +582,16 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
$(OUTPUT)/bench_ringbufs.o \
$(OUTPUT)/bench_bloom_filter_map.o \
$(OUTPUT)/bench_bpf_loop.o \
- $(OUTPUT)/bench_strncmp.o
+ $(OUTPUT)/bench_strncmp.o \
+ $(OUTPUT)/bench_bpf_hashmap_full_update.o
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
feature bpftool \
- $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h no_alu32 bpf_gcc bpf_testmod.ko)
+ $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h \
+ no_alu32 bpf_gcc bpf_testmod.ko \
+ liburandom_read.so)
.PHONY: docs docs-clean
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index f061cc20e776..d8aa62be996b 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -396,6 +396,7 @@ extern const struct bench bench_hashmap_with_bloom;
extern const struct bench bench_bpf_loop;
extern const struct bench bench_strncmp_no_helper;
extern const struct bench bench_strncmp_helper;
+extern const struct bench bench_bpf_hashmap_full_update;
static const struct bench *benchs[] = {
&bench_count_global,
@@ -430,6 +431,7 @@ static const struct bench *benchs[] = {
&bench_bpf_loop,
&bench_strncmp_no_helper,
&bench_strncmp_helper,
+ &bench_bpf_hashmap_full_update,
};
static void setup_benchmark()
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c
new file mode 100644
index 000000000000..cec51e0ff4b8
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Bytedance */
+
+#include <argp.h>
+#include "bench.h"
+#include "bpf_hashmap_full_update_bench.skel.h"
+#include "bpf_util.h"
+
+/* BPF triggering benchmarks */
+static struct ctx {
+ struct bpf_hashmap_full_update_bench *skel;
+} ctx;
+
+#define MAX_LOOP_NUM 10000
+
+static void validate(void)
+{
+ if (env.consumer_cnt != 1) {
+ fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+ exit(1);
+ }
+}
+
+static void *producer(void *input)
+{
+ while (true) {
+ /* trigger the bpf program */
+ syscall(__NR_getpgid);
+ }
+
+ return NULL;
+}
+
+static void *consumer(void *input)
+{
+ return NULL;
+}
+
+static void measure(struct bench_res *res)
+{
+}
+
+static void setup(void)
+{
+ struct bpf_link *link;
+ int map_fd, i, max_entries;
+
+ setup_libbpf();
+
+ ctx.skel = bpf_hashmap_full_update_bench__open_and_load();
+ if (!ctx.skel) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+
+ ctx.skel->bss->nr_loops = MAX_LOOP_NUM;
+
+ link = bpf_program__attach(ctx.skel->progs.benchmark);
+ if (!link) {
+ fprintf(stderr, "failed to attach program!\n");
+ exit(1);
+ }
+
+ /* fill hash_map */
+ map_fd = bpf_map__fd(ctx.skel->maps.hash_map_bench);
+ max_entries = bpf_map__max_entries(ctx.skel->maps.hash_map_bench);
+ for (i = 0; i < max_entries; i++)
+ bpf_map_update_elem(map_fd, &i, &i, BPF_ANY);
+}
+
+void hashmap_report_final(struct bench_res res[], int res_cnt)
+{
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ int i;
+
+ for (i = 0; i < nr_cpus; i++) {
+ u64 time = ctx.skel->bss->percpu_time[i];
+
+ if (!time)
+ continue;
+
+ printf("%d:hash_map_full_perf %lld events per sec\n",
+ i, ctx.skel->bss->nr_loops * 1000000000ll / time);
+ }
+}
+
+const struct bench bench_bpf_hashmap_full_update = {
+ .name = "bpf-hashmap-ful-update",
+ .validate = validate,
+ .setup = setup,
+ .producer_thread = producer,
+ .consumer_thread = consumer,
+ .measure = measure,
+ .report_progress = NULL,
+ .report_final = hashmap_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh b/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh
new file mode 100755
index 000000000000..1e2de838f9fa
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh
@@ -0,0 +1,11 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+nr_threads=`expr $(cat /proc/cpuinfo | grep "processor"| wc -l) - 1`
+summary=$($RUN_BENCH -p $nr_threads bpf-hashmap-ful-update)
+printf "$summary"
+printf "\n"
diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c
index b5941d514e17..1c1c2c26690a 100644
--- a/tools/testing/selftests/bpf/btf_helpers.c
+++ b/tools/testing/selftests/bpf/btf_helpers.c
@@ -26,11 +26,12 @@ static const char * const btf_kind_str_mapping[] = {
[BTF_KIND_FLOAT] = "FLOAT",
[BTF_KIND_DECL_TAG] = "DECL_TAG",
[BTF_KIND_TYPE_TAG] = "TYPE_TAG",
+ [BTF_KIND_ENUM64] = "ENUM64",
};
static const char *btf_kind_str(__u16 kind)
{
- if (kind > BTF_KIND_TYPE_TAG)
+ if (kind > BTF_KIND_ENUM64)
return "UNKNOWN";
return btf_kind_str_mapping[kind];
}
@@ -139,14 +140,32 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id)
}
case BTF_KIND_ENUM: {
const struct btf_enum *v = btf_enum(t);
+ const char *fmt_str;
- fprintf(out, " size=%u vlen=%u", t->size, vlen);
+ fmt_str = btf_kflag(t) ? "\n\t'%s' val=%d" : "\n\t'%s' val=%u";
+ fprintf(out, " encoding=%s size=%u vlen=%u",
+ btf_kflag(t) ? "SIGNED" : "UNSIGNED", t->size, vlen);
for (i = 0; i < vlen; i++, v++) {
- fprintf(out, "\n\t'%s' val=%u",
+ fprintf(out, fmt_str,
btf_str(btf, v->name_off), v->val);
}
break;
}
+ case BTF_KIND_ENUM64: {
+ const struct btf_enum64 *v = btf_enum64(t);
+ const char *fmt_str;
+
+ fmt_str = btf_kflag(t) ? "\n\t'%s' val=%lld" : "\n\t'%s' val=%llu";
+
+ fprintf(out, " encoding=%s size=%u vlen=%u",
+ btf_kflag(t) ? "SIGNED" : "UNSIGNED", t->size, vlen);
+ for (i = 0; i < vlen; i++, v++) {
+ fprintf(out, fmt_str,
+ btf_str(btf, v->name_off),
+ ((__u64)v->val_hi32 << 32) | v->val_lo32);
+ }
+ break;
+ }
case BTF_KIND_FWD:
fprintf(out, " fwd_kind=%s", btf_kflag(t) ? "union" : "struct");
break;
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 08c0601b3e84..0b899d2d8ea7 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -17,6 +17,14 @@ static void trigger_func2(void)
asm volatile ("");
}
+/* attach point for byname sleepable uprobe */
+static void trigger_func3(void)
+{
+ asm volatile ("");
+}
+
+static char test_data[] = "test_data";
+
void test_attach_probe(void)
{
DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
@@ -49,9 +57,17 @@ void test_attach_probe(void)
if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset"))
return;
- skel = test_attach_probe__open_and_load();
+ skel = test_attach_probe__open();
if (!ASSERT_OK_PTR(skel, "skel_open"))
return;
+
+ /* sleepable kprobe test case needs flags set before loading */
+ if (!ASSERT_OK(bpf_program__set_flags(skel->progs.handle_kprobe_sleepable,
+ BPF_F_SLEEPABLE), "kprobe_sleepable_flags"))
+ goto cleanup;
+
+ if (!ASSERT_OK(test_attach_probe__load(skel), "skel_load"))
+ goto cleanup;
if (!ASSERT_OK_PTR(skel->bss, "check_bss"))
goto cleanup;
@@ -151,6 +167,30 @@ void test_attach_probe(void)
if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname2, "attach_uretprobe_byname2"))
goto cleanup;
+ /* sleepable kprobes should not attach successfully */
+ skel->links.handle_kprobe_sleepable = bpf_program__attach(skel->progs.handle_kprobe_sleepable);
+ if (!ASSERT_ERR_PTR(skel->links.handle_kprobe_sleepable, "attach_kprobe_sleepable"))
+ goto cleanup;
+
+ /* test sleepable uprobe and uretprobe variants */
+ skel->links.handle_uprobe_byname3_sleepable = bpf_program__attach(skel->progs.handle_uprobe_byname3_sleepable);
+ if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname3_sleepable, "attach_uprobe_byname3_sleepable"))
+ goto cleanup;
+
+ skel->links.handle_uprobe_byname3 = bpf_program__attach(skel->progs.handle_uprobe_byname3);
+ if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname3, "attach_uprobe_byname3"))
+ goto cleanup;
+
+ skel->links.handle_uretprobe_byname3_sleepable = bpf_program__attach(skel->progs.handle_uretprobe_byname3_sleepable);
+ if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname3_sleepable, "attach_uretprobe_byname3_sleepable"))
+ goto cleanup;
+
+ skel->links.handle_uretprobe_byname3 = bpf_program__attach(skel->progs.handle_uretprobe_byname3);
+ if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname3, "attach_uretprobe_byname3"))
+ goto cleanup;
+
+ skel->bss->user_ptr = test_data;
+
/* trigger & validate kprobe && kretprobe */
usleep(1);
@@ -164,6 +204,9 @@ void test_attach_probe(void)
/* trigger & validate uprobe attached by name */
trigger_func2();
+ /* trigger & validate sleepable uprobe attached by name */
+ trigger_func3();
+
ASSERT_EQ(skel->bss->kprobe_res, 1, "check_kprobe_res");
ASSERT_EQ(skel->bss->kprobe2_res, 11, "check_kprobe_auto_res");
ASSERT_EQ(skel->bss->kretprobe_res, 2, "check_kretprobe_res");
@@ -174,6 +217,10 @@ void test_attach_probe(void)
ASSERT_EQ(skel->bss->uretprobe_byname_res, 6, "check_uretprobe_byname_res");
ASSERT_EQ(skel->bss->uprobe_byname2_res, 7, "check_uprobe_byname2_res");
ASSERT_EQ(skel->bss->uretprobe_byname2_res, 8, "check_uretprobe_byname2_res");
+ ASSERT_EQ(skel->bss->uprobe_byname3_sleepable_res, 9, "check_uprobe_byname3_sleepable_res");
+ ASSERT_EQ(skel->bss->uprobe_byname3_res, 10, "check_uprobe_byname3_res");
+ ASSERT_EQ(skel->bss->uretprobe_byname3_sleepable_res, 11, "check_uretprobe_byname3_sleepable_res");
+ ASSERT_EQ(skel->bss->uretprobe_byname3_res, 12, "check_uretprobe_byname3_res");
cleanup:
test_attach_probe__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 83ef55e3caa4..2974b44f80fa 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -121,24 +121,24 @@ static void kprobe_multi_link_api_subtest(void)
})
GET_ADDR("bpf_fentry_test1", addrs[0]);
- GET_ADDR("bpf_fentry_test2", addrs[1]);
- GET_ADDR("bpf_fentry_test3", addrs[2]);
- GET_ADDR("bpf_fentry_test4", addrs[3]);
- GET_ADDR("bpf_fentry_test5", addrs[4]);
- GET_ADDR("bpf_fentry_test6", addrs[5]);
- GET_ADDR("bpf_fentry_test7", addrs[6]);
+ GET_ADDR("bpf_fentry_test3", addrs[1]);
+ GET_ADDR("bpf_fentry_test4", addrs[2]);
+ GET_ADDR("bpf_fentry_test5", addrs[3]);
+ GET_ADDR("bpf_fentry_test6", addrs[4]);
+ GET_ADDR("bpf_fentry_test7", addrs[5]);
+ GET_ADDR("bpf_fentry_test2", addrs[6]);
GET_ADDR("bpf_fentry_test8", addrs[7]);
#undef GET_ADDR
- cookies[0] = 1;
- cookies[1] = 2;
- cookies[2] = 3;
- cookies[3] = 4;
- cookies[4] = 5;
- cookies[5] = 6;
- cookies[6] = 7;
- cookies[7] = 8;
+ cookies[0] = 1; /* bpf_fentry_test1 */
+ cookies[1] = 2; /* bpf_fentry_test3 */
+ cookies[2] = 3; /* bpf_fentry_test4 */
+ cookies[3] = 4; /* bpf_fentry_test5 */
+ cookies[4] = 5; /* bpf_fentry_test6 */
+ cookies[5] = 6; /* bpf_fentry_test7 */
+ cookies[6] = 7; /* bpf_fentry_test2 */
+ cookies[7] = 8; /* bpf_fentry_test8 */
opts.kprobe_multi.addrs = (const unsigned long *) &addrs;
opts.kprobe_multi.cnt = ARRAY_SIZE(addrs);
@@ -149,14 +149,14 @@ static void kprobe_multi_link_api_subtest(void)
if (!ASSERT_GE(link1_fd, 0, "link1_fd"))
goto cleanup;
- cookies[0] = 8;
- cookies[1] = 7;
- cookies[2] = 6;
- cookies[3] = 5;
- cookies[4] = 4;
- cookies[5] = 3;
- cookies[6] = 2;
- cookies[7] = 1;
+ cookies[0] = 8; /* bpf_fentry_test1 */
+ cookies[1] = 7; /* bpf_fentry_test3 */
+ cookies[2] = 6; /* bpf_fentry_test4 */
+ cookies[3] = 5; /* bpf_fentry_test5 */
+ cookies[4] = 4; /* bpf_fentry_test6 */
+ cookies[5] = 3; /* bpf_fentry_test7 */
+ cookies[6] = 2; /* bpf_fentry_test2 */
+ cookies[7] = 1; /* bpf_fentry_test8 */
opts.kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN;
prog_fd = bpf_program__fd(skel->progs.test_kretprobe);
@@ -181,12 +181,12 @@ static void kprobe_multi_attach_api_subtest(void)
struct kprobe_multi *skel = NULL;
const char *syms[8] = {
"bpf_fentry_test1",
- "bpf_fentry_test2",
"bpf_fentry_test3",
"bpf_fentry_test4",
"bpf_fentry_test5",
"bpf_fentry_test6",
"bpf_fentry_test7",
+ "bpf_fentry_test2",
"bpf_fentry_test8",
};
__u64 cookies[8];
@@ -198,14 +198,14 @@ static void kprobe_multi_attach_api_subtest(void)
skel->bss->pid = getpid();
skel->bss->test_cookie = true;
- cookies[0] = 1;
- cookies[1] = 2;
- cookies[2] = 3;
- cookies[3] = 4;
- cookies[4] = 5;
- cookies[5] = 6;
- cookies[6] = 7;
- cookies[7] = 8;
+ cookies[0] = 1; /* bpf_fentry_test1 */
+ cookies[1] = 2; /* bpf_fentry_test3 */
+ cookies[2] = 3; /* bpf_fentry_test4 */
+ cookies[3] = 4; /* bpf_fentry_test5 */
+ cookies[4] = 5; /* bpf_fentry_test6 */
+ cookies[5] = 6; /* bpf_fentry_test7 */
+ cookies[6] = 7; /* bpf_fentry_test2 */
+ cookies[7] = 8; /* bpf_fentry_test8 */
opts.syms = syms;
opts.cnt = ARRAY_SIZE(syms);
@@ -216,14 +216,14 @@ static void kprobe_multi_attach_api_subtest(void)
if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts"))
goto cleanup;
- cookies[0] = 8;
- cookies[1] = 7;
- cookies[2] = 6;
- cookies[3] = 5;
- cookies[4] = 4;
- cookies[5] = 3;
- cookies[6] = 2;
- cookies[7] = 1;
+ cookies[0] = 8; /* bpf_fentry_test1 */
+ cookies[1] = 7; /* bpf_fentry_test3 */
+ cookies[2] = 6; /* bpf_fentry_test4 */
+ cookies[3] = 5; /* bpf_fentry_test5 */
+ cookies[4] = 4; /* bpf_fentry_test6 */
+ cookies[5] = 3; /* bpf_fentry_test7 */
+ cookies[6] = 2; /* bpf_fentry_test2 */
+ cookies[7] = 1; /* bpf_fentry_test8 */
opts.retprobe = true;
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index ba5bde53d418..edb387163baa 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -2897,26 +2897,6 @@ static struct btf_raw_test raw_tests[] = {
},
{
- .descr = "invalid enum kind_flag",
- .raw_types = {
- BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
- BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 1, 1), 4), /* [2] */
- BTF_ENUM_ENC(NAME_TBD, 0),
- BTF_END_RAW,
- },
- BTF_STR_SEC("\0A"),
- .map_type = BPF_MAP_TYPE_ARRAY,
- .map_name = "enum_type_check_btf",
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .key_type_id = 1,
- .value_type_id = 1,
- .max_entries = 4,
- .btf_load_err = true,
- .err_str = "Invalid btf_info kind_flag",
-},
-
-{
.descr = "valid fwd kind_flag",
.raw_types = {
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
@@ -4072,6 +4052,42 @@ static struct btf_raw_test raw_tests[] = {
.btf_load_err = true,
.err_str = "Type tags don't precede modifiers",
},
+{
+ .descr = "enum64 test #1, unsigned, size 8",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 2), 8), /* [2] */
+ BTF_ENUM64_ENC(NAME_TBD, 0, 0),
+ BTF_ENUM64_ENC(NAME_TBD, 1, 1),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0a\0b\0c"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "tag_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = 8,
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 1,
+},
+{
+ .descr = "enum64 test #2, signed, size 4",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM64, 1, 2), 4), /* [2] */
+ BTF_ENUM64_ENC(NAME_TBD, -1, 0),
+ BTF_ENUM64_ENC(NAME_TBD, 1, 0),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0a\0b\0c"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "tag_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 1,
+},
}; /* struct btf_raw_test raw_tests[] */
@@ -7000,9 +7016,12 @@ static struct btf_dedup_test dedup_tests[] = {
BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] decl_tag */
BTF_DECL_TAG_ENC(NAME_TBD, 7, -1), /* [17] decl_tag */
BTF_TYPE_TAG_ENC(NAME_TBD, 8), /* [18] type_tag */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 2), 8), /* [19] enum64 */
+ BTF_ENUM64_ENC(NAME_TBD, 0, 0),
+ BTF_ENUM64_ENC(NAME_TBD, 1, 1),
BTF_END_RAW,
},
- BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q\0R"),
+ BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q\0R\0S\0T\0U"),
},
.expect = {
.raw_types = {
@@ -7030,9 +7049,12 @@ static struct btf_dedup_test dedup_tests[] = {
BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] decl_tag */
BTF_DECL_TAG_ENC(NAME_TBD, 7, -1), /* [17] decl_tag */
BTF_TYPE_TAG_ENC(NAME_TBD, 8), /* [18] type_tag */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 2), 8), /* [19] enum64 */
+ BTF_ENUM64_ENC(NAME_TBD, 0, 0),
+ BTF_ENUM64_ENC(NAME_TBD, 1, 1),
BTF_END_RAW,
},
- BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q\0R"),
+ BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q\0R\0S\0T\0U"),
},
},
{
@@ -7493,6 +7515,91 @@ static struct btf_dedup_test dedup_tests[] = {
BTF_STR_SEC("\0tag1\0t\0m"),
},
},
+{
+ .descr = "dedup: enum64, standalone",
+ .input = {
+ .raw_types = {
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(2), 1, 123),
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(2), 1, 123),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0e1\0e1_val"),
+ },
+ .expect = {
+ .raw_types = {
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(2), 1, 123),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0e1\0e1_val"),
+ },
+},
+{
+ .descr = "dedup: enum64, fwd resolution",
+ .input = {
+ .raw_types = {
+ /* [1] fwd enum64 'e1' before full enum */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
+ /* [2] full enum64 'e1' after fwd */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(2), 1, 123),
+ /* [3] full enum64 'e2' before fwd */
+ BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(4), 0, 456),
+ /* [4] fwd enum64 'e2' after full enum */
+ BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
+ /* [5] incompatible full enum64 with different value */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(2), 0, 321),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"),
+ },
+ .expect = {
+ .raw_types = {
+ /* [1] full enum64 'e1' */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(2), 1, 123),
+ /* [2] full enum64 'e2' */
+ BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(4), 0, 456),
+ /* [3] incompatible full enum64 with different value */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+ BTF_ENUM64_ENC(NAME_NTH(2), 0, 321),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"),
+ },
+},
+{
+ .descr = "dedup: enum and enum64, no dedup",
+ .input = {
+ .raw_types = {
+ /* [1] enum 'e1' */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+ BTF_ENUM_ENC(NAME_NTH(2), 1),
+ /* [2] enum64 'e1' */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 4),
+ BTF_ENUM64_ENC(NAME_NTH(2), 1, 0),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0e1\0e1_val"),
+ },
+ .expect = {
+ .raw_types = {
+ /* [1] enum 'e1' */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+ BTF_ENUM_ENC(NAME_NTH(2), 1),
+ /* [2] enum64 'e1' */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 4),
+ BTF_ENUM64_ENC(NAME_NTH(2), 1, 0),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0e1\0e1_val"),
+ },
+},
};
@@ -7517,6 +7624,8 @@ static int btf_type_size(const struct btf_type *t)
return base_size + sizeof(__u32);
case BTF_KIND_ENUM:
return base_size + vlen * sizeof(struct btf_enum);
+ case BTF_KIND_ENUM64:
+ return base_size + vlen * sizeof(struct btf_enum64);
case BTF_KIND_ARRAY:
return base_size + sizeof(struct btf_array);
case BTF_KIND_STRUCT:
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index addf99c05896..6e36de1302fc 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -9,6 +9,7 @@ static void gen_btf(struct btf *btf)
const struct btf_var_secinfo *vi;
const struct btf_type *t;
const struct btf_member *m;
+ const struct btf_enum64 *v64;
const struct btf_enum *v;
const struct btf_param *p;
int id, err, str_off;
@@ -171,7 +172,7 @@ static void gen_btf(struct btf *btf)
ASSERT_STREQ(btf__str_by_offset(btf, v->name_off), "v2", "v2_name");
ASSERT_EQ(v->val, 2, "v2_val");
ASSERT_STREQ(btf_type_raw_dump(btf, 9),
- "[9] ENUM 'e1' size=4 vlen=2\n"
+ "[9] ENUM 'e1' encoding=UNSIGNED size=4 vlen=2\n"
"\t'v1' val=1\n"
"\t'v2' val=2", "raw_dump");
@@ -202,7 +203,7 @@ static void gen_btf(struct btf *btf)
ASSERT_EQ(btf_vlen(t), 0, "enum_fwd_kind");
ASSERT_EQ(t->size, 4, "enum_fwd_sz");
ASSERT_STREQ(btf_type_raw_dump(btf, 12),
- "[12] ENUM 'enum_fwd' size=4 vlen=0", "raw_dump");
+ "[12] ENUM 'enum_fwd' encoding=UNSIGNED size=4 vlen=0", "raw_dump");
/* TYPEDEF */
id = btf__add_typedef(btf, "typedef1", 1);
@@ -307,6 +308,48 @@ static void gen_btf(struct btf *btf)
ASSERT_EQ(t->type, 1, "tag_type");
ASSERT_STREQ(btf_type_raw_dump(btf, 20),
"[20] TYPE_TAG 'tag1' type_id=1", "raw_dump");
+
+ /* ENUM64 */
+ id = btf__add_enum64(btf, "e1", 8, true);
+ ASSERT_EQ(id, 21, "enum64_id");
+ err = btf__add_enum64_value(btf, "v1", -1);
+ ASSERT_OK(err, "v1_res");
+ err = btf__add_enum64_value(btf, "v2", 0x123456789); /* 4886718345 */
+ ASSERT_OK(err, "v2_res");
+ t = btf__type_by_id(btf, 21);
+ ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "e1", "enum64_name");
+ ASSERT_EQ(btf_kind(t), BTF_KIND_ENUM64, "enum64_kind");
+ ASSERT_EQ(btf_vlen(t), 2, "enum64_vlen");
+ ASSERT_EQ(t->size, 8, "enum64_sz");
+ v64 = btf_enum64(t) + 0;
+ ASSERT_STREQ(btf__str_by_offset(btf, v64->name_off), "v1", "v1_name");
+ ASSERT_EQ(v64->val_hi32, 0xffffffff, "v1_val");
+ ASSERT_EQ(v64->val_lo32, 0xffffffff, "v1_val");
+ v64 = btf_enum64(t) + 1;
+ ASSERT_STREQ(btf__str_by_offset(btf, v64->name_off), "v2", "v2_name");
+ ASSERT_EQ(v64->val_hi32, 0x1, "v2_val");
+ ASSERT_EQ(v64->val_lo32, 0x23456789, "v2_val");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 21),
+ "[21] ENUM64 'e1' encoding=SIGNED size=8 vlen=2\n"
+ "\t'v1' val=-1\n"
+ "\t'v2' val=4886718345", "raw_dump");
+
+ id = btf__add_enum64(btf, "e1", 8, false);
+ ASSERT_EQ(id, 22, "enum64_id");
+ err = btf__add_enum64_value(btf, "v1", 0xffffffffFFFFFFFF); /* 18446744073709551615 */
+ ASSERT_OK(err, "v1_res");
+ t = btf__type_by_id(btf, 22);
+ ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "e1", "enum64_name");
+ ASSERT_EQ(btf_kind(t), BTF_KIND_ENUM64, "enum64_kind");
+ ASSERT_EQ(btf_vlen(t), 1, "enum64_vlen");
+ ASSERT_EQ(t->size, 8, "enum64_sz");
+ v64 = btf_enum64(t) + 0;
+ ASSERT_STREQ(btf__str_by_offset(btf, v64->name_off), "v1", "v1_name");
+ ASSERT_EQ(v64->val_hi32, 0xffffffff, "v1_val");
+ ASSERT_EQ(v64->val_lo32, 0xffffffff, "v1_val");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 22),
+ "[22] ENUM64 'e1' encoding=UNSIGNED size=8 vlen=1\n"
+ "\t'v1' val=18446744073709551615", "raw_dump");
}
static void test_btf_add()
@@ -332,12 +375,12 @@ static void test_btf_add()
"\t'f2' type_id=1 bits_offset=32 bitfield_size=16",
"[8] UNION 'u1' size=8 vlen=1\n"
"\t'f1' type_id=1 bits_offset=0 bitfield_size=16",
- "[9] ENUM 'e1' size=4 vlen=2\n"
+ "[9] ENUM 'e1' encoding=UNSIGNED size=4 vlen=2\n"
"\t'v1' val=1\n"
"\t'v2' val=2",
"[10] FWD 'struct_fwd' fwd_kind=struct",
"[11] FWD 'union_fwd' fwd_kind=union",
- "[12] ENUM 'enum_fwd' size=4 vlen=0",
+ "[12] ENUM 'enum_fwd' encoding=UNSIGNED size=4 vlen=0",
"[13] TYPEDEF 'typedef1' type_id=1",
"[14] FUNC 'func1' type_id=15 linkage=global",
"[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
@@ -348,7 +391,12 @@ static void test_btf_add()
"\ttype_id=1 offset=4 size=8",
"[18] DECL_TAG 'tag1' type_id=16 component_idx=-1",
"[19] DECL_TAG 'tag2' type_id=14 component_idx=1",
- "[20] TYPE_TAG 'tag1' type_id=1");
+ "[20] TYPE_TAG 'tag1' type_id=1",
+ "[21] ENUM64 'e1' encoding=SIGNED size=8 vlen=2\n"
+ "\t'v1' val=-1\n"
+ "\t'v2' val=4886718345",
+ "[22] ENUM64 'e1' encoding=UNSIGNED size=8 vlen=1\n"
+ "\t'v1' val=18446744073709551615");
btf__free(btf);
}
@@ -370,7 +418,7 @@ static void test_btf_add_btf()
gen_btf(btf2);
id = btf__add_btf(btf1, btf2);
- if (!ASSERT_EQ(id, 21, "id"))
+ if (!ASSERT_EQ(id, 23, "id"))
goto cleanup;
VALIDATE_RAW_BTF(
@@ -386,12 +434,12 @@ static void test_btf_add_btf()
"\t'f2' type_id=1 bits_offset=32 bitfield_size=16",
"[8] UNION 'u1' size=8 vlen=1\n"
"\t'f1' type_id=1 bits_offset=0 bitfield_size=16",
- "[9] ENUM 'e1' size=4 vlen=2\n"
+ "[9] ENUM 'e1' encoding=UNSIGNED size=4 vlen=2\n"
"\t'v1' val=1\n"
"\t'v2' val=2",
"[10] FWD 'struct_fwd' fwd_kind=struct",
"[11] FWD 'union_fwd' fwd_kind=union",
- "[12] ENUM 'enum_fwd' size=4 vlen=0",
+ "[12] ENUM 'enum_fwd' encoding=UNSIGNED size=4 vlen=0",
"[13] TYPEDEF 'typedef1' type_id=1",
"[14] FUNC 'func1' type_id=15 linkage=global",
"[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
@@ -403,36 +451,46 @@ static void test_btf_add_btf()
"[18] DECL_TAG 'tag1' type_id=16 component_idx=-1",
"[19] DECL_TAG 'tag2' type_id=14 component_idx=1",
"[20] TYPE_TAG 'tag1' type_id=1",
+ "[21] ENUM64 'e1' encoding=SIGNED size=8 vlen=2\n"
+ "\t'v1' val=-1\n"
+ "\t'v2' val=4886718345",
+ "[22] ENUM64 'e1' encoding=UNSIGNED size=8 vlen=1\n"
+ "\t'v1' val=18446744073709551615",
/* types appended from the second BTF */
- "[21] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
- "[22] PTR '(anon)' type_id=21",
- "[23] CONST '(anon)' type_id=25",
- "[24] VOLATILE '(anon)' type_id=23",
- "[25] RESTRICT '(anon)' type_id=24",
- "[26] ARRAY '(anon)' type_id=22 index_type_id=21 nr_elems=10",
- "[27] STRUCT 's1' size=8 vlen=2\n"
- "\t'f1' type_id=21 bits_offset=0\n"
- "\t'f2' type_id=21 bits_offset=32 bitfield_size=16",
- "[28] UNION 'u1' size=8 vlen=1\n"
- "\t'f1' type_id=21 bits_offset=0 bitfield_size=16",
- "[29] ENUM 'e1' size=4 vlen=2\n"
+ "[23] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[24] PTR '(anon)' type_id=23",
+ "[25] CONST '(anon)' type_id=27",
+ "[26] VOLATILE '(anon)' type_id=25",
+ "[27] RESTRICT '(anon)' type_id=26",
+ "[28] ARRAY '(anon)' type_id=24 index_type_id=23 nr_elems=10",
+ "[29] STRUCT 's1' size=8 vlen=2\n"
+ "\t'f1' type_id=23 bits_offset=0\n"
+ "\t'f2' type_id=23 bits_offset=32 bitfield_size=16",
+ "[30] UNION 'u1' size=8 vlen=1\n"
+ "\t'f1' type_id=23 bits_offset=0 bitfield_size=16",
+ "[31] ENUM 'e1' encoding=UNSIGNED size=4 vlen=2\n"
"\t'v1' val=1\n"
"\t'v2' val=2",
- "[30] FWD 'struct_fwd' fwd_kind=struct",
- "[31] FWD 'union_fwd' fwd_kind=union",
- "[32] ENUM 'enum_fwd' size=4 vlen=0",
- "[33] TYPEDEF 'typedef1' type_id=21",
- "[34] FUNC 'func1' type_id=35 linkage=global",
- "[35] FUNC_PROTO '(anon)' ret_type_id=21 vlen=2\n"
- "\t'p1' type_id=21\n"
- "\t'p2' type_id=22",
- "[36] VAR 'var1' type_id=21, linkage=global-alloc",
- "[37] DATASEC 'datasec1' size=12 vlen=1\n"
- "\ttype_id=21 offset=4 size=8",
- "[38] DECL_TAG 'tag1' type_id=36 component_idx=-1",
- "[39] DECL_TAG 'tag2' type_id=34 component_idx=1",
- "[40] TYPE_TAG 'tag1' type_id=21");
+ "[32] FWD 'struct_fwd' fwd_kind=struct",
+ "[33] FWD 'union_fwd' fwd_kind=union",
+ "[34] ENUM 'enum_fwd' encoding=UNSIGNED size=4 vlen=0",
+ "[35] TYPEDEF 'typedef1' type_id=23",
+ "[36] FUNC 'func1' type_id=37 linkage=global",
+ "[37] FUNC_PROTO '(anon)' ret_type_id=23 vlen=2\n"
+ "\t'p1' type_id=23\n"
+ "\t'p2' type_id=24",
+ "[38] VAR 'var1' type_id=23, linkage=global-alloc",
+ "[39] DATASEC 'datasec1' size=12 vlen=1\n"
+ "\ttype_id=23 offset=4 size=8",
+ "[40] DECL_TAG 'tag1' type_id=38 component_idx=-1",
+ "[41] DECL_TAG 'tag2' type_id=36 component_idx=1",
+ "[42] TYPE_TAG 'tag1' type_id=23",
+ "[43] ENUM64 'e1' encoding=SIGNED size=8 vlen=2\n"
+ "\t'v1' val=-1\n"
+ "\t'v2' val=4886718345",
+ "[44] ENUM64 'e1' encoding=UNSIGNED size=8 vlen=1\n"
+ "\t'v1' val=18446744073709551615");
cleanup:
btf__free(btf1);
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 3712dfe1be59..2f92feb809be 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -84,6 +84,7 @@ static int duration = 0;
#define NESTING_ERR_CASE(name) { \
NESTING_CASE_COMMON(name), \
.fails = true, \
+ .run_btfgen_fails = true, \
}
#define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \
@@ -258,12 +259,14 @@ static int duration = 0;
BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o", \
"probed:", name), \
.fails = true, \
+ .run_btfgen_fails = true, \
.raw_tp_name = "sys_enter", \
.prog_name = "test_core_bitfields", \
}, { \
BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o", \
"direct:", name), \
.fails = true, \
+ .run_btfgen_fails = true, \
.prog_name = "test_core_bitfields_direct", \
}
@@ -304,6 +307,7 @@ static int duration = 0;
#define SIZE_ERR_CASE(name) { \
SIZE_CASE_COMMON(name), \
.fails = true, \
+ .run_btfgen_fails = true, \
}
#define TYPE_BASED_CASE_COMMON(name) \
@@ -363,6 +367,25 @@ static int duration = 0;
.fails = true, \
}
+#define ENUM64VAL_CASE_COMMON(name) \
+ .case_name = #name, \
+ .bpf_obj_file = "test_core_reloc_enum64val.o", \
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_enum64val"
+
+#define ENUM64VAL_CASE(name, ...) { \
+ ENUM64VAL_CASE_COMMON(name), \
+ .output = STRUCT_TO_CHAR_PTR(core_reloc_enum64val_output) \
+ __VA_ARGS__, \
+ .output_len = sizeof(struct core_reloc_enum64val_output), \
+}
+
+#define ENUM64VAL_ERR_CASE(name) { \
+ ENUM64VAL_CASE_COMMON(name), \
+ .fails = true, \
+}
+
struct core_reloc_test_case;
typedef int (*setup_test_fn)(struct core_reloc_test_case *test);
@@ -377,6 +400,7 @@ struct core_reloc_test_case {
const char *output;
int output_len;
bool fails;
+ bool run_btfgen_fails;
bool needs_testmod;
bool relaxed_core_relocs;
const char *prog_name;
@@ -831,6 +855,45 @@ static const struct core_reloc_test_case test_cases[] = {
.anon_val2 = 0x222,
}),
ENUMVAL_ERR_CASE(enumval___err_missing),
+
+ /* 64bit enumerator value existence and value relocations */
+ ENUM64VAL_CASE(enum64val, {
+ .unsigned_val1_exists = true,
+ .unsigned_val2_exists = true,
+ .unsigned_val3_exists = true,
+ .signed_val1_exists = true,
+ .signed_val2_exists = true,
+ .signed_val3_exists = true,
+ .unsigned_val1 = 0x1ffffffffULL,
+ .unsigned_val2 = 0x2,
+ .signed_val1 = 0x1ffffffffLL,
+ .signed_val2 = -2,
+ }),
+ ENUM64VAL_CASE(enum64val___diff, {
+ .unsigned_val1_exists = true,
+ .unsigned_val2_exists = true,
+ .unsigned_val3_exists = true,
+ .signed_val1_exists = true,
+ .signed_val2_exists = true,
+ .signed_val3_exists = true,
+ .unsigned_val1 = 0x101ffffffffULL,
+ .unsigned_val2 = 0x202ffffffffULL,
+ .signed_val1 = -101,
+ .signed_val2 = -202,
+ }),
+ ENUM64VAL_CASE(enum64val___val3_missing, {
+ .unsigned_val1_exists = true,
+ .unsigned_val2_exists = true,
+ .unsigned_val3_exists = false,
+ .signed_val1_exists = true,
+ .signed_val2_exists = true,
+ .signed_val3_exists = false,
+ .unsigned_val1 = 0x111ffffffffULL,
+ .unsigned_val2 = 0x222,
+ .signed_val1 = 0x111ffffffffLL,
+ .signed_val2 = -222,
+ }),
+ ENUM64VAL_ERR_CASE(enum64val___err_missing),
};
struct data {
@@ -894,7 +957,7 @@ static void run_core_reloc_tests(bool use_btfgen)
/* generate a "minimal" BTF file and use it as source */
if (use_btfgen) {
- if (!test_case->btf_src_file || test_case->fails) {
+ if (!test_case->btf_src_file || test_case->run_btfgen_fails) {
test__skip();
continue;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
index a7e74297f15f..5a7e6011f6bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
@@ -7,11 +7,9 @@
void serial_test_fexit_stress(void)
{
- char test_skb[128] = {};
int fexit_fd[CNT] = {};
int link_fd[CNT] = {};
- char error[4096];
- int err, i, filter_fd;
+ int err, i;
const struct bpf_insn trace_program[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -20,25 +18,9 @@ void serial_test_fexit_stress(void)
LIBBPF_OPTS(bpf_prog_load_opts, trace_opts,
.expected_attach_type = BPF_TRACE_FEXIT,
- .log_buf = error,
- .log_size = sizeof(error),
);
- const struct bpf_insn skb_program[] = {
- BPF_MOV64_IMM(BPF_REG_0, 0),
- BPF_EXIT_INSN(),
- };
-
- LIBBPF_OPTS(bpf_prog_load_opts, skb_opts,
- .log_buf = error,
- .log_size = sizeof(error),
- );
-
- LIBBPF_OPTS(bpf_test_run_opts, topts,
- .data_in = test_skb,
- .data_size_in = sizeof(test_skb),
- .repeat = 1,
- );
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
err = libbpf_find_vmlinux_btf_id("bpf_fentry_test1",
trace_opts.expected_attach_type);
@@ -58,15 +40,9 @@ void serial_test_fexit_stress(void)
goto out;
}
- filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL",
- skb_program, sizeof(skb_program) / sizeof(struct bpf_insn),
- &skb_opts);
- if (!ASSERT_GE(filter_fd, 0, "test_program_loaded"))
- goto out;
+ err = bpf_prog_test_run_opts(fexit_fd[0], &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
- err = bpf_prog_test_run_opts(filter_fd, &topts);
- close(filter_fd);
- CHECK_FAIL(err);
out:
for (i = 0; i < CNT; i++) {
if (link_fd[i])
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 586dc52d6fb9..5b93d5d0bd93 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -364,6 +364,9 @@ static int get_syms(char ***symsp, size_t *cntp)
continue;
if (!strncmp(name, "rcu_", 4))
continue;
+ if (!strncmp(name, "__ftrace_invalid_address__",
+ sizeof("__ftrace_invalid_address__") - 1))
+ continue;
err = hashmap__add(map, name, NULL);
if (err) {
free(name);
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
new file mode 100644
index 000000000000..93e9cddaadcf
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -0,0 +1,207 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <ctype.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+/*
+ * Utility function uppercasing an entire string.
+ */
+static void uppercase(char *s)
+{
+ for (; *s != '\0'; s++)
+ *s = toupper(*s);
+}
+
+/*
+ * Test case to check that all bpf_attach_type variants are covered by
+ * libbpf_bpf_attach_type_str.
+ */
+static void test_libbpf_bpf_attach_type_str(void)
+{
+ struct btf *btf;
+ const struct btf_type *t;
+ const struct btf_enum *e;
+ int i, n, id;
+
+ btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+ if (!ASSERT_OK_PTR(btf, "btf_parse"))
+ return;
+
+ /* find enum bpf_attach_type and enumerate each value */
+ id = btf__find_by_name_kind(btf, "bpf_attach_type", BTF_KIND_ENUM);
+ if (!ASSERT_GT(id, 0, "bpf_attach_type_id"))
+ goto cleanup;
+ t = btf__type_by_id(btf, id);
+ e = btf_enum(t);
+ n = btf_vlen(t);
+ for (i = 0; i < n; e++, i++) {
+ enum bpf_attach_type attach_type = (enum bpf_attach_type)e->val;
+ const char *attach_type_name;
+ const char *attach_type_str;
+ char buf[256];
+
+ if (attach_type == __MAX_BPF_ATTACH_TYPE)
+ continue;
+
+ attach_type_name = btf__str_by_offset(btf, e->name_off);
+ attach_type_str = libbpf_bpf_attach_type_str(attach_type);
+ ASSERT_OK_PTR(attach_type_str, attach_type_name);
+
+ snprintf(buf, sizeof(buf), "BPF_%s", attach_type_str);
+ uppercase(buf);
+
+ ASSERT_STREQ(buf, attach_type_name, "exp_str_value");
+ }
+
+cleanup:
+ btf__free(btf);
+}
+
+/*
+ * Test case to check that all bpf_link_type variants are covered by
+ * libbpf_bpf_link_type_str.
+ */
+static void test_libbpf_bpf_link_type_str(void)
+{
+ struct btf *btf;
+ const struct btf_type *t;
+ const struct btf_enum *e;
+ int i, n, id;
+
+ btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+ if (!ASSERT_OK_PTR(btf, "btf_parse"))
+ return;
+
+ /* find enum bpf_link_type and enumerate each value */
+ id = btf__find_by_name_kind(btf, "bpf_link_type", BTF_KIND_ENUM);
+ if (!ASSERT_GT(id, 0, "bpf_link_type_id"))
+ goto cleanup;
+ t = btf__type_by_id(btf, id);
+ e = btf_enum(t);
+ n = btf_vlen(t);
+ for (i = 0; i < n; e++, i++) {
+ enum bpf_link_type link_type = (enum bpf_link_type)e->val;
+ const char *link_type_name;
+ const char *link_type_str;
+ char buf[256];
+
+ if (link_type == MAX_BPF_LINK_TYPE)
+ continue;
+
+ link_type_name = btf__str_by_offset(btf, e->name_off);
+ link_type_str = libbpf_bpf_link_type_str(link_type);
+ ASSERT_OK_PTR(link_type_str, link_type_name);
+
+ snprintf(buf, sizeof(buf), "BPF_LINK_TYPE_%s", link_type_str);
+ uppercase(buf);
+
+ ASSERT_STREQ(buf, link_type_name, "exp_str_value");
+ }
+
+cleanup:
+ btf__free(btf);
+}
+
+/*
+ * Test case to check that all bpf_map_type variants are covered by
+ * libbpf_bpf_map_type_str.
+ */
+static void test_libbpf_bpf_map_type_str(void)
+{
+ struct btf *btf;
+ const struct btf_type *t;
+ const struct btf_enum *e;
+ int i, n, id;
+
+ btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+ if (!ASSERT_OK_PTR(btf, "btf_parse"))
+ return;
+
+ /* find enum bpf_map_type and enumerate each value */
+ id = btf__find_by_name_kind(btf, "bpf_map_type", BTF_KIND_ENUM);
+ if (!ASSERT_GT(id, 0, "bpf_map_type_id"))
+ goto cleanup;
+ t = btf__type_by_id(btf, id);
+ e = btf_enum(t);
+ n = btf_vlen(t);
+ for (i = 0; i < n; e++, i++) {
+ enum bpf_map_type map_type = (enum bpf_map_type)e->val;
+ const char *map_type_name;
+ const char *map_type_str;
+ char buf[256];
+
+ map_type_name = btf__str_by_offset(btf, e->name_off);
+ map_type_str = libbpf_bpf_map_type_str(map_type);
+ ASSERT_OK_PTR(map_type_str, map_type_name);
+
+ snprintf(buf, sizeof(buf), "BPF_MAP_TYPE_%s", map_type_str);
+ uppercase(buf);
+
+ ASSERT_STREQ(buf, map_type_name, "exp_str_value");
+ }
+
+cleanup:
+ btf__free(btf);
+}
+
+/*
+ * Test case to check that all bpf_prog_type variants are covered by
+ * libbpf_bpf_prog_type_str.
+ */
+static void test_libbpf_bpf_prog_type_str(void)
+{
+ struct btf *btf;
+ const struct btf_type *t;
+ const struct btf_enum *e;
+ int i, n, id;
+
+ btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+ if (!ASSERT_OK_PTR(btf, "btf_parse"))
+ return;
+
+ /* find enum bpf_prog_type and enumerate each value */
+ id = btf__find_by_name_kind(btf, "bpf_prog_type", BTF_KIND_ENUM);
+ if (!ASSERT_GT(id, 0, "bpf_prog_type_id"))
+ goto cleanup;
+ t = btf__type_by_id(btf, id);
+ e = btf_enum(t);
+ n = btf_vlen(t);
+ for (i = 0; i < n; e++, i++) {
+ enum bpf_prog_type prog_type = (enum bpf_prog_type)e->val;
+ const char *prog_type_name;
+ const char *prog_type_str;
+ char buf[256];
+
+ prog_type_name = btf__str_by_offset(btf, e->name_off);
+ prog_type_str = libbpf_bpf_prog_type_str(prog_type);
+ ASSERT_OK_PTR(prog_type_str, prog_type_name);
+
+ snprintf(buf, sizeof(buf), "BPF_PROG_TYPE_%s", prog_type_str);
+ uppercase(buf);
+
+ ASSERT_STREQ(buf, prog_type_name, "exp_str_value");
+ }
+
+cleanup:
+ btf__free(btf);
+}
+
+/*
+ * Run all libbpf str conversion tests.
+ */
+void test_libbpf_str(void)
+{
+ if (test__start_subtest("bpf_attach_type_str"))
+ test_libbpf_bpf_attach_type_str();
+
+ if (test__start_subtest("bpf_link_type_str"))
+ test_libbpf_bpf_link_type_str();
+
+ if (test__start_subtest("bpf_map_type_str"))
+ test_libbpf_bpf_map_type_str();
+
+ if (test__start_subtest("bpf_prog_type_str"))
+ test_libbpf_bpf_prog_type_str();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index c4da87ec3ba4..19c70880cfb3 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -831,6 +831,59 @@ out:
bpf_object__close(obj);
}
+#include "tailcall_bpf2bpf6.skel.h"
+
+/* Tail call counting works even when there is data on stack which is
+ * not aligned to 8 bytes.
+ */
+static void test_tailcall_bpf2bpf_6(void)
+{
+ struct tailcall_bpf2bpf6 *obj;
+ int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 1,
+ );
+
+ obj = tailcall_bpf2bpf6__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "open and load"))
+ return;
+
+ main_fd = bpf_program__fd(obj->progs.entry);
+ if (!ASSERT_GE(main_fd, 0, "entry prog fd"))
+ goto out;
+
+ map_fd = bpf_map__fd(obj->maps.jmp_table);
+ if (!ASSERT_GE(map_fd, 0, "jmp_table map fd"))
+ goto out;
+
+ prog_fd = bpf_program__fd(obj->progs.classifier_0);
+ if (!ASSERT_GE(prog_fd, 0, "classifier_0 prog fd"))
+ goto out;
+
+ i = 0;
+ err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+ if (!ASSERT_OK(err, "jmp_table map update"))
+ goto out;
+
+ err = bpf_prog_test_run_opts(main_fd, &topts);
+ ASSERT_OK(err, "entry prog test run");
+ ASSERT_EQ(topts.retval, 0, "tailcall retval");
+
+ data_fd = bpf_map__fd(obj->maps.bss);
+ if (!ASSERT_GE(map_fd, 0, "bss map fd"))
+ goto out;
+
+ i = 0;
+ err = bpf_map_lookup_elem(data_fd, &i, &val);
+ ASSERT_OK(err, "bss map lookup");
+ ASSERT_EQ(val, 1, "done flag is set");
+
+out:
+ tailcall_bpf2bpf6__destroy(obj);
+}
+
void test_tailcalls(void)
{
if (test__start_subtest("tailcall_1"))
@@ -855,4 +908,6 @@ void test_tailcalls(void)
test_tailcall_bpf2bpf_4(false);
if (test__start_subtest("tailcall_bpf2bpf_5"))
test_tailcall_bpf2bpf_4(true);
+ if (test__start_subtest("tailcall_bpf2bpf_6"))
+ test_tailcall_bpf2bpf_6();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 958dae769c52..cb6a53b3e023 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -646,7 +646,7 @@ static void test_tcp_clear_dtime(struct test_tc_dtime *skel)
__u32 *errs = skel->bss->errs[t];
skel->bss->test = t;
- test_inet_dtime(AF_INET6, SOCK_STREAM, IP6_DST, 0);
+ test_inet_dtime(AF_INET6, SOCK_STREAM, IP6_DST, 50000 + t);
ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0,
dtime_cnt_str(t, INGRESS_FWDNS_P100));
@@ -683,7 +683,7 @@ static void test_tcp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd)
errs = skel->bss->errs[t];
skel->bss->test = t;
- test_inet_dtime(family, SOCK_STREAM, addr, 0);
+ test_inet_dtime(family, SOCK_STREAM, addr, 50000 + t);
/* fwdns_prio100 prog does not read delivery_time_type, so
* kernel puts the (rcv) timetamp in __sk_buff->tstamp
@@ -715,13 +715,13 @@ static void test_udp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd)
errs = skel->bss->errs[t];
skel->bss->test = t;
- test_inet_dtime(family, SOCK_DGRAM, addr, 0);
+ test_inet_dtime(family, SOCK_DGRAM, addr, 50000 + t);
ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0,
dtime_cnt_str(t, INGRESS_FWDNS_P100));
/* non mono delivery time is not forwarded */
ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0,
- dtime_cnt_str(t, INGRESS_FWDNS_P100));
+ dtime_cnt_str(t, INGRESS_FWDNS_P101));
for (i = EGRESS_FWDNS_P100; i < SET_DTIME; i++)
ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i));
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c b/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c
new file mode 100644
index 000000000000..fb77a123fe89
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <ctype.h>
+
+#define CMD_OUT_BUF_SIZE 1023
+
+#define SYS(cmd) ({ \
+ if (!ASSERT_OK(system(cmd), (cmd))) \
+ goto out; \
+})
+
+#define SYS_OUT(cmd, ...) ({ \
+ char buf[1024]; \
+ snprintf(buf, sizeof(buf), (cmd), ##__VA_ARGS__); \
+ FILE *f = popen(buf, "r"); \
+ if (!ASSERT_OK_PTR(f, buf)) \
+ goto out; \
+ f; \
+})
+
+/* out must be at least `size * 4 + 1` bytes long */
+static void escape_str(char *out, const char *in, size_t size)
+{
+ static const char *hex = "0123456789ABCDEF";
+ size_t i;
+
+ for (i = 0; i < size; i++) {
+ if (isprint(in[i]) && in[i] != '\\' && in[i] != '\'') {
+ *out++ = in[i];
+ } else {
+ *out++ = '\\';
+ *out++ = 'x';
+ *out++ = hex[(in[i] >> 4) & 0xf];
+ *out++ = hex[in[i] & 0xf];
+ }
+ }
+ *out++ = '\0';
+}
+
+static bool expect_str(char *buf, size_t size, const char *str, const char *name)
+{
+ static char escbuf_expected[CMD_OUT_BUF_SIZE * 4];
+ static char escbuf_actual[CMD_OUT_BUF_SIZE * 4];
+ static int duration = 0;
+ bool ok;
+
+ ok = size == strlen(str) && !memcmp(buf, str, size);
+
+ if (!ok) {
+ escape_str(escbuf_expected, str, strlen(str));
+ escape_str(escbuf_actual, buf, size);
+ }
+ CHECK(!ok, name, "unexpected %s: actual '%s' != expected '%s'\n",
+ name, escbuf_actual, escbuf_expected);
+
+ return ok;
+}
+
+static void test_synproxy(bool xdp)
+{
+ int server_fd = -1, client_fd = -1, accept_fd = -1;
+ char *prog_id, *prog_id_end;
+ struct nstoken *ns = NULL;
+ FILE *ctrl_file = NULL;
+ char buf[CMD_OUT_BUF_SIZE];
+ size_t size;
+
+ SYS("ip netns add synproxy");
+
+ SYS("ip link add tmp0 type veth peer name tmp1");
+ SYS("ip link set tmp1 netns synproxy");
+ SYS("ip link set tmp0 up");
+ SYS("ip addr replace 198.18.0.1/24 dev tmp0");
+
+ /* When checksum offload is enabled, the XDP program sees wrong
+ * checksums and drops packets.
+ */
+ SYS("ethtool -K tmp0 tx off");
+ if (xdp)
+ /* Workaround required for veth. */
+ SYS("ip link set tmp0 xdp object xdp_dummy.o section xdp 2> /dev/null");
+
+ ns = open_netns("synproxy");
+ if (!ASSERT_OK_PTR(ns, "setns"))
+ goto out;
+
+ SYS("ip link set lo up");
+ SYS("ip link set tmp1 up");
+ SYS("ip addr replace 198.18.0.2/24 dev tmp1");
+ SYS("sysctl -w net.ipv4.tcp_syncookies=2");
+ SYS("sysctl -w net.ipv4.tcp_timestamps=1");
+ SYS("sysctl -w net.netfilter.nf_conntrack_tcp_loose=0");
+ SYS("iptables -t raw -I PREROUTING \
+ -i tmp1 -p tcp -m tcp --syn --dport 8080 -j CT --notrack");
+ SYS("iptables -t filter -A INPUT \
+ -i tmp1 -p tcp -m tcp --dport 8080 -m state --state INVALID,UNTRACKED \
+ -j SYNPROXY --sack-perm --timestamp --wscale 7 --mss 1460");
+ SYS("iptables -t filter -A INPUT \
+ -i tmp1 -m state --state INVALID -j DROP");
+
+ ctrl_file = SYS_OUT("./xdp_synproxy --iface tmp1 --ports 8080 \
+ --single --mss4 1460 --mss6 1440 \
+ --wscale 7 --ttl 64%s", xdp ? "" : " --tc");
+ size = fread(buf, 1, sizeof(buf), ctrl_file);
+ pclose(ctrl_file);
+ if (!expect_str(buf, size, "Total SYNACKs generated: 0\n",
+ "initial SYNACKs"))
+ goto out;
+
+ if (!xdp) {
+ ctrl_file = SYS_OUT("tc filter show dev tmp1 ingress");
+ size = fread(buf, 1, sizeof(buf), ctrl_file);
+ pclose(ctrl_file);
+ prog_id = memmem(buf, size, " id ", 4);
+ if (!ASSERT_OK_PTR(prog_id, "find prog id"))
+ goto out;
+ prog_id += 4;
+ if (!ASSERT_LT(prog_id, buf + size, "find prog id begin"))
+ goto out;
+ prog_id_end = prog_id;
+ while (prog_id_end < buf + size && *prog_id_end >= '0' &&
+ *prog_id_end <= '9')
+ prog_id_end++;
+ if (!ASSERT_LT(prog_id_end, buf + size, "find prog id end"))
+ goto out;
+ *prog_id_end = '\0';
+ }
+
+ server_fd = start_server(AF_INET, SOCK_STREAM, "198.18.0.2", 8080, 0);
+ if (!ASSERT_GE(server_fd, 0, "start_server"))
+ goto out;
+
+ close_netns(ns);
+ ns = NULL;
+
+ client_fd = connect_to_fd(server_fd, 10000);
+ if (!ASSERT_GE(client_fd, 0, "connect_to_fd"))
+ goto out;
+
+ accept_fd = accept(server_fd, NULL, NULL);
+ if (!ASSERT_GE(accept_fd, 0, "accept"))
+ goto out;
+
+ ns = open_netns("synproxy");
+ if (!ASSERT_OK_PTR(ns, "setns"))
+ goto out;
+
+ if (xdp)
+ ctrl_file = SYS_OUT("./xdp_synproxy --iface tmp1 --single");
+ else
+ ctrl_file = SYS_OUT("./xdp_synproxy --prog %s --single",
+ prog_id);
+ size = fread(buf, 1, sizeof(buf), ctrl_file);
+ pclose(ctrl_file);
+ if (!expect_str(buf, size, "Total SYNACKs generated: 1\n",
+ "SYNACKs after connection"))
+ goto out;
+
+out:
+ if (accept_fd >= 0)
+ close(accept_fd);
+ if (client_fd >= 0)
+ close(client_fd);
+ if (server_fd >= 0)
+ close(server_fd);
+ if (ns)
+ close_netns(ns);
+
+ system("ip link del tmp0");
+ system("ip netns del synproxy");
+}
+
+void test_xdp_synproxy(void)
+{
+ if (test__start_subtest("xdp"))
+ test_synproxy(true);
+ if (test__start_subtest("tc"))
+ test_synproxy(false);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_hashmap_full_update_bench.c b/tools/testing/selftests/bpf/progs/bpf_hashmap_full_update_bench.c
new file mode 100644
index 000000000000..56957557e3e1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_hashmap_full_update_bench.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Bytedance */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define MAX_ENTRIES 1000
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, u32);
+ __type(value, u64);
+ __uint(max_entries, MAX_ENTRIES);
+} hash_map_bench SEC(".maps");
+
+u64 __attribute__((__aligned__(256))) percpu_time[256];
+u64 nr_loops;
+
+static int loop_update_callback(__u32 index, u32 *key)
+{
+ u64 init_val = 1;
+
+ bpf_map_update_elem(&hash_map_bench, key, &init_val, BPF_ANY);
+ return 0;
+}
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int benchmark(void *ctx)
+{
+ u32 cpu = bpf_get_smp_processor_id();
+ u32 key = cpu + MAX_ENTRIES;
+ u64 start_time = bpf_ktime_get_ns();
+
+ bpf_loop(nr_loops, loop_update_callback, &key, 0);
+ percpu_time[cpu & 255] = bpf_ktime_get_ns() - start_time;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val.c
new file mode 100644
index 000000000000..888e79db6a77
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_enum64val x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___diff.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___diff.c
new file mode 100644
index 000000000000..194749130d87
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___diff.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_enum64val___diff x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___err_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___err_missing.c
new file mode 100644
index 000000000000..3d732d4193e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___err_missing.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_enum64val___err_missing x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___val3_missing.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___val3_missing.c
new file mode 100644
index 000000000000..17cf5d6a848d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_enum64val___val3_missing.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_enum64val___val3_missing x) {}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index f9dc9766546e..26e103302c05 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -1117,6 +1117,20 @@ struct core_reloc_enumval_output {
int anon_val2;
};
+struct core_reloc_enum64val_output {
+ bool unsigned_val1_exists;
+ bool unsigned_val2_exists;
+ bool unsigned_val3_exists;
+ bool signed_val1_exists;
+ bool signed_val2_exists;
+ bool signed_val3_exists;
+
+ long unsigned_val1;
+ long unsigned_val2;
+ long signed_val1;
+ long signed_val2;
+};
+
enum named_enum {
NAMED_ENUM_VAL1 = 1,
NAMED_ENUM_VAL2 = 2,
@@ -1134,6 +1148,23 @@ struct core_reloc_enumval {
anon_enum f2;
};
+enum named_unsigned_enum64 {
+ UNSIGNED_ENUM64_VAL1 = 0x1ffffffffULL,
+ UNSIGNED_ENUM64_VAL2 = 0x2,
+ UNSIGNED_ENUM64_VAL3 = 0x3ffffffffULL,
+};
+
+enum named_signed_enum64 {
+ SIGNED_ENUM64_VAL1 = 0x1ffffffffLL,
+ SIGNED_ENUM64_VAL2 = -2,
+ SIGNED_ENUM64_VAL3 = 0x3ffffffffLL,
+};
+
+struct core_reloc_enum64val {
+ enum named_unsigned_enum64 f1;
+ enum named_signed_enum64 f2;
+};
+
/* differing enumerator values */
enum named_enum___diff {
NAMED_ENUM_VAL1___diff = 101,
@@ -1152,6 +1183,23 @@ struct core_reloc_enumval___diff {
anon_enum___diff f2;
};
+enum named_unsigned_enum64___diff {
+ UNSIGNED_ENUM64_VAL1___diff = 0x101ffffffffULL,
+ UNSIGNED_ENUM64_VAL2___diff = 0x202ffffffffULL,
+ UNSIGNED_ENUM64_VAL3___diff = 0x303ffffffffULL,
+};
+
+enum named_signed_enum64___diff {
+ SIGNED_ENUM64_VAL1___diff = -101,
+ SIGNED_ENUM64_VAL2___diff = -202,
+ SIGNED_ENUM64_VAL3___diff = -303,
+};
+
+struct core_reloc_enum64val___diff {
+ enum named_unsigned_enum64___diff f1;
+ enum named_signed_enum64___diff f2;
+};
+
/* missing (optional) third enum value */
enum named_enum___val3_missing {
NAMED_ENUM_VAL1___val3_missing = 111,
@@ -1168,6 +1216,21 @@ struct core_reloc_enumval___val3_missing {
anon_enum___val3_missing f2;
};
+enum named_unsigned_enum64___val3_missing {
+ UNSIGNED_ENUM64_VAL1___val3_missing = 0x111ffffffffULL,
+ UNSIGNED_ENUM64_VAL2___val3_missing = 0x222,
+};
+
+enum named_signed_enum64___val3_missing {
+ SIGNED_ENUM64_VAL1___val3_missing = 0x111ffffffffLL,
+ SIGNED_ENUM64_VAL2___val3_missing = -222,
+};
+
+struct core_reloc_enum64val___val3_missing {
+ enum named_unsigned_enum64___val3_missing f1;
+ enum named_signed_enum64___val3_missing f2;
+};
+
/* missing (mandatory) second enum value, should fail */
enum named_enum___err_missing {
NAMED_ENUM_VAL1___err_missing = 1,
@@ -1183,3 +1246,18 @@ struct core_reloc_enumval___err_missing {
enum named_enum___err_missing f1;
anon_enum___err_missing f2;
};
+
+enum named_unsigned_enum64___err_missing {
+ UNSIGNED_ENUM64_VAL1___err_missing = 0x1ffffffffULL,
+ UNSIGNED_ENUM64_VAL3___err_missing = 0x3ffffffffULL,
+};
+
+enum named_signed_enum64___err_missing {
+ SIGNED_ENUM64_VAL1___err_missing = 0x1ffffffffLL,
+ SIGNED_ENUM64_VAL3___err_missing = -3,
+};
+
+struct core_reloc_enum64val___err_missing {
+ enum named_unsigned_enum64___err_missing f1;
+ enum named_signed_enum64___err_missing f2;
+};
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi.c b/tools/testing/selftests/bpf/progs/kprobe_multi.c
index 93510f4f0f3a..08f95a8155d1 100644
--- a/tools/testing/selftests/bpf/progs/kprobe_multi.c
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi.c
@@ -54,21 +54,21 @@ static void kprobe_multi_check(void *ctx, bool is_return)
if (is_return) {
SET(kretprobe_test1_result, &bpf_fentry_test1, 8);
- SET(kretprobe_test2_result, &bpf_fentry_test2, 7);
- SET(kretprobe_test3_result, &bpf_fentry_test3, 6);
- SET(kretprobe_test4_result, &bpf_fentry_test4, 5);
- SET(kretprobe_test5_result, &bpf_fentry_test5, 4);
- SET(kretprobe_test6_result, &bpf_fentry_test6, 3);
- SET(kretprobe_test7_result, &bpf_fentry_test7, 2);
+ SET(kretprobe_test2_result, &bpf_fentry_test2, 2);
+ SET(kretprobe_test3_result, &bpf_fentry_test3, 7);
+ SET(kretprobe_test4_result, &bpf_fentry_test4, 6);
+ SET(kretprobe_test5_result, &bpf_fentry_test5, 5);
+ SET(kretprobe_test6_result, &bpf_fentry_test6, 4);
+ SET(kretprobe_test7_result, &bpf_fentry_test7, 3);
SET(kretprobe_test8_result, &bpf_fentry_test8, 1);
} else {
SET(kprobe_test1_result, &bpf_fentry_test1, 1);
- SET(kprobe_test2_result, &bpf_fentry_test2, 2);
- SET(kprobe_test3_result, &bpf_fentry_test3, 3);
- SET(kprobe_test4_result, &bpf_fentry_test4, 4);
- SET(kprobe_test5_result, &bpf_fentry_test5, 5);
- SET(kprobe_test6_result, &bpf_fentry_test6, 6);
- SET(kprobe_test7_result, &bpf_fentry_test7, 7);
+ SET(kprobe_test2_result, &bpf_fentry_test2, 7);
+ SET(kprobe_test3_result, &bpf_fentry_test3, 2);
+ SET(kprobe_test4_result, &bpf_fentry_test4, 3);
+ SET(kprobe_test5_result, &bpf_fentry_test5, 4);
+ SET(kprobe_test6_result, &bpf_fentry_test6, 5);
+ SET(kprobe_test7_result, &bpf_fentry_test7, 6);
SET(kprobe_test8_result, &bpf_fentry_test8, 8);
}
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
new file mode 100644
index 000000000000..41ce83da78e8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define __unused __attribute__((unused))
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int done = 0;
+
+SEC("tc")
+int classifier_0(struct __sk_buff *skb __unused)
+{
+ done = 1;
+ return 0;
+}
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+ /* Don't propagate the constant to the caller */
+ volatile int ret = 1;
+
+ bpf_tail_call_static(skb, &jmp_table, 0);
+ return ret;
+}
+
+SEC("tc")
+int entry(struct __sk_buff *skb)
+{
+ /* Have data on stack which size is not a multiple of 8 */
+ volatile char arr[1] = {};
+
+ return subprog_tail(skb);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index ce9acf4db8d2..f1c88ad368ef 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -5,6 +5,7 @@
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
#include "bpf_misc.h"
int kprobe_res = 0;
@@ -17,6 +18,11 @@ int uprobe_byname_res = 0;
int uretprobe_byname_res = 0;
int uprobe_byname2_res = 0;
int uretprobe_byname2_res = 0;
+int uprobe_byname3_sleepable_res = 0;
+int uprobe_byname3_res = 0;
+int uretprobe_byname3_sleepable_res = 0;
+int uretprobe_byname3_res = 0;
+void *user_ptr = 0;
SEC("kprobe")
int handle_kprobe(struct pt_regs *ctx)
@@ -32,6 +38,17 @@ int BPF_KPROBE(handle_kprobe_auto)
return 0;
}
+/**
+ * This program will be manually made sleepable on the userspace side
+ * and should thus be unattachable.
+ */
+SEC("kprobe/" SYS_PREFIX "sys_nanosleep")
+int handle_kprobe_sleepable(struct pt_regs *ctx)
+{
+ kprobe_res = 2;
+ return 0;
+}
+
SEC("kretprobe")
int handle_kretprobe(struct pt_regs *ctx)
{
@@ -93,4 +110,47 @@ int handle_uretprobe_byname2(struct pt_regs *ctx)
return 0;
}
+static __always_inline bool verify_sleepable_user_copy(void)
+{
+ char data[9];
+
+ bpf_copy_from_user(data, sizeof(data), user_ptr);
+ return bpf_strncmp(data, sizeof(data), "test_data") == 0;
+}
+
+SEC("uprobe.s//proc/self/exe:trigger_func3")
+int handle_uprobe_byname3_sleepable(struct pt_regs *ctx)
+{
+ if (verify_sleepable_user_copy())
+ uprobe_byname3_sleepable_res = 9;
+ return 0;
+}
+
+/**
+ * same target as the uprobe.s above to force sleepable and non-sleepable
+ * programs in the same bpf_prog_array
+ */
+SEC("uprobe//proc/self/exe:trigger_func3")
+int handle_uprobe_byname3(struct pt_regs *ctx)
+{
+ uprobe_byname3_res = 10;
+ return 0;
+}
+
+SEC("uretprobe.s//proc/self/exe:trigger_func3")
+int handle_uretprobe_byname3_sleepable(struct pt_regs *ctx)
+{
+ if (verify_sleepable_user_copy())
+ uretprobe_byname3_sleepable_res = 11;
+ return 0;
+}
+
+SEC("uretprobe//proc/self/exe:trigger_func3")
+int handle_uretprobe_byname3(struct pt_regs *ctx)
+{
+ uretprobe_byname3_res = 12;
+ return 0;
+}
+
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_enum64val.c b/tools/testing/selftests/bpf/progs/test_core_reloc_enum64val.c
new file mode 100644
index 000000000000..63147fbfae6e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_enum64val.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ char in[256];
+ char out[256];
+ bool skip;
+} data = {};
+
+enum named_unsigned_enum64 {
+ UNSIGNED_ENUM64_VAL1 = 0x1ffffffffULL,
+ UNSIGNED_ENUM64_VAL2 = 0x2ffffffffULL,
+ UNSIGNED_ENUM64_VAL3 = 0x3ffffffffULL,
+};
+
+enum named_signed_enum64 {
+ SIGNED_ENUM64_VAL1 = 0x1ffffffffLL,
+ SIGNED_ENUM64_VAL2 = -2,
+ SIGNED_ENUM64_VAL3 = 0x3ffffffffLL,
+};
+
+struct core_reloc_enum64val_output {
+ bool unsigned_val1_exists;
+ bool unsigned_val2_exists;
+ bool unsigned_val3_exists;
+ bool signed_val1_exists;
+ bool signed_val2_exists;
+ bool signed_val3_exists;
+
+ long unsigned_val1;
+ long unsigned_val2;
+ long signed_val1;
+ long signed_val2;
+};
+
+SEC("raw_tracepoint/sys_enter")
+int test_core_enum64val(void *ctx)
+{
+#if __clang_major__ >= 15
+ struct core_reloc_enum64val_output *out = (void *)&data.out;
+ enum named_unsigned_enum64 named_unsigned = 0;
+ enum named_signed_enum64 named_signed = 0;
+
+ out->unsigned_val1_exists = bpf_core_enum_value_exists(named_unsigned, UNSIGNED_ENUM64_VAL1);
+ out->unsigned_val2_exists = bpf_core_enum_value_exists(enum named_unsigned_enum64, UNSIGNED_ENUM64_VAL2);
+ out->unsigned_val3_exists = bpf_core_enum_value_exists(enum named_unsigned_enum64, UNSIGNED_ENUM64_VAL3);
+ out->signed_val1_exists = bpf_core_enum_value_exists(named_signed, SIGNED_ENUM64_VAL1);
+ out->signed_val2_exists = bpf_core_enum_value_exists(enum named_signed_enum64, SIGNED_ENUM64_VAL2);
+ out->signed_val3_exists = bpf_core_enum_value_exists(enum named_signed_enum64, SIGNED_ENUM64_VAL3);
+
+ out->unsigned_val1 = bpf_core_enum_value(named_unsigned, UNSIGNED_ENUM64_VAL1);
+ out->unsigned_val2 = bpf_core_enum_value(named_unsigned, UNSIGNED_ENUM64_VAL2);
+ out->signed_val1 = bpf_core_enum_value(named_signed, SIGNED_ENUM64_VAL1);
+ out->signed_val2 = bpf_core_enum_value(named_signed, SIGNED_ENUM64_VAL2);
+ /* NAMED_ENUM64_VAL3 value is optional */
+
+#else
+ data.skip = true;
+#endif
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c
index 06f300d06dbd..b596479a9ebe 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_dtime.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c
@@ -11,6 +11,8 @@
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#include <sys/socket.h>
@@ -115,6 +117,19 @@ static bool bpf_fwd(void)
return test < TCP_IP4_RT_FWD;
}
+static __u8 get_proto(void)
+{
+ switch (test) {
+ case UDP_IP4:
+ case UDP_IP6:
+ case UDP_IP4_RT_FWD:
+ case UDP_IP6_RT_FWD:
+ return IPPROTO_UDP;
+ default:
+ return IPPROTO_TCP;
+ }
+}
+
/* -1: parse error: TC_ACT_SHOT
* 0: not testing traffic: TC_ACT_OK
* >0: first byte is the inet_proto, second byte has the netns
@@ -122,11 +137,16 @@ static bool bpf_fwd(void)
*/
static int skb_get_type(struct __sk_buff *skb)
{
+ __u16 dst_ns_port = __bpf_htons(50000 + test);
void *data_end = ctx_ptr(skb->data_end);
void *data = ctx_ptr(skb->data);
__u8 inet_proto = 0, ns = 0;
struct ipv6hdr *ip6h;
+ __u16 sport, dport;
struct iphdr *iph;
+ struct tcphdr *th;
+ struct udphdr *uh;
+ void *trans;
switch (skb->protocol) {
case __bpf_htons(ETH_P_IP):
@@ -138,6 +158,7 @@ static int skb_get_type(struct __sk_buff *skb)
else if (iph->saddr == ip4_dst)
ns = DST_NS;
inet_proto = iph->protocol;
+ trans = iph + 1;
break;
case __bpf_htons(ETH_P_IPV6):
ip6h = data + sizeof(struct ethhdr);
@@ -148,15 +169,43 @@ static int skb_get_type(struct __sk_buff *skb)
else if (v6_equal(ip6h->saddr, (struct in6_addr)ip6_dst))
ns = DST_NS;
inet_proto = ip6h->nexthdr;
+ trans = ip6h + 1;
break;
default:
return 0;
}
- if ((inet_proto != IPPROTO_TCP && inet_proto != IPPROTO_UDP) || !ns)
+ /* skb is not from src_ns or dst_ns.
+ * skb is not the testing IPPROTO.
+ */
+ if (!ns || inet_proto != get_proto())
return 0;
- return (ns << 8 | inet_proto);
+ switch (inet_proto) {
+ case IPPROTO_TCP:
+ th = trans;
+ if (th + 1 > data_end)
+ return -1;
+ sport = th->source;
+ dport = th->dest;
+ break;
+ case IPPROTO_UDP:
+ uh = trans;
+ if (uh + 1 > data_end)
+ return -1;
+ sport = uh->source;
+ dport = uh->dest;
+ break;
+ default:
+ return 0;
+ }
+
+ /* The skb is the testing traffic */
+ if ((ns == SRC_NS && dport == dst_ns_port) ||
+ (ns == DST_NS && sport == dst_ns_port))
+ return (ns << 8 | inet_proto);
+
+ return 0;
}
/* format: direction@iface@netns
diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c
index 913acdffd90f..3987ff174f1f 100644
--- a/tools/testing/selftests/bpf/progs/test_varlen.c
+++ b/tools/testing/selftests/bpf/progs/test_varlen.c
@@ -41,20 +41,20 @@ int handler64_unsigned(void *regs)
{
int pid = bpf_get_current_pid_tgid() >> 32;
void *payload = payload1;
- u64 len;
+ long len;
/* ignore irrelevant invocations */
if (test_pid != pid || !capture)
return 0;
len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]);
- if (len <= MAX_LEN) {
+ if (len >= 0) {
payload += len;
payload1_len1 = len;
}
len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]);
- if (len <= MAX_LEN) {
+ if (len >= 0) {
payload += len;
payload1_len2 = len;
}
@@ -123,7 +123,7 @@ int handler32_signed(void *regs)
{
int pid = bpf_get_current_pid_tgid() >> 32;
void *payload = payload4;
- int len;
+ long len;
/* ignore irrelevant invocations */
if (test_pid != pid || !capture)
diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
new file mode 100644
index 000000000000..9fd62e94b5e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -0,0 +1,833 @@
+// SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <asm/errno.h>
+
+#define TC_ACT_OK 0
+#define TC_ACT_SHOT 2
+
+#define NSEC_PER_SEC 1000000000L
+
+#define ETH_ALEN 6
+#define ETH_P_IP 0x0800
+#define ETH_P_IPV6 0x86DD
+
+#define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3])
+
+#define IP_DF 0x4000
+#define IP_MF 0x2000
+#define IP_OFFSET 0x1fff
+
+#define NEXTHDR_TCP 6
+
+#define TCPOPT_NOP 1
+#define TCPOPT_EOL 0
+#define TCPOPT_MSS 2
+#define TCPOPT_WINDOW 3
+#define TCPOPT_SACK_PERM 4
+#define TCPOPT_TIMESTAMP 8
+
+#define TCPOLEN_MSS 4
+#define TCPOLEN_WINDOW 3
+#define TCPOLEN_SACK_PERM 2
+#define TCPOLEN_TIMESTAMP 10
+
+#define TCP_TS_HZ 1000
+#define TS_OPT_WSCALE_MASK 0xf
+#define TS_OPT_SACK (1 << 4)
+#define TS_OPT_ECN (1 << 5)
+#define TSBITS 6
+#define TSMASK (((__u32)1 << TSBITS) - 1)
+#define TCP_MAX_WSCALE 14U
+
+#define IPV4_MAXLEN 60
+#define TCP_MAXLEN 60
+
+#define DEFAULT_MSS4 1460
+#define DEFAULT_MSS6 1440
+#define DEFAULT_WSCALE 7
+#define DEFAULT_TTL 64
+#define MAX_ALLOWED_PORTS 8
+
+#define swap(a, b) \
+ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
+#define __get_unaligned_t(type, ptr) ({ \
+ const struct { type x; } __attribute__((__packed__)) *__pptr = (typeof(__pptr))(ptr); \
+ __pptr->x; \
+})
+
+#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr))
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u64);
+ __uint(max_entries, 2);
+} values SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u16);
+ __uint(max_entries, MAX_ALLOWED_PORTS);
+} allowed_ports SEC(".maps");
+
+extern struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx,
+ struct bpf_sock_tuple *bpf_tuple,
+ __u32 len_tuple,
+ struct bpf_ct_opts *opts,
+ __u32 len_opts) __ksym;
+
+extern struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *skb_ctx,
+ struct bpf_sock_tuple *bpf_tuple,
+ u32 len_tuple,
+ struct bpf_ct_opts *opts,
+ u32 len_opts) __ksym;
+
+extern void bpf_ct_release(struct nf_conn *ct) __ksym;
+
+static __always_inline void swap_eth_addr(__u8 *a, __u8 *b)
+{
+ __u8 tmp[ETH_ALEN];
+
+ __builtin_memcpy(tmp, a, ETH_ALEN);
+ __builtin_memcpy(a, b, ETH_ALEN);
+ __builtin_memcpy(b, tmp, ETH_ALEN);
+}
+
+static __always_inline __u16 csum_fold(__u32 csum)
+{
+ csum = (csum & 0xffff) + (csum >> 16);
+ csum = (csum & 0xffff) + (csum >> 16);
+ return (__u16)~csum;
+}
+
+static __always_inline __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+ __u32 len, __u8 proto,
+ __u32 csum)
+{
+ __u64 s = csum;
+
+ s += (__u32)saddr;
+ s += (__u32)daddr;
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ s += proto + len;
+#elif __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ s += (proto + len) << 8;
+#else
+#error Unknown endian
+#endif
+ s = (s & 0xffffffff) + (s >> 32);
+ s = (s & 0xffffffff) + (s >> 32);
+
+ return csum_fold((__u32)s);
+}
+
+static __always_inline __u16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __u32 csum)
+{
+ __u64 sum = csum;
+ int i;
+
+#pragma unroll
+ for (i = 0; i < 4; i++)
+ sum += (__u32)saddr->in6_u.u6_addr32[i];
+
+#pragma unroll
+ for (i = 0; i < 4; i++)
+ sum += (__u32)daddr->in6_u.u6_addr32[i];
+
+ /* Don't combine additions to avoid 32-bit overflow. */
+ sum += bpf_htonl(len);
+ sum += bpf_htonl(proto);
+
+ sum = (sum & 0xffffffff) + (sum >> 32);
+ sum = (sum & 0xffffffff) + (sum >> 32);
+
+ return csum_fold((__u32)sum);
+}
+
+static __always_inline __u64 tcp_clock_ns(void)
+{
+ return bpf_ktime_get_ns();
+}
+
+static __always_inline __u32 tcp_ns_to_ts(__u64 ns)
+{
+ return ns / (NSEC_PER_SEC / TCP_TS_HZ);
+}
+
+static __always_inline __u32 tcp_time_stamp_raw(void)
+{
+ return tcp_ns_to_ts(tcp_clock_ns());
+}
+
+struct tcpopt_context {
+ __u8 *ptr;
+ __u8 *end;
+ void *data_end;
+ __be32 *tsecr;
+ __u8 wscale;
+ bool option_timestamp;
+ bool option_sack;
+};
+
+static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+{
+ __u8 opcode, opsize;
+
+ if (ctx->ptr >= ctx->end)
+ return 1;
+ if (ctx->ptr >= ctx->data_end)
+ return 1;
+
+ opcode = ctx->ptr[0];
+
+ if (opcode == TCPOPT_EOL)
+ return 1;
+ if (opcode == TCPOPT_NOP) {
+ ++ctx->ptr;
+ return 0;
+ }
+
+ if (ctx->ptr + 1 >= ctx->end)
+ return 1;
+ if (ctx->ptr + 1 >= ctx->data_end)
+ return 1;
+ opsize = ctx->ptr[1];
+ if (opsize < 2)
+ return 1;
+
+ if (ctx->ptr + opsize > ctx->end)
+ return 1;
+
+ switch (opcode) {
+ case TCPOPT_WINDOW:
+ if (opsize == TCPOLEN_WINDOW && ctx->ptr + TCPOLEN_WINDOW <= ctx->data_end)
+ ctx->wscale = ctx->ptr[2] < TCP_MAX_WSCALE ? ctx->ptr[2] : TCP_MAX_WSCALE;
+ break;
+ case TCPOPT_TIMESTAMP:
+ if (opsize == TCPOLEN_TIMESTAMP && ctx->ptr + TCPOLEN_TIMESTAMP <= ctx->data_end) {
+ ctx->option_timestamp = true;
+ /* Client's tsval becomes our tsecr. */
+ *ctx->tsecr = get_unaligned((__be32 *)(ctx->ptr + 2));
+ }
+ break;
+ case TCPOPT_SACK_PERM:
+ if (opsize == TCPOLEN_SACK_PERM)
+ ctx->option_sack = true;
+ break;
+ }
+
+ ctx->ptr += opsize;
+
+ return 0;
+}
+
+static int tscookie_tcpopt_parse_batch(__u32 index, void *context)
+{
+ int i;
+
+ for (i = 0; i < 7; i++)
+ if (tscookie_tcpopt_parse(context))
+ return 1;
+ return 0;
+}
+
+static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
+ __u16 tcp_len, __be32 *tsval,
+ __be32 *tsecr, void *data_end)
+{
+ struct tcpopt_context loop_ctx = {
+ .ptr = (__u8 *)(tcp_header + 1),
+ .end = (__u8 *)tcp_header + tcp_len,
+ .data_end = data_end,
+ .tsecr = tsecr,
+ .wscale = TS_OPT_WSCALE_MASK,
+ .option_timestamp = false,
+ .option_sack = false,
+ };
+ u32 cookie;
+
+ bpf_loop(6, tscookie_tcpopt_parse_batch, &loop_ctx, 0);
+
+ if (!loop_ctx.option_timestamp)
+ return false;
+
+ cookie = tcp_time_stamp_raw() & ~TSMASK;
+ cookie |= loop_ctx.wscale & TS_OPT_WSCALE_MASK;
+ if (loop_ctx.option_sack)
+ cookie |= TS_OPT_SACK;
+ if (tcp_header->ece && tcp_header->cwr)
+ cookie |= TS_OPT_ECN;
+ *tsval = bpf_htonl(cookie);
+
+ return true;
+}
+
+static __always_inline void values_get_tcpipopts(__u16 *mss, __u8 *wscale,
+ __u8 *ttl, bool ipv6)
+{
+ __u32 key = 0;
+ __u64 *value;
+
+ value = bpf_map_lookup_elem(&values, &key);
+ if (value && *value != 0) {
+ if (ipv6)
+ *mss = (*value >> 32) & 0xffff;
+ else
+ *mss = *value & 0xffff;
+ *wscale = (*value >> 16) & 0xf;
+ *ttl = (*value >> 24) & 0xff;
+ return;
+ }
+
+ *mss = ipv6 ? DEFAULT_MSS6 : DEFAULT_MSS4;
+ *wscale = DEFAULT_WSCALE;
+ *ttl = DEFAULT_TTL;
+}
+
+static __always_inline void values_inc_synacks(void)
+{
+ __u32 key = 1;
+ __u32 *value;
+
+ value = bpf_map_lookup_elem(&values, &key);
+ if (value)
+ __sync_fetch_and_add(value, 1);
+}
+
+static __always_inline bool check_port_allowed(__u16 port)
+{
+ __u32 i;
+
+ for (i = 0; i < MAX_ALLOWED_PORTS; i++) {
+ __u32 key = i;
+ __u16 *value;
+
+ value = bpf_map_lookup_elem(&allowed_ports, &key);
+
+ if (!value)
+ break;
+ /* 0 is a terminator value. Check it first to avoid matching on
+ * a forbidden port == 0 and returning true.
+ */
+ if (*value == 0)
+ break;
+
+ if (*value == port)
+ return true;
+ }
+
+ return false;
+}
+
+struct header_pointers {
+ struct ethhdr *eth;
+ struct iphdr *ipv4;
+ struct ipv6hdr *ipv6;
+ struct tcphdr *tcp;
+ __u16 tcp_len;
+};
+
+static __always_inline int tcp_dissect(void *data, void *data_end,
+ struct header_pointers *hdr)
+{
+ hdr->eth = data;
+ if (hdr->eth + 1 > data_end)
+ return XDP_DROP;
+
+ switch (bpf_ntohs(hdr->eth->h_proto)) {
+ case ETH_P_IP:
+ hdr->ipv6 = NULL;
+
+ hdr->ipv4 = (void *)hdr->eth + sizeof(*hdr->eth);
+ if (hdr->ipv4 + 1 > data_end)
+ return XDP_DROP;
+ if (hdr->ipv4->ihl * 4 < sizeof(*hdr->ipv4))
+ return XDP_DROP;
+ if (hdr->ipv4->version != 4)
+ return XDP_DROP;
+
+ if (hdr->ipv4->protocol != IPPROTO_TCP)
+ return XDP_PASS;
+
+ hdr->tcp = (void *)hdr->ipv4 + hdr->ipv4->ihl * 4;
+ break;
+ case ETH_P_IPV6:
+ hdr->ipv4 = NULL;
+
+ hdr->ipv6 = (void *)hdr->eth + sizeof(*hdr->eth);
+ if (hdr->ipv6 + 1 > data_end)
+ return XDP_DROP;
+ if (hdr->ipv6->version != 6)
+ return XDP_DROP;
+
+ /* XXX: Extension headers are not supported and could circumvent
+ * XDP SYN flood protection.
+ */
+ if (hdr->ipv6->nexthdr != NEXTHDR_TCP)
+ return XDP_PASS;
+
+ hdr->tcp = (void *)hdr->ipv6 + sizeof(*hdr->ipv6);
+ break;
+ default:
+ /* XXX: VLANs will circumvent XDP SYN flood protection. */
+ return XDP_PASS;
+ }
+
+ if (hdr->tcp + 1 > data_end)
+ return XDP_DROP;
+ hdr->tcp_len = hdr->tcp->doff * 4;
+ if (hdr->tcp_len < sizeof(*hdr->tcp))
+ return XDP_DROP;
+
+ return XDP_TX;
+}
+
+static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bool xdp)
+{
+ struct bpf_ct_opts ct_lookup_opts = {
+ .netns_id = BPF_F_CURRENT_NETNS,
+ .l4proto = IPPROTO_TCP,
+ };
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+ __u32 tup_size;
+
+ if (hdr->ipv4) {
+ /* TCP doesn't normally use fragments, and XDP can't reassemble
+ * them.
+ */
+ if ((hdr->ipv4->frag_off & bpf_htons(IP_DF | IP_MF | IP_OFFSET)) != bpf_htons(IP_DF))
+ return XDP_DROP;
+
+ tup.ipv4.saddr = hdr->ipv4->saddr;
+ tup.ipv4.daddr = hdr->ipv4->daddr;
+ tup.ipv4.sport = hdr->tcp->source;
+ tup.ipv4.dport = hdr->tcp->dest;
+ tup_size = sizeof(tup.ipv4);
+ } else if (hdr->ipv6) {
+ __builtin_memcpy(tup.ipv6.saddr, &hdr->ipv6->saddr, sizeof(tup.ipv6.saddr));
+ __builtin_memcpy(tup.ipv6.daddr, &hdr->ipv6->daddr, sizeof(tup.ipv6.daddr));
+ tup.ipv6.sport = hdr->tcp->source;
+ tup.ipv6.dport = hdr->tcp->dest;
+ tup_size = sizeof(tup.ipv6);
+ } else {
+ /* The verifier can't track that either ipv4 or ipv6 is not
+ * NULL.
+ */
+ return XDP_ABORTED;
+ }
+ if (xdp)
+ ct = bpf_xdp_ct_lookup(ctx, &tup, tup_size, &ct_lookup_opts, sizeof(ct_lookup_opts));
+ else
+ ct = bpf_skb_ct_lookup(ctx, &tup, tup_size, &ct_lookup_opts, sizeof(ct_lookup_opts));
+ if (ct) {
+ unsigned long status = ct->status;
+
+ bpf_ct_release(ct);
+ if (status & IPS_CONFIRMED_BIT)
+ return XDP_PASS;
+ } else if (ct_lookup_opts.error != -ENOENT) {
+ return XDP_ABORTED;
+ }
+
+ /* error == -ENOENT || !(status & IPS_CONFIRMED_BIT) */
+ return XDP_TX;
+}
+
+static __always_inline __u8 tcp_mkoptions(__be32 *buf, __be32 *tsopt, __u16 mss,
+ __u8 wscale)
+{
+ __be32 *start = buf;
+
+ *buf++ = bpf_htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
+
+ if (!tsopt)
+ return buf - start;
+
+ if (tsopt[0] & bpf_htonl(1 << 4))
+ *buf++ = bpf_htonl((TCPOPT_SACK_PERM << 24) |
+ (TCPOLEN_SACK_PERM << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
+ else
+ *buf++ = bpf_htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
+ *buf++ = tsopt[0];
+ *buf++ = tsopt[1];
+
+ if ((tsopt[0] & bpf_htonl(0xf)) != bpf_htonl(0xf))
+ *buf++ = bpf_htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_WINDOW << 16) |
+ (TCPOLEN_WINDOW << 8) |
+ wscale);
+
+ return buf - start;
+}
+
+static __always_inline void tcp_gen_synack(struct tcphdr *tcp_header,
+ __u32 cookie, __be32 *tsopt,
+ __u16 mss, __u8 wscale)
+{
+ void *tcp_options;
+
+ tcp_flag_word(tcp_header) = TCP_FLAG_SYN | TCP_FLAG_ACK;
+ if (tsopt && (tsopt[0] & bpf_htonl(1 << 5)))
+ tcp_flag_word(tcp_header) |= TCP_FLAG_ECE;
+ tcp_header->doff = 5; /* doff is part of tcp_flag_word. */
+ swap(tcp_header->source, tcp_header->dest);
+ tcp_header->ack_seq = bpf_htonl(bpf_ntohl(tcp_header->seq) + 1);
+ tcp_header->seq = bpf_htonl(cookie);
+ tcp_header->window = 0;
+ tcp_header->urg_ptr = 0;
+ tcp_header->check = 0; /* Calculate checksum later. */
+
+ tcp_options = (void *)(tcp_header + 1);
+ tcp_header->doff += tcp_mkoptions(tcp_options, tsopt, mss, wscale);
+}
+
+static __always_inline void tcpv4_gen_synack(struct header_pointers *hdr,
+ __u32 cookie, __be32 *tsopt)
+{
+ __u8 wscale;
+ __u16 mss;
+ __u8 ttl;
+
+ values_get_tcpipopts(&mss, &wscale, &ttl, false);
+
+ swap_eth_addr(hdr->eth->h_source, hdr->eth->h_dest);
+
+ swap(hdr->ipv4->saddr, hdr->ipv4->daddr);
+ hdr->ipv4->check = 0; /* Calculate checksum later. */
+ hdr->ipv4->tos = 0;
+ hdr->ipv4->id = 0;
+ hdr->ipv4->ttl = ttl;
+
+ tcp_gen_synack(hdr->tcp, cookie, tsopt, mss, wscale);
+
+ hdr->tcp_len = hdr->tcp->doff * 4;
+ hdr->ipv4->tot_len = bpf_htons(sizeof(*hdr->ipv4) + hdr->tcp_len);
+}
+
+static __always_inline void tcpv6_gen_synack(struct header_pointers *hdr,
+ __u32 cookie, __be32 *tsopt)
+{
+ __u8 wscale;
+ __u16 mss;
+ __u8 ttl;
+
+ values_get_tcpipopts(&mss, &wscale, &ttl, true);
+
+ swap_eth_addr(hdr->eth->h_source, hdr->eth->h_dest);
+
+ swap(hdr->ipv6->saddr, hdr->ipv6->daddr);
+ *(__be32 *)hdr->ipv6 = bpf_htonl(0x60000000);
+ hdr->ipv6->hop_limit = ttl;
+
+ tcp_gen_synack(hdr->tcp, cookie, tsopt, mss, wscale);
+
+ hdr->tcp_len = hdr->tcp->doff * 4;
+ hdr->ipv6->payload_len = bpf_htons(hdr->tcp_len);
+}
+
+static __always_inline int syncookie_handle_syn(struct header_pointers *hdr,
+ void *ctx,
+ void *data, void *data_end,
+ bool xdp)
+{
+ __u32 old_pkt_size, new_pkt_size;
+ /* Unlike clang 10, clang 11 and 12 generate code that doesn't pass the
+ * BPF verifier if tsopt is not volatile. Volatile forces it to store
+ * the pointer value and use it directly, otherwise tcp_mkoptions is
+ * (mis)compiled like this:
+ * if (!tsopt)
+ * return buf - start;
+ * reg = stored_return_value_of_tscookie_init;
+ * if (reg)
+ * tsopt = tsopt_buf;
+ * else
+ * tsopt = NULL;
+ * ...
+ * *buf++ = tsopt[1];
+ * It creates a dead branch where tsopt is assigned NULL, but the
+ * verifier can't prove it's dead and blocks the program.
+ */
+ __be32 * volatile tsopt = NULL;
+ __be32 tsopt_buf[2] = {};
+ __u16 ip_len;
+ __u32 cookie;
+ __s64 value;
+
+ /* Checksum is not yet verified, but both checksum failure and TCP
+ * header checks return XDP_DROP, so the order doesn't matter.
+ */
+ if (hdr->tcp->fin || hdr->tcp->rst)
+ return XDP_DROP;
+
+ /* Issue SYN cookies on allowed ports, drop SYN packets on blocked
+ * ports.
+ */
+ if (!check_port_allowed(bpf_ntohs(hdr->tcp->dest)))
+ return XDP_DROP;
+
+ if (hdr->ipv4) {
+ /* Check the IPv4 and TCP checksums before creating a SYNACK. */
+ value = bpf_csum_diff(0, 0, (void *)hdr->ipv4, hdr->ipv4->ihl * 4, 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ if (csum_fold(value) != 0)
+ return XDP_DROP; /* Bad IPv4 checksum. */
+
+ value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ if (csum_tcpudp_magic(hdr->ipv4->saddr, hdr->ipv4->daddr,
+ hdr->tcp_len, IPPROTO_TCP, value) != 0)
+ return XDP_DROP; /* Bad TCP checksum. */
+
+ ip_len = sizeof(*hdr->ipv4);
+
+ value = bpf_tcp_raw_gen_syncookie_ipv4(hdr->ipv4, hdr->tcp,
+ hdr->tcp_len);
+ } else if (hdr->ipv6) {
+ /* Check the TCP checksum before creating a SYNACK. */
+ value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ if (csum_ipv6_magic(&hdr->ipv6->saddr, &hdr->ipv6->daddr,
+ hdr->tcp_len, IPPROTO_TCP, value) != 0)
+ return XDP_DROP; /* Bad TCP checksum. */
+
+ ip_len = sizeof(*hdr->ipv6);
+
+ value = bpf_tcp_raw_gen_syncookie_ipv6(hdr->ipv6, hdr->tcp,
+ hdr->tcp_len);
+ } else {
+ return XDP_ABORTED;
+ }
+
+ if (value < 0)
+ return XDP_ABORTED;
+ cookie = (__u32)value;
+
+ if (tscookie_init((void *)hdr->tcp, hdr->tcp_len,
+ &tsopt_buf[0], &tsopt_buf[1], data_end))
+ tsopt = tsopt_buf;
+
+ /* Check that there is enough space for a SYNACK. It also covers
+ * the check that the destination of the __builtin_memmove below
+ * doesn't overflow.
+ */
+ if (data + sizeof(*hdr->eth) + ip_len + TCP_MAXLEN > data_end)
+ return XDP_ABORTED;
+
+ if (hdr->ipv4) {
+ if (hdr->ipv4->ihl * 4 > sizeof(*hdr->ipv4)) {
+ struct tcphdr *new_tcp_header;
+
+ new_tcp_header = data + sizeof(*hdr->eth) + sizeof(*hdr->ipv4);
+ __builtin_memmove(new_tcp_header, hdr->tcp, sizeof(*hdr->tcp));
+ hdr->tcp = new_tcp_header;
+
+ hdr->ipv4->ihl = sizeof(*hdr->ipv4) / 4;
+ }
+
+ tcpv4_gen_synack(hdr, cookie, tsopt);
+ } else if (hdr->ipv6) {
+ tcpv6_gen_synack(hdr, cookie, tsopt);
+ } else {
+ return XDP_ABORTED;
+ }
+
+ /* Recalculate checksums. */
+ hdr->tcp->check = 0;
+ value = bpf_csum_diff(0, 0, (void *)hdr->tcp, hdr->tcp_len, 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ if (hdr->ipv4) {
+ hdr->tcp->check = csum_tcpudp_magic(hdr->ipv4->saddr,
+ hdr->ipv4->daddr,
+ hdr->tcp_len,
+ IPPROTO_TCP,
+ value);
+
+ hdr->ipv4->check = 0;
+ value = bpf_csum_diff(0, 0, (void *)hdr->ipv4, sizeof(*hdr->ipv4), 0);
+ if (value < 0)
+ return XDP_ABORTED;
+ hdr->ipv4->check = csum_fold(value);
+ } else if (hdr->ipv6) {
+ hdr->tcp->check = csum_ipv6_magic(&hdr->ipv6->saddr,
+ &hdr->ipv6->daddr,
+ hdr->tcp_len,
+ IPPROTO_TCP,
+ value);
+ } else {
+ return XDP_ABORTED;
+ }
+
+ /* Set the new packet size. */
+ old_pkt_size = data_end - data;
+ new_pkt_size = sizeof(*hdr->eth) + ip_len + hdr->tcp->doff * 4;
+ if (xdp) {
+ if (bpf_xdp_adjust_tail(ctx, new_pkt_size - old_pkt_size))
+ return XDP_ABORTED;
+ } else {
+ if (bpf_skb_change_tail(ctx, new_pkt_size, 0))
+ return XDP_ABORTED;
+ }
+
+ values_inc_synacks();
+
+ return XDP_TX;
+}
+
+static __always_inline int syncookie_handle_ack(struct header_pointers *hdr)
+{
+ int err;
+
+ if (hdr->tcp->rst)
+ return XDP_DROP;
+
+ if (hdr->ipv4)
+ err = bpf_tcp_raw_check_syncookie_ipv4(hdr->ipv4, hdr->tcp);
+ else if (hdr->ipv6)
+ err = bpf_tcp_raw_check_syncookie_ipv6(hdr->ipv6, hdr->tcp);
+ else
+ return XDP_ABORTED;
+ if (err)
+ return XDP_DROP;
+
+ return XDP_PASS;
+}
+
+static __always_inline int syncookie_part1(void *ctx, void *data, void *data_end,
+ struct header_pointers *hdr, bool xdp)
+{
+ struct bpf_ct_opts ct_lookup_opts = {
+ .netns_id = BPF_F_CURRENT_NETNS,
+ .l4proto = IPPROTO_TCP,
+ };
+ int ret;
+
+ ret = tcp_dissect(data, data_end, hdr);
+ if (ret != XDP_TX)
+ return ret;
+
+ ret = tcp_lookup(ctx, hdr, xdp);
+ if (ret != XDP_TX)
+ return ret;
+
+ /* Packet is TCP and doesn't belong to an established connection. */
+
+ if ((hdr->tcp->syn ^ hdr->tcp->ack) != 1)
+ return XDP_DROP;
+
+ /* Grow the TCP header to TCP_MAXLEN to be able to pass any hdr->tcp_len
+ * to bpf_tcp_raw_gen_syncookie_ipv{4,6} and pass the verifier.
+ */
+ if (xdp) {
+ if (bpf_xdp_adjust_tail(ctx, TCP_MAXLEN - hdr->tcp_len))
+ return XDP_ABORTED;
+ } else {
+ /* Without volatile the verifier throws this error:
+ * R9 32-bit pointer arithmetic prohibited
+ */
+ volatile u64 old_len = data_end - data;
+
+ if (bpf_skb_change_tail(ctx, old_len + TCP_MAXLEN - hdr->tcp_len, 0))
+ return XDP_ABORTED;
+ }
+
+ return XDP_TX;
+}
+
+static __always_inline int syncookie_part2(void *ctx, void *data, void *data_end,
+ struct header_pointers *hdr, bool xdp)
+{
+ if (hdr->ipv4) {
+ hdr->eth = data;
+ hdr->ipv4 = (void *)hdr->eth + sizeof(*hdr->eth);
+ /* IPV4_MAXLEN is needed when calculating checksum.
+ * At least sizeof(struct iphdr) is needed here to access ihl.
+ */
+ if ((void *)hdr->ipv4 + IPV4_MAXLEN > data_end)
+ return XDP_ABORTED;
+ hdr->tcp = (void *)hdr->ipv4 + hdr->ipv4->ihl * 4;
+ } else if (hdr->ipv6) {
+ hdr->eth = data;
+ hdr->ipv6 = (void *)hdr->eth + sizeof(*hdr->eth);
+ hdr->tcp = (void *)hdr->ipv6 + sizeof(*hdr->ipv6);
+ } else {
+ return XDP_ABORTED;
+ }
+
+ if ((void *)hdr->tcp + TCP_MAXLEN > data_end)
+ return XDP_ABORTED;
+
+ /* We run out of registers, tcp_len gets spilled to the stack, and the
+ * verifier forgets its min and max values checked above in tcp_dissect.
+ */
+ hdr->tcp_len = hdr->tcp->doff * 4;
+ if (hdr->tcp_len < sizeof(*hdr->tcp))
+ return XDP_ABORTED;
+
+ return hdr->tcp->syn ? syncookie_handle_syn(hdr, ctx, data, data_end, xdp) :
+ syncookie_handle_ack(hdr);
+}
+
+SEC("xdp")
+int syncookie_xdp(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct header_pointers hdr;
+ int ret;
+
+ ret = syncookie_part1(ctx, data, data_end, &hdr, true);
+ if (ret != XDP_TX)
+ return ret;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ return syncookie_part2(ctx, data, data_end, &hdr, true);
+}
+
+SEC("tc")
+int syncookie_tc(struct __sk_buff *skb)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ struct header_pointers hdr;
+ int ret;
+
+ ret = syncookie_part1(skb, data, data_end, &hdr, false);
+ if (ret != XDP_TX)
+ return ret == XDP_PASS ? TC_ACT_OK : TC_ACT_SHOT;
+
+ data_end = (void *)(long)skb->data_end;
+ data = (void *)(long)skb->data;
+
+ ret = syncookie_part2(skb, data, data_end, &hdr, false);
+ switch (ret) {
+ case XDP_PASS:
+ return TC_ACT_OK;
+ case XDP_TX:
+ return bpf_redirect(skb->ifindex, 0);
+ default:
+ return TC_ACT_SHOT;
+ }
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
index c0e7acd698ed..e443e6542cb9 100755
--- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py
+++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
@@ -58,7 +58,7 @@ class BlockParser(object):
class ArrayParser(BlockParser):
"""
- A parser for extracting dicionaries of values from some BPF-related arrays.
+ A parser for extracting a set of values from some BPF-related arrays.
@reader: a pointer to the open file to parse
@array_name: name of the array to parse
"""
@@ -66,7 +66,7 @@ class ArrayParser(BlockParser):
def __init__(self, reader, array_name):
self.array_name = array_name
- self.start_marker = re.compile(f'(static )?const char \* const {self.array_name}\[.*\] = {{\n')
+ self.start_marker = re.compile(f'(static )?const bool {self.array_name}\[.*\] = {{\n')
super().__init__(reader)
def search_block(self):
@@ -80,15 +80,15 @@ class ArrayParser(BlockParser):
Parse a block and return data as a dictionary. Items to extract must be
on separate lines in the file.
"""
- pattern = re.compile('\[(BPF_\w*)\]\s*= "(.*)",?$')
- entries = {}
+ pattern = re.compile('\[(BPF_\w*)\]\s*= (true|false),?$')
+ entries = set()
while True:
line = self.reader.readline()
if line == '' or re.match(self.end_marker, line):
break
capture = pattern.search(line)
if capture:
- entries[capture.group(1)] = capture.group(2)
+ entries |= {capture.group(1)}
return entries
class InlineListParser(BlockParser):
@@ -115,7 +115,7 @@ class InlineListParser(BlockParser):
class FileExtractor(object):
"""
A generic reader for extracting data from a given file. This class contains
- several helper methods that wrap arround parser objects to extract values
+ several helper methods that wrap around parser objects to extract values
from different structures.
This class does not offer a way to set a filename, which is expected to be
defined in children classes.
@@ -139,21 +139,19 @@ class FileExtractor(object):
def get_types_from_array(self, array_name):
"""
- Search for and parse an array associating names to BPF_* enum members,
- for example:
+ Search for and parse a list of allowed BPF_* enum members, for example:
- const char * const prog_type_name[] = {
- [BPF_PROG_TYPE_UNSPEC] = "unspec",
- [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter",
- [BPF_PROG_TYPE_KPROBE] = "kprobe",
+ const bool prog_type_name[] = {
+ [BPF_PROG_TYPE_UNSPEC] = true,
+ [BPF_PROG_TYPE_SOCKET_FILTER] = true,
+ [BPF_PROG_TYPE_KPROBE] = true,
};
- Return a dictionary with the enum member names as keys and the
- associated names as values, for example:
+ Return a set of the enum members, for example:
- {'BPF_PROG_TYPE_UNSPEC': 'unspec',
- 'BPF_PROG_TYPE_SOCKET_FILTER': 'socket_filter',
- 'BPF_PROG_TYPE_KPROBE': 'kprobe'}
+ {'BPF_PROG_TYPE_UNSPEC',
+ 'BPF_PROG_TYPE_SOCKET_FILTER',
+ 'BPF_PROG_TYPE_KPROBE'}
@array_name: name of the array to parse
"""
@@ -186,6 +184,27 @@ class FileExtractor(object):
parser.search_block(start_marker)
return parser.parse(pattern, end_marker)
+ def make_enum_map(self, names, enum_prefix):
+ """
+ Search for and parse an enum containing BPF_* members, just as get_enum
+ does. However, instead of just returning a set of the variant names,
+ also generate a textual representation from them by (assuming and)
+ removing a provided prefix and lowercasing the remainder. Then return a
+ dict mapping from name to textual representation.
+
+ @enum_values: a set of enum values; e.g., as retrieved by get_enum
+ @enum_prefix: the prefix to remove from each of the variants to infer
+ textual representation
+ """
+ mapping = {}
+ for name in names:
+ if not name.startswith(enum_prefix):
+ raise Exception(f"enum variant {name} does not start with {enum_prefix}")
+ text = name[len(enum_prefix):].lower()
+ mapping[name] = text
+
+ return mapping
+
def __get_description_list(self, start_marker, pattern, end_marker):
parser = InlineListParser(self.reader)
parser.search_block(start_marker)
@@ -333,11 +352,9 @@ class ProgFileExtractor(SourceFileExtractor):
"""
filename = os.path.join(BPFTOOL_DIR, 'prog.c')
- def get_prog_types(self):
- return self.get_types_from_array('prog_type_name')
-
def get_attach_types(self):
- return self.get_types_from_array('attach_type_strings')
+ types = self.get_types_from_array('attach_types')
+ return self.make_enum_map(types, 'BPF_')
def get_prog_attach_help(self):
return self.get_help_list('ATTACH_TYPE')
@@ -348,9 +365,6 @@ class MapFileExtractor(SourceFileExtractor):
"""
filename = os.path.join(BPFTOOL_DIR, 'map.c')
- def get_map_types(self):
- return self.get_types_from_array('map_type_name')
-
def get_map_help(self):
return self.get_help_list('TYPE')
@@ -363,30 +377,6 @@ class CgroupFileExtractor(SourceFileExtractor):
def get_prog_attach_help(self):
return self.get_help_list('ATTACH_TYPE')
-class CommonFileExtractor(SourceFileExtractor):
- """
- An extractor for bpftool's common.c.
- """
- filename = os.path.join(BPFTOOL_DIR, 'common.c')
-
- def __init__(self):
- super().__init__()
- self.attach_types = {}
-
- def get_attach_types(self):
- if not self.attach_types:
- self.attach_types = self.get_types_from_array('attach_type_name')
- return self.attach_types
-
- def get_cgroup_attach_types(self):
- if not self.attach_types:
- self.get_attach_types()
- cgroup_types = {}
- for (key, value) in self.attach_types.items():
- if key.find('BPF_CGROUP') != -1:
- cgroup_types[key] = value
- return cgroup_types
-
class GenericSourceExtractor(SourceFileExtractor):
"""
An extractor for generic source code files.
@@ -403,14 +393,28 @@ class BpfHeaderExtractor(FileExtractor):
"""
filename = os.path.join(INCLUDE_DIR, 'uapi/linux/bpf.h')
+ def __init__(self):
+ super().__init__()
+ self.attach_types = {}
+
def get_prog_types(self):
return self.get_enum('bpf_prog_type')
- def get_map_types(self):
- return self.get_enum('bpf_map_type')
+ def get_map_type_map(self):
+ names = self.get_enum('bpf_map_type')
+ return self.make_enum_map(names, 'BPF_MAP_TYPE_')
- def get_attach_types(self):
- return self.get_enum('bpf_attach_type')
+ def get_attach_type_map(self):
+ if not self.attach_types:
+ names = self.get_enum('bpf_attach_type')
+ self.attach_types = self.make_enum_map(names, 'BPF_')
+ return self.attach_types
+
+ def get_cgroup_attach_type_map(self):
+ if not self.attach_types:
+ self.get_attach_type_map()
+ return {name: text for name, text in self.attach_types.items()
+ if name.startswith('BPF_CGROUP')}
class ManPageExtractor(FileExtractor):
"""
@@ -495,21 +499,12 @@ def main():
""")
args = argParser.parse_args()
- # Map types (enum)
-
bpf_info = BpfHeaderExtractor()
- ref = bpf_info.get_map_types()
-
- map_info = MapFileExtractor()
- source_map_items = map_info.get_map_types()
- map_types_enum = set(source_map_items.keys())
-
- verify(ref, map_types_enum,
- f'Comparing BPF header (enum bpf_map_type) and {MapFileExtractor.filename} (map_type_name):')
# Map types (names)
- source_map_types = set(source_map_items.values())
+ map_info = MapFileExtractor()
+ source_map_types = set(bpf_info.get_map_type_map().values())
source_map_types.discard('unspec')
help_map_types = map_info.get_map_help()
@@ -525,37 +520,17 @@ def main():
bashcomp_map_types = bashcomp_info.get_map_types()
verify(source_map_types, help_map_types,
- f'Comparing {MapFileExtractor.filename} (map_type_name) and {MapFileExtractor.filename} (do_help() TYPE):')
+ f'Comparing {BpfHeaderExtractor.filename} (bpf_map_type) and {MapFileExtractor.filename} (do_help() TYPE):')
verify(source_map_types, man_map_types,
- f'Comparing {MapFileExtractor.filename} (map_type_name) and {ManMapExtractor.filename} (TYPE):')
+ f'Comparing {BpfHeaderExtractor.filename} (bpf_map_type) and {ManMapExtractor.filename} (TYPE):')
verify(help_map_options, man_map_options,
f'Comparing {MapFileExtractor.filename} (do_help() OPTIONS) and {ManMapExtractor.filename} (OPTIONS):')
verify(source_map_types, bashcomp_map_types,
- f'Comparing {MapFileExtractor.filename} (map_type_name) and {BashcompExtractor.filename} (BPFTOOL_MAP_CREATE_TYPES):')
-
- # Program types (enum)
-
- ref = bpf_info.get_prog_types()
-
- prog_info = ProgFileExtractor()
- prog_types = set(prog_info.get_prog_types().keys())
-
- verify(ref, prog_types,
- f'Comparing BPF header (enum bpf_prog_type) and {ProgFileExtractor.filename} (prog_type_name):')
-
- # Attach types (enum)
-
- ref = bpf_info.get_attach_types()
- bpf_info.close()
-
- common_info = CommonFileExtractor()
- attach_types = common_info.get_attach_types()
-
- verify(ref, attach_types,
- f'Comparing BPF header (enum bpf_attach_type) and {CommonFileExtractor.filename} (attach_type_name):')
+ f'Comparing {BpfHeaderExtractor.filename} (bpf_map_type) and {BashcompExtractor.filename} (BPFTOOL_MAP_CREATE_TYPES):')
# Attach types (names)
+ prog_info = ProgFileExtractor()
source_prog_attach_types = set(prog_info.get_attach_types().values())
help_prog_attach_types = prog_info.get_prog_attach_help()
@@ -571,18 +546,17 @@ def main():
bashcomp_prog_attach_types = bashcomp_info.get_prog_attach_types()
verify(source_prog_attach_types, help_prog_attach_types,
- f'Comparing {ProgFileExtractor.filename} (attach_type_strings) and {ProgFileExtractor.filename} (do_help() ATTACH_TYPE):')
+ f'Comparing {ProgFileExtractor.filename} (bpf_attach_type) and {ProgFileExtractor.filename} (do_help() ATTACH_TYPE):')
verify(source_prog_attach_types, man_prog_attach_types,
- f'Comparing {ProgFileExtractor.filename} (attach_type_strings) and {ManProgExtractor.filename} (ATTACH_TYPE):')
+ f'Comparing {ProgFileExtractor.filename} (bpf_attach_type) and {ManProgExtractor.filename} (ATTACH_TYPE):')
verify(help_prog_options, man_prog_options,
f'Comparing {ProgFileExtractor.filename} (do_help() OPTIONS) and {ManProgExtractor.filename} (OPTIONS):')
verify(source_prog_attach_types, bashcomp_prog_attach_types,
- f'Comparing {ProgFileExtractor.filename} (attach_type_strings) and {BashcompExtractor.filename} (BPFTOOL_PROG_ATTACH_TYPES):')
+ f'Comparing {ProgFileExtractor.filename} (bpf_attach_type) and {BashcompExtractor.filename} (BPFTOOL_PROG_ATTACH_TYPES):')
# Cgroup attach types
-
- source_cgroup_attach_types = set(common_info.get_cgroup_attach_types().values())
- common_info.close()
+ source_cgroup_attach_types = set(bpf_info.get_cgroup_attach_type_map().values())
+ bpf_info.close()
cgroup_info = CgroupFileExtractor()
help_cgroup_attach_types = cgroup_info.get_prog_attach_help()
@@ -598,13 +572,13 @@ def main():
bashcomp_info.close()
verify(source_cgroup_attach_types, help_cgroup_attach_types,
- f'Comparing {CommonFileExtractor.filename} (attach_type_strings) and {CgroupFileExtractor.filename} (do_help() ATTACH_TYPE):')
+ f'Comparing {BpfHeaderExtractor.filename} (bpf_attach_type) and {CgroupFileExtractor.filename} (do_help() ATTACH_TYPE):')
verify(source_cgroup_attach_types, man_cgroup_attach_types,
- f'Comparing {CommonFileExtractor.filename} (attach_type_strings) and {ManCgroupExtractor.filename} (ATTACH_TYPE):')
+ f'Comparing {BpfHeaderExtractor.filename} (bpf_attach_type) and {ManCgroupExtractor.filename} (ATTACH_TYPE):')
verify(help_cgroup_options, man_cgroup_options,
f'Comparing {CgroupFileExtractor.filename} (do_help() OPTIONS) and {ManCgroupExtractor.filename} (OPTIONS):')
verify(source_cgroup_attach_types, bashcomp_cgroup_attach_types,
- f'Comparing {CommonFileExtractor.filename} (attach_type_strings) and {BashcompExtractor.filename} (BPFTOOL_CGROUP_ATTACH_TYPES):')
+ f'Comparing {BpfHeaderExtractor.filename} (bpf_attach_type) and {BashcompExtractor.filename} (BPFTOOL_CGROUP_ATTACH_TYPES):')
# Options for remaining commands
diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h
index 128989bed8b7..38782bd47fdc 100644
--- a/tools/testing/selftests/bpf/test_btf.h
+++ b/tools/testing/selftests/bpf/test_btf.h
@@ -39,6 +39,7 @@
#define BTF_MEMBER_ENC(name, type, bits_offset) \
(name), (type), (bits_offset)
#define BTF_ENUM_ENC(name, val) (name), (val)
+#define BTF_ENUM64_ENC(name, val_lo32, val_hi32) (name), (val_lo32), (val_hi32)
#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \
((bitfield_size) << 24 | (bits_offset))
diff --git a/tools/testing/selftests/bpf/test_xdping.sh b/tools/testing/selftests/bpf/test_xdping.sh
index c2f0ddb45531..c3d82e0a7378 100755
--- a/tools/testing/selftests/bpf/test_xdping.sh
+++ b/tools/testing/selftests/bpf/test_xdping.sh
@@ -95,5 +95,9 @@ for server_args in "" "-I veth0 -s -S" ; do
test "$client_args" "$server_args"
done
+# Test drv mode
+test "-I veth1 -N" "-I veth0 -s -N"
+test "-I veth1 -N -c 10" "-I veth0 -s -N"
+
echo "OK. All tests passed"
exit 0
diff --git a/tools/testing/selftests/bpf/xdp_synproxy.c b/tools/testing/selftests/bpf/xdp_synproxy.c
new file mode 100644
index 000000000000..d874ddfb39c4
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_synproxy.c
@@ -0,0 +1,466 @@
+// SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <stdnoreturn.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <getopt.h>
+#include <signal.h>
+#include <sys/types.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <net/if.h>
+#include <linux/if_link.h>
+#include <linux/limits.h>
+
+static unsigned int ifindex;
+static __u32 attached_prog_id;
+static bool attached_tc;
+
+static void noreturn cleanup(int sig)
+{
+ LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
+ int prog_fd;
+ int err;
+
+ if (attached_prog_id == 0)
+ exit(0);
+
+ if (attached_tc) {
+ LIBBPF_OPTS(bpf_tc_hook, hook,
+ .ifindex = ifindex,
+ .attach_point = BPF_TC_INGRESS);
+
+ err = bpf_tc_hook_destroy(&hook);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_tc_hook_destroy: %s\n", strerror(-err));
+ fprintf(stderr, "Failed to destroy the TC hook\n");
+ exit(1);
+ }
+ exit(0);
+ }
+
+ prog_fd = bpf_prog_get_fd_by_id(attached_prog_id);
+ if (prog_fd < 0) {
+ fprintf(stderr, "Error: bpf_prog_get_fd_by_id: %s\n", strerror(-prog_fd));
+ err = bpf_xdp_attach(ifindex, -1, 0, NULL);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_set_link_xdp_fd: %s\n", strerror(-err));
+ fprintf(stderr, "Failed to detach XDP program\n");
+ exit(1);
+ }
+ } else {
+ opts.old_prog_fd = prog_fd;
+ err = bpf_xdp_attach(ifindex, -1, XDP_FLAGS_REPLACE, &opts);
+ close(prog_fd);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_set_link_xdp_fd_opts: %s\n", strerror(-err));
+ /* Not an error if already replaced by someone else. */
+ if (err != -EEXIST) {
+ fprintf(stderr, "Failed to detach XDP program\n");
+ exit(1);
+ }
+ }
+ }
+ exit(0);
+}
+
+static noreturn void usage(const char *progname)
+{
+ fprintf(stderr, "Usage: %s [--iface <iface>|--prog <prog_id>] [--mss4 <mss ipv4> --mss6 <mss ipv6> --wscale <wscale> --ttl <ttl>] [--ports <port1>,<port2>,...] [--single] [--tc]\n",
+ progname);
+ exit(1);
+}
+
+static unsigned long parse_arg_ul(const char *progname, const char *arg, unsigned long limit)
+{
+ unsigned long res;
+ char *endptr;
+
+ errno = 0;
+ res = strtoul(arg, &endptr, 10);
+ if (errno != 0 || *endptr != '\0' || arg[0] == '\0' || res > limit)
+ usage(progname);
+
+ return res;
+}
+
+static void parse_options(int argc, char *argv[], unsigned int *ifindex, __u32 *prog_id,
+ __u64 *tcpipopts, char **ports, bool *single, bool *tc)
+{
+ static struct option long_options[] = {
+ { "help", no_argument, NULL, 'h' },
+ { "iface", required_argument, NULL, 'i' },
+ { "prog", required_argument, NULL, 'x' },
+ { "mss4", required_argument, NULL, 4 },
+ { "mss6", required_argument, NULL, 6 },
+ { "wscale", required_argument, NULL, 'w' },
+ { "ttl", required_argument, NULL, 't' },
+ { "ports", required_argument, NULL, 'p' },
+ { "single", no_argument, NULL, 's' },
+ { "tc", no_argument, NULL, 'c' },
+ { NULL, 0, NULL, 0 },
+ };
+ unsigned long mss4, mss6, wscale, ttl;
+ unsigned int tcpipopts_mask = 0;
+
+ if (argc < 2)
+ usage(argv[0]);
+
+ *ifindex = 0;
+ *prog_id = 0;
+ *tcpipopts = 0;
+ *ports = NULL;
+ *single = false;
+
+ while (true) {
+ int opt;
+
+ opt = getopt_long(argc, argv, "", long_options, NULL);
+ if (opt == -1)
+ break;
+
+ switch (opt) {
+ case 'h':
+ usage(argv[0]);
+ break;
+ case 'i':
+ *ifindex = if_nametoindex(optarg);
+ if (*ifindex == 0)
+ usage(argv[0]);
+ break;
+ case 'x':
+ *prog_id = parse_arg_ul(argv[0], optarg, UINT32_MAX);
+ if (*prog_id == 0)
+ usage(argv[0]);
+ break;
+ case 4:
+ mss4 = parse_arg_ul(argv[0], optarg, UINT16_MAX);
+ tcpipopts_mask |= 1 << 0;
+ break;
+ case 6:
+ mss6 = parse_arg_ul(argv[0], optarg, UINT16_MAX);
+ tcpipopts_mask |= 1 << 1;
+ break;
+ case 'w':
+ wscale = parse_arg_ul(argv[0], optarg, 14);
+ tcpipopts_mask |= 1 << 2;
+ break;
+ case 't':
+ ttl = parse_arg_ul(argv[0], optarg, UINT8_MAX);
+ tcpipopts_mask |= 1 << 3;
+ break;
+ case 'p':
+ *ports = optarg;
+ break;
+ case 's':
+ *single = true;
+ break;
+ case 'c':
+ *tc = true;
+ break;
+ default:
+ usage(argv[0]);
+ }
+ }
+ if (optind < argc)
+ usage(argv[0]);
+
+ if (tcpipopts_mask == 0xf) {
+ if (mss4 == 0 || mss6 == 0 || wscale == 0 || ttl == 0)
+ usage(argv[0]);
+ *tcpipopts = (mss6 << 32) | (ttl << 24) | (wscale << 16) | mss4;
+ } else if (tcpipopts_mask != 0) {
+ usage(argv[0]);
+ }
+
+ if (*ifindex != 0 && *prog_id != 0)
+ usage(argv[0]);
+ if (*ifindex == 0 && *prog_id == 0)
+ usage(argv[0]);
+}
+
+static int syncookie_attach(const char *argv0, unsigned int ifindex, bool tc)
+{
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ char xdp_filename[PATH_MAX];
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int prog_fd;
+ int err;
+
+ snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv0);
+ obj = bpf_object__open_file(xdp_filename, NULL);
+ err = libbpf_get_error(obj);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_object__open_file: %s\n", strerror(-err));
+ return err;
+ }
+
+ err = bpf_object__load(obj);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_object__open_file: %s\n", strerror(-err));
+ return err;
+ }
+
+ prog = bpf_object__find_program_by_name(obj, tc ? "syncookie_tc" : "syncookie_xdp");
+ if (!prog) {
+ fprintf(stderr, "Error: bpf_object__find_program_by_name: program was not found\n");
+ return -ENOENT;
+ }
+
+ prog_fd = bpf_program__fd(prog);
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+ goto out;
+ }
+ attached_tc = tc;
+ attached_prog_id = info.id;
+ signal(SIGINT, cleanup);
+ signal(SIGTERM, cleanup);
+ if (tc) {
+ LIBBPF_OPTS(bpf_tc_hook, hook,
+ .ifindex = ifindex,
+ .attach_point = BPF_TC_INGRESS);
+ LIBBPF_OPTS(bpf_tc_opts, opts,
+ .handle = 1,
+ .priority = 1,
+ .prog_fd = prog_fd);
+
+ err = bpf_tc_hook_create(&hook);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_tc_hook_create: %s\n",
+ strerror(-err));
+ goto fail;
+ }
+ err = bpf_tc_attach(&hook, &opts);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_tc_attach: %s\n",
+ strerror(-err));
+ goto fail;
+ }
+
+ } else {
+ err = bpf_xdp_attach(ifindex, prog_fd,
+ XDP_FLAGS_UPDATE_IF_NOEXIST, NULL);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_set_link_xdp_fd: %s\n",
+ strerror(-err));
+ goto fail;
+ }
+ }
+ err = 0;
+out:
+ bpf_object__close(obj);
+ return err;
+fail:
+ signal(SIGINT, SIG_DFL);
+ signal(SIGTERM, SIG_DFL);
+ attached_prog_id = 0;
+ goto out;
+}
+
+static int syncookie_open_bpf_maps(__u32 prog_id, int *values_map_fd, int *ports_map_fd)
+{
+ struct bpf_prog_info prog_info;
+ __u32 map_ids[8];
+ __u32 info_len;
+ int prog_fd;
+ int err;
+ int i;
+
+ *values_map_fd = -1;
+ *ports_map_fd = -1;
+
+ prog_fd = bpf_prog_get_fd_by_id(prog_id);
+ if (prog_fd < 0) {
+ fprintf(stderr, "Error: bpf_prog_get_fd_by_id: %s\n", strerror(-prog_fd));
+ return prog_fd;
+ }
+
+ prog_info = (struct bpf_prog_info) {
+ .nr_map_ids = 8,
+ .map_ids = (__u64)map_ids,
+ };
+ info_len = sizeof(prog_info);
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+ goto out;
+ }
+
+ if (prog_info.nr_map_ids < 2) {
+ fprintf(stderr, "Error: Found %u BPF maps, expected at least 2\n",
+ prog_info.nr_map_ids);
+ err = -ENOENT;
+ goto out;
+ }
+
+ for (i = 0; i < prog_info.nr_map_ids; i++) {
+ struct bpf_map_info map_info = {};
+ int map_fd;
+
+ err = bpf_map_get_fd_by_id(map_ids[i]);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_map_get_fd_by_id: %s\n", strerror(-err));
+ goto err_close_map_fds;
+ }
+ map_fd = err;
+
+ info_len = sizeof(map_info);
+ err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+ close(map_fd);
+ goto err_close_map_fds;
+ }
+ if (strcmp(map_info.name, "values") == 0) {
+ *values_map_fd = map_fd;
+ continue;
+ }
+ if (strcmp(map_info.name, "allowed_ports") == 0) {
+ *ports_map_fd = map_fd;
+ continue;
+ }
+ close(map_fd);
+ }
+
+ if (*values_map_fd != -1 && *ports_map_fd != -1) {
+ err = 0;
+ goto out;
+ }
+
+ err = -ENOENT;
+
+err_close_map_fds:
+ if (*values_map_fd != -1)
+ close(*values_map_fd);
+ if (*ports_map_fd != -1)
+ close(*ports_map_fd);
+ *values_map_fd = -1;
+ *ports_map_fd = -1;
+
+out:
+ close(prog_fd);
+ return err;
+}
+
+int main(int argc, char *argv[])
+{
+ int values_map_fd, ports_map_fd;
+ __u64 tcpipopts;
+ bool firstiter;
+ __u64 prevcnt;
+ __u32 prog_id;
+ char *ports;
+ bool single;
+ int err = 0;
+ bool tc;
+
+ parse_options(argc, argv, &ifindex, &prog_id, &tcpipopts, &ports,
+ &single, &tc);
+
+ if (prog_id == 0) {
+ if (!tc) {
+ err = bpf_xdp_query_id(ifindex, 0, &prog_id);
+ if (err < 0) {
+ fprintf(stderr, "Error: bpf_get_link_xdp_id: %s\n",
+ strerror(-err));
+ goto out;
+ }
+ }
+ if (prog_id == 0) {
+ err = syncookie_attach(argv[0], ifindex, tc);
+ if (err < 0)
+ goto out;
+ prog_id = attached_prog_id;
+ }
+ }
+
+ err = syncookie_open_bpf_maps(prog_id, &values_map_fd, &ports_map_fd);
+ if (err < 0)
+ goto out;
+
+ if (ports) {
+ __u16 port_last = 0;
+ __u32 port_idx = 0;
+ char *p = ports;
+
+ fprintf(stderr, "Replacing allowed ports\n");
+
+ while (p && *p != '\0') {
+ char *token = strsep(&p, ",");
+ __u16 port;
+
+ port = parse_arg_ul(argv[0], token, UINT16_MAX);
+ err = bpf_map_update_elem(ports_map_fd, &port_idx, &port, BPF_ANY);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_map_update_elem: %s\n", strerror(-err));
+ fprintf(stderr, "Failed to add port %u (index %u)\n",
+ port, port_idx);
+ goto out_close_maps;
+ }
+ fprintf(stderr, "Added port %u\n", port);
+ port_idx++;
+ }
+ err = bpf_map_update_elem(ports_map_fd, &port_idx, &port_last, BPF_ANY);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_map_update_elem: %s\n", strerror(-err));
+ fprintf(stderr, "Failed to add the terminator value 0 (index %u)\n",
+ port_idx);
+ goto out_close_maps;
+ }
+ }
+
+ if (tcpipopts) {
+ __u32 key = 0;
+
+ fprintf(stderr, "Replacing TCP/IP options\n");
+
+ err = bpf_map_update_elem(values_map_fd, &key, &tcpipopts, BPF_ANY);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_map_update_elem: %s\n", strerror(-err));
+ goto out_close_maps;
+ }
+ }
+
+ if ((ports || tcpipopts) && attached_prog_id == 0 && !single)
+ goto out_close_maps;
+
+ prevcnt = 0;
+ firstiter = true;
+ while (true) {
+ __u32 key = 1;
+ __u64 value;
+
+ err = bpf_map_lookup_elem(values_map_fd, &key, &value);
+ if (err != 0) {
+ fprintf(stderr, "Error: bpf_map_lookup_elem: %s\n", strerror(-err));
+ goto out_close_maps;
+ }
+ if (firstiter) {
+ prevcnt = value;
+ firstiter = false;
+ }
+ if (single) {
+ printf("Total SYNACKs generated: %llu\n", value);
+ break;
+ }
+ printf("SYNACKs generated: %llu (total %llu)\n", value - prevcnt, value);
+ prevcnt = value;
+ sleep(1);
+ }
+
+out_close_maps:
+ close(values_map_fd);
+ close(ports_map_fd);
+out:
+ return err == 0 ? 0 : 1;
+}
diff --git a/tools/testing/selftests/dma/Makefile b/tools/testing/selftests/dma/Makefile
index aa8e8b5b3864..cd8c5ece1cba 100644
--- a/tools/testing/selftests/dma/Makefile
+++ b/tools/testing/selftests/dma/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -I../../../../usr/include/
+CFLAGS += -I../../../../include/
TEST_GEN_PROGS := dma_map_benchmark
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
index c3b3c09e995e..5c997f17fcbd 100644
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ b/tools/testing/selftests/dma/dma_map_benchmark.c
@@ -10,8 +10,8 @@
#include <unistd.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
-#include <linux/map_benchmark.h>
#include <linux/types.h>
+#include <linux/map_benchmark.h>
#define NSEC_PER_MSEC 1000000L
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_counter_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_counter_scale.sh
new file mode 100644
index 000000000000..a43a9926e690
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_counter_scale.sh
@@ -0,0 +1,107 @@
+# SPDX-License-Identifier: GPL-2.0
+
+RIF_COUNTER_NUM_NETIFS=2
+
+rif_counter_addr4()
+{
+ local i=$1; shift
+ local p=$1; shift
+
+ printf 192.0.%d.%d $((i / 64)) $(((4 * i % 256) + p))
+}
+
+rif_counter_addr4pfx()
+{
+ rif_counter_addr4 $@
+ printf /30
+}
+
+rif_counter_h1_create()
+{
+ simple_if_init $h1
+}
+
+rif_counter_h1_destroy()
+{
+ simple_if_fini $h1
+}
+
+rif_counter_h2_create()
+{
+ simple_if_init $h2
+}
+
+rif_counter_h2_destroy()
+{
+ simple_if_fini $h2
+}
+
+rif_counter_setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ h2=${NETIFS[p2]}
+
+ vrf_prepare
+
+ rif_counter_h1_create
+ rif_counter_h2_create
+}
+
+rif_counter_cleanup()
+{
+ local count=$1; shift
+
+ pre_cleanup
+
+ for ((i = 1; i <= count; i++)); do
+ vlan_destroy $h2 $i
+ done
+
+ rif_counter_h2_destroy
+ rif_counter_h1_destroy
+
+ vrf_cleanup
+
+ if [[ -v RIF_COUNTER_BATCH_FILE ]]; then
+ rm -f $RIF_COUNTER_BATCH_FILE
+ fi
+}
+
+
+rif_counter_test()
+{
+ local count=$1; shift
+ local should_fail=$1; shift
+
+ RIF_COUNTER_BATCH_FILE="$(mktemp)"
+
+ for ((i = 1; i <= count; i++)); do
+ vlan_create $h2 $i v$h2 $(rif_counter_addr4pfx $i 2)
+ done
+ for ((i = 1; i <= count; i++)); do
+ cat >> $RIF_COUNTER_BATCH_FILE <<-EOF
+ stats set dev $h2.$i l3_stats on
+ EOF
+ done
+
+ ip -b $RIF_COUNTER_BATCH_FILE
+ check_err_fail $should_fail $? "RIF counter enablement"
+}
+
+rif_counter_traffic_test()
+{
+ local count=$1; shift
+ local i;
+
+ for ((i = count; i > 0; i /= 2)); do
+ $MZ $h1 -Q $i -c 1 -d 20msec -p 100 -a own -b $(mac_get $h2) \
+ -A $(rif_counter_addr4 $i 1) \
+ -B $(rif_counter_addr4 $i 2) \
+ -q -t udp sp=54321,dp=12345
+ done
+ for ((i = count; i > 0; i /= 2)); do
+ busywait "$TC_HIT_TIMEOUT" until_counter_is "== 1" \
+ hw_stats_get l3_stats $h2.$i rx packets > /dev/null
+ check_err $? "Traffic not seen at RIF $h2.$i"
+ done
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index e9f65bd2e299..688338bbeb97 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -25,7 +25,16 @@ cleanup()
trap cleanup EXIT
-ALL_TESTS="router tc_flower mirror_gre tc_police port rif_mac_profile"
+ALL_TESTS="
+ router
+ tc_flower
+ mirror_gre
+ tc_police
+ port
+ rif_mac_profile
+ rif_counter
+"
+
for current_test in ${TESTS:-$ALL_TESTS}; do
RET_FIN=0
source ${current_test}_scale.sh
@@ -36,16 +45,32 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
for should_fail in 0 1; do
RET=0
target=$(${current_test}_get_target "$should_fail")
+ if ((target == 0)); then
+ log_test_skip "'$current_test' should_fail=$should_fail test"
+ continue
+ fi
+
${current_test}_setup_prepare
setup_wait $num_netifs
+ # Update target in case occupancy of a certain resource changed
+ # following the test setup.
+ target=$(${current_test}_get_target "$should_fail")
${current_test}_test "$target" "$should_fail"
- ${current_test}_cleanup
- devlink_reload
if [[ "$should_fail" -eq 0 ]]; then
log_test "'$current_test' $target"
+
+ if ((!RET)); then
+ tt=${current_test}_traffic_test
+ if [[ $(type -t $tt) == "function" ]]; then
+ $tt "$target"
+ log_test "'$current_test' $target traffic test"
+ fi
+ fi
else
log_test "'$current_test' overflow $target"
fi
+ ${current_test}_cleanup $target
+ devlink_reload
RET_FIN=$(( RET_FIN || RET ))
done
done
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/rif_counter_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/rif_counter_scale.sh
new file mode 120000
index 000000000000..1f5752e8ffc0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/rif_counter_scale.sh
@@ -0,0 +1 @@
+../spectrum/rif_counter_scale.sh \ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh
index efd798a85931..4444bbace1a9 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower_scale.sh
@@ -4,17 +4,22 @@ source ../tc_flower_scale.sh
tc_flower_get_target()
{
local should_fail=$1; shift
+ local max_cnts
# The driver associates a counter with each tc filter, which means the
# number of supported filters is bounded by the number of available
# counters.
- # Currently, the driver supports 30K (30,720) flow counters and six of
- # these are used for multicast routing.
- local target=30714
+ max_cnts=$(devlink_resource_size_get counters flow)
+
+ # Remove already allocated counters.
+ ((max_cnts -= $(devlink_resource_occ_get counters flow)))
+
+ # Each rule uses two counters, for packets and bytes.
+ ((max_cnts /= 2))
if ((! should_fail)); then
- echo $target
+ echo $max_cnts
else
- echo $((target + 1))
+ echo $((max_cnts + 1))
fi
}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index dea33dc93790..95d9f710a630 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -22,7 +22,16 @@ cleanup()
devlink_sp_read_kvd_defaults
trap cleanup EXIT
-ALL_TESTS="router tc_flower mirror_gre tc_police port rif_mac_profile"
+ALL_TESTS="
+ router
+ tc_flower
+ mirror_gre
+ tc_police
+ port
+ rif_mac_profile
+ rif_counter
+"
+
for current_test in ${TESTS:-$ALL_TESTS}; do
RET_FIN=0
source ${current_test}_scale.sh
@@ -41,15 +50,31 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
for should_fail in 0 1; do
RET=0
target=$(${current_test}_get_target "$should_fail")
+ if ((target == 0)); then
+ log_test_skip "'$current_test' [$profile] should_fail=$should_fail test"
+ continue
+ fi
${current_test}_setup_prepare
setup_wait $num_netifs
+ # Update target in case occupancy of a certain resource
+ # changed following the test setup.
+ target=$(${current_test}_get_target "$should_fail")
${current_test}_test "$target" "$should_fail"
- ${current_test}_cleanup
if [[ "$should_fail" -eq 0 ]]; then
log_test "'$current_test' [$profile] $target"
+
+ if ((!RET)); then
+ tt=${current_test}_traffic_test
+ if [[ $(type -t $tt) == "function" ]]
+ then
+ $tt "$target"
+ log_test "'$current_test' [$profile] $target traffic test"
+ fi
+ fi
else
log_test "'$current_test' [$profile] overflow $target"
fi
+ ${current_test}_cleanup $target
RET_FIN=$(( RET_FIN || RET ))
done
done
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/rif_counter_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/rif_counter_scale.sh
new file mode 100644
index 000000000000..d44536276e8a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/rif_counter_scale.sh
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../rif_counter_scale.sh
+
+rif_counter_get_target()
+{
+ local should_fail=$1; shift
+ local max_cnts
+ local max_rifs
+ local target
+
+ max_rifs=$(devlink_resource_size_get rifs)
+ max_cnts=$(devlink_resource_size_get counters rif)
+
+ # Remove already allocated RIFs.
+ ((max_rifs -= $(devlink_resource_occ_get rifs)))
+
+ # 10 KVD slots per counter, ingress+egress counters per RIF
+ ((max_cnts /= 20))
+
+ # Pointless to run the overflow test if we don't have enough RIFs to
+ # host all the counters.
+ if ((max_cnts > max_rifs && should_fail)); then
+ echo 0
+ return
+ fi
+
+ target=$((max_rifs < max_cnts ? max_rifs : max_cnts))
+
+ if ((! should_fail)); then
+ echo $target
+ else
+ echo $((target + 1))
+ fi
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
index aa74be9f47c8..d3d9e60d6ddf 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
@@ -77,6 +77,7 @@ tc_flower_rules_create()
filter add dev $h2 ingress \
prot ipv6 \
pref 1000 \
+ handle 42$i \
flower $tcflags dst_ip $(tc_flower_addr $i) \
action drop
EOF
@@ -121,3 +122,19 @@ tc_flower_test()
tcflags="skip_sw"
__tc_flower_test $count $should_fail
}
+
+tc_flower_traffic_test()
+{
+ local count=$1; shift
+ local i;
+
+ for ((i = count - 1; i > 0; i /= 2)); do
+ $MZ -6 $h1 -c 1 -d 20msec -p 100 -a own -b $(mac_get $h2) \
+ -A $(tc_flower_addr 0) -B $(tc_flower_addr $i) \
+ -q -t udp sp=54321,dp=12345
+ done
+ for ((i = count - 1; i > 0; i /= 2)); do
+ tc_check_packets "dev $h2 ingress" 42$i 1
+ check_err $? "Traffic not seen at rule #$i"
+ done
+}
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 81470a99ed1c..22423c871ed6 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -37,11 +37,38 @@ ifeq ($(ARCH),riscv)
UNAME_M := riscv
endif
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
-LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
-LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c
-LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
-LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c
+LIBKVM += lib/assert.c
+LIBKVM += lib/elf.c
+LIBKVM += lib/guest_modes.c
+LIBKVM += lib/io.c
+LIBKVM += lib/kvm_util.c
+LIBKVM += lib/perf_test_util.c
+LIBKVM += lib/rbtree.c
+LIBKVM += lib/sparsebit.c
+LIBKVM += lib/test_util.c
+
+LIBKVM_x86_64 += lib/x86_64/apic.c
+LIBKVM_x86_64 += lib/x86_64/handlers.S
+LIBKVM_x86_64 += lib/x86_64/perf_test_util.c
+LIBKVM_x86_64 += lib/x86_64/processor.c
+LIBKVM_x86_64 += lib/x86_64/svm.c
+LIBKVM_x86_64 += lib/x86_64/ucall.c
+LIBKVM_x86_64 += lib/x86_64/vmx.c
+
+LIBKVM_aarch64 += lib/aarch64/gic.c
+LIBKVM_aarch64 += lib/aarch64/gic_v3.c
+LIBKVM_aarch64 += lib/aarch64/handlers.S
+LIBKVM_aarch64 += lib/aarch64/processor.c
+LIBKVM_aarch64 += lib/aarch64/spinlock.c
+LIBKVM_aarch64 += lib/aarch64/ucall.c
+LIBKVM_aarch64 += lib/aarch64/vgic.c
+
+LIBKVM_s390x += lib/s390x/diag318_test_handler.c
+LIBKVM_s390x += lib/s390x/processor.c
+LIBKVM_s390x += lib/s390x/ucall.c
+
+LIBKVM_riscv += lib/riscv/processor.c
+LIBKVM_riscv += lib/riscv/ucall.c
TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
@@ -173,12 +200,13 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
include ../lib.mk
-STATIC_LIBS := $(OUTPUT)/libkvm.a
LIBKVM_C := $(filter %.c,$(LIBKVM))
LIBKVM_S := $(filter %.S,$(LIBKVM))
LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
-EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.*
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+
+EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.*
x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
@@ -187,13 +215,8 @@ $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
-LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
- $(AR) crs $@ $^
-
x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
-all: $(STATIC_LIBS)
-$(TEST_GEN_PROGS): $(STATIC_LIBS)
+$(TEST_GEN_PROGS): $(LIBKVM_OBJS)
cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
cscope:
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 7b47ae4f952e..d60a34cdfaee 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -336,8 +336,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
static void help(char *name)
{
puts("");
- printf("usage: %s [-h] [-i iterations] [-p offset] [-g]"
- "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
+ printf("usage: %s [-h] [-i iterations] [-p offset] [-g] "
+ "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
"[-x memslots]\n", name);
puts("");
printf(" -i: specify iteration counts (default: %"PRIu64")\n",
@@ -351,6 +351,7 @@ static void help(char *name)
printf(" -p: specify guest physical test memory offset\n"
" Warning: a low offset can conflict with the loaded test code.\n");
guest_modes_help();
+ printf(" -n: Run the vCPUs in nested mode (L2)\n");
printf(" -b: specify the size of the memory region which should be\n"
" dirtied by each vCPU. e.g. 10M or 3G.\n"
" (default: 1G)\n");
@@ -387,7 +388,7 @@ int main(int argc, char *argv[])
guest_modes_append_default();
- while ((opt = getopt(argc, argv, "ghi:p:m:b:f:v:os:x:")) != -1) {
+ while ((opt = getopt(argc, argv, "ghi:p:m:nb:f:v:os:x:")) != -1) {
switch (opt) {
case 'g':
dirty_log_manual_caps = 0;
@@ -401,6 +402,9 @@ int main(int argc, char *argv[])
case 'm':
guest_modes_cmdline(optarg);
break;
+ case 'n':
+ perf_test_args.nested = true;
+ break;
case 'b':
guest_percpu_mem_size = parse_size(optarg);
break;
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index a86f953d8d36..d822cb670f1c 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -30,10 +30,15 @@ struct perf_test_vcpu_args {
struct perf_test_args {
struct kvm_vm *vm;
+ /* The starting address and size of the guest test region. */
uint64_t gpa;
+ uint64_t size;
uint64_t guest_page_size;
int wr_fract;
+ /* Run vCPUs in L2 instead of L1, if the architecture supports it. */
+ bool nested;
+
struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
};
@@ -49,5 +54,9 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
void perf_test_join_vcpu_threads(int vcpus);
+void perf_test_guest_code(uint32_t vcpu_id);
+
+uint64_t perf_test_nested_pages(int nr_vcpus);
+void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus);
#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index d0d51adec76e..6ce185449259 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -482,13 +482,23 @@ void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
void vm_xsave_req_perm(int bit);
-enum x86_page_size {
- X86_PAGE_SIZE_4K = 0,
- X86_PAGE_SIZE_2M,
- X86_PAGE_SIZE_1G,
+enum pg_level {
+ PG_LEVEL_NONE,
+ PG_LEVEL_4K,
+ PG_LEVEL_2M,
+ PG_LEVEL_1G,
+ PG_LEVEL_512G,
+ PG_LEVEL_NUM
};
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- enum x86_page_size page_size);
+
+#define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12)
+#define PG_LEVEL_SIZE(_level) (1ull << PG_LEVEL_SHIFT(_level))
+
+#define PG_SIZE_4K PG_LEVEL_SIZE(PG_LEVEL_4K)
+#define PG_SIZE_2M PG_LEVEL_SIZE(PG_LEVEL_2M)
+#define PG_SIZE_1G PG_LEVEL_SIZE(PG_LEVEL_1G)
+
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
/*
* Basic CPU control in CR0
@@ -505,9 +515,6 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
#define X86_CR0_CD (1UL<<30) /* Cache Disable */
#define X86_CR0_PG (1UL<<31) /* Paging */
-/* VMX_EPT_VPID_CAP bits */
-#define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21)
-
#define XSTATE_XTILE_CFG_BIT 17
#define XSTATE_XTILE_DATA_BIT 18
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 583ceb0d1457..cc3604f8f1d3 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -96,6 +96,9 @@
#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f
#define VMX_MISC_SAVE_EFER_LMA 0x00000020
+#define VMX_EPT_VPID_CAP_1G_PAGES 0x00020000
+#define VMX_EPT_VPID_CAP_AD_BITS 0x00200000
+
#define EXIT_REASON_FAILED_VMENTRY 0x80000000
#define EXIT_REASON_EXCEPTION_NMI 0
#define EXIT_REASON_EXTERNAL_INTERRUPT 1
@@ -606,6 +609,7 @@ bool load_vmcs(struct vmx_pages *vmx);
bool nested_vmx_supported(void);
void nested_vmx_check_supported(void);
+bool ept_1g_pages_supported(void);
void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
uint64_t nested_paddr, uint64_t paddr);
@@ -613,6 +617,8 @@ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
uint64_t nested_paddr, uint64_t paddr, uint64_t size);
void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
uint32_t memslot);
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t addr, uint64_t size);
void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
uint32_t eptp_memslot);
void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 722df3a28791..f989ff91f022 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -40,7 +40,7 @@ static bool all_vcpu_threads_running;
* Continuously write to the first 8 bytes of each page in the
* specified region.
*/
-static void guest_code(uint32_t vcpu_id)
+void perf_test_guest_code(uint32_t vcpu_id)
{
struct perf_test_args *pta = &perf_test_args;
struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
@@ -108,8 +108,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
{
struct perf_test_args *pta = &perf_test_args;
struct kvm_vm *vm;
- uint64_t guest_num_pages;
+ uint64_t guest_num_pages, slot0_pages = DEFAULT_GUEST_PHY_PAGES;
uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
+ uint64_t region_end_gfn;
int i;
pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
@@ -135,33 +136,53 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
slots);
/*
+ * If using nested, allocate extra pages for the nested page tables and
+ * in-memory data structures.
+ */
+ if (pta->nested)
+ slot0_pages += perf_test_nested_pages(vcpus);
+
+ /*
* Pass guest_num_pages to populate the page tables for test memory.
* The memory is also added to memslot 0, but that's a benign side
* effect as KVM allows aliasing HVAs in meslots.
*/
- vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
- guest_num_pages, 0, guest_code, NULL);
+ vm = vm_create_with_vcpus(mode, vcpus, slot0_pages, guest_num_pages, 0,
+ perf_test_guest_code, NULL);
pta->vm = vm;
+ /* Put the test region at the top guest physical memory. */
+ region_end_gfn = vm_get_max_gfn(vm) + 1;
+
+#ifdef __x86_64__
+ /*
+ * When running vCPUs in L2, restrict the test region to 48 bits to
+ * avoid needing 5-level page tables to identity map L2.
+ */
+ if (pta->nested)
+ region_end_gfn = min(region_end_gfn, (1UL << 48) / pta->guest_page_size);
+#endif
/*
* If there should be more memory in the guest test region than there
* can be pages in the guest, it will definitely cause problems.
*/
- TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+ TEST_ASSERT(guest_num_pages < region_end_gfn,
"Requested more guest memory than address space allows.\n"
" guest pages: %" PRIx64 " max gfn: %" PRIx64
" vcpus: %d wss: %" PRIx64 "]\n",
- guest_num_pages, vm_get_max_gfn(vm), vcpus,
+ guest_num_pages, region_end_gfn - 1, vcpus,
vcpu_memory_bytes);
- pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+ pta->gpa = (region_end_gfn - guest_num_pages) * pta->guest_page_size;
pta->gpa = align_down(pta->gpa, backing_src_pagesz);
#ifdef __s390x__
/* Align to 1M (segment size) */
pta->gpa = align_down(pta->gpa, 1 << 20);
#endif
- pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
+ pta->size = guest_num_pages * pta->guest_page_size;
+ pr_info("guest physical test memory: [0x%lx, 0x%lx)\n",
+ pta->gpa, pta->gpa + pta->size);
/* Add extra memory slots for testing */
for (i = 0; i < slots; i++) {
@@ -178,6 +199,11 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
+ if (pta->nested) {
+ pr_info("Configuring vCPUs to run in L2 (nested).\n");
+ perf_test_setup_nested(vm, vcpus);
+ }
+
ucall_init(vm, NULL);
/* Export the shared variables to the guest. */
@@ -198,6 +224,17 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
sync_global_to_guest(vm, perf_test_args);
}
+uint64_t __weak perf_test_nested_pages(int nr_vcpus)
+{
+ return 0;
+}
+
+void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus)
+{
+ pr_info("%s() not support on this architecture, skipping.\n", __func__);
+ exit(KSFT_SKIP);
+}
+
static void *vcpu_thread_main(void *data)
{
struct vcpu_thread *vcpu = data;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c b/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
new file mode 100644
index 000000000000..e258524435a0
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * x86_64-specific extensions to perf_test_util.c.
+ *
+ * Copyright (C) 2022, Google, Inc.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+#include "vmx.h"
+
+void perf_test_l2_guest_code(uint64_t vcpu_id)
+{
+ perf_test_guest_code(vcpu_id);
+ vmcall();
+}
+
+extern char perf_test_l2_guest_entry[];
+__asm__(
+"perf_test_l2_guest_entry:"
+" mov (%rsp), %rdi;"
+" call perf_test_l2_guest_code;"
+" ud2;"
+);
+
+static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ unsigned long *rsp;
+
+ GUEST_ASSERT(vmx->vmcs_gpa);
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx));
+ GUEST_ASSERT(load_vmcs(vmx));
+ GUEST_ASSERT(ept_1g_pages_supported());
+
+ rsp = &l2_guest_stack[L2_GUEST_STACK_SIZE - 1];
+ *rsp = vcpu_id;
+ prepare_vmcs(vmx, perf_test_l2_guest_entry, rsp);
+
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+ GUEST_DONE();
+}
+
+uint64_t perf_test_nested_pages(int nr_vcpus)
+{
+ /*
+ * 513 page tables is enough to identity-map 256 TiB of L2 with 1G
+ * pages and 4-level paging, plus a few pages per-vCPU for data
+ * structures such as the VMCS.
+ */
+ return 513 + 10 * nr_vcpus;
+}
+
+void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
+{
+ uint64_t start, end;
+
+ prepare_eptp(vmx, vm, 0);
+
+ /*
+ * Identity map the first 4G and the test region with 1G pages so that
+ * KVM can shadow the EPT12 with the maximum huge page size supported
+ * by the backing source.
+ */
+ nested_identity_map_1g(vmx, vm, 0, 0x100000000ULL);
+
+ start = align_down(perf_test_args.gpa, PG_SIZE_1G);
+ end = align_up(perf_test_args.gpa + perf_test_args.size, PG_SIZE_1G);
+ nested_identity_map_1g(vmx, vm, start, end - start);
+}
+
+void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus)
+{
+ struct vmx_pages *vmx, *vmx0 = NULL;
+ struct kvm_regs regs;
+ vm_vaddr_t vmx_gva;
+ int vcpu_id;
+
+ nested_vmx_check_supported();
+
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+ vmx = vcpu_alloc_vmx(vm, &vmx_gva);
+
+ if (vcpu_id == 0) {
+ perf_test_setup_ept(vmx, vm);
+ vmx0 = vmx;
+ } else {
+ /* Share the same EPT table across all vCPUs. */
+ vmx->eptp = vmx0->eptp;
+ vmx->eptp_hva = vmx0->eptp_hva;
+ vmx->eptp_gpa = vmx0->eptp_gpa;
+ }
+
+ /*
+ * Override the vCPU to run perf_test_l1_guest_code() which will
+ * bounce it into L2 before calling perf_test_guest_code().
+ */
+ vcpu_regs_get(vm, vcpu_id, &regs);
+ regs.rip = (unsigned long) perf_test_l1_guest_code;
+ vcpu_regs_set(vm, vcpu_id, &regs);
+ vcpu_args_set(vm, vcpu_id, 2, vmx_gva, vcpu_id);
+ }
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 33ea5e9955d9..ead7011ee8f6 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -158,7 +158,7 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
int level)
{
uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift);
- int index = vaddr >> (vm->page_shift + level * 9) & 0x1ffu;
+ int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
return &page_table[index];
}
@@ -167,14 +167,14 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
uint64_t pt_pfn,
uint64_t vaddr,
uint64_t paddr,
- int level,
- enum x86_page_size page_size)
+ int current_level,
+ int target_level)
{
- uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+ uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, current_level);
if (!(*pte & PTE_PRESENT_MASK)) {
*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
- if (level == page_size)
+ if (current_level == target_level)
*pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK);
else
*pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK;
@@ -184,20 +184,19 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
* a hugepage at this level, and that there isn't a hugepage at
* this level.
*/
- TEST_ASSERT(level != page_size,
+ TEST_ASSERT(current_level != target_level,
"Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
- page_size, vaddr);
+ current_level, vaddr);
TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
"Cannot create page table at level: %u, vaddr: 0x%lx\n",
- level, vaddr);
+ current_level, vaddr);
}
return pte;
}
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- enum x86_page_size page_size)
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
{
- const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
+ const uint64_t pg_size = PG_LEVEL_SIZE(level);
uint64_t *pml4e, *pdpe, *pde;
uint64_t *pte;
@@ -222,20 +221,20 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
* early if a hugepage was created.
*/
pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
- vaddr, paddr, 3, page_size);
+ vaddr, paddr, PG_LEVEL_512G, level);
if (*pml4e & PTE_LARGE_MASK)
return;
- pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size);
+ pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, PG_LEVEL_1G, level);
if (*pdpe & PTE_LARGE_MASK)
return;
- pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size);
+ pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, PG_LEVEL_2M, level);
if (*pde & PTE_LARGE_MASK)
return;
/* Fill in page table entry. */
- pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0);
+ pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, PG_LEVEL_4K);
TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
"PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
@@ -243,7 +242,7 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
{
- __virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
+ __virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K);
}
static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index d089d8b850b5..b77a01d0a271 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -198,6 +198,16 @@ bool load_vmcs(struct vmx_pages *vmx)
return true;
}
+static bool ept_vpid_cap_supported(uint64_t mask)
+{
+ return rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & mask;
+}
+
+bool ept_1g_pages_supported(void)
+{
+ return ept_vpid_cap_supported(VMX_EPT_VPID_CAP_1G_PAGES);
+}
+
/*
* Initialize the control fields to the most basic settings possible.
*/
@@ -215,7 +225,7 @@ static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
struct eptPageTablePointer eptp = {
.memory_type = VMX_BASIC_MEM_TYPE_WB,
.page_walk_length = 3, /* + 1 */
- .ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS),
+ .ad_enabled = ept_vpid_cap_supported(VMX_EPT_VPID_CAP_AD_BITS),
.address = vmx->eptp_gpa >> PAGE_SHIFT_4K,
};
@@ -392,80 +402,93 @@ void nested_vmx_check_supported(void)
}
}
-void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
- uint64_t nested_paddr, uint64_t paddr)
+static void nested_create_pte(struct kvm_vm *vm,
+ struct eptPageTableEntry *pte,
+ uint64_t nested_paddr,
+ uint64_t paddr,
+ int current_level,
+ int target_level)
+{
+ if (!pte->readable) {
+ pte->writable = true;
+ pte->readable = true;
+ pte->executable = true;
+ pte->page_size = (current_level == target_level);
+ if (pte->page_size)
+ pte->address = paddr >> vm->page_shift;
+ else
+ pte->address = vm_alloc_page_table(vm) >> vm->page_shift;
+ } else {
+ /*
+ * Entry already present. Assert that the caller doesn't want
+ * a hugepage at this level, and that there isn't a hugepage at
+ * this level.
+ */
+ TEST_ASSERT(current_level != target_level,
+ "Cannot create hugepage at level: %u, nested_paddr: 0x%lx\n",
+ current_level, nested_paddr);
+ TEST_ASSERT(!pte->page_size,
+ "Cannot create page table at level: %u, nested_paddr: 0x%lx\n",
+ current_level, nested_paddr);
+ }
+}
+
+
+void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, int target_level)
{
- uint16_t index[4];
- struct eptPageTableEntry *pml4e;
+ const uint64_t page_size = PG_LEVEL_SIZE(target_level);
+ struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
+ uint16_t index;
TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
- TEST_ASSERT((nested_paddr % vm->page_size) == 0,
+ TEST_ASSERT((nested_paddr >> 48) == 0,
+ "Nested physical address 0x%lx requires 5-level paging",
+ nested_paddr);
+ TEST_ASSERT((nested_paddr % page_size) == 0,
"Nested physical address not on page boundary,\n"
- " nested_paddr: 0x%lx vm->page_size: 0x%x",
- nested_paddr, vm->page_size);
+ " nested_paddr: 0x%lx page_size: 0x%lx",
+ nested_paddr, page_size);
TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn,
"Physical address beyond beyond maximum supported,\n"
" nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
paddr, vm->max_gfn, vm->page_size);
- TEST_ASSERT((paddr % vm->page_size) == 0,
+ TEST_ASSERT((paddr % page_size) == 0,
"Physical address not on page boundary,\n"
- " paddr: 0x%lx vm->page_size: 0x%x",
- paddr, vm->page_size);
+ " paddr: 0x%lx page_size: 0x%lx",
+ paddr, page_size);
TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
"Physical address beyond beyond maximum supported,\n"
" paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
paddr, vm->max_gfn, vm->page_size);
- index[0] = (nested_paddr >> 12) & 0x1ffu;
- index[1] = (nested_paddr >> 21) & 0x1ffu;
- index[2] = (nested_paddr >> 30) & 0x1ffu;
- index[3] = (nested_paddr >> 39) & 0x1ffu;
-
- /* Allocate page directory pointer table if not present. */
- pml4e = vmx->eptp_hva;
- if (!pml4e[index[3]].readable) {
- pml4e[index[3]].address = vm_alloc_page_table(vm) >> vm->page_shift;
- pml4e[index[3]].writable = true;
- pml4e[index[3]].readable = true;
- pml4e[index[3]].executable = true;
- }
+ for (int level = PG_LEVEL_512G; level >= PG_LEVEL_4K; level--) {
+ index = (nested_paddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
+ pte = &pt[index];
- /* Allocate page directory table if not present. */
- struct eptPageTableEntry *pdpe;
- pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
- if (!pdpe[index[2]].readable) {
- pdpe[index[2]].address = vm_alloc_page_table(vm) >> vm->page_shift;
- pdpe[index[2]].writable = true;
- pdpe[index[2]].readable = true;
- pdpe[index[2]].executable = true;
- }
+ nested_create_pte(vm, pte, nested_paddr, paddr, level, target_level);
- /* Allocate page table if not present. */
- struct eptPageTableEntry *pde;
- pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
- if (!pde[index[1]].readable) {
- pde[index[1]].address = vm_alloc_page_table(vm) >> vm->page_shift;
- pde[index[1]].writable = true;
- pde[index[1]].readable = true;
- pde[index[1]].executable = true;
- }
+ if (pte->page_size)
+ break;
- /* Fill in page table entry. */
- struct eptPageTableEntry *pte;
- pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
- pte[index[0]].address = paddr >> vm->page_shift;
- pte[index[0]].writable = true;
- pte[index[0]].readable = true;
- pte[index[0]].executable = true;
+ pt = addr_gpa2hva(vm, pte->address * vm->page_size);
+ }
/*
* For now mark these as accessed and dirty because the only
* testcase we have needs that. Can be reconsidered later.
*/
- pte[index[0]].accessed = true;
- pte[index[0]].dirty = true;
+ pte->accessed = true;
+ pte->dirty = true;
+
+}
+
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr)
+{
+ __nested_pg_map(vmx, vm, nested_paddr, paddr, PG_LEVEL_4K);
}
/*
@@ -476,7 +499,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
* nested_paddr - Nested guest physical address to map
* paddr - VM Physical Address
* size - The size of the range to map
- * eptp_memslot - Memory region slot for new virtual translation tables
+ * level - The level at which to map the range
*
* Output Args: None
*
@@ -485,22 +508,29 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
* Within the VM given by vm, creates a nested guest translation for the
* page range starting at nested_paddr to the page range starting at paddr.
*/
-void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
- uint64_t nested_paddr, uint64_t paddr, uint64_t size)
+void __nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+ int level)
{
- size_t page_size = vm->page_size;
+ size_t page_size = PG_LEVEL_SIZE(level);
size_t npages = size / page_size;
TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow");
TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
while (npages--) {
- nested_pg_map(vmx, vm, nested_paddr, paddr);
+ __nested_pg_map(vmx, vm, nested_paddr, paddr, level);
nested_paddr += page_size;
paddr += page_size;
}
}
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint64_t size)
+{
+ __nested_map(vmx, vm, nested_paddr, paddr, size, PG_LEVEL_4K);
+}
+
/* Prepare an identity extended page table that maps all the
* physical pages in VM.
*/
@@ -525,6 +555,13 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
}
}
+/* Identity map a region with 1GiB Pages. */
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t addr, uint64_t size)
+{
+ __nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G);
+}
+
void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
uint32_t eptp_memslot)
{
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 3875c4b23a04..15f046e19cb2 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -244,7 +244,7 @@ int main(int argc, char *argv[])
#ifdef __x86_64__
/* Identity map memory in the guest using 1gb pages. */
for (i = 0; i < slot_size; i += size_1gb)
- __virt_pg_map(vm, gpa + i, gpa + i, X86_PAGE_SIZE_1G);
+ __virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G);
#else
for (i = 0; i < slot_size; i += vm_get_page_size(vm))
virt_pg_map(vm, gpa + i, gpa + i);
diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
index da2325fcad87..bdecd532f935 100644
--- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
@@ -35,7 +35,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val)
run = vcpu_state(vm, VCPU_ID);
/* Map 1gb page without a backing memlot. */
- __virt_pg_map(vm, MMIO_GPA, MMIO_GPA, X86_PAGE_SIZE_1G);
+ __virt_pg_map(vm, MMIO_GPA, MMIO_GPA, PG_LEVEL_1G);
r = _vcpu_run(vm, VCPU_ID);
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 2a2d240cdc1b..1a5cc3cd97ec 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -7,10 +7,31 @@ else ifneq ($(filter -%,$(LLVM)),)
LLVM_SUFFIX := $(LLVM)
endif
-CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX)
+CLANG_TARGET_FLAGS_arm := arm-linux-gnueabi
+CLANG_TARGET_FLAGS_arm64 := aarch64-linux-gnu
+CLANG_TARGET_FLAGS_hexagon := hexagon-linux-musl
+CLANG_TARGET_FLAGS_m68k := m68k-linux-gnu
+CLANG_TARGET_FLAGS_mips := mipsel-linux-gnu
+CLANG_TARGET_FLAGS_powerpc := powerpc64le-linux-gnu
+CLANG_TARGET_FLAGS_riscv := riscv64-linux-gnu
+CLANG_TARGET_FLAGS_s390 := s390x-linux-gnu
+CLANG_TARGET_FLAGS_x86 := x86_64-linux-gnu
+CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH))
+
+ifeq ($(CROSS_COMPILE),)
+ifeq ($(CLANG_TARGET_FLAGS),)
+$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk
+else
+CLANG_FLAGS += --target=$(CLANG_TARGET_FLAGS)
+endif # CLANG_TARGET_FLAGS
+else
+CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%))
+endif # CROSS_COMPILE
+
+CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as
else
CC := $(CROSS_COMPILE)gcc
-endif
+endif # LLVM
ifeq (0,$(MAKELEVEL))
ifeq ($(OUTPUT),)
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index b984f8c8d523..a29f79618934 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -37,4 +37,3 @@ gro
ioam6_parser
toeplitz
cmsg_sender
-bind_bhash_test
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 464df13831f2..7ea54af55490 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -59,7 +59,6 @@ TEST_GEN_FILES += toeplitz
TEST_GEN_FILES += cmsg_sender
TEST_GEN_FILES += stress_reuseport_listen
TEST_PROGS += test_vxlan_vnifiltering.sh
-TEST_GEN_FILES += bind_bhash_test
TEST_FILES := settings
@@ -70,5 +69,4 @@ include bpf/Makefile
$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread
-$(OUTPUT)/bind_bhash_test: LDLIBS += -lpthread
$(OUTPUT)/tcp_inq: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/net/bind_bhash_test.c b/tools/testing/selftests/net/bind_bhash_test.c
deleted file mode 100644
index 252e73754e76..000000000000
--- a/tools/testing/selftests/net/bind_bhash_test.c
+++ /dev/null
@@ -1,119 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This times how long it takes to bind to a port when the port already
- * has multiple sockets in its bhash table.
- *
- * In the setup(), we populate the port's bhash table with
- * MAX_THREADS * MAX_CONNECTIONS number of entries.
- */
-
-#include <unistd.h>
-#include <stdio.h>
-#include <netdb.h>
-#include <pthread.h>
-
-#define MAX_THREADS 600
-#define MAX_CONNECTIONS 40
-
-static const char *bind_addr = "::1";
-static const char *port;
-
-static int fd_array[MAX_THREADS][MAX_CONNECTIONS];
-
-static int bind_socket(int opt, const char *addr)
-{
- struct addrinfo *res, hint = {};
- int sock_fd, reuse = 1, err;
-
- sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
- if (sock_fd < 0) {
- perror("socket fd err");
- return -1;
- }
-
- hint.ai_family = AF_INET6;
- hint.ai_socktype = SOCK_STREAM;
-
- err = getaddrinfo(addr, port, &hint, &res);
- if (err) {
- perror("getaddrinfo failed");
- return -1;
- }
-
- if (opt) {
- err = setsockopt(sock_fd, SOL_SOCKET, opt, &reuse, sizeof(reuse));
- if (err) {
- perror("setsockopt failed");
- return -1;
- }
- }
-
- err = bind(sock_fd, res->ai_addr, res->ai_addrlen);
- if (err) {
- perror("failed to bind to port");
- return -1;
- }
-
- return sock_fd;
-}
-
-static void *setup(void *arg)
-{
- int sock_fd, i;
- int *array = (int *)arg;
-
- for (i = 0; i < MAX_CONNECTIONS; i++) {
- sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, bind_addr);
- if (sock_fd < 0)
- return NULL;
- array[i] = sock_fd;
- }
-
- return NULL;
-}
-
-int main(int argc, const char *argv[])
-{
- int listener_fd, sock_fd, i, j;
- pthread_t tid[MAX_THREADS];
- clock_t begin, end;
-
- if (argc != 2) {
- printf("Usage: listener <port>\n");
- return -1;
- }
-
- port = argv[1];
-
- listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, bind_addr);
- if (listen(listener_fd, 100) < 0) {
- perror("listen failed");
- return -1;
- }
-
- /* Set up threads to populate the bhash table entry for the port */
- for (i = 0; i < MAX_THREADS; i++)
- pthread_create(&tid[i], NULL, setup, fd_array[i]);
-
- for (i = 0; i < MAX_THREADS; i++)
- pthread_join(tid[i], NULL);
-
- begin = clock();
-
- /* Bind to the same port on a different address */
- sock_fd = bind_socket(0, "2001:0db8:0:f101::1");
-
- end = clock();
-
- printf("time spent = %f\n", (double)(end - begin) / CLOCKS_PER_SEC);
-
- /* clean up */
- close(sock_fd);
- close(listener_fd);
- for (i = 0; i < MAX_THREADS; i++) {
- for (j = 0; i < MAX_THREADS; i++)
- close(fd_array[i][j]);
- }
-
- return 0;
-}
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 54701c8b0cd7..03b586760164 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -70,6 +70,10 @@ NSB_LO_IP6=2001:db8:2::2
NL_IP=172.17.1.1
NL_IP6=2001:db8:4::1
+# multicast and broadcast addresses
+MCAST_IP=224.0.0.1
+BCAST_IP=255.255.255.255
+
MD5_PW=abc123
MD5_WRONG_PW=abc1234
@@ -308,6 +312,9 @@ addr2str()
127.0.0.1) echo "loopback";;
::1) echo "IPv6 loopback";;
+ ${BCAST_IP}) echo "broadcast";;
+ ${MCAST_IP}) echo "multicast";;
+
${NSA_IP}) echo "ns-A IP";;
${NSA_IP6}) echo "ns-A IPv6";;
${NSA_LO_IP}) echo "ns-A loopback IP";;
@@ -1793,12 +1800,33 @@ ipv4_addr_bind_novrf()
done
#
- # raw socket with nonlocal bind
+ # tests for nonlocal bind
#
a=${NL_IP}
log_start
- run_cmd nettest -s -R -P icmp -f -l ${a} -I ${NSA_DEV} -b
- log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after device bind"
+ run_cmd nettest -s -R -f -l ${a} -b
+ log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address"
+
+ log_start
+ run_cmd nettest -s -f -l ${a} -b
+ log_test_addr ${a} $? 0 "TCP socket bind to nonlocal address"
+
+ log_start
+ run_cmd nettest -s -D -P icmp -f -l ${a} -b
+ log_test_addr ${a} $? 0 "ICMP socket bind to nonlocal address"
+
+ #
+ # check that ICMP sockets cannot bind to broadcast and multicast addresses
+ #
+ a=${BCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to broadcast address"
+
+ a=${MCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to multicast address"
#
# tcp sockets
@@ -1850,13 +1878,34 @@ ipv4_addr_bind_vrf()
log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind"
#
- # raw socket with nonlocal bind
+ # tests for nonlocal bind
#
a=${NL_IP}
log_start
- run_cmd nettest -s -R -P icmp -f -l ${a} -I ${VRF} -b
+ run_cmd nettest -s -R -f -l ${a} -I ${VRF} -b
log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after VRF bind"
+ log_start
+ run_cmd nettest -s -f -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 0 "TCP socket bind to nonlocal address after VRF bind"
+
+ log_start
+ run_cmd nettest -s -D -P icmp -f -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 0 "ICMP socket bind to nonlocal address after VRF bind"
+
+ #
+ # check that ICMP sockets cannot bind to broadcast and multicast addresses
+ #
+ a=${BCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to broadcast address after VRF bind"
+
+ a=${MCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to multicast address after VRF bind"
+
#
# tcp sockets
#
@@ -1889,10 +1938,12 @@ ipv4_addr_bind()
log_subsection "No VRF"
setup
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
ipv4_addr_bind_novrf
log_subsection "With VRF"
setup "yes"
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
ipv4_addr_bind_vrf
}
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
index 28d568c48a73..91e431cd919e 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
@@ -141,12 +141,13 @@ switch_create()
ip link set dev $swp4 up
ip link add name br1 type bridge vlan_filtering 1
- ip link set dev br1 up
- __addr_add_del br1 add 192.0.2.129/32
- ip -4 route add 192.0.2.130/32 dev br1
team_create lag loadbalance $swp3 $swp4
ip link set dev lag master br1
+
+ ip link set dev br1 up
+ __addr_add_del br1 add 192.0.2.129/32
+ ip -4 route add 192.0.2.130/32 dev br1
}
switch_destroy()
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index b35010cc7f6a..a6991877e50c 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -31,7 +31,7 @@ BUGS="flush_remove_add reload"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
- ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
+ ../../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
pktgen/pktgen_bench_xmit_mode_netif_receive.sh"
# Definition of set types:
diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore
index d52f65de23b4..9fe1cef72728 100644
--- a/tools/testing/selftests/tc-testing/.gitignore
+++ b/tools/testing/selftests/tc-testing/.gitignore
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
__pycache__/
*.pyc
-plugins/
*.xml
*.tap
tdc_config_local.py
diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c
index 6bb36ca71cb5..a309876d832f 100644
--- a/tools/testing/selftests/vm/gup_test.c
+++ b/tools/testing/selftests/vm/gup_test.c
@@ -209,7 +209,7 @@ int main(int argc, char **argv)
if (write)
gup.gup_flags |= FOLL_WRITE;
- gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR);
+ gup_fd = open(GUP_TEST_FILE, O_RDWR);
if (gup_fd == -1) {
switch (errno) {
case EACCES:
@@ -224,7 +224,7 @@ int main(int argc, char **argv)
printf("check if CONFIG_GUP_TEST is enabled in kernel config\n");
break;
default:
- perror("failed to open /sys/kernel/debug/gup_test");
+ perror("failed to open " GUP_TEST_FILE);
break;
}
exit(KSFT_SKIP);
diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c
index 2fcf24312da8..f5e4e0bbd081 100644
--- a/tools/testing/selftests/vm/ksm_tests.c
+++ b/tools/testing/selftests/vm/ksm_tests.c
@@ -54,6 +54,7 @@ static int ksm_write_sysfs(const char *file_path, unsigned long val)
}
if (fprintf(f, "%lu", val) < 0) {
perror("fprintf");
+ fclose(f);
return 1;
}
fclose(f);
@@ -72,6 +73,7 @@ static int ksm_read_sysfs(const char *file_path, unsigned long *val)
}
if (fscanf(f, "%lu", val) != 1) {
perror("fscanf");
+ fclose(f);
return 1;
}
fclose(f);
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index bca07b93eeb0..7d1b80988d8a 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -64,8 +64,8 @@ QEMU_VPORT_RESULT := virtio-serial-device
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
-QEMU_MACHINE := -cpu cortex-a53 -machine virt
-CFLAGS += -march=armv8-a -mtune=cortex-a53
+QEMU_MACHINE := -cpu max -machine virt
+CFLAGS += -march=armv8-a
endif
else ifeq ($(ARCH),aarch64_be)
CHOST := aarch64_be-linux-musl
@@ -76,8 +76,8 @@ QEMU_VPORT_RESULT := virtio-serial-device
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
-QEMU_MACHINE := -cpu cortex-a53 -machine virt
-CFLAGS += -march=armv8-a -mtune=cortex-a53
+QEMU_MACHINE := -cpu max -machine virt
+CFLAGS += -march=armv8-a
endif
else ifeq ($(ARCH),arm)
CHOST := arm-linux-musleabi
@@ -88,8 +88,8 @@ QEMU_VPORT_RESULT := virtio-serial-device
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
-QEMU_MACHINE := -cpu cortex-a15 -machine virt
-CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux
+QEMU_MACHINE := -cpu max -machine virt
+CFLAGS += -march=armv7-a -mabi=aapcs-linux
endif
else ifeq ($(ARCH),armeb)
CHOST := armeb-linux-musleabi
@@ -100,8 +100,8 @@ QEMU_VPORT_RESULT := virtio-serial-device
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
-QEMU_MACHINE := -cpu cortex-a15 -machine virt
-CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due to a compiler bug on big endian.
+QEMU_MACHINE := -cpu max -machine virt
+CFLAGS += -march=armv7-a -mabi=aapcs-linux
LDFLAGS += -Wl,--be8
endif
else ifeq ($(ARCH),x86_64)
@@ -112,8 +112,7 @@ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine q35,accel=kvm
else
-QEMU_MACHINE := -cpu Skylake-Server -machine q35
-CFLAGS += -march=skylake-avx512
+QEMU_MACHINE := -cpu max -machine q35
endif
else ifeq ($(ARCH),i686)
CHOST := i686-linux-musl
@@ -123,8 +122,7 @@ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH))
QEMU_MACHINE := -cpu host -machine q35,accel=kvm
else
-QEMU_MACHINE := -cpu coreduo -machine q35
-CFLAGS += -march=prescott
+QEMU_MACHINE := -cpu max -machine q35
endif
else ifeq ($(ARCH),mips64)
CHOST := mips64-linux-musl
@@ -182,7 +180,7 @@ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
else
-QEMU_MACHINE := -machine pseries
+QEMU_MACHINE := -machine pseries -device spapr-rng,rng=rng -object rng-random,id=rng
endif
else ifeq ($(ARCH),powerpc64le)
CHOST := powerpc64le-linux-musl
@@ -192,7 +190,7 @@ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
else
-QEMU_MACHINE := -machine pseries
+QEMU_MACHINE := -machine pseries -device spapr-rng,rng=rng -object rng-random,id=rng
endif
else ifeq ($(ARCH),powerpc)
CHOST := powerpc-linux-musl
@@ -247,7 +245,7 @@ QEMU_VPORT_RESULT := virtio-serial-ccw
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host,accel=kvm -machine s390-ccw-virtio -append $(KERNEL_CMDLINE)
else
-QEMU_MACHINE := -machine s390-ccw-virtio -append $(KERNEL_CMDLINE)
+QEMU_MACHINE := -cpu max -machine s390-ccw-virtio -append $(KERNEL_CMDLINE)
endif
else
$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64, powerpc64le, powerpc, m68k, riscv64, riscv32, s390x)
diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c
index 2a0f48fac925..c9e128436546 100644
--- a/tools/testing/selftests/wireguard/qemu/init.c
+++ b/tools/testing/selftests/wireguard/qemu/init.c
@@ -21,6 +21,7 @@
#include <sys/utsname.h>
#include <sys/sendfile.h>
#include <sys/sysmacros.h>
+#include <sys/random.h>
#include <linux/random.h>
#include <linux/version.h>
@@ -58,6 +59,8 @@ static void seed_rng(void)
{
int bits = 256, fd;
+ if (!getrandom(NULL, 0, GRND_NONBLOCK))
+ return;
pretty_message("[+] Fake seeding RNG...");
fd = open("/dev/random", O_WRONLY);
if (fd < 0)
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index a9b5a520a1d2..bad88f4b0a03 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -31,6 +31,7 @@ CONFIG_TTY=y
CONFIG_BINFMT_ELF=y
CONFIG_BINFMT_SCRIPT=y
CONFIG_VDSO=y
+CONFIG_STRICT_KERNEL_RWX=y
CONFIG_VIRTUALIZATION=y
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
@@ -65,6 +66,8 @@ CONFIG_PROC_FS=y
CONFIG_PROC_SYSCTL=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
+CONFIG_RANDOM_TRUST_CPU=y
+CONFIG_RANDOM_TRUST_BOOTLOADER=y
CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15
CONFIG_LOG_BUF_SHIFT=18
CONFIG_PRINTK_TIME=y