summaryrefslogtreecommitdiff
path: root/tools/testing/selftests
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests')
-rw-r--r--tools/testing/selftests/Makefile1
-rw-r--r--tools/testing/selftests/bpf/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/Makefile25
-rw-r--r--tools/testing/selftests/bpf/bpf_flow.c2
-rw-r--r--tools/testing/selftests/bpf/bpf_helpers.h4
-rw-r--r--tools/testing/selftests/bpf/config1
-rw-r--r--tools/testing/selftests/bpf/connect4_prog.c45
-rw-r--r--tools/testing/selftests/bpf/connect6_prog.c58
-rw-r--r--tools/testing/selftests/bpf/netcnt_prog.c6
-rw-r--r--tools/testing/selftests/bpf/test_align.c4
-rw-r--r--tools/testing/selftests/bpf/test_btf.c2212
-rw-r--r--tools/testing/selftests/bpf/test_btf_haskv.c16
-rw-r--r--tools/testing/selftests/bpf/test_btf_nokv.c16
-rwxr-xr-xtools/testing/selftests/bpf/test_flow_dissector.sh2
-rwxr-xr-xtools/testing/selftests/bpf/test_libbpf.sh14
-rwxr-xr-xtools/testing/selftests/bpf/test_lirc_mode2.sh3
-rw-r--r--tools/testing/selftests/bpf/test_lirc_mode2_kern.c3
-rw-r--r--tools/testing/selftests/bpf/test_lirc_mode2_user.c65
-rw-r--r--tools/testing/selftests/bpf/test_map_in_map.c49
-rw-r--r--tools/testing/selftests/bpf/test_maps.c154
-rw-r--r--tools/testing/selftests/bpf/test_progs.c75
-rw-r--r--tools/testing/selftests/bpf/test_sock_addr.c28
-rw-r--r--tools/testing/selftests/bpf/test_sockmap.c127
-rw-r--r--tools/testing/selftests/bpf/test_sockmap_kern.h70
-rw-r--r--tools/testing/selftests/bpf/test_tcpnotify.h19
-rw-r--r--tools/testing/selftests/bpf/test_tcpnotify_kern.c95
-rw-r--r--tools/testing/selftests/bpf/test_tcpnotify_user.c186
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c630
-rw-r--r--tools/testing/selftests/bpf/xdp_dummy.c13
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/extack.sh145
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh259
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh565
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh259
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/vxlan.sh1103
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh309
-rw-r--r--tools/testing/selftests/net/.gitignore2
-rw-r--r--tools/testing/selftests/net/Makefile8
-rw-r--r--tools/testing/selftests/net/config14
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh44
-rwxr-xr-xtools/testing/selftests/net/forwarding/router_multicast.sh311
-rwxr-xr-xtools/testing/selftests/net/forwarding/router_vid_1.sh135
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh786
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh10
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh860
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh10
-rw-r--r--tools/testing/selftests/net/msg_zerocopy.c3
-rwxr-xr-xtools/testing/selftests/net/msg_zerocopy.sh2
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh377
-rw-r--r--tools/testing/selftests/net/reuseport_addr_any.c274
-rwxr-xr-xtools/testing/selftests/net/reuseport_addr_any.sh4
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.sh122
-rwxr-xr-xtools/testing/selftests/net/run_afpackettests10
-rwxr-xr-xtools/testing/selftests/net/test_vxlan_under_vrf.sh129
-rw-r--r--tools/testing/selftests/net/txring_overwrite.c179
-rwxr-xr-xtools/testing/selftests/net/udpgro.sh182
-rwxr-xr-xtools/testing/selftests/net/udpgro_bench.sh95
-rwxr-xr-xtools/testing/selftests/net/udpgso_bench.sh5
-rw-r--r--tools/testing/selftests/net/udpgso_bench_rx.c156
-rw-r--r--tools/testing/selftests/net/udpgso_bench_tx.c22
-rwxr-xr-xtools/testing/selftests/net/xfrm_policy.sh302
-rw-r--r--tools/testing/selftests/networking/timestamping/Makefile5
-rw-r--r--tools/testing/selftests/networking/timestamping/config2
-rw-r--r--tools/testing/selftests/networking/timestamping/txtimestamp.c382
-rwxr-xr-xtools/testing/selftests/networking/timestamping/txtimestamp.sh57
-rw-r--r--tools/testing/selftests/tc-testing/.gitignore3
-rw-r--r--tools/testing/selftests/tc-testing/TdcPlugin.py3
-rw-r--r--tools/testing/selftests/tc-testing/TdcResults.py132
-rw-r--r--tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py22
-rwxr-xr-xtools/testing/selftests/tc-testing/tdc.py133
-rw-r--r--tools/testing/selftests/tc-testing/tdc_config.py2
70 files changed, 10949 insertions, 398 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index f0017c831e57..24b9934fb269 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -25,6 +25,7 @@ TARGETS += mount
TARGETS += mqueue
TARGETS += net
TARGETS += netfilter
+TARGETS += networking/timestamping
TARGETS += nsfs
TARGETS += powerpc
TARGETS += proc
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 1b799e30c06d..4a9785043a39 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -27,3 +27,4 @@ test_flow_dissector
flow_dissector_load
test_netcnt
test_section_names
+test_tcpnotify_user
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e39dfb4e7970..73aa6d8f4a2f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -24,12 +24,13 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
- test_netcnt
+ test_netcnt test_tcpnotify_user
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+ test_tcpnotify_kern.o \
sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
@@ -37,7 +38,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
- test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o
+ test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o \
+ xdp_dummy.o test_map_in_map.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
@@ -74,6 +76,7 @@ $(OUTPUT)/test_sock_addr: cgroup_helpers.c
$(OUTPUT)/test_socket_cookie: cgroup_helpers.c
$(OUTPUT)/test_sockmap: cgroup_helpers.c
$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
+$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
$(OUTPUT)/test_progs: trace_helpers.c
$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
@@ -124,7 +127,14 @@ $(OUTPUT)/test_stack_map.o: test_queue_stack_map.h
BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
+BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
+ $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
+ readelf -S ./llvm_btf_verify.o | grep BTF; \
+ /bin/rm -f ./llvm_btf_verify.o)
+ifneq ($(BTF_LLVM_PROBE),)
+ CLANG_FLAGS += -g
+else
ifneq ($(BTF_LLC_PROBE),)
ifneq ($(BTF_PAHOLE_PROBE),)
ifneq ($(BTF_OBJCOPY_PROBE),)
@@ -134,6 +144,17 @@ ifneq ($(BTF_OBJCOPY_PROBE),)
endif
endif
endif
+endif
+
+# Have one program compiled without "-target bpf" to test whether libbpf loads
+# it successfully
+$(OUTPUT)/test_xdp.o: test_xdp.c
+ $(CLANG) $(CLANG_FLAGS) \
+ -O2 -emit-llvm -c $< -o - | \
+ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
+ifeq ($(DWARF2BTF),y)
+ $(BTF_PAHOLE) -J $@
+endif
$(OUTPUT)/%.o: %.c
$(CLANG) $(CLANG_FLAGS) \
diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
index df9d32fd2055..284660f5aa95 100644
--- a/tools/testing/selftests/bpf/bpf_flow.c
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -116,7 +116,7 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
return BPF_DROP;
}
-SEC("dissect")
+SEC("flow_dissector")
int _dissect(struct __sk_buff *skb)
{
if (!skb->vlan_present)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index efb6c13ab0de..6c77cf7bedce 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -113,6 +113,8 @@ static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
(void *) BPF_FUNC_msg_pull_data;
static int (*bpf_msg_push_data)(void *ctx, int start, int end, int flags) =
(void *) BPF_FUNC_msg_push_data;
+static int (*bpf_msg_pop_data)(void *ctx, int start, int cut, int flags) =
+ (void *) BPF_FUNC_msg_pop_data;
static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
(void *) BPF_FUNC_bind;
static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
@@ -168,6 +170,8 @@ static int (*bpf_skb_vlan_push)(void *ctx, __be16 vlan_proto, __u16 vlan_tci) =
(void *) BPF_FUNC_skb_vlan_push;
static int (*bpf_skb_vlan_pop)(void *ctx) =
(void *) BPF_FUNC_skb_vlan_pop;
+static int (*bpf_rc_pointer_rel)(void *ctx, int rel_x, int rel_y) =
+ (void *) BPF_FUNC_rc_pointer_rel;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 7f90d3645af8..37f947ec44ed 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -22,3 +22,4 @@ CONFIG_NET_CLS_FLOWER=m
CONFIG_LWTUNNEL=y
CONFIG_BPF_STREAM_PARSER=y
CONFIG_XDP_SOCKETS=y
+CONFIG_FTRACE_SYSCALLS=y
diff --git a/tools/testing/selftests/bpf/connect4_prog.c b/tools/testing/selftests/bpf/connect4_prog.c
index 5a88a681d2ab..1fd244d35ba9 100644
--- a/tools/testing/selftests/bpf/connect4_prog.c
+++ b/tools/testing/selftests/bpf/connect4_prog.c
@@ -21,23 +21,50 @@ int _version SEC("version") = 1;
SEC("cgroup/connect4")
int connect_v4_prog(struct bpf_sock_addr *ctx)
{
+ struct bpf_sock_tuple tuple = {};
struct sockaddr_in sa;
+ struct bpf_sock *sk;
+
+ /* Verify that new destination is available. */
+ memset(&tuple.ipv4.saddr, 0, sizeof(tuple.ipv4.saddr));
+ memset(&tuple.ipv4.sport, 0, sizeof(tuple.ipv4.sport));
+
+ tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4);
+ tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4);
+
+ if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+ return 0;
+ else if (ctx->type == SOCK_STREAM)
+ sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4),
+ BPF_F_CURRENT_NETNS, 0);
+ else
+ sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4),
+ BPF_F_CURRENT_NETNS, 0);
+
+ if (!sk)
+ return 0;
+
+ if (sk->src_ip4 != tuple.ipv4.daddr ||
+ sk->src_port != DST_REWRITE_PORT4) {
+ bpf_sk_release(sk);
+ return 0;
+ }
+
+ bpf_sk_release(sk);
/* Rewrite destination. */
ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
- if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) {
- ///* Rewrite source. */
- memset(&sa, 0, sizeof(sa));
+ /* Rewrite source. */
+ memset(&sa, 0, sizeof(sa));
- sa.sin_family = AF_INET;
- sa.sin_port = bpf_htons(0);
- sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
+ sa.sin_family = AF_INET;
+ sa.sin_port = bpf_htons(0);
+ sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
- if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
- return 0;
- }
+ if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+ return 0;
return 1;
}
diff --git a/tools/testing/selftests/bpf/connect6_prog.c b/tools/testing/selftests/bpf/connect6_prog.c
index 8ea3f7d12dee..26397ab7b3c7 100644
--- a/tools/testing/selftests/bpf/connect6_prog.c
+++ b/tools/testing/selftests/bpf/connect6_prog.c
@@ -29,7 +29,43 @@ int _version SEC("version") = 1;
SEC("cgroup/connect6")
int connect_v6_prog(struct bpf_sock_addr *ctx)
{
+ struct bpf_sock_tuple tuple = {};
struct sockaddr_in6 sa;
+ struct bpf_sock *sk;
+
+ /* Verify that new destination is available. */
+ memset(&tuple.ipv6.saddr, 0, sizeof(tuple.ipv6.saddr));
+ memset(&tuple.ipv6.sport, 0, sizeof(tuple.ipv6.sport));
+
+ tuple.ipv6.daddr[0] = bpf_htonl(DST_REWRITE_IP6_0);
+ tuple.ipv6.daddr[1] = bpf_htonl(DST_REWRITE_IP6_1);
+ tuple.ipv6.daddr[2] = bpf_htonl(DST_REWRITE_IP6_2);
+ tuple.ipv6.daddr[3] = bpf_htonl(DST_REWRITE_IP6_3);
+
+ tuple.ipv6.dport = bpf_htons(DST_REWRITE_PORT6);
+
+ if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+ return 0;
+ else if (ctx->type == SOCK_STREAM)
+ sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6),
+ BPF_F_CURRENT_NETNS, 0);
+ else
+ sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6),
+ BPF_F_CURRENT_NETNS, 0);
+
+ if (!sk)
+ return 0;
+
+ if (sk->src_ip6[0] != tuple.ipv6.daddr[0] ||
+ sk->src_ip6[1] != tuple.ipv6.daddr[1] ||
+ sk->src_ip6[2] != tuple.ipv6.daddr[2] ||
+ sk->src_ip6[3] != tuple.ipv6.daddr[3] ||
+ sk->src_port != DST_REWRITE_PORT6) {
+ bpf_sk_release(sk);
+ return 0;
+ }
+
+ bpf_sk_release(sk);
/* Rewrite destination. */
ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0);
@@ -39,21 +75,19 @@ int connect_v6_prog(struct bpf_sock_addr *ctx)
ctx->user_port = bpf_htons(DST_REWRITE_PORT6);
- if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) {
- /* Rewrite source. */
- memset(&sa, 0, sizeof(sa));
+ /* Rewrite source. */
+ memset(&sa, 0, sizeof(sa));
- sa.sin6_family = AF_INET6;
- sa.sin6_port = bpf_htons(0);
+ sa.sin6_family = AF_INET6;
+ sa.sin6_port = bpf_htons(0);
- sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0);
- sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1);
- sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2);
- sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3);
+ sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0);
+ sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1);
+ sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2);
+ sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3);
- if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
- return 0;
- }
+ if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+ return 0;
return 1;
}
diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/netcnt_prog.c
index 1198abca1360..9f741e69cebe 100644
--- a/tools/testing/selftests/bpf/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/netcnt_prog.c
@@ -16,12 +16,18 @@ struct bpf_map_def SEC("maps") percpu_netcnt = {
.value_size = sizeof(struct percpu_net_cnt),
};
+BPF_ANNOTATE_KV_PAIR(percpu_netcnt, struct bpf_cgroup_storage_key,
+ struct percpu_net_cnt);
+
struct bpf_map_def SEC("maps") netcnt = {
.type = BPF_MAP_TYPE_CGROUP_STORAGE,
.key_size = sizeof(struct bpf_cgroup_storage_key),
.value_size = sizeof(struct net_cnt),
};
+BPF_ANNOTATE_KV_PAIR(netcnt, struct bpf_cgroup_storage_key,
+ struct net_cnt);
+
SEC("cgroup/skb")
int bpf_nextcnt(struct __sk_buff *skb)
{
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c
index 5f377ec53f2f..3c789d03b629 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/test_align.c
@@ -620,8 +620,8 @@ static int do_test_single(struct bpf_align_test *test)
prog_len = probe_filter_length(prog);
fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
- prog, prog_len, 1, "GPL", 0,
- bpf_vlog, sizeof(bpf_vlog), 2);
+ prog, prog_len, BPF_F_STRICT_ALIGNMENT,
+ "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 2);
if (fd_prog < 0 && test->result != REJECT) {
printf("Failed to load program.\n");
printf("%s", bpf_vlog);
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 38e1cbaaffdb..8bcd38010582 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -5,6 +5,8 @@
#include <linux/btf.h>
#include <linux/err.h>
#include <linux/kernel.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
#include <bpf/bpf.h>
#include <sys/resource.h>
#include <libelf.h>
@@ -22,6 +24,9 @@
#include "bpf_rlimit.h"
#include "bpf_util.h"
+#define MAX_INSNS 512
+#define MAX_SUBPROGS 16
+
static uint32_t pass_cnt;
static uint32_t error_cnt;
static uint32_t skip_cnt;
@@ -60,8 +65,8 @@ static int __base_pr(const char *format, ...)
return err;
}
-#define BTF_INFO_ENC(kind, root, vlen) \
- ((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+#define BTF_INFO_ENC(kind, kind_flag, vlen) \
+ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
#define BTF_TYPE_ENC(name, info, size_or_type) \
(name), (info), (size_or_type)
@@ -81,28 +86,44 @@ static int __base_pr(const char *format, ...)
#define BTF_MEMBER_ENC(name, type, bits_offset) \
(name), (type), (bits_offset)
#define BTF_ENUM_ENC(name, val) (name), (val)
+#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \
+ ((bitfield_size) << 24 | (bits_offset))
#define BTF_TYPEDEF_ENC(name, type) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
-#define BTF_PTR_ENC(name, type) \
- BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
+#define BTF_PTR_ENC(type) \
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
+
+#define BTF_CONST_ENC(type) \
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type)
+
+#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type)
+
+#define BTF_FUNC_PROTO_ARG_ENC(name, type) \
+ (name), (type)
+
+#define BTF_FUNC_ENC(name, func_proto) \
+ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto)
#define BTF_END_RAW 0xdeadbeef
#define NAME_TBD 0xdeadb33f
-#define MAX_NR_RAW_TYPES 1024
+#define MAX_NR_RAW_U32 1024
#define BTF_LOG_BUF_SIZE 65535
static struct args {
unsigned int raw_test_num;
unsigned int file_test_num;
unsigned int get_info_test_num;
+ unsigned int info_raw_test_num;
bool raw_test;
bool file_test;
bool get_info_test;
bool pprint_test;
bool always_log;
+ bool info_raw_test;
} args;
static char btf_log_buf[BTF_LOG_BUF_SIZE];
@@ -118,7 +139,7 @@ struct btf_raw_test {
const char *str_sec;
const char *map_name;
const char *err_str;
- __u32 raw_types[MAX_NR_RAW_TYPES];
+ __u32 raw_types[MAX_NR_RAW_U32];
__u32 str_sec_size;
enum bpf_map_type map_type;
__u32 key_size;
@@ -137,6 +158,9 @@ struct btf_raw_test {
int str_len_delta;
};
+#define BTF_STR_SEC(str) \
+ .str_sec = str, .str_sec_size = sizeof(str)
+
static struct btf_raw_test raw_tests[] = {
/* enum E {
* E0,
@@ -1735,6 +1759,954 @@ static struct btf_raw_test raw_tests[] = {
.map_create_err = true,
},
+{
+ .descr = "func proto (int (*)(int, unsigned int))",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* int (*)(int, unsigned int) */
+ BTF_FUNC_PROTO_ENC(1, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "func proto (vararg)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int, unsigned int, ...) */
+ BTF_FUNC_PROTO_ENC(0, 3), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0, 2),
+ BTF_FUNC_PROTO_ARG_ENC(0, 0),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "func proto (vararg with name)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, unsigned int b, ... c) */
+ BTF_FUNC_PROTO_ENC(0, 3), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 0),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a\0b\0c",
+ .str_sec_size = sizeof("\0a\0b\0c"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 arg#3",
+},
+
+{
+ .descr = "func proto (arg after vararg)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, ..., unsigned int b) */
+ BTF_FUNC_PROTO_ENC(0, 3), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0, 0),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a\0b",
+ .str_sec_size = sizeof("\0a\0b"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 arg#2",
+},
+
+{
+ .descr = "func proto (CONST=>TYPEDEF=>PTR=>FUNC_PROTO)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* typedef void (*func_ptr)(int, unsigned int) */
+ BTF_TYPEDEF_ENC(NAME_TBD, 5), /* [3] */
+ /* const func_ptr */
+ BTF_CONST_ENC(3), /* [4] */
+ BTF_PTR_ENC(6), /* [5] */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [6] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0func_ptr",
+ .str_sec_size = sizeof("\0func_ptr"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ BTF_CONST_ENC(4), /* [3] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 5), /* [4] */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [5] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0func_typedef",
+ .str_sec_size = sizeof("\0func_typedef"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 type_id",
+},
+
+{
+ .descr = "func proto (btf_resolve(arg))",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* void (*)(const void *) */
+ BTF_FUNC_PROTO_ENC(0, 1), /* [2] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 3),
+ BTF_CONST_ENC(4), /* [3] */
+ BTF_PTR_ENC(0), /* [4] */
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "func proto (Not all arg has name)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int, unsigned int b) */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0b",
+ .str_sec_size = sizeof("\0b"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "func proto (Bad arg name_off)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, unsigned int <bad_name_off>) */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0xffffffff, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a",
+ .str_sec_size = sizeof("\0a"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 arg#2",
+},
+
+{
+ .descr = "func proto (Bad arg name)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, unsigned int !!!) */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a\0!!!",
+ .str_sec_size = sizeof("\0a\0!!!"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 arg#2",
+},
+
+{
+ .descr = "func proto (Invalid return type)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* <bad_ret_type> (*)(int, unsigned int) */
+ BTF_FUNC_PROTO_ENC(100, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 return type",
+},
+
+{
+ .descr = "func proto (with func name)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void func_proto(int, unsigned int) */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 2), 0), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0func_proto",
+ .str_sec_size = sizeof("\0func_proto"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 name",
+},
+
+{
+ .descr = "func proto (const void arg)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(const void) */
+ BTF_FUNC_PROTO_ENC(0, 1), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(0, 4),
+ BTF_CONST_ENC(0), /* [4] */
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 arg#1",
+},
+
+{
+ .descr = "func (void func(int a, unsigned int b))",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, unsigned int b) */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ /* void func(int a, unsigned int b) */
+ BTF_FUNC_ENC(NAME_TBD, 3), /* [4] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a\0b\0func",
+ .str_sec_size = sizeof("\0a\0b\0func"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "func (No func name)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, unsigned int b) */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ /* void <no_name>(int a, unsigned int b) */
+ BTF_FUNC_ENC(0, 3), /* [4] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a\0b",
+ .str_sec_size = sizeof("\0a\0b"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_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 name",
+},
+
+{
+ .descr = "func (Invalid func name)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, unsigned int b) */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ /* void !!!(int a, unsigned int b) */
+ BTF_FUNC_ENC(NAME_TBD, 3), /* [4] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a\0b\0!!!",
+ .str_sec_size = sizeof("\0a\0b\0!!!"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_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 name",
+},
+
+{
+ .descr = "func (Some arg has no name)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, unsigned int) */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(0, 2),
+ /* void func(int a, unsigned int) */
+ BTF_FUNC_ENC(NAME_TBD, 3), /* [4] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a\0func",
+ .str_sec_size = sizeof("\0a\0func"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_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 arg#2",
+},
+
+{
+ .descr = "func (Non zero vlen)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */
+ /* void (*)(int a, unsigned int b) */
+ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ /* void func(int a, unsigned int b) */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 2), 3), /* [4] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0a\0b\0func",
+ .str_sec_size = sizeof("\0a\0b\0func"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_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 = "vlen != 0",
+},
+
+{
+ .descr = "func (Not referring to FUNC_PROTO)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_FUNC_ENC(NAME_TBD, 1), /* [2] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0func",
+ .str_sec_size = sizeof("\0func"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_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 type_id",
+},
+
+{
+ .descr = "invalid int 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_INT, 1, 0), 4), /* [2] */
+ BTF_INT_ENC(0, 0, 32),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "int_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 = "invalid ptr 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_PTR, 1, 0), 1), /* [2] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "ptr_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 = "invalid array 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_ARRAY, 1, 0), 0), /* [2] */
+ BTF_ARRAY_ENC(1, 1, 1),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_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 = "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] */
+ BTF_TYPE_ENC(NAME_TBD,
+ BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [2] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "fwd_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "invalid typedef kind_flag",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(NAME_TBD,
+ BTF_INFO_ENC(BTF_KIND_TYPEDEF, 1, 0), 1), /* [2] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "typedef_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 = "invalid volatile 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_VOLATILE, 1, 0), 1), /* [2] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "volatile_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 = "invalid const 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_CONST, 1, 0), 1), /* [2] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "const_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 = "invalid restrict 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_RESTRICT, 1, 0), 1), /* [2] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "restrict_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 = "invalid func 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_FUNC_PROTO, 0, 0), 0), /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC, 1, 0), 2), /* [3] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_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 = "invalid func_proto 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_FUNC_PROTO, 1, 0), 0), /* [2] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "func_proto_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 struct, kind_flag, bitfield_size = 0",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 8), /* [2] */
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(0, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(0, 32)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "valid struct, kind_flag, int member, bitfield_size != 0",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4), /* [2] */
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 4)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "valid union, kind_flag, int member, bitfield_size != 0",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4), /* [2] */
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "union_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "valid struct, kind_flag, enum member, bitfield_size != 0",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), /* [2] */
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),/* [3] */
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 4)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B\0C"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "valid union, kind_flag, enum member, bitfield_size != 0",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), /* [2] */
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4), /* [3] */
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B\0C"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "union_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "valid struct, kind_flag, typedef member, bitfield_size != 0",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), /* [2] */
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),/* [3] */
+ BTF_MEMBER_ENC(NAME_TBD, 4, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 5, BTF_MEMBER_OFFSET(4, 4)),
+ BTF_TYPEDEF_ENC(NAME_TBD, 1), /* [4] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 2), /* [5] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B\0C\0D\0E"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "valid union, kind_flag, typedef member, bitfield_size != 0",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), /* [2] */
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4), /* [3] */
+ BTF_MEMBER_ENC(NAME_TBD, 4, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 5, BTF_MEMBER_OFFSET(4, 0)),
+ BTF_TYPEDEF_ENC(NAME_TBD, 1), /* [4] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 2), /* [5] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B\0C\0D\0E"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "union_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "invalid struct, kind_flag, bitfield_size greater than struct size",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4), /* [2] */
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 20)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_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 = "Member exceeds struct_size",
+},
+
+{
+ .descr = "invalid struct, kind_flag, bitfield base_type int not regular",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 20, 4), /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4), /* [3] */
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(20, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(20, 20)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_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 member base type",
+},
+
+{
+ .descr = "invalid struct, kind_flag, base_type int not regular",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 12, 4), /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4), /* [3] */
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(8, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(8, 8)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_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 member base type",
+},
+
+{
+ .descr = "invalid union, kind_flag, bitfield_size greater than struct size",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 2), /* [2] */
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(8, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 0)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "union_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 = "Member exceeds struct_size",
+},
+
+{
+ .descr = "invalid struct, kind_flag, int member, bitfield_size = 0, wrong byte alignment",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 12), /* [3] */
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 36)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_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 member offset",
+},
+
+{
+ .descr = "invalid struct, kind_flag, enum member, bitfield_size = 0, wrong byte alignment",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), /* [2] */
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 12), /* [3] */
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 0)),
+ BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 36)),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0A\0B\0C"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_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 member offset",
+},
+
}; /* struct btf_raw_test raw_tests[] */
static const char *get_next_str(const char *start, const char *end)
@@ -1742,11 +2714,11 @@ static const char *get_next_str(const char *start, const char *end)
return start < end - 1 ? start + 1 : NULL;
}
-static int get_type_sec_size(const __u32 *raw_types)
+static int get_raw_sec_size(const __u32 *raw_types)
{
int i;
- for (i = MAX_NR_RAW_TYPES - 1;
+ for (i = MAX_NR_RAW_U32 - 1;
i >= 0 && raw_types[i] != BTF_END_RAW;
i--)
;
@@ -1758,7 +2730,8 @@ static void *btf_raw_create(const struct btf_header *hdr,
const __u32 *raw_types,
const char *str,
unsigned int str_sec_size,
- unsigned int *btf_size)
+ unsigned int *btf_size,
+ const char **ret_next_str)
{
const char *next_str = str, *end_str = str + str_sec_size;
unsigned int size_needed, offset;
@@ -1767,7 +2740,7 @@ static void *btf_raw_create(const struct btf_header *hdr,
uint32_t *ret_types;
void *raw_btf;
- type_sec_size = get_type_sec_size(raw_types);
+ type_sec_size = get_raw_sec_size(raw_types);
if (CHECK(type_sec_size < 0, "Cannot get nr_raw_types"))
return NULL;
@@ -1806,6 +2779,8 @@ static void *btf_raw_create(const struct btf_header *hdr,
ret_hdr->str_len = str_sec_size;
*btf_size = size_needed;
+ if (ret_next_str)
+ *ret_next_str = next_str;
return raw_btf;
}
@@ -1825,7 +2800,7 @@ static int do_test_raw(unsigned int test_num)
test->raw_types,
test->str_sec,
test->str_sec_size,
- &raw_btf_size);
+ &raw_btf_size, NULL);
if (!raw_btf)
return -1;
@@ -1902,7 +2877,7 @@ static int test_raw(void)
struct btf_get_info_test {
const char *descr;
const char *str_sec;
- __u32 raw_types[MAX_NR_RAW_TYPES];
+ __u32 raw_types[MAX_NR_RAW_U32];
__u32 str_sec_size;
int btf_size_delta;
int (*special_test)(unsigned int test_num);
@@ -1982,7 +2957,7 @@ static int test_big_btf_info(unsigned int test_num)
test->raw_types,
test->str_sec,
test->str_sec_size,
- &raw_btf_size);
+ &raw_btf_size, NULL);
if (!raw_btf)
return -1;
@@ -2066,7 +3041,7 @@ static int test_btf_id(unsigned int test_num)
test->raw_types,
test->str_sec,
test->str_sec_size,
- &raw_btf_size);
+ &raw_btf_size, NULL);
if (!raw_btf)
return -1;
@@ -2204,7 +3179,7 @@ static int do_test_get_info(unsigned int test_num)
test->raw_types,
test->str_sec,
test->str_sec_size,
- &raw_btf_size);
+ &raw_btf_size, NULL);
if (!raw_btf)
return -1;
@@ -2301,13 +3276,13 @@ static struct btf_file_test file_tests[] = {
},
};
-static int file_has_btf_elf(const char *fn)
+static int file_has_btf_elf(const char *fn, bool *has_btf_ext)
{
Elf_Scn *scn = NULL;
GElf_Ehdr ehdr;
+ int ret = 0;
int elf_fd;
Elf *elf;
- int ret;
if (CHECK(elf_version(EV_CURRENT) == EV_NONE,
"elf_version(EV_CURRENT) == EV_NONE"))
@@ -2339,14 +3314,12 @@ static int file_has_btf_elf(const char *fn)
}
sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
- if (!strcmp(sh_name, BTF_ELF_SEC)) {
+ if (!strcmp(sh_name, BTF_ELF_SEC))
ret = 1;
- goto done;
- }
+ if (!strcmp(sh_name, BTF_EXT_ELF_SEC))
+ *has_btf_ext = true;
}
- ret = 0;
-
done:
close(elf_fd);
elf_end(elf);
@@ -2356,15 +3329,24 @@ done:
static int do_test_file(unsigned int test_num)
{
const struct btf_file_test *test = &file_tests[test_num - 1];
+ const char *expected_fnames[] = {"_dummy_tracepoint",
+ "test_long_fname_1",
+ "test_long_fname_2"};
+ struct bpf_prog_info info = {};
struct bpf_object *obj = NULL;
+ struct bpf_func_info *finfo;
struct bpf_program *prog;
+ __u32 info_len, rec_size;
+ bool has_btf_ext = false;
+ struct btf *btf = NULL;
+ void *func_info = NULL;
struct bpf_map *map;
- int err;
+ int i, err, prog_fd;
fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num,
test->file);
- err = file_has_btf_elf(test->file);
+ err = file_has_btf_elf(test->file, &has_btf_ext);
if (err == -1)
return err;
@@ -2392,6 +3374,7 @@ static int do_test_file(unsigned int test_num)
err = bpf_object__load(obj);
if (CHECK(err < 0, "bpf_object__load: %d", err))
goto done;
+ prog_fd = bpf_program__fd(prog);
map = bpf_object__find_map_by_name(obj, "btf_map");
if (CHECK(!map, "btf_map not found")) {
@@ -2406,9 +3389,100 @@ static int do_test_file(unsigned int test_num)
test->btf_kv_notfound))
goto done;
+ if (!has_btf_ext)
+ goto skip;
+
+ /* get necessary program info */
+ info_len = sizeof(struct bpf_prog_info);
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+
+ if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
+ fprintf(stderr, "%s\n", btf_log_buf);
+ err = -1;
+ goto done;
+ }
+ if (CHECK(info.nr_func_info != 3,
+ "incorrect info.nr_func_info (1st) %d",
+ info.nr_func_info)) {
+ err = -1;
+ goto done;
+ }
+ rec_size = info.func_info_rec_size;
+ if (CHECK(rec_size != sizeof(struct bpf_func_info),
+ "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) {
+ err = -1;
+ goto done;
+ }
+
+ func_info = malloc(info.nr_func_info * rec_size);
+ if (CHECK(!func_info, "out of memory")) {
+ err = -1;
+ goto done;
+ }
+
+ /* reset info to only retrieve func_info related data */
+ memset(&info, 0, sizeof(info));
+ info.nr_func_info = 3;
+ info.func_info_rec_size = rec_size;
+ info.func_info = ptr_to_u64(func_info);
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+
+ if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) {
+ fprintf(stderr, "%s\n", btf_log_buf);
+ err = -1;
+ goto done;
+ }
+ if (CHECK(info.nr_func_info != 3,
+ "incorrect info.nr_func_info (2nd) %d",
+ info.nr_func_info)) {
+ err = -1;
+ goto done;
+ }
+ if (CHECK(info.func_info_rec_size != rec_size,
+ "incorrect info.func_info_rec_size (2nd) %d",
+ info.func_info_rec_size)) {
+ err = -1;
+ goto done;
+ }
+
+ err = btf__get_from_id(info.btf_id, &btf);
+ if (CHECK(err, "cannot get btf from kernel, err: %d", err))
+ goto done;
+
+ /* check three functions */
+ finfo = func_info;
+ for (i = 0; i < 3; i++) {
+ const struct btf_type *t;
+ const char *fname;
+
+ t = btf__type_by_id(btf, finfo->type_id);
+ if (CHECK(!t, "btf__type_by_id failure: id %u",
+ finfo->type_id)) {
+ err = -1;
+ goto done;
+ }
+
+ fname = btf__name_by_offset(btf, t->name_off);
+ err = strcmp(fname, expected_fnames[i]);
+ /* for the second and third functions in .text section,
+ * the compiler may order them either way.
+ */
+ if (i && err)
+ err = strcmp(fname, expected_fnames[3 - i]);
+ if (CHECK(err, "incorrect fname %s", fname ? : "")) {
+ err = -1;
+ goto done;
+ }
+
+ finfo = (void *)finfo + rec_size;
+ }
+
+skip:
fprintf(stderr, "OK");
done:
+ free(func_info);
bpf_object__close(obj);
return err;
}
@@ -2454,7 +3528,8 @@ struct pprint_mapv {
} aenum;
};
-static struct btf_raw_test pprint_test_template = {
+static struct btf_raw_test pprint_test_template[] = {
+{
.raw_types = {
/* unsighed char */ /* [1] */
BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
@@ -2504,13 +3579,140 @@ static struct btf_raw_test pprint_test_template = {
BTF_MEMBER_ENC(NAME_TBD, 15, 192), /* aenum */
BTF_END_RAW,
},
- .str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum",
- .str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
+ BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
+ .key_size = sizeof(unsigned int),
+ .value_size = sizeof(struct pprint_mapv),
+ .key_type_id = 3, /* unsigned int */
+ .value_type_id = 16, /* struct pprint_mapv */
+ .max_entries = 128 * 1024,
+},
+
+{
+ /* this type will have the same type as the
+ * first .raw_types definition, but struct type will
+ * be encoded with kind_flag set.
+ */
+ .raw_types = {
+ /* unsighed char */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
+ /* unsigned short */ /* [2] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
+ /* unsigned int */ /* [3] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),
+ /* int */ /* [4] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ /* unsigned long long */ /* [5] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [6] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [7] */
+ /* uint8_t[8] */ /* [8] */
+ BTF_TYPE_ARRAY_ENC(9, 1, 8),
+ /* typedef unsigned char uint8_t */ /* [9] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 1),
+ /* typedef unsigned short uint16_t */ /* [10] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 2),
+ /* typedef unsigned int uint32_t */ /* [11] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 3),
+ /* typedef int int32_t */ /* [12] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 4),
+ /* typedef unsigned long long uint64_t *//* [13] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 5),
+ /* union (anon) */ /* [14] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8),
+ BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */
+ BTF_MEMBER_ENC(NAME_TBD, 8, 0), /* uint8_t ui8a[8]; */
+ /* enum (anon) */ /* [15] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4),
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_ENUM_ENC(NAME_TBD, 1),
+ BTF_ENUM_ENC(NAME_TBD, 2),
+ BTF_ENUM_ENC(NAME_TBD, 3),
+ /* struct pprint_mapv */ /* [16] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 8), 32),
+ BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)), /* uint32_t ui32 */
+ BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)), /* uint16_t ui16 */
+ BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)), /* int32_t si32 */
+ BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 96)), /* unused_bits2a */
+ BTF_MEMBER_ENC(NAME_TBD, 7, BTF_MEMBER_OFFSET(28, 98)), /* bits28 */
+ BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 126)), /* unused_bits2b */
+ BTF_MEMBER_ENC(0, 14, BTF_MEMBER_OFFSET(0, 128)), /* union (anon) */
+ BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)), /* aenum */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
+ .key_size = sizeof(unsigned int),
+ .value_size = sizeof(struct pprint_mapv),
+ .key_type_id = 3, /* unsigned int */
+ .value_type_id = 16, /* struct pprint_mapv */
+ .max_entries = 128 * 1024,
+},
+
+{
+ /* this type will have the same layout as the
+ * first .raw_types definition. The struct type will
+ * be encoded with kind_flag set, bitfield members
+ * are added typedef/const/volatile, and bitfield members
+ * will have both int and enum types.
+ */
+ .raw_types = {
+ /* unsighed char */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
+ /* unsigned short */ /* [2] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
+ /* unsigned int */ /* [3] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),
+ /* int */ /* [4] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ /* unsigned long long */ /* [5] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [6] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [7] */
+ /* uint8_t[8] */ /* [8] */
+ BTF_TYPE_ARRAY_ENC(9, 1, 8),
+ /* typedef unsigned char uint8_t */ /* [9] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 1),
+ /* typedef unsigned short uint16_t */ /* [10] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 2),
+ /* typedef unsigned int uint32_t */ /* [11] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 3),
+ /* typedef int int32_t */ /* [12] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 4),
+ /* typedef unsigned long long uint64_t *//* [13] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 5),
+ /* union (anon) */ /* [14] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8),
+ BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */
+ BTF_MEMBER_ENC(NAME_TBD, 8, 0), /* uint8_t ui8a[8]; */
+ /* enum (anon) */ /* [15] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4),
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_ENUM_ENC(NAME_TBD, 1),
+ BTF_ENUM_ENC(NAME_TBD, 2),
+ BTF_ENUM_ENC(NAME_TBD, 3),
+ /* struct pprint_mapv */ /* [16] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 8), 32),
+ BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)), /* uint32_t ui32 */
+ BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)), /* uint16_t ui16 */
+ BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)), /* int32_t si32 */
+ BTF_MEMBER_ENC(NAME_TBD, 17, BTF_MEMBER_OFFSET(2, 96)), /* unused_bits2a */
+ BTF_MEMBER_ENC(NAME_TBD, 7, BTF_MEMBER_OFFSET(28, 98)), /* bits28 */
+ BTF_MEMBER_ENC(NAME_TBD, 19, BTF_MEMBER_OFFSET(2, 126)),/* unused_bits2b */
+ BTF_MEMBER_ENC(0, 14, BTF_MEMBER_OFFSET(0, 128)), /* union (anon) */
+ BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)), /* aenum */
+ /* typedef unsigned int ___int */ /* [17] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 18),
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), 6), /* [18] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 15), /* [19] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0___int"),
.key_size = sizeof(unsigned int),
.value_size = sizeof(struct pprint_mapv),
.key_type_id = 3, /* unsigned int */
.value_type_id = 16, /* struct pprint_mapv */
.max_entries = 128 * 1024,
+},
+
};
static struct btf_pprint_test_meta {
@@ -2613,9 +3815,9 @@ static int check_line(const char *expected_line, int nexpected_line,
}
-static int do_test_pprint(void)
+static int do_test_pprint(int test_num)
{
- const struct btf_raw_test *test = &pprint_test_template;
+ const struct btf_raw_test *test = &pprint_test_template[test_num];
struct bpf_create_map_attr create_attr = {};
bool ordered_map, lossless_map, percpu_map;
int err, ret, num_cpus, rounded_value_size;
@@ -2631,10 +3833,10 @@ static int do_test_pprint(void)
uint8_t *raw_btf;
ssize_t nread;
- fprintf(stderr, "%s......", test->descr);
+ fprintf(stderr, "%s(#%d)......", test->descr, test_num);
raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
test->str_sec, test->str_sec_size,
- &raw_btf_size);
+ &raw_btf_size, NULL);
if (!raw_btf)
return -1;
@@ -2824,30 +4026,940 @@ static int test_pprint(void)
unsigned int i;
int err = 0;
+ /* test various maps with the first test template */
for (i = 0; i < ARRAY_SIZE(pprint_tests_meta); i++) {
- pprint_test_template.descr = pprint_tests_meta[i].descr;
- pprint_test_template.map_type = pprint_tests_meta[i].map_type;
- pprint_test_template.map_name = pprint_tests_meta[i].map_name;
- pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map;
- pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map;
- pprint_test_template.percpu_map = pprint_tests_meta[i].percpu_map;
+ pprint_test_template[0].descr = pprint_tests_meta[i].descr;
+ pprint_test_template[0].map_type = pprint_tests_meta[i].map_type;
+ pprint_test_template[0].map_name = pprint_tests_meta[i].map_name;
+ pprint_test_template[0].ordered_map = pprint_tests_meta[i].ordered_map;
+ pprint_test_template[0].lossless_map = pprint_tests_meta[i].lossless_map;
+ pprint_test_template[0].percpu_map = pprint_tests_meta[i].percpu_map;
+
+ err |= count_result(do_test_pprint(0));
+ }
- err |= count_result(do_test_pprint());
+ /* test rest test templates with the first map */
+ for (i = 1; i < ARRAY_SIZE(pprint_test_template); i++) {
+ pprint_test_template[i].descr = pprint_tests_meta[0].descr;
+ pprint_test_template[i].map_type = pprint_tests_meta[0].map_type;
+ pprint_test_template[i].map_name = pprint_tests_meta[0].map_name;
+ pprint_test_template[i].ordered_map = pprint_tests_meta[0].ordered_map;
+ pprint_test_template[i].lossless_map = pprint_tests_meta[0].lossless_map;
+ pprint_test_template[i].percpu_map = pprint_tests_meta[0].percpu_map;
+ err |= count_result(do_test_pprint(i));
}
return err;
}
+#define BPF_LINE_INFO_ENC(insn_off, file_off, line_off, line_num, line_col) \
+ (insn_off), (file_off), (line_off), ((line_num) << 10 | ((line_col) & 0x3ff))
+
+static struct prog_info_raw_test {
+ const char *descr;
+ const char *str_sec;
+ const char *err_str;
+ __u32 raw_types[MAX_NR_RAW_U32];
+ __u32 str_sec_size;
+ struct bpf_insn insns[MAX_INSNS];
+ __u32 prog_type;
+ __u32 func_info[MAX_SUBPROGS][2];
+ __u32 func_info_rec_size;
+ __u32 func_info_cnt;
+ __u32 line_info[MAX_NR_RAW_U32];
+ __u32 line_info_rec_size;
+ __u32 nr_jited_ksyms;
+ bool expected_prog_load_failure;
+} info_raw_tests[] = {
+{
+ .descr = "func_type (main func + one sub)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), /* [2] */
+ BTF_FUNC_PROTO_ENC(1, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ENC(1, 2), /* [4] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_ENC(NAME_TBD, 3), /* [5] */
+ BTF_FUNC_ENC(NAME_TBD, 4), /* [6] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+ .str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info = { {0, 5}, {3, 6} },
+ .func_info_rec_size = 8,
+ .func_info_cnt = 2,
+ .line_info = { BTF_END_RAW },
+},
+
+{
+ .descr = "func_type (Incorrect func_info_rec_size)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), /* [2] */
+ BTF_FUNC_PROTO_ENC(1, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ENC(1, 2), /* [4] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_ENC(NAME_TBD, 3), /* [5] */
+ BTF_FUNC_ENC(NAME_TBD, 4), /* [6] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+ .str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info = { {0, 5}, {3, 6} },
+ .func_info_rec_size = 4,
+ .func_info_cnt = 2,
+ .line_info = { BTF_END_RAW },
+ .expected_prog_load_failure = true,
+},
+
+{
+ .descr = "func_type (Incorrect func_info_cnt)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), /* [2] */
+ BTF_FUNC_PROTO_ENC(1, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ENC(1, 2), /* [4] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_ENC(NAME_TBD, 3), /* [5] */
+ BTF_FUNC_ENC(NAME_TBD, 4), /* [6] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+ .str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info = { {0, 5}, {3, 6} },
+ .func_info_rec_size = 8,
+ .func_info_cnt = 1,
+ .line_info = { BTF_END_RAW },
+ .expected_prog_load_failure = true,
+},
+
+{
+ .descr = "func_type (Incorrect bpf_func_info.insn_off)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), /* [2] */
+ BTF_FUNC_PROTO_ENC(1, 2), /* [3] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ENC(1, 2), /* [4] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_ENC(NAME_TBD, 3), /* [5] */
+ BTF_FUNC_ENC(NAME_TBD, 4), /* [6] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+ .str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info = { {0, 5}, {2, 6} },
+ .func_info_rec_size = 8,
+ .func_info_cnt = 2,
+ .line_info = { BTF_END_RAW },
+ .expected_prog_load_failure = true,
+},
+
+{
+ .descr = "line_info (No subprog)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0int a=1;\0int b=2;\0return a + b;\0return a + b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+ BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 2, 9),
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+ BPF_LINE_INFO_ENC(3, 0, NAME_TBD, 4, 7),
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info),
+ .nr_jited_ksyms = 1,
+},
+
+{
+ .descr = "line_info (No subprog. insn_off >= prog->len)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0int a=1;\0int b=2;\0return a + b;\0return a + b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+ BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 2, 9),
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+ BPF_LINE_INFO_ENC(3, 0, NAME_TBD, 4, 7),
+ BPF_LINE_INFO_ENC(4, 0, 0, 5, 6),
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info),
+ .nr_jited_ksyms = 1,
+ .err_str = "line_info[4].insn_off",
+ .expected_prog_load_failure = true,
+},
+
+{
+ .descr = "line_info (Zero bpf insn code)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8), /* [2] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 2), /* [3] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0unsigned long\0u64\0u64 a=1;\0return a;"),
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+ BPF_LINE_INFO_ENC(1, 0, 0, 2, 9),
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info),
+ .nr_jited_ksyms = 1,
+ .err_str = "Invalid insn code at line_info[1]",
+ .expected_prog_load_failure = true,
+},
+
+{
+ .descr = "line_info (No subprog. zero tailing line_info",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0int a=1;\0int b=2;\0return a + b;\0return a + b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10), 0,
+ BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 2, 9), 0,
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8), 0,
+ BPF_LINE_INFO_ENC(3, 0, NAME_TBD, 4, 7), 0,
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info) + sizeof(__u32),
+ .nr_jited_ksyms = 1,
+},
+
+{
+ .descr = "line_info (No subprog. nonzero tailing line_info)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0int a=1;\0int b=2;\0return a + b;\0return a + b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10), 0,
+ BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 2, 9), 0,
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8), 0,
+ BPF_LINE_INFO_ENC(3, 0, NAME_TBD, 4, 7), 1,
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info) + sizeof(__u32),
+ .nr_jited_ksyms = 1,
+ .err_str = "nonzero tailing record in line_info",
+ .expected_prog_load_failure = true,
+},
+
+{
+ .descr = "line_info (subprog)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_CALL_REL(1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 2, 9),
+ BPF_LINE_INFO_ENC(5, 0, NAME_TBD, 3, 8),
+ BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info),
+ .nr_jited_ksyms = 2,
+},
+
+{
+ .descr = "line_info (subprog + func_info)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_FUNC_PROTO_ENC(1, 1), /* [2] */
+ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+ BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */
+ BTF_FUNC_ENC(NAME_TBD, 2), /* [4] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0x\0sub\0main\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_CALL_REL(1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 2,
+ .func_info_rec_size = 8,
+ .func_info = { {0, 4}, {5, 3} },
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 2, 9),
+ BPF_LINE_INFO_ENC(5, 0, NAME_TBD, 3, 8),
+ BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info),
+ .nr_jited_ksyms = 2,
+},
+
+{
+ .descr = "line_info (subprog. missing 1st func line info)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_CALL_REL(1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 1, 10),
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 2, 9),
+ BPF_LINE_INFO_ENC(5, 0, NAME_TBD, 3, 8),
+ BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info),
+ .nr_jited_ksyms = 2,
+ .err_str = "missing bpf_line_info for func#0",
+ .expected_prog_load_failure = true,
+},
+
+{
+ .descr = "line_info (subprog. missing 2nd func line info)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_CALL_REL(1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 2, 9),
+ BPF_LINE_INFO_ENC(6, 0, NAME_TBD, 3, 8),
+ BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info),
+ .nr_jited_ksyms = 2,
+ .err_str = "missing bpf_line_info for func#1",
+ .expected_prog_load_failure = true,
+},
+
+{
+ .descr = "line_info (subprog. unordered insn offset)",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0int\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_CALL_REL(1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .func_info_cnt = 0,
+ .line_info = {
+ BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+ BPF_LINE_INFO_ENC(5, 0, NAME_TBD, 2, 9),
+ BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+ BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+ BTF_END_RAW,
+ },
+ .line_info_rec_size = sizeof(struct bpf_line_info),
+ .nr_jited_ksyms = 2,
+ .err_str = "Invalid line_info[2].insn_off",
+ .expected_prog_load_failure = true,
+},
+
+};
+
+static size_t probe_prog_length(const struct bpf_insn *fp)
+{
+ size_t len;
+
+ for (len = MAX_INSNS - 1; len > 0; --len)
+ if (fp[len].code != 0 || fp[len].imm != 0)
+ break;
+ return len + 1;
+}
+
+static __u32 *patch_name_tbd(const __u32 *raw_u32,
+ const char *str, __u32 str_off,
+ unsigned int str_sec_size,
+ unsigned int *ret_size)
+{
+ int i, raw_u32_size = get_raw_sec_size(raw_u32);
+ const char *end_str = str + str_sec_size;
+ const char *next_str = str + str_off;
+ __u32 *new_u32 = NULL;
+
+ if (raw_u32_size == -1)
+ return ERR_PTR(-EINVAL);
+
+ if (!raw_u32_size) {
+ *ret_size = 0;
+ return NULL;
+ }
+
+ new_u32 = malloc(raw_u32_size);
+ if (!new_u32)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < raw_u32_size / sizeof(raw_u32[0]); i++) {
+ if (raw_u32[i] == NAME_TBD) {
+ next_str = get_next_str(next_str, end_str);
+ if (CHECK(!next_str, "Error in getting next_str\n")) {
+ free(new_u32);
+ return ERR_PTR(-EINVAL);
+ }
+ new_u32[i] = next_str - str;
+ next_str += strlen(next_str);
+ } else {
+ new_u32[i] = raw_u32[i];
+ }
+ }
+
+ *ret_size = raw_u32_size;
+ return new_u32;
+}
+
+static int test_get_finfo(const struct prog_info_raw_test *test,
+ int prog_fd)
+{
+ struct bpf_prog_info info = {};
+ struct bpf_func_info *finfo;
+ __u32 info_len, rec_size, i;
+ void *func_info = NULL;
+ int err;
+
+ /* get necessary lens */
+ info_len = sizeof(struct bpf_prog_info);
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
+ fprintf(stderr, "%s\n", btf_log_buf);
+ return -1;
+ }
+ if (CHECK(info.nr_func_info != test->func_info_cnt,
+ "incorrect info.nr_func_info (1st) %d",
+ info.nr_func_info)) {
+ return -1;
+ }
+
+ rec_size = info.func_info_rec_size;
+ if (CHECK(rec_size != sizeof(struct bpf_func_info),
+ "incorrect info.func_info_rec_size (1st) %d", rec_size)) {
+ return -1;
+ }
+
+ if (!info.nr_func_info)
+ return 0;
+
+ func_info = malloc(info.nr_func_info * rec_size);
+ if (CHECK(!func_info, "out of memory"))
+ return -1;
+
+ /* reset info to only retrieve func_info related data */
+ memset(&info, 0, sizeof(info));
+ info.nr_func_info = test->func_info_cnt;
+ info.func_info_rec_size = rec_size;
+ info.func_info = ptr_to_u64(func_info);
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) {
+ fprintf(stderr, "%s\n", btf_log_buf);
+ err = -1;
+ goto done;
+ }
+ if (CHECK(info.nr_func_info != test->func_info_cnt,
+ "incorrect info.nr_func_info (2nd) %d",
+ info.nr_func_info)) {
+ err = -1;
+ goto done;
+ }
+ if (CHECK(info.func_info_rec_size != rec_size,
+ "incorrect info.func_info_rec_size (2nd) %d",
+ info.func_info_rec_size)) {
+ err = -1;
+ goto done;
+ }
+
+ finfo = func_info;
+ for (i = 0; i < test->func_info_cnt; i++) {
+ if (CHECK(finfo->type_id != test->func_info[i][1],
+ "incorrect func_type %u expected %u",
+ finfo->type_id, test->func_info[i][1])) {
+ err = -1;
+ goto done;
+ }
+ finfo = (void *)finfo + rec_size;
+ }
+
+ err = 0;
+
+done:
+ free(func_info);
+ return err;
+}
+
+static int test_get_linfo(const struct prog_info_raw_test *test,
+ const void *patched_linfo,
+ __u32 cnt, int prog_fd)
+{
+ __u32 i, info_len, nr_jited_ksyms, nr_jited_func_lens;
+ __u64 *jited_linfo = NULL, *jited_ksyms = NULL;
+ __u32 rec_size, jited_rec_size, jited_cnt;
+ struct bpf_line_info *linfo = NULL;
+ __u32 cur_func_len, ksyms_found;
+ struct bpf_prog_info info = {};
+ __u32 *jited_func_lens = NULL;
+ __u64 cur_func_ksyms;
+ int err;
+
+ jited_cnt = cnt;
+ rec_size = sizeof(*linfo);
+ jited_rec_size = sizeof(*jited_linfo);
+ if (test->nr_jited_ksyms)
+ nr_jited_ksyms = test->nr_jited_ksyms;
+ else
+ nr_jited_ksyms = test->func_info_cnt;
+ nr_jited_func_lens = nr_jited_ksyms;
+
+ info_len = sizeof(struct bpf_prog_info);
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (CHECK(err == -1, "err:%d errno:%d", err, errno)) {
+ err = -1;
+ goto done;
+ }
+
+ if (!info.jited_prog_len) {
+ /* prog is not jited */
+ jited_cnt = 0;
+ nr_jited_ksyms = 1;
+ nr_jited_func_lens = 1;
+ }
+
+ if (CHECK(info.nr_line_info != cnt ||
+ info.nr_jited_line_info != jited_cnt ||
+ info.nr_jited_ksyms != nr_jited_ksyms ||
+ info.nr_jited_func_lens != nr_jited_func_lens ||
+ (!info.nr_line_info && info.nr_jited_line_info),
+ "info: nr_line_info:%u(expected:%u) nr_jited_line_info:%u(expected:%u) nr_jited_ksyms:%u(expected:%u) nr_jited_func_lens:%u(expected:%u)",
+ info.nr_line_info, cnt,
+ info.nr_jited_line_info, jited_cnt,
+ info.nr_jited_ksyms, nr_jited_ksyms,
+ info.nr_jited_func_lens, nr_jited_func_lens)) {
+ err = -1;
+ goto done;
+ }
+
+ if (CHECK(info.line_info_rec_size != sizeof(struct bpf_line_info) ||
+ info.jited_line_info_rec_size != sizeof(__u64),
+ "info: line_info_rec_size:%u(userspace expected:%u) jited_line_info_rec_size:%u(userspace expected:%u)",
+ info.line_info_rec_size, rec_size,
+ info.jited_line_info_rec_size, jited_rec_size)) {
+ err = -1;
+ goto done;
+ }
+
+ if (!cnt)
+ return 0;
+
+ rec_size = info.line_info_rec_size;
+ jited_rec_size = info.jited_line_info_rec_size;
+
+ memset(&info, 0, sizeof(info));
+
+ linfo = calloc(cnt, rec_size);
+ if (CHECK(!linfo, "!linfo")) {
+ err = -1;
+ goto done;
+ }
+ info.nr_line_info = cnt;
+ info.line_info_rec_size = rec_size;
+ info.line_info = ptr_to_u64(linfo);
+
+ if (jited_cnt) {
+ jited_linfo = calloc(jited_cnt, jited_rec_size);
+ jited_ksyms = calloc(nr_jited_ksyms, sizeof(*jited_ksyms));
+ jited_func_lens = calloc(nr_jited_func_lens,
+ sizeof(*jited_func_lens));
+ if (CHECK(!jited_linfo || !jited_ksyms || !jited_func_lens,
+ "jited_linfo:%p jited_ksyms:%p jited_func_lens:%p",
+ jited_linfo, jited_ksyms, jited_func_lens)) {
+ err = -1;
+ goto done;
+ }
+
+ info.nr_jited_line_info = jited_cnt;
+ info.jited_line_info_rec_size = jited_rec_size;
+ info.jited_line_info = ptr_to_u64(jited_linfo);
+ info.nr_jited_ksyms = nr_jited_ksyms;
+ info.jited_ksyms = ptr_to_u64(jited_ksyms);
+ info.nr_jited_func_lens = nr_jited_func_lens;
+ info.jited_func_lens = ptr_to_u64(jited_func_lens);
+ }
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+
+ /*
+ * Only recheck the info.*line_info* fields.
+ * Other fields are not the concern of this test.
+ */
+ if (CHECK(err == -1 ||
+ info.nr_line_info != cnt ||
+ (jited_cnt && !info.jited_line_info) ||
+ info.nr_jited_line_info != jited_cnt ||
+ info.line_info_rec_size != rec_size ||
+ info.jited_line_info_rec_size != jited_rec_size,
+ "err:%d errno:%d info: nr_line_info:%u(expected:%u) nr_jited_line_info:%u(expected:%u) line_info_rec_size:%u(expected:%u) jited_linfo_rec_size:%u(expected:%u) line_info:%p jited_line_info:%p",
+ err, errno,
+ info.nr_line_info, cnt,
+ info.nr_jited_line_info, jited_cnt,
+ info.line_info_rec_size, rec_size,
+ info.jited_line_info_rec_size, jited_rec_size,
+ (void *)(long)info.line_info,
+ (void *)(long)info.jited_line_info)) {
+ err = -1;
+ goto done;
+ }
+
+ CHECK(linfo[0].insn_off, "linfo[0].insn_off:%u",
+ linfo[0].insn_off);
+ for (i = 1; i < cnt; i++) {
+ const struct bpf_line_info *expected_linfo;
+
+ expected_linfo = patched_linfo + (i * test->line_info_rec_size);
+ if (CHECK(linfo[i].insn_off <= linfo[i - 1].insn_off,
+ "linfo[%u].insn_off:%u <= linfo[%u].insn_off:%u",
+ i, linfo[i].insn_off,
+ i - 1, linfo[i - 1].insn_off)) {
+ err = -1;
+ goto done;
+ }
+ if (CHECK(linfo[i].file_name_off != expected_linfo->file_name_off ||
+ linfo[i].line_off != expected_linfo->line_off ||
+ linfo[i].line_col != expected_linfo->line_col,
+ "linfo[%u] (%u, %u, %u) != (%u, %u, %u)", i,
+ linfo[i].file_name_off,
+ linfo[i].line_off,
+ linfo[i].line_col,
+ expected_linfo->file_name_off,
+ expected_linfo->line_off,
+ expected_linfo->line_col)) {
+ err = -1;
+ goto done;
+ }
+ }
+
+ if (!jited_cnt) {
+ fprintf(stderr, "not jited. skipping jited_line_info check. ");
+ err = 0;
+ goto done;
+ }
+
+ if (CHECK(jited_linfo[0] != jited_ksyms[0],
+ "jited_linfo[0]:%lx != jited_ksyms[0]:%lx",
+ (long)(jited_linfo[0]), (long)(jited_ksyms[0]))) {
+ err = -1;
+ goto done;
+ }
+
+ ksyms_found = 1;
+ cur_func_len = jited_func_lens[0];
+ cur_func_ksyms = jited_ksyms[0];
+ for (i = 1; i < jited_cnt; i++) {
+ if (ksyms_found < nr_jited_ksyms &&
+ jited_linfo[i] == jited_ksyms[ksyms_found]) {
+ cur_func_ksyms = jited_ksyms[ksyms_found];
+ cur_func_len = jited_ksyms[ksyms_found];
+ ksyms_found++;
+ continue;
+ }
+
+ if (CHECK(jited_linfo[i] <= jited_linfo[i - 1],
+ "jited_linfo[%u]:%lx <= jited_linfo[%u]:%lx",
+ i, (long)jited_linfo[i],
+ i - 1, (long)(jited_linfo[i - 1]))) {
+ err = -1;
+ goto done;
+ }
+
+ if (CHECK(jited_linfo[i] - cur_func_ksyms > cur_func_len,
+ "jited_linfo[%u]:%lx - %lx > %u",
+ i, (long)jited_linfo[i], (long)cur_func_ksyms,
+ cur_func_len)) {
+ err = -1;
+ goto done;
+ }
+ }
+
+ if (CHECK(ksyms_found != nr_jited_ksyms,
+ "ksyms_found:%u != nr_jited_ksyms:%u",
+ ksyms_found, nr_jited_ksyms)) {
+ err = -1;
+ goto done;
+ }
+
+ err = 0;
+
+done:
+ free(linfo);
+ free(jited_linfo);
+ free(jited_ksyms);
+ free(jited_func_lens);
+ return err;
+}
+
+static int do_test_info_raw(unsigned int test_num)
+{
+ const struct prog_info_raw_test *test = &info_raw_tests[test_num - 1];
+ unsigned int raw_btf_size, linfo_str_off, linfo_size;
+ int btf_fd = -1, prog_fd = -1, err = 0;
+ void *raw_btf, *patched_linfo = NULL;
+ const char *ret_next_str;
+ union bpf_attr attr = {};
+
+ fprintf(stderr, "BTF prog info raw test[%u] (%s): ", test_num, test->descr);
+ raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
+ test->str_sec, test->str_sec_size,
+ &raw_btf_size, &ret_next_str);
+
+ if (!raw_btf)
+ return -1;
+
+ *btf_log_buf = '\0';
+ btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+ btf_log_buf, BTF_LOG_BUF_SIZE,
+ args.always_log);
+ free(raw_btf);
+
+ if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ if (*btf_log_buf && args.always_log)
+ fprintf(stderr, "\n%s", btf_log_buf);
+ *btf_log_buf = '\0';
+
+ linfo_str_off = ret_next_str - test->str_sec;
+ patched_linfo = patch_name_tbd(test->line_info,
+ test->str_sec, linfo_str_off,
+ test->str_sec_size, &linfo_size);
+ if (IS_ERR(patched_linfo)) {
+ fprintf(stderr, "error in creating raw bpf_line_info");
+ err = -1;
+ goto done;
+ }
+
+ attr.prog_type = test->prog_type;
+ attr.insns = ptr_to_u64(test->insns);
+ attr.insn_cnt = probe_prog_length(test->insns);
+ attr.license = ptr_to_u64("GPL");
+ attr.prog_btf_fd = btf_fd;
+ attr.func_info_rec_size = test->func_info_rec_size;
+ attr.func_info_cnt = test->func_info_cnt;
+ attr.func_info = ptr_to_u64(test->func_info);
+ attr.log_buf = ptr_to_u64(btf_log_buf);
+ attr.log_size = BTF_LOG_BUF_SIZE;
+ attr.log_level = 1;
+ if (linfo_size) {
+ attr.line_info_rec_size = test->line_info_rec_size;
+ attr.line_info = ptr_to_u64(patched_linfo);
+ attr.line_info_cnt = linfo_size / attr.line_info_rec_size;
+ }
+
+ prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+ err = ((prog_fd == -1) != test->expected_prog_load_failure);
+ if (CHECK(err, "prog_fd:%d expected_prog_load_failure:%u errno:%d",
+ prog_fd, test->expected_prog_load_failure, errno) ||
+ CHECK(test->err_str && !strstr(btf_log_buf, test->err_str),
+ "expected err_str:%s", test->err_str)) {
+ err = -1;
+ goto done;
+ }
+
+ if (prog_fd == -1)
+ goto done;
+
+ err = test_get_finfo(test, prog_fd);
+ if (err)
+ goto done;
+
+ err = test_get_linfo(test, patched_linfo, attr.line_info_cnt, prog_fd);
+ if (err)
+ goto done;
+
+done:
+ if (!err)
+ fprintf(stderr, "OK");
+
+ if (*btf_log_buf && (err || args.always_log))
+ fprintf(stderr, "\n%s", btf_log_buf);
+
+ if (btf_fd != -1)
+ close(btf_fd);
+ if (prog_fd != -1)
+ close(prog_fd);
+
+ if (!IS_ERR(patched_linfo))
+ free(patched_linfo);
+
+ return err;
+}
+
+static int test_info_raw(void)
+{
+ unsigned int i;
+ int err = 0;
+
+ if (args.info_raw_test_num)
+ return count_result(do_test_info_raw(args.info_raw_test_num));
+
+ for (i = 1; i <= ARRAY_SIZE(info_raw_tests); i++)
+ err |= count_result(do_test_info_raw(i));
+
+ return err;
+}
+
static void usage(const char *cmd)
{
- fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n",
+ fprintf(stderr, "Usage: %s [-l] [[-r btf_raw_test_num (1 - %zu)] |\n"
+ "\t[-g btf_get_info_test_num (1 - %zu)] |\n"
+ "\t[-f btf_file_test_num (1 - %zu)] |\n"
+ "\t[-k btf_prog_info_raw_test_num (1 - %zu)] |\n"
+ "\t[-p (pretty print test)]]\n",
cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests),
- ARRAY_SIZE(file_tests));
+ ARRAY_SIZE(file_tests), ARRAY_SIZE(info_raw_tests));
}
static int parse_args(int argc, char **argv)
{
- const char *optstr = "lpf:r:g:";
+ const char *optstr = "lpk:f:r:g:";
int opt;
while ((opt = getopt(argc, argv, optstr)) != -1) {
@@ -2870,6 +4982,10 @@ static int parse_args(int argc, char **argv)
case 'p':
args.pprint_test = true;
break;
+ case 'k':
+ args.info_raw_test_num = atoi(optarg);
+ args.info_raw_test = true;
+ break;
case 'h':
usage(argv[0]);
exit(0);
@@ -2903,6 +5019,14 @@ static int parse_args(int argc, char **argv)
return -1;
}
+ if (args.info_raw_test_num &&
+ (args.info_raw_test_num < 1 ||
+ args.info_raw_test_num > ARRAY_SIZE(info_raw_tests))) {
+ fprintf(stderr, "BTF prog info raw test number must be [1 - %zu]\n",
+ ARRAY_SIZE(info_raw_tests));
+ return -1;
+ }
+
return 0;
}
@@ -2935,13 +5059,17 @@ int main(int argc, char **argv)
if (args.pprint_test)
err |= test_pprint();
+ if (args.info_raw_test)
+ err |= test_info_raw();
+
if (args.raw_test || args.get_info_test || args.file_test ||
- args.pprint_test)
+ args.pprint_test || args.info_raw_test)
goto done;
err |= test_raw();
err |= test_get_info();
err |= test_file();
+ err |= test_info_raw();
done:
print_summary();
diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c
index b21b876f475d..e5c79fe0ffdb 100644
--- a/tools/testing/selftests/bpf/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/test_btf_haskv.c
@@ -24,8 +24,8 @@ struct dummy_tracepoint_args {
struct sock *sock;
};
-SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+__attribute__((noinline))
+static int test_long_fname_2(struct dummy_tracepoint_args *arg)
{
struct ipv_counts *counts;
int key = 0;
@@ -42,4 +42,16 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
return 0;
}
+__attribute__((noinline))
+static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+{
+ return test_long_fname_2(arg);
+}
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+ return test_long_fname_1(arg);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/test_btf_nokv.c
index 0ed8e088eebf..434188c37774 100644
--- a/tools/testing/selftests/bpf/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/test_btf_nokv.c
@@ -22,8 +22,8 @@ struct dummy_tracepoint_args {
struct sock *sock;
};
-SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+__attribute__((noinline))
+static int test_long_fname_2(struct dummy_tracepoint_args *arg)
{
struct ipv_counts *counts;
int key = 0;
@@ -40,4 +40,16 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
return 0;
}
+__attribute__((noinline))
+static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+{
+ return test_long_fname_2(arg);
+}
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+ return test_long_fname_1(arg);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
index c0fb073b5eab..d23d4da66b83 100755
--- a/tools/testing/selftests/bpf/test_flow_dissector.sh
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -59,7 +59,7 @@ else
fi
# Attach BPF program
-./flow_dissector_load -p bpf_flow.o -s dissect
+./flow_dissector_load -p bpf_flow.o -s flow_dissector
# Setup
tc qdisc add dev lo ingress
diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh
index 156d89f1edcc..2989b2e2d856 100755
--- a/tools/testing/selftests/bpf/test_libbpf.sh
+++ b/tools/testing/selftests/bpf/test_libbpf.sh
@@ -33,17 +33,11 @@ trap exit_handler 0 2 3 6 9
libbpf_open_file test_l4lb.o
-# TODO: fix libbpf to load noinline functions
-# [warning] libbpf: incorrect bpf_call opcode
-#libbpf_open_file test_l4lb_noinline.o
+# Load a program with BPF-to-BPF calls
+libbpf_open_file test_l4lb_noinline.o
-# TODO: fix test_xdp_meta.c to load with libbpf
-# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version
-#libbpf_open_file test_xdp_meta.o
-
-# TODO: fix libbpf to handle .eh_frame
-# [warning] libbpf: relocation failed: no section(10)
-#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
+# Load a program compiled without the "-target bpf" flag
+libbpf_open_file test_xdp.o
# Success
exit 0
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh
index 677686198df3..ec4e15948e40 100755
--- a/tools/testing/selftests/bpf/test_lirc_mode2.sh
+++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh
@@ -21,13 +21,14 @@ do
if grep -q DRV_NAME=rc-loopback $i/uevent
then
LIRCDEV=$(grep DEVNAME= $i/lirc*/uevent | sed sQDEVNAME=Q/dev/Q)
+ INPUTDEV=$(grep DEVNAME= $i/input*/event*/uevent | sed sQDEVNAME=Q/dev/Q)
fi
done
if [ -n $LIRCDEV ];
then
TYPE=lirc_mode2
- ./test_lirc_mode2_user $LIRCDEV
+ ./test_lirc_mode2_user $LIRCDEV $INPUTDEV
ret=$?
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
index ba26855563a5..4147130cc3b7 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
@@ -15,6 +15,9 @@ int bpf_decoder(unsigned int *sample)
if (duration & 0x10000)
bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0);
+ if (duration & 0x20000)
+ bpf_rc_pointer_rel(sample, (duration >> 8) & 0xff,
+ duration & 0xff);
}
return 0;
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
index d470d63c33db..fb5fd6841ef3 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -29,6 +29,7 @@
#include <linux/bpf.h>
#include <linux/lirc.h>
+#include <linux/input.h>
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
@@ -47,12 +48,13 @@
int main(int argc, char **argv)
{
struct bpf_object *obj;
- int ret, lircfd, progfd, mode;
- int testir = 0x1dead;
+ int ret, lircfd, progfd, inputfd;
+ int testir1 = 0x1dead;
+ int testir2 = 0x20101;
u32 prog_ids[10], prog_flags[10], prog_cnt;
- if (argc != 2) {
- printf("Usage: %s /dev/lircN\n", argv[0]);
+ if (argc != 3) {
+ printf("Usage: %s /dev/lircN /dev/input/eventM\n", argv[0]);
return 2;
}
@@ -76,9 +78,9 @@ int main(int argc, char **argv)
return 1;
}
- mode = LIRC_MODE_SCANCODE;
- if (ioctl(lircfd, LIRC_SET_REC_MODE, &mode)) {
- printf("failed to set rec mode: %m\n");
+ inputfd = open(argv[2], O_RDONLY | O_NONBLOCK);
+ if (inputfd == -1) {
+ printf("failed to open input device %s: %m\n", argv[1]);
return 1;
}
@@ -102,29 +104,54 @@ int main(int argc, char **argv)
}
/* Write raw IR */
- ret = write(lircfd, &testir, sizeof(testir));
- if (ret != sizeof(testir)) {
+ ret = write(lircfd, &testir1, sizeof(testir1));
+ if (ret != sizeof(testir1)) {
printf("Failed to send test IR message: %m\n");
return 1;
}
- struct pollfd pfd = { .fd = lircfd, .events = POLLIN };
- struct lirc_scancode lsc;
+ struct pollfd pfd = { .fd = inputfd, .events = POLLIN };
+ struct input_event event;
- poll(&pfd, 1, 100);
+ for (;;) {
+ poll(&pfd, 1, 100);
- /* Read decoded IR */
- ret = read(lircfd, &lsc, sizeof(lsc));
- if (ret != sizeof(lsc)) {
- printf("Failed to read decoded IR: %m\n");
- return 1;
+ /* Read decoded IR */
+ ret = read(inputfd, &event, sizeof(event));
+ if (ret != sizeof(event)) {
+ printf("Failed to read decoded IR: %m\n");
+ return 1;
+ }
+
+ if (event.type == EV_MSC && event.code == MSC_SCAN &&
+ event.value == 0xdead) {
+ break;
+ }
}
- if (lsc.scancode != 0xdead || lsc.rc_proto != 64) {
- printf("Incorrect scancode decoded\n");
+ /* Write raw IR */
+ ret = write(lircfd, &testir2, sizeof(testir2));
+ if (ret != sizeof(testir2)) {
+ printf("Failed to send test IR message: %m\n");
return 1;
}
+ for (;;) {
+ poll(&pfd, 1, 100);
+
+ /* Read decoded IR */
+ ret = read(inputfd, &event, sizeof(event));
+ if (ret != sizeof(event)) {
+ printf("Failed to read decoded IR: %m\n");
+ return 1;
+ }
+
+ if (event.type == EV_REL && event.code == REL_Y &&
+ event.value == 1 ) {
+ break;
+ }
+ }
+
prog_cnt = 10;
ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
&prog_cnt);
diff --git a/tools/testing/selftests/bpf/test_map_in_map.c b/tools/testing/selftests/bpf/test_map_in_map.c
new file mode 100644
index 000000000000..ce923e67e08e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_map_in_map.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") mim_array = {
+ .type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+ .key_size = sizeof(int),
+ /* must be sizeof(__u32) for map in map */
+ .value_size = sizeof(__u32),
+ .max_entries = 1,
+ .map_flags = 0,
+};
+
+struct bpf_map_def SEC("maps") mim_hash = {
+ .type = BPF_MAP_TYPE_HASH_OF_MAPS,
+ .key_size = sizeof(int),
+ /* must be sizeof(__u32) for map in map */
+ .value_size = sizeof(__u32),
+ .max_entries = 1,
+ .map_flags = 0,
+};
+
+SEC("xdp_mimtest")
+int xdp_mimtest0(struct xdp_md *ctx)
+{
+ int value = 123;
+ int key = 0;
+ void *map;
+
+ map = bpf_map_lookup_elem(&mim_array, &key);
+ if (!map)
+ return XDP_DROP;
+
+ bpf_map_update_elem(map, &key, &value, 0);
+
+ map = bpf_map_lookup_elem(&mim_hash, &key);
+ if (!map)
+ return XDP_DROP;
+
+ bpf_map_update_elem(map, &key, &value, 0);
+
+ return XDP_PASS;
+}
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 4db2116e52be..9c79ee017df3 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -258,24 +258,36 @@ static void test_hashmap_percpu(int task, void *data)
close(fd);
}
-static void test_hashmap_walk(int task, void *data)
+static int helper_fill_hashmap(int max_entries)
{
- int fd, i, max_entries = 1000;
- long long key, value, next_key;
- bool next_key_valid = true;
+ int i, fd, ret;
+ long long key, value;
fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
max_entries, map_flags);
- if (fd < 0) {
- printf("Failed to create hashmap '%s'!\n", strerror(errno));
- exit(1);
- }
+ CHECK(fd < 0,
+ "failed to create hashmap",
+ "err: %s, flags: 0x%x\n", strerror(errno), map_flags);
for (i = 0; i < max_entries; i++) {
key = i; value = key;
- assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0);
+ ret = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(ret != 0,
+ "can't update hashmap",
+ "err: %s\n", strerror(ret));
}
+ return fd;
+}
+
+static void test_hashmap_walk(int task, void *data)
+{
+ int fd, i, max_entries = 1000;
+ long long key, value, next_key;
+ bool next_key_valid = true;
+
+ fd = helper_fill_hashmap(max_entries);
+
for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key,
&next_key) == 0; i++) {
key = next_key;
@@ -306,6 +318,39 @@ static void test_hashmap_walk(int task, void *data)
close(fd);
}
+static void test_hashmap_zero_seed(void)
+{
+ int i, first, second, old_flags;
+ long long key, next_first, next_second;
+
+ old_flags = map_flags;
+ map_flags |= BPF_F_ZERO_SEED;
+
+ first = helper_fill_hashmap(3);
+ second = helper_fill_hashmap(3);
+
+ for (i = 0; ; i++) {
+ void *key_ptr = !i ? NULL : &key;
+
+ if (bpf_map_get_next_key(first, key_ptr, &next_first) != 0)
+ break;
+
+ CHECK(bpf_map_get_next_key(second, key_ptr, &next_second) != 0,
+ "next_key for second map must succeed",
+ "key_ptr: %p", key_ptr);
+ CHECK(next_first != next_second,
+ "keys must match",
+ "i: %d first: %lld second: %lld\n", i,
+ next_first, next_second);
+
+ key = next_first;
+ }
+
+ map_flags = old_flags;
+ close(first);
+ close(second);
+}
+
static void test_arraymap(int task, void *data)
{
int key, next_key, fd;
@@ -1080,6 +1125,94 @@ out_sockmap:
exit(1);
}
+#define MAPINMAP_PROG "./test_map_in_map.o"
+static void test_map_in_map(void)
+{
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ struct bpf_map *map;
+ int mim_fd, fd, err;
+ int pos = 0;
+
+ obj = bpf_object__open(MAPINMAP_PROG);
+
+ fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), sizeof(int),
+ 2, 0);
+ if (fd < 0) {
+ printf("Failed to create hashmap '%s'!\n", strerror(errno));
+ exit(1);
+ }
+
+ map = bpf_object__find_map_by_name(obj, "mim_array");
+ if (IS_ERR(map)) {
+ printf("Failed to load array of maps from test prog\n");
+ goto out_map_in_map;
+ }
+ err = bpf_map__set_inner_map_fd(map, fd);
+ if (err) {
+ printf("Failed to set inner_map_fd for array of maps\n");
+ goto out_map_in_map;
+ }
+
+ map = bpf_object__find_map_by_name(obj, "mim_hash");
+ if (IS_ERR(map)) {
+ printf("Failed to load hash of maps from test prog\n");
+ goto out_map_in_map;
+ }
+ err = bpf_map__set_inner_map_fd(map, fd);
+ if (err) {
+ printf("Failed to set inner_map_fd for hash of maps\n");
+ goto out_map_in_map;
+ }
+
+ bpf_object__for_each_program(prog, obj) {
+ bpf_program__set_xdp(prog);
+ }
+ bpf_object__load(obj);
+
+ map = bpf_object__find_map_by_name(obj, "mim_array");
+ if (IS_ERR(map)) {
+ printf("Failed to load array of maps from test prog\n");
+ goto out_map_in_map;
+ }
+ mim_fd = bpf_map__fd(map);
+ if (mim_fd < 0) {
+ printf("Failed to get descriptor for array of maps\n");
+ goto out_map_in_map;
+ }
+
+ err = bpf_map_update_elem(mim_fd, &pos, &fd, 0);
+ if (err) {
+ printf("Failed to update array of maps\n");
+ goto out_map_in_map;
+ }
+
+ map = bpf_object__find_map_by_name(obj, "mim_hash");
+ if (IS_ERR(map)) {
+ printf("Failed to load hash of maps from test prog\n");
+ goto out_map_in_map;
+ }
+ mim_fd = bpf_map__fd(map);
+ if (mim_fd < 0) {
+ printf("Failed to get descriptor for hash of maps\n");
+ goto out_map_in_map;
+ }
+
+ err = bpf_map_update_elem(mim_fd, &pos, &fd, 0);
+ if (err) {
+ printf("Failed to update hash of maps\n");
+ goto out_map_in_map;
+ }
+
+ close(fd);
+ bpf_object__close(obj);
+ return;
+
+out_map_in_map:
+ close(fd);
+ exit(1);
+}
+
#define MAP_SIZE (32 * 1024)
static void test_map_large(void)
@@ -1534,6 +1667,7 @@ static void run_all_tests(void)
test_hashmap(0, NULL);
test_hashmap_percpu(0, NULL);
test_hashmap_walk(0, NULL);
+ test_hashmap_zero_seed();
test_arraymap(0, NULL);
test_arraymap_percpu(0, NULL);
@@ -1554,6 +1688,8 @@ static void run_all_tests(void)
test_queuemap(0, NULL);
test_stackmap(0, NULL);
+
+ test_map_in_map();
}
int main(void)
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 2d3c04f45530..126fc624290d 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -51,10 +51,10 @@ static struct {
struct iphdr iph;
struct tcphdr tcp;
} __packed pkt_v4 = {
- .eth.h_proto = bpf_htons(ETH_P_IP),
+ .eth.h_proto = __bpf_constant_htons(ETH_P_IP),
.iph.ihl = 5,
.iph.protocol = 6,
- .iph.tot_len = bpf_htons(MAGIC_BYTES),
+ .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
.tcp.urg_ptr = 123,
};
@@ -64,13 +64,13 @@ static struct {
struct ipv6hdr iph;
struct tcphdr tcp;
} __packed pkt_v6 = {
- .eth.h_proto = bpf_htons(ETH_P_IPV6),
+ .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
.iph.nexthdr = 6,
- .iph.payload_len = bpf_htons(MAGIC_BYTES),
+ .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
.tcp.urg_ptr = 123,
};
-#define CHECK(condition, tag, format...) ({ \
+#define _CHECK(condition, tag, duration, format...) ({ \
int __ret = !!(condition); \
if (__ret) { \
error_cnt++; \
@@ -83,6 +83,11 @@ static struct {
__ret; \
})
+#define CHECK(condition, tag, format...) \
+ _CHECK(condition, tag, duration, format)
+#define CHECK_ATTR(condition, tag, format...) \
+ _CHECK(condition, tag, tattr.duration, format)
+
static int bpf_find_map(const char *test, struct bpf_object *obj,
const char *name)
{
@@ -124,6 +129,53 @@ static void test_pkt_access(void)
bpf_object__close(obj);
}
+static void test_prog_run_xattr(void)
+{
+ const char *file = "./test_pkt_access.o";
+ struct bpf_object *obj;
+ char buf[10];
+ int err;
+ struct bpf_prog_test_run_attr tattr = {
+ .repeat = 1,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .data_out = buf,
+ .data_size_out = 5,
+ };
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj,
+ &tattr.prog_fd);
+ if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+ return;
+
+ memset(buf, 0, sizeof(buf));
+
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err != -1 || errno != ENOSPC || tattr.retval, "run",
+ "err %d errno %d retval %d\n", err, errno, tattr.retval);
+
+ CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out",
+ "incorrect output size, want %lu have %u\n",
+ sizeof(pkt_v4), tattr.data_size_out);
+
+ CHECK_ATTR(buf[5] != 0, "overflow",
+ "BPF_PROG_TEST_RUN ignored size hint\n");
+
+ tattr.data_out = NULL;
+ tattr.data_size_out = 0;
+ errno = 0;
+
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err || errno || tattr.retval, "run_no_output",
+ "err %d errno %d retval %d\n", err, errno, tattr.retval);
+
+ tattr.data_size_out = 1;
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err != -EINVAL, "run_wrong_size_out", "err %d\n", err);
+
+ bpf_object__close(obj);
+}
+
static void test_xdp(void)
{
struct vip key4 = {.protocol = 6, .family = AF_INET};
@@ -524,7 +576,7 @@ static void test_bpf_obj_id(void)
load_time < now - 60 || load_time > now + 60 ||
prog_infos[i].created_by_uid != my_uid ||
prog_infos[i].nr_map_ids != 1 ||
- *(int *)prog_infos[i].map_ids != map_infos[i].id ||
+ *(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
strcmp((char *)prog_infos[i].name, expected_prog_name),
"get-prog-info(fd)",
"err %d errno %d i %d type %d(%d) info_len %u(%Zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
@@ -539,7 +591,7 @@ static void test_bpf_obj_id(void)
load_time, now,
prog_infos[i].created_by_uid, my_uid,
prog_infos[i].nr_map_ids, 1,
- *(int *)prog_infos[i].map_ids, map_infos[i].id,
+ *(int *)(long)prog_infos[i].map_ids, map_infos[i].id,
prog_infos[i].name, expected_prog_name))
goto done;
}
@@ -585,7 +637,7 @@ static void test_bpf_obj_id(void)
bzero(&prog_info, sizeof(prog_info));
info_len = sizeof(prog_info);
- saved_map_id = *(int *)(prog_infos[i].map_ids);
+ saved_map_id = *(int *)((long)prog_infos[i].map_ids);
prog_info.map_ids = prog_infos[i].map_ids;
prog_info.nr_map_ids = 2;
err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
@@ -593,12 +645,12 @@ static void test_bpf_obj_id(void)
prog_infos[i].xlated_prog_insns = 0;
CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
memcmp(&prog_info, &prog_infos[i], info_len) ||
- *(int *)prog_info.map_ids != saved_map_id,
+ *(int *)(long)prog_info.map_ids != saved_map_id,
"get-prog-info(next_id->fd)",
"err %d errno %d info_len %u(%Zu) memcmp %d map_id %u(%u)\n",
err, errno, info_len, sizeof(struct bpf_prog_info),
memcmp(&prog_info, &prog_infos[i], info_len),
- *(int *)prog_info.map_ids, saved_map_id);
+ *(int *)(long)prog_info.map_ids, saved_map_id);
close(prog_fd);
}
CHECK(nr_id_found != nr_iters,
@@ -1703,7 +1755,7 @@ static void test_reference_tracking()
const char *file = "./test_sk_lookup_kern.o";
struct bpf_object *obj;
struct bpf_program *prog;
- __u32 duration;
+ __u32 duration = 0;
int err = 0;
obj = bpf_object__open(file);
@@ -1837,6 +1889,7 @@ int main(void)
jit_enabled = is_jit_enabled();
test_pkt_access();
+ test_prog_run_xattr();
test_xdp();
test_xdp_adjust_tail();
test_l4lb_all();
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index aeeb76a54d63..73b7493d4120 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -574,24 +574,44 @@ static int bind4_prog_load(const struct sock_addr_test *test)
/* if (sk.family == AF_INET && */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, family)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 16),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 24),
/* (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, type)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
BPF_JMP_A(1),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 12),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 20),
/* 1st_byte_of_user_ip4 == expected && */
BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 10),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 18),
+
+ /* 2nd_byte_of_user_ip4 == expected && */
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4) + 1),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 16),
+
+ /* 3rd_byte_of_user_ip4 == expected && */
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4) + 2),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 14),
+
+ /* 4th_byte_of_user_ip4 == expected && */
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4) + 3),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 12),
/* 1st_half_of_user_ip4 == expected && */
BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock_addr, user_ip4)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 8),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 10),
+
+ /* 2nd_half_of_user_ip4 == expected && */
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4) + 2),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 8),
/* whole_user_ip4 == expected) { */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 622ade0a0957..e85a771f607b 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -79,6 +79,8 @@ int txmsg_start;
int txmsg_end;
int txmsg_start_push;
int txmsg_end_push;
+int txmsg_start_pop;
+int txmsg_pop;
int txmsg_ingress;
int txmsg_skb;
int ktls;
@@ -104,6 +106,8 @@ static const struct option long_options[] = {
{"txmsg_end", required_argument, NULL, 'e'},
{"txmsg_start_push", required_argument, NULL, 'p'},
{"txmsg_end_push", required_argument, NULL, 'q'},
+ {"txmsg_start_pop", required_argument, NULL, 'w'},
+ {"txmsg_pop", required_argument, NULL, 'x'},
{"txmsg_ingress", no_argument, &txmsg_ingress, 1 },
{"txmsg_skb", no_argument, &txmsg_skb, 1 },
{"ktls", no_argument, &ktls, 1 },
@@ -473,13 +477,27 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
clock_gettime(CLOCK_MONOTONIC, &s->end);
} else {
int slct, recvp = 0, recv, max_fd = fd;
+ float total_bytes, txmsg_pop_total;
int fd_flags = O_NONBLOCK;
struct timeval timeout;
- float total_bytes;
fd_set w;
fcntl(fd, fd_flags);
+ /* Account for pop bytes noting each iteration of apply will
+ * call msg_pop_data helper so we need to account for this
+ * by calculating the number of apply iterations. Note user
+ * of the tool can create cases where no data is sent by
+ * manipulating pop/push/pull/etc. For example txmsg_apply 1
+ * with txmsg_pop 1 will try to apply 1B at a time but each
+ * iteration will then pop 1B so no data will ever be sent.
+ * This is really only useful for testing edge cases in code
+ * paths.
+ */
total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
+ txmsg_pop_total = txmsg_pop;
+ if (txmsg_apply)
+ txmsg_pop_total *= (total_bytes / txmsg_apply);
+ total_bytes -= txmsg_pop_total;
err = clock_gettime(CLOCK_MONOTONIC, &s->start);
if (err < 0)
perror("recv start time: ");
@@ -488,7 +506,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
timeout.tv_sec = 0;
timeout.tv_usec = 300000;
} else {
- timeout.tv_sec = 1;
+ timeout.tv_sec = 3;
timeout.tv_usec = 0;
}
@@ -503,7 +521,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
goto out_errno;
} else if (!slct) {
if (opt->verbose)
- fprintf(stderr, "unexpected timeout\n");
+ fprintf(stderr, "unexpected timeout: recved %zu/%f pop_total %f\n", s->bytes_recvd, total_bytes, txmsg_pop_total);
errno = -EIO;
clock_gettime(CLOCK_MONOTONIC, &s->end);
goto out_errno;
@@ -619,7 +637,7 @@ static int sendmsg_test(struct sockmap_options *opt)
iov_count = 1;
err = msg_loop(rx_fd, iov_count, iov_buf,
cnt, &s, false, opt);
- if (err && opt->verbose)
+ if (opt->verbose)
fprintf(stderr,
"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
iov_count, iov_buf, cnt, err);
@@ -931,6 +949,39 @@ run:
}
}
+ if (txmsg_start_pop) {
+ i = 4;
+ err = bpf_map_update_elem(map_fd[5],
+ &i, &txmsg_start_pop, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem %i@%i (txmsg_start_pop): %d (%s)\n",
+ txmsg_start_pop, i, err, strerror(errno));
+ goto out;
+ }
+ } else {
+ i = 4;
+ bpf_map_update_elem(map_fd[5],
+ &i, &txmsg_start_pop, BPF_ANY);
+ }
+
+ if (txmsg_pop) {
+ i = 5;
+ err = bpf_map_update_elem(map_fd[5],
+ &i, &txmsg_pop, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem %i@%i (txmsg_pop): %d (%s)\n",
+ txmsg_pop, i, err, strerror(errno));
+ goto out;
+ }
+ } else {
+ i = 5;
+ bpf_map_update_elem(map_fd[5],
+ &i, &txmsg_pop, BPF_ANY);
+
+ }
+
if (txmsg_ingress) {
int in = BPF_F_INGRESS;
@@ -1082,6 +1133,11 @@ static void test_options(char *options)
snprintf(tstr, OPTSTRING, "end %d,", txmsg_end);
strncat(options, tstr, OPTSTRING);
}
+ if (txmsg_start_pop) {
+ snprintf(tstr, OPTSTRING, "pop (%d,%d),",
+ txmsg_start_pop, txmsg_start_pop + txmsg_pop);
+ strncat(options, tstr, OPTSTRING);
+ }
if (txmsg_ingress)
strncat(options, "ingress,", OPTSTRING);
if (txmsg_skb)
@@ -1264,6 +1320,7 @@ static int test_mixed(int cgrp)
txmsg_apply = txmsg_cork = 0;
txmsg_start = txmsg_end = 0;
txmsg_start_push = txmsg_end_push = 0;
+ txmsg_start_pop = txmsg_pop = 0;
/* Test small and large iov_count values with pass/redir/apply/cork */
txmsg_pass = 1;
@@ -1383,6 +1440,19 @@ static int test_start_end(int cgrp)
txmsg_end = 2;
txmsg_start_push = 1;
txmsg_end_push = 2;
+ txmsg_start_pop = 1;
+ txmsg_pop = 1;
+ err = test_txmsg(cgrp);
+ if (err)
+ goto out;
+
+ /* Cut a byte of pushed data but leave reamining in place */
+ txmsg_start = 1;
+ txmsg_end = 2;
+ txmsg_start_push = 1;
+ txmsg_end_push = 3;
+ txmsg_start_pop = 1;
+ txmsg_pop = 1;
err = test_txmsg(cgrp);
if (err)
goto out;
@@ -1393,6 +1463,9 @@ static int test_start_end(int cgrp)
opt.iov_length = 100;
txmsg_cork = 1600;
+ txmsg_start_pop = 0;
+ txmsg_pop = 0;
+
for (i = 99; i <= 1600; i += 500) {
txmsg_start = 0;
txmsg_end = i;
@@ -1403,6 +1476,17 @@ static int test_start_end(int cgrp)
goto out;
}
+ /* Test pop data in middle of cork */
+ for (i = 99; i <= 1600; i += 500) {
+ txmsg_start_pop = 10;
+ txmsg_pop = i;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ }
+ txmsg_start_pop = 0;
+ txmsg_pop = 0;
+
/* Test start/end with cork but pull data in middle */
for (i = 199; i <= 1600; i += 500) {
txmsg_start = 100;
@@ -1423,6 +1507,15 @@ static int test_start_end(int cgrp)
if (err)
goto out;
+ /* Test pop with cork pulling last sg entry */
+ txmsg_start_pop = 1500;
+ txmsg_pop = 1600;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ txmsg_start_pop = 0;
+ txmsg_pop = 0;
+
/* Test start/end pull of single byte in last page */
txmsg_start = 1111;
txmsg_end = 1112;
@@ -1432,6 +1525,13 @@ static int test_start_end(int cgrp)
if (err)
goto out;
+ /* Test pop of single byte in last page */
+ txmsg_start_pop = 1111;
+ txmsg_pop = 1112;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
/* Test start/end with end < start */
txmsg_start = 1111;
txmsg_end = 0;
@@ -1456,7 +1556,20 @@ static int test_start_end(int cgrp)
txmsg_start_push = 1601;
txmsg_end_push = 1600;
err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test pop with start > data */
+ txmsg_start_pop = 1601;
+ txmsg_pop = 1;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ /* Test pop with pop range > data */
+ txmsg_start_pop = 1599;
+ txmsg_pop = 10;
+ err = test_exec(cgrp, &opt);
out:
txmsg_start = 0;
txmsg_end = 0;
@@ -1641,6 +1754,12 @@ int main(int argc, char **argv)
case 'q':
txmsg_end_push = atoi(optarg);
break;
+ case 'w':
+ txmsg_start_pop = atoi(optarg);
+ break;
+ case 'x':
+ txmsg_pop = atoi(optarg);
+ break;
case 'a':
txmsg_apply = atoi(optarg);
break;
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
index 14b8bbac004f..e7639f66a941 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@@ -74,7 +74,7 @@ struct bpf_map_def SEC("maps") sock_bytes = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
- .max_entries = 4
+ .max_entries = 6
};
struct bpf_map_def SEC("maps") sock_redir_flags = {
@@ -181,8 +181,8 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
SEC("sk_msg1")
int bpf_prog4(struct sk_msg_md *msg)
{
- int *bytes, zero = 0, one = 1, two = 2, three = 3;
- int *start, *end, *start_push, *end_push;
+ int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+ int *start, *end, *start_push, *end_push, *start_pop, *pop;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
@@ -198,15 +198,19 @@ int bpf_prog4(struct sk_msg_md *msg)
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
if (start_push && end_push)
bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+ pop = bpf_map_lookup_elem(&sock_bytes, &five);
+ if (start_pop && pop)
+ bpf_msg_pop_data(msg, *start_pop, *pop, 0);
return SK_PASS;
}
SEC("sk_msg2")
int bpf_prog5(struct sk_msg_md *msg)
{
- int zero = 0, one = 1, two = 2, three = 3;
- int *start, *end, *start_push, *end_push;
- int *bytes, len1, len2 = 0, len3;
+ int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+ int *start, *end, *start_push, *end_push, *start_pop, *pop;
+ int *bytes, len1, len2 = 0, len3, len4;
int err1 = -1, err2 = -1;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -247,6 +251,20 @@ int bpf_prog5(struct sk_msg_md *msg)
bpf_printk("sk_msg2: length push_update %i->%i\n",
len2 ? len2 : len1, len3);
}
+ start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+ pop = bpf_map_lookup_elem(&sock_bytes, &five);
+ if (start_pop && pop) {
+ int err;
+
+ bpf_printk("sk_msg2: pop(%i@%i)\n",
+ start_pop, pop);
+ err = bpf_msg_pop_data(msg, *start_pop, *pop, 0);
+ if (err)
+ bpf_printk("sk_msg2: pop_data err %i\n", err);
+ len4 = (__u64)msg->data_end - (__u64)msg->data;
+ bpf_printk("sk_msg2: length pop_data %i->%i\n",
+ len1 ? len1 : 0, len4);
+ }
bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
len1, err1, err2);
@@ -256,8 +274,8 @@ int bpf_prog5(struct sk_msg_md *msg)
SEC("sk_msg3")
int bpf_prog6(struct sk_msg_md *msg)
{
- int *bytes, *start, *end, *start_push, *end_push, *f;
- int zero = 0, one = 1, two = 2, three = 3, key = 0;
+ int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
+ int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
__u64 flags = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -277,6 +295,11 @@ int bpf_prog6(struct sk_msg_md *msg)
if (start_push && end_push)
bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+ pop = bpf_map_lookup_elem(&sock_bytes, &five);
+ if (start_pop && pop)
+ bpf_msg_pop_data(msg, *start_pop, *pop, 0);
+
f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
if (f && *f) {
key = 2;
@@ -292,8 +315,9 @@ int bpf_prog6(struct sk_msg_md *msg)
SEC("sk_msg4")
int bpf_prog7(struct sk_msg_md *msg)
{
- int zero = 0, one = 1, two = 2, three = 3, len1, len2 = 0, len3;
- int *bytes, *start, *end, *start_push, *end_push, *f;
+ int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
+ int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+ int len1, len2 = 0, len3, len4;
int err1 = 0, err2 = 0, key = 0;
__u64 flags = 0;
@@ -335,6 +359,22 @@ int bpf_prog7(struct sk_msg_md *msg)
len2 ? len2 : len1, len3);
}
+ start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+ pop = bpf_map_lookup_elem(&sock_bytes, &five);
+ if (start_pop && pop) {
+ int err;
+
+ bpf_printk("sk_msg4: pop(%i@%i)\n",
+ start_pop, pop);
+ err = bpf_msg_pop_data(msg, *start_pop, *pop, 0);
+ if (err)
+ bpf_printk("sk_msg4: pop_data err %i\n", err);
+ len4 = (__u64)msg->data_end - (__u64)msg->data;
+ bpf_printk("sk_msg4: length pop_data %i->%i\n",
+ len1 ? len1 : 0, len4);
+ }
+
+
f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
if (f && *f) {
key = 2;
@@ -389,8 +429,8 @@ int bpf_prog9(struct sk_msg_md *msg)
SEC("sk_msg7")
int bpf_prog10(struct sk_msg_md *msg)
{
- int *bytes, *start, *end, *start_push, *end_push;
- int zero = 0, one = 1, two = 2, three = 3;
+ int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
+ int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
@@ -406,7 +446,11 @@ int bpf_prog10(struct sk_msg_md *msg)
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
if (start_push && end_push)
bpf_msg_push_data(msg, *start_push, *end_push, 0);
-
+ start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+ pop = bpf_map_lookup_elem(&sock_bytes, &five);
+ if (start_pop && pop)
+ bpf_msg_pop_data(msg, *start_pop, *pop, 0);
+ bpf_printk("return sk drop\n");
return SK_DROP;
}
diff --git a/tools/testing/selftests/bpf/test_tcpnotify.h b/tools/testing/selftests/bpf/test_tcpnotify.h
new file mode 100644
index 000000000000..8b6cea030bfc
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify.h
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpnotify_globals {
+ __u32 total_retrans;
+ __u32 ncalls;
+};
+
+struct tcp_notifier {
+ __u8 type;
+ __u8 subtype;
+ __u8 source;
+ __u8 hash;
+};
+
+#define TESTPORT 12877
+#endif
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/test_tcpnotify_kern.c
new file mode 100644
index 000000000000..edbca203ce2d
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify_kern.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/tcp.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_tcpnotify.h"
+
+struct bpf_map_def SEC("maps") global_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct tcpnotify_globals),
+ .max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") perf_event_map = {
+ .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(__u32),
+ .max_entries = 2,
+};
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+ int rv = -1;
+ int op;
+
+ op = (int) skops->op;
+
+ if (bpf_ntohl(skops->remote_port) != TESTPORT) {
+ skops->reply = -1;
+ return 0;
+ }
+
+ switch (op) {
+ case BPF_SOCK_OPS_TIMEOUT_INIT:
+ case BPF_SOCK_OPS_RWND_INIT:
+ case BPF_SOCK_OPS_NEEDS_ECN:
+ case BPF_SOCK_OPS_BASE_RTT:
+ case BPF_SOCK_OPS_RTO_CB:
+ rv = 1;
+ break;
+
+ case BPF_SOCK_OPS_TCP_CONNECT_CB:
+ case BPF_SOCK_OPS_TCP_LISTEN_CB:
+ case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+ case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+ bpf_sock_ops_cb_flags_set(skops, (BPF_SOCK_OPS_RETRANS_CB_FLAG|
+ BPF_SOCK_OPS_RTO_CB_FLAG));
+ rv = 1;
+ break;
+ case BPF_SOCK_OPS_RETRANS_CB: {
+ __u32 key = 0;
+ struct tcpnotify_globals g, *gp;
+ struct tcp_notifier msg = {
+ .type = 0xde,
+ .subtype = 0xad,
+ .source = 0xbe,
+ .hash = 0xef,
+ };
+
+ rv = 1;
+
+ /* Update results */
+ gp = bpf_map_lookup_elem(&global_map, &key);
+ if (!gp)
+ break;
+ g = *gp;
+ g.total_retrans = skops->total_retrans;
+ g.ncalls++;
+ bpf_map_update_elem(&global_map, &key, &g,
+ BPF_ANY);
+ bpf_perf_event_output(skops, &perf_event_map,
+ BPF_F_CURRENT_CPU,
+ &msg, sizeof(msg));
+ }
+ break;
+ default:
+ rv = -1;
+ }
+ skops->reply = rv;
+ return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c
new file mode 100644
index 000000000000..ff3c4522aed6
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <asm/types.h>
+#include <sys/syscall.h>
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <sys/socket.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <sys/ioctl.h>
+#include <linux/rtnetlink.h>
+#include <signal.h>
+#include <linux/perf_event.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+#include "test_tcpnotify.h"
+#include "trace_helpers.h"
+
+#define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L)
+
+pthread_t tid;
+int rx_callbacks;
+
+static int dummyfn(void *data, int size)
+{
+ struct tcp_notifier *t = data;
+
+ if (t->type != 0xde || t->subtype != 0xad ||
+ t->source != 0xbe || t->hash != 0xef)
+ return 1;
+ rx_callbacks++;
+ return 0;
+}
+
+void tcp_notifier_poller(int fd)
+{
+ while (1)
+ perf_event_poller(fd, dummyfn);
+}
+
+static void *poller_thread(void *arg)
+{
+ int fd = *(int *)arg;
+
+ tcp_notifier_poller(fd);
+ return arg;
+}
+
+int verify_result(const struct tcpnotify_globals *result)
+{
+ return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1);
+}
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+ const char *name)
+{
+ struct bpf_map *map;
+
+ map = bpf_object__find_map_by_name(obj, name);
+ if (!map) {
+ printf("%s:FAIL:map '%s' not found\n", test, name);
+ return -1;
+ }
+ return bpf_map__fd(map);
+}
+
+static int setup_bpf_perf_event(int mapfd)
+{
+ struct perf_event_attr attr = {
+ .sample_type = PERF_SAMPLE_RAW,
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_BPF_OUTPUT,
+ };
+ int key = 0;
+ int pmu_fd;
+
+ pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0);
+ if (pmu_fd < 0)
+ return pmu_fd;
+ bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY);
+
+ ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+ return pmu_fd;
+}
+
+int main(int argc, char **argv)
+{
+ const char *file = "test_tcpnotify_kern.o";
+ int prog_fd, map_fd, perf_event_fd;
+ struct tcpnotify_globals g = {0};
+ const char *cg_path = "/foo";
+ int error = EXIT_FAILURE;
+ struct bpf_object *obj;
+ int cg_fd = -1;
+ __u32 key = 0;
+ int rv;
+ char test_script[80];
+ int pmu_fd;
+ cpu_set_t cpuset;
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+ pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
+
+ if (setup_cgroup_environment())
+ goto err;
+
+ cg_fd = create_and_get_cgroup(cg_path);
+ if (!cg_fd)
+ goto err;
+
+ if (join_cgroup(cg_path))
+ goto err;
+
+ if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+ printf("FAILED: load_bpf_file failed for: %s\n", file);
+ goto err;
+ }
+
+ rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+ if (rv) {
+ printf("FAILED: bpf_prog_attach: %d (%s)\n",
+ error, strerror(errno));
+ goto err;
+ }
+
+ perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map");
+ if (perf_event_fd < 0)
+ goto err;
+
+ map_fd = bpf_find_map(__func__, obj, "global_map");
+ if (map_fd < 0)
+ goto err;
+
+ pmu_fd = setup_bpf_perf_event(perf_event_fd);
+ if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0)
+ goto err;
+
+ pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd);
+
+ sprintf(test_script,
+ "/usr/sbin/iptables -A INPUT -p tcp --dport %d -j DROP",
+ TESTPORT);
+ system(test_script);
+
+ sprintf(test_script,
+ "/usr/bin/nc 127.0.0.1 %d < /etc/passwd > /dev/null 2>&1 ",
+ TESTPORT);
+ system(test_script);
+
+ sprintf(test_script,
+ "/usr/sbin/iptables -D INPUT -p tcp --dport %d -j DROP",
+ TESTPORT);
+ system(test_script);
+
+ rv = bpf_map_lookup_elem(map_fd, &key, &g);
+ if (rv != 0) {
+ printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+ goto err;
+ }
+
+ sleep(10);
+
+ if (verify_result(&g)) {
+ printf("FAILED: Wrong stats Expected %d calls, got %d\n",
+ g.ncalls, rx_callbacks);
+ goto err;
+ }
+
+ printf("PASSED!\n");
+ error = 0;
+err:
+ bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+ close(cg_fd);
+ cleanup_cgroup_environment();
+ return error;
+}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index f8eac4a544f4..33f7d38849b8 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -49,6 +49,7 @@
#define MAX_INSNS BPF_MAXINSNS
#define MAX_FIXUPS 8
#define MAX_NR_MAPS 13
+#define MAX_TEST_RUNS 8
#define POINTER_VALUE 0xcafe4all
#define TEST_DATA_LEN 64
@@ -76,7 +77,7 @@ struct bpf_test {
int fixup_percpu_cgroup_storage[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
- uint32_t retval, retval_unpriv;
+ uint32_t retval, retval_unpriv, insn_processed;
enum {
UNDEF,
ACCEPT,
@@ -86,6 +87,14 @@ struct bpf_test {
uint8_t flags;
__u8 data[TEST_DATA_LEN];
void (*fill_helper)(struct bpf_test *self);
+ uint8_t runs;
+ struct {
+ uint32_t retval, retval_unpriv;
+ union {
+ __u8 data[TEST_DATA_LEN];
+ __u64 data64[TEST_DATA_LEN / 8];
+ };
+ } retvals[MAX_TEST_RUNS];
};
/* Note we want this to be 64 bit aligned so that the end of our array is
@@ -721,8 +730,18 @@ static struct bpf_test tests[] = {
BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 5),
BPF_EXIT_INSN(),
},
- .result = REJECT,
- .errstr = "unknown opcode c4",
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "arsh32 on imm 2",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 0x1122334485667788),
+ BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 7),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = -16069393,
},
{
"arsh32 on reg",
@@ -732,8 +751,19 @@ static struct bpf_test tests[] = {
BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
- .errstr = "unknown opcode cc",
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "arsh32 on reg 2",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_0, 0xffff55667788),
+ BPF_MOV64_IMM(BPF_REG_1, 15),
+ BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 43724,
},
{
"arsh64 on imm",
@@ -980,15 +1010,45 @@ static struct bpf_test tests[] = {
BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
/* mess up with R1 pointer on stack */
BPF_ST_MEM(BPF_B, BPF_REG_10, -7, 0x23),
- /* fill back into R0 should fail */
+ /* fill back into R0 is fine for priv.
+ * R0 now becomes SCALAR_VALUE.
+ */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+ /* Load from R0 should fail. */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
BPF_EXIT_INSN(),
},
.errstr_unpriv = "attempt to corrupt spilled",
- .errstr = "corrupted spill",
+ .errstr = "R0 invalid mem access 'inv",
.result = REJECT,
},
{
+ "check corrupted spill/fill, LSB",
+ .insns = {
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_ST_MEM(BPF_H, BPF_REG_10, -8, 0xcafe),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+ BPF_EXIT_INSN(),
+ },
+ .errstr_unpriv = "attempt to corrupt spilled",
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+ .retval = POINTER_VALUE,
+ },
+ {
+ "check corrupted spill/fill, MSB",
+ .insns = {
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0x12345678),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+ BPF_EXIT_INSN(),
+ },
+ .errstr_unpriv = "attempt to corrupt spilled",
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+ .retval = POINTER_VALUE,
+ },
+ {
"invalid src register in STX",
.insns = {
BPF_STX_MEM(BPF_B, BPF_REG_10, -1, -1),
@@ -1792,10 +1852,20 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SK_SKB,
},
{
- "invalid 64B read of family in SK_MSG",
+ "valid access size in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, size)),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
+ "invalid 64B read of size in SK_MSG",
.insns = {
BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
- offsetof(struct sk_msg_md, family)),
+ offsetof(struct sk_msg_md, size)),
BPF_EXIT_INSN(),
},
.errstr = "invalid bpf_context access",
@@ -1806,10 +1876,10 @@ static struct bpf_test tests[] = {
"invalid read past end of SK_MSG",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
- offsetof(struct sk_msg_md, local_port) + 4),
+ offsetof(struct sk_msg_md, size) + 4),
BPF_EXIT_INSN(),
},
- .errstr = "R0 !read_ok",
+ .errstr = "invalid bpf_context access",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_MSG,
},
@@ -1823,6 +1893,7 @@ static struct bpf_test tests[] = {
.errstr = "invalid bpf_context access",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_MSG,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct packet read for SK_MSG",
@@ -2026,29 +2097,27 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
},
{
- "check skb->hash byte load not permitted 1",
+ "check skb->hash byte load permitted 1",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
offsetof(struct __sk_buff, hash) + 1),
BPF_EXIT_INSN(),
},
- .errstr = "invalid bpf_context access",
- .result = REJECT,
+ .result = ACCEPT,
},
{
- "check skb->hash byte load not permitted 2",
+ "check skb->hash byte load permitted 2",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
offsetof(struct __sk_buff, hash) + 2),
BPF_EXIT_INSN(),
},
- .errstr = "invalid bpf_context access",
- .result = REJECT,
+ .result = ACCEPT,
},
{
- "check skb->hash byte load not permitted 3",
+ "check skb->hash byte load permitted 3",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
#if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -2060,8 +2129,7 @@ static struct bpf_test tests[] = {
#endif
BPF_EXIT_INSN(),
},
- .errstr = "invalid bpf_context access",
- .result = REJECT,
+ .result = ACCEPT,
},
{
"check cb access: byte, wrong type",
@@ -2173,7 +2241,7 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
},
{
- "check skb->hash half load not permitted",
+ "check skb->hash half load permitted 2",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
#if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -2185,8 +2253,41 @@ static struct bpf_test tests[] = {
#endif
BPF_EXIT_INSN(),
},
+ .result = ACCEPT,
+ },
+ {
+ "check skb->hash half load not permitted, unaligned 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, hash) + 1),
+#else
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, hash) + 3),
+#endif
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "invalid bpf_context access",
+ .result = REJECT,
+ },
+ {
+ "check skb->hash half load not permitted, unaligned 3",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, hash) + 3),
+#else
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, hash) + 1),
+#endif
+ BPF_EXIT_INSN(),
+ },
.errstr = "invalid bpf_context access",
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"check cb access: half, wrong type",
@@ -2418,6 +2519,10 @@ static struct bpf_test tests[] = {
offsetof(struct __sk_buff, tc_index)),
BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
offsetof(struct __sk_buff, cb[3])),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, tstamp)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+ offsetof(struct __sk_buff, tstamp)),
BPF_EXIT_INSN(),
},
.errstr_unpriv = "",
@@ -2904,6 +3009,19 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
},
{
+ "alu32: mov u32 const",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_7, 0),
+ BPF_ALU32_IMM(BPF_AND, BPF_REG_7, 1),
+ BPF_MOV32_REG(BPF_REG_0, BPF_REG_7),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
"unpriv: partial copy of pointer",
.insns = {
BPF_MOV32_REG(BPF_REG_1, BPF_REG_10),
@@ -3249,6 +3367,7 @@ static struct bpf_test tests[] = {
.result = REJECT,
.errstr = "R0 invalid mem access 'inv'",
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"raw_stack: skb_load_bytes, spilled regs corruption 2",
@@ -3279,6 +3398,7 @@ static struct bpf_test tests[] = {
.result = REJECT,
.errstr = "R3 invalid mem access 'inv'",
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"raw_stack: skb_load_bytes, spilled regs + data",
@@ -3778,6 +3898,7 @@ static struct bpf_test tests[] = {
.errstr = "R2 invalid mem access 'inv'",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct packet access: test16 (arith on data_end)",
@@ -3880,6 +4001,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct packet access: test21 (x += pkt_ptr, 2)",
@@ -3905,6 +4027,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct packet access: test22 (x += pkt_ptr, 3)",
@@ -3935,6 +4058,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct packet access: test23 (x += pkt_ptr, 4)",
@@ -3961,6 +4085,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.errstr = "invalid access to packet, off=0 size=8, R5(id=1,off=0,r=0)",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct packet access: test24 (x += pkt_ptr, 5)",
@@ -3986,6 +4111,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct packet access: test25 (marking on <, good access)",
@@ -5117,6 +5243,7 @@ static struct bpf_test tests[] = {
.result = REJECT,
.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid cgroup storage access 5",
@@ -5233,6 +5360,7 @@ static struct bpf_test tests[] = {
.result = REJECT,
.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid per-cpu cgroup storage access 5",
@@ -5270,6 +5398,31 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
},
{
+ "write tstamp from CGROUP_SKB",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+ offsetof(struct __sk_buff, tstamp)),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "invalid bpf_context access off=152 size=8",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "read tstamp from CGROUP_SKB",
+ .insns = {
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, tstamp)),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
"multiple registers share map_lookup_elem result",
.insns = {
BPF_MOV64_IMM(BPF_REG_1, 10),
@@ -7149,6 +7302,7 @@ static struct bpf_test tests[] = {
.errstr = "invalid mem access 'inv'",
.result = REJECT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"map element value illegal alu op, 5",
@@ -7171,6 +7325,7 @@ static struct bpf_test tests[] = {
.fixup_map_hash_48b = { 3 },
.errstr = "R0 invalid mem access 'inv'",
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"map element value is preserved across register spilling",
@@ -7664,6 +7819,7 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.retval = 0 /* csum_diff of 64-byte packet */,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
@@ -9626,6 +9782,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data' > pkt_end, bad access 1",
@@ -9663,6 +9820,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_end > pkt_data', good access",
@@ -9701,6 +9859,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_end > pkt_data', bad access 2",
@@ -9719,6 +9878,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data' < pkt_end, good access",
@@ -9757,6 +9917,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data' < pkt_end, bad access 2",
@@ -9775,6 +9936,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_end < pkt_data', good access",
@@ -9792,6 +9954,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_end < pkt_data', bad access 1",
@@ -9829,6 +9992,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data' >= pkt_end, good access",
@@ -9865,6 +10029,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data' >= pkt_end, bad access 2",
@@ -9902,6 +10067,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_end >= pkt_data', bad access 1",
@@ -9940,6 +10106,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data' <= pkt_end, good access",
@@ -9958,6 +10125,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data' <= pkt_end, bad access 1",
@@ -9996,6 +10164,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_end <= pkt_data', good access",
@@ -10032,6 +10201,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_end <= pkt_data', bad access 2",
@@ -10068,6 +10238,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_meta' > pkt_data, bad access 1",
@@ -10105,6 +10276,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data > pkt_meta', good access",
@@ -10143,6 +10315,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data > pkt_meta', bad access 2",
@@ -10161,6 +10334,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_meta' < pkt_data, good access",
@@ -10199,6 +10373,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_meta' < pkt_data, bad access 2",
@@ -10217,6 +10392,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data < pkt_meta', good access",
@@ -10234,6 +10410,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data < pkt_meta', bad access 1",
@@ -10271,6 +10448,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_meta' >= pkt_data, good access",
@@ -10307,6 +10485,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_meta' >= pkt_data, bad access 2",
@@ -10344,6 +10523,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data >= pkt_meta', bad access 1",
@@ -10382,6 +10562,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_meta' <= pkt_data, good access",
@@ -10400,6 +10581,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_meta' <= pkt_data, bad access 1",
@@ -10438,6 +10620,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data <= pkt_meta', good access",
@@ -10474,6 +10657,7 @@ static struct bpf_test tests[] = {
.errstr = "R1 offset is outside of the packet",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"XDP pkt read, pkt_data <= pkt_meta', bad access 2",
@@ -10578,6 +10762,7 @@ static struct bpf_test tests[] = {
},
.result = REJECT,
.errstr = "dereference of modified ctx ptr",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"check deducing bounds from const, 8",
@@ -10591,6 +10776,7 @@ static struct bpf_test tests[] = {
},
.result = REJECT,
.errstr = "dereference of modified ctx ptr",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"check deducing bounds from const, 9",
@@ -11065,6 +11251,7 @@ static struct bpf_test tests[] = {
.result = REJECT,
.errstr = "R6 invalid mem access 'inv'",
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: two calls with args",
@@ -11930,6 +12117,7 @@ static struct bpf_test tests[] = {
.fixup_map_hash_8b = { 12, 22 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=8 off=2 size=8",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: two calls that receive map_value via arg=ptr_stack_of_caller. test2",
@@ -12073,6 +12261,7 @@ static struct bpf_test tests[] = {
.fixup_map_hash_8b = { 12, 22 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=8 off=2 size=8",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: two calls that receive map_value_ptr_or_null via arg. test1",
@@ -12244,6 +12433,7 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.retval = POINTER_VALUE,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: pkt_ptr spill into caller stack 2",
@@ -12275,6 +12465,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.errstr = "invalid access to packet",
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: pkt_ptr spill into caller stack 3",
@@ -12310,6 +12501,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
.retval = 1,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: pkt_ptr spill into caller stack 4",
@@ -12344,6 +12536,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
.retval = 1,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: pkt_ptr spill into caller stack 5",
@@ -12377,6 +12570,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.errstr = "same insn cannot be used with different",
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: pkt_ptr spill into caller stack 6",
@@ -12412,6 +12606,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.errstr = "R4 invalid mem access",
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: pkt_ptr spill into caller stack 7",
@@ -12446,6 +12641,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.errstr = "R4 invalid mem access",
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: pkt_ptr spill into caller stack 8",
@@ -12486,6 +12682,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: pkt_ptr spill into caller stack 9",
@@ -12527,6 +12724,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.errstr = "invalid access to packet",
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"calls: caller stack init to zero or map_value_or_null",
@@ -12892,6 +13090,7 @@ static struct bpf_test tests[] = {
.result = REJECT,
.errstr = "BPF_XADD stores into R2 pkt is not allowed",
.prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"xadd/w check whether src/dst got mangled, 1",
@@ -13378,6 +13577,7 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.errstr = "Unreleased reference",
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"reference tracking: alloc, check, free in both subbranches",
@@ -13406,6 +13606,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"reference tracking in call: free reference in subprog",
@@ -13496,6 +13697,28 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
},
{
+ "allocated_stack",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_7, BPF_REG_0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, -8),
+ BPF_STX_MEM(BPF_B, BPF_REG_10, BPF_REG_7, -9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_10, -9),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .result_unpriv = ACCEPT,
+ .insn_processed = 15,
+ },
+ {
"reference tracking in call: free reference in subprog and outside",
.insns = {
BPF_SK_LOOKUP,
@@ -13916,6 +14139,38 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
},
{
+ "check wire_len is not readable by sockets",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, wire_len)),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "invalid bpf_context access",
+ .result = REJECT,
+ },
+ {
+ "check wire_len is readable by tc classifier",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, wire_len)),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ },
+ {
+ "check wire_len is not writable by tc classifier",
+ .insns = {
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+ offsetof(struct __sk_buff, wire_len)),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .errstr = "invalid bpf_context access",
+ .errstr_unpriv = "R1 leaks addr",
+ .result = REJECT,
+ },
+ {
"calls: cross frame pruning",
.insns = {
/* r8 = !!random();
@@ -13939,10 +14194,200 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .errstr = "!read_ok",
+ .result = REJECT,
+ },
+ {
+ "jset: functional",
+ .insns = {
+ /* r0 = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* prep for direct packet access via r2 */
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_4, BPF_REG_3, 1),
+ BPF_EXIT_INSN(),
+
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_2, 0),
+
+ /* reg, bit 63 or bit 0 set, taken */
+ BPF_LD_IMM64(BPF_REG_8, 0x8000000000000001),
+ BPF_JMP_REG(BPF_JSET, BPF_REG_7, BPF_REG_8, 1),
+ BPF_EXIT_INSN(),
+
+ /* reg, bit 62, not taken */
+ BPF_LD_IMM64(BPF_REG_8, 0x4000000000000000),
+ BPF_JMP_REG(BPF_JSET, BPF_REG_7, BPF_REG_8, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_EXIT_INSN(),
+
+ /* imm, any bit set, taken */
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_7, -1, 1),
+ BPF_EXIT_INSN(),
+
+ /* imm, bit 31 set, taken */
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x80000000, 1),
+ BPF_EXIT_INSN(),
+
+ /* all good - return r0 == 2 */
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .runs = 7,
+ .retvals = {
+ { .retval = 2,
+ .data64 = { (1ULL << 63) | (1U << 31) | (1U << 0), }
+ },
+ { .retval = 2,
+ .data64 = { (1ULL << 63) | (1U << 31), }
+ },
+ { .retval = 2,
+ .data64 = { (1ULL << 31) | (1U << 0), }
+ },
+ { .retval = 2,
+ .data64 = { (__u32)-1, }
+ },
+ { .retval = 2,
+ .data64 = { ~0x4000000000000000ULL, }
+ },
+ { .retval = 0,
+ .data64 = { 0, }
+ },
+ { .retval = 0,
+ .data64 = { ~0ULL, }
+ },
+ },
+ },
+ {
+ "jset: sign-extend",
+ .insns = {
+ /* r0 = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* prep for direct packet access via r2 */
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_4, BPF_REG_3, 1),
+ BPF_EXIT_INSN(),
+
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_2, 0),
+
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x80000000, 1),
+ BPF_EXIT_INSN(),
+
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 2,
+ .data = { 1, 0, 0, 0, 0, 0, 0, 1, },
+ },
+ {
+ "jset: known const compare",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+ .retval_unpriv = 1,
+ .result_unpriv = ACCEPT,
+ .retval = 1,
+ .result = ACCEPT,
+ },
+ {
+ "jset: known const compare bad",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+ .errstr_unpriv = "!read_ok",
+ .result_unpriv = REJECT,
+ .errstr = "!read_ok",
+ .result = REJECT,
+ },
+ {
+ "jset: unknown const compare taken",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_prandom_u32),
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+ .errstr_unpriv = "!read_ok",
.result_unpriv = REJECT,
.errstr = "!read_ok",
.result = REJECT,
},
+ {
+ "jset: unknown const compare not taken",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_prandom_u32),
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+ .errstr_unpriv = "!read_ok",
+ .result_unpriv = REJECT,
+ .errstr = "!read_ok",
+ .result = REJECT,
+ },
+ {
+ "jset: half-known const compare",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_prandom_u32),
+ BPF_ALU64_IMM(BPF_OR, BPF_REG_0, 2),
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 3, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+ .result_unpriv = ACCEPT,
+ .result = ACCEPT,
+ },
+ {
+ "jset: range",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_prandom_u32),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xff),
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0xf0, 3),
+ BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 0x10, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+ BPF_EXIT_INSN(),
+ BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0x10, 1),
+ BPF_EXIT_INSN(),
+ BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0x10, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+ .result_unpriv = ACCEPT,
+ .result = ACCEPT,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
@@ -14225,16 +14670,43 @@ out:
return ret;
}
+static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val,
+ void *data, size_t size_data)
+{
+ __u8 tmp[TEST_DATA_LEN << 2];
+ __u32 size_tmp = sizeof(tmp);
+ uint32_t retval;
+ int err;
+
+ if (unpriv)
+ set_admin(true);
+ err = bpf_prog_test_run(fd_prog, 1, data, size_data,
+ tmp, &size_tmp, &retval, NULL);
+ if (unpriv)
+ set_admin(false);
+ if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
+ printf("Unexpected bpf_prog_test_run error ");
+ return err;
+ }
+ if (!err && retval != expected_val &&
+ expected_val != POINTER_VALUE) {
+ printf("FAIL retval %d != %d ", retval, expected_val);
+ return 1;
+ }
+
+ return 0;
+}
+
static void do_test_single(struct bpf_test *test, bool unpriv,
int *passes, int *errors)
{
- int fd_prog, expected_ret, reject_from_alignment;
+ int fd_prog, expected_ret, alignment_prevented_execution;
int prog_len, prog_type = test->prog_type;
struct bpf_insn *prog = test->insns;
+ int run_errs, run_successes;
int map_fds[MAX_NR_MAPS];
const char *expected_err;
- uint32_t expected_val;
- uint32_t retval;
+ __u32 pflags;
int i, err;
for (i = 0; i < MAX_NR_MAPS; i++)
@@ -14245,69 +14717,105 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
do_test_fixup(test, prog_type, prog, map_fds);
prog_len = probe_filter_length(prog);
- fd_prog = bpf_verify_program(prog_type, prog, prog_len,
- test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
+ pflags = 0;
+ if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
+ pflags |= BPF_F_STRICT_ALIGNMENT;
+ if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
+ pflags |= BPF_F_ANY_ALIGNMENT;
+ fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags,
"GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
expected_ret = unpriv && test->result_unpriv != UNDEF ?
test->result_unpriv : test->result;
expected_err = unpriv && test->errstr_unpriv ?
test->errstr_unpriv : test->errstr;
- expected_val = unpriv && test->retval_unpriv ?
- test->retval_unpriv : test->retval;
-
- reject_from_alignment = fd_prog < 0 &&
- (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
- strstr(bpf_vlog, "misaligned");
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
- if (reject_from_alignment) {
- printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",
- strerror(errno));
- goto fail_log;
- }
-#endif
+
+ alignment_prevented_execution = 0;
+
if (expected_ret == ACCEPT) {
- if (fd_prog < 0 && !reject_from_alignment) {
+ if (fd_prog < 0) {
printf("FAIL\nFailed to load prog '%s'!\n",
strerror(errno));
goto fail_log;
}
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ if (fd_prog >= 0 &&
+ (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS))
+ alignment_prevented_execution = 1;
+#endif
} else {
if (fd_prog >= 0) {
printf("FAIL\nUnexpected success to load!\n");
goto fail_log;
}
- if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
+ if (!strstr(bpf_vlog, expected_err)) {
printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n",
expected_err, bpf_vlog);
goto fail_log;
}
}
- if (fd_prog >= 0) {
- __u8 tmp[TEST_DATA_LEN << 2];
- __u32 size_tmp = sizeof(tmp);
-
- if (unpriv)
- set_admin(true);
- err = bpf_prog_test_run(fd_prog, 1, test->data,
- sizeof(test->data), tmp, &size_tmp,
- &retval, NULL);
- if (unpriv)
- set_admin(false);
- if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
- printf("Unexpected bpf_prog_test_run error\n");
+ if (test->insn_processed) {
+ uint32_t insn_processed;
+ char *proc;
+
+ proc = strstr(bpf_vlog, "processed ");
+ insn_processed = atoi(proc + 10);
+ if (test->insn_processed != insn_processed) {
+ printf("FAIL\nUnexpected insn_processed %u vs %u\n",
+ insn_processed, test->insn_processed);
goto fail_log;
}
- if (!err && retval != expected_val &&
- expected_val != POINTER_VALUE) {
- printf("FAIL retval %d != %d\n", retval, expected_val);
- goto fail_log;
+ }
+
+ run_errs = 0;
+ run_successes = 0;
+ if (!alignment_prevented_execution && fd_prog >= 0) {
+ uint32_t expected_val;
+ int i;
+
+ if (!test->runs) {
+ expected_val = unpriv && test->retval_unpriv ?
+ test->retval_unpriv : test->retval;
+
+ err = do_prog_test_run(fd_prog, unpriv, expected_val,
+ test->data, sizeof(test->data));
+ if (err)
+ run_errs++;
+ else
+ run_successes++;
}
+
+ for (i = 0; i < test->runs; i++) {
+ if (unpriv && test->retvals[i].retval_unpriv)
+ expected_val = test->retvals[i].retval_unpriv;
+ else
+ expected_val = test->retvals[i].retval;
+
+ err = do_prog_test_run(fd_prog, unpriv, expected_val,
+ test->retvals[i].data,
+ sizeof(test->retvals[i].data));
+ if (err) {
+ printf("(run %d/%d) ", i + 1, test->runs);
+ run_errs++;
+ } else {
+ run_successes++;
+ }
+ }
+ }
+
+ if (!run_errs) {
+ (*passes)++;
+ if (run_successes > 1)
+ printf("%d cases ", run_successes);
+ printf("OK");
+ if (alignment_prevented_execution)
+ printf(" (NOTE: not executed due to unknown alignment)");
+ printf("\n");
+ } else {
+ printf("\n");
+ goto fail_log;
}
- (*passes)++;
- printf("OK%s\n", reject_from_alignment ?
- " (NOTE: reject due to unknown alignment)" : "");
close_fds:
close(fd_prog);
for (i = 0; i < MAX_NR_MAPS; i++)
diff --git a/tools/testing/selftests/bpf/xdp_dummy.c b/tools/testing/selftests/bpf/xdp_dummy.c
new file mode 100644
index 000000000000..43b0ef1001ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_dummy.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+SEC("xdp_dummy")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
new file mode 100755
index 000000000000..d72d8488a3b2
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
@@ -0,0 +1,145 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test operations that we expect to report extended ack.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ netdev_pre_up_test
+ vxlan_vlan_add_test
+ port_vlan_add_test
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+ swp1=${NETIFS[p1]}
+ swp2=${NETIFS[p2]}
+
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+}
+
+netdev_pre_up_test()
+{
+ RET=0
+
+ ip link add name br1 up type bridge vlan_filtering 0 mcast_snooping 0
+ ip link add name vx1 up type vxlan id 1000 \
+ local 192.0.2.17 remote 192.0.2.18 \
+ dstport 4789 nolearning noudpcsum tos inherit ttl 100
+
+ ip link set dev vx1 master br1
+ check_err $?
+
+ ip link set dev $swp1 master br1
+ check_err $?
+
+ ip link add name br2 up type bridge vlan_filtering 0 mcast_snooping 0
+ ip link add name vx2 up type vxlan id 2000 \
+ local 192.0.2.17 remote 192.0.2.18 \
+ dstport 4789 nolearning noudpcsum tos inherit ttl 100
+
+ ip link set dev vx2 master br2
+ check_err $?
+
+ ip link set dev $swp2 master br2
+ check_err $?
+
+ # Unsupported configuration: mlxsw demands that all offloaded VXLAN
+ # devices have the same TTL.
+ ip link set dev vx2 down
+ ip link set dev vx2 type vxlan ttl 200
+
+ ip link set dev vx2 up &>/dev/null
+ check_fail $?
+
+ ip link set dev vx2 up 2>&1 >/dev/null | grep -q mlxsw_spectrum
+ check_err $?
+
+ log_test "extack - NETDEV_PRE_UP"
+
+ ip link del dev vx2
+ ip link del dev br2
+
+ ip link del dev vx1
+ ip link del dev br1
+}
+
+vxlan_vlan_add_test()
+{
+ RET=0
+
+ ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0
+
+ # Unsupported configuration: mlxsw demands VXLAN with "noudpcsum".
+ ip link add name vx1 up type vxlan id 1000 \
+ local 192.0.2.17 remote 192.0.2.18 \
+ dstport 4789 tos inherit ttl 100
+
+ ip link set dev vx1 master br1
+ check_err $?
+
+ bridge vlan add dev vx1 vid 1
+ check_err $?
+
+ ip link set dev $swp1 master br1
+ check_err $?
+
+ bridge vlan add dev vx1 vid 1 pvid untagged 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $?
+
+ log_test "extack - map VLAN at VXLAN device"
+
+ ip link del dev vx1
+ ip link del dev br1
+}
+
+port_vlan_add_test()
+{
+ RET=0
+
+ ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0
+
+ # Unsupported configuration: mlxsw demands VXLAN with "noudpcsum".
+ ip link add name vx1 up type vxlan id 1000 \
+ local 192.0.2.17 remote 192.0.2.18 \
+ dstport 4789 tos inherit ttl 100
+
+ ip link set dev $swp1 master br1
+ check_err $?
+
+ bridge vlan del dev $swp1 vid 1
+
+ ip link set dev vx1 master br1
+ check_err $?
+
+ bridge vlan add dev $swp1 vid 1 pvid untagged 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $?
+
+ log_test "extack - map VLAN at port"
+
+ ip link del dev vx1
+ ip link del dev br1
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh
new file mode 100755
index 000000000000..f02d83e94576
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test a "one-armed router" [1] scenario. Packets forwarded between H1 and H2
+# should be forwarded by the ASIC, but also trapped so that ICMP redirect
+# packets could be potentially generated.
+#
+# 1. https://en.wikipedia.org/wiki/One-armed_router
+#
+# +---------------------------------+
+# | H1 (vrf) |
+# | + $h1 |
+# | | 192.0.2.1/24 |
+# | | 2001:db8:1::1/64 |
+# | | |
+# | | default via 192.0.2.2 |
+# | | default via 2001:db8:1::2 |
+# +----|----------------------------+
+# |
+# +----|----------------------------------------------------------------------+
+# | SW | |
+# | +--|--------------------------------------------------------------------+ |
+# | | + $swp1 BR0 (802.1d) | |
+# | | | |
+# | | 192.0.2.2/24 | |
+# | | 2001:db8:1::2/64 | |
+# | | 198.51.100.2/24 | |
+# | | 2001:db8:2::2/64 | |
+# | | | |
+# | | + $swp2 | |
+# | +--|--------------------------------------------------------------------+ |
+# | | |
+# +----|----------------------------------------------------------------------+
+# |
+# +----|----------------------------+
+# | | default via 198.51.100.2 |
+# | | default via 2001:db8:2::2 |
+# | | |
+# | | 2001:db8:2::1/64 |
+# | | 198.51.100.1/24 |
+# | + $h2 |
+# | H2 (vrf) |
+# +---------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="ping_ipv4 ping_ipv6 fwd_mark_ipv4 fwd_mark_ipv6"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+
+ ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
+ ip -6 route add default vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+ ip -6 route del default vrf v$h1 nexthop via 2001:db8:1::2
+ ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
+
+ simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 198.51.100.1/24 2001:db8:2::1/64
+
+ ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
+ ip -6 route add default vrf v$h2 nexthop via 2001:db8:2::2
+}
+
+h2_destroy()
+{
+ ip -6 route del default vrf v$h2 nexthop via 2001:db8:2::2
+ ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
+
+ simple_if_fini $h2 198.51.100.1/24 2001:db8:2::1/64
+}
+
+switch_create()
+{
+ ip link add name br0 type bridge mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp1 up
+ ip link set dev $swp2 master br0
+ ip link set dev $swp2 up
+
+ tc qdisc add dev $swp1 clsact
+ tc qdisc add dev $swp2 clsact
+
+ __addr_add_del br0 add 192.0.2.2/24 2001:db8:1::2/64
+ __addr_add_del br0 add 198.51.100.2/24 2001:db8:2::2/64
+}
+
+switch_destroy()
+{
+ __addr_add_del br0 del 198.51.100.2/24 2001:db8:2::2/64
+ __addr_add_del br0 del 192.0.2.2/24 2001:db8:1::2/64
+
+ tc qdisc del dev $swp2 clsact
+ tc qdisc del dev $swp1 clsact
+
+ ip link set dev $swp2 down
+ ip link set dev $swp2 nomaster
+ ip link set dev $swp1 down
+ ip link set dev $swp1 nomaster
+
+ ip link set dev br0 down
+ ip link del dev br0
+}
+
+ping_ipv4()
+{
+ ping_test $h1 198.51.100.1 ": h1->h2"
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::1 ": h1->h2"
+}
+
+fwd_mark_ipv4()
+{
+ # Transmit packets from H1 to H2 and make sure they are trapped at
+ # swp1 due to loopback error, but only forwarded by the ASIC through
+ # swp2
+
+ tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
+ skip_hw dst_ip 198.51.100.1 ip_proto udp dst_port 52768 \
+ action pass
+
+ tc filter add dev $swp2 egress protocol ip pref 1 handle 101 flower \
+ skip_hw dst_ip 198.51.100.1 ip_proto udp dst_port 52768 \
+ action pass
+
+ tc filter add dev $swp2 egress protocol ip pref 2 handle 102 flower \
+ skip_sw dst_ip 198.51.100.1 ip_proto udp dst_port 52768 \
+ action pass
+
+ ip vrf exec v$h1 $MZ $h1 -c 10 -d 100msec -p 64 -A 192.0.2.1 \
+ -B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+ RET=0
+
+ tc_check_packets "dev $swp1 ingress" 101 10
+ check_err $?
+
+ log_test "fwd mark: trapping IPv4 packets due to LBERROR"
+
+ RET=0
+
+ tc_check_packets "dev $swp2 egress" 101 0
+ check_err $?
+
+ log_test "fwd mark: forwarding IPv4 packets in software"
+
+ RET=0
+
+ tc_check_packets "dev $swp2 egress" 102 10
+ check_err $?
+
+ log_test "fwd mark: forwarding IPv4 packets in hardware"
+
+ tc filter del dev $swp2 egress protocol ip pref 2 handle 102 flower
+ tc filter del dev $swp2 egress protocol ip pref 1 handle 101 flower
+ tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+}
+
+fwd_mark_ipv6()
+{
+ tc filter add dev $swp1 ingress protocol ipv6 pref 1 handle 101 flower \
+ skip_hw dst_ip 2001:db8:2::1 ip_proto udp dst_port 52768 \
+ action pass
+
+ tc filter add dev $swp2 egress protocol ipv6 pref 1 handle 101 flower \
+ skip_hw dst_ip 2001:db8:2::1 ip_proto udp dst_port 52768 \
+ action pass
+
+ tc filter add dev $swp2 egress protocol ipv6 pref 2 handle 102 flower \
+ skip_sw dst_ip 2001:db8:2::1 ip_proto udp dst_port 52768 \
+ action pass
+
+ ip vrf exec v$h1 $MZ $h1 -6 -c 10 -d 100msec -p 64 -A 2001:db8:1::1 \
+ -B 2001:db8:2::1 -t udp dp=52768,sp=42768 -q
+
+ RET=0
+
+ tc_check_packets "dev $swp1 ingress" 101 10
+ check_err $?
+
+ log_test "fwd mark: trapping IPv6 packets due to LBERROR"
+
+ RET=0
+
+ tc_check_packets "dev $swp2 egress" 101 0
+ check_err $?
+
+ log_test "fwd mark: forwarding IPv6 packets in software"
+
+ RET=0
+
+ tc_check_packets "dev $swp2 egress" 102 10
+ check_err $?
+
+ log_test "fwd mark: forwarding IPv6 packets in hardware"
+
+ tc filter del dev $swp2 egress protocol ipv6 pref 2 handle 102 flower
+ tc filter del dev $swp2 egress protocol ipv6 pref 1 handle 101 flower
+ tc filter del dev $swp1 ingress protocol ipv6 pref 1 handle 101 flower
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+ forwarding_enable
+
+ sysctl_set net.ipv4.conf.all.accept_redirects 0
+ sysctl_set net.ipv6.conf.all.accept_redirects 0
+
+ h1_create
+ h2_create
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ sysctl_restore net.ipv6.conf.all.accept_redirects
+ sysctl_restore net.ipv4.conf.all.accept_redirects
+
+ forwarding_restore
+ vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
new file mode 100755
index 000000000000..94fdbf215c14
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -0,0 +1,565 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test various interface configuration scenarios. Observe that configurations
+# deemed valid by mlxsw succeed, invalid configurations fail and that no traces
+# are produced. To prevent the test from passing in case traces are produced,
+# the user can set the 'kernel.panic_on_warn' and 'kernel.panic_on_oops'
+# sysctls in its environment.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ rif_set_addr_test
+ rif_inherit_bridge_addr_test
+ rif_non_inherit_bridge_addr_test
+ vlan_interface_deletion_test
+ bridge_deletion_test
+ bridge_vlan_flags_test
+ vlan_1_test
+ lag_bridge_upper_test
+ duplicate_vlans_test
+ vlan_rif_refcount_test
+ subport_rif_refcount_test
+ vlan_dev_deletion_test
+ lag_unlink_slaves_test
+ lag_dev_deletion_test
+ vlan_interface_uppers_test
+ devlink_reload_test
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+setup_prepare()
+{
+ swp1=${NETIFS[p1]}
+ swp2=${NETIFS[p2]}
+
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+}
+
+rif_set_addr_test()
+{
+ local swp1_mac=$(mac_get $swp1)
+ local swp2_mac=$(mac_get $swp2)
+
+ RET=0
+
+ # $swp1 and $swp2 likely got their IPv6 local addresses already, but
+ # here we need to test the transition to RIF.
+ ip addr flush dev $swp1
+ ip addr flush dev $swp2
+ sleep .1
+
+ ip addr add dev $swp1 192.0.2.1/28
+ check_err $?
+
+ ip link set dev $swp1 addr 00:11:22:33:44:55
+ check_err $?
+
+ # IP address enablement should be rejected if the MAC address prefix
+ # doesn't match other RIFs.
+ ip addr add dev $swp2 192.0.2.2/28 &>/dev/null
+ check_fail $? "IP address addition passed for a device with a wrong MAC"
+ ip addr add dev $swp2 192.0.2.2/28 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "no extack for IP address addition"
+
+ ip link set dev $swp2 addr 00:11:22:33:44:66
+ check_err $?
+ ip addr add dev $swp2 192.0.2.2/28 &>/dev/null
+ check_err $?
+
+ # Change of MAC address of a RIF should be forbidden if the new MAC
+ # doesn't share the prefix with other MAC addresses.
+ ip link set dev $swp2 addr 00:11:22:33:00:66 &>/dev/null
+ check_fail $? "change of MAC address passed for a wrong MAC"
+ ip link set dev $swp2 addr 00:11:22:33:00:66 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "no extack for MAC address change"
+
+ log_test "RIF - bad MAC change"
+
+ ip addr del dev $swp2 192.0.2.2/28
+ ip addr del dev $swp1 192.0.2.1/28
+
+ ip link set dev $swp2 addr $swp2_mac
+ ip link set dev $swp1 addr $swp1_mac
+}
+
+rif_inherit_bridge_addr_test()
+{
+ RET=0
+
+ # Create first RIF
+ ip addr add dev $swp1 192.0.2.1/28
+ check_err $?
+
+ # Create a FID RIF
+ ip link add name br1 up type bridge vlan_filtering 0
+ ip link set dev $swp2 master br1
+ ip addr add dev br1 192.0.2.17/28
+ check_err $?
+
+ # Prepare a device with a low MAC address
+ ip link add name d up type dummy
+ ip link set dev d addr 00:11:22:33:44:55
+
+ # Attach the device to br1. That prompts bridge address change, which
+ # should be vetoed, thus preventing the attachment.
+ ip link set dev d master br1 &>/dev/null
+ check_fail $? "Device with low MAC was permitted to attach a bridge with RIF"
+ ip link set dev d master br1 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "no extack for bridge attach rejection"
+
+ ip link set dev $swp2 addr 00:11:22:33:44:55 &>/dev/null
+ check_fail $? "Changing swp2's MAC address permitted"
+ ip link set dev $swp2 addr 00:11:22:33:44:55 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "no extack for bridge port MAC address change rejection"
+
+ log_test "RIF - attach port with bad MAC to bridge"
+
+ ip link del dev d
+ ip link del dev br1
+ ip addr del dev $swp1 192.0.2.1/28
+}
+
+rif_non_inherit_bridge_addr_test()
+{
+ local swp2_mac=$(mac_get $swp2)
+
+ RET=0
+
+ # Create first RIF
+ ip addr add dev $swp1 192.0.2.1/28
+ check_err $?
+
+ # Create a FID RIF
+ ip link add name br1 up type bridge vlan_filtering 0
+ ip link set dev br1 addr $swp2_mac
+ ip link set dev $swp2 master br1
+ ip addr add dev br1 192.0.2.17/28
+ check_err $?
+
+ # Prepare a device with a low MAC address
+ ip link add name d up type dummy
+ ip link set dev d addr 00:11:22:33:44:55
+
+ # Attach the device to br1. Since the bridge address was set, it should
+ # work.
+ ip link set dev d master br1 &>/dev/null
+ check_err $? "Could not attach a device with low MAC to a bridge with RIF"
+
+ # Port MAC address change should be allowed for a bridge with set MAC.
+ ip link set dev $swp2 addr 00:11:22:33:44:55
+ check_err $? "Changing swp2's MAC address not permitted"
+
+ log_test "RIF - attach port with bad MAC to bridge with set MAC"
+
+ ip link set dev $swp2 addr $swp2_mac
+ ip link del dev d
+ ip link del dev br1
+ ip addr del dev $swp1 192.0.2.1/28
+}
+
+vlan_interface_deletion_test()
+{
+ # Test that when a VLAN interface is deleted, its associated router
+ # interface (RIF) is correctly deleted and not leaked. See commit
+ # c360867ec46a ("mlxsw: spectrum: Delete RIF when VLAN device is
+ # removed") for more details
+ RET=0
+
+ ip link add name br0 type bridge vlan_filtering 1
+ ip link set dev $swp1 master br0
+
+ ip link add link br0 name br0.10 type vlan id 10
+ ip -6 address add 2001:db8:1::1/64 dev br0.10
+ ip link del dev br0.10
+
+ # If we leaked the previous RIF, then this should produce a trace
+ ip link add link br0 name br0.20 type vlan id 20
+ ip -6 address add 2001:db8:1::1/64 dev br0.20
+ ip link del dev br0.20
+
+ log_test "vlan interface deletion"
+
+ ip link del dev br0
+}
+
+bridge_deletion_test()
+{
+ # Test that when a bridge with VLAN interfaces is deleted, we correctly
+ # delete the associated RIFs. See commit 602b74eda813 ("mlxsw:
+ # spectrum_switchdev: Do not leak RIFs when removing bridge") for more
+ # details
+ RET=0
+
+ ip link add name br0 type bridge vlan_filtering 1
+ ip link set dev $swp1 master br0
+ ip -6 address add 2001:db8::1/64 dev br0
+
+ ip link add link br0 name br0.10 type vlan id 10
+ ip -6 address add 2001:db8:1::1/64 dev br0.10
+
+ ip link add link br0 name br0.20 type vlan id 20
+ ip -6 address add 2001:db8:2::1/64 dev br0.20
+
+ ip link del dev br0
+
+ # If we leaked previous RIFs, then this should produce a trace
+ ip -6 address add 2001:db8:1::1/64 dev $swp1
+ ip -6 address del 2001:db8:1::1/64 dev $swp1
+
+ log_test "bridge deletion"
+}
+
+bridge_vlan_flags_test()
+{
+ # Test that when bridge VLAN flags are toggled, we do not take
+ # unnecessary references on related structs. See commit 9e25826ffc94
+ # ("mlxsw: spectrum_switchdev: Fix port_vlan refcounting") for more
+ # details
+ RET=0
+
+ ip link add name br0 type bridge vlan_filtering 1
+ ip link set dev $swp1 master br0
+
+ bridge vlan add vid 10 dev $swp1 pvid untagged
+ bridge vlan add vid 10 dev $swp1 untagged
+ bridge vlan add vid 10 dev $swp1 pvid
+ bridge vlan add vid 10 dev $swp1
+ ip link del dev br0
+
+ # If we did not handle references correctly, then this should produce a
+ # trace
+ devlink dev reload "$DEVLINK_DEV"
+
+ # Allow netdevices to be re-created following the reload
+ sleep 20
+
+ log_test "bridge vlan flags"
+}
+
+vlan_1_test()
+{
+ # Test that VLAN 1 can be configured over mlxsw ports. In the past it
+ # was used internally for untagged traffic. See commit 47bf9df2e820
+ # ("mlxsw: spectrum: Forbid creation of VLAN 1 over port/LAG") for more
+ # details
+ RET=0
+
+ ip link add link $swp1 name $swp1.1 type vlan id 1
+ check_err $? "did not manage to create vlan 1 when should"
+
+ log_test "vlan 1"
+
+ ip link del dev $swp1.1
+}
+
+lag_bridge_upper_test()
+{
+ # Test that ports cannot be enslaved to LAG devices that have uppers
+ # and that failure is handled gracefully. See commit b3529af6bb0d
+ # ("spectrum: Reference count VLAN entries") for more details
+ RET=0
+
+ ip link add name bond1 type bond mode 802.3ad
+
+ ip link add name br0 type bridge vlan_filtering 1
+ ip link set dev bond1 master br0
+
+ ip link set dev $swp1 down
+ ip link set dev $swp1 master bond1 &> /dev/null
+ check_fail $? "managed to enslave port to lag when should not"
+
+ # This might generate a trace, if we did not handle the failure
+ # correctly
+ ip -6 address add 2001:db8:1::1/64 dev $swp1
+ ip -6 address del 2001:db8:1::1/64 dev $swp1
+
+ log_test "lag with bridge upper"
+
+ ip link del dev br0
+ ip link del dev bond1
+}
+
+duplicate_vlans_test()
+{
+ # Test that on a given port a VLAN is only used once. Either as VLAN
+ # in a VLAN-aware bridge or as a VLAN device
+ RET=0
+
+ ip link add name br0 type bridge vlan_filtering 1
+ ip link set dev $swp1 master br0
+ bridge vlan add vid 10 dev $swp1
+
+ ip link add link $swp1 name $swp1.10 type vlan id 10 &> /dev/null
+ check_fail $? "managed to create vlan device when should not"
+
+ bridge vlan del vid 10 dev $swp1
+ ip link add link $swp1 name $swp1.10 type vlan id 10
+ check_err $? "did not manage to create vlan device when should"
+ bridge vlan add vid 10 dev $swp1 &> /dev/null
+ check_fail $? "managed to add bridge vlan when should not"
+
+ log_test "duplicate vlans"
+
+ ip link del dev $swp1.10
+ ip link del dev br0
+}
+
+vlan_rif_refcount_test()
+{
+ # Test that RIFs representing VLAN interfaces are not affected from
+ # ports member in the VLAN. We use the offload indication on routes
+ # configured on the RIF to understand if it was created / destroyed
+ RET=0
+
+ ip link add name br0 type bridge vlan_filtering 1
+ ip link set dev $swp1 master br0
+
+ ip link set dev $swp1 up
+ ip link set dev br0 up
+
+ ip link add link br0 name br0.10 up type vlan id 10
+ ip -6 address add 2001:db8:1::1/64 dev br0.10
+
+ ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+ check_err $? "vlan rif was not created before adding port to vlan"
+
+ bridge vlan add vid 10 dev $swp1
+ ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+ check_err $? "vlan rif was destroyed after adding port to vlan"
+
+ bridge vlan del vid 10 dev $swp1
+ ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+ check_err $? "vlan rif was destroyed after removing port from vlan"
+
+ ip link set dev $swp1 nomaster
+ ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+ check_fail $? "vlan rif was not destroyed after unlinking port from bridge"
+
+ log_test "vlan rif refcount"
+
+ ip link del dev br0.10
+ ip link set dev $swp1 down
+ ip link del dev br0
+}
+
+subport_rif_refcount_test()
+{
+ # Test that RIFs representing upper devices of physical ports are
+ # reference counted correctly and destroyed when should. We use the
+ # offload indication on routes configured on the RIF to understand if
+ # it was created / destroyed
+ RET=0
+
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp2 down
+ ip link set dev $swp1 master bond1
+ ip link set dev $swp2 master bond1
+
+ ip link set dev bond1 up
+ ip link add link bond1 name bond1.10 up type vlan id 10
+ ip -6 address add 2001:db8:1::1/64 dev bond1
+ ip -6 address add 2001:db8:2::1/64 dev bond1.10
+
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+ check_err $? "subport rif was not created on lag device"
+ ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+ check_err $? "subport rif was not created on vlan device"
+
+ ip link set dev $swp1 nomaster
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+ check_err $? "subport rif of lag device was destroyed when should not"
+ ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+ check_err $? "subport rif of vlan device was destroyed when should not"
+
+ ip link set dev $swp2 nomaster
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+ check_fail $? "subport rif of lag device was not destroyed when should"
+ ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+ check_fail $? "subport rif of vlan device was not destroyed when should"
+
+ log_test "subport rif refcount"
+
+ ip link del dev bond1.10
+ ip link del dev bond1
+}
+
+vlan_dev_deletion_test()
+{
+ # Test that VLAN devices are correctly deleted / unlinked when enslaved
+ # to bridge
+ RET=0
+
+ ip link add name br10 type bridge
+ ip link add name br20 type bridge
+ ip link add name br30 type bridge
+ ip link add link $swp1 name $swp1.10 type vlan id 10
+ ip link add link $swp1 name $swp1.20 type vlan id 20
+ ip link add link $swp1 name $swp1.30 type vlan id 30
+ ip link set dev $swp1.10 master br10
+ ip link set dev $swp1.20 master br20
+ ip link set dev $swp1.30 master br30
+
+ # If we did not handle the situation correctly, then these operations
+ # might produce a trace
+ ip link set dev $swp1.30 nomaster
+ ip link del dev $swp1.20
+ # Deletion via ioctl uses different code paths from netlink
+ vconfig rem $swp1.10 &> /dev/null
+
+ log_test "vlan device deletion"
+
+ ip link del dev $swp1.30
+ ip link del dev br30
+ ip link del dev br20
+ ip link del dev br10
+}
+
+lag_create()
+{
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp2 down
+ ip link set dev $swp1 master bond1
+ ip link set dev $swp2 master bond1
+
+ ip link add link bond1 name bond1.10 type vlan id 10
+ ip link add link bond1 name bond1.20 type vlan id 20
+
+ ip link add name br0 type bridge vlan_filtering 1
+ ip link set dev bond1 master br0
+
+ ip link add name br10 type bridge
+ ip link set dev bond1.10 master br10
+
+ ip link add name br20 type bridge
+ ip link set dev bond1.20 master br20
+}
+
+lag_unlink_slaves_test()
+{
+ # Test that ports are correctly unlinked from their LAG master, when
+ # the LAG and its VLAN uppers are enslaved to bridges
+ RET=0
+
+ lag_create
+
+ ip link set dev $swp1 nomaster
+ check_err $? "lag slave $swp1 was not unlinked from master"
+ ip link set dev $swp2 nomaster
+ check_err $? "lag slave $swp2 was not unlinked from master"
+
+ # Try to configure corresponding VLANs as router interfaces
+ ip -6 address add 2001:db8:1::1/64 dev $swp1
+ check_err $? "failed to configure ip address on $swp1"
+
+ ip link add link $swp1 name $swp1.10 type vlan id 10
+ ip -6 address add 2001:db8:10::1/64 dev $swp1.10
+ check_err $? "failed to configure ip address on $swp1.10"
+
+ ip link add link $swp1 name $swp1.20 type vlan id 20
+ ip -6 address add 2001:db8:20::1/64 dev $swp1.20
+ check_err $? "failed to configure ip address on $swp1.20"
+
+ log_test "lag slaves unlinking"
+
+ ip link del dev $swp1.20
+ ip link del dev $swp1.10
+ ip address flush dev $swp1
+
+ ip link del dev br20
+ ip link del dev br10
+ ip link del dev br0
+ ip link del dev bond1
+}
+
+lag_dev_deletion_test()
+{
+ # Test that LAG device is correctly deleted, when the LAG and its VLAN
+ # uppers are enslaved to bridges
+ RET=0
+
+ lag_create
+
+ ip link del dev bond1
+
+ log_test "lag device deletion"
+
+ ip link del dev br20
+ ip link del dev br10
+ ip link del dev br0
+}
+
+vlan_interface_uppers_test()
+{
+ # Test that uppers of a VLAN interface are correctly sanitized
+ RET=0
+
+ ip link add name br0 type bridge vlan_filtering 1
+ ip link set dev $swp1 master br0
+
+ ip link add link br0 name br0.10 type vlan id 10
+ ip link add link br0.10 name macvlan0 \
+ type macvlan mode private &> /dev/null
+ check_fail $? "managed to create a macvlan when should not"
+
+ ip -6 address add 2001:db8:1::1/64 dev br0.10
+ ip link add link br0.10 name macvlan0 type macvlan mode private
+ check_err $? "did not manage to create a macvlan when should"
+
+ ip link del dev macvlan0
+
+ ip link add name vrf-test type vrf table 10
+ ip link set dev br0.10 master vrf-test
+ check_err $? "did not manage to enslave vlan interface to vrf"
+ ip link del dev vrf-test
+
+ ip link add name br-test type bridge
+ ip link set dev br0.10 master br-test &> /dev/null
+ check_fail $? "managed to enslave vlan interface to bridge when should not"
+ ip link del dev br-test
+
+ log_test "vlan interface uppers"
+
+ ip link del dev br0
+}
+
+devlink_reload_test()
+{
+ # Test that after executing all the above configuration tests, a
+ # devlink reload can be performed without errors
+ RET=0
+
+ devlink dev reload "$DEVLINK_DEV"
+ check_err $? "devlink reload failed"
+
+ log_test "devlink reload - last test"
+
+ sleep 20
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index 3b75180f455d..b41d6256b2d0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -8,7 +8,8 @@
lib_dir=$(dirname $0)/../../../../net/forwarding
ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
- multiple_masks_test ctcam_edge_cases_test"
+ multiple_masks_test ctcam_edge_cases_test delta_simple_test \
+ bloom_simple_test bloom_complex_test bloom_delta_test"
NUM_NETIFS=2
source $lib_dir/tc_common.sh
source $lib_dir/lib.sh
@@ -142,7 +143,7 @@ two_masks_test()
tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
$tcflags dst_ip 192.0.2.2 action drop
tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
- $tcflags dst_ip 192.0.0.0/16 action drop
+ $tcflags dst_ip 192.0.0.0/8 action drop
$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
-t ip -q
@@ -235,7 +236,7 @@ ctcam_two_atcam_masks_test()
$tcflags dst_ip 192.0.2.2 action drop
# Filter goes into A-TCAM
tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
- $tcflags dst_ip 192.0.2.0/24 action drop
+ $tcflags dst_ip 192.0.0.0/16 action drop
$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
-t ip -q
@@ -324,6 +325,258 @@ ctcam_edge_cases_test()
ctcam_no_atcam_masks_test
}
+tp_record()
+{
+ local tracepoint=$1
+ local cmd=$2
+
+ perf record -q -e $tracepoint $cmd
+ return $?
+}
+
+tp_check_hits()
+{
+ local tracepoint=$1
+ local count=$2
+
+ perf_output=`perf script -F trace:event,trace`
+ hits=`echo $perf_output | grep "$tracepoint:" | wc -l`
+ if [[ "$count" -ne "$hits" ]]; then
+ return 1
+ fi
+ return 0
+}
+
+delta_simple_test()
+{
+ # The first filter will create eRP, the second filter will fit into
+ # the first eRP with delta. Remove the first rule then and check that
+ # the eRP stays (referenced by the second filter).
+
+ RET=0
+
+ if [[ "$tcflags" != "skip_sw" ]]; then
+ return 0;
+ fi
+
+ tp_record "objagg:*" "tc filter add dev $h2 ingress protocol ip \
+ pref 1 handle 101 flower $tcflags dst_ip 192.0.0.0/24 \
+ action drop"
+ tp_check_hits "objagg:objagg_obj_root_create" 1
+ check_err $? "eRP was not created"
+
+ tp_record "objagg:*" "tc filter add dev $h2 ingress protocol ip \
+ pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \
+ action drop"
+ tp_check_hits "objagg:objagg_obj_root_create" 0
+ check_err $? "eRP was incorrectly created"
+ tp_check_hits "objagg:objagg_obj_parent_assign" 1
+ check_err $? "delta was not created"
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -q
+
+ tc_check_packets "dev $h2 ingress" 101 1
+ check_fail $? "Matched a wrong filter"
+
+ tc_check_packets "dev $h2 ingress" 102 1
+ check_err $? "Did not match on correct filter"
+
+ tp_record "objagg:*" "tc filter del dev $h2 ingress protocol ip \
+ pref 1 handle 101 flower"
+ tp_check_hits "objagg:objagg_obj_root_destroy" 0
+ check_err $? "eRP was incorrectly destroyed"
+ tp_check_hits "objagg:objagg_obj_parent_unassign" 0
+ check_err $? "delta was incorrectly destroyed"
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -q
+
+ tc_check_packets "dev $h2 ingress" 102 2
+ check_err $? "Did not match on correct filter after the first was removed"
+
+ tp_record "objagg:*" "tc filter del dev $h2 ingress protocol ip \
+ pref 2 handle 102 flower"
+ tp_check_hits "objagg:objagg_obj_parent_unassign" 1
+ check_err $? "delta was not destroyed"
+ tp_check_hits "objagg:objagg_obj_root_destroy" 1
+ check_err $? "eRP was not destroyed"
+
+ log_test "delta simple test ($tcflags)"
+}
+
+bloom_simple_test()
+{
+ # Bloom filter requires that the eRP table is used. This test
+ # verifies that Bloom filter is not harming correctness of ACLs.
+ # First, make sure that eRP table is used and then set rule patterns
+ # which are distant enough and will result skipping a lookup after
+ # consulting the Bloom filter. Although some eRP lookups are skipped,
+ # the correct filter should be hit.
+
+ RET=0
+
+ tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+ $tcflags dst_ip 192.0.2.2 action drop
+ tc filter add dev $h2 ingress protocol ip pref 5 handle 104 flower \
+ $tcflags dst_ip 198.51.100.2 action drop
+ tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+ $tcflags dst_ip 192.0.0.0/8 action drop
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -q
+
+ tc_check_packets "dev $h2 ingress" 101 1
+ check_err $? "Two filters - did not match highest priority"
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 198.51.100.1 -B 198.51.100.2 \
+ -t ip -q
+
+ tc_check_packets "dev $h2 ingress" 104 1
+ check_err $? "Single filter - did not match"
+
+ tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -q
+
+ tc_check_packets "dev $h2 ingress" 103 1
+ check_err $? "Low prio filter - did not match"
+
+ tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+ $tcflags dst_ip 198.0.0.0/8 action drop
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 198.51.100.1 -B 198.51.100.2 \
+ -t ip -q
+
+ tc_check_packets "dev $h2 ingress" 102 1
+ check_err $? "Two filters - did not match highest priority after add"
+
+ tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+ tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+ tc filter del dev $h2 ingress protocol ip pref 5 handle 104 flower
+
+ log_test "bloom simple test ($tcflags)"
+}
+
+bloom_complex_test()
+{
+ # Bloom filter index computation is affected from region ID, eRP
+ # ID and from the region key size. In order to excercise those parts
+ # of the Bloom filter code, use a series of regions, each with a
+ # different key size and send packet that should hit all of them.
+ local index
+
+ RET=0
+ NUM_CHAINS=4
+ BASE_INDEX=100
+
+ # Create chain with up to 2 key blocks (ip_proto only)
+ tc chain add dev $h2 ingress chain 1 protocol ip flower \
+ ip_proto tcp &> /dev/null
+ # Create chain with 2-4 key blocks (ip_proto, src MAC)
+ tc chain add dev $h2 ingress chain 2 protocol ip flower \
+ ip_proto tcp \
+ src_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+ # Create chain with 4-8 key blocks (ip_proto, src & dst MAC, IPv4 dest)
+ tc chain add dev $h2 ingress chain 3 protocol ip flower \
+ ip_proto tcp \
+ dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF \
+ src_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF \
+ dst_ip 0.0.0.0/32 &> /dev/null
+ # Default chain contains all fields and therefore is 8-12 key blocks
+ tc chain add dev $h2 ingress chain 4
+
+ # We need at least 2 rules in every region to have eRP table active
+ # so create a dummy rule per chain using a different pattern
+ for i in $(eval echo {0..$NUM_CHAINS}); do
+ index=$((BASE_INDEX - 1 - i))
+ tc filter add dev $h2 ingress chain $i protocol ip \
+ pref 2 handle $index flower \
+ $tcflags ip_proto tcp action drop
+ done
+
+ # Add rules to test Bloom filter, each in a different chain
+ index=$BASE_INDEX
+ tc filter add dev $h2 ingress protocol ip \
+ pref 1 handle $((++index)) flower \
+ $tcflags dst_ip 192.0.0.0/16 action goto chain 1
+ tc filter add dev $h2 ingress chain 1 protocol ip \
+ pref 1 handle $((++index)) flower \
+ $tcflags action goto chain 2
+ tc filter add dev $h2 ingress chain 2 protocol ip \
+ pref 1 handle $((++index)) flower \
+ $tcflags src_mac $h1mac action goto chain 3
+ tc filter add dev $h2 ingress chain 3 protocol ip \
+ pref 1 handle $((++index)) flower \
+ $tcflags dst_ip 192.0.0.0/8 action goto chain 4
+ tc filter add dev $h2 ingress chain 4 protocol ip \
+ pref 1 handle $((++index)) flower \
+ $tcflags src_ip 192.0.2.0/24 action drop
+
+ # Send a packet that is supposed to hit all chains
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -q
+
+ for i in $(eval echo {0..$NUM_CHAINS}); do
+ index=$((BASE_INDEX + i + 1))
+ tc_check_packets "dev $h2 ingress" $index 1
+ check_err $? "Did not match chain $i"
+ done
+
+ # Rules cleanup
+ for i in $(eval echo {$NUM_CHAINS..0}); do
+ index=$((BASE_INDEX - i - 1))
+ tc filter del dev $h2 ingress chain $i \
+ pref 2 handle $index flower
+ index=$((BASE_INDEX + i + 1))
+ tc filter del dev $h2 ingress chain $i \
+ pref 1 handle $index flower
+ done
+
+ # Chains cleanup
+ for i in $(eval echo {$NUM_CHAINS..1}); do
+ tc chain del dev $h2 ingress chain $i
+ done
+
+ log_test "bloom complex test ($tcflags)"
+}
+
+
+bloom_delta_test()
+{
+ # When multiple masks are used, the eRP table is activated. When
+ # masks are close enough (delta) the masks reside on the same
+ # eRP table. This test verifies that the eRP table is correctly
+ # allocated and used in delta condition and that Bloom filter is
+ # still functional with delta.
+
+ RET=0
+
+ tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+ $tcflags dst_ip 192.1.0.0/16 action drop
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.1.2.1 -B 192.1.2.2 \
+ -t ip -q
+
+ tc_check_packets "dev $h2 ingress" 103 1
+ check_err $? "Single filter - did not match"
+
+ tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+ $tcflags dst_ip 192.2.1.0/24 action drop
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.2.1.1 -B 192.2.1.2 \
+ -t ip -q
+
+ tc_check_packets "dev $h2 ingress" 102 1
+ check_err $? "Delta filters - did not match second filter"
+
+ tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+ tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+ log_test "bloom delta test ($tcflags)"
+}
+
setup_prepare()
{
h1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
new file mode 100755
index 000000000000..dcf9f4e913e0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -0,0 +1,1103 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test various aspects of VxLAN offloading which are specific to mlxsw, such
+# as sanitization of invalid configurations and offload indication.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="sanitization_test offload_indication_test \
+ sanitization_vlan_aware_test offload_indication_vlan_aware_test"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+ swp1=${NETIFS[p1]}
+ swp2=${NETIFS[p2]}
+
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+}
+
+sanitization_single_dev_test_pass()
+{
+ ip link set dev $swp1 master br0
+ check_err $?
+ ip link set dev vxlan0 master br0
+ check_err $?
+
+ ip link set dev $swp1 nomaster
+
+ ip link set dev $swp1 master br0
+ check_err $?
+}
+
+sanitization_single_dev_test_fail()
+{
+ ip link set dev $swp1 master br0
+ check_err $?
+ ip link set dev vxlan0 master br0 &> /dev/null
+ check_fail $?
+
+ ip link set dev $swp1 nomaster
+
+ ip link set dev vxlan0 master br0
+ check_err $?
+ ip link set dev $swp1 master br0 &> /dev/null
+ check_fail $?
+}
+
+sanitization_single_dev_valid_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ sanitization_single_dev_test_pass
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device - valid configuration"
+}
+
+sanitization_single_dev_vlan_aware_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ sanitization_single_dev_test_pass
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with a vlan-aware bridge"
+}
+
+sanitization_single_dev_mcast_enabled_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with a multicast enabled bridge"
+}
+
+sanitization_single_dev_mcast_group_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789 \
+ dev $swp2 group 239.0.0.1
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with a multicast group"
+}
+
+sanitization_single_dev_no_local_ip_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit dstport 4789
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with no local ip"
+}
+
+sanitization_single_dev_local_ipv6_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 2001:db8::1 dstport 4789
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with local ipv6 address"
+}
+
+sanitization_single_dev_learning_enabled_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 learning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ sanitization_single_dev_test_pass
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with learning enabled"
+}
+
+sanitization_single_dev_local_interface_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789 dev $swp2
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with local interface"
+}
+
+sanitization_single_dev_port_range_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789 \
+ srcport 4000 5000
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with udp source port range"
+}
+
+sanitization_single_dev_tos_static_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos 20 local 198.51.100.1 dstport 4789
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with static tos"
+}
+
+sanitization_single_dev_ttl_inherit_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl inherit tos inherit local 198.51.100.1 dstport 4789
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with inherit ttl"
+}
+
+sanitization_single_dev_udp_checksum_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning udpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ sanitization_single_dev_test_fail
+
+ ip link del dev vxlan0
+ ip link del dev br0
+
+ log_test "vxlan device with udp checksum"
+}
+
+sanitization_single_dev_test()
+{
+ # These tests make sure that we correctly sanitize VxLAN device
+ # configurations we do not support
+ sanitization_single_dev_valid_test
+ sanitization_single_dev_vlan_aware_test
+ sanitization_single_dev_mcast_enabled_test
+ sanitization_single_dev_mcast_group_test
+ sanitization_single_dev_no_local_ip_test
+ sanitization_single_dev_local_ipv6_test
+ sanitization_single_dev_learning_enabled_test
+ sanitization_single_dev_local_interface_test
+ sanitization_single_dev_port_range_test
+ sanitization_single_dev_tos_static_test
+ sanitization_single_dev_ttl_inherit_test
+ sanitization_single_dev_udp_checksum_test
+}
+
+sanitization_multi_devs_test_pass()
+{
+ ip link set dev $swp1 master br0
+ check_err $?
+ ip link set dev vxlan0 master br0
+ check_err $?
+ ip link set dev $swp2 master br1
+ check_err $?
+ ip link set dev vxlan1 master br1
+ check_err $?
+
+ ip link set dev $swp2 nomaster
+ ip link set dev $swp1 nomaster
+
+ ip link set dev $swp1 master br0
+ check_err $?
+ ip link set dev $swp2 master br1
+ check_err $?
+}
+
+sanitization_multi_devs_test_fail()
+{
+ ip link set dev $swp1 master br0
+ check_err $?
+ ip link set dev vxlan0 master br0
+ check_err $?
+ ip link set dev $swp2 master br1
+ check_err $?
+ ip link set dev vxlan1 master br1 &> /dev/null
+ check_fail $?
+
+ ip link set dev $swp2 nomaster
+ ip link set dev $swp1 nomaster
+
+ ip link set dev vxlan1 master br1
+ check_err $?
+ ip link set dev $swp1 master br0
+ check_err $?
+ ip link set dev $swp2 master br1 &> /dev/null
+ check_fail $?
+}
+
+sanitization_multi_devs_valid_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+ ip link add dev br1 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+ ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ sanitization_multi_devs_test_pass
+
+ ip link del dev vxlan1
+ ip link del dev vxlan0
+ ip link del dev br1
+ ip link del dev br0
+
+ log_test "multiple vxlan devices - valid configuration"
+}
+
+sanitization_multi_devs_ttl_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+ ip link add dev br1 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+ ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+ ttl 40 tos inherit local 198.51.100.1 dstport 4789
+
+ sanitization_multi_devs_test_fail
+
+ ip link del dev vxlan1
+ ip link del dev vxlan0
+ ip link del dev br1
+ ip link del dev br0
+
+ log_test "multiple vxlan devices with different ttl"
+}
+
+sanitization_multi_devs_udp_dstport_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+ ip link add dev br1 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+ ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 5789
+
+ sanitization_multi_devs_test_fail
+
+ ip link del dev vxlan1
+ ip link del dev vxlan0
+ ip link del dev br1
+ ip link del dev br0
+
+ log_test "multiple vxlan devices with different udp destination port"
+}
+
+sanitization_multi_devs_local_ip_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0
+ ip link add dev br1 type bridge mcast_snooping 0
+
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+ ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.2 dstport 4789
+
+ sanitization_multi_devs_test_fail
+
+ ip link del dev vxlan1
+ ip link del dev vxlan0
+ ip link del dev br1
+ ip link del dev br0
+
+ log_test "multiple vxlan devices with different local ip"
+}
+
+sanitization_multi_devs_test()
+{
+ # The device has a single VTEP, which means all the VxLAN devices
+ # we offload must share certain properties such as source IP and
+ # UDP destination port. These tests make sure that we forbid
+ # configurations that violate this limitation
+ sanitization_multi_devs_valid_test
+ sanitization_multi_devs_ttl_test
+ sanitization_multi_devs_udp_dstport_test
+ sanitization_multi_devs_local_ip_test
+}
+
+sanitization_test()
+{
+ sanitization_single_dev_test
+ sanitization_multi_devs_test
+}
+
+offload_indication_setup_create()
+{
+ # Create a simple setup with two bridges, each with a VxLAN device
+ # and one local port
+ ip link add name br0 up type bridge mcast_snooping 0
+ ip link add name br1 up type bridge mcast_snooping 0
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br1
+
+ ip address add 198.51.100.1/32 dev lo
+
+ ip link add name vxlan0 up master br0 type vxlan id 10 nolearning \
+ noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+ ip link add name vxlan1 up master br1 type vxlan id 20 nolearning \
+ noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+}
+
+offload_indication_setup_destroy()
+{
+ ip link del dev vxlan1
+ ip link del dev vxlan0
+
+ ip address del 198.51.100.1/32 dev lo
+
+ ip link set dev $swp2 nomaster
+ ip link set dev $swp1 nomaster
+
+ ip link del dev br1
+ ip link del dev br0
+}
+
+offload_indication_fdb_flood_test()
+{
+ RET=0
+
+ bridge fdb append 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2
+
+ bridge fdb show brport vxlan0 | grep 00:00:00:00:00:00 \
+ | grep -q offload
+ check_err $?
+
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self
+
+ log_test "vxlan flood entry offload indication"
+}
+
+offload_indication_fdb_bridge_test()
+{
+ RET=0
+
+ bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self master static \
+ dst 198.51.100.2
+
+ bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+ | grep -q offload
+ check_err $?
+ bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+ | grep -q offload
+ check_err $?
+
+ log_test "vxlan entry offload indication - initial state"
+
+ # Remove FDB entry from the bridge driver and check that corresponding
+ # entry in the VxLAN driver is not marked as offloaded
+ RET=0
+
+ bridge fdb del de:ad:be:ef:13:37 dev vxlan0 master
+ bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+ | grep -q offload
+ check_fail $?
+
+ log_test "vxlan entry offload indication - after removal from bridge"
+
+ # Add the FDB entry back to the bridge driver and make sure it is
+ # marked as offloaded in both drivers
+ RET=0
+
+ bridge fdb add de:ad:be:ef:13:37 dev vxlan0 master static
+ bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+ | grep -q offload
+ check_err $?
+ bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+ | grep -q offload
+ check_err $?
+
+ log_test "vxlan entry offload indication - after re-add to bridge"
+
+ # Remove FDB entry from the VxLAN driver and check that corresponding
+ # entry in the bridge driver is not marked as offloaded
+ RET=0
+
+ bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self
+ bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+ | grep -q offload
+ check_fail $?
+
+ log_test "vxlan entry offload indication - after removal from vxlan"
+
+ # Add the FDB entry back to the VxLAN driver and make sure it is
+ # marked as offloaded in both drivers
+ RET=0
+
+ bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self dst 198.51.100.2
+ bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+ | grep -q offload
+ check_err $?
+ bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+ | grep -q offload
+ check_err $?
+
+ log_test "vxlan entry offload indication - after re-add to vxlan"
+
+ bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self master
+}
+
+offload_indication_fdb_test()
+{
+ offload_indication_fdb_flood_test
+ offload_indication_fdb_bridge_test
+}
+
+offload_indication_decap_route_test()
+{
+ RET=0
+
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ ip link set dev vxlan0 down
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ ip link set dev vxlan1 down
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_fail $?
+
+ log_test "vxlan decap route - vxlan device down"
+
+ RET=0
+
+ ip link set dev vxlan1 up
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ ip link set dev vxlan0 up
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ log_test "vxlan decap route - vxlan device up"
+
+ RET=0
+
+ ip address delete 198.51.100.1/32 dev lo
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_fail $?
+
+ ip address add 198.51.100.1/32 dev lo
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ log_test "vxlan decap route - add local route"
+
+ RET=0
+
+ ip link set dev $swp1 nomaster
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ ip link set dev $swp2 nomaster
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_fail $?
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br1
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ log_test "vxlan decap route - local ports enslavement"
+
+ RET=0
+
+ ip link del dev br0
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ ip link del dev br1
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_fail $?
+
+ log_test "vxlan decap route - bridge device deletion"
+
+ RET=0
+
+ ip link add name br0 up type bridge mcast_snooping 0
+ ip link add name br1 up type bridge mcast_snooping 0
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br1
+ ip link set dev vxlan0 master br0
+ ip link set dev vxlan1 master br1
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ ip link del dev vxlan0
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ ip link del dev vxlan1
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_fail $?
+
+ log_test "vxlan decap route - vxlan device deletion"
+
+ ip link add name vxlan0 up master br0 type vxlan id 10 nolearning \
+ noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+ ip link add name vxlan1 up master br1 type vxlan id 20 nolearning \
+ noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+}
+
+check_fdb_offloaded()
+{
+ local mac=00:11:22:33:44:55
+ local zmac=00:00:00:00:00:00
+
+ bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload
+ check_err $?
+ bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload
+ check_err $?
+
+ bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+ check_err $?
+}
+
+check_vxlan_fdb_not_offloaded()
+{
+ local mac=00:11:22:33:44:55
+ local zmac=00:00:00:00:00:00
+
+ bridge fdb show dev vxlan0 | grep $mac | grep -q self
+ check_err $?
+ bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload
+ check_fail $?
+
+ bridge fdb show dev vxlan0 | grep $zmac | grep -q self
+ check_err $?
+ bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+ check_fail $?
+}
+
+check_bridge_fdb_not_offloaded()
+{
+ local mac=00:11:22:33:44:55
+ local zmac=00:00:00:00:00:00
+
+ bridge fdb show dev vxlan0 | grep $mac | grep -q master
+ check_err $?
+ bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload
+ check_fail $?
+}
+
+__offload_indication_join_vxlan_first()
+{
+ local vid=$1; shift
+
+ local mac=00:11:22:33:44:55
+ local zmac=00:00:00:00:00:00
+
+ bridge fdb append $zmac dev vxlan0 self dst 198.51.100.2
+
+ ip link set dev vxlan0 master br0
+ bridge fdb add dev vxlan0 $mac self master static dst 198.51.100.2
+
+ RET=0
+ check_vxlan_fdb_not_offloaded
+ ip link set dev $swp1 master br0
+ sleep .1
+ check_fdb_offloaded
+ log_test "offload indication - attach vxlan first"
+
+ RET=0
+ ip link set dev vxlan0 down
+ check_vxlan_fdb_not_offloaded
+ check_bridge_fdb_not_offloaded
+ log_test "offload indication - set vxlan down"
+
+ RET=0
+ ip link set dev vxlan0 up
+ sleep .1
+ check_fdb_offloaded
+ log_test "offload indication - set vxlan up"
+
+ if [[ ! -z $vid ]]; then
+ RET=0
+ bridge vlan del dev vxlan0 vid $vid
+ check_vxlan_fdb_not_offloaded
+ check_bridge_fdb_not_offloaded
+ log_test "offload indication - delete VLAN"
+
+ RET=0
+ bridge vlan add dev vxlan0 vid $vid
+ check_vxlan_fdb_not_offloaded
+ check_bridge_fdb_not_offloaded
+ log_test "offload indication - add tagged VLAN"
+
+ RET=0
+ bridge vlan add dev vxlan0 vid $vid pvid untagged
+ sleep .1
+ check_fdb_offloaded
+ log_test "offload indication - add pvid/untagged VLAN"
+ fi
+
+ RET=0
+ ip link set dev $swp1 nomaster
+ check_vxlan_fdb_not_offloaded
+ log_test "offload indication - detach port"
+}
+
+offload_indication_join_vxlan_first()
+{
+ ip link add dev br0 up type bridge mcast_snooping 0
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ __offload_indication_join_vxlan_first
+
+ ip link del dev vxlan0
+ ip link del dev br0
+}
+
+__offload_indication_join_vxlan_last()
+{
+ local zmac=00:00:00:00:00:00
+
+ RET=0
+
+ bridge fdb append $zmac dev vxlan0 self dst 198.51.100.2
+
+ ip link set dev $swp1 master br0
+
+ bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+ check_fail $?
+
+ ip link set dev vxlan0 master br0
+
+ bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+ check_err $?
+
+ log_test "offload indication - attach vxlan last"
+}
+
+offload_indication_join_vxlan_last()
+{
+ ip link add dev br0 up type bridge mcast_snooping 0
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ __offload_indication_join_vxlan_last
+
+ ip link del dev vxlan0
+ ip link del dev br0
+}
+
+offload_indication_test()
+{
+ offload_indication_setup_create
+ offload_indication_fdb_test
+ offload_indication_decap_route_test
+ offload_indication_setup_destroy
+
+ log_info "offload indication - replay & cleanup"
+ offload_indication_join_vxlan_first
+ offload_indication_join_vxlan_last
+}
+
+sanitization_vlan_aware_test()
+{
+ RET=0
+
+ ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1
+
+ ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \
+ noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ ip link add name vxlan20 up master br0 type vxlan id 20 nolearning \
+ noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ # Test that when each VNI is mapped to a different VLAN we can enslave
+ # a port to the bridge
+ bridge vlan add vid 10 dev vxlan10 pvid untagged
+ bridge vlan add vid 20 dev vxlan20 pvid untagged
+
+ ip link set dev $swp1 master br0
+ check_err $?
+
+ log_test "vlan-aware - enslavement to vlan-aware bridge"
+
+ # Try to map both VNIs to the same VLAN and make sure configuration
+ # fails
+ RET=0
+
+ bridge vlan add vid 10 dev vxlan20 pvid untagged &> /dev/null
+ check_fail $?
+
+ log_test "vlan-aware - two vnis mapped to the same vlan"
+
+ # Test that enslavement of a port to a bridge fails when two VNIs
+ # are mapped to the same VLAN
+ RET=0
+
+ ip link set dev $swp1 nomaster
+
+ bridge vlan del vid 20 dev vxlan20 pvid untagged
+ bridge vlan add vid 10 dev vxlan20 pvid untagged
+
+ ip link set dev $swp1 master br0 &> /dev/null
+ check_fail $?
+
+ log_test "vlan-aware - failed enslavement to vlan-aware bridge"
+
+ ip link del dev vxlan20
+ ip link del dev vxlan10
+ ip link del dev br0
+}
+
+offload_indication_vlan_aware_setup_create()
+{
+ # Create a simple setup with two VxLAN devices and a single VLAN-aware
+ # bridge
+ ip link add name br0 up type bridge mcast_snooping 0 vlan_filtering 1 \
+ vlan_default_pvid 0
+
+ ip link set dev $swp1 master br0
+
+ bridge vlan add vid 10 dev $swp1
+ bridge vlan add vid 20 dev $swp1
+
+ ip address add 198.51.100.1/32 dev lo
+
+ ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \
+ noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+ ip link add name vxlan20 up master br0 type vxlan id 20 nolearning \
+ noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ bridge vlan add vid 10 dev vxlan10 pvid untagged
+ bridge vlan add vid 20 dev vxlan20 pvid untagged
+}
+
+offload_indication_vlan_aware_setup_destroy()
+{
+ bridge vlan del vid 20 dev vxlan20
+ bridge vlan del vid 10 dev vxlan10
+
+ ip link del dev vxlan20
+ ip link del dev vxlan10
+
+ ip address del 198.51.100.1/32 dev lo
+
+ bridge vlan del vid 20 dev $swp1
+ bridge vlan del vid 10 dev $swp1
+
+ ip link set dev $swp1 nomaster
+
+ ip link del dev br0
+}
+
+offload_indication_vlan_aware_fdb_test()
+{
+ RET=0
+
+ log_info "vxlan entry offload indication - vlan-aware"
+
+ bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self master static \
+ dst 198.51.100.2 vlan 10
+
+ bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
+ | grep -q offload
+ check_err $?
+ bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
+ | grep -q offload
+ check_err $?
+
+ log_test "vxlan entry offload indication - initial state"
+
+ # Remove FDB entry from the bridge driver and check that corresponding
+ # entry in the VxLAN driver is not marked as offloaded
+ RET=0
+
+ bridge fdb del de:ad:be:ef:13:37 dev vxlan10 master vlan 10
+ bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
+ | grep -q offload
+ check_fail $?
+
+ log_test "vxlan entry offload indication - after removal from bridge"
+
+ # Add the FDB entry back to the bridge driver and make sure it is
+ # marked as offloaded in both drivers
+ RET=0
+
+ bridge fdb add de:ad:be:ef:13:37 dev vxlan10 master static vlan 10
+ bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
+ | grep -q offload
+ check_err $?
+ bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
+ | grep -q offload
+ check_err $?
+
+ log_test "vxlan entry offload indication - after re-add to bridge"
+
+ # Remove FDB entry from the VxLAN driver and check that corresponding
+ # entry in the bridge driver is not marked as offloaded
+ RET=0
+
+ bridge fdb del de:ad:be:ef:13:37 dev vxlan10 self
+ bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
+ | grep -q offload
+ check_fail $?
+
+ log_test "vxlan entry offload indication - after removal from vxlan"
+
+ # Add the FDB entry back to the VxLAN driver and make sure it is
+ # marked as offloaded in both drivers
+ RET=0
+
+ bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self dst 198.51.100.2
+ bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
+ | grep -q offload
+ check_err $?
+ bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
+ | grep -q offload
+ check_err $?
+
+ log_test "vxlan entry offload indication - after re-add to vxlan"
+
+ bridge fdb del de:ad:be:ef:13:37 dev vxlan10 self master vlan 10
+}
+
+offload_indication_vlan_aware_decap_route_test()
+{
+ RET=0
+
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ # Toggle PVID flag on one VxLAN device and make sure route is still
+ # marked as offloaded
+ bridge vlan add vid 10 dev vxlan10 untagged
+
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ # Toggle PVID flag on second VxLAN device and make sure route is no
+ # longer marked as offloaded
+ bridge vlan add vid 20 dev vxlan20 untagged
+
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_fail $?
+
+ # Toggle PVID flag back and make sure route is marked as offloaded
+ bridge vlan add vid 10 dev vxlan10 pvid untagged
+ bridge vlan add vid 20 dev vxlan20 pvid untagged
+
+ ip route show table local | grep 198.51.100.1 | grep -q offload
+ check_err $?
+
+ log_test "vxlan decap route - vni map/unmap"
+}
+
+offload_indication_vlan_aware_join_vxlan_first()
+{
+ ip link add dev br0 up type bridge mcast_snooping 0 \
+ vlan_filtering 1 vlan_default_pvid 1
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ __offload_indication_join_vxlan_first 1
+
+ ip link del dev vxlan0
+ ip link del dev br0
+}
+
+offload_indication_vlan_aware_join_vxlan_last()
+{
+ ip link add dev br0 up type bridge mcast_snooping 0 \
+ vlan_filtering 1 vlan_default_pvid 1
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ __offload_indication_join_vxlan_last
+
+ ip link del dev vxlan0
+ ip link del dev br0
+}
+
+offload_indication_vlan_aware_l3vni_test()
+{
+ local zmac=00:00:00:00:00:00
+
+ RET=0
+
+ sysctl_set net.ipv6.conf.default.disable_ipv6 1
+ ip link add dev br0 up type bridge mcast_snooping 0 \
+ vlan_filtering 1 vlan_default_pvid 0
+ ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ ip link set dev $swp1 master br0
+
+ # The test will use the offload indication on the FDB entry to
+ # understand if the tunnel is offloaded or not
+ bridge fdb append $zmac dev vxlan0 self dst 192.0.2.1
+
+ ip link set dev vxlan0 master br0
+ bridge vlan add dev vxlan0 vid 10 pvid untagged
+
+ # No local port or router port is member in the VLAN, so tunnel should
+ # not be offloaded
+ bridge fdb show brport vxlan0 | grep $zmac | grep self \
+ | grep -q offload
+ check_fail $? "vxlan tunnel offloaded when should not"
+
+ # Configure a VLAN interface and make sure tunnel is offloaded
+ ip link add link br0 name br10 up type vlan id 10
+ sysctl_set net.ipv6.conf.br10.disable_ipv6 0
+ ip -6 address add 2001:db8:1::1/64 dev br10
+ bridge fdb show brport vxlan0 | grep $zmac | grep self \
+ | grep -q offload
+ check_err $? "vxlan tunnel not offloaded when should"
+
+ # Unlink the VXLAN device, make sure tunnel is no longer offloaded,
+ # then add it back to the bridge and make sure it is offloaded
+ ip link set dev vxlan0 nomaster
+ bridge fdb show brport vxlan0 | grep $zmac | grep self \
+ | grep -q offload
+ check_fail $? "vxlan tunnel offloaded after unlinked from bridge"
+
+ ip link set dev vxlan0 master br0
+ bridge fdb show brport vxlan0 | grep $zmac | grep self \
+ | grep -q offload
+ check_fail $? "vxlan tunnel offloaded despite no matching vid"
+
+ bridge vlan add dev vxlan0 vid 10 pvid untagged
+ bridge fdb show brport vxlan0 | grep $zmac | grep self \
+ | grep -q offload
+ check_err $? "vxlan tunnel not offloaded after adding vid"
+
+ log_test "vxlan - l3 vni"
+
+ ip link del dev vxlan0
+ ip link del dev br0
+ sysctl_restore net.ipv6.conf.default.disable_ipv6
+}
+
+offload_indication_vlan_aware_test()
+{
+ offload_indication_vlan_aware_setup_create
+ offload_indication_vlan_aware_fdb_test
+ offload_indication_vlan_aware_decap_route_test
+ offload_indication_vlan_aware_setup_destroy
+
+ log_info "offload indication - replay & cleanup - vlan aware"
+ offload_indication_vlan_aware_join_vxlan_first
+ offload_indication_vlan_aware_join_vxlan_last
+ offload_indication_vlan_aware_l3vni_test
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
new file mode 100755
index 000000000000..fedcb7b35af9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
@@ -0,0 +1,309 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test VxLAN flooding. The device stores flood records in a singly linked list
+# where each record stores up to three IPv4 addresses of remote VTEPs. The test
+# verifies that packets are correctly flooded in various cases such as deletion
+# of a record in the middle of the list.
+#
+# +--------------------+
+# | H1 (vrf) |
+# | + $h1 |
+# | | 203.0.113.1/24|
+# +----|---------------+
+# |
+# +----|----------------------------------------------------------------------+
+# | SW | |
+# | +--|--------------------------------------------------------------------+ |
+# | | + $swp1 BR0 (802.1d) | |
+# | | | |
+# | | + vxlan0 (vxlan) | |
+# | | local 198.51.100.1 | |
+# | | remote 198.51.100.{2..13} | |
+# | | id 10 dstport 4789 | |
+# | +-----------------------------------------------------------------------+ |
+# | |
+# | 198.51.100.0/24 via 192.0.2.2 |
+# | |
+# | + $rp1 |
+# | | 192.0.2.1/24 |
+# +----|----------------------------------------------------------------------+
+# |
+# +----|--------------------------------------------------------+
+# | | R2 (vrf) |
+# | + $rp2 |
+# | 192.0.2.2/24 |
+# | |
+# +-------------------------------------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="flooding_test"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 203.0.113.1/24
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 203.0.113.1/24
+}
+
+switch_create()
+{
+ # Make sure the bridge uses the MAC address of the local port and
+ # not that of the VxLAN's device
+ ip link add dev br0 type bridge mcast_snooping 0
+ ip link set dev br0 address $(mac_get $swp1)
+
+ ip link add name vxlan0 type vxlan id 10 nolearning noudpcsum \
+ ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+ ip address add 198.51.100.1/32 dev lo
+
+ ip link set dev $swp1 master br0
+ ip link set dev vxlan0 master br0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 up
+ ip link set dev vxlan0 up
+}
+
+switch_destroy()
+{
+ ip link set dev vxlan0 down
+ ip link set dev $swp1 down
+ ip link set dev br0 down
+
+ ip link set dev vxlan0 nomaster
+ ip link set dev $swp1 nomaster
+
+ ip address del 198.51.100.1/32 dev lo
+
+ ip link del dev vxlan0
+
+ ip link del dev br0
+}
+
+router1_create()
+{
+ # This router is in the default VRF, where the VxLAN device is
+ # performing the L3 lookup
+ ip link set dev $rp1 up
+ ip address add 192.0.2.1/24 dev $rp1
+ ip route add 198.51.100.0/24 via 192.0.2.2
+}
+
+router1_destroy()
+{
+ ip route del 198.51.100.0/24 via 192.0.2.2
+ ip address del 192.0.2.1/24 dev $rp1
+ ip link set dev $rp1 down
+}
+
+router2_create()
+{
+ # This router is not in the default VRF, so use simple_if_init()
+ simple_if_init $rp2 192.0.2.2/24
+}
+
+router2_destroy()
+{
+ simple_if_fini $rp2 192.0.2.2/24
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ rp1=${NETIFS[p3]}
+ rp2=${NETIFS[p4]}
+
+ vrf_prepare
+
+ h1_create
+
+ switch_create
+
+ router1_create
+ router2_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ router2_destroy
+ router1_destroy
+
+ switch_destroy
+
+ h1_destroy
+
+ vrf_cleanup
+}
+
+flooding_remotes_add()
+{
+ local num_remotes=$1
+ local lsb
+ local i
+
+ for i in $(eval echo {1..$num_remotes}); do
+ lsb=$((i + 1))
+
+ bridge fdb append 00:00:00:00:00:00 dev vxlan0 self \
+ dst 198.51.100.$lsb
+ done
+}
+
+flooding_filters_add()
+{
+ local num_remotes=$1
+ local lsb
+ local i
+
+ tc qdisc add dev $rp2 clsact
+
+ for i in $(eval echo {1..$num_remotes}); do
+ lsb=$((i + 1))
+
+ tc filter add dev $rp2 ingress protocol ip pref $i handle $i \
+ flower ip_proto udp dst_ip 198.51.100.$lsb \
+ dst_port 4789 skip_sw action drop
+ done
+}
+
+flooding_filters_del()
+{
+ local num_remotes=$1
+ local i
+
+ for i in $(eval echo {1..$num_remotes}); do
+ tc filter del dev $rp2 ingress protocol ip pref $i \
+ handle $i flower
+ done
+
+ tc qdisc del dev $rp2 clsact
+}
+
+flooding_check_packets()
+{
+ local packets=("$@")
+ local num_remotes=${#packets[@]}
+ local i
+
+ for i in $(eval echo {1..$num_remotes}); do
+ tc_check_packets "dev $rp2 ingress" $i ${packets[i - 1]}
+ check_err $? "remote $i - did not get expected number of packets"
+ done
+}
+
+flooding_test()
+{
+ # Use 12 remote VTEPs that will be stored in 4 records. The array
+ # 'packets' will store how many packets are expected to be received
+ # by each remote VTEP at each stage of the test
+ declare -a packets=(1 1 1 1 1 1 1 1 1 1 1 1)
+ local num_remotes=12
+
+ RET=0
+
+ # Add FDB entries for remote VTEPs and corresponding tc filters on the
+ # ingress of the nexthop router. These filters will count how many
+ # packets were flooded to each remote VTEP
+ flooding_remotes_add $num_remotes
+ flooding_filters_add $num_remotes
+
+ # Send one packet and make sure it is flooded to all the remote VTEPs
+ $MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+ flooding_check_packets "${packets[@]}"
+ log_test "flood after 1 packet"
+
+ # Delete the third record which corresponds to VTEPs with LSB 8..10
+ # and check that packet is flooded correctly when we remove a record
+ # from the middle of the list
+ RET=0
+
+ packets=(2 2 2 2 2 2 1 1 1 2 2 2)
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.8
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.9
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.10
+
+ $MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+ flooding_check_packets "${packets[@]}"
+ log_test "flood after 2 packets"
+
+ # Delete the first record and make sure the packet is flooded correctly
+ RET=0
+
+ packets=(2 2 2 3 3 3 1 1 1 3 3 3)
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.3
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.4
+
+ $MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+ flooding_check_packets "${packets[@]}"
+ log_test "flood after 3 packets"
+
+ # Delete the last record and make sure the packet is flooded correctly
+ RET=0
+
+ packets=(2 2 2 4 4 4 1 1 1 3 3 3)
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.11
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.12
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.13
+
+ $MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+ flooding_check_packets "${packets[@]}"
+ log_test "flood after 4 packets"
+
+ # Delete the last record, one entry at a time and make sure single
+ # entries are correctly removed
+ RET=0
+
+ packets=(2 2 2 4 5 5 1 1 1 3 3 3)
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.5
+
+ $MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+ flooding_check_packets "${packets[@]}"
+ log_test "flood after 5 packets"
+
+ RET=0
+
+ packets=(2 2 2 4 5 6 1 1 1 3 3 3)
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.6
+
+ $MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+ flooding_check_packets "${packets[@]}"
+ log_test "flood after 6 packets"
+
+ RET=0
+
+ packets=(2 2 2 4 5 6 1 1 1 3 3 3)
+ bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.7
+
+ $MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+ flooding_check_packets "${packets[@]}"
+ log_test "flood after 7 packets"
+
+ flooding_filters_del $num_remotes
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 8cf22b3c2563..6f81130605d7 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -3,6 +3,7 @@ socket
psock_fanout
psock_snd
psock_tpacket
+reuseport_addr_any
reuseport_bpf
reuseport_bpf_cpu
reuseport_bpf_numa
@@ -14,4 +15,5 @@ udpgso_bench_rx
udpgso_bench_tx
tcp_inq
tls
+txring_overwrite
ip_defrag
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 923570a9708a..f8f3e90700c0 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -4,14 +4,16 @@
CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
CFLAGS += -I../../../../usr/include/
-TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
+TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \
+ rtnetlink.sh xfrm_policy.sh
TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
+TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
TEST_PROGS += test_vxlan_fdb_changelink.sh
TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket
-TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
-TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
+TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
+TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index cd3a2f1545b5..5821bdd98d20 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -14,3 +14,17 @@ CONFIG_IPV6_VTI=y
CONFIG_DUMMY=y
CONFIG_BRIDGE=y
CONFIG_VLAN_8021Q=y
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_ADVANCED=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_NAT_IPV6=m
+CONFIG_NF_NAT_IPV4=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP6_NF_NAT=m
+CONFIG_IP_NF_NAT=m
+CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_IPV6=y
+CONFIG_NF_TABLES_IPV4=y
+CONFIG_NFT_CHAIN_NAT_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 85d253546684..3f248d1f5b91 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -15,6 +15,8 @@ PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no}
NETIF_TYPE=${NETIF_TYPE:=veth}
NETIF_CREATE=${NETIF_CREATE:=yes}
+MCD=${MCD:=smcrouted}
+MC_CLI=${MC_CLI:=smcroutectl}
relative_path="${BASH_SOURCE%/*}"
if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
@@ -104,7 +106,7 @@ create_netif_veth()
{
local i
- for i in $(eval echo {1..$NUM_NETIFS}); do
+ for ((i = 1; i <= NUM_NETIFS; ++i)); do
local j=$((i+1))
ip link show dev ${NETIFS[p$i]} &> /dev/null
@@ -135,7 +137,7 @@ if [[ "$NETIF_CREATE" = "yes" ]]; then
create_netif
fi
-for i in $(eval echo {1..$NUM_NETIFS}); do
+for ((i = 1; i <= NUM_NETIFS; ++i)); do
ip link show dev ${NETIFS[p$i]} &> /dev/null
if [[ $? -ne 0 ]]; then
echo "SKIP: could not find all required interfaces"
@@ -477,11 +479,24 @@ master_name_get()
ip -j link show dev $if_name | jq -r '.[]["master"]'
}
+link_stats_get()
+{
+ local if_name=$1; shift
+ local dir=$1; shift
+ local stat=$1; shift
+
+ ip -j -s link show dev $if_name \
+ | jq '.[]["stats64"]["'$dir'"]["'$stat'"]'
+}
+
link_stats_tx_packets_get()
{
- local if_name=$1
+ link_stats_get $1 tx packets
+}
- ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]'
+link_stats_rx_errors_get()
+{
+ link_stats_get $1 rx errors
}
tc_rule_stats_get()
@@ -783,6 +798,17 @@ multipath_eval()
log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
}
+in_ns()
+{
+ local name=$1; shift
+
+ ip netns exec $name bash <<-EOF
+ NUM_NETIFS=0
+ source lib.sh
+ $(for a in "$@"; do printf "%q${IFS:0:1}" "$a"; done)
+ EOF
+}
+
##############################################################################
# Tests
@@ -790,10 +816,11 @@ ping_do()
{
local if_name=$1
local dip=$2
+ local args=$3
local vrf_name
vrf_name=$(master_name_get $if_name)
- ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null
+ ip vrf exec $vrf_name $PING $args $dip -c 10 -i 0.1 -w 2 &> /dev/null
}
ping_test()
@@ -802,17 +829,18 @@ ping_test()
ping_do $1 $2
check_err $?
- log_test "ping"
+ log_test "ping$3"
}
ping6_do()
{
local if_name=$1
local dip=$2
+ local args=$3
local vrf_name
vrf_name=$(master_name_get $if_name)
- ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null
+ ip vrf exec $vrf_name $PING6 $args $dip -c 10 -i 0.1 -w 2 &> /dev/null
}
ping6_test()
@@ -821,7 +849,7 @@ ping6_test()
ping6_do $1 $2
check_err $?
- log_test "ping6"
+ log_test "ping6$3"
}
learning_test()
diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh
new file mode 100755
index 000000000000..109e6d785169
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_multicast.sh
@@ -0,0 +1,311 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +------------------+
+# | H1 (v$h1) |
+# | 2001:db8:1::2/64 |
+# | 198.51.100.2/28 |
+# | $h1 + |
+# +-------------|----+
+# |
+# +-------------|-------------------------------+
+# | SW1 | |
+# | $rp1 + |
+# | 198.51.100.1/28 |
+# | 2001:db8:1::1/64 |
+# | |
+# | 2001:db8:2::1/64 2001:db8:3::1/64 |
+# | 198.51.100.17/28 198.51.100.33/28 |
+# | $rp2 + $rp3 + |
+# +--------------|--------------------------|---+
+# | |
+# | |
+# +--------------|---+ +--------------|---+
+# | H2 (v$h2) | | | H3 (v$h3) | |
+# | $h2 + | | $h3 + |
+# | 198.51.100.18/28 | | 198.51.100.34/28 |
+# | 2001:db8:2::2/64 | | 2001:db8:3::2/64 |
+# +------------------+ +------------------+
+#
+
+ALL_TESTS="mcast_v4 mcast_v6"
+NUM_NETIFS=6
+source lib.sh
+source tc_common.sh
+
+require_command $MCD
+require_command $MC_CLI
+table_name=selftests
+
+h1_create()
+{
+ simple_if_init $h1 198.51.100.2/28 2001:db8:1::2/64
+
+ ip route add 198.51.100.16/28 vrf v$h1 nexthop via 198.51.100.1
+ ip route add 198.51.100.32/28 vrf v$h1 nexthop via 198.51.100.1
+
+ ip route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::1
+ ip route add 2001:db8:3::/64 vrf v$h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+ ip route del 2001:db8:3::/64 vrf v$h1
+ ip route del 2001:db8:2::/64 vrf v$h1
+
+ ip route del 198.51.100.32/28 vrf v$h1
+ ip route del 198.51.100.16/28 vrf v$h1
+
+ simple_if_fini $h1 198.51.100.2/28 2001:db8:1::2/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 198.51.100.18/28 2001:db8:2::2/64
+
+ ip route add 198.51.100.0/28 vrf v$h2 nexthop via 198.51.100.17
+ ip route add 198.51.100.32/28 vrf v$h2 nexthop via 198.51.100.17
+
+ ip route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+ ip route add 2001:db8:3::/64 vrf v$h2 nexthop via 2001:db8:2::1
+
+ tc qdisc add dev $h2 ingress
+}
+
+h2_destroy()
+{
+ tc qdisc del dev $h2 ingress
+
+ ip route del 2001:db8:3::/64 vrf v$h2
+ ip route del 2001:db8:1::/64 vrf v$h2
+
+ ip route del 198.51.100.32/28 vrf v$h2
+ ip route del 198.51.100.0/28 vrf v$h2
+
+ simple_if_fini $h2 198.51.100.18/28 2001:db8:2::2/64
+}
+
+h3_create()
+{
+ simple_if_init $h3 198.51.100.34/28 2001:db8:3::2/64
+
+ ip route add 198.51.100.0/28 vrf v$h3 nexthop via 198.51.100.33
+ ip route add 198.51.100.16/28 vrf v$h3 nexthop via 198.51.100.33
+
+ ip route add 2001:db8:1::/64 vrf v$h3 nexthop via 2001:db8:3::1
+ ip route add 2001:db8:2::/64 vrf v$h3 nexthop via 2001:db8:3::1
+
+ tc qdisc add dev $h3 ingress
+}
+
+h3_destroy()
+{
+ tc qdisc del dev $h3 ingress
+
+ ip route del 2001:db8:2::/64 vrf v$h3
+ ip route del 2001:db8:1::/64 vrf v$h3
+
+ ip route del 198.51.100.16/28 vrf v$h3
+ ip route del 198.51.100.0/28 vrf v$h3
+
+ simple_if_fini $h3 198.51.100.34/28 2001:db8:3::2/64
+}
+
+router_create()
+{
+ ip link set dev $rp1 up
+ ip link set dev $rp2 up
+ ip link set dev $rp3 up
+
+ ip address add 198.51.100.1/28 dev $rp1
+ ip address add 198.51.100.17/28 dev $rp2
+ ip address add 198.51.100.33/28 dev $rp3
+
+ ip address add 2001:db8:1::1/64 dev $rp1
+ ip address add 2001:db8:2::1/64 dev $rp2
+ ip address add 2001:db8:3::1/64 dev $rp3
+}
+
+router_destroy()
+{
+ ip address del 2001:db8:3::1/64 dev $rp3
+ ip address del 2001:db8:2::1/64 dev $rp2
+ ip address del 2001:db8:1::1/64 dev $rp1
+
+ ip address del 198.51.100.33/28 dev $rp3
+ ip address del 198.51.100.17/28 dev $rp2
+ ip address del 198.51.100.1/28 dev $rp1
+
+ ip link set dev $rp3 down
+ ip link set dev $rp2 down
+ ip link set dev $rp1 down
+}
+
+start_mcd()
+{
+ SMCROUTEDIR="$(mktemp -d)"
+
+ for ((i = 1; i <= $NUM_NETIFS; ++i)); do
+ echo "phyint ${NETIFS[p$i]} enable" >> \
+ $SMCROUTEDIR/$table_name.conf
+ done
+
+ $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \
+ -P $SMCROUTEDIR/$table_name.pid
+}
+
+kill_mcd()
+{
+ pkill $MCD
+ rm -rf $SMCROUTEDIR
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ rp1=${NETIFS[p2]}
+
+ rp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ rp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ start_mcd
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+ h3_create
+
+ router_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ router_destroy
+
+ h3_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+
+ kill_mcd
+}
+
+create_mcast_sg()
+{
+ local if_name=$1; shift
+ local s_addr=$1; shift
+ local mcast=$1; shift
+ local dest_ifs=${@}
+
+ $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs
+}
+
+delete_mcast_sg()
+{
+ local if_name=$1; shift
+ local s_addr=$1; shift
+ local mcast=$1; shift
+ local dest_ifs=${@}
+
+ $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs
+}
+
+mcast_v4()
+{
+ # Add two interfaces to an MC group, send a packet to the MC group and
+ # verify packets are received on both. Then delete the route and verify
+ # packets are no longer received.
+
+ RET=0
+
+ tc filter add dev $h2 ingress protocol ip pref 1 handle 122 flower \
+ dst_ip 225.1.2.3 action drop
+ tc filter add dev $h3 ingress protocol ip pref 1 handle 133 flower \
+ dst_ip 225.1.2.3 action drop
+
+ create_mcast_sg $rp1 198.51.100.2 225.1.2.3 $rp2 $rp3
+
+ # Send frames with the corresponding L2 destination address.
+ $MZ $h1 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \
+ -A 198.51.100.2 -B 225.1.2.3 -q
+
+ tc_check_packets "dev $h2 ingress" 122 5
+ check_err $? "Multicast not received on first host"
+ tc_check_packets "dev $h3 ingress" 133 5
+ check_err $? "Multicast not received on second host"
+
+ delete_mcast_sg $rp1 198.51.100.2 225.1.2.3 $rp2 $rp3
+
+ $MZ $h1 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \
+ -A 198.51.100.2 -B 225.1.2.3 -q
+
+ tc_check_packets "dev $h2 ingress" 122 5
+ check_err $? "Multicast received on host although deleted"
+ tc_check_packets "dev $h3 ingress" 133 5
+ check_err $? "Multicast received on second host although deleted"
+
+ tc filter del dev $h3 ingress protocol ip pref 1 handle 133 flower
+ tc filter del dev $h2 ingress protocol ip pref 1 handle 122 flower
+
+ log_test "mcast IPv4"
+}
+
+mcast_v6()
+{
+ # Add two interfaces to an MC group, send a packet to the MC group and
+ # verify packets are received on both. Then delete the route and verify
+ # packets are no longer received.
+
+ RET=0
+
+ tc filter add dev $h2 ingress protocol ipv6 pref 1 handle 122 flower \
+ dst_ip ff0e::3 action drop
+ tc filter add dev $h3 ingress protocol ipv6 pref 1 handle 133 flower \
+ dst_ip ff0e::3 action drop
+
+ create_mcast_sg $rp1 2001:db8:1::2 ff0e::3 $rp2 $rp3
+
+ # Send frames with the corresponding L2 destination address.
+ $MZ $h1 -6 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 \
+ -b 33:33:00:00:00:03 -A 2001:db8:1::2 -B ff0e::3 -q
+
+ tc_check_packets "dev $h2 ingress" 122 5
+ check_err $? "Multicast not received on first host"
+ tc_check_packets "dev $h3 ingress" 133 5
+ check_err $? "Multicast not received on second host"
+
+ delete_mcast_sg $rp1 2001:db8:1::2 ff0e::3 $rp2 $rp3
+
+ $MZ $h1 -6 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 \
+ -b 33:33:00:00:00:03 -A 2001:db8:1::2 -B ff0e::3 -q
+
+ tc_check_packets "dev $h2 ingress" 122 5
+ check_err $? "Multicast received on first host although deleted"
+ tc_check_packets "dev $h3 ingress" 133 5
+ check_err $? "Multicast received on second host although deleted"
+
+ tc filter del dev $h3 ingress protocol ipv6 pref 1 handle 133 flower
+ tc filter del dev $h2 ingress protocol ipv6 pref 1 handle 122 flower
+
+ log_test "mcast IPv6"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_vid_1.sh b/tools/testing/selftests/net/forwarding/router_vid_1.sh
new file mode 100755
index 000000000000..a7306c7ac06d
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_vid_1.sh
@@ -0,0 +1,135 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4 ping_ipv6"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+ vrf_create "vrf-h1"
+ ip link set dev vrf-h1 up
+
+ ip link set dev $h1 up
+ vlan_create $h1 1 vrf-h1 192.0.2.2/24 2001:db8:1::2/64
+
+ ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+ ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+ ip route del 2001:db8:2::/64 vrf vrf-h1
+ ip route del 198.51.100.0/24 vrf vrf-h1
+
+ vlan_destroy $h1 1
+ ip link set dev $h1 down
+
+ ip link set dev vrf-h1 down
+ vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+ vrf_create "vrf-h2"
+ ip link set dev vrf-h2 up
+
+ ip link set dev $h2 up
+ vlan_create $h2 1 vrf-h2 198.51.100.2/24 2001:db8:2::2/64
+
+ ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+ ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+ ip route del 2001:db8:1::/64 vrf vrf-h2
+ ip route del 192.0.2.0/24 vrf vrf-h2
+
+ vlan_destroy $h2 1
+ ip link set dev $h2 down
+
+ ip link set dev vrf-h2 down
+ vrf_destroy "vrf-h2"
+}
+
+router_create()
+{
+ ip link set dev $rp1 up
+ ip link add link $rp1 name $rp1.1 up type vlan id 1
+
+ ip address add 192.0.2.1/24 dev $rp1.1
+ ip address add 2001:db8:1::1/64 dev $rp1.1
+
+ ip link set dev $rp2 up
+ ip link add link $rp2 name $rp2.1 up type vlan id 1
+
+ ip address add 198.51.100.1/24 dev $rp2.1
+ ip address add 2001:db8:2::1/64 dev $rp2.1
+}
+
+router_destroy()
+{
+ ip address del 2001:db8:2::1/64 dev $rp2.1
+ ip address del 198.51.100.1/24 dev $rp2.1
+
+ ip link del dev $rp2.1
+ ip link set dev $rp2 down
+
+ ip address del 2001:db8:1::1/64 dev $rp1.1
+ ip address del 192.0.2.1/24 dev $rp1.1
+
+ ip link del dev $rp1.1
+ ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ rp1=${NETIFS[p2]}
+
+ rp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ router_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ router_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1.1 198.51.100.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1.1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
new file mode 100755
index 000000000000..56cef3b1c194
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -0,0 +1,786 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +--------------------+ +----------------------+
+# | H1 (vrf) | | H2 (vrf) |
+# | + $h1 | | + $h2 |
+# | | 192.0.2.1/28 | | | 192.0.2.2/28 |
+# +----|---------------+ +--|-------------------+
+# | |
+# +----|--------------------------------------------------|-------------------+
+# | SW | | |
+# | +--|--------------------------------------------------|-----------------+ |
+# | | + $swp1 BR1 (802.1d) + $swp2 | |
+# | | | |
+# | | + vx1 (vxlan) | |
+# | | local 192.0.2.17 | |
+# | | remote 192.0.2.34 192.0.2.50 | |
+# | | id 1000 dstport $VXPORT | |
+# | +-----------------------------------------------------------------------+ |
+# | |
+# | 192.0.2.32/28 via 192.0.2.18 |
+# | 192.0.2.48/28 via 192.0.2.18 |
+# | |
+# | + $rp1 |
+# | | 192.0.2.17/28 |
+# +----|----------------------------------------------------------------------+
+# |
+# +----|--------------------------------------------------------+
+# | | VRP2 (vrf) |
+# | + $rp2 |
+# | 192.0.2.18/28 |
+# | | (maybe) HW
+# =============================================================================
+# | | (likely) SW
+# | + v1 (veth) + v3 (veth) |
+# | | 192.0.2.33/28 | 192.0.2.49/28 |
+# +----|---------------------------------------|----------------+
+# | |
+# +----|------------------------------+ +----|------------------------------+
+# | + v2 (veth) NS1 (netns) | | + v4 (veth) NS2 (netns) |
+# | 192.0.2.34/28 | | 192.0.2.50/28 |
+# | | | |
+# | 192.0.2.16/28 via 192.0.2.33 | | 192.0.2.16/28 via 192.0.2.49 |
+# | 192.0.2.50/32 via 192.0.2.33 | | 192.0.2.34/32 via 192.0.2.49 |
+# | | | |
+# | +-------------------------------+ | | +-------------------------------+ |
+# | | BR2 (802.1d) | | | | BR2 (802.1d) | |
+# | | + vx2 (vxlan) | | | | + vx2 (vxlan) | |
+# | | local 192.0.2.34 | | | | local 192.0.2.50 | |
+# | | remote 192.0.2.17 | | | | remote 192.0.2.17 | |
+# | | remote 192.0.2.50 | | | | remote 192.0.2.34 | |
+# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | |
+# | | | | | | | |
+# | | + w1 (veth) | | | | + w1 (veth) | |
+# | +--|----------------------------+ | | +--|----------------------------+ |
+# | | | | | |
+# | +--|----------------------------+ | | +--|----------------------------+ |
+# | | | VW2 (vrf) | | | | | VW2 (vrf) | |
+# | | + w2 (veth) | | | | + w2 (veth) | |
+# | | 192.0.2.3/28 | | | | 192.0.2.4/28 | |
+# | +-------------------------------+ | | +-------------------------------+ |
+# +-----------------------------------+ +-----------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+ ping_ipv4
+ test_flood
+ test_unicast
+ test_ttl
+ test_tos
+ test_ecn_encap
+ test_ecn_decap
+ reapply_config
+ ping_ipv4
+ test_flood
+ test_unicast
+ test_learning
+ "}
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+ tc qdisc add dev $h1 clsact
+}
+
+h1_destroy()
+{
+ tc qdisc del dev $h1 clsact
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/28
+ tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+ tc qdisc del dev $h2 clsact
+ simple_if_fini $h2 192.0.2.2/28
+}
+
+rp1_set_addr()
+{
+ ip address add dev $rp1 192.0.2.17/28
+
+ ip route add 192.0.2.32/28 nexthop via 192.0.2.18
+ ip route add 192.0.2.48/28 nexthop via 192.0.2.18
+}
+
+rp1_unset_addr()
+{
+ ip route del 192.0.2.48/28 nexthop via 192.0.2.18
+ ip route del 192.0.2.32/28 nexthop via 192.0.2.18
+
+ ip address del dev $rp1 192.0.2.17/28
+}
+
+switch_create()
+{
+ ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0
+ # Make sure the bridge uses the MAC address of the local port and not
+ # that of the VxLAN's device.
+ ip link set dev br1 address $(mac_get $swp1)
+ ip link set dev br1 up
+
+ ip link set dev $rp1 up
+ rp1_set_addr
+
+ ip link add name vx1 type vxlan id 1000 \
+ local 192.0.2.17 dstport "$VXPORT" \
+ nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx1 up
+
+ ip link set dev vx1 master br1
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+
+ bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+ bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+}
+
+switch_destroy()
+{
+ rp1_unset_addr
+ ip link set dev $rp1 down
+
+ bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+ bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+
+ ip link set dev vx1 nomaster
+ ip link set dev vx1 down
+ ip link del dev vx1
+
+ ip link set dev $swp2 down
+ ip link set dev $swp2 nomaster
+
+ ip link set dev $swp1 down
+ ip link set dev $swp1 nomaster
+
+ ip link set dev br1 down
+ ip link del dev br1
+}
+
+vrp2_create()
+{
+ simple_if_init $rp2 192.0.2.18/28
+ __simple_if_init v1 v$rp2 192.0.2.33/28
+ __simple_if_init v3 v$rp2 192.0.2.49/28
+ tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+ tc qdisc del dev v1 clsact
+ __simple_if_fini v3 192.0.2.49/28
+ __simple_if_fini v1 192.0.2.33/28
+ simple_if_fini $rp2 192.0.2.18/28
+}
+
+ns_init_common()
+{
+ local in_if=$1; shift
+ local in_addr=$1; shift
+ local other_in_addr=$1; shift
+ local nh_addr=$1; shift
+ local host_addr=$1; shift
+
+ ip link set dev $in_if up
+ ip address add dev $in_if $in_addr/28
+ tc qdisc add dev $in_if clsact
+
+ ip link add name br2 type bridge vlan_filtering 0
+ ip link set dev br2 up
+
+ ip link add name w1 type veth peer name w2
+
+ ip link set dev w1 master br2
+ ip link set dev w1 up
+
+ ip link add name vx2 type vxlan id 1000 local $in_addr dstport "$VXPORT"
+ ip link set dev vx2 up
+ bridge fdb append dev vx2 00:00:00:00:00:00 dst 192.0.2.17 self
+ bridge fdb append dev vx2 00:00:00:00:00:00 dst $other_in_addr self
+
+ ip link set dev vx2 master br2
+ tc qdisc add dev vx2 clsact
+
+ simple_if_init w2 $host_addr/28
+
+ ip route add 192.0.2.16/28 nexthop via $nh_addr
+ ip route add $other_in_addr/32 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+ ip netns add ns1
+ ip link set dev v2 netns ns1
+ in_ns ns1 \
+ ns_init_common v2 192.0.2.34 192.0.2.50 192.0.2.33 192.0.2.3
+}
+
+ns1_destroy()
+{
+ ip netns exec ns1 ip link set dev v2 netns 1
+ ip netns del ns1
+}
+
+ns2_create()
+{
+ ip netns add ns2
+ ip link set dev v4 netns ns2
+ in_ns ns2 \
+ ns_init_common v4 192.0.2.50 192.0.2.34 192.0.2.49 192.0.2.4
+}
+
+ns2_destroy()
+{
+ ip netns exec ns2 ip link set dev v4 netns 1
+ ip netns del ns2
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ rp1=${NETIFS[p5]}
+ rp2=${NETIFS[p6]}
+
+ vrf_prepare
+ forwarding_enable
+
+ h1_create
+ h2_create
+ switch_create
+
+ ip link add name v1 type veth peer name v2
+ ip link add name v3 type veth peer name v4
+ vrp2_create
+ ns1_create
+ ns2_create
+
+ r1_mac=$(in_ns ns1 mac_get w2)
+ r2_mac=$(in_ns ns2 mac_get w2)
+ h2_mac=$(mac_get $h2)
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ns2_destroy
+ ns1_destroy
+ vrp2_destroy
+ ip link del dev v3
+ ip link del dev v1
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ forwarding_restore
+ vrf_cleanup
+}
+
+# For the first round of tests, vx1 is the first device to get attached to the
+# bridge, and that at the point that the local IP is already configured. Try the
+# other scenario of attaching the device to an already-offloaded bridge, and
+# only then attach the local IP.
+reapply_config()
+{
+ echo "Reapplying configuration"
+
+ bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+ bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+ rp1_unset_addr
+ ip link set dev vx1 nomaster
+ sleep 5
+
+ ip link set dev vx1 master br1
+ bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+ bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+ sleep 1
+ rp1_set_addr
+ sleep 5
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.2 ": local->local"
+ ping_test $h1 192.0.2.3 ": local->remote 1"
+ ping_test $h1 192.0.2.4 ": local->remote 2"
+}
+
+maybe_in_ns()
+{
+ echo ${1:+in_ns} $1
+}
+
+__flood_counter_add_del()
+{
+ local add_del=$1; shift
+ local dev=$1; shift
+ local ns=$1; shift
+
+ # Putting the ICMP capture both to HW and to SW will end up
+ # double-counting the packets that are trapped to slow path, such as for
+ # the unicast test. Adding either skip_hw or skip_sw fixes this problem,
+ # but with skip_hw, the flooded packets are not counted at all, because
+ # those are dropped due to MAC address mismatch; and skip_sw is a no-go
+ # for veth-based topologies.
+ #
+ # So try to install with skip_sw and fall back to skip_sw if that fails.
+
+ $(maybe_in_ns $ns) __icmp_capture_add_del \
+ $add_del 100 "" $dev skip_sw 2>/dev/null || \
+ $(maybe_in_ns $ns) __icmp_capture_add_del \
+ $add_del 100 "" $dev skip_hw
+}
+
+flood_counter_install()
+{
+ __flood_counter_add_del add "$@"
+}
+
+flood_counter_uninstall()
+{
+ __flood_counter_add_del del "$@"
+}
+
+flood_fetch_stat()
+{
+ local dev=$1; shift
+ local ns=$1; shift
+
+ $(maybe_in_ns $ns) tc_rule_stats_get $dev 100 ingress
+}
+
+flood_fetch_stats()
+{
+ local counters=("${@}")
+ local counter
+
+ for counter in "${counters[@]}"; do
+ flood_fetch_stat $counter
+ done
+}
+
+vxlan_flood_test()
+{
+ local mac=$1; shift
+ local dst=$1; shift
+ local -a expects=("${@}")
+
+ local -a counters=($h2 "vx2 ns1" "vx2 ns2")
+ local counter
+ local key
+
+ for counter in "${counters[@]}"; do
+ flood_counter_install $counter
+ done
+
+ local -a t0s=($(flood_fetch_stats "${counters[@]}"))
+ $MZ $h1 -c 10 -d 100msec -p 64 -b $mac -B $dst -t icmp -q
+ sleep 1
+ local -a t1s=($(flood_fetch_stats "${counters[@]}"))
+
+ for key in ${!t0s[@]}; do
+ local delta=$((t1s[$key] - t0s[$key]))
+ local expect=${expects[$key]}
+
+ ((expect == delta))
+ check_err $? "${counters[$key]}: Expected to capture $expect packets, got $delta."
+ done
+
+ for counter in "${counters[@]}"; do
+ flood_counter_uninstall $counter
+ done
+}
+
+__test_flood()
+{
+ local mac=$1; shift
+ local dst=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ vxlan_flood_test $mac $dst 10 10 10
+
+ log_test "VXLAN: $what"
+}
+
+test_flood()
+{
+ __test_flood de:ad:be:ef:13:37 192.0.2.100 "flood"
+}
+
+vxlan_fdb_add_del()
+{
+ local add_del=$1; shift
+ local mac=$1; shift
+ local dev=$1; shift
+ local dst=$1; shift
+
+ bridge fdb $add_del dev $dev $mac self static permanent \
+ ${dst:+dst} $dst 2>/dev/null
+ bridge fdb $add_del dev $dev $mac master static 2>/dev/null
+}
+
+__test_unicast()
+{
+ local mac=$1; shift
+ local dst=$1; shift
+ local hit_idx=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ local -a expects=(0 0 0)
+ expects[$hit_idx]=10
+
+ vxlan_flood_test $mac $dst "${expects[@]}"
+
+ log_test "VXLAN: $what"
+}
+
+test_unicast()
+{
+ local -a targets=("$h2_mac $h2"
+ "$r1_mac vx1 192.0.2.34"
+ "$r2_mac vx1 192.0.2.50")
+ local target
+
+ for target in "${targets[@]}"; do
+ vxlan_fdb_add_del add $target
+ done
+
+ __test_unicast $h2_mac 192.0.2.2 0 "local MAC unicast"
+ __test_unicast $r1_mac 192.0.2.3 1 "remote MAC 1 unicast"
+ __test_unicast $r2_mac 192.0.2.4 2 "remote MAC 2 unicast"
+
+ for target in "${targets[@]}"; do
+ vxlan_fdb_add_del del $target
+ done
+}
+
+vxlan_ping_test()
+{
+ local ping_dev=$1; shift
+ local ping_dip=$1; shift
+ local ping_args=$1; shift
+ local capture_dev=$1; shift
+ local capture_dir=$1; shift
+ local capture_pref=$1; shift
+ local expect=$1; shift
+
+ local t0=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+ ping_do $ping_dev $ping_dip "$ping_args"
+ local t1=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+ local delta=$((t1 - t0))
+
+ # Tolerate a couple stray extra packets.
+ ((expect <= delta && delta <= expect + 2))
+ check_err $? "$capture_dev: Expected to capture $expect packets, got $delta."
+}
+
+test_ttl()
+{
+ RET=0
+
+ tc filter add dev v1 egress pref 77 prot ip \
+ flower ip_ttl 99 action pass
+ vxlan_ping_test $h1 192.0.2.3 "" v1 egress 77 10
+ tc filter del dev v1 egress pref 77 prot ip
+
+ log_test "VXLAN: envelope TTL"
+}
+
+test_tos()
+{
+ RET=0
+
+ tc filter add dev v1 egress pref 77 prot ip \
+ flower ip_tos 0x40 action pass
+ vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10
+ vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0
+ tc filter del dev v1 egress pref 77 prot ip
+
+ log_test "VXLAN: envelope TOS inheritance"
+}
+
+__test_ecn_encap()
+{
+ local q=$1; shift
+ local tos=$1; shift
+
+ RET=0
+
+ tc filter add dev v1 egress pref 77 prot ip \
+ flower ip_tos $tos action pass
+ sleep 1
+ vxlan_ping_test $h1 192.0.2.3 "-Q $q" v1 egress 77 10
+ tc filter del dev v1 egress pref 77 prot ip
+
+ log_test "VXLAN: ECN encap: $q->$tos"
+}
+
+test_ecn_encap()
+{
+ # In accordance with INET_ECN_encapsulate()
+ __test_ecn_encap 0x00 0x00
+ __test_ecn_encap 0x01 0x01
+ __test_ecn_encap 0x02 0x02
+ __test_ecn_encap 0x03 0x02
+}
+
+vxlan_encapped_ping_do()
+{
+ local count=$1; shift
+ local dev=$1; shift
+ local next_hop_mac=$1; shift
+ local dest_ip=$1; shift
+ local dest_mac=$1; shift
+ local inner_tos=$1; shift
+ local outer_tos=$1; shift
+
+ $MZ $dev -c $count -d 100msec -q \
+ -b $next_hop_mac -B $dest_ip \
+ -t udp tos=$outer_tos,sp=23456,dp=$VXPORT,p=$(:
+ )"08:"$( : VXLAN flags
+ )"00:00:00:"$( : VXLAN reserved
+ )"00:03:e8:"$( : VXLAN VNI
+ )"00:"$( : VXLAN reserved
+ )"$dest_mac:"$( : ETH daddr
+ )"$(mac_get w2):"$( : ETH saddr
+ )"08:00:"$( : ETH type
+ )"45:"$( : IP version + IHL
+ )"$inner_tos:"$( : IP TOS
+ )"00:54:"$( : IP total length
+ )"99:83:"$( : IP identification
+ )"40:00:"$( : IP flags + frag off
+ )"40:"$( : IP TTL
+ )"01:"$( : IP proto
+ )"00:00:"$( : IP header csum
+ )"c0:00:02:03:"$( : IP saddr: 192.0.2.3
+ )"c0:00:02:01:"$( : IP daddr: 192.0.2.1
+ )"08:"$( : ICMP type
+ )"00:"$( : ICMP code
+ )"8b:f2:"$( : ICMP csum
+ )"1f:6a:"$( : ICMP request identifier
+ )"00:01:"$( : ICMP request sequence number
+ )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload
+ )"6d:74:0b:00:00:00:00:00:"$( :
+ )"10:11:12:13:14:15:16:17:"$( :
+ )"18:19:1a:1b:1c:1d:1e:1f:"$( :
+ )"20:21:22:23:24:25:26:27:"$( :
+ )"28:29:2a:2b:2c:2d:2e:2f:"$( :
+ )"30:31:32:33:34:35:36:37"
+}
+export -f vxlan_encapped_ping_do
+
+vxlan_encapped_ping_test()
+{
+ local ping_dev=$1; shift
+ local nh_dev=$1; shift
+ local ping_dip=$1; shift
+ local inner_tos=$1; shift
+ local outer_tos=$1; shift
+ local stat_get=$1; shift
+ local expect=$1; shift
+
+ local t0=$($stat_get)
+
+ in_ns ns1 \
+ vxlan_encapped_ping_do 10 $ping_dev $(mac_get $nh_dev) \
+ $ping_dip $(mac_get $h1) \
+ $inner_tos $outer_tos
+
+ local t1=$($stat_get)
+ local delta=$((t1 - t0))
+
+ # Tolerate a couple stray extra packets.
+ ((expect <= delta && delta <= expect + 2))
+ check_err $? "Expected to capture $expect packets, got $delta."
+}
+export -f vxlan_encapped_ping_test
+
+__test_ecn_decap()
+{
+ local orig_inner_tos=$1; shift
+ local orig_outer_tos=$1; shift
+ local decapped_tos=$1; shift
+
+ RET=0
+
+ tc filter add dev $h1 ingress pref 77 prot ip \
+ flower ip_tos $decapped_tos action pass
+ sleep 1
+ vxlan_encapped_ping_test v2 v1 192.0.2.17 \
+ $orig_inner_tos $orig_outer_tos \
+ "tc_rule_stats_get $h1 77 ingress" 10
+ tc filter del dev $h1 ingress pref 77
+
+ log_test "VXLAN: ECN decap: $orig_outer_tos/$orig_inner_tos->$decapped_tos"
+}
+
+test_ecn_decap_error()
+{
+ local orig_inner_tos=00
+ local orig_outer_tos=03
+
+ RET=0
+
+ vxlan_encapped_ping_test v2 v1 192.0.2.17 \
+ $orig_inner_tos $orig_outer_tos \
+ "link_stats_rx_errors_get vx1" 10
+
+ log_test "VXLAN: ECN decap: $orig_outer_tos/$orig_inner_tos->error"
+}
+
+test_ecn_decap()
+{
+ # In accordance with INET_ECN_decapsulate()
+ __test_ecn_decap 00 00 0x00
+ __test_ecn_decap 01 01 0x01
+ __test_ecn_decap 02 01 0x02
+ __test_ecn_decap 01 03 0x03
+ __test_ecn_decap 02 03 0x03
+ test_ecn_decap_error
+}
+
+test_learning()
+{
+ local mac=de:ad:be:ef:13:37
+ local dst=192.0.2.100
+
+ # Enable learning on the VxLAN device and set ageing time to 10 seconds
+ ip link set dev br1 type bridge ageing_time 1000
+ ip link set dev vx1 type vxlan ageing 10
+ ip link set dev vx1 type vxlan learning
+ reapply_config
+
+ # Check that flooding works
+ RET=0
+
+ vxlan_flood_test $mac $dst 10 10 10
+
+ log_test "VXLAN: flood before learning"
+
+ # Send a packet with source mac set to $mac from host w2 and check that
+ # a corresponding entry is created in VxLAN device vx1
+ RET=0
+
+ in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \
+ -t icmp -q
+ sleep 1
+
+ bridge fdb show brport vx1 | grep $mac | grep -q self
+ check_err $?
+ bridge fdb show brport vx1 | grep $mac | grep -q -v self
+ check_err $?
+
+ log_test "VXLAN: show learned FDB entry"
+
+ # Repeat first test and check that packets only reach host w2 in ns1
+ RET=0
+
+ vxlan_flood_test $mac $dst 0 10 0
+
+ log_test "VXLAN: learned FDB entry"
+
+ # Delete the learned FDB entry from the VxLAN and bridge devices and
+ # check that packets are flooded
+ RET=0
+
+ bridge fdb del dev vx1 $mac master self
+ sleep 1
+
+ vxlan_flood_test $mac $dst 10 10 10
+
+ log_test "VXLAN: deletion of learned FDB entry"
+
+ # Re-learn the first FDB entry and check that it is correctly aged-out
+ RET=0
+
+ in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \
+ -t icmp -q
+ sleep 1
+
+ bridge fdb show brport vx1 | grep $mac | grep -q self
+ check_err $?
+ bridge fdb show brport vx1 | grep $mac | grep -q -v self
+ check_err $?
+
+ vxlan_flood_test $mac $dst 0 10 0
+
+ sleep 20
+
+ bridge fdb show brport vx1 | grep $mac | grep -q self
+ check_fail $?
+ bridge fdb show brport vx1 | grep $mac | grep -q -v self
+ check_fail $?
+
+ vxlan_flood_test $mac $dst 10 10 10
+
+ log_test "VXLAN: Ageing of learned FDB entry"
+
+ # Toggle learning on the bridge port and check that the bridge's FDB
+ # is populated only when it should
+ RET=0
+
+ ip link set dev vx1 type bridge_slave learning off
+
+ in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \
+ -t icmp -q
+ sleep 1
+
+ bridge fdb show brport vx1 | grep $mac | grep -q -v self
+ check_fail $?
+
+ ip link set dev vx1 type bridge_slave learning on
+
+ in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \
+ -t icmp -q
+ sleep 1
+
+ bridge fdb show brport vx1 | grep $mac | grep -q -v self
+ check_err $?
+
+ log_test "VXLAN: learning toggling on bridge port"
+
+ # Restore previous settings
+ ip link set dev vx1 type vxlan nolearning
+ ip link set dev vx1 type vxlan ageing 300
+ ip link set dev br1 type bridge ageing_time 30000
+ reapply_config
+}
+
+test_all()
+{
+ echo "Running tests with UDP port $VXPORT"
+ tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh
new file mode 100755
index 000000000000..3bf3da69195f
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# A wrapper to run VXLAN tests with an unusual port number.
+
+VXPORT=8472
+ALL_TESTS="
+ ping_ipv4
+"
+source vxlan_bridge_1d.sh
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
new file mode 100755
index 000000000000..a5789721ba92
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
@@ -0,0 +1,860 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------+ +------------------------+
+# | H1 (vrf) | | H2 (vrf) |
+# | + $h1.10 | | + $h2.10 |
+# | | 192.0.2.1/28 | | | 192.0.2.2/28 |
+# | | | | | |
+# | | + $h1.20 | | | + $h2.20 |
+# | \ | 198.51.100.1/24 | | \ | 198.51.100.2/24 |
+# | \| | | \| |
+# | + $h1 | | + $h2 |
+# +----|------------------+ +----|-------------------+
+# | |
+# +----|--------------------------------------------------|-------------------+
+# | SW | | |
+# | +--|--------------------------------------------------|-----------------+ |
+# | | + $swp1 BR1 (802.1q) + $swp2 | |
+# | | vid 10 vid 10 | |
+# | | vid 20 vid 20 | |
+# | | | |
+# | | + vx10 (vxlan) + vx20 (vxlan) | |
+# | | local 192.0.2.17 local 192.0.2.17 | |
+# | | remote 192.0.2.34 192.0.2.50 remote 192.0.2.34 192.0.2.50 | |
+# | | id 1000 dstport $VXPORT id 2000 dstport $VXPORT | |
+# | | vid 10 pvid untagged vid 20 pvid untagged | |
+# | +-----------------------------------------------------------------------+ |
+# | |
+# | 192.0.2.32/28 via 192.0.2.18 |
+# | 192.0.2.48/28 via 192.0.2.18 |
+# | |
+# | + $rp1 |
+# | | 192.0.2.17/28 |
+# +----|----------------------------------------------------------------------+
+# |
+# +----|--------------------------------------------------------+
+# | | VRP2 (vrf) |
+# | + $rp2 |
+# | 192.0.2.18/28 |
+# | | (maybe) HW
+# =============================================================================
+# | | (likely) SW
+# | + v1 (veth) + v3 (veth) |
+# | | 192.0.2.33/28 | 192.0.2.49/28 |
+# +----|---------------------------------------|----------------+
+# | |
+# +----|------------------------------+ +----|------------------------------+
+# | + v2 (veth) NS1 (netns) | | + v4 (veth) NS2 (netns) |
+# | 192.0.2.34/28 | | 192.0.2.50/28 |
+# | | | |
+# | 192.0.2.16/28 via 192.0.2.33 | | 192.0.2.16/28 via 192.0.2.49 |
+# | 192.0.2.50/32 via 192.0.2.33 | | 192.0.2.34/32 via 192.0.2.49 |
+# | | | |
+# | +-------------------------------+ | | +-------------------------------+ |
+# | | BR2 (802.1q) | | | | BR2 (802.1q) | |
+# | | + vx10 (vxlan) | | | | + vx10 (vxlan) | |
+# | | local 192.0.2.34 | | | | local 192.0.2.50 | |
+# | | remote 192.0.2.17 | | | | remote 192.0.2.17 | |
+# | | remote 192.0.2.50 | | | | remote 192.0.2.34 | |
+# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | |
+# | | vid 10 pvid untagged | | | | vid 10 pvid untagged | |
+# | | | | | | | |
+# | | + vx20 (vxlan) | | | | + vx20 (vxlan) | |
+# | | local 192.0.2.34 | | | | local 192.0.2.50 | |
+# | | remote 192.0.2.17 | | | | remote 192.0.2.17 | |
+# | | remote 192.0.2.50 | | | | remote 192.0.2.34 | |
+# | | id 2000 dstport $VXPORT | | | | id 2000 dstport $VXPORT | |
+# | | vid 20 pvid untagged | | | | vid 20 pvid untagged | |
+# | | | | | | | |
+# | | + w1 (veth) | | | | + w1 (veth) | |
+# | | | vid 10 | | | | | vid 10 | |
+# | | | vid 20 | | | | | vid 20 | |
+# | +--|----------------------------+ | | +--|----------------------------+ |
+# | | | | | |
+# | +--|----------------------------+ | | +--|----------------------------+ |
+# | | + w2 (veth) VW2 (vrf) | | | | + w2 (veth) VW2 (vrf) | |
+# | | |\ | | | | |\ | |
+# | | | + w2.10 | | | | | + w2.10 | |
+# | | | 192.0.2.3/28 | | | | | 192.0.2.4/28 | |
+# | | | | | | | | | |
+# | | + w2.20 | | | | + w2.20 | |
+# | | 198.51.100.3/24 | | | | 198.51.100.4/24 | |
+# | +-------------------------------+ | | +-------------------------------+ |
+# +-----------------------------------+ +-----------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+ ping_ipv4
+ test_flood
+ test_unicast
+ reapply_config
+ ping_ipv4
+ test_flood
+ test_unicast
+ test_learning
+ test_pvid
+ "}
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1
+ tc qdisc add dev $h1 clsact
+ vlan_create $h1 10 v$h1 192.0.2.1/28
+ vlan_create $h1 20 v$h1 198.51.100.1/24
+}
+
+h1_destroy()
+{
+ vlan_destroy $h1 20
+ vlan_destroy $h1 10
+ tc qdisc del dev $h1 clsact
+ simple_if_fini $h1
+}
+
+h2_create()
+{
+ simple_if_init $h2
+ tc qdisc add dev $h2 clsact
+ vlan_create $h2 10 v$h2 192.0.2.2/28
+ vlan_create $h2 20 v$h2 198.51.100.2/24
+}
+
+h2_destroy()
+{
+ vlan_destroy $h2 20
+ vlan_destroy $h2 10
+ tc qdisc del dev $h2 clsact
+ simple_if_fini $h2
+}
+
+rp1_set_addr()
+{
+ ip address add dev $rp1 192.0.2.17/28
+
+ ip route add 192.0.2.32/28 nexthop via 192.0.2.18
+ ip route add 192.0.2.48/28 nexthop via 192.0.2.18
+}
+
+rp1_unset_addr()
+{
+ ip route del 192.0.2.48/28 nexthop via 192.0.2.18
+ ip route del 192.0.2.32/28 nexthop via 192.0.2.18
+
+ ip address del dev $rp1 192.0.2.17/28
+}
+
+switch_create()
+{
+ ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 \
+ mcast_snooping 0
+ # Make sure the bridge uses the MAC address of the local port and not
+ # that of the VxLAN's device.
+ ip link set dev br1 address $(mac_get $swp1)
+ ip link set dev br1 up
+
+ ip link set dev $rp1 up
+ rp1_set_addr
+
+ ip link add name vx10 type vxlan id 1000 \
+ local 192.0.2.17 dstport "$VXPORT" \
+ nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx10 up
+
+ ip link set dev vx10 master br1
+ bridge vlan add vid 10 dev vx10 pvid untagged
+
+ ip link add name vx20 type vxlan id 2000 \
+ local 192.0.2.17 dstport "$VXPORT" \
+ nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx20 up
+
+ ip link set dev vx20 master br1
+ bridge vlan add vid 20 dev vx20 pvid untagged
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+ bridge vlan add vid 10 dev $swp1
+ bridge vlan add vid 20 dev $swp1
+
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+ bridge vlan add vid 10 dev $swp2
+ bridge vlan add vid 20 dev $swp2
+
+ bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self
+ bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self
+
+ bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self
+ bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self
+}
+
+switch_destroy()
+{
+ bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self
+ bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self
+
+ bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self
+ bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self
+
+ bridge vlan del vid 20 dev $swp2
+ bridge vlan del vid 10 dev $swp2
+ ip link set dev $swp2 down
+ ip link set dev $swp2 nomaster
+
+ bridge vlan del vid 20 dev $swp1
+ bridge vlan del vid 10 dev $swp1
+ ip link set dev $swp1 down
+ ip link set dev $swp1 nomaster
+
+ bridge vlan del vid 20 dev vx20
+ ip link set dev vx20 nomaster
+
+ ip link set dev vx20 down
+ ip link del dev vx20
+
+ bridge vlan del vid 10 dev vx10
+ ip link set dev vx10 nomaster
+
+ ip link set dev vx10 down
+ ip link del dev vx10
+
+ rp1_unset_addr
+ ip link set dev $rp1 down
+
+ ip link set dev br1 down
+ ip link del dev br1
+}
+
+vrp2_create()
+{
+ simple_if_init $rp2 192.0.2.18/28
+ __simple_if_init v1 v$rp2 192.0.2.33/28
+ __simple_if_init v3 v$rp2 192.0.2.49/28
+ tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+ tc qdisc del dev v1 clsact
+ __simple_if_fini v3 192.0.2.49/28
+ __simple_if_fini v1 192.0.2.33/28
+ simple_if_fini $rp2 192.0.2.18/28
+}
+
+ns_init_common()
+{
+ local in_if=$1; shift
+ local in_addr=$1; shift
+ local other_in_addr=$1; shift
+ local nh_addr=$1; shift
+ local host_addr1=$1; shift
+ local host_addr2=$1; shift
+
+ ip link set dev $in_if up
+ ip address add dev $in_if $in_addr/28
+ tc qdisc add dev $in_if clsact
+
+ ip link add name br2 type bridge vlan_filtering 1 vlan_default_pvid 0
+ ip link set dev br2 up
+
+ ip link add name w1 type veth peer name w2
+
+ ip link set dev w1 master br2
+ ip link set dev w1 up
+
+ bridge vlan add vid 10 dev w1
+ bridge vlan add vid 20 dev w1
+
+ ip link add name vx10 type vxlan id 1000 local $in_addr \
+ dstport "$VXPORT"
+ ip link set dev vx10 up
+ bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.17 self
+ bridge fdb append dev vx10 00:00:00:00:00:00 dst $other_in_addr self
+
+ ip link set dev vx10 master br2
+ tc qdisc add dev vx10 clsact
+
+ bridge vlan add vid 10 dev vx10 pvid untagged
+
+ ip link add name vx20 type vxlan id 2000 local $in_addr \
+ dstport "$VXPORT"
+ ip link set dev vx20 up
+ bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.17 self
+ bridge fdb append dev vx20 00:00:00:00:00:00 dst $other_in_addr self
+
+ ip link set dev vx20 master br2
+ tc qdisc add dev vx20 clsact
+
+ bridge vlan add vid 20 dev vx20 pvid untagged
+
+ simple_if_init w2
+ vlan_create w2 10 vw2 $host_addr1/28
+ vlan_create w2 20 vw2 $host_addr2/24
+
+ ip route add 192.0.2.16/28 nexthop via $nh_addr
+ ip route add $other_in_addr/32 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+ ip netns add ns1
+ ip link set dev v2 netns ns1
+ in_ns ns1 \
+ ns_init_common v2 192.0.2.34 192.0.2.50 192.0.2.33 192.0.2.3 \
+ 198.51.100.3
+}
+
+ns1_destroy()
+{
+ ip netns exec ns1 ip link set dev v2 netns 1
+ ip netns del ns1
+}
+
+ns2_create()
+{
+ ip netns add ns2
+ ip link set dev v4 netns ns2
+ in_ns ns2 \
+ ns_init_common v4 192.0.2.50 192.0.2.34 192.0.2.49 192.0.2.4 \
+ 198.51.100.4
+}
+
+ns2_destroy()
+{
+ ip netns exec ns2 ip link set dev v4 netns 1
+ ip netns del ns2
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ rp1=${NETIFS[p5]}
+ rp2=${NETIFS[p6]}
+
+ vrf_prepare
+ forwarding_enable
+
+ h1_create
+ h2_create
+ switch_create
+
+ ip link add name v1 type veth peer name v2
+ ip link add name v3 type veth peer name v4
+ vrp2_create
+ ns1_create
+ ns2_create
+
+ r1_mac=$(in_ns ns1 mac_get w2)
+ r2_mac=$(in_ns ns2 mac_get w2)
+ h2_mac=$(mac_get $h2)
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ns2_destroy
+ ns1_destroy
+ vrp2_destroy
+ ip link del dev v3
+ ip link del dev v1
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ forwarding_restore
+ vrf_cleanup
+}
+
+# For the first round of tests, vx10 and vx20 were the first devices to get
+# attached to the bridge, and that at the point that the local IP is already
+# configured. Try the other scenario of attaching these devices to a bridge
+# that already has local ports members, and only then assign the local IP.
+reapply_config()
+{
+ log_info "Reapplying configuration"
+
+ bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self
+ bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self
+
+ bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self
+ bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self
+
+ ip link set dev vx20 nomaster
+ ip link set dev vx10 nomaster
+
+ rp1_unset_addr
+ sleep 5
+
+ ip link set dev vx10 master br1
+ bridge vlan add vid 10 dev vx10 pvid untagged
+
+ ip link set dev vx20 master br1
+ bridge vlan add vid 20 dev vx20 pvid untagged
+
+ bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self
+ bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self
+
+ bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self
+ bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self
+
+ rp1_set_addr
+ sleep 5
+}
+
+ping_ipv4()
+{
+ ping_test $h1.10 192.0.2.2 ": local->local vid 10"
+ ping_test $h1.20 198.51.100.2 ": local->local vid 20"
+ ping_test $h1.10 192.0.2.3 ": local->remote 1 vid 10"
+ ping_test $h1.10 192.0.2.4 ": local->remote 2 vid 10"
+ ping_test $h1.20 198.51.100.3 ": local->remote 1 vid 20"
+ ping_test $h1.20 198.51.100.4 ": local->remote 2 vid 20"
+}
+
+maybe_in_ns()
+{
+ echo ${1:+in_ns} $1
+}
+
+__flood_counter_add_del()
+{
+ local add_del=$1; shift
+ local dev=$1; shift
+ local ns=$1; shift
+
+ # Putting the ICMP capture both to HW and to SW will end up
+ # double-counting the packets that are trapped to slow path, such as for
+ # the unicast test. Adding either skip_hw or skip_sw fixes this problem,
+ # but with skip_hw, the flooded packets are not counted at all, because
+ # those are dropped due to MAC address mismatch; and skip_sw is a no-go
+ # for veth-based topologies.
+ #
+ # So try to install with skip_sw and fall back to skip_sw if that fails.
+
+ $(maybe_in_ns $ns) __icmp_capture_add_del \
+ $add_del 100 "" $dev skip_sw 2>/dev/null || \
+ $(maybe_in_ns $ns) __icmp_capture_add_del \
+ $add_del 100 "" $dev skip_hw
+}
+
+flood_counter_install()
+{
+ __flood_counter_add_del add "$@"
+}
+
+flood_counter_uninstall()
+{
+ __flood_counter_add_del del "$@"
+}
+
+flood_fetch_stat()
+{
+ local dev=$1; shift
+ local ns=$1; shift
+
+ $(maybe_in_ns $ns) tc_rule_stats_get $dev 100 ingress
+}
+
+flood_fetch_stats()
+{
+ local counters=("${@}")
+ local counter
+
+ for counter in "${counters[@]}"; do
+ flood_fetch_stat $counter
+ done
+}
+
+vxlan_flood_test()
+{
+ local mac=$1; shift
+ local dst=$1; shift
+ local vid=$1; shift
+ local -a expects=("${@}")
+
+ local -a counters=($h2 "vx10 ns1" "vx20 ns1" "vx10 ns2" "vx20 ns2")
+ local counter
+ local key
+
+ # Packets reach the local host tagged whereas they reach the VxLAN
+ # devices untagged. In order to be able to use the same filter for
+ # all counters, make sure the packets also reach the local host
+ # untagged
+ bridge vlan add vid $vid dev $swp2 untagged
+ for counter in "${counters[@]}"; do
+ flood_counter_install $counter
+ done
+
+ local -a t0s=($(flood_fetch_stats "${counters[@]}"))
+ $MZ $h1 -Q $vid -c 10 -d 100msec -p 64 -b $mac -B $dst -t icmp -q
+ sleep 1
+ local -a t1s=($(flood_fetch_stats "${counters[@]}"))
+
+ for key in ${!t0s[@]}; do
+ local delta=$((t1s[$key] - t0s[$key]))
+ local expect=${expects[$key]}
+
+ ((expect == delta))
+ check_err $? "${counters[$key]}: Expected to capture $expect packets, got $delta."
+ done
+
+ for counter in "${counters[@]}"; do
+ flood_counter_uninstall $counter
+ done
+ bridge vlan add vid $vid dev $swp2
+}
+
+__test_flood()
+{
+ local mac=$1; shift
+ local dst=$1; shift
+ local vid=$1; shift
+ local what=$1; shift
+ local -a expects=("${@}")
+
+ RET=0
+
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: $what"
+}
+
+test_flood()
+{
+ __test_flood de:ad:be:ef:13:37 192.0.2.100 10 "flood vlan 10" \
+ 10 10 0 10 0
+ __test_flood ca:fe:be:ef:13:37 198.51.100.100 20 "flood vlan 20" \
+ 10 0 10 0 10
+}
+
+vxlan_fdb_add_del()
+{
+ local add_del=$1; shift
+ local vid=$1; shift
+ local mac=$1; shift
+ local dev=$1; shift
+ local dst=$1; shift
+
+ bridge fdb $add_del dev $dev $mac self static permanent \
+ ${dst:+dst} $dst 2>/dev/null
+ bridge fdb $add_del dev $dev $mac master static vlan $vid 2>/dev/null
+}
+
+__test_unicast()
+{
+ local mac=$1; shift
+ local dst=$1; shift
+ local hit_idx=$1; shift
+ local vid=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ local -a expects=(0 0 0 0 0)
+ expects[$hit_idx]=10
+
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: $what"
+}
+
+test_unicast()
+{
+ local -a targets=("$h2_mac $h2"
+ "$r1_mac vx10 192.0.2.34"
+ "$r2_mac vx10 192.0.2.50")
+ local target
+
+ log_info "unicast vlan 10"
+
+ for target in "${targets[@]}"; do
+ vxlan_fdb_add_del add 10 $target
+ done
+
+ __test_unicast $h2_mac 192.0.2.2 0 10 "local MAC unicast"
+ __test_unicast $r1_mac 192.0.2.3 1 10 "remote MAC 1 unicast"
+ __test_unicast $r2_mac 192.0.2.4 3 10 "remote MAC 2 unicast"
+
+ for target in "${targets[@]}"; do
+ vxlan_fdb_add_del del 10 $target
+ done
+
+ log_info "unicast vlan 20"
+
+ targets=("$h2_mac $h2" "$r1_mac vx20 192.0.2.34" \
+ "$r2_mac vx20 192.0.2.50")
+
+ for target in "${targets[@]}"; do
+ vxlan_fdb_add_del add 20 $target
+ done
+
+ __test_unicast $h2_mac 198.51.100.2 0 20 "local MAC unicast"
+ __test_unicast $r1_mac 198.51.100.3 2 20 "remote MAC 1 unicast"
+ __test_unicast $r2_mac 198.51.100.4 4 20 "remote MAC 2 unicast"
+
+ for target in "${targets[@]}"; do
+ vxlan_fdb_add_del del 20 $target
+ done
+}
+
+test_pvid()
+{
+ local -a expects=(0 0 0 0 0)
+ local mac=de:ad:be:ef:13:37
+ local dst=192.0.2.100
+ local vid=10
+
+ # Check that flooding works
+ RET=0
+
+ expects[0]=10; expects[1]=10; expects[3]=10
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: flood before pvid off"
+
+ # Toggle PVID off and test that flood to remote hosts does not work
+ RET=0
+
+ bridge vlan add vid 10 dev vx10
+
+ expects[0]=10; expects[1]=0; expects[3]=0
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: flood after pvid off"
+
+ # Toggle PVID on and test that flood to remote hosts does work
+ RET=0
+
+ bridge vlan add vid 10 dev vx10 pvid untagged
+
+ expects[0]=10; expects[1]=10; expects[3]=10
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: flood after pvid on"
+
+ # Add a new VLAN and test that it does not affect flooding
+ RET=0
+
+ bridge vlan add vid 30 dev vx10
+
+ expects[0]=10; expects[1]=10; expects[3]=10
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ bridge vlan del vid 30 dev vx10
+
+ log_test "VXLAN: flood after vlan add"
+
+ # Remove currently mapped VLAN and test that flood to remote hosts does
+ # not work
+ RET=0
+
+ bridge vlan del vid 10 dev vx10
+
+ expects[0]=10; expects[1]=0; expects[3]=0
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: flood after vlan delete"
+
+ # Re-add the VLAN and test that flood to remote hosts does work
+ RET=0
+
+ bridge vlan add vid 10 dev vx10 pvid untagged
+
+ expects[0]=10; expects[1]=10; expects[3]=10
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: flood after vlan re-add"
+}
+
+vxlan_ping_test()
+{
+ local ping_dev=$1; shift
+ local ping_dip=$1; shift
+ local ping_args=$1; shift
+ local capture_dev=$1; shift
+ local capture_dir=$1; shift
+ local capture_pref=$1; shift
+ local expect=$1; shift
+
+ local t0=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+ ping_do $ping_dev $ping_dip "$ping_args"
+ local t1=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+ local delta=$((t1 - t0))
+
+ # Tolerate a couple stray extra packets.
+ ((expect <= delta && delta <= expect + 2))
+ check_err $? "$capture_dev: Expected to capture $expect packets, got $delta."
+}
+
+__test_learning()
+{
+ local -a expects=(0 0 0 0 0)
+ local mac=$1; shift
+ local dst=$1; shift
+ local vid=$1; shift
+ local idx1=$1; shift
+ local idx2=$1; shift
+ local vx=vx$vid
+
+ # Check that flooding works
+ RET=0
+
+ expects[0]=10; expects[$idx1]=10; expects[$idx2]=10
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: flood before learning"
+
+ # Send a packet with source mac set to $mac from host w2 and check that
+ # a corresponding entry is created in the VxLAN device
+ RET=0
+
+ in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \
+ -B $dst -t icmp -q
+ sleep 1
+
+ bridge fdb show brport $vx | grep $mac | grep -q self
+ check_err $?
+ bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+ | grep -q -v self
+ check_err $?
+
+ log_test "VXLAN: show learned FDB entry"
+
+ # Repeat first test and check that packets only reach host w2 in ns1
+ RET=0
+
+ expects[0]=0; expects[$idx1]=10; expects[$idx2]=0
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: learned FDB entry"
+
+ # Delete the learned FDB entry from the VxLAN and bridge devices and
+ # check that packets are flooded
+ RET=0
+
+ bridge fdb del dev $vx $mac master self vlan $vid
+ sleep 1
+
+ expects[0]=10; expects[$idx1]=10; expects[$idx2]=10
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: deletion of learned FDB entry"
+
+ # Re-learn the first FDB entry and check that it is correctly aged-out
+ RET=0
+
+ in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \
+ -B $dst -t icmp -q
+ sleep 1
+
+ bridge fdb show brport $vx | grep $mac | grep -q self
+ check_err $?
+ bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+ | grep -q -v self
+ check_err $?
+
+ expects[0]=0; expects[$idx1]=10; expects[$idx2]=0
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ sleep 20
+
+ bridge fdb show brport $vx | grep $mac | grep -q self
+ check_fail $?
+ bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+ | grep -q -v self
+ check_fail $?
+
+ expects[0]=10; expects[$idx1]=10; expects[$idx2]=10
+ vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+ log_test "VXLAN: Ageing of learned FDB entry"
+
+ # Toggle learning on the bridge port and check that the bridge's FDB
+ # is populated only when it should
+ RET=0
+
+ ip link set dev $vx type bridge_slave learning off
+
+ in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \
+ -B $dst -t icmp -q
+ sleep 1
+
+ bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+ | grep -q -v self
+ check_fail $?
+
+ ip link set dev $vx type bridge_slave learning on
+
+ in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \
+ -B $dst -t icmp -q
+ sleep 1
+
+ bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+ | grep -q -v self
+ check_err $?
+
+ log_test "VXLAN: learning toggling on bridge port"
+}
+
+test_learning()
+{
+ local mac=de:ad:be:ef:13:37
+ local dst=192.0.2.100
+ local vid=10
+
+ # Enable learning on the VxLAN devices and set ageing time to 10 seconds
+ ip link set dev br1 type bridge ageing_time 1000
+ ip link set dev vx10 type vxlan ageing 10
+ ip link set dev vx10 type vxlan learning
+ ip link set dev vx20 type vxlan ageing 10
+ ip link set dev vx20 type vxlan learning
+ reapply_config
+
+ log_info "learning vlan 10"
+
+ __test_learning $mac $dst $vid 1 3
+
+ log_info "learning vlan 20"
+
+ mac=ca:fe:be:ef:13:37
+ dst=198.51.100.100
+ vid=20
+
+ __test_learning $mac $dst $vid 2 4
+
+ # Restore previous settings
+ ip link set dev vx20 type vxlan nolearning
+ ip link set dev vx20 type vxlan ageing 300
+ ip link set dev vx10 type vxlan nolearning
+ ip link set dev vx10 type vxlan ageing 300
+ ip link set dev br1 type bridge ageing_time 30000
+ reapply_config
+}
+
+test_all()
+{
+ log_info "Running tests with UDP port $VXPORT"
+ tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh
new file mode 100755
index 000000000000..b1b2d1a3164f
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# A wrapper to run VXLAN tests with an unusual port number.
+
+VXPORT=8472
+ALL_TESTS="
+ ping_ipv4
+"
+source vxlan_bridge_1q.sh
diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 406cc70c571d..4b02933cab8a 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -651,12 +651,13 @@ static void do_flush_datagram(int fd, int type)
static void do_rx(int domain, int type, int protocol)
{
+ const int cfg_receiver_wait_ms = 400;
uint64_t tstop;
int fd;
fd = do_setup_rx(domain, type, protocol);
- tstop = gettimeofday_ms() + cfg_runtime_ms;
+ tstop = gettimeofday_ms() + cfg_runtime_ms + cfg_receiver_wait_ms;
do {
if (type == SOCK_STREAM)
do_flush_tcp(fd);
diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh
index c43c6debda06..825ffec85cea 100755
--- a/tools/testing/selftests/net/msg_zerocopy.sh
+++ b/tools/testing/selftests/net/msg_zerocopy.sh
@@ -25,6 +25,8 @@ readonly path_sysctl_mem="net.core.optmem_max"
if [[ "$#" -eq "0" ]]; then
$0 4 tcp -t 1
$0 6 tcp -t 1
+ $0 4 udp -t 1
+ $0 6 udp -t 1
echo "OK. All tests passed"
exit 0
fi
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index a369d616b390..e2c94e47707c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -26,6 +26,47 @@
# - pmtu_ipv6
# Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
#
+# - pmtu_ipv4_vxlan4_exception
+# Set up the same network topology as pmtu_ipv4, create a VXLAN tunnel
+# over IPv4 between A and B, routed via R1. On the link between R1 and B,
+# set a MTU lower than the VXLAN MTU and the MTU on the link between A and
+# R1. Send IPv4 packets, exceeding the MTU between R1 and B, over VXLAN
+# from A to B and check that the PMTU exception is created with the right
+# value on A
+#
+# - pmtu_ipv6_vxlan4_exception
+# Same as pmtu_ipv4_vxlan4_exception, but send IPv6 packets from A to B
+#
+# - pmtu_ipv4_vxlan6_exception
+# Same as pmtu_ipv4_vxlan4_exception, but use IPv6 transport from A to B
+#
+# - pmtu_ipv6_vxlan6_exception
+# Same as pmtu_ipv4_vxlan6_exception, but send IPv6 packets from A to B
+#
+# - pmtu_ipv4_geneve4_exception
+# Same as pmtu_ipv4_vxlan4_exception, but using a GENEVE tunnel instead of
+# VXLAN
+#
+# - pmtu_ipv6_geneve4_exception
+# Same as pmtu_ipv6_vxlan4_exception, but using a GENEVE tunnel instead of
+# VXLAN
+#
+# - pmtu_ipv4_geneve6_exception
+# Same as pmtu_ipv4_vxlan6_exception, but using a GENEVE tunnel instead of
+# VXLAN
+#
+# - pmtu_ipv6_geneve6_exception
+# Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of
+# VXLAN
+#
+# - pmtu_ipv{4,6}_fou{4,6}_exception
+# Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation
+# (FoU) over IPv4/IPv6, instead of VXLAN
+#
+# - pmtu_ipv{4,6}_fou{4,6}_exception
+# Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6
+# encapsulation (GUE) over IPv4/IPv6, instead of VXLAN
+#
# - pmtu_vti4_exception
# Set up vti tunnel on top of veth, with xfrm states and policies, in two
# namespaces with matching endpoints. Check that route exception is not
@@ -72,6 +113,22 @@ which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
tests="
pmtu_ipv4_exception ipv4: PMTU exceptions
pmtu_ipv6_exception ipv6: PMTU exceptions
+ pmtu_ipv4_vxlan4_exception IPv4 over vxlan4: PMTU exceptions
+ pmtu_ipv6_vxlan4_exception IPv6 over vxlan4: PMTU exceptions
+ pmtu_ipv4_vxlan6_exception IPv4 over vxlan6: PMTU exceptions
+ pmtu_ipv6_vxlan6_exception IPv6 over vxlan6: PMTU exceptions
+ pmtu_ipv4_geneve4_exception IPv4 over geneve4: PMTU exceptions
+ pmtu_ipv6_geneve4_exception IPv6 over geneve4: PMTU exceptions
+ pmtu_ipv4_geneve6_exception IPv4 over geneve6: PMTU exceptions
+ pmtu_ipv6_geneve6_exception IPv6 over geneve6: PMTU exceptions
+ pmtu_ipv4_fou4_exception IPv4 over fou4: PMTU exceptions
+ pmtu_ipv6_fou4_exception IPv6 over fou4: PMTU exceptions
+ pmtu_ipv4_fou6_exception IPv4 over fou6: PMTU exceptions
+ pmtu_ipv6_fou6_exception IPv6 over fou6: PMTU exceptions
+ pmtu_ipv4_gue4_exception IPv4 over gue4: PMTU exceptions
+ pmtu_ipv6_gue4_exception IPv6 over gue4: PMTU exceptions
+ pmtu_ipv4_gue6_exception IPv4 over gue6: PMTU exceptions
+ pmtu_ipv6_gue6_exception IPv6 over gue6: PMTU exceptions
pmtu_vti6_exception vti6: PMTU exceptions
pmtu_vti4_exception vti4: PMTU exceptions
pmtu_vti4_default_mtu vti4: default MTU assignment
@@ -95,8 +152,8 @@ ns_r2="ip netns exec ${NS_R2}"
# Addresses are:
# - IPv4: PREFIX4.SEGMENT.ID (/24)
# - IPv6: PREFIX6:SEGMENT::ID (/64)
-prefix4="192.168"
-prefix6="fd00"
+prefix4="10.0"
+prefix6="fc00"
a_r1=1
a_r2=2
b_r1=3
@@ -129,12 +186,12 @@ veth6_a_addr="fd00:1::a"
veth6_b_addr="fd00:1::b"
veth6_mask="64"
-vti4_a_addr="192.168.2.1"
-vti4_b_addr="192.168.2.2"
-vti4_mask="24"
-vti6_a_addr="fd00:2::a"
-vti6_b_addr="fd00:2::b"
-vti6_mask="64"
+tunnel4_a_addr="192.168.2.1"
+tunnel4_b_addr="192.168.2.2"
+tunnel4_mask="24"
+tunnel6_a_addr="fd00:2::a"
+tunnel6_b_addr="fd00:2::b"
+tunnel6_mask="64"
dummy6_0_addr="fc00:1000::0"
dummy6_1_addr="fc00:1001::0"
@@ -159,6 +216,89 @@ nsname() {
eval echo \$NS_$1
}
+setup_fou_or_gue() {
+ outer="${1}"
+ inner="${2}"
+ encap="${3}"
+
+ if [ "${outer}" = "4" ]; then
+ modprobe fou || return 2
+ a_addr="${prefix4}.${a_r1}.1"
+ b_addr="${prefix4}.${b_r1}.1"
+ if [ "${inner}" = "4" ]; then
+ type="ipip"
+ ipproto="4"
+ else
+ type="sit"
+ ipproto="41"
+ fi
+ else
+ modprobe fou6 || return 2
+ a_addr="${prefix6}:${a_r1}::1"
+ b_addr="${prefix6}:${b_r1}::1"
+ if [ "${inner}" = "4" ]; then
+ type="ip6tnl"
+ mode="mode ipip6"
+ ipproto="4 -6"
+ else
+ type="ip6tnl"
+ mode="mode ip6ip6"
+ ipproto="41 -6"
+ fi
+ fi
+
+ ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
+ ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2
+
+ ${ns_b} ip fou add port 5556 ipproto ${ipproto}
+ ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555
+
+ if [ "${inner}" = "4" ]; then
+ ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a
+ ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b
+ else
+ ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a
+ ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b
+ fi
+
+ ${ns_a} ip link set ${encap}_a up
+ ${ns_b} ip link set ${encap}_b up
+
+ sleep 1
+}
+
+setup_fou44() {
+ setup_fou_or_gue 4 4 fou
+}
+
+setup_fou46() {
+ setup_fou_or_gue 4 6 fou
+}
+
+setup_fou64() {
+ setup_fou_or_gue 6 4 fou
+}
+
+setup_fou66() {
+ setup_fou_or_gue 6 6 fou
+}
+
+setup_gue44() {
+ setup_fou_or_gue 4 4 gue
+}
+
+setup_gue46() {
+ setup_fou_or_gue 4 6 gue
+}
+
+setup_gue64() {
+ setup_fou_or_gue 6 4 gue
+}
+
+setup_gue66() {
+ setup_fou_or_gue 6 6 gue
+}
+
setup_namespaces() {
for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
ip netns add ${n} || return 1
@@ -202,11 +342,57 @@ setup_vti() {
}
setup_vti4() {
- setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${vti4_a_addr} ${vti4_b_addr} ${vti4_mask}
+ setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
}
setup_vti6() {
- setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${vti6_a_addr} ${vti6_b_addr} ${vti6_mask}
+ setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
+}
+
+setup_vxlan_or_geneve() {
+ type="${1}"
+ a_addr="${2}"
+ b_addr="${3}"
+ opts="${4}"
+
+ if [ "${type}" = "vxlan" ]; then
+ opts="${opts} ttl 64 dstport 4789"
+ opts_a="local ${a_addr}"
+ opts_b="local ${b_addr}"
+ else
+ opts_a=""
+ opts_b=""
+ fi
+
+ ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1
+ ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts}
+
+ ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
+ ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
+
+ ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
+ ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b
+
+ ${ns_a} ip link set ${type}_a up
+ ${ns_b} ip link set ${type}_b up
+
+ sleep 1
+}
+
+setup_geneve4() {
+ setup_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set"
+}
+
+setup_vxlan4() {
+ setup_vxlan_or_geneve vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set"
+}
+
+setup_geneve6() {
+ setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
+}
+
+setup_vxlan6() {
+ setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
}
setup_xfrm() {
@@ -465,6 +651,161 @@ test_pmtu_ipv6_exception() {
test_pmtu_ipvX 6
}
+test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() {
+ type=${1}
+ family=${2}
+ outer_family=${3}
+ ll_mtu=4000
+
+ if [ ${outer_family} -eq 4 ]; then
+ setup namespaces routing ${type}4 || return 2
+ # IPv4 header UDP header VXLAN/GENEVE header Ethernet header
+ exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
+ else
+ setup namespaces routing ${type}6 || return 2
+ # IPv6 header UDP header VXLAN/GENEVE header Ethernet header
+ exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
+ fi
+
+ trace "${ns_a}" ${type}_a "${ns_b}" ${type}_b \
+ "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
+ "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
+
+ if [ ${family} -eq 4 ]; then
+ ping=ping
+ dst=${tunnel4_b_addr}
+ else
+ ping=${ping6}
+ dst=${tunnel6_b_addr}
+ fi
+
+ # Create route exception by exceeding link layer MTU
+ mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000))
+ mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+ mtu "${ns_b}" veth_B-R1 ${ll_mtu}
+ mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+ mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000))
+ mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000))
+ ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+
+ # Check that exception was created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+ check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${type} interface"
+}
+
+test_pmtu_ipv4_vxlan4_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 4 4
+}
+
+test_pmtu_ipv6_vxlan4_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 6 4
+}
+
+test_pmtu_ipv4_geneve4_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 4
+}
+
+test_pmtu_ipv6_geneve4_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 4
+}
+
+test_pmtu_ipv4_vxlan6_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 4 6
+}
+
+test_pmtu_ipv6_vxlan6_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 6 6
+}
+
+test_pmtu_ipv4_geneve6_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 6
+}
+
+test_pmtu_ipv6_geneve6_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6
+}
+
+test_pmtu_ipvX_over_fouY_or_gueY() {
+ inner_family=${1}
+ outer_family=${2}
+ encap=${3}
+ ll_mtu=4000
+
+ setup namespaces routing ${encap}${outer_family}${inner_family} || return 2
+ trace "${ns_a}" ${encap}_a "${ns_b}" ${encap}_b \
+ "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
+ "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
+
+ if [ ${inner_family} -eq 4 ]; then
+ ping=ping
+ dst=${tunnel4_b_addr}
+ else
+ ping=${ping6}
+ dst=${tunnel6_b_addr}
+ fi
+
+ if [ "${encap}" = "gue" ]; then
+ encap_overhead=4
+ else
+ encap_overhead=0
+ fi
+
+ if [ ${outer_family} -eq 4 ]; then
+ # IPv4 header UDP header
+ exp_mtu=$((${ll_mtu} - 20 - 8 - ${encap_overhead}))
+ else
+ # IPv6 header Option 4 UDP header
+ exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - ${encap_overhead}))
+ fi
+
+ # Create route exception by exceeding link layer MTU
+ mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000))
+ mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+ mtu "${ns_b}" veth_B-R1 ${ll_mtu}
+ mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+ mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000))
+ mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000))
+ ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+
+ # Check that exception was created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+ check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${encap} interface"
+}
+
+test_pmtu_ipv4_fou4_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 4 4 fou
+}
+
+test_pmtu_ipv6_fou4_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 6 4 fou
+}
+
+test_pmtu_ipv4_fou6_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 4 6 fou
+}
+
+test_pmtu_ipv6_fou6_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 6 6 fou
+}
+
+test_pmtu_ipv4_gue4_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 4 4 gue
+}
+
+test_pmtu_ipv6_gue4_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 6 4 gue
+}
+
+test_pmtu_ipv4_gue6_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 4 6 gue
+}
+
+test_pmtu_ipv6_gue6_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue
+}
+
test_pmtu_vti4_exception() {
setup namespaces veth vti4 xfrm4 || return 2
trace "${ns_a}" veth_a "${ns_b}" veth_b \
@@ -484,14 +825,14 @@ test_pmtu_vti4_exception() {
# Send DF packet without exceeding link layer MTU, check that no
# exception is created
- ${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
+ ${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
# Now exceed link layer MTU by one byte, check that exception is created
# with the right PMTU value
- ${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
+ ${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
}
@@ -506,20 +847,20 @@ test_pmtu_vti6_exception() {
mtu "${ns_b}" veth_b 4000
mtu "${ns_a}" vti6_a 5000
mtu "${ns_b}" vti6_b 5000
- ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
+ ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${tunnel6_b_addr} > /dev/null
# Check that exception was created
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
# Decrease tunnel MTU, check for PMTU decrease in route exception
mtu "${ns_a}" vti6_a 3000
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
# Increase tunnel MTU, check for PMTU increase in route exception
mtu "${ns_a}" vti6_a 9000
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
return ${fail}
diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
new file mode 100644
index 000000000000..c6233935fed1
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Test that sockets listening on a specific address are preferred
+ * over sockets listening on addr_any.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/dccp.h>
+#include <linux/in.h>
+#include <linux/unistd.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+static const char *IP4_ADDR = "127.0.0.1";
+static const char *IP6_ADDR = "::1";
+static const char *IP4_MAPPED6 = "::ffff:127.0.0.1";
+
+static const int PORT = 8888;
+
+static void build_rcv_fd(int family, int proto, int *rcv_fds, int count,
+ const char *addr_str)
+{
+ struct sockaddr_in addr4 = {0};
+ struct sockaddr_in6 addr6 = {0};
+ struct sockaddr *addr;
+ int opt, i, sz;
+
+ memset(&addr, 0, sizeof(addr));
+
+ switch (family) {
+ case AF_INET:
+ addr4.sin_family = family;
+ if (!addr_str)
+ addr4.sin_addr.s_addr = htonl(INADDR_ANY);
+ else if (!inet_pton(family, addr_str, &addr4.sin_addr.s_addr))
+ error(1, errno, "inet_pton failed: %s", addr_str);
+ addr4.sin_port = htons(PORT);
+ sz = sizeof(addr4);
+ addr = (struct sockaddr *)&addr4;
+ break;
+ case AF_INET6:
+ addr6.sin6_family = AF_INET6;
+ if (!addr_str)
+ addr6.sin6_addr = in6addr_any;
+ else if (!inet_pton(family, addr_str, &addr6.sin6_addr))
+ error(1, errno, "inet_pton failed: %s", addr_str);
+ addr6.sin6_port = htons(PORT);
+ sz = sizeof(addr6);
+ addr = (struct sockaddr *)&addr6;
+ break;
+ default:
+ error(1, 0, "Unsupported family %d", family);
+ /* clang does not recognize error() above as terminating
+ * the program, so it complains that saddr, sz are
+ * not initialized when this code path is taken. Silence it.
+ */
+ return;
+ }
+
+ for (i = 0; i < count; ++i) {
+ rcv_fds[i] = socket(family, proto, 0);
+ if (rcv_fds[i] < 0)
+ error(1, errno, "failed to create receive socket");
+
+ opt = 1;
+ if (setsockopt(rcv_fds[i], SOL_SOCKET, SO_REUSEPORT, &opt,
+ sizeof(opt)))
+ error(1, errno, "failed to set SO_REUSEPORT");
+
+ if (bind(rcv_fds[i], addr, sz))
+ error(1, errno, "failed to bind receive socket");
+
+ if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
+ error(1, errno, "tcp: failed to listen on receive port");
+ else if (proto == SOCK_DCCP) {
+ if (setsockopt(rcv_fds[i], SOL_DCCP,
+ DCCP_SOCKOPT_SERVICE,
+ &(int) {htonl(42)}, sizeof(int)))
+ error(1, errno, "failed to setsockopt");
+
+ if (listen(rcv_fds[i], 10))
+ error(1, errno, "dccp: failed to listen on receive port");
+ }
+ }
+}
+
+static int connect_and_send(int family, int proto)
+{
+ struct sockaddr_in saddr4 = {0};
+ struct sockaddr_in daddr4 = {0};
+ struct sockaddr_in6 saddr6 = {0};
+ struct sockaddr_in6 daddr6 = {0};
+ struct sockaddr *saddr, *daddr;
+ int fd, sz;
+
+ switch (family) {
+ case AF_INET:
+ saddr4.sin_family = AF_INET;
+ saddr4.sin_addr.s_addr = htonl(INADDR_ANY);
+ saddr4.sin_port = 0;
+
+ daddr4.sin_family = AF_INET;
+ if (!inet_pton(family, IP4_ADDR, &daddr4.sin_addr.s_addr))
+ error(1, errno, "inet_pton failed: %s", IP4_ADDR);
+ daddr4.sin_port = htons(PORT);
+
+ sz = sizeof(saddr4);
+ saddr = (struct sockaddr *)&saddr4;
+ daddr = (struct sockaddr *)&daddr4;
+ break;
+ case AF_INET6:
+ saddr6.sin6_family = AF_INET6;
+ saddr6.sin6_addr = in6addr_any;
+
+ daddr6.sin6_family = AF_INET6;
+ if (!inet_pton(family, IP6_ADDR, &daddr6.sin6_addr))
+ error(1, errno, "inet_pton failed: %s", IP6_ADDR);
+ daddr6.sin6_port = htons(PORT);
+
+ sz = sizeof(saddr6);
+ saddr = (struct sockaddr *)&saddr6;
+ daddr = (struct sockaddr *)&daddr6;
+ break;
+ default:
+ error(1, 0, "Unsupported family %d", family);
+ /* clang does not recognize error() above as terminating
+ * the program, so it complains that saddr, daddr, sz are
+ * not initialized when this code path is taken. Silence it.
+ */
+ return -1;
+ }
+
+ fd = socket(family, proto, 0);
+ if (fd < 0)
+ error(1, errno, "failed to create send socket");
+
+ if (proto == SOCK_DCCP &&
+ setsockopt(fd, SOL_DCCP, DCCP_SOCKOPT_SERVICE,
+ &(int){htonl(42)}, sizeof(int)))
+ error(1, errno, "failed to setsockopt");
+
+ if (bind(fd, saddr, sz))
+ error(1, errno, "failed to bind send socket");
+
+ if (connect(fd, daddr, sz))
+ error(1, errno, "failed to connect send socket");
+
+ if (send(fd, "a", 1, 0) < 0)
+ error(1, errno, "failed to send message");
+
+ return fd;
+}
+
+static int receive_once(int epfd, int proto)
+{
+ struct epoll_event ev;
+ int i, fd;
+ char buf[8];
+
+ i = epoll_wait(epfd, &ev, 1, 3);
+ if (i < 0)
+ error(1, errno, "epoll_wait failed");
+
+ if (proto == SOCK_STREAM || proto == SOCK_DCCP) {
+ fd = accept(ev.data.fd, NULL, NULL);
+ if (fd < 0)
+ error(1, errno, "failed to accept");
+ i = recv(fd, buf, sizeof(buf), 0);
+ close(fd);
+ } else {
+ i = recv(ev.data.fd, buf, sizeof(buf), 0);
+ }
+
+ if (i < 0)
+ error(1, errno, "failed to recv");
+
+ return ev.data.fd;
+}
+
+static void test(int *rcv_fds, int count, int family, int proto, int fd)
+{
+ struct epoll_event ev;
+ int epfd, i, send_fd, recv_fd;
+
+ epfd = epoll_create(1);
+ if (epfd < 0)
+ error(1, errno, "failed to create epoll");
+
+ ev.events = EPOLLIN;
+ for (i = 0; i < count; ++i) {
+ ev.data.fd = rcv_fds[i];
+ if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fds[i], &ev))
+ error(1, errno, "failed to register sock epoll");
+ }
+
+ send_fd = connect_and_send(family, proto);
+
+ recv_fd = receive_once(epfd, proto);
+ if (recv_fd != fd)
+ error(1, 0, "received on an unexpected socket");
+
+ close(send_fd);
+ close(epfd);
+}
+
+
+static void run_one_test(int fam_send, int fam_rcv, int proto,
+ const char *addr_str)
+{
+ /* Below we test that a socket listening on a specific address
+ * is always selected in preference over a socket listening
+ * on addr_any. Bugs where this is not the case often result
+ * in sockets created first or last to get picked. So below
+ * we make sure that there are always addr_any sockets created
+ * before and after a specific socket is created.
+ */
+ int rcv_fds[10], i;
+
+ build_rcv_fd(AF_INET, proto, rcv_fds, 2, NULL);
+ build_rcv_fd(AF_INET6, proto, rcv_fds + 2, 2, NULL);
+ build_rcv_fd(fam_rcv, proto, rcv_fds + 4, 1, addr_str);
+ build_rcv_fd(AF_INET, proto, rcv_fds + 5, 2, NULL);
+ build_rcv_fd(AF_INET6, proto, rcv_fds + 7, 2, NULL);
+ test(rcv_fds, 9, fam_send, proto, rcv_fds[4]);
+ for (i = 0; i < 9; ++i)
+ close(rcv_fds[i]);
+ fprintf(stderr, "pass\n");
+}
+
+static void test_proto(int proto, const char *proto_str)
+{
+ if (proto == SOCK_DCCP) {
+ int test_fd;
+
+ test_fd = socket(AF_INET, proto, 0);
+ if (test_fd < 0) {
+ if (errno == ESOCKTNOSUPPORT) {
+ fprintf(stderr, "DCCP not supported: skipping DCCP tests\n");
+ return;
+ } else
+ error(1, errno, "failed to create a DCCP socket");
+ }
+ close(test_fd);
+ }
+
+ fprintf(stderr, "%s IPv4 ... ", proto_str);
+ run_one_test(AF_INET, AF_INET, proto, IP4_ADDR);
+
+ fprintf(stderr, "%s IPv6 ... ", proto_str);
+ run_one_test(AF_INET6, AF_INET6, proto, IP6_ADDR);
+
+ fprintf(stderr, "%s IPv4 mapped to IPv6 ... ", proto_str);
+ run_one_test(AF_INET, AF_INET6, proto, IP4_MAPPED6);
+}
+
+int main(void)
+{
+ test_proto(SOCK_DGRAM, "UDP");
+ test_proto(SOCK_STREAM, "TCP");
+ test_proto(SOCK_DCCP, "DCCP");
+
+ fprintf(stderr, "SUCCESS\n");
+ return 0;
+}
diff --git a/tools/testing/selftests/net/reuseport_addr_any.sh b/tools/testing/selftests/net/reuseport_addr_any.sh
new file mode 100755
index 000000000000..104592f62ad4
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_addr_any.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+./in_netns.sh ./reuseport_addr_any
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index e101af52d1d6..78fc593dfe40 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -205,6 +205,8 @@ kci_test_polrouting()
kci_test_route_get()
{
+ local hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy)
+
ret=0
ip route get 127.0.0.1 > /dev/null
@@ -223,6 +225,19 @@ kci_test_route_get()
check_err $?
ip route get 10.23.7.11 from 10.23.7.12 iif "$devdummy" > /dev/null
check_err $?
+ ip route add 10.23.8.0/24 \
+ nexthop via 10.23.7.13 dev "$devdummy" \
+ nexthop via 10.23.7.14 dev "$devdummy"
+ check_err $?
+ sysctl -wq net.ipv4.fib_multipath_hash_policy=0
+ ip route get 10.23.8.11 > /dev/null
+ check_err $?
+ sysctl -wq net.ipv4.fib_multipath_hash_policy=1
+ ip route get 10.23.8.11 > /dev/null
+ check_err $?
+ sysctl -wq net.ipv4.fib_multipath_hash_policy="$hash_policy"
+ ip route del 10.23.8.0/24
+ check_err $?
ip addr del dev "$devdummy" 10.23.7.11/24
check_err $?
@@ -955,6 +970,111 @@ kci_test_ip6erspan()
ip netns del "$testns"
}
+kci_test_fdb_get()
+{
+ IP="ip -netns testns"
+ BRIDGE="bridge -netns testns"
+ brdev="test-br0"
+ vxlandev="vxlan10"
+ test_mac=de:ad:be:ef:13:37
+ localip="10.0.2.2"
+ dstip="10.0.2.3"
+ ret=0
+
+ bridge fdb help 2>&1 |grep -q 'bridge fdb get'
+ if [ $? -ne 0 ];then
+ echo "SKIP: fdb get tests: iproute2 too old"
+ return $ksft_skip
+ fi
+
+ ip netns add testns
+ if [ $? -ne 0 ]; then
+ echo "SKIP fdb get tests: cannot add net namespace $testns"
+ return $ksft_skip
+ fi
+
+ $IP link add "$vxlandev" type vxlan id 10 local $localip \
+ dstport 4789 2>/dev/null
+ check_err $?
+ $IP link add name "$brdev" type bridge &>/dev/null
+ check_err $?
+ $IP link set dev "$vxlandev" master "$brdev" &>/dev/null
+ check_err $?
+ $BRIDGE fdb add $test_mac dev "$vxlandev" master &>/dev/null
+ check_err $?
+ $BRIDGE fdb add $test_mac dev "$vxlandev" dst $dstip self &>/dev/null
+ check_err $?
+
+ $BRIDGE fdb get $test_mac brport "$vxlandev" 2>/dev/null | grep -q "dev $vxlandev master $brdev"
+ check_err $?
+ $BRIDGE fdb get $test_mac br "$brdev" 2>/dev/null | grep -q "dev $vxlandev master $brdev"
+ check_err $?
+ $BRIDGE fdb get $test_mac dev "$vxlandev" self 2>/dev/null | grep -q "dev $vxlandev dst $dstip"
+ check_err $?
+
+ ip netns del testns &>/dev/null
+
+ if [ $ret -ne 0 ]; then
+ echo "FAIL: bridge fdb get"
+ return 1
+ fi
+
+ echo "PASS: bridge fdb get"
+}
+
+kci_test_neigh_get()
+{
+ dstmac=de:ad:be:ef:13:37
+ dstip=10.0.2.4
+ dstip6=dead::2
+ ret=0
+
+ ip neigh help 2>&1 |grep -q 'ip neigh get'
+ if [ $? -ne 0 ];then
+ echo "SKIP: fdb get tests: iproute2 too old"
+ return $ksft_skip
+ fi
+
+ # ipv4
+ ip neigh add $dstip lladdr $dstmac dev "$devdummy" > /dev/null
+ check_err $?
+ ip neigh get $dstip dev "$devdummy" 2> /dev/null | grep -q "$dstmac"
+ check_err $?
+ ip neigh del $dstip lladdr $dstmac dev "$devdummy" > /dev/null
+ check_err $?
+
+ # ipv4 proxy
+ ip neigh add proxy $dstip dev "$devdummy" > /dev/null
+ check_err $?
+ ip neigh get proxy $dstip dev "$devdummy" 2>/dev/null | grep -q "$dstip"
+ check_err $?
+ ip neigh del proxy $dstip dev "$devdummy" > /dev/null
+ check_err $?
+
+ # ipv6
+ ip neigh add $dstip6 lladdr $dstmac dev "$devdummy" > /dev/null
+ check_err $?
+ ip neigh get $dstip6 dev "$devdummy" 2> /dev/null | grep -q "$dstmac"
+ check_err $?
+ ip neigh del $dstip6 lladdr $dstmac dev "$devdummy" > /dev/null
+ check_err $?
+
+ # ipv6 proxy
+ ip neigh add proxy $dstip6 dev "$devdummy" > /dev/null
+ check_err $?
+ ip neigh get proxy $dstip6 dev "$devdummy" 2>/dev/null | grep -q "$dstip6"
+ check_err $?
+ ip neigh del proxy $dstip6 dev "$devdummy" > /dev/null
+ check_err $?
+
+ if [ $ret -ne 0 ];then
+ echo "FAIL: neigh get"
+ return 1
+ fi
+
+ echo "PASS: neigh get"
+}
+
kci_test_rtnl()
{
kci_add_dummy
@@ -979,6 +1099,8 @@ kci_test_rtnl()
kci_test_macsec
kci_test_ipsec
kci_test_ipsec_offload
+ kci_test_fdb_get
+ kci_test_neigh_get
kci_del_dummy
}
diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests
index bea079edc278..2dc95fda7ef7 100755
--- a/tools/testing/selftests/net/run_afpackettests
+++ b/tools/testing/selftests/net/run_afpackettests
@@ -25,3 +25,13 @@ if [ $? -ne 0 ]; then
else
echo "[PASS]"
fi
+
+echo "--------------------"
+echo "running txring_overwrite test"
+echo "--------------------"
+./in_netns.sh ./txring_overwrite
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+else
+ echo "[PASS]"
+fi
diff --git a/tools/testing/selftests/net/test_vxlan_under_vrf.sh b/tools/testing/selftests/net/test_vxlan_under_vrf.sh
new file mode 100755
index 000000000000..09f9ed92cbe4
--- /dev/null
+++ b/tools/testing/selftests/net/test_vxlan_under_vrf.sh
@@ -0,0 +1,129 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for checking VXLAN underlay in a non-default VRF.
+#
+# It simulates two hypervisors running a VM each using four network namespaces:
+# two for the HVs, two for the VMs.
+# A small VXLAN tunnel is made between the two hypervisors to have the two vms
+# in the same virtual L2:
+#
+# +-------------------+ +-------------------+
+# | | | |
+# | vm-1 netns | | vm-2 netns |
+# | | | |
+# | +-------------+ | | +-------------+ |
+# | | veth-hv | | | | veth-hv | |
+# | | 10.0.0.1/24 | | | | 10.0.0.2/24 | |
+# | +-------------+ | | +-------------+ |
+# | . | | . |
+# +-------------------+ +-------------------+
+# . .
+# . .
+# . .
+# +-----------------------------------+ +------------------------------------+
+# | . | | . |
+# | +----------+ | | +----------+ |
+# | | veth-tap | | | | veth-tap | |
+# | +----+-----+ | | +----+-----+ |
+# | | | | | |
+# | +--+--+ +--------------+ | | +--------------+ +--+--+ |
+# | | br0 | | vrf-underlay | | | | vrf-underlay | | br0 | |
+# | +--+--+ +-------+------+ | | +------+-------+ +--+--+ |
+# | | | | | | | |
+# | +---+----+ +-------+-------+ | | +-------+-------+ +---+----+ |
+# | | vxlan0 |....| veth0 |.|...|.| veth0 |....| vxlan0 | |
+# | +--------+ | 172.16.0.1/24 | | | | 172.16.0.2/24 | +--------+ |
+# | +---------------+ | | +---------------+ |
+# | | | |
+# | hv-1 netns | | hv-2 netns |
+# | | | |
+# +-----------------------------------+ +------------------------------------+
+#
+# This tests both the connectivity between vm-1 and vm-2, and that the underlay
+# can be moved in and out of the vrf by unsetting and setting veth0's master.
+
+set -e
+
+cleanup() {
+ ip link del veth-hv-1 2>/dev/null || true
+ ip link del veth-tap 2>/dev/null || true
+
+ for ns in hv-1 hv-2 vm-1 vm-2; do
+ ip netns del $ns || true
+ done
+}
+
+# Clean start
+cleanup &> /dev/null
+
+[[ $1 == "clean" ]] && exit 0
+
+trap cleanup EXIT
+
+# Setup "Hypervisors" simulated with netns
+ip link add veth-hv-1 type veth peer name veth-hv-2
+setup-hv-networking() {
+ hv=$1
+
+ ip netns add hv-$hv
+ ip link set veth-hv-$hv netns hv-$hv
+ ip -netns hv-$hv link set veth-hv-$hv name veth0
+
+ ip -netns hv-$hv link add vrf-underlay type vrf table 1
+ ip -netns hv-$hv link set vrf-underlay up
+ ip -netns hv-$hv addr add 172.16.0.$hv/24 dev veth0
+ ip -netns hv-$hv link set veth0 up
+
+ ip -netns hv-$hv link add br0 type bridge
+ ip -netns hv-$hv link set br0 up
+
+ ip -netns hv-$hv link add vxlan0 type vxlan id 10 local 172.16.0.$hv dev veth0 dstport 4789
+ ip -netns hv-$hv link set vxlan0 master br0
+ ip -netns hv-$hv link set vxlan0 up
+}
+setup-hv-networking 1
+setup-hv-networking 2
+
+# Check connectivity between HVs by pinging hv-2 from hv-1
+echo -n "Checking HV connectivity "
+ip netns exec hv-1 ping -c 1 -W 1 172.16.0.2 &> /dev/null || (echo "[FAIL]"; false)
+echo "[ OK ]"
+
+# Setups a "VM" simulated by a netns an a veth pair
+setup-vm() {
+ id=$1
+
+ ip netns add vm-$id
+ ip link add veth-tap type veth peer name veth-hv
+
+ ip link set veth-tap netns hv-$id
+ ip -netns hv-$id link set veth-tap master br0
+ ip -netns hv-$id link set veth-tap up
+
+ ip link set veth-hv netns vm-$id
+ ip -netns vm-$id addr add 10.0.0.$id/24 dev veth-hv
+ ip -netns vm-$id link set veth-hv up
+}
+setup-vm 1
+setup-vm 2
+
+# Setup VTEP routes to make ARP work
+bridge -netns hv-1 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.2 self permanent
+bridge -netns hv-2 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.1 self permanent
+
+echo -n "Check VM connectivity through VXLAN (underlay in the default VRF) "
+ip netns exec vm-1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false)
+echo "[ OK ]"
+
+# Move the underlay to a non-default VRF
+ip -netns hv-1 link set veth0 vrf vrf-underlay
+ip -netns hv-1 link set veth0 down
+ip -netns hv-1 link set veth0 up
+ip -netns hv-2 link set veth0 vrf vrf-underlay
+ip -netns hv-2 link set veth0 down
+ip -netns hv-2 link set veth0 up
+
+echo -n "Check VM connectivity through VXLAN (underlay in a VRF) "
+ip netns exec vm-1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false)
+echo "[ OK ]"
diff --git a/tools/testing/selftests/net/txring_overwrite.c b/tools/testing/selftests/net/txring_overwrite.c
new file mode 100644
index 000000000000..fd8b1c663c39
--- /dev/null
+++ b/tools/testing/selftests/net/txring_overwrite.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Verify that consecutive sends over packet tx_ring are mirrored
+ * with their original content intact.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <assert.h>
+#include <error.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/filter.h>
+#include <linux/if_packet.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <pthread.h>
+#include <sched.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+const int eth_off = TPACKET_HDRLEN - sizeof(struct sockaddr_ll);
+const int cfg_frame_size = 1000;
+
+static void build_packet(void *buffer, size_t blen, char payload_char)
+{
+ struct udphdr *udph;
+ struct ethhdr *eth;
+ struct iphdr *iph;
+ size_t off = 0;
+
+ memset(buffer, 0, blen);
+
+ eth = buffer;
+ eth->h_proto = htons(ETH_P_IP);
+
+ off += sizeof(*eth);
+ iph = buffer + off;
+ iph->ttl = 8;
+ iph->ihl = 5;
+ iph->version = 4;
+ iph->saddr = htonl(INADDR_LOOPBACK);
+ iph->daddr = htonl(INADDR_LOOPBACK + 1);
+ iph->protocol = IPPROTO_UDP;
+ iph->tot_len = htons(blen - off);
+ iph->check = 0;
+
+ off += sizeof(*iph);
+ udph = buffer + off;
+ udph->dest = htons(8000);
+ udph->source = htons(8001);
+ udph->len = htons(blen - off);
+ udph->check = 0;
+
+ off += sizeof(*udph);
+ memset(buffer + off, payload_char, blen - off);
+}
+
+static int setup_rx(void)
+{
+ int fdr;
+
+ fdr = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP));
+ if (fdr == -1)
+ error(1, errno, "socket r");
+
+ return fdr;
+}
+
+static int setup_tx(char **ring)
+{
+ struct sockaddr_ll laddr = {};
+ struct tpacket_req req = {};
+ int fdt;
+
+ fdt = socket(PF_PACKET, SOCK_RAW, 0);
+ if (fdt == -1)
+ error(1, errno, "socket t");
+
+ laddr.sll_family = AF_PACKET;
+ laddr.sll_protocol = htons(0);
+ laddr.sll_ifindex = if_nametoindex("lo");
+ if (!laddr.sll_ifindex)
+ error(1, errno, "if_nametoindex");
+
+ if (bind(fdt, (void *)&laddr, sizeof(laddr)))
+ error(1, errno, "bind fdt");
+
+ req.tp_block_size = getpagesize();
+ req.tp_block_nr = 1;
+ req.tp_frame_size = getpagesize();
+ req.tp_frame_nr = 1;
+
+ if (setsockopt(fdt, SOL_PACKET, PACKET_TX_RING,
+ (void *)&req, sizeof(req)))
+ error(1, errno, "setsockopt ring");
+
+ *ring = mmap(0, req.tp_block_size * req.tp_block_nr,
+ PROT_READ | PROT_WRITE, MAP_SHARED, fdt, 0);
+ if (!*ring)
+ error(1, errno, "mmap");
+
+ return fdt;
+}
+
+static void send_pkt(int fdt, void *slot, char payload_char)
+{
+ struct tpacket_hdr *header = slot;
+ int ret;
+
+ while (header->tp_status != TP_STATUS_AVAILABLE)
+ usleep(1000);
+
+ build_packet(slot + eth_off, cfg_frame_size, payload_char);
+
+ header->tp_len = cfg_frame_size;
+ header->tp_status = TP_STATUS_SEND_REQUEST;
+
+ ret = sendto(fdt, NULL, 0, 0, NULL, 0);
+ if (ret == -1)
+ error(1, errno, "kick tx");
+}
+
+static int read_verify_pkt(int fdr, char payload_char)
+{
+ char buf[100];
+ int ret;
+
+ ret = read(fdr, buf, sizeof(buf));
+ if (ret != sizeof(buf))
+ error(1, errno, "read");
+
+ if (buf[60] != payload_char) {
+ printf("wrong pattern: 0x%x != 0x%x\n", buf[60], payload_char);
+ return 1;
+ }
+
+ printf("read: %c (0x%x)\n", buf[60], buf[60]);
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ const char payload_patterns[] = "ab";
+ char *ring;
+ int fdr, fdt, ret = 0;
+
+ fdr = setup_rx();
+ fdt = setup_tx(&ring);
+
+ send_pkt(fdt, ring, payload_patterns[0]);
+ send_pkt(fdt, ring, payload_patterns[1]);
+
+ ret |= read_verify_pkt(fdr, payload_patterns[0]);
+ ret |= read_verify_pkt(fdr, payload_patterns[1]);
+
+ if (close(fdt))
+ error(1, errno, "close t");
+ if (close(fdr))
+ error(1, errno, "close r");
+
+ return ret;
+}
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
new file mode 100755
index 000000000000..aeac53a99aeb
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -0,0 +1,182 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro functional tests.
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+ local -r jobs="$(jobs -p)"
+ local -r ns="$(ip netns list|grep $PEER_NS)"
+
+ [ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+ [ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+cfg_veth() {
+ ip netns add "${PEER_NS}"
+ ip -netns "${PEER_NS}" link set lo up
+ ip link add type veth
+ ip link set dev veth0 up
+ ip addr add dev veth0 192.168.1.2/24
+ ip addr add dev veth0 2001:db8::2/64 nodad
+
+ ip link set dev veth1 netns "${PEER_NS}"
+ ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+ ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+ ip -netns "${PEER_NS}" link set dev veth1 up
+ ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+}
+
+run_one() {
+ # use 'rx' as separator between sender args and receiver args
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local -r rx_args=${all#*rx}
+
+ cfg_veth
+
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \
+ echo "ok" || \
+ echo "failed" &
+
+ # Hack: let bg programs complete the startup
+ sleep 0.1
+ ./udpgso_bench_tx ${tx_args}
+ wait $(jobs -p)
+}
+
+run_test() {
+ local -r args=$@
+
+ printf " %-40s" "$1"
+ ./in_netns.sh $0 __subprocess $2 rx -G -r $3
+}
+
+run_one_nat() {
+ # use 'rx' as separator between sender args and receiver args
+ local addr1 addr2 pid family="" ipt_cmd=ip6tables
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local -r rx_args=${all#*rx}
+
+ if [[ ${tx_args} = *-4* ]]; then
+ ipt_cmd=iptables
+ family=-4
+ addr1=192.168.1.1
+ addr2=192.168.1.3/24
+ else
+ addr1=2001:db8::1
+ addr2="2001:db8::3/64 nodad"
+ fi
+
+ cfg_veth
+ ip -netns "${PEER_NS}" addr add dev veth1 ${addr2}
+
+ # fool the GRO engine changing the destination address ...
+ ip netns exec "${PEER_NS}" $ipt_cmd -t nat -I PREROUTING -d ${addr1} -j DNAT --to-destination ${addr2%/*}
+
+ # ... so that GRO will match the UDP_GRO enabled socket, but packets
+ # will land on the 'plain' one
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
+ pid=$!
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${family} -b ${addr2%/*} ${rx_args} && \
+ echo "ok" || \
+ echo "failed"&
+
+ sleep 0.1
+ ./udpgso_bench_tx ${tx_args}
+ kill -INT $pid
+ wait $(jobs -p)
+}
+
+run_one_2sock() {
+ # use 'rx' as separator between sender args and receiver args
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local -r rx_args=${all#*rx}
+
+ cfg_veth
+
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -p 12345 &
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \
+ echo "ok" || \
+ echo "failed" &
+
+ # Hack: let bg programs complete the startup
+ sleep 0.1
+ ./udpgso_bench_tx ${tx_args} -p 12345
+ sleep 0.1
+ # first UDP GSO socket should be closed at this point
+ ./udpgso_bench_tx ${tx_args}
+ wait $(jobs -p)
+}
+
+run_nat_test() {
+ local -r args=$@
+
+ printf " %-40s" "$1"
+ ./in_netns.sh $0 __subprocess_nat $2 rx -r $3
+}
+
+run_2sock_test() {
+ local -r args=$@
+
+ printf " %-40s" "$1"
+ ./in_netns.sh $0 __subprocess_2sock $2 rx -G -r $3
+}
+
+run_all() {
+ local -r core_args="-l 4"
+ local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+ local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+ echo "ipv4"
+ run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400"
+
+ # explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1)
+ # when GRO does not take place
+ run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1"
+
+ # the GSO packets are aggregated because:
+ # * veth schedule napi after each xmit
+ # * segmentation happens in BH context, veth napi poll is delayed after
+ # the transmission of the last segment
+ run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720"
+ run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+ run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720"
+ run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
+
+ run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+ run_2sock_test "multiple GRO socks" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+
+ echo "ipv6"
+ run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
+ run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1"
+ run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520"
+ run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452"
+ run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520"
+ run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
+
+ run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+ run_2sock_test "multiple GRO socks" "${ipv6_args} -M 1 -s 14520 -S 0 " "-n 1 -l 14520 -S 1452"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+ echo "Missing xdp_dummy helper. Build bpf selftest first"
+ exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+ run_all
+elif [[ $1 == "__subprocess" ]]; then
+ shift
+ run_one $@
+elif [[ $1 == "__subprocess_nat" ]]; then
+ shift
+ run_one_nat $@
+elif [[ $1 == "__subprocess_2sock" ]]; then
+ shift
+ run_one_2sock $@
+fi
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
new file mode 100755
index 000000000000..820bc50f6b68
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -0,0 +1,95 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro benchmarks
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+ local -r jobs="$(jobs -p)"
+ local -r ns="$(ip netns list|grep $PEER_NS)"
+
+ [ -n "${jobs}" ] && kill -INT ${jobs} 2>/dev/null
+ [ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+run_one() {
+ # use 'rx' as separator between sender args and receiver args
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local rx_args=${all#*rx}
+
+ [[ "${tx_args}" == *"-4"* ]] && rx_args="${rx_args} -4"
+
+ ip netns add "${PEER_NS}"
+ ip -netns "${PEER_NS}" link set lo up
+ ip link add type veth
+ ip link set dev veth0 up
+ ip addr add dev veth0 192.168.1.2/24
+ ip addr add dev veth0 2001:db8::2/64 nodad
+
+ ip link set dev veth1 netns "${PEER_NS}"
+ ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+ ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+ ip -netns "${PEER_NS}" link set dev veth1 up
+
+ ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r &
+
+ # Hack: let bg programs complete the startup
+ sleep 0.1
+ ./udpgso_bench_tx ${tx_args}
+}
+
+run_in_netns() {
+ local -r args=$@
+
+ ./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+ local -r args=$@
+
+ echo "udp gso - over veth touching data"
+ run_in_netns ${args} -S 0 rx
+
+ echo "udp gso and gro - over veth touching data"
+ run_in_netns ${args} -S 0 rx -G
+}
+
+run_tcp() {
+ local -r args=$@
+
+ echo "tcp - over veth touching data"
+ run_in_netns ${args} -t rx
+}
+
+run_all() {
+ local -r core_args="-l 4"
+ local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+ local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+ echo "ipv4"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv4_args}"
+
+ echo "ipv6"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv6_args}"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+ echo "Missing xdp_dummy helper. Build bpf selftest first"
+ exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+ run_all
+elif [[ $1 == "__subprocess" ]]; then
+ shift
+ run_one $@
+else
+ run_in_netns $@
+fi
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 99e537ab5ad9..5670a9ffd8eb 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -34,7 +34,10 @@ run_udp() {
run_in_netns ${args}
echo "udp gso"
- run_in_netns ${args} -S
+ run_in_netns ${args} -S 0
+
+ echo "udp gso zerocopy"
+ run_in_netns ${args} -S 0 -z
}
run_tcp() {
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 727cf67a3f75..0c960f673324 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -31,9 +31,21 @@
#include <sys/wait.h>
#include <unistd.h>
+#ifndef UDP_GRO
+#define UDP_GRO 104
+#endif
+
static int cfg_port = 8000;
static bool cfg_tcp;
static bool cfg_verify;
+static bool cfg_read_all;
+static bool cfg_gro_segment;
+static int cfg_family = PF_INET6;
+static int cfg_alen = sizeof(struct sockaddr_in6);
+static int cfg_expected_pkt_nr;
+static int cfg_expected_pkt_len;
+static int cfg_expected_gso_size;
+static struct sockaddr_storage cfg_bind_addr;
static bool interrupted;
static unsigned long packets, bytes;
@@ -44,6 +56,29 @@ static void sigint_handler(int signum)
interrupted = true;
}
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+ struct sockaddr_in6 *addr6 = (void *) sockaddr;
+ struct sockaddr_in *addr4 = (void *) sockaddr;
+
+ switch (domain) {
+ case PF_INET:
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = htons(cfg_port);
+ if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+ error(1, 0, "ipv4 parse error: %s", str_addr);
+ break;
+ case PF_INET6:
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+ error(1, 0, "ipv6 parse error: %s", str_addr);
+ break;
+ default:
+ error(1, 0, "illegal domain");
+ }
+}
+
static unsigned long gettimeofday_ms(void)
{
struct timeval tv;
@@ -63,6 +98,8 @@ static void do_poll(int fd)
do {
ret = poll(&pfd, 1, 10);
+ if (interrupted)
+ break;
if (ret == -1)
error(1, errno, "poll");
if (ret == 0)
@@ -70,15 +107,14 @@ static void do_poll(int fd)
if (pfd.revents != POLLIN)
error(1, errno, "poll: 0x%x expected 0x%x\n",
pfd.revents, POLLIN);
- } while (!ret && !interrupted);
+ } while (!ret);
}
static int do_socket(bool do_tcp)
{
- struct sockaddr_in6 addr = {0};
int fd, val;
- fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+ fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
if (fd == -1)
error(1, errno, "socket");
@@ -89,10 +125,7 @@ static int do_socket(bool do_tcp)
if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val)))
error(1, errno, "setsockopt reuseport");
- addr.sin6_family = PF_INET6;
- addr.sin6_port = htons(cfg_port);
- addr.sin6_addr = in6addr_any;
- if (bind(fd, (void *) &addr, sizeof(addr)))
+ if (bind(fd, (void *)&cfg_bind_addr, cfg_alen))
error(1, errno, "bind");
if (do_tcp) {
@@ -102,6 +135,8 @@ static int do_socket(bool do_tcp)
error(1, errno, "listen");
do_poll(accept_fd);
+ if (interrupted)
+ exit(0);
fd = accept(accept_fd, NULL, NULL);
if (fd == -1)
@@ -164,51 +199,123 @@ static void do_verify_udp(const char *data, int len)
}
}
+static int recv_msg(int fd, char *buf, int len, int *gso_size)
+{
+ char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ struct cmsghdr *cmsg;
+ uint16_t *gsosizeptr;
+ int ret;
+
+ iov.iov_base = buf;
+ iov.iov_len = len;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+
+ *gso_size = -1;
+ ret = recvmsg(fd, &msg, MSG_TRUNC | MSG_DONTWAIT);
+ if (ret != -1) {
+ for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL;
+ cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+ if (cmsg->cmsg_level == SOL_UDP
+ && cmsg->cmsg_type == UDP_GRO) {
+ gsosizeptr = (uint16_t *) CMSG_DATA(cmsg);
+ *gso_size = *gsosizeptr;
+ break;
+ }
+ }
+ }
+ return ret;
+}
+
/* Flush all outstanding datagrams. Verify first few bytes of each. */
static void do_flush_udp(int fd)
{
- static char rbuf[ETH_DATA_LEN];
- int ret, len, budget = 256;
+ static char rbuf[ETH_MAX_MTU];
+ int ret, len, gso_size, budget = 256;
- len = cfg_verify ? sizeof(rbuf) : 0;
+ len = cfg_read_all ? sizeof(rbuf) : 0;
while (budget--) {
/* MSG_TRUNC will make return value full datagram length */
- ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+ if (!cfg_expected_gso_size)
+ ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+ else
+ ret = recv_msg(fd, rbuf, len, &gso_size);
if (ret == -1 && errno == EAGAIN)
- return;
+ break;
if (ret == -1)
error(1, errno, "recv");
- if (len) {
+ if (cfg_expected_pkt_len && ret != cfg_expected_pkt_len)
+ error(1, 0, "recv: bad packet len, got %d,"
+ " expected %d\n", ret, cfg_expected_pkt_len);
+ if (len && cfg_verify) {
if (ret == 0)
error(1, errno, "recv: 0 byte datagram\n");
do_verify_udp(rbuf, ret);
}
+ if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size)
+ error(1, 0, "recv: bad gso size, got %d, expected %d "
+ "(-1 == no gso cmsg))\n", gso_size,
+ cfg_expected_gso_size);
packets++;
bytes += ret;
+ if (cfg_expected_pkt_nr && packets >= cfg_expected_pkt_nr)
+ break;
}
}
static void usage(const char *filepath)
{
- error(1, 0, "Usage: %s [-tv] [-p port]", filepath);
+ error(1, 0, "Usage: %s [-Grtv] [-b addr] [-p port] [-l pktlen] [-n packetnr] [-S gsosize]", filepath);
}
static void parse_opts(int argc, char **argv)
{
int c;
- while ((c = getopt(argc, argv, "ptv")) != -1) {
+ /* bind to any by default */
+ setup_sockaddr(PF_INET6, "::", &cfg_bind_addr);
+ while ((c = getopt(argc, argv, "4b:Gl:n:p:rS:tv")) != -1) {
switch (c) {
+ case '4':
+ cfg_family = PF_INET;
+ cfg_alen = sizeof(struct sockaddr_in);
+ setup_sockaddr(PF_INET, "0.0.0.0", &cfg_bind_addr);
+ break;
+ case 'b':
+ setup_sockaddr(cfg_family, optarg, &cfg_bind_addr);
+ break;
+ case 'G':
+ cfg_gro_segment = true;
+ break;
+ case 'l':
+ cfg_expected_pkt_len = strtoul(optarg, NULL, 0);
+ break;
+ case 'n':
+ cfg_expected_pkt_nr = strtoul(optarg, NULL, 0);
+ break;
case 'p':
- cfg_port = htons(strtoul(optarg, NULL, 0));
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 'r':
+ cfg_read_all = true;
+ break;
+ case 'S':
+ cfg_expected_gso_size = strtol(optarg, NULL, 0);
break;
case 't':
cfg_tcp = true;
break;
case 'v':
cfg_verify = true;
+ cfg_read_all = true;
break;
}
}
@@ -223,12 +330,23 @@ static void parse_opts(int argc, char **argv)
static void do_recv(void)
{
unsigned long tnow, treport;
- int fd;
+ int fd, loop = 0;
fd = do_socket(cfg_tcp);
+ if (cfg_gro_segment && !cfg_tcp) {
+ int val = 1;
+ if (setsockopt(fd, IPPROTO_UDP, UDP_GRO, &val, sizeof(val)))
+ error(1, errno, "setsockopt UDP_GRO");
+ }
+
treport = gettimeofday_ms() + 1000;
do {
+ /* force termination after the second poll(); this cope both
+ * with sender slower than receiver and missing packet errors
+ */
+ if (cfg_expected_pkt_nr && loop++)
+ interrupted = true;
do_poll(fd);
if (cfg_tcp)
@@ -249,6 +367,10 @@ static void do_recv(void)
} while (!interrupted);
+ if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr))
+ error(1, 0, "wrong packet number! got %ld, expected %d\n",
+ packets, cfg_expected_pkt_nr);
+
if (close(fd))
error(1, errno, "close");
}
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index e821564053cf..4074538b5df5 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -52,6 +52,8 @@ static bool cfg_segment;
static bool cfg_sendmmsg;
static bool cfg_tcp;
static bool cfg_zerocopy;
+static int cfg_msg_nr;
+static uint16_t cfg_gso_size;
static socklen_t cfg_alen;
static struct sockaddr_storage cfg_dst_addr;
@@ -205,14 +207,14 @@ static void send_udp_segment_cmsg(struct cmsghdr *cm)
cm->cmsg_level = SOL_UDP;
cm->cmsg_type = UDP_SEGMENT;
- cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss));
+ cm->cmsg_len = CMSG_LEN(sizeof(cfg_gso_size));
valp = (void *)CMSG_DATA(cm);
- *valp = cfg_mss;
+ *valp = cfg_gso_size;
}
static int send_udp_segment(int fd, char *data)
{
- char control[CMSG_SPACE(sizeof(cfg_mss))] = {0};
+ char control[CMSG_SPACE(sizeof(cfg_gso_size))] = {0};
struct msghdr msg = {0};
struct iovec iov = {0};
int ret;
@@ -241,7 +243,7 @@ static int send_udp_segment(int fd, char *data)
static void usage(const char *filepath)
{
- error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]",
+ error(1, 0, "Usage: %s [-46cmtuz] [-C cpu] [-D dst ip] [-l secs] [-m messagenr] [-p port] [-s sendsize] [-S gsosize]",
filepath);
}
@@ -250,7 +252,7 @@ static void parse_opts(int argc, char **argv)
int max_len, hdrlen;
int c;
- while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) {
+ while ((c = getopt(argc, argv, "46cC:D:l:mM:p:s:S:tuz")) != -1) {
switch (c) {
case '4':
if (cfg_family != PF_UNSPEC)
@@ -279,6 +281,9 @@ static void parse_opts(int argc, char **argv)
case 'm':
cfg_sendmmsg = true;
break;
+ case 'M':
+ cfg_msg_nr = strtoul(optarg, NULL, 10);
+ break;
case 'p':
cfg_port = strtoul(optarg, NULL, 0);
break;
@@ -286,6 +291,7 @@ static void parse_opts(int argc, char **argv)
cfg_payload_len = strtoul(optarg, NULL, 0);
break;
case 'S':
+ cfg_gso_size = strtoul(optarg, NULL, 0);
cfg_segment = true;
break;
case 't':
@@ -317,6 +323,8 @@ static void parse_opts(int argc, char **argv)
cfg_mss = ETH_DATA_LEN - hdrlen;
max_len = ETH_MAX_MTU - hdrlen;
+ if (!cfg_gso_size)
+ cfg_gso_size = cfg_mss;
if (cfg_payload_len > max_len)
error(1, 0, "payload length %u exceeds max %u",
@@ -392,10 +400,12 @@ int main(int argc, char **argv)
else
num_sends += send_udp(fd, buf[i]);
num_msgs++;
-
if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
flush_zerocopy(fd);
+ if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
+ break;
+
tnow = gettimeofday_ms();
if (tnow > treport) {
fprintf(stderr,
diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh
new file mode 100755
index 000000000000..8db35b99457c
--- /dev/null
+++ b/tools/testing/selftests/net/xfrm_policy.sh
@@ -0,0 +1,302 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check xfrm policy resolution. Topology:
+#
+# 1.2 1.1 3.1 3.10 2.1 2.2
+# eth1 eth1 veth0 veth0 eth1 eth1
+# ns1 ---- ns3 ----- ns4 ---- ns2
+#
+# ns3 and ns4 are connected via ipsec tunnel.
+# pings from ns1 to ns2 (and vice versa) are supposed to work like this:
+# ns1: ping 10.0.2.2: passes via ipsec tunnel.
+# ns2: ping 10.0.1.2: passes via ipsec tunnel.
+
+# ns1: ping 10.0.1.253: passes via ipsec tunnel (direct policy)
+# ns2: ping 10.0.2.253: passes via ipsec tunnel (direct policy)
+#
+# ns1: ping 10.0.2.254: does NOT pass via ipsec tunnel (exception)
+# ns2: ping 10.0.1.254: does NOT pass via ipsec tunnel (exception)
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+policy_checks_ok=1
+
+KEY_SHA=0xdeadbeef1234567890abcdefabcdefabcdefabcd
+KEY_AES=0x0123456789abcdef0123456789012345
+SPI1=0x1
+SPI2=0x2
+
+do_esp() {
+ local ns=$1
+ local me=$2
+ local remote=$3
+ local lnet=$4
+ local rnet=$5
+ local spi_out=$6
+ local spi_in=$7
+
+ ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet
+ ip -net $ns xfrm state add src $me dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet
+
+ # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
+ ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow
+ # to fwd decrypted packets after esp processing:
+ ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow
+}
+
+do_esp_policy_get_check() {
+ local ns=$1
+ local lnet=$2
+ local rnet=$3
+
+ ip -net $ns xfrm policy get src $lnet dst $rnet dir out > /dev/null
+ if [ $? -ne 0 ] && [ $policy_checks_ok -eq 1 ] ;then
+ policy_checks_ok=0
+ echo "FAIL: ip -net $ns xfrm policy get src $lnet dst $rnet dir out"
+ ret=1
+ fi
+
+ ip -net $ns xfrm policy get src $rnet dst $lnet dir fwd > /dev/null
+ if [ $? -ne 0 ] && [ $policy_checks_ok -eq 1 ] ;then
+ policy_checks_ok=0
+ echo "FAIL: ip -net $ns xfrm policy get src $rnet dst $lnet dir fwd"
+ ret=1
+ fi
+}
+
+do_exception() {
+ local ns=$1
+ local me=$2
+ local remote=$3
+ local encryptip=$4
+ local plain=$5
+
+ # network $plain passes without tunnel
+ ip -net $ns xfrm policy add dst $plain dir out priority 10 action allow
+
+ # direct policy for $encryptip, use tunnel, higher prio takes precedence
+ ip -net $ns xfrm policy add dst $encryptip dir out tmpl src $me dst $remote proto esp mode tunnel priority 1 action allow
+}
+
+# policies that are not supposed to match any packets generated in this test.
+do_dummies4() {
+ local ns=$1
+
+ for i in $(seq 10 16);do
+ # dummy policy with wildcard src/dst.
+ echo netns exec $ns ip xfrm policy add src 0.0.0.0/0 dst 10.$i.99.0/30 dir out action block
+ echo netns exec $ns ip xfrm policy add src 10.$i.99.0/30 dst 0.0.0.0/0 dir out action block
+ for j in $(seq 32 64);do
+ echo netns exec $ns ip xfrm policy add src 10.$i.1.0/30 dst 10.$i.$j.0/30 dir out action block
+ # silly, as it encompasses the one above too, but its allowed:
+ echo netns exec $ns ip xfrm policy add src 10.$i.1.0/29 dst 10.$i.$j.0/29 dir out action block
+ # and yet again, even more broad one.
+ echo netns exec $ns ip xfrm policy add src 10.$i.1.0/24 dst 10.$i.$j.0/24 dir out action block
+ echo netns exec $ns ip xfrm policy add src 10.$i.$j.0/24 dst 10.$i.1.0/24 dir fwd action block
+ done
+ done | ip -batch /dev/stdin
+}
+
+do_dummies6() {
+ local ns=$1
+
+ for i in $(seq 10 16);do
+ for j in $(seq 32 64);do
+ echo netns exec $ns ip xfrm policy add src dead:$i::/64 dst dead:$i:$j::/64 dir out action block
+ echo netns exec $ns ip xfrm policy add src dead:$i:$j::/64 dst dead:$i::/24 dir fwd action block
+ done
+ done | ip -batch /dev/stdin
+}
+
+check_ipt_policy_count()
+{
+ ns=$1
+
+ ip netns exec $ns iptables-save -c |grep policy | ( read c rest
+ ip netns exec $ns iptables -Z
+ if [ x"$c" = x'[0:0]' ]; then
+ exit 0
+ elif [ x"$c" = x ]; then
+ echo "ERROR: No counters"
+ ret=1
+ exit 111
+ else
+ exit 1
+ fi
+ )
+}
+
+check_xfrm() {
+ # 0: iptables -m policy rule count == 0
+ # 1: iptables -m policy rule count != 0
+ rval=$1
+ ip=$2
+ lret=0
+
+ ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null
+
+ check_ipt_policy_count ns3
+ if [ $? -ne $rval ] ; then
+ lret=1
+ fi
+ check_ipt_policy_count ns4
+ if [ $? -ne $rval ] ; then
+ lret=1
+ fi
+
+ ip netns exec ns2 ping -q -c 1 10.0.1.$ip > /dev/null
+
+ check_ipt_policy_count ns3
+ if [ $? -ne $rval ] ; then
+ lret=1
+ fi
+ check_ipt_policy_count ns4
+ if [ $? -ne $rval ] ; then
+ lret=1
+ fi
+
+ return $lret
+}
+
+#check for needed privileges
+if [ "$(id -u)" -ne 0 ];then
+ echo "SKIP: Need root privileges"
+ exit $ksft_skip
+fi
+
+ip -Version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without the ip tool"
+ exit $ksft_skip
+fi
+
+# needed to check if policy lookup got valid ipsec result
+iptables --version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without iptables tool"
+ exit $ksft_skip
+fi
+
+for i in 1 2 3 4; do
+ ip netns add ns$i
+ ip -net ns$i link set lo up
+done
+
+DEV=veth0
+ip link add $DEV netns ns1 type veth peer name eth1 netns ns3
+ip link add $DEV netns ns2 type veth peer name eth1 netns ns4
+
+ip link add $DEV netns ns3 type veth peer name veth0 netns ns4
+
+DEV=veth0
+for i in 1 2; do
+ ip -net ns$i link set $DEV up
+ ip -net ns$i addr add 10.0.$i.2/24 dev $DEV
+ ip -net ns$i addr add dead:$i::2/64 dev $DEV
+
+ ip -net ns$i addr add 10.0.$i.253 dev $DEV
+ ip -net ns$i addr add 10.0.$i.254 dev $DEV
+ ip -net ns$i addr add dead:$i::fd dev $DEV
+ ip -net ns$i addr add dead:$i::fe dev $DEV
+done
+
+for i in 3 4; do
+ip -net ns$i link set eth1 up
+ip -net ns$i link set veth0 up
+done
+
+ip -net ns1 route add default via 10.0.1.1
+ip -net ns2 route add default via 10.0.2.1
+
+ip -net ns3 addr add 10.0.1.1/24 dev eth1
+ip -net ns3 addr add 10.0.3.1/24 dev veth0
+ip -net ns3 addr add 2001:1::1/64 dev eth1
+ip -net ns3 addr add 2001:3::1/64 dev veth0
+
+ip -net ns3 route add default via 10.0.3.10
+
+ip -net ns4 addr add 10.0.2.1/24 dev eth1
+ip -net ns4 addr add 10.0.3.10/24 dev veth0
+ip -net ns4 addr add 2001:2::1/64 dev eth1
+ip -net ns4 addr add 2001:3::10/64 dev veth0
+ip -net ns4 route add default via 10.0.3.1
+
+for j in 4 6; do
+ for i in 3 4;do
+ ip netns exec ns$i sysctl net.ipv$j.conf.eth1.forwarding=1 > /dev/null
+ ip netns exec ns$i sysctl net.ipv$j.conf.veth0.forwarding=1 > /dev/null
+ done
+done
+
+# abuse iptables rule counter to check if ping matches a policy
+ip netns exec ns3 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
+ip netns exec ns4 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not insert iptables rule"
+ for i in 1 2 3 4;do ip netns del ns$i;done
+ exit $ksft_skip
+fi
+
+# localip remoteip localnet remotenet
+do_esp ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+do_esp ns3 dead:3::1 dead:3::10 dead:1::/64 dead:2::/64 $SPI1 $SPI2
+do_esp ns4 10.0.3.10 10.0.3.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+do_esp ns4 dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1
+
+do_dummies4 ns3
+do_dummies6 ns4
+
+do_esp_policy_get_check ns3 10.0.1.0/24 10.0.2.0/24
+do_esp_policy_get_check ns4 10.0.2.0/24 10.0.1.0/24
+do_esp_policy_get_check ns3 dead:1::/64 dead:2::/64
+do_esp_policy_get_check ns4 dead:2::/64 dead:1::/64
+
+# ping to .254 should use ipsec, exception is not installed.
+check_xfrm 1 254
+if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .254 to use ipsec tunnel"
+ ret=1
+else
+ echo "PASS: policy before exception matches"
+fi
+
+# installs exceptions
+# localip remoteip encryptdst plaindst
+do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
+do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28
+
+do_exception ns3 dead:3::1 dead:3::10 dead:2::fd dead:2:f0::/96
+do_exception ns4 dead:3::10 dead:3::1 dead:1::fd dead:1:f0::/96
+
+# ping to .254 should now be excluded from the tunnel
+check_xfrm 0 254
+if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .254 to fail"
+ ret=1
+else
+ echo "PASS: ping to .254 bypassed ipsec tunnel"
+fi
+
+# ping to .253 should use use ipsec due to direct policy exception.
+check_xfrm 1 253
+if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .253 to use ipsec tunnel"
+ ret=1
+else
+ echo "PASS: direct policy matches"
+fi
+
+# ping to .2 should use ipsec.
+check_xfrm 1 2
+if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .2 to use ipsec tunnel"
+ ret=1
+else
+ echo "PASS: policy matches"
+fi
+
+for i in 1 2 3 4;do ip netns del ns$i;done
+
+exit $ret
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
index c46c0eefab9e..9050eeea5f5f 100644
--- a/tools/testing/selftests/networking/timestamping/Makefile
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -1,7 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -I../../../../../usr/include
-TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp
+TEST_GEN_FILES := hwtstamp_config rxtimestamp timestamping txtimestamp
+TEST_PROGS := txtimestamp.sh
all: $(TEST_PROGS)
@@ -10,4 +11,4 @@ KSFT_KHDR_INSTALL := 1
include ../../lib.mk
clean:
- rm -fr $(TEST_PROGS)
+ rm -fr $(TEST_GEN_FILES)
diff --git a/tools/testing/selftests/networking/timestamping/config b/tools/testing/selftests/networking/timestamping/config
new file mode 100644
index 000000000000..a13e3169b0a4
--- /dev/null
+++ b/tools/testing/selftests/networking/timestamping/config
@@ -0,0 +1,2 @@
+CONFIG_IFB=y
+CONFIG_NET_SCH_NETEM=y
diff --git a/tools/testing/selftests/networking/timestamping/txtimestamp.c b/tools/testing/selftests/networking/timestamping/txtimestamp.c
index 81a98a240456..2e563d17cf0c 100644
--- a/tools/testing/selftests/networking/timestamping/txtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/txtimestamp.c
@@ -39,6 +39,7 @@
#include <inttypes.h>
#include <linux/errqueue.h>
#include <linux/if_ether.h>
+#include <linux/ipv6.h>
#include <linux/net_tstamp.h>
#include <netdb.h>
#include <net/if.h>
@@ -69,15 +70,67 @@ static int do_ipv4 = 1;
static int do_ipv6 = 1;
static int cfg_payload_len = 10;
static int cfg_poll_timeout = 100;
+static int cfg_delay_snd;
+static int cfg_delay_ack;
static bool cfg_show_payload;
static bool cfg_do_pktinfo;
static bool cfg_loop_nodata;
static bool cfg_no_delay;
+static bool cfg_use_cmsg;
+static bool cfg_use_pf_packet;
+static bool cfg_do_listen;
static uint16_t dest_port = 9000;
static struct sockaddr_in daddr;
static struct sockaddr_in6 daddr6;
-static struct timespec ts_prev;
+static struct timespec ts_usr;
+
+static int saved_tskey = -1;
+static int saved_tskey_type = -1;
+
+static bool test_failed;
+
+static int64_t timespec_to_us64(struct timespec *ts)
+{
+ return ts->tv_sec * 1000 * 1000 + ts->tv_nsec / 1000;
+}
+
+static void validate_key(int tskey, int tstype)
+{
+ int stepsize;
+
+ /* compare key for each subsequent request
+ * must only test for one type, the first one requested
+ */
+ if (saved_tskey == -1)
+ saved_tskey_type = tstype;
+ else if (saved_tskey_type != tstype)
+ return;
+
+ stepsize = cfg_proto == SOCK_STREAM ? cfg_payload_len : 1;
+ if (tskey != saved_tskey + stepsize) {
+ fprintf(stderr, "ERROR: key %d, expected %d\n",
+ tskey, saved_tskey + stepsize);
+ test_failed = true;
+ }
+
+ saved_tskey = tskey;
+}
+
+static void validate_timestamp(struct timespec *cur, int min_delay)
+{
+ int max_delay = min_delay + 500 /* processing time upper bound */;
+ int64_t cur64, start64;
+
+ cur64 = timespec_to_us64(cur);
+ start64 = timespec_to_us64(&ts_usr);
+
+ if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) {
+ fprintf(stderr, "ERROR: delay %lu expected between %d and %d\n",
+ cur64 - start64, min_delay, max_delay);
+ test_failed = true;
+ }
+}
static void __print_timestamp(const char *name, struct timespec *cur,
uint32_t key, int payload_len)
@@ -89,32 +142,19 @@ static void __print_timestamp(const char *name, struct timespec *cur,
name, cur->tv_sec, cur->tv_nsec / 1000,
key, payload_len);
- if ((ts_prev.tv_sec | ts_prev.tv_nsec)) {
- int64_t cur_ms, prev_ms;
-
- cur_ms = (long) cur->tv_sec * 1000 * 1000;
- cur_ms += cur->tv_nsec / 1000;
-
- prev_ms = (long) ts_prev.tv_sec * 1000 * 1000;
- prev_ms += ts_prev.tv_nsec / 1000;
-
- fprintf(stderr, " (%+" PRId64 " us)", cur_ms - prev_ms);
- }
+ if (cur != &ts_usr)
+ fprintf(stderr, " (USR %+" PRId64 " us)",
+ timespec_to_us64(cur) - timespec_to_us64(&ts_usr));
- ts_prev = *cur;
fprintf(stderr, "\n");
}
static void print_timestamp_usr(void)
{
- struct timespec ts;
- struct timeval tv; /* avoid dependency on -lrt */
-
- gettimeofday(&tv, NULL);
- ts.tv_sec = tv.tv_sec;
- ts.tv_nsec = tv.tv_usec * 1000;
+ if (clock_gettime(CLOCK_REALTIME, &ts_usr))
+ error(1, errno, "clock_gettime");
- __print_timestamp(" USR", &ts, 0, 0);
+ __print_timestamp(" USR", &ts_usr, 0, 0);
}
static void print_timestamp(struct scm_timestamping *tss, int tstype,
@@ -122,15 +162,20 @@ static void print_timestamp(struct scm_timestamping *tss, int tstype,
{
const char *tsname;
+ validate_key(tskey, tstype);
+
switch (tstype) {
case SCM_TSTAMP_SCHED:
tsname = " ENQ";
+ validate_timestamp(&tss->ts[0], 0);
break;
case SCM_TSTAMP_SND:
tsname = " SND";
+ validate_timestamp(&tss->ts[0], cfg_delay_snd);
break;
case SCM_TSTAMP_ACK:
tsname = " ACK";
+ validate_timestamp(&tss->ts[0], cfg_delay_ack);
break;
default:
error(1, 0, "unknown timestamp type: %u",
@@ -194,7 +239,9 @@ static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len)
} else if ((cm->cmsg_level == SOL_IP &&
cm->cmsg_type == IP_RECVERR) ||
(cm->cmsg_level == SOL_IPV6 &&
- cm->cmsg_type == IPV6_RECVERR)) {
+ cm->cmsg_type == IPV6_RECVERR) ||
+ (cm->cmsg_level = SOL_PACKET &&
+ cm->cmsg_type == PACKET_TX_TIMESTAMP)) {
serr = (void *) CMSG_DATA(cm);
if (serr->ee_errno != ENOMSG ||
serr->ee_origin != SO_EE_ORIGIN_TIMESTAMPING) {
@@ -269,32 +316,124 @@ static int recv_errmsg(int fd)
return ret == -1;
}
-static void do_test(int family, unsigned int opt)
+static uint16_t get_ip_csum(const uint16_t *start, int num_words,
+ unsigned long sum)
+{
+ int i;
+
+ for (i = 0; i < num_words; i++)
+ sum += start[i];
+
+ while (sum >> 16)
+ sum = (sum & 0xFFFF) + (sum >> 16);
+
+ return ~sum;
+}
+
+static uint16_t get_udp_csum(const struct udphdr *udph, int alen)
+{
+ unsigned long pseudo_sum, csum_len;
+ const void *csum_start = udph;
+
+ pseudo_sum = htons(IPPROTO_UDP);
+ pseudo_sum += udph->len;
+
+ /* checksum ip(v6) addresses + udp header + payload */
+ csum_start -= alen * 2;
+ csum_len = ntohs(udph->len) + alen * 2;
+
+ return get_ip_csum(csum_start, csum_len >> 1, pseudo_sum);
+}
+
+static int fill_header_ipv4(void *p)
+{
+ struct iphdr *iph = p;
+
+ memset(iph, 0, sizeof(*iph));
+
+ iph->ihl = 5;
+ iph->version = 4;
+ iph->ttl = 2;
+ iph->saddr = daddr.sin_addr.s_addr; /* set for udp csum calc */
+ iph->daddr = daddr.sin_addr.s_addr;
+ iph->protocol = IPPROTO_UDP;
+
+ /* kernel writes saddr, csum, len */
+
+ return sizeof(*iph);
+}
+
+static int fill_header_ipv6(void *p)
+{
+ struct ipv6hdr *ip6h = p;
+
+ memset(ip6h, 0, sizeof(*ip6h));
+
+ ip6h->version = 6;
+ ip6h->payload_len = htons(sizeof(struct udphdr) + cfg_payload_len);
+ ip6h->nexthdr = IPPROTO_UDP;
+ ip6h->hop_limit = 64;
+
+ ip6h->saddr = daddr6.sin6_addr;
+ ip6h->daddr = daddr6.sin6_addr;
+
+ /* kernel does not write saddr in case of ipv6 */
+
+ return sizeof(*ip6h);
+}
+
+static void fill_header_udp(void *p, bool is_ipv4)
{
+ struct udphdr *udph = p;
+
+ udph->source = ntohs(dest_port + 1); /* spoof */
+ udph->dest = ntohs(dest_port);
+ udph->len = ntohs(sizeof(*udph) + cfg_payload_len);
+ udph->check = 0;
+
+ udph->check = get_udp_csum(udph, is_ipv4 ? sizeof(struct in_addr) :
+ sizeof(struct in6_addr));
+}
+
+static void do_test(int family, unsigned int report_opt)
+{
+ char control[CMSG_SPACE(sizeof(uint32_t))];
+ struct sockaddr_ll laddr;
+ unsigned int sock_opt;
+ struct cmsghdr *cmsg;
+ struct msghdr msg;
+ struct iovec iov;
char *buf;
int fd, i, val = 1, total_len;
- if (family == AF_INET6 && cfg_proto != SOCK_STREAM) {
- /* due to lack of checksum generation code */
- fprintf(stderr, "test: skipping datagram over IPv6\n");
- return;
- }
-
total_len = cfg_payload_len;
- if (cfg_proto == SOCK_RAW) {
+ if (cfg_use_pf_packet || cfg_proto == SOCK_RAW) {
total_len += sizeof(struct udphdr);
- if (cfg_ipproto == IPPROTO_RAW)
- total_len += sizeof(struct iphdr);
+ if (cfg_use_pf_packet || cfg_ipproto == IPPROTO_RAW)
+ if (family == PF_INET)
+ total_len += sizeof(struct iphdr);
+ else
+ total_len += sizeof(struct ipv6hdr);
+
+ /* special case, only rawv6_sendmsg:
+ * pass proto in sin6_port if not connected
+ * also see ANK comment in net/ipv4/raw.c
+ */
+ daddr6.sin6_port = htons(cfg_ipproto);
}
buf = malloc(total_len);
if (!buf)
error(1, 0, "malloc");
- fd = socket(family, cfg_proto, cfg_ipproto);
+ fd = socket(cfg_use_pf_packet ? PF_PACKET : family,
+ cfg_proto, cfg_ipproto);
if (fd < 0)
error(1, errno, "socket");
+ /* reset expected key on each new socket */
+ saved_tskey = -1;
+
if (cfg_proto == SOCK_STREAM) {
if (setsockopt(fd, IPPROTO_TCP, TCP_NODELAY,
(char*) &val, sizeof(val)))
@@ -321,54 +460,80 @@ static void do_test(int family, unsigned int opt)
}
}
- opt |= SOF_TIMESTAMPING_SOFTWARE |
- SOF_TIMESTAMPING_OPT_CMSG |
- SOF_TIMESTAMPING_OPT_ID;
+ sock_opt = SOF_TIMESTAMPING_SOFTWARE |
+ SOF_TIMESTAMPING_OPT_CMSG |
+ SOF_TIMESTAMPING_OPT_ID;
+
+ if (!cfg_use_cmsg)
+ sock_opt |= report_opt;
+
if (cfg_loop_nodata)
- opt |= SOF_TIMESTAMPING_OPT_TSONLY;
+ sock_opt |= SOF_TIMESTAMPING_OPT_TSONLY;
if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING,
- (char *) &opt, sizeof(opt)))
+ (char *) &sock_opt, sizeof(sock_opt)))
error(1, 0, "setsockopt timestamping");
for (i = 0; i < cfg_num_pkts; i++) {
- memset(&ts_prev, 0, sizeof(ts_prev));
+ memset(&msg, 0, sizeof(msg));
memset(buf, 'a' + i, total_len);
- if (cfg_proto == SOCK_RAW) {
- struct udphdr *udph;
+ if (cfg_use_pf_packet || cfg_proto == SOCK_RAW) {
int off = 0;
- if (cfg_ipproto == IPPROTO_RAW) {
- struct iphdr *iph = (void *) buf;
-
- memset(iph, 0, sizeof(*iph));
- iph->ihl = 5;
- iph->version = 4;
- iph->ttl = 2;
- iph->daddr = daddr.sin_addr.s_addr;
- iph->protocol = IPPROTO_UDP;
- /* kernel writes saddr, csum, len */
-
- off = sizeof(*iph);
+ if (cfg_use_pf_packet || cfg_ipproto == IPPROTO_RAW) {
+ if (family == PF_INET)
+ off = fill_header_ipv4(buf);
+ else
+ off = fill_header_ipv6(buf);
}
- udph = (void *) buf + off;
- udph->source = ntohs(9000); /* random spoof */
- udph->dest = ntohs(dest_port);
- udph->len = ntohs(sizeof(*udph) + cfg_payload_len);
- udph->check = 0; /* not allowed for IPv6 */
+ fill_header_udp(buf + off, family == PF_INET);
}
print_timestamp_usr();
+
+ iov.iov_base = buf;
+ iov.iov_len = total_len;
+
if (cfg_proto != SOCK_STREAM) {
- if (family == PF_INET)
- val = sendto(fd, buf, total_len, 0, (void *) &daddr, sizeof(daddr));
- else
- val = sendto(fd, buf, total_len, 0, (void *) &daddr6, sizeof(daddr6));
- } else {
- val = send(fd, buf, cfg_payload_len, 0);
+ if (cfg_use_pf_packet) {
+ memset(&laddr, 0, sizeof(laddr));
+
+ laddr.sll_family = AF_PACKET;
+ laddr.sll_ifindex = 1;
+ laddr.sll_protocol = htons(family == AF_INET ? ETH_P_IP : ETH_P_IPV6);
+ laddr.sll_halen = ETH_ALEN;
+
+ msg.msg_name = (void *)&laddr;
+ msg.msg_namelen = sizeof(laddr);
+ } else if (family == PF_INET) {
+ msg.msg_name = (void *)&daddr;
+ msg.msg_namelen = sizeof(daddr);
+ } else {
+ msg.msg_name = (void *)&daddr6;
+ msg.msg_namelen = sizeof(daddr6);
+ }
+ }
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ if (cfg_use_cmsg) {
+ memset(control, 0, sizeof(control));
+
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+
+ cmsg = CMSG_FIRSTHDR(&msg);
+ cmsg->cmsg_level = SOL_SOCKET;
+ cmsg->cmsg_type = SO_TIMESTAMPING;
+ cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t));
+
+ *((uint32_t *) CMSG_DATA(cmsg)) = report_opt;
}
+
+ val = sendmsg(fd, &msg, 0);
if (val != total_len)
error(1, errno, "send");
@@ -385,7 +550,7 @@ static void do_test(int family, unsigned int opt)
error(1, errno, "close");
free(buf);
- usleep(400 * 1000);
+ usleep(100 * 1000);
}
static void __attribute__((noreturn)) usage(const char *filepath)
@@ -396,15 +561,20 @@ static void __attribute__((noreturn)) usage(const char *filepath)
" -6: only IPv6\n"
" -h: show this message\n"
" -c N: number of packets for each test\n"
+ " -C: use cmsg to set tstamp recording options\n"
" -D: no delay between packets\n"
" -F: poll() waits forever for an event\n"
" -I: request PKTINFO\n"
" -l N: send N bytes at a time\n"
+ " -L listen on hostname and port\n"
" -n: set no-payload option\n"
+ " -p N: connect to port N\n"
+ " -P: use PF_PACKET\n"
" -r: use raw\n"
" -R: use raw (IP_HDRINCL)\n"
- " -p N: connect to port N\n"
" -u: use udp\n"
+ " -v: validate SND delay (usec)\n"
+ " -V: validate ACK delay (usec)\n"
" -x: show payload (up to 70 bytes)\n",
filepath);
exit(1);
@@ -413,9 +583,9 @@ static void __attribute__((noreturn)) usage(const char *filepath)
static void parse_opt(int argc, char **argv)
{
int proto_count = 0;
- char c;
+ int c;
- while ((c = getopt(argc, argv, "46c:DFhIl:np:rRux")) != -1) {
+ while ((c = getopt(argc, argv, "46c:CDFhIl:Lnp:PrRuv:V:x")) != -1) {
switch (c) {
case '4':
do_ipv6 = 0;
@@ -426,6 +596,9 @@ static void parse_opt(int argc, char **argv)
case 'c':
cfg_num_pkts = strtoul(optarg, NULL, 10);
break;
+ case 'C':
+ cfg_use_cmsg = true;
+ break;
case 'D':
cfg_no_delay = true;
break;
@@ -435,9 +608,24 @@ static void parse_opt(int argc, char **argv)
case 'I':
cfg_do_pktinfo = true;
break;
+ case 'l':
+ cfg_payload_len = strtoul(optarg, NULL, 10);
+ break;
+ case 'L':
+ cfg_do_listen = true;
+ break;
case 'n':
cfg_loop_nodata = true;
break;
+ case 'p':
+ dest_port = strtoul(optarg, NULL, 10);
+ break;
+ case 'P':
+ proto_count++;
+ cfg_use_pf_packet = true;
+ cfg_proto = SOCK_DGRAM;
+ cfg_ipproto = 0;
+ break;
case 'r':
proto_count++;
cfg_proto = SOCK_RAW;
@@ -453,11 +641,11 @@ static void parse_opt(int argc, char **argv)
cfg_proto = SOCK_DGRAM;
cfg_ipproto = IPPROTO_UDP;
break;
- case 'l':
- cfg_payload_len = strtoul(optarg, NULL, 10);
+ case 'v':
+ cfg_delay_snd = strtoul(optarg, NULL, 10);
break;
- case 'p':
- dest_port = strtoul(optarg, NULL, 10);
+ case 'V':
+ cfg_delay_ack = strtoul(optarg, NULL, 10);
break;
case 'x':
cfg_show_payload = true;
@@ -475,7 +663,9 @@ static void parse_opt(int argc, char **argv)
if (!do_ipv4 && !do_ipv6)
error(1, 0, "pass -4 or -6, not both");
if (proto_count > 1)
- error(1, 0, "pass -r, -R or -u, not multiple");
+ error(1, 0, "pass -P, -r, -R or -u, not multiple");
+ if (cfg_do_pktinfo && cfg_use_pf_packet)
+ error(1, 0, "cannot ask for pktinfo over pf_packet");
if (optind != argc - 1)
error(1, 0, "missing required hostname argument");
@@ -483,10 +673,12 @@ static void parse_opt(int argc, char **argv)
static void resolve_hostname(const char *hostname)
{
+ struct addrinfo hints = { .ai_family = do_ipv4 ? AF_INET : AF_INET6 };
struct addrinfo *addrs, *cur;
int have_ipv4 = 0, have_ipv6 = 0;
- if (getaddrinfo(hostname, NULL, NULL, &addrs))
+retry:
+ if (getaddrinfo(hostname, NULL, &hints, &addrs))
error(1, errno, "getaddrinfo");
cur = addrs;
@@ -506,14 +698,41 @@ static void resolve_hostname(const char *hostname)
if (addrs)
freeaddrinfo(addrs);
+ if (do_ipv6 && hints.ai_family != AF_INET6) {
+ hints.ai_family = AF_INET6;
+ goto retry;
+ }
+
do_ipv4 &= have_ipv4;
do_ipv6 &= have_ipv6;
}
+static void do_listen(int family, void *addr, int alen)
+{
+ int fd, type;
+
+ type = cfg_proto == SOCK_RAW ? SOCK_DGRAM : cfg_proto;
+
+ fd = socket(family, type, 0);
+ if (fd == -1)
+ error(1, errno, "socket rx");
+
+ if (bind(fd, addr, alen))
+ error(1, errno, "bind rx");
+
+ if (type == SOCK_STREAM && listen(fd, 10))
+ error(1, errno, "listen rx");
+
+ /* leave fd open, will be closed on process exit.
+ * this enables connect() to succeed and avoids icmp replies
+ */
+}
+
static void do_main(int family)
{
- fprintf(stderr, "family: %s\n",
- family == PF_INET ? "INET" : "INET6");
+ fprintf(stderr, "family: %s %s\n",
+ family == PF_INET ? "INET" : "INET6",
+ cfg_use_pf_packet ? "(PF_PACKET)" : "");
fprintf(stderr, "test SND\n");
do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE);
@@ -555,10 +774,17 @@ int main(int argc, char **argv)
fprintf(stderr, "server port: %u\n", dest_port);
fprintf(stderr, "\n");
- if (do_ipv4)
+ if (do_ipv4) {
+ if (cfg_do_listen)
+ do_listen(PF_INET, &daddr, sizeof(daddr));
do_main(PF_INET);
- if (do_ipv6)
+ }
+
+ if (do_ipv6) {
+ if (cfg_do_listen)
+ do_listen(PF_INET6, &daddr6, sizeof(daddr6));
do_main(PF_INET6);
+ }
- return 0;
+ return test_failed;
}
diff --git a/tools/testing/selftests/networking/timestamping/txtimestamp.sh b/tools/testing/selftests/networking/timestamping/txtimestamp.sh
new file mode 100755
index 000000000000..df0d86ca72b7
--- /dev/null
+++ b/tools/testing/selftests/networking/timestamping/txtimestamp.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Send packets with transmit timestamps over loopback with netem
+# Verify that timestamps correspond to netem delay
+
+set -e
+
+setup() {
+ # set 1ms delay on lo egress
+ tc qdisc add dev lo root netem delay 1ms
+
+ # set 2ms delay on ifb0 egress
+ modprobe ifb
+ ip link add ifb_netem0 type ifb
+ ip link set dev ifb_netem0 up
+ tc qdisc add dev ifb_netem0 root netem delay 2ms
+
+ # redirect lo ingress through ifb0 egress
+ tc qdisc add dev lo handle ffff: ingress
+ tc filter add dev lo parent ffff: \
+ u32 match mark 0 0xffff \
+ action mirred egress redirect dev ifb_netem0
+}
+
+run_test_v4v6() {
+ # SND will be delayed 1000us
+ # ACK will be delayed 6000us: 1 + 2 ms round-trip
+ local -r args="$@ -v 1000 -V 6000"
+
+ ./txtimestamp ${args} -4 -L 127.0.0.1
+ ./txtimestamp ${args} -6 -L ::1
+}
+
+run_test_tcpudpraw() {
+ local -r args=$@
+
+ run_test_v4v6 ${args} # tcp
+ run_test_v4v6 ${args} -u # udp
+ run_test_v4v6 ${args} -r # raw
+ run_test_v4v6 ${args} -R # raw (IPPROTO_RAW)
+ run_test_v4v6 ${args} -P # pf_packet
+}
+
+run_test_all() {
+ run_test_tcpudpraw # setsockopt
+ run_test_tcpudpraw -C # cmsg
+ run_test_tcpudpraw -n # timestamp w/o data
+}
+
+if [[ "$(ip netns identify)" == "root" ]]; then
+ ../../net/in_netns.sh $0 $@
+else
+ setup
+ run_test_all
+ echo "OK. All tests passed"
+fi
diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore
index 7a60b85e148f..c5cc160948b3 100644
--- a/tools/testing/selftests/tc-testing/.gitignore
+++ b/tools/testing/selftests/tc-testing/.gitignore
@@ -1,2 +1,5 @@
__pycache__/
*.pyc
+plugins/
+*.xml
+*.tap
diff --git a/tools/testing/selftests/tc-testing/TdcPlugin.py b/tools/testing/selftests/tc-testing/TdcPlugin.py
index 3ee9a6dacb52..1d9e279331eb 100644
--- a/tools/testing/selftests/tc-testing/TdcPlugin.py
+++ b/tools/testing/selftests/tc-testing/TdcPlugin.py
@@ -18,11 +18,12 @@ class TdcPlugin:
if self.args.verbose > 1:
print(' -- {}.post_suite'.format(self.sub_class))
- def pre_case(self, test_ordinal, testid):
+ def pre_case(self, test_ordinal, testid, test_name):
'''run commands before test_runner does one test'''
if self.args.verbose > 1:
print(' -- {}.pre_case'.format(self.sub_class))
self.args.testid = testid
+ self.args.test_name = test_name
self.args.test_ordinal = test_ordinal
def post_case(self):
diff --git a/tools/testing/selftests/tc-testing/TdcResults.py b/tools/testing/selftests/tc-testing/TdcResults.py
new file mode 100644
index 000000000000..1e4d95fdf8d0
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/TdcResults.py
@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+from enum import Enum
+
+class ResultState(Enum):
+ noresult = -1
+ skip = 0
+ success = 1
+ fail = 2
+
+class TestResult:
+ def __init__(self, test_id="", test_name=""):
+ self.test_id = test_id
+ self.test_name = test_name
+ self.result = ResultState.noresult
+ self.failmsg = ""
+ self.errormsg = ""
+ self.steps = []
+
+ def set_result(self, result):
+ if (isinstance(result, ResultState)):
+ self.result = result
+ return True
+ else:
+ raise TypeError('Unknown result type, must be type ResultState')
+
+ def get_result(self):
+ return self.result
+
+ def set_errormsg(self, errormsg):
+ self.errormsg = errormsg
+ return True
+
+ def append_errormsg(self, errormsg):
+ self.errormsg = '{}\n{}'.format(self.errormsg, errormsg)
+
+ def get_errormsg(self):
+ return self.errormsg
+
+ def set_failmsg(self, failmsg):
+ self.failmsg = failmsg
+ return True
+
+ def append_failmsg(self, failmsg):
+ self.failmsg = '{}\n{}'.format(self.failmsg, failmsg)
+
+ def get_failmsg(self):
+ return self.failmsg
+
+ def add_steps(self, newstep):
+ if type(newstep) == list:
+ self.steps.extend(newstep)
+ elif type(newstep) == str:
+ self.steps.append(step)
+ else:
+ raise TypeError('TdcResults.add_steps() requires a list or str')
+
+ def get_executed_steps(self):
+ return self.steps
+
+class TestSuiteReport():
+ _testsuite = []
+
+ def add_resultdata(self, result_data):
+ if isinstance(result_data, TestResult):
+ self._testsuite.append(result_data)
+ return True
+
+ def count_tests(self):
+ return len(self._testsuite)
+
+ def count_failures(self):
+ return sum(1 for t in self._testsuite if t.result == ResultState.fail)
+
+ def count_skips(self):
+ return sum(1 for t in self._testsuite if t.result == ResultState.skip)
+
+ def find_result(self, test_id):
+ return next((tr for tr in self._testsuite if tr.test_id == test_id), None)
+
+ def update_result(self, result_data):
+ orig = self.find_result(result_data.test_id)
+ if orig != None:
+ idx = self._testsuite.index(orig)
+ self._testsuite[idx] = result_data
+ else:
+ self.add_resultdata(result_data)
+
+ def format_tap(self):
+ ftap = ""
+ ftap += '1..{}\n'.format(self.count_tests())
+ index = 1
+ for t in self._testsuite:
+ if t.result == ResultState.fail:
+ ftap += 'not '
+ ftap += 'ok {} {} - {}'.format(str(index), t.test_id, t.test_name)
+ if t.result == ResultState.skip or t.result == ResultState.noresult:
+ ftap += ' # skipped - {}\n'.format(t.errormsg)
+ elif t.result == ResultState.fail:
+ if len(t.steps) > 0:
+ ftap += '\tCommands executed in this test case:'
+ for step in t.steps:
+ ftap += '\n\t\t{}'.format(step)
+ ftap += '\n\t{}'.format(t.failmsg)
+ ftap += '\n'
+ index += 1
+ return ftap
+
+ def format_xunit(self):
+ from xml.sax.saxutils import escape
+ xunit = "<testsuites>\n"
+ xunit += '\t<testsuite tests=\"{}\" skips=\"{}\">\n'.format(self.count_tests(), self.count_skips())
+ for t in self._testsuite:
+ xunit += '\t\t<testcase classname=\"{}\" '.format(escape(t.test_id))
+ xunit += 'name=\"{}\">\n'.format(escape(t.test_name))
+ if t.failmsg:
+ xunit += '\t\t\t<failure>\n'
+ if len(t.steps) > 0:
+ xunit += 'Commands executed in this test case:\n'
+ for step in t.steps:
+ xunit += '\t{}\n'.format(escape(step))
+ xunit += 'FAILURE: {}\n'.format(escape(t.failmsg))
+ xunit += '\t\t\t</failure>\n'
+ if t.errormsg:
+ xunit += '\t\t\t<error>\n{}\n'.format(escape(t.errormsg))
+ xunit += '\t\t\t</error>\n'
+ if t.result == ResultState.skip:
+ xunit += '\t\t\t<skipped/>\n'
+ xunit += '\t\t</testcase>\n'
+ xunit += '\t</testsuite>\n'
+ xunit += '</testsuites>\n'
+ return xunit
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
index 477a7bd7d7fb..e00c798de0bb 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
@@ -11,6 +11,7 @@ from string import Template
import subprocess
import time
from TdcPlugin import TdcPlugin
+from TdcResults import *
from tdc_config import *
@@ -21,6 +22,7 @@ class SubPlugin(TdcPlugin):
def __init__(self):
self.sub_class = 'valgrind/SubPlugin'
self.tap = ''
+ self._tsr = TestSuiteReport()
super().__init__()
def pre_suite(self, testcount, testidlist):
@@ -34,10 +36,14 @@ class SubPlugin(TdcPlugin):
def post_suite(self, index):
'''run commands after test_runner goes into a test loop'''
super().post_suite(index)
- self._add_to_tap('\n|---\n')
if self.args.verbose > 1:
print('{}.post_suite'.format(self.sub_class))
- print('{}'.format(self.tap))
+ #print('{}'.format(self.tap))
+ for xx in range(index - 1, self.testcount):
+ res = TestResult('{}-mem'.format(self.testidlist[xx]), 'Test skipped')
+ res.set_result(ResultState.skip)
+ res.set_errormsg('Skipped because of prior setup/teardown failure')
+ self._add_results(res)
if self.args.verbose < 4:
subprocess.check_output('rm -f vgnd-*.log', shell=True)
@@ -128,8 +134,17 @@ class SubPlugin(TdcPlugin):
nle_num = int(nle_mo.group(1))
mem_results = ''
+ res = TestResult('{}-mem'.format(self.args.testid),
+ '{} memory leak check'.format(self.args.test_name))
if (def_num > 0) or (ind_num > 0) or (pos_num > 0) or (nle_num > 0):
mem_results += 'not '
+ res.set_result(ResultState.fail)
+ res.set_failmsg('Memory leak detected')
+ res.append_failmsg(content)
+ else:
+ res.set_result(ResultState.success)
+
+ self._add_results(res)
mem_results += 'ok {} - {}-mem # {}\n'.format(
self.args.test_ordinal, self.args.testid, 'memory leak check')
@@ -138,5 +153,8 @@ class SubPlugin(TdcPlugin):
print('{}'.format(content))
self._add_to_tap(content)
+ def _add_results(self, res):
+ self._tsr.add_resultdata(res)
+
def _add_to_tap(self, more_tap_output):
self.tap += more_tap_output
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index 7607ba3e3cbe..e6e4ce80a726 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -23,6 +23,7 @@ from tdc_config import *
from tdc_helper import *
import TdcPlugin
+from TdcResults import *
class PluginMgrTestFail(Exception):
@@ -60,10 +61,10 @@ class PluginMgr:
for pgn_inst in reversed(self.plugin_instances):
pgn_inst.post_suite(index)
- def call_pre_case(self, test_ordinal, testid):
+ def call_pre_case(self, test_ordinal, testid, test_name):
for pgn_inst in self.plugin_instances:
try:
- pgn_inst.pre_case(test_ordinal, testid)
+ pgn_inst.pre_case(test_ordinal, testid, test_name)
except Exception as ee:
print('exception {} in call to pre_case for {} plugin'.
format(ee, pgn_inst.__class__))
@@ -102,7 +103,6 @@ class PluginMgr:
self.argparser = argparse.ArgumentParser(
description='Linux TC unit tests')
-
def replace_keywords(cmd):
"""
For a given executable command, substitute any known
@@ -131,12 +131,16 @@ def exec_cmd(args, pm, stage, command):
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
env=ENVIR)
- (rawout, serr) = proc.communicate()
- if proc.returncode != 0 and len(serr) > 0:
- foutput = serr.decode("utf-8", errors="ignore")
- else:
- foutput = rawout.decode("utf-8", errors="ignore")
+ try:
+ (rawout, serr) = proc.communicate(timeout=NAMES['TIMEOUT'])
+ if proc.returncode != 0 and len(serr) > 0:
+ foutput = serr.decode("utf-8", errors="ignore")
+ else:
+ foutput = rawout.decode("utf-8", errors="ignore")
+ except subprocess.TimeoutExpired:
+ foutput = "Command \"{}\" timed out\n".format(command)
+ proc.returncode = 255
proc.stdout.close()
proc.stderr.close()
@@ -183,6 +187,7 @@ def run_one_test(pm, args, index, tidx):
result = True
tresult = ""
tap = ""
+ res = TestResult(tidx['id'], tidx['name'])
if args.verbose > 0:
print("\t====================\n=====> ", end="")
print("Test " + tidx["id"] + ": " + tidx["name"])
@@ -190,7 +195,7 @@ def run_one_test(pm, args, index, tidx):
# populate NAMES with TESTID for this test
NAMES['TESTID'] = tidx['id']
- pm.call_pre_case(index, tidx['id'])
+ pm.call_pre_case(index, tidx['id'], tidx['name'])
prepare_env(args, pm, 'setup', "-----> prepare stage", tidx["setup"])
if (args.verbose > 0):
@@ -205,10 +210,11 @@ def run_one_test(pm, args, index, tidx):
pm.call_post_execute()
if (exit_code is None or exit_code != int(tidx["expExitCode"])):
- result = False
print("exit: {!r}".format(exit_code))
print("exit: {}".format(int(tidx["expExitCode"])))
#print("exit: {!r} {}".format(exit_code, int(tidx["expExitCode"])))
+ res.set_result(ResultState.fail)
+ res.set_failmsg('Command exited with {}, expected {}\n{}'.format(exit_code, tidx["expExitCode"], procout))
print(procout)
else:
if args.verbose > 0:
@@ -219,20 +225,15 @@ def run_one_test(pm, args, index, tidx):
if procout:
match_index = re.findall(match_pattern, procout)
if len(match_index) != int(tidx["matchCount"]):
- result = False
+ res.set_result(ResultState.fail)
+ res.set_failmsg('Could not match regex pattern. Verify command output:\n{}'.format(procout))
+ else:
+ res.set_result(ResultState.success)
elif int(tidx["matchCount"]) != 0:
- result = False
-
- if not result:
- tresult += 'not '
- tresult += 'ok {} - {} # {}\n'.format(str(index), tidx['id'], tidx['name'])
- tap += tresult
-
- if result == False:
- if procout:
- tap += procout
+ res.set_result(ResultState.fail)
+ res.set_failmsg('No output generated by verify command.')
else:
- tap += 'No output!\n'
+ res.set_result(ResultState.success)
prepare_env(args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout)
pm.call_post_case()
@@ -241,7 +242,7 @@ def run_one_test(pm, args, index, tidx):
# remove TESTID from NAMES
del(NAMES['TESTID'])
- return tap
+ return res
def test_runner(pm, args, filtered_tests):
"""
@@ -261,25 +262,15 @@ def test_runner(pm, args, filtered_tests):
emergency_exit = False
emergency_exit_message = ''
- if args.notap:
- if args.verbose:
- tap = 'notap requested: omitting test plan\n'
- else:
- tap = str(index) + ".." + str(tcount) + "\n"
+ tsr = TestSuiteReport()
+
try:
pm.call_pre_suite(tcount, [tidx['id'] for tidx in testlist])
except Exception as ee:
ex_type, ex, ex_tb = sys.exc_info()
print('Exception {} {} (caught in pre_suite).'.
format(ex_type, ex))
- # when the extra print statements are uncommented,
- # the traceback does not appear between them
- # (it appears way earlier in the tdc.py output)
- # so don't bother ...
- # print('--------------------(')
- # print('traceback')
traceback.print_tb(ex_tb)
- # print('--------------------)')
emergency_exit_message = 'EMERGENCY EXIT, call_pre_suite failed with exception {} {}\n'.format(ex_type, ex)
emergency_exit = True
stage = 'pre-SUITE'
@@ -295,15 +286,26 @@ def test_runner(pm, args, filtered_tests):
if args.verbose > 1:
print('Not executing test {} {} because DEV2 not defined'.
format(tidx['id'], tidx['name']))
+ res = TestResult(tidx['id'], tidx['name'])
+ res.set_result(ResultState.skip)
+ res.set_errormsg('Not executed because DEV2 is not defined')
+ tsr.add_resultdata(res)
continue
try:
badtest = tidx # in case it goes bad
- tap += run_one_test(pm, args, index, tidx)
+ res = run_one_test(pm, args, index, tidx)
+ tsr.add_resultdata(res)
except PluginMgrTestFail as pmtf:
ex_type, ex, ex_tb = sys.exc_info()
stage = pmtf.stage
message = pmtf.message
output = pmtf.output
+ res = TestResult(tidx['id'], tidx['name'])
+ res.set_result(ResultState.skip)
+ res.set_errormsg(pmtf.message)
+ res.set_failmsg(pmtf.output)
+ tsr.add_resultdata(res)
+ index += 1
print(message)
print('Exception {} {} (caught in test_runner, running test {} {} {} stage {})'.
format(ex_type, ex, index, tidx['id'], tidx['name'], stage))
@@ -322,16 +324,16 @@ def test_runner(pm, args, filtered_tests):
# if we failed in setup or teardown,
# fill in the remaining tests with ok-skipped
count = index
- if not args.notap:
- tap += 'about to flush the tap output if tests need to be skipped\n'
- if tcount + 1 != index:
- for tidx in testlist[index - 1:]:
- msg = 'skipped - previous {} failed'.format(stage)
- tap += 'ok {} - {} # {} {} {}\n'.format(
- count, tidx['id'], msg, index, badtest.get('id', '--Unknown--'))
- count += 1
- tap += 'done flushing skipped test tap output\n'
+ if tcount + 1 != count:
+ for tidx in testlist[count - 1:]:
+ res = TestResult(tidx['id'], tidx['name'])
+ res.set_result(ResultState.skip)
+ msg = 'skipped - previous {} failed {} {}'.format(stage,
+ index, badtest.get('id', '--Unknown--'))
+ res.set_errormsg(msg)
+ tsr.add_resultdata(res)
+ count += 1
if args.pause:
print('Want to pause\nPress enter to continue ...')
@@ -340,7 +342,7 @@ def test_runner(pm, args, filtered_tests):
pm.call_post_suite(index)
- return tap
+ return tsr
def has_blank_ids(idlist):
"""
@@ -381,6 +383,10 @@ def set_args(parser):
Set the command line arguments for tdc.
"""
parser.add_argument(
+ '--outfile', type=str,
+ help='Path to the file in which results should be saved. ' +
+ 'Default target is the current directory.')
+ parser.add_argument(
'-p', '--path', type=str,
help='The full path to the tc executable to use')
sg = parser.add_argument_group(
@@ -416,8 +422,9 @@ def set_args(parser):
'-v', '--verbose', action='count', default=0,
help='Show the commands that are being run')
parser.add_argument(
- '-N', '--notap', action='store_true',
- help='Suppress tap results for command under test')
+ '--format', default='tap', const='tap', nargs='?',
+ choices=['none', 'xunit', 'tap'],
+ help='Specify the format for test results. (Default: TAP)')
parser.add_argument('-d', '--device',
help='Execute the test case in flower category')
parser.add_argument(
@@ -438,6 +445,8 @@ def check_default_settings(args, remaining, pm):
NAMES['TC'] = args.path
if args.device != None:
NAMES['DEV2'] = args.device
+ if 'TIMEOUT' not in NAMES:
+ NAMES['TIMEOUT'] = None
if not os.path.isfile(NAMES['TC']):
print("The specified tc path " + NAMES['TC'] + " does not exist.")
exit(1)
@@ -632,12 +641,30 @@ def set_operation_mode(pm, args):
if len(alltests):
catresults = test_runner(pm, args, alltests)
+ if args.format == 'none':
+ print('Test results output suppression requested\n')
+ else:
+ print('\nAll test results: \n')
+ if args.format == 'xunit':
+ suffix = 'xml'
+ res = catresults.format_xunit()
+ elif args.format == 'tap':
+ suffix = 'tap'
+ res = catresults.format_tap()
+ print(res)
+ print('\n\n')
+ if not args.outfile:
+ fname = 'test-results.{}'.format(suffix)
+ else:
+ fname = args.outfile
+ with open(fname, 'w') as fh:
+ fh.write(res)
+ fh.close()
+ if os.getenv('SUDO_UID') is not None:
+ os.chown(fname, uid=int(os.getenv('SUDO_UID')),
+ gid=int(os.getenv('SUDO_GID')))
else:
- catresults = 'No tests found\n'
- if args.notap:
- print('Tap output suppression requested\n')
- else:
- print('All test results: \n\n{}'.format(catresults))
+ print('No tests found\n')
def main():
"""
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index d651bc1501bd..6d91e48c2625 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -15,6 +15,8 @@ NAMES = {
'DEV1': 'v0p1',
'DEV2': '',
'BATCH_FILE': './batch.txt',
+ # Length of time in seconds to wait before terminating a command
+ 'TIMEOUT': 12,
# Name of the namespace to use
'NS': 'tcut',
# Directory containing eBPF test programs