diff options
Diffstat (limited to 'tools/testing')
-rw-r--r-- | tools/testing/selftests/bpf/Makefile | 21 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/bpf_helpers.h | 64 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_lpm_map.c | 201 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_progs.c | 195 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_verifier.c | 321 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_xdp_meta.c | 53 | ||||
-rwxr-xr-x | tools/testing/selftests/bpf/test_xdp_meta.sh | 51 | ||||
-rwxr-xr-x | tools/testing/selftests/net/rtnetlink.sh | 201 | ||||
-rw-r--r-- | tools/testing/vsock/.gitignore | 2 | ||||
-rw-r--r-- | tools/testing/vsock/Makefile | 9 | ||||
-rw-r--r-- | tools/testing/vsock/README | 36 | ||||
-rw-r--r-- | tools/testing/vsock/control.c | 219 | ||||
-rw-r--r-- | tools/testing/vsock/control.h | 13 | ||||
-rw-r--r-- | tools/testing/vsock/timeout.c | 64 | ||||
-rw-r--r-- | tools/testing/vsock/timeout.h | 14 | ||||
-rw-r--r-- | tools/testing/vsock/vsock_diag_test.c | 681 |
16 files changed, 2092 insertions, 53 deletions
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f4b23d697448..924af8d79bde 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -15,9 +15,10 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_align 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 sockmap_parse_prog.o sockmap_verdict_prog.o + test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ + sockmap_verdict_prog.o -TEST_PROGS := test_kmod.sh test_xdp_redirect.sh +TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh include ../lib.mk @@ -34,8 +35,20 @@ $(BPFOBJ): force $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ CLANG ?= clang +LLC ?= llc + +PROBE := $(shell llc -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) + +# Let newer LLVM versions transparently probe the kernel for availability +# of full BPF instruction set. +ifeq ($(PROBE),) + CPU ?= probe +else + CPU ?= generic +endif %.o: %.c $(CLANG) -I. -I./include/uapi -I../../../include/uapi \ - -Wno-compare-distinct-pointer-types \ - -O2 -target bpf -c $< -o $@ + -Wno-compare-distinct-pointer-types \ + -O2 -target bpf -emit-llvm -c $< -o - | \ + $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 36fb9161b34a..e25dbf6038cf 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -62,6 +62,8 @@ static unsigned long long (*bpf_get_prandom_u32)(void) = (void *) BPF_FUNC_get_prandom_u32; static int (*bpf_xdp_adjust_head)(void *ctx, int offset) = (void *) BPF_FUNC_xdp_adjust_head; +static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) = + (void *) BPF_FUNC_xdp_adjust_meta; static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, int optlen) = (void *) BPF_FUNC_setsockopt; @@ -70,6 +72,12 @@ static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = static int (*bpf_sock_map_update)(void *map, void *key, void *value, unsigned long long flags) = (void *) BPF_FUNC_sock_map_update; +static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags, + void *buf, unsigned int buf_size) = + (void *) BPF_FUNC_perf_event_read_value; +static int (*bpf_perf_prog_read_value)(void *ctx, void *buf, + unsigned int buf_size) = + (void *) BPF_FUNC_perf_prog_read_value; /* llvm builtin functions that eBPF C program may use to @@ -109,7 +117,47 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = static int (*bpf_skb_change_head)(void *, int len, int flags) = (void *) BPF_FUNC_skb_change_head; +/* Scan the ARCH passed in from ARCH env variable (see Makefile) */ +#if defined(__TARGET_ARCH_x86) + #define bpf_target_x86 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_s930x) + #define bpf_target_s930x + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arm64) + #define bpf_target_arm64 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_mips) + #define bpf_target_mips + #define bpf_target_defined +#elif defined(__TARGET_ARCH_powerpc) + #define bpf_target_powerpc + #define bpf_target_defined +#elif defined(__TARGET_ARCH_sparc) + #define bpf_target_sparc + #define bpf_target_defined +#else + #undef bpf_target_defined +#endif + +/* Fall back to what the compiler says */ +#ifndef bpf_target_defined #if defined(__x86_64__) + #define bpf_target_x86 +#elif defined(__s390x__) + #define bpf_target_s930x +#elif defined(__aarch64__) + #define bpf_target_arm64 +#elif defined(__mips__) + #define bpf_target_mips +#elif defined(__powerpc__) + #define bpf_target_powerpc +#elif defined(__sparc__) + #define bpf_target_sparc +#endif +#endif + +#if defined(bpf_target_x86) #define PT_REGS_PARM1(x) ((x)->di) #define PT_REGS_PARM2(x) ((x)->si) @@ -122,7 +170,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) = #define PT_REGS_SP(x) ((x)->sp) #define PT_REGS_IP(x) ((x)->ip) -#elif defined(__s390x__) +#elif defined(bpf_target_s390x) #define PT_REGS_PARM1(x) ((x)->gprs[2]) #define PT_REGS_PARM2(x) ((x)->gprs[3]) @@ -135,7 +183,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) = #define PT_REGS_SP(x) ((x)->gprs[15]) #define PT_REGS_IP(x) ((x)->psw.addr) -#elif defined(__aarch64__) +#elif defined(bpf_target_arm64) #define PT_REGS_PARM1(x) ((x)->regs[0]) #define PT_REGS_PARM2(x) ((x)->regs[1]) @@ -148,7 +196,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) = #define PT_REGS_SP(x) ((x)->sp) #define PT_REGS_IP(x) ((x)->pc) -#elif defined(__mips__) +#elif defined(bpf_target_mips) #define PT_REGS_PARM1(x) ((x)->regs[4]) #define PT_REGS_PARM2(x) ((x)->regs[5]) @@ -161,7 +209,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) = #define PT_REGS_SP(x) ((x)->regs[29]) #define PT_REGS_IP(x) ((x)->cp0_epc) -#elif defined(__powerpc__) +#elif defined(bpf_target_powerpc) #define PT_REGS_PARM1(x) ((x)->gpr[3]) #define PT_REGS_PARM2(x) ((x)->gpr[4]) @@ -172,7 +220,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) = #define PT_REGS_SP(x) ((x)->sp) #define PT_REGS_IP(x) ((x)->nip) -#elif defined(__sparc__) +#elif defined(bpf_target_sparc) #define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0]) #define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1]) @@ -182,6 +230,8 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) = #define PT_REGS_RET(x) ((x)->u_regs[UREG_I7]) #define PT_REGS_RC(x) ((x)->u_regs[UREG_I0]) #define PT_REGS_SP(x) ((x)->u_regs[UREG_FP]) + +/* Should this also be a bpf_target check for the sparc case? */ #if defined(__arch64__) #define PT_REGS_IP(x) ((x)->tpc) #else @@ -190,10 +240,10 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) = #endif -#ifdef __powerpc__ +#ifdef bpf_target_powerpc #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP -#elif defined(__sparc__) +#elif bpf_target_sparc #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP #else diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index e97565243d59..6fedb9fec36b 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -31,6 +31,10 @@ struct tlpm_node { uint8_t key[]; }; +static struct tlpm_node *tlpm_match(struct tlpm_node *list, + const uint8_t *key, + size_t n_bits); + static struct tlpm_node *tlpm_add(struct tlpm_node *list, const uint8_t *key, size_t n_bits) @@ -38,9 +42,17 @@ static struct tlpm_node *tlpm_add(struct tlpm_node *list, struct tlpm_node *node; size_t n; + n = (n_bits + 7) / 8; + + /* 'overwrite' an equivalent entry if one already exists */ + node = tlpm_match(list, key, n_bits); + if (node && node->n_bits == n_bits) { + memcpy(node->key, key, n); + return list; + } + /* add new entry with @key/@n_bits to @list and return new head */ - n = (n_bits + 7) / 8; node = malloc(sizeof(*node) + n); assert(node); @@ -92,6 +104,34 @@ static struct tlpm_node *tlpm_match(struct tlpm_node *list, return best; } +static struct tlpm_node *tlpm_delete(struct tlpm_node *list, + const uint8_t *key, + size_t n_bits) +{ + struct tlpm_node *best = tlpm_match(list, key, n_bits); + struct tlpm_node *node; + + if (!best || best->n_bits != n_bits) + return list; + + if (best == list) { + node = best->next; + free(best); + return node; + } + + for (node = list; node; node = node->next) { + if (node->next == best) { + node->next = best->next; + free(best); + return list; + } + } + /* should never get here */ + assert(0); + return list; +} + static void test_lpm_basic(void) { struct tlpm_node *list = NULL, *t1, *t2; @@ -114,6 +154,13 @@ static void test_lpm_basic(void) assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15)); assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16)); + list = tlpm_delete(list, (uint8_t[]){ 0xff, 0xff }, 16); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); + + list = tlpm_delete(list, (uint8_t[]){ 0xff }, 8); + assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + tlpm_clear(list); } @@ -158,7 +205,7 @@ static void test_lpm_order(void) static void test_lpm_map(int keysize) { - size_t i, j, n_matches, n_nodes, n_lookups; + size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups; struct tlpm_node *t, *list = NULL; struct bpf_lpm_trie_key *key; uint8_t *data, *value; @@ -170,6 +217,7 @@ static void test_lpm_map(int keysize) */ n_matches = 0; + n_matches_after_delete = 0; n_nodes = 1 << 8; n_lookups = 1 << 16; @@ -223,15 +271,54 @@ static void test_lpm_map(int keysize) } } + /* Remove the first half of the elements in the tlpm and the + * corresponding nodes from the bpf-lpm. Then run the same + * large number of random lookups in both and make sure they match. + * Note: we need to count the number of nodes actually inserted + * since there may have been duplicates. + */ + for (i = 0, t = list; t; i++, t = t->next) + ; + for (j = 0; j < i / 2; ++j) { + key->prefixlen = list->n_bits; + memcpy(key->data, list->key, keysize); + r = bpf_map_delete_elem(map, key); + assert(!r); + list = tlpm_delete(list, list->key, list->n_bits); + assert(list); + } + for (i = 0; i < n_lookups; ++i) { + for (j = 0; j < keysize; ++j) + data[j] = rand() & 0xff; + + t = tlpm_match(list, data, 8 * keysize); + + key->prefixlen = 8 * keysize; + memcpy(key->data, data, keysize); + r = bpf_map_lookup_elem(map, key, value); + assert(!r || errno == ENOENT); + assert(!t == !!r); + + if (t) { + ++n_matches_after_delete; + assert(t->n_bits == value[keysize]); + for (j = 0; j < t->n_bits; ++j) + assert((t->key[j / 8] & (1 << (7 - j % 8))) == + (value[j / 8] & (1 << (7 - j % 8)))); + } + } + close(map); tlpm_clear(list); /* With 255 random nodes in the map, we are pretty likely to match * something on every lookup. For statistics, use this: * - * printf(" nodes: %zu\n" - * "lookups: %zu\n" - * "matches: %zu\n", n_nodes, n_lookups, n_matches); + * printf(" nodes: %zu\n" + * " lookups: %zu\n" + * " matches: %zu\n" + * "matches(delete): %zu\n", + * n_nodes, n_lookups, n_matches, n_matches_after_delete); */ } @@ -331,6 +418,108 @@ static void test_lpm_ipaddr(void) close(map_fd_ipv6); } +static void test_lpm_delete(void) +{ + struct bpf_lpm_trie_key *key; + size_t key_size; + int map_fd; + __u64 value; + + key_size = sizeof(*key) + sizeof(__u32); + key = alloca(key_size); + + map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + key_size, sizeof(value), + 100, BPF_F_NO_PREALLOC); + assert(map_fd >= 0); + + /* Add nodes: + * 192.168.0.0/16 (1) + * 192.168.0.0/24 (2) + * 192.168.128.0/24 (3) + * 192.168.1.0/24 (4) + * + * (1) + * / \ + * (IM) (3) + * / \ + * (2) (4) + */ + value = 1; + key->prefixlen = 16; + inet_pton(AF_INET, "192.168.0.0", key->data); + assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); + + value = 2; + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.0.0", key->data); + assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); + + value = 3; + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.128.0", key->data); + assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); + + value = 4; + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.1.0", key->data); + assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); + + /* remove non-existent node */ + key->prefixlen = 32; + inet_pton(AF_INET, "10.0.0.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 && + errno == ENOENT); + + /* assert initial lookup */ + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.0.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); + assert(value == 2); + + /* remove leaf node */ + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == 0); + + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.0.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); + assert(value == 1); + + /* remove leaf (and intermediary) node */ + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.1.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == 0); + + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.1.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); + assert(value == 1); + + /* remove root node */ + key->prefixlen = 16; + inet_pton(AF_INET, "192.168.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == 0); + + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.128.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); + assert(value == 3); + + /* remove last node */ + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.128.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == 0); + + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.128.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 && + errno == ENOENT); + + close(map_fd); +} + int main(void) { struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY }; @@ -353,6 +542,8 @@ int main(void) test_lpm_ipaddr(); + test_lpm_delete(); + printf("test_lpm: OK\n"); return 0; } diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 11ee25cea227..69427531408d 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -10,6 +10,7 @@ #include <string.h> #include <assert.h> #include <stdlib.h> +#include <time.h> #include <linux/types.h> typedef __u16 __sum16; @@ -19,6 +20,8 @@ typedef __u16 __sum16; #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> +#include <linux/filter.h> +#include <linux/unistd.h> #include <sys/wait.h> #include <sys/resource.h> @@ -273,16 +276,26 @@ static void test_bpf_obj_id(void) const int nr_iters = 2; const char *file = "./test_obj_id.o"; const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + const char *expected_prog_name = "test_obj_id"; + const char *expected_map_name = "test_map_id"; + const __u64 nsec_per_sec = 1000000000; struct bpf_object *objs[nr_iters]; int prog_fds[nr_iters], map_fds[nr_iters]; /* +1 to test for the info_len returned by kernel */ struct bpf_prog_info prog_infos[nr_iters + 1]; struct bpf_map_info map_infos[nr_iters + 1]; + /* Each prog only uses one map. +1 to test nr_map_ids + * returned by kernel. + */ + __u32 map_ids[nr_iters + 1]; char jited_insns[128], xlated_insns[128], zeros[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; + struct timespec real_time_ts, boot_time_ts; int sysctl_fd, jit_enabled = 0, err = 0; __u64 array_value; + uid_t my_uid = getuid(); + time_t now, load_time; sysctl_fd = open(jit_sysctl, 0, O_RDONLY); if (sysctl_fd != -1) { @@ -307,6 +320,7 @@ static void test_bpf_obj_id(void) /* Check bpf_obj_get_info_by_fd() */ bzero(zeros, sizeof(zeros)); for (i = 0; i < nr_iters; i++) { + now = time(NULL); err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER, &objs[i], &prog_fds[i]); /* test_obj_id.o is a dumb prog. It should never fail @@ -316,6 +330,38 @@ static void test_bpf_obj_id(void) error_cnt++; assert(!err); + /* Insert a magic value to the map */ + map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id"); + assert(map_fds[i] >= 0); + err = bpf_map_update_elem(map_fds[i], &array_key, + &array_magic_value, 0); + assert(!err); + + /* Check getting map info */ + info_len = sizeof(struct bpf_map_info) * 2; + bzero(&map_infos[i], info_len); + err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i], + &info_len); + if (CHECK(err || + map_infos[i].type != BPF_MAP_TYPE_ARRAY || + map_infos[i].key_size != sizeof(__u32) || + map_infos[i].value_size != sizeof(__u64) || + map_infos[i].max_entries != 1 || + map_infos[i].map_flags != 0 || + info_len != sizeof(struct bpf_map_info) || + strcmp((char *)map_infos[i].name, expected_map_name), + "get-map-info(fd)", + "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", + err, errno, + map_infos[i].type, BPF_MAP_TYPE_ARRAY, + info_len, sizeof(struct bpf_map_info), + map_infos[i].key_size, + map_infos[i].value_size, + map_infos[i].max_entries, + map_infos[i].map_flags, + map_infos[i].name, expected_map_name)) + goto done; + /* Check getting prog info */ info_len = sizeof(struct bpf_prog_info) * 2; bzero(&prog_infos[i], info_len); @@ -325,8 +371,16 @@ static void test_bpf_obj_id(void) prog_infos[i].jited_prog_len = sizeof(jited_insns); prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns); prog_infos[i].xlated_prog_len = sizeof(xlated_insns); + prog_infos[i].map_ids = ptr_to_u64(map_ids + i); + prog_infos[i].nr_map_ids = 2; + err = clock_gettime(CLOCK_REALTIME, &real_time_ts); + assert(!err); + err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts); + assert(!err); err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i], &info_len); + load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + + (prog_infos[i].load_time / nsec_per_sec); if (CHECK(err || prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || info_len != sizeof(struct bpf_prog_info) || @@ -334,9 +388,14 @@ static void test_bpf_obj_id(void) (jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))) || !prog_infos[i].xlated_prog_len || - !memcmp(xlated_insns, zeros, sizeof(zeros)), + !memcmp(xlated_insns, zeros, sizeof(zeros)) || + 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 || + 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(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d\n", + "err %d errno %d i %d type %d(%d) info_len %u(%lu) 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", err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), @@ -344,36 +403,12 @@ static void test_bpf_obj_id(void) prog_infos[i].jited_prog_len, prog_infos[i].xlated_prog_len, !!memcmp(jited_insns, zeros, sizeof(zeros)), - !!memcmp(xlated_insns, zeros, sizeof(zeros)))) - goto done; - - map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id"); - assert(map_fds[i] >= 0); - err = bpf_map_update_elem(map_fds[i], &array_key, - &array_magic_value, 0); - assert(!err); - - /* Check getting map info */ - info_len = sizeof(struct bpf_map_info) * 2; - bzero(&map_infos[i], info_len); - err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i], - &info_len); - if (CHECK(err || - map_infos[i].type != BPF_MAP_TYPE_ARRAY || - map_infos[i].key_size != sizeof(__u32) || - map_infos[i].value_size != sizeof(__u64) || - map_infos[i].max_entries != 1 || - map_infos[i].map_flags != 0 || - info_len != sizeof(struct bpf_map_info), - "get-map-info(fd)", - "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n", - err, errno, - map_infos[i].type, BPF_MAP_TYPE_ARRAY, - info_len, sizeof(struct bpf_map_info), - map_infos[i].key_size, - map_infos[i].value_size, - map_infos[i].max_entries, - map_infos[i].map_flags)) + !!memcmp(xlated_insns, zeros, sizeof(zeros)), + 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, + prog_infos[i].name, expected_prog_name)) goto done; } @@ -382,6 +417,7 @@ static void test_bpf_obj_id(void) next_id = 0; while (!bpf_prog_get_next_id(next_id, &next_id)) { struct bpf_prog_info prog_info = {}; + __u32 saved_map_id; int prog_fd; info_len = sizeof(prog_info); @@ -404,16 +440,33 @@ static void test_bpf_obj_id(void) nr_id_found++; + /* Negative test: + * prog_info.nr_map_ids = 1 + * prog_info.map_ids = NULL + */ + prog_info.nr_map_ids = 1; + err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len); + if (CHECK(!err || errno != EFAULT, + "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)", + err, errno, EFAULT)) + break; + bzero(&prog_info, sizeof(prog_info)); + info_len = sizeof(prog_info); + + saved_map_id = *(int *)(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); prog_infos[i].jited_prog_insns = 0; prog_infos[i].xlated_prog_insns = 0; CHECK(err || info_len != sizeof(struct bpf_prog_info) || - memcmp(&prog_info, &prog_infos[i], info_len), + memcmp(&prog_info, &prog_infos[i], info_len) || + *(int *)prog_info.map_ids != saved_map_id, "get-prog-info(next_id->fd)", - "err %d errno %d info_len %u(%lu) memcmp %d\n", + "err %d errno %d info_len %u(%lu) memcmp %d map_id %u(%u)\n", err, errno, info_len, sizeof(struct bpf_prog_info), - memcmp(&prog_info, &prog_infos[i], info_len)); - + memcmp(&prog_info, &prog_infos[i], info_len), + *(int *)prog_info.map_ids, saved_map_id); close(prog_fd); } CHECK(nr_id_found != nr_iters, @@ -495,6 +548,75 @@ static void test_pkt_md_access(void) bpf_object__close(obj); } +static void test_obj_name(void) +{ + struct { + const char *name; + int success; + int expected_errno; + } tests[] = { + { "", 1, 0 }, + { "_123456789ABCDE", 1, 0 }, + { "_123456789ABCDEF", 0, EINVAL }, + { "_123456789ABCD\n", 0, EINVAL }, + }; + struct bpf_insn prog[] = { + BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + __u32 duration = 0; + int i; + + for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + size_t name_len = strlen(tests[i].name) + 1; + union bpf_attr attr; + size_t ncopy; + int fd; + + /* test different attr.prog_name during BPF_PROG_LOAD */ + ncopy = name_len < sizeof(attr.prog_name) ? + name_len : sizeof(attr.prog_name); + bzero(&attr, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SCHED_CLS; + attr.insn_cnt = 2; + attr.insns = ptr_to_u64(prog); + attr.license = ptr_to_u64(""); + memcpy(attr.prog_name, tests[i].name, ncopy); + + fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + CHECK((tests[i].success && fd < 0) || + (!tests[i].success && fd != -1) || + (!tests[i].success && errno != tests[i].expected_errno), + "check-bpf-prog-name", + "fd %d(%d) errno %d(%d)\n", + fd, tests[i].success, errno, tests[i].expected_errno); + + if (fd != -1) + close(fd); + + /* test different attr.map_name during BPF_MAP_CREATE */ + ncopy = name_len < sizeof(attr.map_name) ? + name_len : sizeof(attr.map_name); + bzero(&attr, sizeof(attr)); + attr.map_type = BPF_MAP_TYPE_ARRAY; + attr.key_size = 4; + attr.value_size = 4; + attr.max_entries = 1; + attr.map_flags = 0; + memcpy(attr.map_name, tests[i].name, ncopy); + fd = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr)); + CHECK((tests[i].success && fd < 0) || + (!tests[i].success && fd != -1) || + (!tests[i].success && errno != tests[i].expected_errno), + "check-bpf-map-name", + "fd %d(%d) errno %d(%d)\n", + fd, tests[i].success, errno, tests[i].expected_errno); + + if (fd != -1) + close(fd); + } +} + int main(void) { struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; @@ -507,6 +629,7 @@ int main(void) test_tcp_estats(); test_bpf_obj_id(); test_pkt_md_access(); + test_obj_name(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 26f3250bdcd2..cc91d0159f43 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -6645,6 +6645,325 @@ static struct bpf_test tests[] = { .errstr = "BPF_END uses reserved fields", .result = REJECT, }, + { + "meta access, test1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet, off=-8", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test5", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_4, 3), + BPF_MOV64_IMM(BPF_REG_2, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_xdp_adjust_meta), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R3 !read_ok", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_0, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test7", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test8", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test9", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test10", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_IMM(BPF_REG_5, 42), + BPF_MOV64_IMM(BPF_REG_6, 24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8), + BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_5), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_5, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test11", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_IMM(BPF_REG_5, 42), + BPF_MOV64_IMM(BPF_REG_6, 24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8), + BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_5), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_5, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test12", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16), + BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 5), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16), + BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "bpf_exit with invalid return code. test1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R0 has value (0x0; 0xffffffff)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .errstr = "R0 has value (0x0; 0x3)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test5", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .errstr = "R0 has value (0x2; 0x0)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test6", + .insns = { + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .errstr = "R0 is not a known value (ctx)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test7", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4), + BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .errstr = "R0 has unknown scalar value", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, }; static int probe_filter_length(const struct bpf_insn *fp) @@ -6692,7 +7011,7 @@ static int create_map_in_map(void) return inner_map_fd; } - outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, sizeof(int), inner_map_fd, 1, 0); if (outer_map_fd < 0) printf("Failed to create array of maps '%s'!\n", diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/test_xdp_meta.c new file mode 100644 index 000000000000..8d0182650653 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_meta.c @@ -0,0 +1,53 @@ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> + +#include "bpf_helpers.h" + +#define __round_mask(x, y) ((__typeof__(x))((y) - 1)) +#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) +#define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem + +SEC("t") +int ing_cls(struct __sk_buff *ctx) +{ + __u8 *data, *data_meta, *data_end; + __u32 diff = 0; + + data_meta = ctx_ptr(ctx, data_meta); + data_end = ctx_ptr(ctx, data_end); + data = ctx_ptr(ctx, data); + + if (data + ETH_ALEN > data_end || + data_meta + round_up(ETH_ALEN, 4) > data) + return TC_ACT_SHOT; + + diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0]; + diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2]; + + return diff ? TC_ACT_SHOT : TC_ACT_OK; +} + +SEC("x") +int ing_xdp(struct xdp_md *ctx) +{ + __u8 *data, *data_meta, *data_end; + int ret; + + ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4)); + if (ret < 0) + return XDP_DROP; + + data_meta = ctx_ptr(ctx, data_meta); + data_end = ctx_ptr(ctx, data_end); + data = ctx_ptr(ctx, data); + + if (data + ETH_ALEN > data_end || + data_meta + round_up(ETH_ALEN, 4) > data) + return XDP_DROP; + + __builtin_memcpy(data_meta, data, ETH_ALEN); + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh new file mode 100755 index 000000000000..307aa856cee3 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -0,0 +1,51 @@ +#!/bin/sh + +cleanup() +{ + if [ "$?" = "0" ]; then + echo "selftests: test_xdp_meta [PASS]"; + else + echo "selftests: test_xdp_meta [FAILED]"; + fi + + set +e + ip netns del ns1 2> /dev/null + ip netns del ns2 2> /dev/null +} + +ip link set dev lo xdp off 2>/dev/null > /dev/null +if [ $? -ne 0 ];then + echo "selftests: [SKIP] Could not run test without the ip xdp support" + exit 0 +fi +set -e + +ip netns add ns1 +ip netns add ns2 + +trap cleanup 0 2 3 6 9 + +ip link add veth1 type veth peer name veth2 + +ip link set veth1 netns ns1 +ip link set veth2 netns ns2 + +ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1 +ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2 + +ip netns exec ns1 tc qdisc add dev veth1 clsact +ip netns exec ns2 tc qdisc add dev veth2 clsact + +ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t +ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t + +ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x +ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x + +ip netns exec ns1 ip link set dev veth1 up +ip netns exec ns2 ip link set dev veth2 up + +ip netns exec ns1 ping -c 1 10.1.1.22 +ip netns exec ns2 ping -c 1 10.1.1.11 + +exit 0 diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 57b5ff576240..e8c86c416ed0 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -15,6 +15,14 @@ check_err() fi } +# same but inverted -- used when command must fail for test to pass +check_fail() +{ + if [ $1 -eq 0 ]; then + ret=1 + fi +} + kci_add_dummy() { ip link add name "$devdummy" type dummy @@ -235,6 +243,196 @@ kci_test_addrlabel() echo "PASS: ipv6 addrlabel" } +kci_test_ifalias() +{ + ret=0 + namewant=$(uuidgen) + syspathname="/sys/class/net/$devdummy/ifalias" + + ip link set dev "$devdummy" alias "$namewant" + check_err $? + + if [ $ret -ne 0 ]; then + echo "FAIL: cannot set interface alias of $devdummy to $namewant" + return 1 + fi + + ip link show "$devdummy" | grep -q "alias $namewant" + check_err $? + + if [ -r "$syspathname" ] ; then + read namehave < "$syspathname" + if [ "$namewant" != "$namehave" ]; then + echo "FAIL: did set ifalias $namewant but got $namehave" + return 1 + fi + + namewant=$(uuidgen) + echo "$namewant" > "$syspathname" + ip link show "$devdummy" | grep -q "alias $namewant" + check_err $? + + # sysfs interface allows to delete alias again + echo "" > "$syspathname" + + ip link show "$devdummy" | grep -q "alias $namewant" + check_fail $? + + for i in $(seq 1 100); do + uuidgen > "$syspathname" & + done + + wait + + # re-add the alias -- kernel should free mem when dummy dev is removed + ip link set dev "$devdummy" alias "$namewant" + check_err $? + fi + + if [ $ret -ne 0 ]; then + echo "FAIL: set interface alias $devdummy to $namewant" + return 1 + fi + + echo "PASS: set ifalias $namewant for $devdummy" +} + +kci_test_vrf() +{ + vrfname="test-vrf" + ret=0 + + ip link show type vrf 2>/dev/null + if [ $? -ne 0 ]; then + echo "SKIP: vrf: iproute2 too old" + return 0 + fi + + ip link add "$vrfname" type vrf table 10 + check_err $? + if [ $ret -ne 0 ];then + echo "FAIL: can't add vrf interface, skipping test" + return 0 + fi + + ip -br link show type vrf | grep -q "$vrfname" + check_err $? + if [ $ret -ne 0 ];then + echo "FAIL: created vrf device not found" + return 1 + fi + + ip link set dev "$vrfname" up + check_err $? + + ip link set dev "$devdummy" master "$vrfname" + check_err $? + ip link del dev "$vrfname" + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: vrf" + return 1 + fi + + echo "PASS: vrf" +} + +kci_test_encap_vxlan() +{ + ret=0 + vxlan="test-vxlan0" + vlan="test-vlan0" + testns="$1" + + ip netns exec "$testns" ip link add "$vxlan" type vxlan id 42 group 239.1.1.1 \ + dev "$devdummy" dstport 4789 2>/dev/null + if [ $? -ne 0 ]; then + echo "FAIL: can't add vxlan interface, skipping test" + return 0 + fi + check_err $? + + ip netns exec "$testns" ip addr add 10.2.11.49/24 dev "$vxlan" + check_err $? + + ip netns exec "$testns" ip link set up dev "$vxlan" + check_err $? + + ip netns exec "$testns" ip link add link "$vxlan" name "$vlan" type vlan id 1 + check_err $? + + ip netns exec "$testns" ip link del "$vxlan" + check_err $? + + if [ $ret -ne 0 ]; then + echo "FAIL: vxlan" + return 1 + fi + echo "PASS: vxlan" +} + +kci_test_encap_fou() +{ + ret=0 + name="test-fou" + testns="$1" + + ip fou help 2>&1 |grep -q 'Usage: ip fou' + if [ $? -ne 0 ];then + echo "SKIP: fou: iproute2 too old" + return 1 + fi + + ip netns exec "$testns" ip fou add port 7777 ipproto 47 2>/dev/null + if [ $? -ne 0 ];then + echo "FAIL: can't add fou port 7777, skipping test" + return 1 + fi + + ip netns exec "$testns" ip fou add port 8888 ipproto 4 + check_err $? + + ip netns exec "$testns" ip fou del port 9999 2>/dev/null + check_fail $? + + ip netns exec "$testns" ip fou del port 7777 + check_err $? + + if [ $ret -ne 0 ]; then + echo "FAIL: fou" + return 1 + fi + + echo "PASS: fou" +} + +# test various encap methods, use netns to avoid unwanted interference +kci_test_encap() +{ + testns="testns" + ret=0 + + ip netns add "$testns" + if [ $? -ne 0 ]; then + echo "SKIP encap tests: cannot add net namespace $testns" + return 1 + fi + + ip netns exec "$testns" ip link set lo up + check_err $? + + ip netns exec "$testns" ip link add name "$devdummy" type dummy + check_err $? + ip netns exec "$testns" ip link set "$devdummy" up + check_err $? + + kci_test_encap_vxlan "$testns" + kci_test_encap_fou "$testns" + + ip netns del "$testns" +} + kci_test_rtnl() { kci_add_dummy @@ -249,6 +447,9 @@ kci_test_rtnl() kci_test_gre kci_test_bridge kci_test_addrlabel + kci_test_ifalias + kci_test_vrf + kci_test_encap kci_del_dummy } diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore new file mode 100644 index 000000000000..dc5f11faf530 --- /dev/null +++ b/tools/testing/vsock/.gitignore @@ -0,0 +1,2 @@ +*.d +vsock_diag_test diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile new file mode 100644 index 000000000000..66ba0924194d --- /dev/null +++ b/tools/testing/vsock/Makefile @@ -0,0 +1,9 @@ +all: test +test: vsock_diag_test +vsock_diag_test: vsock_diag_test.o timeout.o control.o + +CFLAGS += -g -O2 -Werror -Wall -I. -I../../include/uapi -I../../include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE +.PHONY: all test clean +clean: + ${RM} *.o *.d vsock_diag_test +-include *.d diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README new file mode 100644 index 000000000000..2cc6d7302db6 --- /dev/null +++ b/tools/testing/vsock/README @@ -0,0 +1,36 @@ +AF_VSOCK test suite +------------------- +These tests exercise net/vmw_vsock/ host<->guest sockets for VMware, KVM, and +Hyper-V. + +The following tests are available: + + * vsock_diag_test - vsock_diag.ko module for listing open sockets + +The following prerequisite steps are not automated and must be performed prior +to running tests: + +1. Build the kernel and these tests. +2. Install the kernel and tests on the host. +3. Install the kernel and tests inside the guest. +4. Boot the guest and ensure that the AF_VSOCK transport is enabled. + +Invoke test binaries in both directions as follows: + + # host=server, guest=client + (host)# $TEST_BINARY --mode=server \ + --control-port=1234 \ + --peer-cid=3 + (guest)# $TEST_BINARY --mode=client \ + --control-host=$HOST_IP \ + --control-port=1234 \ + --peer-cid=2 + + # host=client, guest=server + (guest)# $TEST_BINARY --mode=server \ + --control-port=1234 \ + --peer-cid=2 + (host)# $TEST_BINARY --mode=client \ + --control-port=$GUEST_IP \ + --control-port=1234 \ + --peer-cid=3 diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c new file mode 100644 index 000000000000..90fd47f0e422 --- /dev/null +++ b/tools/testing/vsock/control.c @@ -0,0 +1,219 @@ +/* Control socket for client/server test execution + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +/* The client and server may need to coordinate to avoid race conditions like + * the client attempting to connect to a socket that the server is not + * listening on yet. The control socket offers a communications channel for + * such coordination tasks. + * + * If the client calls control_expectln("LISTENING"), then it will block until + * the server calls control_writeln("LISTENING"). This provides a simple + * mechanism for coordinating between the client and the server. + */ + +#include <errno.h> +#include <netdb.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/socket.h> + +#include "timeout.h" +#include "control.h" + +static int control_fd = -1; + +/* Open the control socket, either in server or client mode */ +void control_init(const char *control_host, + const char *control_port, + bool server) +{ + struct addrinfo hints = { + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *result = NULL; + struct addrinfo *ai; + int ret; + + ret = getaddrinfo(control_host, control_port, &hints, &result); + if (ret != 0) { + fprintf(stderr, "%s\n", gai_strerror(ret)); + exit(EXIT_FAILURE); + } + + for (ai = result; ai; ai = ai->ai_next) { + int fd; + int val = 1; + + fd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol); + if (fd < 0) + continue; + + if (!server) { + if (connect(fd, ai->ai_addr, ai->ai_addrlen) < 0) + goto next; + control_fd = fd; + printf("Control socket connected to %s:%s.\n", + control_host, control_port); + break; + } + + if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, + &val, sizeof(val)) < 0) { + perror("setsockopt"); + exit(EXIT_FAILURE); + } + + if (bind(fd, ai->ai_addr, ai->ai_addrlen) < 0) + goto next; + if (listen(fd, 1) < 0) + goto next; + + printf("Control socket listening on %s:%s\n", + control_host, control_port); + fflush(stdout); + + control_fd = accept(fd, NULL, 0); + close(fd); + + if (control_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + printf("Control socket connection accepted...\n"); + break; + +next: + close(fd); + } + + if (control_fd < 0) { + fprintf(stderr, "Control socket initialization failed. Invalid address %s:%s?\n", + control_host, control_port); + exit(EXIT_FAILURE); + } + + freeaddrinfo(result); +} + +/* Free resources */ +void control_cleanup(void) +{ + close(control_fd); + control_fd = -1; +} + +/* Write a line to the control socket */ +void control_writeln(const char *str) +{ + ssize_t len = strlen(str); + ssize_t ret; + + timeout_begin(TIMEOUT); + + do { + ret = send(control_fd, str, len, MSG_MORE); + timeout_check("send"); + } while (ret < 0 && errno == EINTR); + + if (ret != len) { + perror("send"); + exit(EXIT_FAILURE); + } + + do { + ret = send(control_fd, "\n", 1, 0); + timeout_check("send"); + } while (ret < 0 && errno == EINTR); + + if (ret != 1) { + perror("send"); + exit(EXIT_FAILURE); + } + + timeout_end(); +} + +/* Return the next line from the control socket (without the trailing newline). + * + * The program terminates if a timeout occurs. + * + * The caller must free() the returned string. + */ +char *control_readln(void) +{ + char *buf = NULL; + size_t idx = 0; + size_t buflen = 0; + + timeout_begin(TIMEOUT); + + for (;;) { + ssize_t ret; + + if (idx >= buflen) { + char *new_buf; + + new_buf = realloc(buf, buflen + 80); + if (!new_buf) { + perror("realloc"); + exit(EXIT_FAILURE); + } + + buf = new_buf; + buflen += 80; + } + + do { + ret = recv(control_fd, &buf[idx], 1, 0); + timeout_check("recv"); + } while (ret < 0 && errno == EINTR); + + if (ret == 0) { + fprintf(stderr, "unexpected EOF on control socket\n"); + exit(EXIT_FAILURE); + } + + if (ret != 1) { + perror("recv"); + exit(EXIT_FAILURE); + } + + if (buf[idx] == '\n') { + buf[idx] = '\0'; + break; + } + + idx++; + } + + timeout_end(); + + return buf; +} + +/* Wait until a given line is received or a timeout occurs */ +void control_expectln(const char *str) +{ + char *line; + + line = control_readln(); + if (strcmp(str, line) != 0) { + fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n", + str, line); + exit(EXIT_FAILURE); + } + + free(line); +} diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h new file mode 100644 index 000000000000..54a07efd267c --- /dev/null +++ b/tools/testing/vsock/control.h @@ -0,0 +1,13 @@ +#ifndef CONTROL_H +#define CONTROL_H + +#include <stdbool.h> + +void control_init(const char *control_host, const char *control_port, + bool server); +void control_cleanup(void); +void control_writeln(const char *str); +char *control_readln(void); +void control_expectln(const char *str); + +#endif /* CONTROL_H */ diff --git a/tools/testing/vsock/timeout.c b/tools/testing/vsock/timeout.c new file mode 100644 index 000000000000..c49b3003b2db --- /dev/null +++ b/tools/testing/vsock/timeout.c @@ -0,0 +1,64 @@ +/* Timeout API for single-threaded programs that use blocking + * syscalls (read/write/send/recv/connect/accept). + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +/* Use the following pattern: + * + * timeout_begin(TIMEOUT); + * do { + * ret = accept(...); + * timeout_check("accept"); + * } while (ret < 0 && ret == EINTR); + * timeout_end(); + */ + +#include <stdlib.h> +#include <stdbool.h> +#include <unistd.h> +#include <stdio.h> +#include "timeout.h" + +static volatile bool timeout; + +/* SIGALRM handler function. Do not use sleep(2), alarm(2), or + * setitimer(2) while using this API - they may interfere with each + * other. + */ +void sigalrm(int signo) +{ + timeout = true; +} + +/* Start a timeout. Call timeout_check() to verify that the timeout hasn't + * expired. timeout_end() must be called to stop the timeout. Timeouts cannot + * be nested. + */ +void timeout_begin(unsigned int seconds) +{ + alarm(seconds); +} + +/* Exit with an error message if the timeout has expired */ +void timeout_check(const char *operation) +{ + if (timeout) { + fprintf(stderr, "%s timed out\n", operation); + exit(EXIT_FAILURE); + } +} + +/* Stop a timeout */ +void timeout_end(void) +{ + alarm(0); + timeout = false; +} diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h new file mode 100644 index 000000000000..77db9ce9860a --- /dev/null +++ b/tools/testing/vsock/timeout.h @@ -0,0 +1,14 @@ +#ifndef TIMEOUT_H +#define TIMEOUT_H + +enum { + /* Default timeout */ + TIMEOUT = 10 /* seconds */ +}; + +void sigalrm(int signo); +void timeout_begin(unsigned int seconds); +void timeout_check(const char *operation); +void timeout_end(void); + +#endif /* TIMEOUT_H */ diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c new file mode 100644 index 000000000000..e896a4af52f4 --- /dev/null +++ b/tools/testing/vsock/vsock_diag_test.c @@ -0,0 +1,681 @@ +/* + * vsock_diag_test - vsock_diag.ko test suite + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <getopt.h> +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <signal.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <linux/list.h> +#include <linux/net.h> +#include <linux/netlink.h> +#include <linux/sock_diag.h> +#include <netinet/tcp.h> + +#include "../../../include/uapi/linux/vm_sockets.h" +#include "../../../include/uapi/linux/vm_sockets_diag.h" + +#include "timeout.h" +#include "control.h" + +enum test_mode { + TEST_MODE_UNSET, + TEST_MODE_CLIENT, + TEST_MODE_SERVER +}; + +/* Per-socket status */ +struct vsock_stat { + struct list_head list; + struct vsock_diag_msg msg; +}; + +static const char *sock_type_str(int type) +{ + switch (type) { + case SOCK_DGRAM: + return "DGRAM"; + case SOCK_STREAM: + return "STREAM"; + default: + return "INVALID TYPE"; + } +} + +static const char *sock_state_str(int state) +{ + switch (state) { + case TCP_CLOSE: + return "UNCONNECTED"; + case TCP_SYN_SENT: + return "CONNECTING"; + case TCP_ESTABLISHED: + return "CONNECTED"; + case TCP_CLOSING: + return "DISCONNECTING"; + case TCP_LISTEN: + return "LISTEN"; + default: + return "INVALID STATE"; + } +} + +static const char *sock_shutdown_str(int shutdown) +{ + switch (shutdown) { + case 1: + return "RCV_SHUTDOWN"; + case 2: + return "SEND_SHUTDOWN"; + case 3: + return "RCV_SHUTDOWN | SEND_SHUTDOWN"; + default: + return "0"; + } +} + +static void print_vsock_addr(FILE *fp, unsigned int cid, unsigned int port) +{ + if (cid == VMADDR_CID_ANY) + fprintf(fp, "*:"); + else + fprintf(fp, "%u:", cid); + + if (port == VMADDR_PORT_ANY) + fprintf(fp, "*"); + else + fprintf(fp, "%u", port); +} + +static void print_vsock_stat(FILE *fp, struct vsock_stat *st) +{ + print_vsock_addr(fp, st->msg.vdiag_src_cid, st->msg.vdiag_src_port); + fprintf(fp, " "); + print_vsock_addr(fp, st->msg.vdiag_dst_cid, st->msg.vdiag_dst_port); + fprintf(fp, " %s %s %s %u\n", + sock_type_str(st->msg.vdiag_type), + sock_state_str(st->msg.vdiag_state), + sock_shutdown_str(st->msg.vdiag_shutdown), + st->msg.vdiag_ino); +} + +static void print_vsock_stats(FILE *fp, struct list_head *head) +{ + struct vsock_stat *st; + + list_for_each_entry(st, head, list) + print_vsock_stat(fp, st); +} + +static struct vsock_stat *find_vsock_stat(struct list_head *head, int fd) +{ + struct vsock_stat *st; + struct stat stat; + + if (fstat(fd, &stat) < 0) { + perror("fstat"); + exit(EXIT_FAILURE); + } + + list_for_each_entry(st, head, list) + if (st->msg.vdiag_ino == stat.st_ino) + return st; + + fprintf(stderr, "cannot find fd %d\n", fd); + exit(EXIT_FAILURE); +} + +static void check_no_sockets(struct list_head *head) +{ + if (!list_empty(head)) { + fprintf(stderr, "expected no sockets\n"); + print_vsock_stats(stderr, head); + exit(1); + } +} + +static void check_num_sockets(struct list_head *head, int expected) +{ + struct list_head *node; + int n = 0; + + list_for_each(node, head) + n++; + + if (n != expected) { + fprintf(stderr, "expected %d sockets, found %d\n", + expected, n); + print_vsock_stats(stderr, head); + exit(EXIT_FAILURE); + } +} + +static void check_socket_state(struct vsock_stat *st, __u8 state) +{ + if (st->msg.vdiag_state != state) { + fprintf(stderr, "expected socket state %#x, got %#x\n", + state, st->msg.vdiag_state); + exit(EXIT_FAILURE); + } +} + +static void send_req(int fd) +{ + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK, + }; + struct { + struct nlmsghdr nlh; + struct vsock_diag_req vreq; + } req = { + .nlh = { + .nlmsg_len = sizeof(req), + .nlmsg_type = SOCK_DIAG_BY_FAMILY, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP, + }, + .vreq = { + .sdiag_family = AF_VSOCK, + .vdiag_states = ~(__u32)0, + }, + }; + struct iovec iov = { + .iov_base = &req, + .iov_len = sizeof(req), + }; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1, + }; + + for (;;) { + if (sendmsg(fd, &msg, 0) < 0) { + if (errno == EINTR) + continue; + + perror("sendmsg"); + exit(EXIT_FAILURE); + } + + return; + } +} + +static ssize_t recv_resp(int fd, void *buf, size_t len) +{ + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK, + }; + struct iovec iov = { + .iov_base = buf, + .iov_len = len, + }; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1, + }; + ssize_t ret; + + do { + ret = recvmsg(fd, &msg, 0); + } while (ret < 0 && errno == EINTR); + + if (ret < 0) { + perror("recvmsg"); + exit(EXIT_FAILURE); + } + + return ret; +} + +static void add_vsock_stat(struct list_head *sockets, + const struct vsock_diag_msg *resp) +{ + struct vsock_stat *st; + + st = malloc(sizeof(*st)); + if (!st) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + st->msg = *resp; + list_add_tail(&st->list, sockets); +} + +/* + * Read vsock stats into a list. + */ +static void read_vsock_stat(struct list_head *sockets) +{ + long buf[8192 / sizeof(long)]; + int fd; + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + send_req(fd); + + for (;;) { + const struct nlmsghdr *h; + ssize_t ret; + + ret = recv_resp(fd, buf, sizeof(buf)); + if (ret == 0) + goto done; + if (ret < sizeof(*h)) { + fprintf(stderr, "short read of %zd bytes\n", ret); + exit(EXIT_FAILURE); + } + + h = (struct nlmsghdr *)buf; + + while (NLMSG_OK(h, ret)) { + if (h->nlmsg_type == NLMSG_DONE) + goto done; + + if (h->nlmsg_type == NLMSG_ERROR) { + const struct nlmsgerr *err = NLMSG_DATA(h); + + if (h->nlmsg_len < NLMSG_LENGTH(sizeof(*err))) + fprintf(stderr, "NLMSG_ERROR\n"); + else { + errno = -err->error; + perror("NLMSG_ERROR"); + } + + exit(EXIT_FAILURE); + } + + if (h->nlmsg_type != SOCK_DIAG_BY_FAMILY) { + fprintf(stderr, "unexpected nlmsg_type %#x\n", + h->nlmsg_type); + exit(EXIT_FAILURE); + } + if (h->nlmsg_len < + NLMSG_LENGTH(sizeof(struct vsock_diag_msg))) { + fprintf(stderr, "short vsock_diag_msg\n"); + exit(EXIT_FAILURE); + } + + add_vsock_stat(sockets, NLMSG_DATA(h)); + + h = NLMSG_NEXT(h, ret); + } + } + +done: + close(fd); +} + +static void free_sock_stat(struct list_head *sockets) +{ + struct vsock_stat *st; + struct vsock_stat *next; + + list_for_each_entry_safe(st, next, sockets, list) + free(st); +} + +static void test_no_sockets(unsigned int peer_cid) +{ + LIST_HEAD(sockets); + + read_vsock_stat(&sockets); + + check_no_sockets(&sockets); + + free_sock_stat(&sockets); +} + +static void test_listen_socket_server(unsigned int peer_cid) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = VMADDR_CID_ANY, + }, + }; + LIST_HEAD(sockets); + struct vsock_stat *st; + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("bind"); + exit(EXIT_FAILURE); + } + + if (listen(fd, 1) < 0) { + perror("listen"); + exit(EXIT_FAILURE); + } + + read_vsock_stat(&sockets); + + check_num_sockets(&sockets, 1); + st = find_vsock_stat(&sockets, fd); + check_socket_state(st, TCP_LISTEN); + + close(fd); + free_sock_stat(&sockets); +} + +static void test_connect_client(unsigned int peer_cid) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = peer_cid, + }, + }; + int fd; + int ret; + LIST_HEAD(sockets); + struct vsock_stat *st; + + control_expectln("LISTENING"); + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + read_vsock_stat(&sockets); + + check_num_sockets(&sockets, 1); + st = find_vsock_stat(&sockets, fd); + check_socket_state(st, TCP_ESTABLISHED); + + control_expectln("DONE"); + control_writeln("DONE"); + + close(fd); + free_sock_stat(&sockets); +} + +static void test_connect_server(unsigned int peer_cid) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = VMADDR_CID_ANY, + }, + }; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } clientaddr; + socklen_t clientaddr_len = sizeof(clientaddr.svm); + LIST_HEAD(sockets); + struct vsock_stat *st; + int fd; + int client_fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("bind"); + exit(EXIT_FAILURE); + } + + if (listen(fd, 1) < 0) { + perror("listen"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTENING"); + + timeout_begin(TIMEOUT); + do { + client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); + timeout_check("accept"); + } while (client_fd < 0 && errno == EINTR); + timeout_end(); + + if (client_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + if (clientaddr.sa.sa_family != AF_VSOCK) { + fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n", + clientaddr.sa.sa_family); + exit(EXIT_FAILURE); + } + if (clientaddr.svm.svm_cid != peer_cid) { + fprintf(stderr, "expected peer CID %u from accept(2), got %u\n", + peer_cid, clientaddr.svm.svm_cid); + exit(EXIT_FAILURE); + } + + read_vsock_stat(&sockets); + + check_num_sockets(&sockets, 2); + find_vsock_stat(&sockets, fd); + st = find_vsock_stat(&sockets, client_fd); + check_socket_state(st, TCP_ESTABLISHED); + + control_writeln("DONE"); + control_expectln("DONE"); + + close(client_fd); + close(fd); + free_sock_stat(&sockets); +} + +static struct { + const char *name; + void (*run_client)(unsigned int peer_cid); + void (*run_server)(unsigned int peer_cid); +} test_cases[] = { + { + .name = "No sockets", + .run_server = test_no_sockets, + }, + { + .name = "Listen socket", + .run_server = test_listen_socket_server, + }, + { + .name = "Connect", + .run_client = test_connect_client, + .run_server = test_connect_server, + }, + {}, +}; + +static void init_signals(void) +{ + struct sigaction act = { + .sa_handler = sigalrm, + }; + + sigaction(SIGALRM, &act, NULL); + signal(SIGPIPE, SIG_IGN); +} + +static unsigned int parse_cid(const char *str) +{ + char *endptr = NULL; + unsigned long int n; + + errno = 0; + n = strtoul(str, &endptr, 10); + if (errno || *endptr != '\0') { + fprintf(stderr, "malformed CID \"%s\"\n", str); + exit(EXIT_FAILURE); + } + return n; +} + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "control-host", + .has_arg = required_argument, + .val = 'H', + }, + { + .name = "control-port", + .has_arg = required_argument, + .val = 'P', + }, + { + .name = "mode", + .has_arg = required_argument, + .val = 'm', + }, + { + .name = "peer-cid", + .has_arg = required_argument, + .val = 'p', + }, + { + .name = "help", + .has_arg = no_argument, + .val = '?', + }, + {}, +}; + +static void usage(void) +{ + fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid>\n" + "\n" + " Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n" + " Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n" + "\n" + "Run vsock_diag.ko tests. Must be launched in both\n" + "guest and host. One side must use --mode=client and\n" + "the other side must use --mode=server.\n" + "\n" + "A TCP control socket connection is used to coordinate tests\n" + "between the client and the server. The server requires a\n" + "listen address and the client requires an address to\n" + "connect to.\n" + "\n" + "The CID of the other side must be given with --peer-cid=<cid>.\n"); + exit(EXIT_FAILURE); +} + +int main(int argc, char **argv) +{ + const char *control_host = NULL; + const char *control_port = NULL; + int mode = TEST_MODE_UNSET; + unsigned int peer_cid = VMADDR_CID_ANY; + int i; + + init_signals(); + + for (;;) { + int opt = getopt_long(argc, argv, optstring, longopts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'H': + control_host = optarg; + break; + case 'm': + if (strcmp(optarg, "client") == 0) + mode = TEST_MODE_CLIENT; + else if (strcmp(optarg, "server") == 0) + mode = TEST_MODE_SERVER; + else { + fprintf(stderr, "--mode must be \"client\" or \"server\"\n"); + return EXIT_FAILURE; + } + break; + case 'p': + peer_cid = parse_cid(optarg); + break; + case 'P': + control_port = optarg; + break; + case '?': + default: + usage(); + } + } + + if (!control_port) + usage(); + if (mode == TEST_MODE_UNSET) + usage(); + if (peer_cid == VMADDR_CID_ANY) + usage(); + + if (!control_host) { + if (mode != TEST_MODE_SERVER) + usage(); + control_host = "0.0.0.0"; + } + + control_init(control_host, control_port, mode == TEST_MODE_SERVER); + + for (i = 0; test_cases[i].name; i++) { + void (*run)(unsigned int peer_cid); + + printf("%s...", test_cases[i].name); + fflush(stdout); + + if (mode == TEST_MODE_CLIENT) + run = test_cases[i].run_client; + else + run = test_cases[i].run_server; + + if (run) + run(peer_cid); + + printf("ok\n"); + } + + control_cleanup(); + return EXIT_SUCCESS; +} |