diff options
Diffstat (limited to 'tools')
97 files changed, 4864 insertions, 832 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2acf9b336371..defa5bb881f4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6913,6 +6913,12 @@ enum { BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; +enum { + SK_BPF_CB_TX_TIMESTAMPING = 1<<0, + SK_BPF_CB_MASK = (SK_BPF_CB_TX_TIMESTAMPING - 1) | + SK_BPF_CB_TX_TIMESTAMPING +}; + /* List of known BPF sock_ops operators. * New entries can only be added at the end */ @@ -7025,6 +7031,29 @@ enum { * by the kernel or the * earlier bpf-progs. */ + BPF_SOCK_OPS_TSTAMP_SCHED_CB, /* Called when skb is passing + * through dev layer when + * SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SND_SW_CB, /* Called when skb is about to send + * to the nic when SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SND_HW_CB, /* Called in hardware phase when + * SK_BPF_CB_TX_TIMESTAMPING feature + * is on. + */ + BPF_SOCK_OPS_TSTAMP_ACK_CB, /* Called when all the skbs in the + * same sendmsg call are acked + * when SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SENDMSG_CB, /* Called when every sendmsg syscall + * is triggered. It's used to correlate + * sendmsg timestamp with corresponding + * tskey. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -7091,6 +7120,7 @@ enum { TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ + SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ }; enum { diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index 42ec5ddaab8d..42869770776e 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -127,6 +127,12 @@ struct xdp_options { */ #define XDP_TXMD_FLAGS_CHECKSUM (1 << 1) +/* Request launch time hardware offload. The device will schedule the packet for + * transmission at a pre-determined time called launch time. The value of + * launch time is communicated via launch_time field of struct xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_LAUNCH_TIME (1 << 2) + /* AF_XDP offloads request. 'request' union member is consumed by the driver * when the packet is being transmitted. 'completion' union member is * filled by the driver when the transmit completion arrives. @@ -142,6 +148,10 @@ struct xsk_tx_metadata { __u16 csum_start; /* Offset from csum_start where checksum should be stored. */ __u16 csum_offset; + + /* XDP_TXMD_FLAGS_LAUNCH_TIME */ + /* Launch time in nanosecond against the PTP HW Clock */ + __u64 launch_time; } request; struct { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index e4be227d3ad6..7600bf62dbdf 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -59,10 +59,13 @@ enum netdev_xdp_rx_metadata { * by the driver. * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the * driver. + * @NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO: Launch time HW offload is supported + * by the driver. */ enum netdev_xsk_flags { NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1, NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, + NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO = 4, }; enum netdev_queue_type { @@ -87,6 +90,11 @@ enum { }; enum { + __NETDEV_A_IO_URING_PROVIDER_INFO_MAX, + NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1) +}; + +enum { NETDEV_A_PAGE_POOL_ID = 1, NETDEV_A_PAGE_POOL_IFINDEX, NETDEV_A_PAGE_POOL_NAPI_ID, @@ -94,6 +102,7 @@ enum { NETDEV_A_PAGE_POOL_INFLIGHT_MEM, NETDEV_A_PAGE_POOL_DETACH_TIME, NETDEV_A_PAGE_POOL_DMABUF, + NETDEV_A_PAGE_POOL_IO_URING, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) @@ -131,11 +140,18 @@ enum { }; enum { + __NETDEV_A_XSK_INFO_MAX, + NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1) +}; + +enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, NETDEV_A_QUEUE_DMABUF, + NETDEV_A_QUEUE_IO_URING, + NETDEV_A_QUEUE_XSK, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index 0712b5e82eb7..f3269ce39e5b 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -17,10 +17,13 @@ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h) CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ - $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) + $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) \ + $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_GENERATED_H,ethtool_netlink_generated.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h) +CFLAGS_net_shaper:=$(call get_hdr_inc,_LINUX_NET_SHAPER_H,net_shaper.h) CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h) +CFLAGS_nl80211:=$(call get_hdr_inc,__LINUX_NL802121_H,nl80211.h) CFLAGS_nlctrl:=$(call get_hdr_inc,__LINUX_GENERIC_NETLINK_H,genetlink.h) CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h) CFLAGS_ovs_datapath:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 08f8bf89cfc2..dcc2c6b298d6 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -536,9 +536,11 @@ class YnlFamily(SpecFamily): try: return int(value) except (ValueError, TypeError) as e: - if 'enum' not in attr_spec: - raise e - return self._encode_enum(attr_spec, value) + if 'enum' in attr_spec: + return self._encode_enum(attr_spec, value) + if attr_spec.display_hint: + return self._from_string(value, attr_spec) + raise e def _add_attr(self, space, name, value, search_attrs): try: @@ -571,7 +573,10 @@ class YnlFamily(SpecFamily): if isinstance(value, bytes): attr_payload = value elif isinstance(value, str): - attr_payload = bytes.fromhex(value) + if attr.display_hint: + attr_payload = self._from_string(value, attr) + else: + attr_payload = bytes.fromhex(value) elif isinstance(value, dict) and attr.struct_name: attr_payload = self._encode_struct(attr.struct_name, value) else: @@ -627,6 +632,11 @@ class YnlFamily(SpecFamily): decoded = self._decode_struct(attr.raw, attr_spec.struct_name) elif attr_spec.sub_type: decoded = attr.as_c_array(attr_spec.sub_type) + if 'enum' in attr_spec: + decoded = [ self._decode_enum(x, attr_spec) for x in decoded ] + elif attr_spec.display_hint: + decoded = [ self._formatted_string(x, attr_spec.display_hint) + for x in decoded ] else: decoded = attr.as_bin() if attr_spec.display_hint: @@ -644,15 +654,17 @@ class YnlFamily(SpecFamily): subattrs = self._decode(NlAttrs(item.raw), attr_spec['nested-attributes']) decoded.append({ item.type: subattrs }) elif attr_spec["sub-type"] == 'binary': - subattrs = item.as_bin() + subattr = item.as_bin() if attr_spec.display_hint: - subattrs = self._formatted_string(subattrs, attr_spec.display_hint) - decoded.append(subattrs) + subattr = self._formatted_string(subattr, attr_spec.display_hint) + decoded.append(subattr) elif attr_spec["sub-type"] in NlAttr.type_formats: - subattrs = item.as_scalar(attr_spec['sub-type'], attr_spec.byte_order) - if attr_spec.display_hint: - subattrs = self._formatted_string(subattrs, attr_spec.display_hint) - decoded.append(subattrs) + subattr = item.as_scalar(attr_spec['sub-type'], attr_spec.byte_order) + if 'enum' in attr_spec: + subattr = self._decode_enum(subattr, attr_spec) + elif attr_spec.display_hint: + subattr = self._formatted_string(subattr, attr_spec.display_hint) + decoded.append(subattr) else: raise Exception(f'Unknown {attr_spec["sub-type"]} with name {attr_spec["name"]}') return decoded @@ -899,6 +911,18 @@ class YnlFamily(SpecFamily): formatted = raw return formatted + def _from_string(self, string, attr_spec): + if attr_spec.display_hint in ['ipv4', 'ipv6']: + ip = ipaddress.ip_address(string) + if attr_spec['type'] == 'binary': + raw = ip.packed + else: + raw = int(ip) + else: + raise Exception(f"Display hint '{attr_spec.display_hint}' not implemented" + f" when parsing '{attr_spec['name']}'") + return raw + def handle_ntf(self, decoded): msg = dict() if self.include_raw: diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index c2eabc90dce8..a1427c537030 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -74,6 +74,8 @@ class Type(SpecAttr): self.c_name = c_lower(self.name) if self.c_name in _C_KW: self.c_name += '_' + if self.c_name[0].isdigit(): + self.c_name = '_' + self.c_name # Added by resolve(): self.enum_name = None @@ -100,7 +102,7 @@ class Type(SpecAttr): if isinstance(value, int): return value if value in self.family.consts: - raise Exception("Resolving family constants not implemented, yet") + return self.family.consts[value]["value"] return limit_to_number(value) def get_limit_str(self, limit, default=None, suffix=''): @@ -110,6 +112,9 @@ class Type(SpecAttr): if isinstance(value, int): return str(value) + suffix if value in self.family.consts: + const = self.family.consts[value] + if const.get('header'): + return c_upper(value) return c_upper(f"{self.family['name']}-{value}") return c_upper(value) @@ -683,7 +688,10 @@ class TypeArrayNest(Type): raise Exception(f"Sub-type {self.attr['sub-type']} not supported yet") def _attr_typol(self): - return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, ' + if self.attr['sub-type'] in scalars: + return f'.type = YNL_PT_U{c_upper(self.sub_type[1:])}, ' + else: + return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, ' def _attr_get(self, ri, var): local_vars = ['const struct nlattr *attr2;'] @@ -885,7 +893,7 @@ class AttrSet(SpecAttrSet): elif elem['type'] == 'nest': t = TypeNest(self.family, self, elem, value) elif elem['type'] == 'indexed-array' and 'sub-type' in elem: - if elem["sub-type"] == 'nest': + if elem["sub-type"] in ['nest', 'u32']: t = TypeArrayNest(self.family, self, elem, value) else: raise Exception(f'new_attr: unsupported sub-type {elem["sub-type"]}') @@ -1437,7 +1445,7 @@ class CodeWriter: self._ifdef_block = config_option -scalars = {'u8', 'u16', 'u32', 'u64', 's32', 's64', 'uint', 'sint'} +scalars = {'u8', 'u16', 'u32', 'u64', 's8', 's16', 's32', 's64', 'uint', 'sint'} direction_to_suffix = { 'reply': '_rsp', @@ -1669,6 +1677,9 @@ def _multi_parse(ri, struct, init_lines, local_vars): if aspec["sub-type"] == 'nest': local_vars.append(f'const struct nlattr *attr_{aspec.c_name};') array_nests.add(arg) + elif aspec['sub-type'] in scalars: + local_vars.append(f'const struct nlattr *attr_{aspec.c_name};') + array_nests.add(arg) else: raise Exception(f'Not supported sub-type {aspec["sub-type"]}') if 'multi-attr' in aspec: @@ -1724,11 +1735,17 @@ def _multi_parse(ri, struct, init_lines, local_vars): ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') - ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") + if 'nested-attributes' in aspec: + ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") ri.cw.block_start(line=f"ynl_attr_for_each_nested(attr, attr_{aspec.c_name})") - ri.cw.p(f"parg.data = &dst->{aspec.c_name}[i];") - ri.cw.p(f"if ({aspec.nested_render_name}_parse(&parg, attr, ynl_attr_type(attr)))") - ri.cw.p('return YNL_PARSE_CB_ERROR;') + if 'nested-attributes' in aspec: + ri.cw.p(f"parg.data = &dst->{aspec.c_name}[i];") + ri.cw.p(f"if ({aspec.nested_render_name}_parse(&parg, attr, ynl_attr_type(attr)))") + ri.cw.p('return YNL_PARSE_CB_ERROR;') + elif aspec.sub_type in scalars: + ri.cw.p(f"dst->{aspec.c_name}[i] = ynl_attr_get_{aspec.sub_type}(attr);") + else: + raise Exception(f"Nest parsing type not supported in {aspec['name']}") ri.cw.p('i++;') ri.cw.block_end() ri.cw.block_end() @@ -2549,6 +2566,9 @@ def render_uapi(family, cw): defines = [] for const in family['definitions']: + if const.get('header'): + continue + if const['type'] != 'const': cw.writes_defines(defines) defines = [] diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 80844a5fb1fe..29541d486c5e 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -548,6 +548,34 @@ void close_netns(struct nstoken *token) free(token); } +int open_tuntap(const char *dev_name, bool need_mac) +{ + int err = 0; + struct ifreq ifr; + int fd = open("/dev/net/tun", O_RDWR); + + if (!ASSERT_GE(fd, 0, "open(/dev/net/tun)")) + return -1; + + ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN); + strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1); + ifr.ifr_name[IFNAMSIZ - 1] = '\0'; + + err = ioctl(fd, TUNSETIFF, &ifr); + if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) { + close(fd); + return -1; + } + + err = fcntl(fd, F_SETFL, O_NONBLOCK); + if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) { + close(fd); + return -1; + } + + return fd; +} + int get_socket_local_port(int sock_fd) { struct sockaddr_storage addr; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index ebec8a8d6f81..9235976d0c50 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -8,6 +8,7 @@ typedef __u16 __sum16; #include <linux/if_ether.h> #include <linux/if_packet.h> +#include <linux/if_tun.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/ethtool.h> @@ -85,6 +86,8 @@ int get_socket_local_port(int sock_fd); int get_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param); int set_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param); +int open_tuntap(const char *dev_name, bool need_mac); + struct nstoken; /** * open_netns() - Switch to specified network namespace by name. diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h index fb1eb8c67361..ccec0fcdabc1 100644 --- a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h @@ -5,7 +5,6 @@ #include <time.h> #include <net/if.h> -#include <linux/if_tun.h> #include <linux/icmp.h> #include "test_progs.h" @@ -37,34 +36,6 @@ static inline int netns_delete(void) return system("ip netns del " NETNS ">/dev/null 2>&1"); } -static int open_tuntap(const char *dev_name, bool need_mac) -{ - int err = 0; - struct ifreq ifr; - int fd = open("/dev/net/tun", O_RDWR); - - if (!ASSERT_GT(fd, 0, "open(/dev/net/tun)")) - return -1; - - ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN); - strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1); - ifr.ifr_name[IFNAMSIZ - 1] = '\0'; - - err = ioctl(fd, TUNSETIFF, &ifr); - if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) { - close(fd); - return -1; - } - - err = fcntl(fd, F_SETFL, O_NONBLOCK); - if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) { - close(fd); - return -1; - } - - return fd; -} - #define ICMP_PAYLOAD_SIZE 100 /* Match an ICMP packet with payload len ICMP_PAYLOAD_SIZE */ diff --git a/tools/testing/selftests/bpf/prog_tests/net_timestamping.c b/tools/testing/selftests/bpf/prog_tests/net_timestamping.c new file mode 100644 index 000000000000..dbfd87499b6b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/net_timestamping.c @@ -0,0 +1,239 @@ +#include <linux/net_tstamp.h> +#include <sys/time.h> +#include <linux/errqueue.h> +#include "test_progs.h" +#include "network_helpers.h" +#include "net_timestamping.skel.h" + +#define CG_NAME "/net-timestamping-test" +#define NSEC_PER_SEC 1000000000LL + +static const char addr4_str[] = "127.0.0.1"; +static const char addr6_str[] = "::1"; +static struct net_timestamping *skel; +static const int cfg_payload_len = 30; +static struct timespec usr_ts; +static u64 delay_tolerance_nsec = 10000000000; /* 10 seconds */ +int SK_TS_SCHED; +int SK_TS_TXSW; +int SK_TS_ACK; + +static int64_t timespec_to_ns64(struct timespec *ts) +{ + return ts->tv_sec * NSEC_PER_SEC + ts->tv_nsec; +} + +static void validate_key(int tskey, int tstype) +{ + static int expected_tskey = -1; + + if (tstype == SCM_TSTAMP_SCHED) + expected_tskey = cfg_payload_len - 1; + + ASSERT_EQ(expected_tskey, tskey, "tskey mismatch"); + + expected_tskey = tskey; +} + +static void validate_timestamp(struct timespec *cur, struct timespec *prev) +{ + int64_t cur_ns, prev_ns; + + cur_ns = timespec_to_ns64(cur); + prev_ns = timespec_to_ns64(prev); + + ASSERT_LT(cur_ns - prev_ns, delay_tolerance_nsec, "latency"); +} + +static void test_socket_timestamp(struct scm_timestamping *tss, int tstype, + int tskey) +{ + static struct timespec prev_ts; + + validate_key(tskey, tstype); + + switch (tstype) { + case SCM_TSTAMP_SCHED: + validate_timestamp(&tss->ts[0], &usr_ts); + SK_TS_SCHED += 1; + break; + case SCM_TSTAMP_SND: + validate_timestamp(&tss->ts[0], &prev_ts); + SK_TS_TXSW += 1; + break; + case SCM_TSTAMP_ACK: + validate_timestamp(&tss->ts[0], &prev_ts); + SK_TS_ACK += 1; + break; + } + + prev_ts = tss->ts[0]; +} + +static void test_recv_errmsg_cmsg(struct msghdr *msg) +{ + struct sock_extended_err *serr = NULL; + struct scm_timestamping *tss = NULL; + struct cmsghdr *cm; + + for (cm = CMSG_FIRSTHDR(msg); + cm && cm->cmsg_len; + cm = CMSG_NXTHDR(msg, cm)) { + if (cm->cmsg_level == SOL_SOCKET && + cm->cmsg_type == SCM_TIMESTAMPING) { + tss = (void *)CMSG_DATA(cm); + } else if ((cm->cmsg_level == SOL_IP && + cm->cmsg_type == IP_RECVERR) || + (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type == IPV6_RECVERR) || + (cm->cmsg_level == SOL_PACKET && + cm->cmsg_type == PACKET_TX_TIMESTAMP)) { + serr = (void *)CMSG_DATA(cm); + ASSERT_EQ(serr->ee_origin, SO_EE_ORIGIN_TIMESTAMPING, + "cmsg type"); + } + + if (serr && tss) + test_socket_timestamp(tss, serr->ee_info, + serr->ee_data); + } +} + +static bool socket_recv_errmsg(int fd) +{ + static char ctrl[1024 /* overprovision*/]; + char data[cfg_payload_len]; + static struct msghdr msg; + struct iovec entry; + int n = 0; + + memset(&msg, 0, sizeof(msg)); + memset(&entry, 0, sizeof(entry)); + memset(ctrl, 0, sizeof(ctrl)); + + entry.iov_base = data; + entry.iov_len = cfg_payload_len; + msg.msg_iov = &entry; + msg.msg_iovlen = 1; + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_control = ctrl; + msg.msg_controllen = sizeof(ctrl); + + n = recvmsg(fd, &msg, MSG_ERRQUEUE); + if (n == -1) + ASSERT_EQ(errno, EAGAIN, "recvmsg MSG_ERRQUEUE"); + + if (n >= 0) + test_recv_errmsg_cmsg(&msg); + + return n == -1; +} + +static void test_socket_timestamping(int fd) +{ + while (!socket_recv_errmsg(fd)); + + ASSERT_EQ(SK_TS_SCHED, 1, "SCM_TSTAMP_SCHED"); + ASSERT_EQ(SK_TS_TXSW, 1, "SCM_TSTAMP_SND"); + ASSERT_EQ(SK_TS_ACK, 1, "SCM_TSTAMP_ACK"); + + SK_TS_SCHED = 0; + SK_TS_TXSW = 0; + SK_TS_ACK = 0; +} + +static void test_tcp(int family, bool enable_socket_timestamping) +{ + struct net_timestamping__bss *bss; + char buf[cfg_payload_len]; + int sfd = -1, cfd = -1; + unsigned int sock_opt; + struct netns_obj *ns; + int cg_fd; + int ret; + + cg_fd = test__join_cgroup(CG_NAME); + if (!ASSERT_OK_FD(cg_fd, "join cgroup")) + return; + + ns = netns_new("net_timestamping_ns", true); + if (!ASSERT_OK_PTR(ns, "create ns")) + goto out; + + skel = net_timestamping__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skel")) + goto out; + + if (!ASSERT_OK(net_timestamping__attach(skel), "attach skel")) + goto out; + + skel->links.skops_sockopt = + bpf_program__attach_cgroup(skel->progs.skops_sockopt, cg_fd); + if (!ASSERT_OK_PTR(skel->links.skops_sockopt, "attach cgroup")) + goto out; + + bss = skel->bss; + memset(bss, 0, sizeof(*bss)); + + skel->bss->monitored_pid = getpid(); + + sfd = start_server(family, SOCK_STREAM, + family == AF_INET6 ? addr6_str : addr4_str, 0, 0); + if (!ASSERT_OK_FD(sfd, "start_server")) + goto out; + + cfd = connect_to_fd(sfd, 0); + if (!ASSERT_OK_FD(cfd, "connect_to_fd_server")) + goto out; + + if (enable_socket_timestamping) { + sock_opt = SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_ID | + SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK; + ret = setsockopt(cfd, SOL_SOCKET, SO_TIMESTAMPING, + (char *) &sock_opt, sizeof(sock_opt)); + if (!ASSERT_OK(ret, "setsockopt SO_TIMESTAMPING")) + goto out; + + ret = clock_gettime(CLOCK_REALTIME, &usr_ts); + if (!ASSERT_OK(ret, "get user time")) + goto out; + } + + ret = write(cfd, buf, sizeof(buf)); + if (!ASSERT_EQ(ret, sizeof(buf), "send to server")) + goto out; + + if (enable_socket_timestamping) + test_socket_timestamping(cfd); + + ASSERT_EQ(bss->nr_active, 1, "nr_active"); + ASSERT_EQ(bss->nr_snd, 2, "nr_snd"); + ASSERT_EQ(bss->nr_sched, 1, "nr_sched"); + ASSERT_EQ(bss->nr_txsw, 1, "nr_txsw"); + ASSERT_EQ(bss->nr_ack, 1, "nr_ack"); + +out: + if (sfd >= 0) + close(sfd); + if (cfd >= 0) + close(cfd); + net_timestamping__destroy(skel); + netns_free(ns); + close(cg_fd); +} + +void test_net_timestamping(void) +{ + if (test__start_subtest("INET4: bpf timestamping")) + test_tcp(AF_INET, false); + if (test__start_subtest("INET4: bpf and socket timestamping")) + test_tcp(AF_INET, true); + if (test__start_subtest("INET6: bpf timestamping")) + test_tcp(AF_INET6, false); + if (test__start_subtest("INET6: bpf and socket timestamping")) + test_tcp(AF_INET6, true); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index 937da9b7532a..b9d9f0a502ce 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -4,12 +4,20 @@ #include "test_xdp_context_test_run.skel.h" #include "test_xdp_meta.skel.h" -#define TX_ADDR "10.0.0.1" -#define RX_ADDR "10.0.0.2" #define RX_NAME "veth0" #define TX_NAME "veth1" #define TX_NETNS "xdp_context_tx" #define RX_NETNS "xdp_context_rx" +#define TAP_NAME "tap0" +#define TAP_NETNS "xdp_context_tuntap" + +#define TEST_PAYLOAD_LEN 32 +static const __u8 test_payload[TEST_PAYLOAD_LEN] = { + 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, + 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, + 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, + 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, +}; void test_xdp_context_error(int prog_fd, struct bpf_test_run_opts opts, __u32 data_meta, __u32 data, __u32 data_end, @@ -112,7 +120,59 @@ void test_xdp_context_test_run(void) test_xdp_context_test_run__destroy(skel); } -void test_xdp_context_functional(void) +static int send_test_packet(int ifindex) +{ + int n, sock = -1; + __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; + + /* The ethernet header is not relevant for this test and doesn't need to + * be meaningful. + */ + struct ethhdr eth = { 0 }; + + memcpy(packet, ð, sizeof(eth)); + memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN); + + sock = socket(AF_PACKET, SOCK_RAW, IPPROTO_RAW); + if (!ASSERT_GE(sock, 0, "socket")) + goto err; + + struct sockaddr_ll saddr = { + .sll_family = PF_PACKET, + .sll_ifindex = ifindex, + .sll_halen = ETH_ALEN + }; + n = sendto(sock, packet, sizeof(packet), 0, (struct sockaddr *)&saddr, + sizeof(saddr)); + if (!ASSERT_EQ(n, sizeof(packet), "sendto")) + goto err; + + close(sock); + return 0; + +err: + if (sock >= 0) + close(sock); + return -1; +} + +static void assert_test_result(struct test_xdp_meta *skel) +{ + int err; + __u32 map_key = 0; + __u8 map_value[TEST_PAYLOAD_LEN]; + + err = bpf_map__lookup_elem(skel->maps.test_result, &map_key, + sizeof(map_key), &map_value, + TEST_PAYLOAD_LEN, BPF_ANY); + if (!ASSERT_OK(err, "lookup test_result")) + return; + + ASSERT_MEMEQ(&map_value, &test_payload, TEST_PAYLOAD_LEN, + "test_result map contains test payload"); +} + +void test_xdp_context_veth(void) { LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); @@ -120,7 +180,7 @@ void test_xdp_context_functional(void) struct bpf_program *tc_prog, *xdp_prog; struct test_xdp_meta *skel = NULL; struct nstoken *nstoken = NULL; - int rx_ifindex; + int rx_ifindex, tx_ifindex; int ret; tx_ns = netns_new(TX_NETNS, false); @@ -138,7 +198,6 @@ void test_xdp_context_functional(void) if (!ASSERT_OK_PTR(nstoken, "setns rx_ns")) goto close; - SYS(close, "ip addr add " RX_ADDR "/24 dev " RX_NAME); SYS(close, "ip link set dev " RX_NAME " up"); skel = test_xdp_meta__open_and_load(); @@ -179,9 +238,17 @@ void test_xdp_context_functional(void) if (!ASSERT_OK_PTR(nstoken, "setns tx_ns")) goto close; - SYS(close, "ip addr add " TX_ADDR "/24 dev " TX_NAME); SYS(close, "ip link set dev " TX_NAME " up"); - ASSERT_OK(SYS_NOFAIL("ping -c 1 " RX_ADDR), "ping"); + + tx_ifindex = if_nametoindex(TX_NAME); + if (!ASSERT_GE(tx_ifindex, 0, "if_nametoindex tx")) + goto close; + + ret = send_test_packet(tx_ifindex); + if (!ASSERT_OK(ret, "send_test_packet")) + goto close; + + assert_test_result(skel); close: close_netns(nstoken); @@ -190,3 +257,67 @@ close: netns_free(tx_ns); } +void test_xdp_context_tuntap(void) +{ + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + struct netns_obj *ns = NULL; + struct test_xdp_meta *skel = NULL; + __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; + int tap_fd = -1; + int tap_ifindex; + int ret; + + ns = netns_new(TAP_NETNS, true); + if (!ASSERT_OK_PTR(ns, "create and open ns")) + return; + + tap_fd = open_tuntap(TAP_NAME, true); + if (!ASSERT_GE(tap_fd, 0, "open_tuntap")) + goto close; + + SYS(close, "ip link set dev " TAP_NAME " up"); + + skel = test_xdp_meta__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skeleton")) + goto close; + + tap_ifindex = if_nametoindex(TAP_NAME); + if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex")) + goto close; + + tc_hook.ifindex = tap_ifindex; + ret = bpf_tc_hook_create(&tc_hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto close; + + tc_opts.prog_fd = bpf_program__fd(skel->progs.ing_cls); + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto close; + + ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(skel->progs.ing_xdp), + 0, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + /* The ethernet header is not relevant for this test and doesn't need to + * be meaningful. + */ + struct ethhdr eth = { 0 }; + + memcpy(packet, ð, sizeof(eth)); + memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN); + + ret = write(tap_fd, packet, sizeof(packet)); + if (!ASSERT_EQ(ret, sizeof(packet), "write packet")) + goto close; + + assert_test_result(skel); + +close: + if (tap_fd >= 0) + close(tap_fd); + test_xdp_meta__destroy(skel); + netns_free(ns); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c index d22449c69363..164640db3a29 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c @@ -99,10 +99,10 @@ static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp, icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk->icsk_timeout; + timer_expires = icsk->icsk_retransmit_timer.expires; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk->icsk_timeout; + timer_expires = icsk->icsk_retransmit_timer.expires; } else if (timer_pending(&sp->sk_timer)) { timer_active = 2; timer_expires = sp->sk_timer.expires; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c index 8b072666f9d9..591c703f5032 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -99,10 +99,10 @@ static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp, icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk->icsk_timeout; + timer_expires = icsk->icsk_retransmit_timer.expires; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk->icsk_timeout; + timer_expires = icsk->icsk_retransmit_timer.expires; } else if (timer_pending(&sp->sk_timer)) { timer_active = 2; timer_expires = sp->sk_timer.expires; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 59843b430f76..eb6ed1b7b2ef 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -49,6 +49,7 @@ #define TCP_SAVED_SYN 28 #define TCP_CA_NAME_MAX 16 #define TCP_NAGLE_OFF 1 +#define TCP_RTO_MAX_MS 44 #define TCP_ECN_OK 1 #define TCP_ECN_QUEUE_CWR 2 diff --git a/tools/testing/selftests/bpf/progs/net_timestamping.c b/tools/testing/selftests/bpf/progs/net_timestamping.c new file mode 100644 index 000000000000..b4c2f0f2be11 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/net_timestamping.c @@ -0,0 +1,248 @@ +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_kfuncs.h" +#include <errno.h> + +__u32 monitored_pid = 0; + +int nr_active; +int nr_snd; +int nr_passive; +int nr_sched; +int nr_txsw; +int nr_ack; + +struct sk_stg { + __u64 sendmsg_ns; /* record ts when sendmsg is called */ +}; + +struct sk_tskey { + u64 cookie; + u32 tskey; +}; + +struct delay_info { + u64 sendmsg_ns; /* record ts when sendmsg is called */ + u32 sched_delay; /* SCHED_CB - sendmsg_ns */ + u32 snd_sw_delay; /* SND_SW_CB - SCHED_CB */ + u32 ack_delay; /* ACK_CB - SND_SW_CB */ +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct sk_stg); +} sk_stg_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct sk_tskey); + __type(value, struct delay_info); + __uint(max_entries, 1024); +} time_map SEC(".maps"); + +static u64 delay_tolerance_nsec = 10000000000; /* 10 second as an example */ + +extern int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops, u64 flags) __ksym; + +static int bpf_test_sockopt(void *ctx, const struct sock *sk, int expected) +{ + int tmp, new = SK_BPF_CB_TX_TIMESTAMPING; + int opt = SK_BPF_CB_FLAGS; + int level = SOL_SOCKET; + + if (bpf_setsockopt(ctx, level, opt, &new, sizeof(new)) != expected) + return 1; + + if (bpf_getsockopt(ctx, level, opt, &tmp, sizeof(tmp)) != expected || + (!expected && tmp != new)) + return 1; + + return 0; +} + +static bool bpf_test_access_sockopt(void *ctx, const struct sock *sk) +{ + if (bpf_test_sockopt(ctx, sk, -EOPNOTSUPP)) + return true; + return false; +} + +static bool bpf_test_access_load_hdr_opt(struct bpf_sock_ops *skops) +{ + u8 opt[3] = {0}; + int load_flags = 0; + int ret; + + ret = bpf_load_hdr_opt(skops, opt, sizeof(opt), load_flags); + if (ret != -EOPNOTSUPP) + return true; + + return false; +} + +static bool bpf_test_access_cb_flags_set(struct bpf_sock_ops *skops) +{ + int ret; + + ret = bpf_sock_ops_cb_flags_set(skops, 0); + if (ret != -EOPNOTSUPP) + return true; + + return false; +} + +/* In the timestamping callbacks, we're not allowed to call the following + * BPF CALLs for the safety concern. Return false if expected. + */ +static bool bpf_test_access_bpf_calls(struct bpf_sock_ops *skops, + const struct sock *sk) +{ + if (bpf_test_access_sockopt(skops, sk)) + return true; + + if (bpf_test_access_load_hdr_opt(skops)) + return true; + + if (bpf_test_access_cb_flags_set(skops)) + return true; + + return false; +} + +static bool bpf_test_delay(struct bpf_sock_ops *skops, const struct sock *sk) +{ + struct bpf_sock_ops_kern *skops_kern; + u64 timestamp = bpf_ktime_get_ns(); + struct skb_shared_info *shinfo; + struct delay_info dinfo = {0}; + struct sk_tskey key = {0}; + struct delay_info *val; + struct sk_buff *skb; + struct sk_stg *stg; + u64 prior_ts, delay; + + if (bpf_test_access_bpf_calls(skops, sk)) + return false; + + skops_kern = bpf_cast_to_kern_ctx(skops); + skb = skops_kern->skb; + shinfo = bpf_core_cast(skb->head + skb->end, struct skb_shared_info); + + key.cookie = bpf_get_socket_cookie(skops); + if (!key.cookie) + return false; + + if (skops->op == BPF_SOCK_OPS_TSTAMP_SENDMSG_CB) { + stg = bpf_sk_storage_get(&sk_stg_map, (void *)sk, 0, 0); + if (!stg) + return false; + dinfo.sendmsg_ns = stg->sendmsg_ns; + bpf_sock_ops_enable_tx_tstamp(skops_kern, 0); + key.tskey = shinfo->tskey; + if (!key.tskey) + return false; + bpf_map_update_elem(&time_map, &key, &dinfo, BPF_ANY); + return true; + } + + key.tskey = shinfo->tskey; + if (!key.tskey) + return false; + + val = bpf_map_lookup_elem(&time_map, &key); + if (!val) + return false; + + switch (skops->op) { + case BPF_SOCK_OPS_TSTAMP_SCHED_CB: + val->sched_delay = timestamp - val->sendmsg_ns; + delay = val->sched_delay; + break; + case BPF_SOCK_OPS_TSTAMP_SND_SW_CB: + prior_ts = val->sched_delay + val->sendmsg_ns; + val->snd_sw_delay = timestamp - prior_ts; + delay = val->snd_sw_delay; + break; + case BPF_SOCK_OPS_TSTAMP_ACK_CB: + prior_ts = val->snd_sw_delay + val->sched_delay + val->sendmsg_ns; + val->ack_delay = timestamp - prior_ts; + delay = val->ack_delay; + break; + } + + if (delay >= delay_tolerance_nsec) + return false; + + /* Since it's the last one, remove from the map after latency check */ + if (skops->op == BPF_SOCK_OPS_TSTAMP_ACK_CB) + bpf_map_delete_elem(&time_map, &key); + + return true; +} + +SEC("fentry/tcp_sendmsg_locked") +int BPF_PROG(trace_tcp_sendmsg_locked, struct sock *sk, struct msghdr *msg, + size_t size) +{ + __u32 pid = bpf_get_current_pid_tgid() >> 32; + u64 timestamp = bpf_ktime_get_ns(); + u32 flag = sk->sk_bpf_cb_flags; + struct sk_stg *stg; + + if (pid != monitored_pid || !flag) + return 0; + + stg = bpf_sk_storage_get(&sk_stg_map, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!stg) + return 0; + + stg->sendmsg_ns = timestamp; + nr_snd += 1; + return 0; +} + +SEC("sockops") +int skops_sockopt(struct bpf_sock_ops *skops) +{ + struct bpf_sock *bpf_sk = skops->sk; + const struct sock *sk; + + if (!bpf_sk) + return 1; + + sk = (struct sock *)bpf_skc_to_tcp_sock(bpf_sk); + if (!sk) + return 1; + + switch (skops->op) { + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + nr_active += !bpf_test_sockopt(skops, sk, 0); + break; + case BPF_SOCK_OPS_TSTAMP_SENDMSG_CB: + if (bpf_test_delay(skops, sk)) + nr_snd += 1; + break; + case BPF_SOCK_OPS_TSTAMP_SCHED_CB: + if (bpf_test_delay(skops, sk)) + nr_sched += 1; + break; + case BPF_SOCK_OPS_TSTAMP_SND_SW_CB: + if (bpf_test_delay(skops, sk)) + nr_txsw += 1; + break; + case BPF_SOCK_OPS_TSTAMP_ACK_CB: + if (bpf_test_delay(skops, sk)) + nr_ack += 1; + break; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c index 6dd4318debbf..0107a24b7522 100644 --- a/tools/testing/selftests/bpf/progs/setget_sockopt.c +++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c @@ -61,6 +61,9 @@ static const struct sockopt_test sol_tcp_tests[] = { { .opt = TCP_NOTSENT_LOWAT, .new = 1314, .expected = 1314, }, { .opt = TCP_BPF_SOCK_OPS_CB_FLAGS, .new = BPF_SOCK_OPS_ALL_CB_FLAGS, .expected = BPF_SOCK_OPS_ALL_CB_FLAGS, }, + { .opt = TCP_BPF_DELACK_MAX, .new = 30000, .expected = 30000, }, + { .opt = TCP_BPF_RTO_MIN, .new = 30000, .expected = 30000, }, + { .opt = TCP_RTO_MAX_MS, .new = 2000, .expected = 2000, }, { .opt = 0, }, }; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index fe2d71ae0e71..fcf6ca14f2ea 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -4,37 +4,50 @@ #include <bpf/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 META_SIZE 32 + #define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem +/* Demonstrates how metadata can be passed from an XDP program to a TC program + * using bpf_xdp_adjust_meta. + * For the sake of testing the metadata support in drivers, the XDP program uses + * a fixed-size payload after the Ethernet header as metadata. The TC program + * copies the metadata it receives into a map so it can be checked from + * userspace. + */ + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __uint(value_size, META_SIZE); +} test_result SEC(".maps"); + SEC("tc") int ing_cls(struct __sk_buff *ctx) { - __u8 *data, *data_meta, *data_end; - __u32 diff = 0; + __u8 *data, *data_meta; + __u32 key = 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) + if (data_meta + META_SIZE > data) return TC_ACT_SHOT; - diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0]; - diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2]; + bpf_map_update_elem(&test_result, &key, data_meta, BPF_ANY); - return diff ? TC_ACT_SHOT : TC_ACT_OK; + return TC_ACT_SHOT; } SEC("xdp") int ing_xdp(struct xdp_md *ctx) { - __u8 *data, *data_meta, *data_end; + __u8 *data, *data_meta, *data_end, *payload; + struct ethhdr *eth; int ret; - ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4)); + ret = bpf_xdp_adjust_meta(ctx, -META_SIZE); if (ret < 0) return XDP_DROP; @@ -42,11 +55,21 @@ int ing_xdp(struct xdp_md *ctx) 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) + eth = (struct ethhdr *)data; + payload = data + sizeof(struct ethhdr); + + if (payload + META_SIZE > data_end || + data_meta + META_SIZE > data) + return XDP_DROP; + + /* The Linux networking stack may send other packets on the test + * interface that interfere with the test. Just drop them. + * The test packets can be recognized by their ethertype of zero. + */ + if (eth->h_proto != 0) return XDP_DROP; - __builtin_memcpy(data_meta, data, ETH_ALEN); + __builtin_memcpy(data_meta, payload, META_SIZE); return XDP_PASS; } diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 6f7b15d6c6ed..3d8de0d4c96a 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -13,6 +13,7 @@ * - UDP 9091 packets trigger TX reply * - TX HW timestamp is requested and reported back upon completion * - TX checksum is requested + * - TX launch time HW offload is requested for transmission */ #include <test_progs.h> @@ -37,6 +38,15 @@ #include <time.h> #include <unistd.h> #include <libgen.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <linux/pkt_sched.h> +#include <linux/pkt_cls.h> +#include <linux/ethtool.h> +#include <sys/socket.h> +#include <arpa/inet.h> #include "xdp_metadata.h" @@ -64,6 +74,18 @@ int rxq; bool skip_tx; __u64 last_hw_rx_timestamp; __u64 last_xdp_rx_timestamp; +__u64 last_launch_time; +__u64 launch_time_delta_to_hw_rx_timestamp; +int launch_time_queue; + +#define run_command(cmd, ...) \ +({ \ + char command[1024]; \ + memset(command, 0, sizeof(command)); \ + snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \ + fprintf(stderr, "Running: %s\n", command); \ + system(command); \ +}) void test__fail(void) { /* for network_helpers.c */ } @@ -298,6 +320,12 @@ static bool complete_tx(struct xsk *xsk, clockid_t clock_id) if (meta->completion.tx_timestamp) { __u64 ref_tstamp = gettime(clock_id); + if (launch_time_delta_to_hw_rx_timestamp) { + print_tstamp_delta("HW Launch-time", + "HW TX-complete-time", + last_launch_time, + meta->completion.tx_timestamp); + } print_tstamp_delta("HW TX-complete-time", "User TX-complete-time", meta->completion.tx_timestamp, ref_tstamp); print_tstamp_delta("XDP RX-time", "User TX-complete-time", @@ -395,6 +423,17 @@ static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id) xsk, ntohs(udph->check), ntohs(want_csum), meta->request.csum_start, meta->request.csum_offset); + /* Set the value of launch time */ + if (launch_time_delta_to_hw_rx_timestamp) { + meta->flags |= XDP_TXMD_FLAGS_LAUNCH_TIME; + meta->request.launch_time = last_hw_rx_timestamp + + launch_time_delta_to_hw_rx_timestamp; + last_launch_time = meta->request.launch_time; + print_tstamp_delta("HW RX-time", "HW Launch-time", + last_hw_rx_timestamp, + meta->request.launch_time); + } + memcpy(data, rx_packet, len); /* don't share umem chunk for simplicity */ tx_desc->options |= XDP_TX_METADATA; tx_desc->len = len; @@ -407,6 +446,7 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t const struct xdp_desc *rx_desc; struct pollfd fds[rxq + 1]; __u64 comp_addr; + __u64 deadline; __u64 addr; __u32 idx = 0; int ret; @@ -477,9 +517,15 @@ peek: if (ret) printf("kick_tx ret=%d\n", ret); - for (int j = 0; j < 500; j++) { + /* wait 1 second + cover launch time */ + deadline = gettime(clock_id) + + NANOSEC_PER_SEC + + launch_time_delta_to_hw_rx_timestamp; + while (true) { if (complete_tx(xsk, clock_id)) break; + if (gettime(clock_id) >= deadline) + break; usleep(10); } } @@ -608,6 +654,10 @@ static void print_usage(void) " -h Display this help and exit\n\n" " -m Enable multi-buffer XDP for larger MTU\n" " -r Don't generate AF_XDP reply (rx metadata only)\n" + " -l Delta of launch time relative to HW RX-time in ns\n" + " default: 0 ns (launch time request is disabled)\n" + " -L Tx Queue to be enabled with launch time offload\n" + " default: 0 (Tx Queue 0)\n" "Generate test packets on the other machine with:\n" " echo -n xdp | nc -u -q1 <dst_ip> 9091\n"; @@ -618,7 +668,7 @@ static void read_args(int argc, char *argv[]) { int opt; - while ((opt = getopt(argc, argv, "chmr")) != -1) { + while ((opt = getopt(argc, argv, "chmrl:L:")) != -1) { switch (opt) { case 'c': bind_flags &= ~XDP_USE_NEED_WAKEUP; @@ -634,6 +684,12 @@ static void read_args(int argc, char *argv[]) case 'r': skip_tx = true; break; + case 'l': + launch_time_delta_to_hw_rx_timestamp = atoll(optarg); + break; + case 'L': + launch_time_queue = atoll(optarg); + break; case '?': if (isprint(optopt)) fprintf(stderr, "Unknown option: -%c\n", optopt); @@ -657,23 +713,118 @@ static void read_args(int argc, char *argv[]) error(-1, errno, "Invalid interface name"); } +void clean_existing_configurations(void) +{ + /* Check and delete root qdisc if exists */ + if (run_command("sudo tc qdisc show dev %s | grep -q 'qdisc mqprio 8001:'", ifname) == 0) + run_command("sudo tc qdisc del dev %s root", ifname); + + /* Check and delete ingress qdisc if exists */ + if (run_command("sudo tc qdisc show dev %s | grep -q 'qdisc ingress ffff:'", ifname) == 0) + run_command("sudo tc qdisc del dev %s ingress", ifname); + + /* Check and delete ethtool filters if any exist */ + if (run_command("sudo ethtool -n %s | grep -q 'Filter:'", ifname) == 0) { + run_command("sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 sudo ethtool -N %s delete >&2", + ifname, ifname); + } +} + +#define MAX_TC 16 + int main(int argc, char *argv[]) { clockid_t clock_id = CLOCK_TAI; + struct bpf_program *prog; int server_fd = -1; + size_t map_len = 0; + size_t que_len = 0; + char *buf = NULL; + char *map = NULL; + char *que = NULL; + char *tmp = NULL; + int tc = 0; int ret; int i; - struct bpf_program *prog; - read_args(argc, argv); rxq = rxq_num(ifname); - printf("rxq: %d\n", rxq); + if (launch_time_queue >= rxq || launch_time_queue < 0) + error(1, 0, "Invalid launch_time_queue."); + + clean_existing_configurations(); + sleep(1); + + /* Enable tx and rx hardware timestamping */ hwtstamp_enable(ifname); + /* Prepare priority to traffic class map for tc-mqprio */ + for (i = 0; i < MAX_TC; i++) { + if (i < rxq) + tc = i; + + if (asprintf(&buf, "%d ", tc) == -1) { + printf("Failed to malloc buf for tc map.\n"); + goto free_mem; + } + + map_len += strlen(buf); + tmp = realloc(map, map_len + 1); + if (!tmp) { + printf("Failed to realloc tc map.\n"); + goto free_mem; + } + map = tmp; + strcat(map, buf); + free(buf); + buf = NULL; + } + + /* Prepare traffic class to hardware queue map for tc-mqprio */ + for (i = 0; i <= tc; i++) { + if (asprintf(&buf, "1@%d ", i) == -1) { + printf("Failed to malloc buf for tc queues.\n"); + goto free_mem; + } + + que_len += strlen(buf); + tmp = realloc(que, que_len + 1); + if (!tmp) { + printf("Failed to realloc tc queues.\n"); + goto free_mem; + } + que = tmp; + strcat(que, buf); + free(buf); + buf = NULL; + } + + /* Add mqprio qdisc */ + run_command("sudo tc qdisc add dev %s handle 8001: parent root mqprio num_tc %d map %squeues %shw 0", + ifname, tc + 1, map, que); + + /* To test launch time, send UDP packet with VLAN priority 1 to port 9091 */ + if (launch_time_delta_to_hw_rx_timestamp) { + /* Enable launch time hardware offload on launch_time_queue */ + run_command("sudo tc qdisc replace dev %s parent 8001:%d etf offload clockid CLOCK_TAI delta 500000", + ifname, launch_time_queue + 1); + sleep(1); + + /* Route incoming packet with VLAN priority 1 into launch_time_queue */ + if (run_command("sudo ethtool -N %s flow-type ether vlan 0x2000 vlan-mask 0x1FFF action %d", + ifname, launch_time_queue)) { + run_command("sudo tc qdisc add dev %s ingress", ifname); + run_command("sudo tc filter add dev %s parent ffff: protocol 802.1Q flower vlan_prio 1 hw_tc %d", + ifname, launch_time_queue); + } + + /* Enable VLAN tag stripping offload */ + run_command("sudo ethtool -K %s rxvlan on", ifname); + } + rx_xsk = malloc(sizeof(struct xsk) * rxq); if (!rx_xsk) error(1, ENOMEM, "malloc"); @@ -733,4 +884,11 @@ int main(int argc, char *argv[]) cleanup(); if (ret) error(1, -ret, "verify_metadata"); + + clean_existing_configurations(); + +free_mem: + free(buf); + free(map); + free(que); } diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore new file mode 100644 index 000000000000..ec746f374e85 --- /dev/null +++ b/tools/testing/selftests/drivers/net/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +xdp_helper diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 137470bdee0c..0c95bd944d56 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,13 +1,18 @@ # SPDX-License-Identifier: GPL-2.0 +CFLAGS += $(KHDR_INCLUDES) TEST_INCLUDES := $(wildcard lib/py/*.py) \ $(wildcard lib/sh/*.sh) \ ../../net/net_helper.sh \ ../../net/lib.sh \ +TEST_GEN_FILES := xdp_helper + TEST_PROGS := \ netcons_basic.sh \ + netcons_fragmented_msg.sh \ netcons_overflow.sh \ + netcons_sysdata.sh \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/README.rst b/tools/testing/selftests/drivers/net/README.rst index 3b6a29e6564b..eb838ae94844 100644 --- a/tools/testing/selftests/drivers/net/README.rst +++ b/tools/testing/selftests/drivers/net/README.rst @@ -107,7 +107,7 @@ On the target machine, running the tests will use netdevsim by default:: 1..1 # timeout set to 45 # selftests: drivers/net: ping.py - # KTAP version 1 + # TAP version 13 # 1..3 # ok 1 ping.test_v4 # ok 2 ping.test_v6 @@ -128,7 +128,7 @@ Create a config with remote info:: Run the test:: [/root] # ./ksft-net-drv/drivers/net/ping.py - KTAP version 1 + TAP version 13 1..3 ok 1 ping.test_v4 ok 2 ping.test_v6 # SKIP Test requires IPv6 connectivity diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index a2d8af60876d..f27172ddee0a 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -4,3 +4,4 @@ CONFIG_CONFIGFS_FS=y CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_NETCONSOLE_EXTENDED_LOG=y +CONFIG_XDP_SOCKETS=y diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py index 873f5219e41d..7cc74faed743 100755 --- a/tools/testing/selftests/drivers/net/hds.py +++ b/tools/testing/selftests/drivers/net/hds.py @@ -20,8 +20,7 @@ def _get_hds_mode(cfg, netnl) -> str: def _xdp_onoff(cfg): - test_dir = os.path.dirname(os.path.realpath(__file__)) - prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" + prog = cfg.rpath("../../net/lib/xdp_dummy.bpf.o") ip("link set dev %s xdp obj %s sec xdp" % (cfg.ifname, prog)) ip("link set dev %s xdp off" % cfg.ifname) diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 21ba64ce1e34..cde5814ff9a7 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -10,11 +10,14 @@ TEST_PROGS = \ ethtool_rmon.sh \ hw_stats_l3.sh \ hw_stats_l3_gre.sh \ + irq.py \ loopback.sh \ nic_link_layer.py \ nic_performance.py \ pp_alloc_fail.py \ rss_ctx.py \ + rss_input_xfrm.py \ + tso.py \ # TEST_FILES := \ @@ -32,9 +35,12 @@ TEST_INCLUDES := \ # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := ncdevmem TEST_GEN_FILES += $(YNL_GEN_FILES) +TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) include ../../../lib.mk # YNL build YNL_GENS := ethtool netdev include ../../../net/ynl.mk + +include ../../../net/bpf.mk diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py index cb40497faee4..701aca1361e0 100755 --- a/tools/testing/selftests/drivers/net/hw/csum.py +++ b/tools/testing/selftests/drivers/net/hw/csum.py @@ -9,15 +9,12 @@ from lib.py import ksft_run, ksft_exit, KsftSkipEx from lib.py import EthtoolFamily, NetDrvEpEnv from lib.py import bkg, cmd, wait_port_listen -def test_receive(cfg, ipv4=False, extra_args=None): +def test_receive(cfg, ipver="6", extra_args=None): """Test local nic checksum receive. Remote host sends crafted packets.""" if not cfg.have_rx_csum: raise KsftSkipEx(f"Test requires rx checksum offload on {cfg.ifname}") - if ipv4: - ip_args = f"-4 -S {cfg.remote_v4} -D {cfg.v4}" - else: - ip_args = f"-6 -S {cfg.remote_v6} -D {cfg.v6}" + ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}" rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}" tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}" @@ -27,17 +24,14 @@ def test_receive(cfg, ipv4=False, extra_args=None): cmd(tx_cmd, host=cfg.remote) -def test_transmit(cfg, ipv4=False, extra_args=None): +def test_transmit(cfg, ipver="6", extra_args=None): """Test local nic checksum transmit. Remote host verifies packets.""" if (not cfg.have_tx_csum_generic and - not (cfg.have_tx_csum_ipv4 and ipv4) and - not (cfg.have_tx_csum_ipv6 and not ipv4)): + not (cfg.have_tx_csum_ipv4 and ipver == "4") and + not (cfg.have_tx_csum_ipv6 and ipver == "6")): raise KsftSkipEx(f"Test requires tx checksum offload on {cfg.ifname}") - if ipv4: - ip_args = f"-4 -S {cfg.v4} -D {cfg.remote_v4}" - else: - ip_args = f"-6 -S {cfg.v6} -D {cfg.remote_v6}" + ip_args = f"-{ipver} -S {cfg.addr_v[ipver]} -D {cfg.remote_addr_v[ipver]}" # Cannot randomize input when calculating zero checksum if extra_args != "-U -Z": @@ -51,26 +45,20 @@ def test_transmit(cfg, ipv4=False, extra_args=None): cmd(tx_cmd) -def test_builder(name, cfg, ipv4=False, tx=False, extra_args=""): +def test_builder(name, cfg, ipver="6", tx=False, extra_args=""): """Construct specific tests from the common template. Most tests follow the same basic pattern, differing only in Direction of the test and optional flags passed to csum.""" def f(cfg): - if ipv4: - cfg.require_v4() - else: - cfg.require_v6() + cfg.require_ipver(ipver) if tx: - test_transmit(cfg, ipv4, extra_args) + test_transmit(cfg, ipver, extra_args) else: - test_receive(cfg, ipv4, extra_args) + test_receive(cfg, ipver, extra_args) - if ipv4: - f.__name__ = "ipv4_" + name - else: - f.__name__ = "ipv6_" + name + f.__name__ = f"ipv{ipver}_" + name return f @@ -100,19 +88,19 @@ def main() -> None: with NetDrvEpEnv(__file__, nsim_test=False) as cfg: check_nic_features(cfg) - cfg.bin_local = path.abspath(path.dirname(__file__) + "/../../../net/lib/csum") + cfg.bin_local = cfg.rpath("../../../net/lib/csum") cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) cases = [] - for ipv4 in [True, False]: - cases.append(test_builder("rx_tcp", cfg, ipv4, False, "-t")) - cases.append(test_builder("rx_tcp_invalid", cfg, ipv4, False, "-t -E")) + for ipver in ["4", "6"]: + cases.append(test_builder("rx_tcp", cfg, ipver, False, "-t")) + cases.append(test_builder("rx_tcp_invalid", cfg, ipver, False, "-t -E")) - cases.append(test_builder("rx_udp", cfg, ipv4, False, "")) - cases.append(test_builder("rx_udp_invalid", cfg, ipv4, False, "-E")) + cases.append(test_builder("rx_udp", cfg, ipver, False, "")) + cases.append(test_builder("rx_udp_invalid", cfg, ipver, False, "-E")) - cases.append(test_builder("tx_udp_csum_offload", cfg, ipv4, True, "-U")) - cases.append(test_builder("tx_udp_zero_checksum", cfg, ipv4, True, "-U -Z")) + cases.append(test_builder("tx_udp_csum_offload", cfg, ipver, True, "-U")) + cases.append(test_builder("tx_udp_zero_checksum", cfg, ipver, True, "-U -Z")) ksft_run(cases=cases, args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index 1223f0f5c10c..3947e9157115 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -21,15 +21,15 @@ def require_devmem(cfg): @ksft_disruptive def check_rx(cfg) -> None: - cfg.require_v6() + cfg.require_ipver("6") require_devmem(cfg) port = rand_port() - listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.v6} -p {port}" + listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}" with bkg(listen_cmd) as socat: wait_port_listen(port) - cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.v6}]:{port}", host=cfg.remote, shell=True) + cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.addr_v['6']}]:{port}", host=cfg.remote, shell=True) ksft_eq(socat.stdout.strip(), "hello\nworld") diff --git a/tools/testing/selftests/drivers/net/hw/irq.py b/tools/testing/selftests/drivers/net/hw/irq.py new file mode 100755 index 000000000000..42ab98370245 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/irq.py @@ -0,0 +1,99 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +from lib.py import ksft_run, ksft_exit +from lib.py import ksft_ge, ksft_eq +from lib.py import KsftSkipEx +from lib.py import ksft_disruptive +from lib.py import EthtoolFamily, NetdevFamily +from lib.py import NetDrvEnv +from lib.py import cmd, ip, defer + + +def read_affinity(irq) -> str: + with open(f'/proc/irq/{irq}/smp_affinity', 'r') as fp: + return fp.read().lstrip("0,").strip() + + +def write_affinity(irq, what) -> str: + if what != read_affinity(irq): + with open(f'/proc/irq/{irq}/smp_affinity', 'w') as fp: + fp.write(what) + + +def check_irqs_reported(cfg) -> None: + """ Check that device reports IRQs for NAPI instances """ + napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True) + irqs = sum(['irq' in x for x in napis]) + + ksft_ge(irqs, 1) + ksft_eq(irqs, len(napis)) + + +def _check_reconfig(cfg, reconfig_cb) -> None: + napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True) + for n in reversed(napis): + if 'irq' in n: + break + else: + raise KsftSkipEx(f"Device has no NAPI with IRQ attribute (#napis: {len(napis)}") + + old = read_affinity(n['irq']) + # pick an affinity that's not the current one + new = "3" if old != "3" else "5" + write_affinity(n['irq'], new) + defer(write_affinity, n['irq'], old) + + reconfig_cb(cfg) + + ksft_eq(read_affinity(n['irq']), new, comment="IRQ affinity changed after reconfig") + + +def check_reconfig_queues(cfg) -> None: + def reconfig(cfg) -> None: + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + if channels['combined-count'] == 0: + rx_type = 'rx' + else: + rx_type = 'combined' + cur_queue_cnt = channels[f'{rx_type}-count'] + max_queue_cnt = channels[f'{rx_type}-max'] + + cmd(f"ethtool -L {cfg.ifname} {rx_type} 1") + cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}") + cmd(f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}") + + _check_reconfig(cfg, reconfig) + + +def check_reconfig_xdp(cfg) -> None: + def reconfig(cfg) -> None: + ip(f"link set dev %s xdp obj %s sec xdp" % + (cfg.ifname, cfg.rpath("xdp_dummy.bpf.o"))) + ip(f"link set dev %s xdp off" % cfg.ifname) + + _check_reconfig(cfg, reconfig) + + +@ksft_disruptive +def check_down(cfg) -> None: + def reconfig(cfg) -> None: + ip("link set dev %s down" % cfg.ifname) + ip("link set dev %s up" % cfg.ifname) + + _check_reconfig(cfg, reconfig) + + +def main() -> None: + with NetDrvEnv(__file__, nsim_test=False) as cfg: + cfg.ethnl = EthtoolFamily() + cfg.netnl = NetdevFamily() + + ksft_run([check_irqs_reported, check_reconfig_queues, + check_reconfig_xdp, check_down], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 19a6969643f4..2bf14ac2b8c6 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -50,7 +50,6 @@ #include <linux/memfd.h> #include <linux/dma-buf.h> #include <linux/udmabuf.h> -#include <libmnl/libmnl.h> #include <linux/types.h> #include <linux/netlink.h> #include <linux/genetlink.h> diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 319aaa004c40..ca60ae325c22 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -4,7 +4,8 @@ import datetime import random import re -from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt, ksft_true +from lib.py import ksft_run, ksft_pr, ksft_exit +from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises from lib.py import NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily from lib.py import KsftSkipEx, KsftFailEx @@ -58,6 +59,14 @@ def require_ntuple(cfg): raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"])) +def require_context_cnt(cfg, need_cnt): + # There's no good API to get the context count, so the tests + # which try to add a lot opportunisitically set the count they + # discovered. Careful with test ordering! + if need_cnt and cfg.context_cnt and cfg.context_cnt < need_cnt: + raise KsftSkipEx(f"Test requires at least {need_cnt} contexts, but device only has {cfg.context_cnt}") + + # Get Rx packet counts for all queues, as a simple list of integers # if @prev is specified the prev counts will be subtracted def _get_rx_cnts(cfg, prev=None): @@ -383,7 +392,7 @@ def test_rss_context_dump(cfg): # Sanity-check the results for data in ctxs: - ksft_ne(set(data['indir']), {0}, "indir table is all zero") + ksft_ne(set(data.get('indir', [1])), {0}, "indir table is all zero") ksft_ne(set(data.get('hkey', [1])), {0}, "key is all zero") # More specific checks @@ -456,6 +465,8 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): raise ksft_pr(f"Failed to create context {i + 1}, trying to test what we got") ctx_cnt = i + if cfg.context_cnt is None: + cfg.context_cnt = ctx_cnt break _rss_key_check(cfg, context=ctx_id) @@ -511,8 +522,7 @@ def test_rss_context_out_of_order(cfg, ctx_cnt=4): """ require_ntuple(cfg) - - requested_ctx_cnt = ctx_cnt + require_context_cnt(cfg, 4) # Try to allocate more queues when necessary qcnt = len(_get_rx_cnts(cfg)) @@ -577,9 +587,6 @@ def test_rss_context_out_of_order(cfg, ctx_cnt=4): remove_ctx(-1) check_traffic() - if requested_ctx_cnt != ctx_cnt: - raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}") - def test_rss_context_overlap(cfg, other_ctx=0): """ @@ -588,6 +595,8 @@ def test_rss_context_overlap(cfg, other_ctx=0): """ require_ntuple(cfg) + if other_ctx: + require_context_cnt(cfg, 2) queue_cnt = len(_get_rx_cnts(cfg)) if queue_cnt < 4: @@ -649,6 +658,29 @@ def test_rss_context_overlap2(cfg): test_rss_context_overlap(cfg, True) +def test_flow_add_context_missing(cfg): + """ + Test that we are not allowed to add a rule pointing to an RSS context + which was never created. + """ + + require_ntuple(cfg) + + # Find a context which doesn't exist + for ctx_id in range(1, 100): + try: + get_rss(cfg, context=ctx_id) + except CmdExitFailure: + break + + with ksft_raises(CmdExitFailure) as cm: + flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port 1234 context {ctx_id}" + ntuple_id = ethtool_create(cfg, "-N", flow) + ethtool(f"-N {cfg.ifname} delete {ntuple_id}") + if cm.exception: + ksft_in('Invalid argument', cm.exception.cmd.stderr) + + def test_delete_rss_context_busy(cfg): """ Test that deletion returns -EBUSY when an rss context is being used @@ -717,6 +749,7 @@ def test_rss_ntuple_addition(cfg): def main() -> None: with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.context_cnt = None cfg.ethnl = EthtoolFamily() cfg.netdevnl = NetdevFamily() @@ -726,6 +759,7 @@ def main() -> None: test_rss_context_dump, test_rss_context_queue_reconfigure, test_rss_context_overlap, test_rss_context_overlap2, test_rss_context_out_of_order, test_rss_context4_create_with_cfg, + test_flow_add_context_missing, test_delete_rss_context_busy, test_rss_ntuple_addition], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py new file mode 100755 index 000000000000..53bb08cc29ec --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py @@ -0,0 +1,87 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import multiprocessing +import socket +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, cmd, fd_read_timeout +from lib.py import NetDrvEpEnv +from lib.py import EthtoolFamily, NetdevFamily +from lib.py import KsftSkipEx, KsftFailEx +from lib.py import rand_port + + +def traffic(cfg, local_port, remote_port, ipver): + af_inet = socket.AF_INET if ipver == "4" else socket.AF_INET6 + sock = socket.socket(af_inet, socket.SOCK_DGRAM) + sock.bind(("", local_port)) + sock.connect((cfg.remote_addr_v[ipver], remote_port)) + tgt = f"{ipver}:[{cfg.addr_v[ipver]}]:{local_port},sourceport={remote_port}" + cmd("echo a | socat - UDP" + tgt, host=cfg.remote) + fd_read_timeout(sock.fileno(), 5) + return sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU) + + +def test_rss_input_xfrm(cfg, ipver): + """ + Test symmetric input_xfrm. + If symmetric RSS hash is configured, send traffic twice, swapping the + src/dst UDP ports, and verify that the same queue is receiving the traffic + in both cases (IPs are constant). + """ + + if multiprocessing.cpu_count() < 2: + raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash") + + input_xfrm = cfg.ethnl.rss_get( + {'header': {'dev-name': cfg.ifname}}).get('input_xfrm') + + # Check for symmetric xor/or-xor + if not input_xfrm or (input_xfrm != 1 and input_xfrm != 2): + raise KsftSkipEx("Symmetric RSS hash not requested") + + cpus = set() + successful = 0 + for _ in range(100): + try: + port1 = rand_port(socket.SOCK_DGRAM) + port2 = rand_port(socket.SOCK_DGRAM) + cpu1 = traffic(cfg, port1, port2, ipver) + cpu2 = traffic(cfg, port2, port1, ipver) + cpus.update([cpu1, cpu2]) + ksft_eq( + cpu1, cpu2, comment=f"Received traffic on different cpus with ports ({port1 = }, {port2 = }) while symmetric hash is configured") + + successful += 1 + if successful == 10: + break + except: + continue + else: + raise KsftFailEx("Failed to run traffic") + + ksft_ge(len(cpus), 2, + comment=f"Received traffic on less than two cpus {cpus = }") + + +def test_rss_input_xfrm_ipv4(cfg): + cfg.require_ipver("4") + test_rss_input_xfrm(cfg, "4") + + +def test_rss_input_xfrm_ipv6(cfg): + cfg.require_ipver("6") + test_rss_input_xfrm(cfg, "6") + + +def main() -> None: + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.ethnl = EthtoolFamily() + cfg.netdevnl = NetdevFamily() + + ksft_run([test_rss_input_xfrm_ipv4, test_rss_input_xfrm_ipv6], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py new file mode 100755 index 000000000000..e1ecb92f79d9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/tso.py @@ -0,0 +1,241 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +"""Run the tools/testing/selftests/net/csum testsuite.""" + +import fcntl +import socket +import struct +import termios +import time + +from lib.py import ksft_pr, ksft_run, ksft_exit, KsftSkipEx, KsftXfailEx +from lib.py import ksft_eq, ksft_ge, ksft_lt +from lib.py import EthtoolFamily, NetdevFamily, NetDrvEpEnv +from lib.py import bkg, cmd, defer, ethtool, ip, rand_port, wait_port_listen + + +def sock_wait_drain(sock, max_wait=1000): + """Wait for all pending write data on the socket to get ACKed.""" + for _ in range(max_wait): + one = b'\0' * 4 + outq = fcntl.ioctl(sock.fileno(), termios.TIOCOUTQ, one) + outq = struct.unpack("I", outq)[0] + if outq == 0: + break + time.sleep(0.01) + ksft_eq(outq, 0) + + +def tcp_sock_get_retrans(sock): + """Get the number of retransmissions for the TCP socket.""" + info = sock.getsockopt(socket.SOL_TCP, socket.TCP_INFO, 512) + return struct.unpack("I", info[100:104])[0] + + +def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso): + cfg.require_cmd("socat", remote=True) + + port = rand_port() + listen_cmd = f"socat -{ipver} -t 2 -u TCP-LISTEN:{port},reuseport /dev/null,ignoreeof" + + with bkg(listen_cmd, host=cfg.remote) as nc: + wait_port_listen(port, host=cfg.remote) + + if ipver == "4": + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + sock.connect((remote_v4, port)) + else: + sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) + sock.connect((remote_v6, port)) + + # Small send to make sure the connection is working. + sock.send("ping".encode()) + sock_wait_drain(sock) + + # Send 4MB of data, record the LSO packet count. + qstat_old = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + buf = b"0" * 1024 * 1024 * 4 + sock.send(buf) + sock_wait_drain(sock) + qstat_new = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + + # No math behind the 10 here, but try to catch cases where + # TCP falls back to non-LSO. + ksft_lt(tcp_sock_get_retrans(sock), 10) + sock.close() + + # Check that at least 90% of the data was sent as LSO packets. + # System noise may cause false negatives. Also header overheads + # will add up to 5% of extra packes... The check is best effort. + total_lso_wire = len(buf) * 0.90 // cfg.dev["mtu"] + total_lso_super = len(buf) * 0.90 // cfg.dev["tso_max_size"] + if should_lso: + if cfg.have_stat_super_count: + ksft_ge(qstat_new['tx-hw-gso-packets'] - + qstat_old['tx-hw-gso-packets'], + total_lso_super, + comment="Number of LSO super-packets with LSO enabled") + if cfg.have_stat_wire_count: + ksft_ge(qstat_new['tx-hw-gso-wire-packets'] - + qstat_old['tx-hw-gso-wire-packets'], + total_lso_wire, + comment="Number of LSO wire-packets with LSO enabled") + else: + if cfg.have_stat_super_count: + ksft_lt(qstat_new['tx-hw-gso-packets'] - + qstat_old['tx-hw-gso-packets'], + 15, comment="Number of LSO super-packets with LSO disabled") + if cfg.have_stat_wire_count: + ksft_lt(qstat_new['tx-hw-gso-wire-packets'] - + qstat_old['tx-hw-gso-wire-packets'], + 500, comment="Number of LSO wire-packets with LSO disabled") + + +def build_tunnel(cfg, outer_ipver, tun_info): + local_v4 = NetDrvEpEnv.nsim_v4_pfx + "1" + local_v6 = NetDrvEpEnv.nsim_v6_pfx + "1" + remote_v4 = NetDrvEpEnv.nsim_v4_pfx + "2" + remote_v6 = NetDrvEpEnv.nsim_v6_pfx + "2" + + local_addr = cfg.addr_v[outer_ipver] + remote_addr = cfg.remote_addr_v[outer_ipver] + + tun_type = tun_info[0] + tun_arg = tun_info[2] + ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {local_addr} remote {remote_addr} dev {cfg.ifname}") + defer(ip, f"link del {tun_type}-ksft") + ip(f"link set dev {tun_type}-ksft up") + ip(f"addr add {local_v4}/24 dev {tun_type}-ksft") + ip(f"addr add {local_v6}/64 dev {tun_type}-ksft") + + ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}", + host=cfg.remote) + defer(ip, f"link del {tun_type}-ksft", host=cfg.remote) + ip(f"link set dev {tun_type}-ksft up", host=cfg.remote) + ip(f"addr add {remote_v4}/24 dev {tun_type}-ksft", host=cfg.remote) + ip(f"addr add {remote_v6}/64 dev {tun_type}-ksft", host=cfg.remote) + + return remote_v4, remote_v6 + + +def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None): + """Construct specific tests from the common template.""" + def f(cfg): + cfg.require_ipver(outer_ipver) + + if not cfg.have_stat_super_count and \ + not cfg.have_stat_wire_count: + raise KsftSkipEx(f"Device does not support LSO queue stats") + + ipver = outer_ipver + if tun: + remote_v4, remote_v6 = build_tunnel(cfg, ipver, tun) + ipver = inner_ipver + else: + remote_v4 = cfg.remote_addr_v["4"] + remote_v6 = cfg.remote_addr_v["6"] + + tun_partial = tun and tun[1] + # Tunnel which can silently fall back to gso-partial + has_gso_partial = tun and 'tx-gso-partial' in cfg.features + + # For TSO4 via partial we need mangleid + if ipver == "4" and feature in cfg.partial_features: + ksft_pr("Testing with mangleid enabled") + if 'tx-tcp-mangleid-segmentation' not in cfg.features: + ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on") + defer(ethtool, f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off") + + # First test without the feature enabled. + ethtool(f"-K {cfg.ifname} {feature} off") + if has_gso_partial: + ethtool(f"-K {cfg.ifname} tx-gso-partial off") + run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=False) + + # Now test with the feature enabled. + # For compatible tunnels only - just GSO partial, not specific feature. + if has_gso_partial: + ethtool(f"-K {cfg.ifname} tx-gso-partial on") + run_one_stream(cfg, ipver, remote_v4, remote_v6, + should_lso=tun_partial) + + # Full feature enabled. + if feature in cfg.features: + ethtool(f"-K {cfg.ifname} {feature} on") + run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True) + else: + raise KsftXfailEx(f"Device does not support {feature}") + + f.__name__ = name + ((outer_ipver + "_") if tun else "") + "ipv" + inner_ipver + return f + + +def query_nic_features(cfg) -> None: + """Query and cache the NIC features.""" + cfg.have_stat_super_count = False + cfg.have_stat_wire_count = False + + cfg.features = set() + features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}}) + for f in features["active"]["bits"]["bit"]: + cfg.features.add(f["name"]) + + # Check which features are supported via GSO partial + cfg.partial_features = set() + if 'tx-gso-partial' in cfg.features: + ethtool(f"-K {cfg.ifname} tx-gso-partial off") + + no_partial = set() + features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}}) + for f in features["active"]["bits"]["bit"]: + no_partial.add(f["name"]) + cfg.partial_features = cfg.features - no_partial + ethtool(f"-K {cfg.ifname} tx-gso-partial on") + + stats = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True) + if stats: + if 'tx-hw-gso-packets' in stats[0]: + ksft_pr("Detected qstat for LSO super-packets") + cfg.have_stat_super_count = True + if 'tx-hw-gso-wire-packets' in stats[0]: + ksft_pr("Detected qstat for LSO wire-packets") + cfg.have_stat_wire_count = True + + +def main() -> None: + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.ethnl = EthtoolFamily() + cfg.netnl = NetdevFamily() + + query_nic_features(cfg) + + test_info = ( + # name, v4/v6 ethtool_feature tun:(type, partial, args) + ("", "4", "tx-tcp-segmentation", None), + ("", "6", "tx-tcp6-segmentation", None), + ("vxlan", "", "tx-udp_tnl-segmentation", ("vxlan", True, "id 100 dstport 4789 noudpcsum")), + ("vxlan_csum", "", "tx-udp_tnl-csum-segmentation", ("vxlan", False, "id 100 dstport 4789 udpcsum")), + ("gre", "4", "tx-gre-segmentation", ("ipgre", False, "")), + ("gre", "6", "tx-gre-segmentation", ("ip6gre", False, "")), + ) + + cases = [] + for outer_ipver in ["4", "6"]: + for info in test_info: + # Skip if test which only works for a specific IP version + if info[1] and outer_ipver != info[1]: + continue + + cases.append(test_builder(info[0], cfg, outer_ipver, info[2], + tun=info[3], inner_ipver="4")) + if info[3]: + cases.append(test_builder(info[0], cfg, outer_ipver, info[2], + tun=info[3], inner_ipver="6")) + + ksft_run(cases=cases, args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c b/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c new file mode 100644 index 000000000000..d988b2e0cee8 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define KBUILD_MODNAME "xdp_dummy" +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index 987e452d3a45..fd4d674e6c72 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -10,42 +10,68 @@ from lib.py import NetNS, NetdevSimDev from .remote import Remote -def _load_env_file(src_path): - env = os.environ.copy() +class NetDrvEnvBase: + """ + Base class for a NIC / host envirnoments + """ + def __init__(self, src_path): + self.src_path = src_path + self.env = self._load_env_file() - src_dir = Path(src_path).parent.resolve() - if not (src_dir / "net.config").exists(): + def rpath(self, path): + """ + Get an absolute path to a file based on a path relative to the directory + containing the test which constructed env. + + For example, if the test.py is in the same directory as + a binary (built from helper.c), the test can use env.rpath("helper") + to get the absolute path to the binary + """ + src_dir = Path(self.src_path).parent.resolve() + return (src_dir / path).as_posix() + + def _load_env_file(self): + env = os.environ.copy() + + src_dir = Path(self.src_path).parent.resolve() + if not (src_dir / "net.config").exists(): + return ksft_setup(env) + + with open((src_dir / "net.config").as_posix(), 'r') as fp: + for line in fp.readlines(): + full_file = line + # Strip comments + pos = line.find("#") + if pos >= 0: + line = line[:pos] + line = line.strip() + if not line: + continue + pair = line.split('=', maxsplit=1) + if len(pair) != 2: + raise Exception("Can't parse configuration line:", full_file) + env[pair[0]] = pair[1] return ksft_setup(env) - with open((src_dir / "net.config").as_posix(), 'r') as fp: - for line in fp.readlines(): - full_file = line - # Strip comments - pos = line.find("#") - if pos >= 0: - line = line[:pos] - line = line.strip() - if not line: - continue - pair = line.split('=', maxsplit=1) - if len(pair) != 2: - raise Exception("Can't parse configuration line:", full_file) - env[pair[0]] = pair[1] - return ksft_setup(env) - - -class NetDrvEnv: + +class NetDrvEnv(NetDrvEnvBase): """ Class for a single NIC / host env, with no remote end """ - def __init__(self, src_path, **kwargs): - self._ns = None + def __init__(self, src_path, nsim_test=None, **kwargs): + super().__init__(src_path) - self.env = _load_env_file(src_path) + self._ns = None if 'NETIF' in self.env: - self.dev = ip("link show dev " + self.env['NETIF'], json=True)[0] + if nsim_test is True: + raise KsftXfailEx("Test only works on netdevsim") + + self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0] else: + if nsim_test is False: + raise KsftXfailEx("Test does not work on netdevsim") + self._ns = NetdevSimDev(**kwargs) self.dev = self._ns.nsims[0].dev self.ifname = self.dev['ifname'] @@ -68,7 +94,7 @@ class NetDrvEnv: self._ns = None -class NetDrvEpEnv: +class NetDrvEpEnv(NetDrvEnvBase): """ Class for an environment with a local device and "remote endpoint" which can be used to send traffic in. @@ -82,8 +108,7 @@ class NetDrvEpEnv: nsim_v6_pfx = "2001:db8::" def __init__(self, src_path, nsim_test=None): - - self.env = _load_env_file(src_path) + super().__init__(src_path) self._stats_settle_time = None @@ -94,17 +119,20 @@ class NetDrvEpEnv: self._ns = None self._ns_peer = None + self.addr_v = { "4": None, "6": None } + self.remote_addr_v = { "4": None, "6": None } + if "NETIF" in self.env: if nsim_test is True: raise KsftXfailEx("Test only works on netdevsim") self._check_env() - self.dev = ip("link show dev " + self.env['NETIF'], json=True)[0] + self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0] - self.v4 = self.env.get("LOCAL_V4") - self.v6 = self.env.get("LOCAL_V6") - self.remote_v4 = self.env.get("REMOTE_V4") - self.remote_v6 = self.env.get("REMOTE_V6") + self.addr_v["4"] = self.env.get("LOCAL_V4") + self.addr_v["6"] = self.env.get("LOCAL_V6") + self.remote_addr_v["4"] = self.env.get("REMOTE_V4") + self.remote_addr_v["6"] = self.env.get("REMOTE_V6") kind = self.env["REMOTE_TYPE"] args = self.env["REMOTE_ARGS"] else: @@ -115,26 +143,29 @@ class NetDrvEpEnv: self.dev = self._ns.nsims[0].dev - self.v4 = self.nsim_v4_pfx + "1" - self.v6 = self.nsim_v6_pfx + "1" - self.remote_v4 = self.nsim_v4_pfx + "2" - self.remote_v6 = self.nsim_v6_pfx + "2" + self.addr_v["4"] = self.nsim_v4_pfx + "1" + self.addr_v["6"] = self.nsim_v6_pfx + "1" + self.remote_addr_v["4"] = self.nsim_v4_pfx + "2" + self.remote_addr_v["6"] = self.nsim_v6_pfx + "2" kind = "netns" args = self._netns.name self.remote = Remote(kind, args, src_path) - self.addr = self.v6 if self.v6 else self.v4 - self.remote_addr = self.remote_v6 if self.remote_v6 else self.remote_v4 + self.addr_ipver = "6" if self.addr_v["6"] else "4" + self.addr = self.addr_v[self.addr_ipver] + self.remote_addr = self.remote_addr_v[self.addr_ipver] - self.addr_ipver = "6" if self.v6 else "4" # Bracketed addresses, some commands need IPv6 to be inside [] - self.baddr = f"[{self.v6}]" if self.v6 else self.v4 - self.remote_baddr = f"[{self.remote_v6}]" if self.remote_v6 else self.remote_v4 + self.baddr = f"[{self.addr_v['6']}]" if self.addr_v["6"] else self.addr_v["4"] + self.remote_baddr = f"[{self.remote_addr_v['6']}]" if self.remote_addr_v["6"] else self.remote_addr_v["4"] self.ifname = self.dev['ifname'] self.ifindex = self.dev['ifindex'] + # resolve remote interface name + self.remote_ifname = self.resolve_remote_ifc() + self._required_cmd = {} def create_local(self): @@ -181,6 +212,18 @@ class NetDrvEpEnv: raise Exception("Invalid environment, missing configuration:", missing, "Please see tools/testing/selftests/drivers/net/README.rst") + def resolve_remote_ifc(self): + v4 = v6 = None + if self.remote_addr_v["4"]: + v4 = ip("addr show to " + self.remote_addr_v["4"], json=True, host=self.remote) + if self.remote_addr_v["6"]: + v6 = ip("addr show to " + self.remote_addr_v["6"], json=True, host=self.remote) + if v4 and v6 and v4[0]["ifname"] != v6[0]["ifname"]: + raise Exception("Can't resolve remote interface name, v4 and v6 don't match") + if (v4 and len(v4) > 1) or (v6 and len(v6) > 1): + raise Exception("Can't resolve remote interface name, multiple interfaces match") + return v6[0]["ifname"] if v6 else v4[0]["ifname"] + def __enter__(self): return self @@ -204,13 +247,9 @@ class NetDrvEpEnv: del self.remote self.remote = None - def require_v4(self): - if not self.v4 or not self.remote_v4: - raise KsftSkipEx("Test requires IPv4 connectivity") - - def require_v6(self): - if not self.v6 or not self.remote_v6: - raise KsftSkipEx("Test requires IPv6 connectivity") + def require_ipver(self, ipver): + if not self.addr_v[ipver] or not self.remote_addr_v[ipver]: + raise KsftSkipEx(f"Test requires IPv{ipver} connectivity") def _require_cmd(self, comm, key, host=None): cached = self._required_cmd.get(comm, {}) diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index 3acaba41ac7b..3c96b022954d 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -110,6 +110,13 @@ function create_dynamic_target() { echo 1 > "${NETCONS_PATH}"/enabled } +# Do not append the release to the header of the message +function disable_release_append() { + echo 0 > "${NETCONS_PATH}"/enabled + echo 0 > "${NETCONS_PATH}"/release + echo 1 > "${NETCONS_PATH}"/enabled +} + function cleanup() { local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" @@ -223,3 +230,20 @@ function check_for_dependencies() { exit "${ksft_skip}" fi } + +function check_for_taskset() { + if ! which taskset > /dev/null ; then + echo "SKIP: taskset(1) is not available" >&2 + exit "${ksft_skip}" + fi +} + +# This is necessary if running multiple tests in a row +function pkill_socat() { + PROCESS_NAME="socat UDP-LISTEN:6666,fork ${OUTPUT_FILE}" + # socat runs under timeout(1), kill it if it is still alive + # do not fail if socat doesn't exist anymore + set +e + pkill -f "${PROCESS_NAME}" + set -e +} diff --git a/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh b/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh new file mode 100755 index 000000000000..4a71e01a230c --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh @@ -0,0 +1,122 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# Test netconsole's message fragmentation functionality. +# +# When a message exceeds the maximum packet size, netconsole splits it into +# multiple fragments for transmission. This test verifies: +# - Correct fragmentation of large messages +# - Proper reassembly of fragments at the receiver +# - Preservation of userdata across fragments +# - Behavior with and without kernel release version appending +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh + +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# set userdata to a long value. In this case, it is "1-2-3-4...50-" +USERDATA_VALUE=$(printf -- '%.2s-' {1..60}) + +# Convert the header string in a regexp, so, we can remove +# the second header as well. +# A header looks like "13,468,514729715,-,ncfrag=0/1135;". If +# release is appended, you might find something like:L +# "6.13.0-04048-g4f561a87745a,13,468,514729715,-,ncfrag=0/1135;" +function header_to_regex() { + # header is everything before ; + local HEADER="${1}" + REGEX=$(echo "${HEADER}" | cut -d'=' -f1) + echo "${REGEX}=[0-9]*\/[0-9]*;" +} + +# We have two headers in the message. Remove both to get the full message, +# and extract the full message. +function extract_msg() { + local MSGFILE="${1}" + # Extract the header, which is the very first thing that arrives in the + # first list. + HEADER=$(sed -n '1p' "${MSGFILE}" | cut -d';' -f1) + HEADER_REGEX=$(header_to_regex "${HEADER}") + + # Remove the two headers from the received message + # This will return the message without any header, similarly to what + # was sent. + sed "s/""${HEADER_REGEX}""//g" "${MSGFILE}" +} + +# Validate the message, which has two messages glued together. +# unwrap them to make sure all the characters were transmitted. +# File will look like the following: +# 13,468,514729715,-,ncfrag=0/1135;<message> +# key=<part of key>-13,468,514729715,-,ncfrag=967/1135;<rest of the key> +function validate_fragmented_result() { + # Discard the netconsole headers, and assemble the full message + RCVMSG=$(extract_msg "${1}") + + # check for the main message + if ! echo "${RCVMSG}" | grep -q "${MSG}"; then + echo "Message body doesn't match." >&2 + echo "msg received=" "${RCVMSG}" >&2 + exit "${ksft_fail}" + fi + + # check userdata + if ! echo "${RCVMSG}" | grep -q "${USERDATA_VALUE}"; then + echo "message userdata doesn't match" >&2 + echo "msg received=" "${RCVMSG}" >&2 + exit "${ksft_fail}" + fi + # test passed. hooray +} + +# Check for basic system dependency and exit if not found +check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target +# Set userdata "key" with the "value" value +set_user_data + + +# TEST 1: Send message and userdata. They will fragment +# ======= +MSG=$(printf -- 'MSG%.3s=' {1..150}) + +# Listen for netconsole port inside the namespace and destination interface +listen_port_and_save_to "${OUTPUT_FILE}" & +# Wait for socat to start and listen to the port. +wait_local_port_listen "${NAMESPACE}" "${PORT}" udp +# Send the message +echo "${MSG}: ${TARGET}" > /dev/kmsg +# Wait until socat saves the file to disk +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +# Check if the message was not corrupted +validate_fragmented_result "${OUTPUT_FILE}" + +# TEST 2: Test with smaller message, and without release appended +# ======= +MSG=$(printf -- 'FOOBAR%.3s=' {1..100}) +# Let's disable release and test again. +disable_release_append + +listen_port_and_save_to "${OUTPUT_FILE}" & +wait_local_port_listen "${NAMESPACE}" "${PORT}" udp +echo "${MSG}: ${TARGET}" > /dev/kmsg +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +validate_fragmented_result "${OUTPUT_FILE}" +exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netcons_sysdata.sh new file mode 100755 index 000000000000..a737e377bf08 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_sysdata.sh @@ -0,0 +1,242 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# A test that makes sure that sysdata runtime CPU data is properly set +# when a message is sent. +# +# There are 3 different tests, every time sent using a random CPU. +# - Test #1 +# * Only enable cpu_nr sysdata feature. +# - Test #2 +# * Keep cpu_nr sysdata feature enable and enable userdata. +# - Test #3 +# * keep userdata enabled, and disable sysdata cpu_nr feature. +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh + +# Enable the sysdata cpu_nr feature +function set_cpu_nr() { + if [[ ! -f "${NETCONS_PATH}/userdata/cpu_nr_enabled" ]] + then + echo "Populate CPU configfs path not available in ${NETCONS_PATH}/userdata/cpu_nr_enabled" >&2 + exit "${ksft_skip}" + fi + + echo 1 > "${NETCONS_PATH}/userdata/cpu_nr_enabled" +} + +# Enable the taskname to be appended to sysdata +function set_taskname() { + if [[ ! -f "${NETCONS_PATH}/userdata/taskname_enabled" ]] + then + echo "Not able to enable taskname sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/taskname_enabled" >&2 + exit "${ksft_skip}" + fi + + echo 1 > "${NETCONS_PATH}/userdata/taskname_enabled" +} + +# Enable the release to be appended to sysdata +function set_release() { + if [[ ! -f "${NETCONS_PATH}/userdata/release_enabled" ]] + then + echo "Not able to enable release sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/release_enabled" >&2 + exit "${ksft_skip}" + fi + + echo 1 > "${NETCONS_PATH}/userdata/release_enabled" +} + +# Disable the sysdata cpu_nr feature +function unset_cpu_nr() { + echo 0 > "${NETCONS_PATH}/userdata/cpu_nr_enabled" +} + +# Once called, taskname=<..> will not be appended anymore +function unset_taskname() { + echo 0 > "${NETCONS_PATH}/userdata/taskname_enabled" +} + +function unset_release() { + echo 0 > "${NETCONS_PATH}/userdata/release_enabled" +} + +# Test if MSG contains sysdata +function validate_sysdata() { + # OUTPUT_FILE will contain something like: + # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM + # userdatakey=userdatavalue + # cpu=X + # taskname=<taskname> + + # Echo is what this test uses to create the message. See runtest() + # function + SENDER="echo" + + if [ ! -f "$OUTPUT_FILE" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${OUTPUT_FILE}"; then + echo "FAIL: ${MSG} not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + # Check if cpu=XX exists in the file and matches the one used + # in taskset(1) + if ! grep -q "cpu=${CPU}\+" "${OUTPUT_FILE}"; then + echo "FAIL: 'cpu=${CPU}' not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "taskname=${SENDER}" "${OUTPUT_FILE}"; then + echo "FAIL: 'taskname=echo' not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + rm "${OUTPUT_FILE}" + pkill_socat +} + +function validate_release() { + RELEASE=$(uname -r) + + if [ ! -f "$OUTPUT_FILE" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "release=${RELEASE}" "${OUTPUT_FILE}"; then + echo "FAIL: 'release=${RELEASE}' not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi +} + +# Test if MSG content exists in OUTPUT_FILE but no `cpu=` and `taskname=` +# strings +function validate_no_sysdata() { + if [ ! -f "$OUTPUT_FILE" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${OUTPUT_FILE}"; then + echo "FAIL: ${MSG} not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + if grep -q "cpu=" "${OUTPUT_FILE}"; then + echo "FAIL: 'cpu= found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + if grep -q "taskname=" "${OUTPUT_FILE}"; then + echo "FAIL: 'taskname= found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + if grep -q "release=" "${OUTPUT_FILE}"; then + echo "FAIL: 'release= found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + rm "${OUTPUT_FILE}" +} + +# Start socat, send the message and wait for the file to show up in the file +# system +function runtest { + # Listen for netconsole port inside the namespace and destination + # interface + listen_port_and_save_to "${OUTPUT_FILE}" & + # Wait for socat to start and listen to the port. + wait_local_port_listen "${NAMESPACE}" "${PORT}" udp + # Send the message + taskset -c "${CPU}" echo "${MSG}: ${TARGET}" > /dev/kmsg + # Wait until socat saves the file to disk + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +} + +# ========== # +# Start here # +# ========== # + +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true + +# Check for basic system dependency and exit if not found +check_for_dependencies +# This test also depends on taskset(1). Check for it before starting the test +check_for_taskset + +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target + +#==================================================== +# TEST #1 +# Send message from a random CPU +#==================================================== +# Random CPU in the system +CPU=$((RANDOM % $(nproc))) +OUTPUT_FILE="/tmp/${TARGET}_1" +MSG="Test #1 from CPU${CPU}" +# Enable the auto population of cpu_nr +set_cpu_nr +# Enable taskname to be appended to sysdata +set_taskname +set_release +runtest +# Make sure the message was received in the dst part +# and exit +validate_release +validate_sysdata + +#==================================================== +# TEST #2 +# This test now adds userdata together with sysdata +# =================================================== +# Get a new random CPU +CPU=$((RANDOM % $(nproc))) +OUTPUT_FILE="/tmp/${TARGET}_2" +MSG="Test #2 from CPU${CPU}" +set_user_data +runtest +validate_release +validate_sysdata + +# =================================================== +# TEST #3 +# Unset all sysdata, fail if any userdata is set +# =================================================== +CPU=$((RANDOM % $(nproc))) +OUTPUT_FILE="/tmp/${TARGET}_3" +MSG="Test #3 from CPU${CPU}" +unset_cpu_nr +unset_taskname +unset_release +runtest +# At this time, cpu= shouldn't be present in the msg +validate_no_sysdata + +exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py index fc69bfcc37c4..93120e86e102 100755 --- a/tools/testing/selftests/drivers/net/ping.py +++ b/tools/testing/selftests/drivers/net/ping.py @@ -13,20 +13,20 @@ remote_ifname="" no_sleep=False def _test_v4(cfg) -> None: - cfg.require_v4() + cfg.require_ipver("4") - cmd(f"ping -c 1 -W0.5 {cfg.remote_v4}") - cmd(f"ping -c 1 -W0.5 {cfg.v4}", host=cfg.remote) - cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.remote_v4}") - cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.v4}", host=cfg.remote) + cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"]) + cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote) + cmd("ping -s 65000 -c 1 -W0.5 " + cfg.remote_addr_v["4"]) + cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote) def _test_v6(cfg) -> None: - cfg.require_v6() + cfg.require_ipver("6") - cmd(f"ping -c 1 -W5 {cfg.remote_v6}") - cmd(f"ping -c 1 -W5 {cfg.v6}", host=cfg.remote) - cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.remote_v6}") - cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.v6}", host=cfg.remote) + cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"]) + cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote) + cmd("ping -s 65000 -c 1 -W0.5 " + cfg.remote_addr_v["6"]) + cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["6"], host=cfg.remote) def _test_tcp(cfg) -> None: cfg.require_cmd("socat", remote=True) @@ -126,7 +126,7 @@ def get_interface_info(cfg) -> None: global remote_ifname global no_sleep - remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_v4} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout + remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_addr_v['4']} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout remote_ifname = remote_info.rstrip('\n') if remote_ifname == "": raise KsftFailEx('Can not get remote interface') diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 8a518905a9f9..cae923f84f69 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -2,13 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 from lib.py import ksft_disruptive, ksft_exit, ksft_run -from lib.py import ksft_eq, ksft_raises, KsftSkipEx +from lib.py import ksft_eq, ksft_not_in, ksft_raises, KsftSkipEx, KsftFailEx from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import NetDrvEnv -from lib.py import cmd, defer, ip +from lib.py import bkg, cmd, defer, ip import errno import glob - +import os +import socket +import struct def sys_get_queues(ifname, qtype='rx') -> int: folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*') @@ -22,6 +24,40 @@ def nl_get_queues(cfg, nl, qtype='rx'): return None +def check_xsk(cfg, nl, xdp_queue_id=0) -> None: + # Probe for support + xdp = cmd(cfg.rpath("xdp_helper") + ' - -', fail=False) + if xdp.ret == 255: + raise KsftSkipEx('AF_XDP unsupported') + elif xdp.ret > 0: + raise KsftFailEx('unable to create AF_XDP socket') + + with bkg(f'{cfg.rpath("xdp_helper")} {cfg.ifindex} {xdp_queue_id}', + ksft_wait=3): + + rx = tx = False + + queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True) + if not queues: + raise KsftSkipEx("Netlink reports no queues") + + for q in queues: + if q['id'] == 0: + if q['type'] == 'rx': + rx = True + if q['type'] == 'tx': + tx = True + + ksft_eq(q.get('xsk', None), {}, + comment="xsk attr on queue we configured") + else: + ksft_not_in('xsk', q, + comment="xsk attr on queue we didn't configure") + + ksft_eq(rx, True) + ksft_eq(tx, True) + + def get_queues(cfg, nl) -> None: snl = NetdevFamily(recv_size=4096) @@ -80,7 +116,8 @@ def check_down(cfg, nl) -> None: def main() -> None: with NetDrvEnv(__file__, queue_count=100) as cfg: - ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily())) + ksft_run([get_queues, addremove_queues, check_down, check_xsk], + args=(cfg, NetdevFamily())) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/xdp_helper.c b/tools/testing/selftests/drivers/net/xdp_helper.c new file mode 100644 index 000000000000..aeed25914104 --- /dev/null +++ b/tools/testing/selftests/drivers/net/xdp_helper.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <linux/if_xdp.h> +#include <linux/if_link.h> +#include <net/if.h> +#include <inttypes.h> + +#define UMEM_SZ (1U << 16) +#define NUM_DESC (UMEM_SZ / 2048) + +/* Move this to a common header when reused! */ +static void ksft_ready(void) +{ + const char msg[7] = "ready\n"; + char *env_str; + int fd; + + env_str = getenv("KSFT_READY_FD"); + if (env_str) { + fd = atoi(env_str); + if (!fd) { + fprintf(stderr, "invalid KSFT_READY_FD = '%s'\n", + env_str); + return; + } + } else { + fd = STDOUT_FILENO; + } + + write(fd, msg, sizeof(msg)); + if (fd != STDOUT_FILENO) + close(fd); +} + +static void ksft_wait(void) +{ + char *env_str; + char byte; + int fd; + + env_str = getenv("KSFT_WAIT_FD"); + if (env_str) { + fd = atoi(env_str); + if (!fd) { + fprintf(stderr, "invalid KSFT_WAIT_FD = '%s'\n", + env_str); + return; + } + } else { + /* Not running in KSFT env, wait for input from STDIN instead */ + fd = STDIN_FILENO; + } + + read(fd, &byte, sizeof(byte)); + if (fd != STDIN_FILENO) + close(fd); +} + +/* this is a simple helper program that creates an XDP socket and does the + * minimum necessary to get bind() to succeed. + * + * this test program is not intended to actually process packets, but could be + * extended in the future if that is actually needed. + * + * it is used by queues.py to ensure the xsk netlinux attribute is set + * correctly. + */ +int main(int argc, char **argv) +{ + struct xdp_umem_reg umem_reg = { 0 }; + struct sockaddr_xdp sxdp = { 0 }; + int num_desc = NUM_DESC; + void *umem_area; + int ifindex; + int sock_fd; + int queue; + + if (argc != 3) { + fprintf(stderr, "Usage: %s ifindex queue_id\n", argv[0]); + return 1; + } + + sock_fd = socket(AF_XDP, SOCK_RAW, 0); + if (sock_fd < 0) { + perror("socket creation failed"); + /* if the kernel doesn't support AF_XDP, let the test program + * know with -1. All other error paths return 1. + */ + if (errno == EAFNOSUPPORT) + return -1; + return 1; + } + + /* "Probing mode", just checking if AF_XDP sockets are supported */ + if (!strcmp(argv[1], "-") && !strcmp(argv[2], "-")) { + printf("AF_XDP support detected\n"); + close(sock_fd); + return 0; + } + + ifindex = atoi(argv[1]); + queue = atoi(argv[2]); + + umem_area = mmap(NULL, UMEM_SZ, PROT_READ | PROT_WRITE, MAP_PRIVATE | + MAP_ANONYMOUS, -1, 0); + if (umem_area == MAP_FAILED) { + perror("mmap failed"); + return 1; + } + + umem_reg.addr = (uintptr_t)umem_area; + umem_reg.len = UMEM_SZ; + umem_reg.chunk_size = 2048; + umem_reg.headroom = 0; + + setsockopt(sock_fd, SOL_XDP, XDP_UMEM_REG, &umem_reg, + sizeof(umem_reg)); + setsockopt(sock_fd, SOL_XDP, XDP_UMEM_FILL_RING, &num_desc, + sizeof(num_desc)); + setsockopt(sock_fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &num_desc, + sizeof(num_desc)); + setsockopt(sock_fd, SOL_XDP, XDP_RX_RING, &num_desc, sizeof(num_desc)); + + sxdp.sxdp_family = AF_XDP; + sxdp.sxdp_ifindex = ifindex; + sxdp.sxdp_queue_id = queue; + sxdp.sxdp_flags = 0; + + if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) != 0) { + munmap(umem_area, UMEM_SZ); + perror("bind failed"); + close(sock_fd); + return 1; + } + + ksft_ready(); + ksft_wait(); + + /* parent program will write a byte to stdin when its ready for this + * helper to exit + */ + + close(sock_fd); + return 0; +} diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 28a715a8ef2b..679542f565a4 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -21,6 +21,7 @@ msg_oob msg_zerocopy netlink-dumps nettest +proc_net_pktgen psock_fanout psock_snd psock_tpacket @@ -42,6 +43,7 @@ socket so_incoming_cpu so_netns_cookie so_txtime +so_rcv_listener stress_reuseport_listen tap tcp_fastopen_backup_key diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 8f32b4f01aee..6d718b478ed8 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -7,7 +7,7 @@ CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) CFLAGS += -I../ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ - rtnetlink.sh xfrm_policy.sh test_blackhole_dev.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 @@ -33,9 +33,12 @@ TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh TEST_PROGS += cmsg_so_priority.sh -TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh +TEST_PROGS += test_so_rcv.sh +TEST_PROGS += cmsg_time.sh cmsg_ip.sh TEST_PROGS += netns-name.sh +TEST_PROGS += link_netns.py TEST_PROGS += nl_netdev.py +TEST_PROGS += rtnetlink.py TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh @@ -75,6 +78,7 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap epoll_busy_ TEST_GEN_FILES += toeplitz TEST_GEN_FILES += cmsg_sender TEST_GEN_FILES += stress_reuseport_listen +TEST_GEN_FILES += so_rcv_listener TEST_PROGS += test_vxlan_vnifiltering.sh TEST_GEN_FILES += io_uring_zerocopy_tx TEST_PROGS += io_uring_zerocopy_tx.sh @@ -100,6 +104,7 @@ TEST_PROGS += vlan_bridge_binding.sh TEST_PROGS += bpf_offload.py TEST_PROGS += ipv6_route_update_soft_lockup.sh TEST_PROGS += busy_poll_test.sh +TEST_GEN_PROGS += proc_net_pktgen TEST_PROGS += lwt_dst_cache_ref_loop.sh # YNL files, must be before "include ..lib.mk" diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py index fd0d959914e4..b2c271b79240 100755 --- a/tools/testing/selftests/net/bpf_offload.py +++ b/tools/testing/selftests/net/bpf_offload.py @@ -207,9 +207,11 @@ def bpftool_prog_list_wait(expected=0, n_retry=20): raise Exception("Time out waiting for program counts to stabilize want %d, have %d" % (expected, nprogs)) def bpftool_map_list_wait(expected=0, n_retry=20, ns=""): + nmaps = None for i in range(n_retry): maps = bpftool_map_list(ns=ns) - if len(maps) == expected: + nmaps = len(maps) + if nmaps == expected: return maps time.sleep(0.05) raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps)) @@ -710,6 +712,7 @@ _, base_maps = bpftool("map") base_map_names = [ 'pid_iter.rodata', # created on each bpftool invocation 'libbpf_det_bind', # created on each bpftool invocation + 'libbpf_global', ] # Check netdevsim diff --git a/tools/testing/selftests/net/cmsg_ip.sh b/tools/testing/selftests/net/cmsg_ip.sh new file mode 100755 index 000000000000..b55680e081ad --- /dev/null +++ b/tools/testing/selftests/net/cmsg_ip.sh @@ -0,0 +1,187 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +IP4=172.16.0.1/24 +TGT4=172.16.0.2 +IP6=2001:db8:1::1/64 +TGT6=2001:db8:1::2 +TMPF=$(mktemp --suffix ".pcap") + +cleanup() +{ + rm -f $TMPF + cleanup_ns $NS +} + +trap cleanup EXIT + +tcpdump -h | grep immediate-mode >> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP - tcpdump with --immediate-mode option required" + exit $ksft_skip +fi + +# Namespaces +setup_ns NS +NSEXE="ip netns exec $NS" + +$NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + +# Connectivity +ip -netns $NS link add type dummy +ip -netns $NS link set dev dummy0 up +ip -netns $NS addr add $IP4 dev dummy0 +ip -netns $NS addr add $IP6 dev dummy0 + +# Test +BAD=0 +TOTAL=0 + +check_result() { + ((TOTAL++)) + if [ $1 -ne $2 ]; then + echo " Case $3 returned $1, expected $2" + ((BAD++)) + fi +} + +# IPV6_DONTFRAG +for ovr in setsock cmsg both diff; do + for df in 0 1; do + for p in u U i r; do + [ $p == "u" ] && prot=UDP + [ $p == "U" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-F $df" + [ $ovr == "cmsg" ] && m="-f $df" + [ $ovr == "both" ] && m="-F $df -f $df" + [ $ovr == "diff" ] && m="-F $((1 - df)) -f $df" + + $NSEXE ./cmsg_sender -s -S 2000 -6 -p $p $m $TGT6 1234 + check_result $? $df "DONTFRAG $prot $ovr" + done + done +done + +# IP_TOS + IPV6_TCLASS + +test_dscp() { + local -r IPVER=$1 + local -r TGT=$2 + local -r MATCH=$3 + + local -r TOS=0x10 + local -r TOS2=0x20 + local -r ECN=0x3 + + ip $IPVER -netns $NS rule add tos $TOS lookup 300 + ip $IPVER -netns $NS route add table 300 prohibit any + + for ovr in setsock cmsg both diff; do + for p in u U i r; do + [ $p == "u" ] && prot=UDP + [ $p == "U" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-C" + [ $ovr == "cmsg" ] && m="-c" + [ $ovr == "both" ] && m="-C $((TOS2)) -c" + [ $ovr == "diff" ] && m="-C $((TOS )) -c" + + $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & + BG=$! + sleep 0.05 + + $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS2)) $TGT 1234 + check_result $? 0 "$MATCH $prot $ovr - pass" + + while [ -d /proc/$BG ]; do + $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS2)) $TGT 1234 + done + + tcpdump -r $TMPF -v 2>&1 | grep "$MATCH $TOS2" >> /dev/null + check_result $? 0 "$MATCH $prot $ovr - packet data" + rm $TMPF + + [ $ovr == "both" ] && m="-C $((TOS )) -c" + [ $ovr == "diff" ] && m="-C $((TOS2)) -c" + + # Match prohibit rule: expect failure + $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS)) -s $TGT 1234 + check_result $? 1 "$MATCH $prot $ovr - rejection" + + # Match prohibit rule: IPv4 masks ECN: expect failure + if [[ "$IPVER" == "-4" ]]; then + $NSEXE ./cmsg_sender $IPVER -p $p $m "$((TOS | ECN))" -s $TGT 1234 + check_result $? 1 "$MATCH $prot $ovr - rejection (ECN)" + fi + done + done +} + +test_dscp -4 $TGT4 tos +test_dscp -6 $TGT6 class + +# IP_TTL + IPV6_HOPLIMIT +test_ttl_hoplimit() { + local -r IPVER=$1 + local -r TGT=$2 + local -r MATCH=$3 + + local -r LIM=4 + + for ovr in setsock cmsg both diff; do + for p in u U i r; do + [ $p == "u" ] && prot=UDP + [ $p == "U" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-L" + [ $ovr == "cmsg" ] && m="-l" + [ $ovr == "both" ] && m="-L $LIM -l" + [ $ovr == "diff" ] && m="-L $((LIM + 1)) -l" + + $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & + BG=$! + sleep 0.05 + + $NSEXE ./cmsg_sender $IPVER -p $p $m $LIM $TGT 1234 + check_result $? 0 "$MATCH $prot $ovr - pass" + + while [ -d /proc/$BG ]; do + $NSEXE ./cmsg_sender $IPVER -p $p $m $LIM $TGT 1234 + done + + tcpdump -r $TMPF -v 2>&1 | grep "$MATCH $LIM[^0-9]" >> /dev/null + check_result $? 0 "$MATCH $prot $ovr - packet data" + rm $TMPF + done + done +} + +test_ttl_hoplimit -4 $TGT4 ttl +test_ttl_hoplimit -6 $TGT6 hlim + +# IPV6 exthdr +for p in u U i r; do + # Very basic "does it crash" test + for h in h d r; do + $NSEXE ./cmsg_sender -p $p -6 -H $h $TGT6 1234 + check_result $? 0 "ExtHdr $prot $ovr - pass" + done +done + +# Summary +if [ $BAD -ne 0 ]; then + echo "FAIL - $BAD/$TOTAL cases failed" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh deleted file mode 100755 index 8bc23fb4c82b..000000000000 --- a/tools/testing/selftests/net/cmsg_ipv6.sh +++ /dev/null @@ -1,154 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source lib.sh - -IP6=2001:db8:1::1/64 -TGT6=2001:db8:1::2 -TMPF=$(mktemp --suffix ".pcap") - -cleanup() -{ - rm -f $TMPF - cleanup_ns $NS -} - -trap cleanup EXIT - -tcpdump -h | grep immediate-mode >> /dev/null -if [ $? -ne 0 ]; then - echo "SKIP - tcpdump with --immediate-mode option required" - exit $ksft_skip -fi - -# Namespaces -setup_ns NS -NSEXE="ip netns exec $NS" - -$NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null - -# Connectivity -ip -netns $NS link add type dummy -ip -netns $NS link set dev dummy0 up -ip -netns $NS addr add $IP6 dev dummy0 - -# Test -BAD=0 -TOTAL=0 - -check_result() { - ((TOTAL++)) - if [ $1 -ne $2 ]; then - echo " Case $3 returned $1, expected $2" - ((BAD++)) - fi -} - -# IPV6_DONTFRAG -for ovr in setsock cmsg both diff; do - for df in 0 1; do - for p in u i r; do - [ $p == "u" ] && prot=UDP - [ $p == "i" ] && prot=ICMP - [ $p == "r" ] && prot=RAW - - [ $ovr == "setsock" ] && m="-F $df" - [ $ovr == "cmsg" ] && m="-f $df" - [ $ovr == "both" ] && m="-F $df -f $df" - [ $ovr == "diff" ] && m="-F $((1 - df)) -f $df" - - $NSEXE ./cmsg_sender -s -S 2000 -6 -p $p $m $TGT6 1234 - check_result $? $df "DONTFRAG $prot $ovr" - done - done -done - -# IPV6_TCLASS -TOS=0x10 -TOS2=0x20 - -ip -6 -netns $NS rule add tos $TOS lookup 300 -ip -6 -netns $NS route add table 300 prohibit any - -for ovr in setsock cmsg both diff; do - for p in u i r; do - [ $p == "u" ] && prot=UDP - [ $p == "i" ] && prot=ICMP - [ $p == "r" ] && prot=RAW - - [ $ovr == "setsock" ] && m="-C" - [ $ovr == "cmsg" ] && m="-c" - [ $ovr == "both" ] && m="-C $((TOS2)) -c" - [ $ovr == "diff" ] && m="-C $((TOS )) -c" - - $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & - BG=$! - sleep 0.05 - - $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234 - check_result $? 0 "TCLASS $prot $ovr - pass" - - while [ -d /proc/$BG ]; do - $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234 - done - - tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null - check_result $? 0 "TCLASS $prot $ovr - packet data" - rm $TMPF - - [ $ovr == "both" ] && m="-C $((TOS )) -c" - [ $ovr == "diff" ] && m="-C $((TOS2)) -c" - - $NSEXE ./cmsg_sender -6 -p $p $m $((TOS)) -s $TGT6 1234 - check_result $? 1 "TCLASS $prot $ovr - rejection" - done -done - -# IPV6_HOPLIMIT -LIM=4 - -for ovr in setsock cmsg both diff; do - for p in u i r; do - [ $p == "u" ] && prot=UDP - [ $p == "i" ] && prot=ICMP - [ $p == "r" ] && prot=RAW - - [ $ovr == "setsock" ] && m="-L" - [ $ovr == "cmsg" ] && m="-l" - [ $ovr == "both" ] && m="-L $LIM -l" - [ $ovr == "diff" ] && m="-L $((LIM + 1)) -l" - - $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & - BG=$! - sleep 0.05 - - $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234 - check_result $? 0 "HOPLIMIT $prot $ovr - pass" - - while [ -d /proc/$BG ]; do - $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234 - done - - tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null - check_result $? 0 "HOPLIMIT $prot $ovr - packet data" - rm $TMPF - done -done - -# IPV6 exthdr -for p in u i r; do - # Very basic "does it crash" test - for h in h d r; do - $NSEXE ./cmsg_sender -p $p -6 -H $h $TGT6 1234 - check_result $? 0 "ExtHdr $prot $ovr - pass" - done -done - -# Summary -if [ $BAD -ne 0 ]; then - echo "FAIL - $BAD/$TOTAL cases failed" - exit 1 -else - echo "OK" - exit 0 -fi diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index bc314382e4e1..a825e628aee7 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -33,6 +33,7 @@ enum { ERN_RECVERR, ERN_CMSG_RD, ERN_CMSG_RCV, + ERN_SEND_MORE, }; struct option_cmsg_u32 { @@ -46,6 +47,7 @@ struct options { const char *service; unsigned int size; unsigned int num_pkt; + bool msg_more; struct { unsigned int mark; unsigned int dontfrag; @@ -72,7 +74,7 @@ struct options { struct option_cmsg_u32 tclass; struct option_cmsg_u32 hlimit; struct option_cmsg_u32 exthdr; - } v6; + } cmsg; } opt = { .size = 13, .num_pkt = 1, @@ -94,7 +96,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin) "\t\t-S send() size\n" "\t\t-4/-6 Force IPv4 / IPv6 only\n" "\t\t-p prot Socket protocol\n" - "\t\t (u = UDP (default); i = ICMP; r = RAW)\n" + "\t\t (u = UDP (default); i = ICMP; r = RAW;\n" + "\t\t U = UDP with MSG_MORE)\n" "\n" "\t\t-m val Set SO_MARK with given value\n" "\t\t-M val Set SO_MARK via setsockopt\n" @@ -104,13 +107,13 @@ static void __attribute__((noreturn)) cs_usage(const char *bin) "\t\t-t Enable time stamp reporting\n" "\t\t-f val Set don't fragment via cmsg\n" "\t\t-F val Set don't fragment via setsockopt\n" - "\t\t-c val Set TCLASS via cmsg\n" - "\t\t-C val Set TCLASS via setsockopt\n" - "\t\t-l val Set HOPLIMIT via cmsg\n" - "\t\t-L val Set HOPLIMIT via setsockopt\n" + "\t\t-c val Set TOS/TCLASS via cmsg\n" + "\t\t-C val Set TOS/TCLASS via setsockopt\n" + "\t\t-l val Set TTL/HOPLIMIT via cmsg\n" + "\t\t-L val Set TTL/HOPLIMIT via setsockopt\n" "\t\t-H type Add an IPv6 header option\n" - "\t\t (h = HOP; d = DST; r = RTDST)" - ""); + "\t\t (h = HOP; d = DST; r = RTDST)\n" + "\n"); exit(ERN_HELP); } @@ -133,8 +136,11 @@ static void cs_parse_args(int argc, char *argv[]) opt.sock.family = AF_INET6; break; case 'p': - if (*optarg == 'u' || *optarg == 'U') { + if (*optarg == 'u') { opt.sock.proto = IPPROTO_UDP; + } else if (*optarg == 'U') { + opt.sock.proto = IPPROTO_UDP; + opt.msg_more = true; } else if (*optarg == 'i' || *optarg == 'I') { opt.sock.proto = IPPROTO_ICMP; } else if (*optarg == 'r') { @@ -169,37 +175,37 @@ static void cs_parse_args(int argc, char *argv[]) opt.ts.ena = true; break; case 'f': - opt.v6.dontfrag.ena = true; - opt.v6.dontfrag.val = atoi(optarg); + opt.cmsg.dontfrag.ena = true; + opt.cmsg.dontfrag.val = atoi(optarg); break; case 'F': opt.sockopt.dontfrag = atoi(optarg); break; case 'c': - opt.v6.tclass.ena = true; - opt.v6.tclass.val = atoi(optarg); + opt.cmsg.tclass.ena = true; + opt.cmsg.tclass.val = atoi(optarg); break; case 'C': opt.sockopt.tclass = atoi(optarg); break; case 'l': - opt.v6.hlimit.ena = true; - opt.v6.hlimit.val = atoi(optarg); + opt.cmsg.hlimit.ena = true; + opt.cmsg.hlimit.val = atoi(optarg); break; case 'L': opt.sockopt.hlimit = atoi(optarg); break; case 'H': - opt.v6.exthdr.ena = true; + opt.cmsg.exthdr.ena = true; switch (optarg[0]) { case 'h': - opt.v6.exthdr.val = IPV6_HOPOPTS; + opt.cmsg.exthdr.val = IPV6_HOPOPTS; break; case 'd': - opt.v6.exthdr.val = IPV6_DSTOPTS; + opt.cmsg.exthdr.val = IPV6_DSTOPTS; break; case 'r': - opt.v6.exthdr.val = IPV6_RTHDRDSTOPTS; + opt.cmsg.exthdr.val = IPV6_RTHDRDSTOPTS; break; default: printf("Error: hdr type: %s\n", optarg); @@ -261,12 +267,20 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) SOL_SOCKET, SO_MARK, &opt.mark); ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, SOL_SOCKET, SO_PRIORITY, &opt.priority); - ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, - SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag); - ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, - SOL_IPV6, IPV6_TCLASS, &opt.v6.tclass); - ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, - SOL_IPV6, IPV6_HOPLIMIT, &opt.v6.hlimit); + + if (opt.sock.family == AF_INET) { + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IP, IP_TOS, &opt.cmsg.tclass); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IP, IP_TTL, &opt.cmsg.hlimit); + } else { + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_DONTFRAG, &opt.cmsg.dontfrag); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_TCLASS, &opt.cmsg.tclass); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_HOPLIMIT, &opt.cmsg.hlimit); + } if (opt.txtime.ena) { __u64 txtime; @@ -297,14 +311,14 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) *(__u32 *)CMSG_DATA(cmsg) = SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE; } - if (opt.v6.exthdr.ena) { + if (opt.cmsg.exthdr.ena) { cmsg = (struct cmsghdr *)(cbuf + cmsg_len); cmsg_len += CMSG_SPACE(8); if (cbuf_sz < cmsg_len) error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); cmsg->cmsg_level = SOL_IPV6; - cmsg->cmsg_type = opt.v6.exthdr.val; + cmsg->cmsg_type = opt.cmsg.exthdr.val; cmsg->cmsg_len = CMSG_LEN(8); *(__u64 *)CMSG_DATA(cmsg) = 0; } @@ -405,23 +419,35 @@ static void ca_set_sockopts(int fd) setsockopt(fd, SOL_SOCKET, SO_MARK, &opt.sockopt.mark, sizeof(opt.sockopt.mark))) error(ERN_SOCKOPT, errno, "setsockopt SO_MARK"); - if (opt.sockopt.dontfrag && - setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG, - &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag))) - error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG"); - if (opt.sockopt.tclass && - setsockopt(fd, SOL_IPV6, IPV6_TCLASS, - &opt.sockopt.tclass, sizeof(opt.sockopt.tclass))) - error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS"); - if (opt.sockopt.hlimit && - setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS, - &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit))) - error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT"); if (opt.sockopt.priority && setsockopt(fd, SOL_SOCKET, SO_PRIORITY, &opt.sockopt.priority, sizeof(opt.sockopt.priority))) error(ERN_SOCKOPT, errno, "setsockopt SO_PRIORITY"); + if (opt.sock.family == AF_INET) { + if (opt.sockopt.tclass && + setsockopt(fd, SOL_IP, IP_TOS, + &opt.sockopt.tclass, sizeof(opt.sockopt.tclass))) + error(ERN_SOCKOPT, errno, "setsockopt IP_TOS"); + if (opt.sockopt.hlimit && + setsockopt(fd, SOL_IP, IP_TTL, + &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit))) + error(ERN_SOCKOPT, errno, "setsockopt IP_TTL"); + } else { + if (opt.sockopt.dontfrag && + setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG, + &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG"); + if (opt.sockopt.tclass && + setsockopt(fd, SOL_IPV6, IPV6_TCLASS, + &opt.sockopt.tclass, sizeof(opt.sockopt.tclass))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS"); + if (opt.sockopt.hlimit && + setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS, + &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT"); + } + if (opt.txtime.ena) { struct sock_txtime so_txtime = { .clockid = CLOCK_MONOTONIC, @@ -511,7 +537,7 @@ int main(int argc, char *argv[]) cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf)); for (i = 0; i < opt.num_pkt; i++) { - err = sendmsg(fd, &msg, 0); + err = sendmsg(fd, &msg, opt.msg_more ? MSG_MORE : 0); if (err < 0) { if (!opt.silent_send) fprintf(stderr, "send failed: %s\n", strerror(errno)); @@ -522,6 +548,14 @@ int main(int argc, char *argv[]) err = ERN_SEND_SHORT; goto err_out; } + if (opt.msg_more) { + err = write(fd, NULL, 0); + if (err < 0) { + fprintf(stderr, "send more: %s\n", strerror(errno)); + err = ERN_SEND_MORE; + goto err_out; + } + } } err = ERN_SUCCESS; diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 61e5116987f3..130d532b7e67 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -18,6 +18,8 @@ CONFIG_DUMMY=y CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_BRIDGE=y CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_DEBUG_INFO_BTF=y +CONFIG_DEBUG_INFO_BTF_MODULES=n CONFIG_VLAN_8021Q=y CONFIG_GENEVE=m CONFIG_IFB=y @@ -107,5 +109,11 @@ CONFIG_XFRM_INTERFACE=m CONFIG_XFRM_USER=m CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_MATCH_RPFILTER=m +CONFIG_IPVLAN=m +CONFIG_CAN=m +CONFIG_CAN_DEV=m +CONFIG_CAN_VXCAN=m +CONFIG_NETKIT=y +CONFIG_NET_PKTGEN=m CONFIG_IPV6_ILA=m CONFIG_IPV6_RPL_LWTUNNEL=y diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 899dbad0104b..4fcc38907e48 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -3667,7 +3667,7 @@ ipv6_addr_bind_novrf() # when it really should not a=${NSA_LO_IP6} log_start - show_hint "Tecnically should fail since address is not on device but kernel allows" + show_hint "Technically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address" } @@ -3724,7 +3724,7 @@ ipv6_addr_bind_vrf() # passes when it really should not a=${VRF_IP6} log_start - show_hint "Tecnically should fail since address is not on device but kernel allows" + show_hint "Technically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind" diff --git a/tools/testing/selftests/net/fdb_flush.sh b/tools/testing/selftests/net/fdb_flush.sh index d5e3abb8658c..9931a1e36e3d 100755 --- a/tools/testing/selftests/net/fdb_flush.sh +++ b/tools/testing/selftests/net/fdb_flush.sh @@ -583,7 +583,7 @@ vxlan_test_flush_by_remote_attributes() $IP link del dev vx10 $IP link add name vx10 type vxlan dstport "$VXPORT" external - # For multicat FDB entries, the VXLAN driver stores a linked list of + # For multicast FDB entries, the VXLAN driver stores a linked list of # remotes for a given key. Verify that only the expected remotes are # flushed. multicast_fdb_entries_add diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 77c83d9508d3..b39f748c2572 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -76,11 +76,13 @@ log_test() printf "TEST: %-60s [ OK ]\n" "${msg}" nsuccess=$((nsuccess+1)) else - ret=1 - nfail=$((nfail+1)) if [[ $rc -eq $ksft_skip ]]; then + [[ $ret -eq 0 ]] && ret=$ksft_skip + nskip=$((nskip+1)) printf "TEST: %-60s [SKIP]\n" "${msg}" else + ret=1 + nfail=$((nfail+1)) printf "TEST: %-60s [FAIL]\n" "${msg}" fi @@ -741,7 +743,7 @@ ipv6_fcnal() run_cmd "$IP nexthop add id 52 via 2001:db8:92::3" log_test $? 2 "Create nexthop - gw only" - # gw is not reachable throught given dev + # gw is not reachable through given dev run_cmd "$IP nexthop add id 53 via 2001:db8:3::3 dev veth1" log_test $? 2 "Create nexthop - invalid gw+dev combination" @@ -2528,6 +2530,7 @@ done if [ "$TESTS" != "none" ]; then printf "\nTests passed: %3d\n" ${nsuccess} printf "Tests failed: %3d\n" ${nfail} + printf "Tests skipped: %2d\n" ${nskip} fi exit $ret diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 847936363a12..b866bab1d92a 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -256,6 +256,24 @@ fib_rule6_test() fib_rule6_test_match_n_redirect "$match" "$match" \ "$getnomatch" "sport and dport redirect to table" \ "sport and dport no redirect to table" + + match="sport 100-200 dport 300-400" + getmatch="sport 100 dport 400" + getnomatch="sport 100 dport 401" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" \ + "sport and dport range redirect to table" \ + "sport and dport range no redirect to table" + fi + + ip rule help 2>&1 | grep sport | grep -q MASK + if [ $? -eq 0 ]; then + match="sport 0x0f00/0xff00 dport 0x000f/0x00ff" + getmatch="sport 0x0f11 dport 0x220f" + getnomatch="sport 0x1f11 dport 0x221f" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "sport and dport masked redirect to table" \ + "sport and dport masked no redirect to table" fi fib_check_iproute_support "ipproto" "ipproto" @@ -292,6 +310,25 @@ fib_rule6_test() "iif dscp no redirect to table" fi + ip rule help 2>&1 | grep -q "DSCP\[/MASK\]" + if [ $? -eq 0 ]; then + match="dscp 0x0f/0x0f" + tosmatch=$(printf 0x"%x" $((0x1f << 2))) + tosnomatch=$(printf 0x"%x" $((0x1e << 2))) + getmatch="tos $tosmatch" + getnomatch="tos $tosnomatch" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "dscp masked redirect to table" \ + "dscp masked no redirect to table" + + match="dscp 0x0f/0x0f" + getmatch="from $SRC_IP6 iif $DEV tos $tosmatch" + getnomatch="from $SRC_IP6 iif $DEV tos $tosnomatch" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "iif dscp masked redirect to table" \ + "iif dscp masked no redirect to table" + fi + fib_check_iproute_support "flowlabel" "flowlabel" if [ $? -eq 0 ]; then match="flowlabel 0xfffff" @@ -525,6 +562,24 @@ fib_rule4_test() fib_rule4_test_match_n_redirect "$match" "$match" \ "$getnomatch" "sport and dport redirect to table" \ "sport and dport no redirect to table" + + match="sport 100-200 dport 300-400" + getmatch="sport 100 dport 400" + getnomatch="sport 100 dport 401" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" \ + "sport and dport range redirect to table" \ + "sport and dport range no redirect to table" + fi + + ip rule help 2>&1 | grep sport | grep -q MASK + if [ $? -eq 0 ]; then + match="sport 0x0f00/0xff00 dport 0x000f/0x00ff" + getmatch="sport 0x0f11 dport 0x220f" + getnomatch="sport 0x1f11 dport 0x221f" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "sport and dport masked redirect to table" \ + "sport and dport masked no redirect to table" fi fib_check_iproute_support "ipproto" "ipproto" @@ -561,6 +616,25 @@ fib_rule4_test() "$getnomatch" "iif dscp redirect to table" \ "iif dscp no redirect to table" fi + + ip rule help 2>&1 | grep -q "DSCP\[/MASK\]" + if [ $? -eq 0 ]; then + match="dscp 0x0f/0x0f" + tosmatch=$(printf 0x"%x" $((0x1f << 2))) + tosnomatch=$(printf 0x"%x" $((0x1e << 2))) + getmatch="tos $tosmatch" + getnomatch="tos $tosnomatch" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "dscp masked redirect to table" \ + "dscp masked no redirect to table" + + match="dscp 0x0f/0x0f" + getmatch="from $SRC_IP iif $DEV tos $tosmatch" + getnomatch="from $SRC_IP iif $DEV tos $tosnomatch" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "iif dscp masked redirect to table" \ + "iif dscp masked no redirect to table" + fi } fib_rule4_vrf_test() diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README index a652429bfd53..7b41cff993ad 100644 --- a/tools/testing/selftests/net/forwarding/README +++ b/tools/testing/selftests/net/forwarding/README @@ -6,7 +6,7 @@ to easily create and test complex environments. Unfortunately, these namespaces can not be used with actual switching ASICs, as their ports can not be migrated to other network namespaces -(dev->netns_local) and most of them probably do not support the +(dev->netns_immutable) and most of them probably do not support the L1-separation provided by namespaces. However, a similar kind of flexibility can be achieved by using VRFs and diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index d9d587454d20..8c1597ebc2d3 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -149,7 +149,7 @@ cfg_test_host_common() check_err $? "Failed to add $name host entry" bridge mdb replace dev br0 port br0 grp $grp $state vid 10 &> /dev/null - check_fail $? "Managed to replace $name host entry" + check_err $? "Failed to replace $name host entry" bridge mdb del dev br0 port br0 grp $grp $state vid 10 bridge mdb get dev br0 grp $grp vid 10 &> /dev/null diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8de80acf249e..508f3c700d71 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -291,16 +291,6 @@ if [[ "$CHECK_TC" = "yes" ]]; then check_tc_version fi -require_command() -{ - local cmd=$1; shift - - if [[ ! -x "$(command -v "$cmd")" ]]; then - echo "SKIP: $cmd not installed" - exit $ksft_skip - fi -} - # IPv6 support was added in v3.0 check_mtools_version() { diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index 3f9d50f1ef9e..b43816dd998c 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -428,6 +428,14 @@ __test_flood() test_flood() { __test_flood de:ad:be:ef:13:37 192.0.2.100 "flood" + + # Add an entry with arbitrary destination IP. Verify that packets are + # not duplicated (this can happen if hardware floods the packets, and + # then traps them due to misconfiguration, so software data path repeats + # flooding and resends packets). + bridge fdb append dev vx1 00:00:00:00:00:00 dst 198.51.100.1 self + __test_flood de:ad:be:ef:13:37 192.0.2.100 "flood, unresolved FDB entry" + bridge fdb del dev vx1 00:00:00:00:00:00 dst 198.51.100.1 self } vxlan_fdb_add_del() @@ -740,6 +748,8 @@ test_learning() vxlan_flood_test $mac $dst 0 10 0 + # The entry should age out when it only forwards traffic + $MZ $h1 -c 50 -d 1sec -p 64 -b $mac -B $dst -t icmp -q & sleep 60 bridge fdb show brport vx1 | grep $mac | grep -q self diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh index fb9a34cb50c6..afc65647f673 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh @@ -539,6 +539,21 @@ test_flood() 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 + + # Add entries with arbitrary destination IP. Verify that packets are + # not duplicated (this can happen if hardware floods the packets, and + # then traps them due to misconfiguration, so software data path repeats + # flooding and resends packets). + bridge fdb append dev vx10 00:00:00:00:00:00 dst 203.0.113.1 self + bridge fdb append dev vx20 00:00:00:00:00:00 dst 203.0.113.2 self + + __test_flood de:ad:be:ef:13:37 192.0.2.100 10 \ + "flood vlan 10, unresolved FDB entry" 10 10 0 10 0 + __test_flood ca:fe:be:ef:13:37 198.51.100.100 20 \ + "flood vlan 20, unresolved FDB entry" 10 0 10 0 10 + + bridge fdb del dev vx20 00:00:00:00:00:00 dst 203.0.113.2 self + bridge fdb del dev vx10 00:00:00:00:00:00 dst 203.0.113.1 self } vxlan_fdb_add_del() diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index b2184847e388..d5824eadea10 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -1318,11 +1318,13 @@ int main(int argc, char **argv) read_MAC(src_mac, smac); read_MAC(dst_mac, dmac); - if (tx_socket) + if (tx_socket) { gro_sender(); - else + } else { + /* Only the receiver exit status determines test success. */ gro_receiver(); + fprintf(stderr, "Gro::%s test passed.\n", testname); + } - fprintf(stderr, "Gro::%s test passed.\n", testname); return 0; } diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 02c21ff4ca81..9e3f186bc2a1 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -18,10 +18,10 @@ run_test() { "--smac" "${CLIENT_MAC}" "--test" "${test}" "--verbose" ) setup_ns - # Each test is run 3 times to deflake, because given the receive timing, + # Each test is run 6 times to deflake, because given the receive timing, # not all packets that should coalesce will be considered in the same flow # on every try. - for tries in {1..3}; do + for tries in {1..6}; do # Actual test starts here ip netns exec $server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \ 1>>log.txt & @@ -100,5 +100,6 @@ trap cleanup EXIT if [[ "${test}" == "all" ]]; then run_all_tests else - run_test "${proto}" "${test}" + exit_code=$(run_test "${proto}" "${test}") + exit $exit_code fi; diff --git a/tools/testing/selftests/net/ip_local_port_range.sh b/tools/testing/selftests/net/ip_local_port_range.sh index 6c6ad346eaa0..4ff746db1256 100755 --- a/tools/testing/selftests/net/ip_local_port_range.sh +++ b/tools/testing/selftests/net/ip_local_port_range.sh @@ -2,4 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 ./in_netns.sh \ - sh -c 'sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && ./ip_local_port_range' + sh -c 'sysctl -q -w net.mptcp.enabled=1 && \ + sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && \ + ./ip_local_port_range' diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 0bd9a038a1f0..975be4fdbcdb 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -450,6 +450,25 @@ kill_process() { kill $pid && wait $pid; } 2>/dev/null } +check_command() +{ + local cmd=$1; shift + + if [[ ! -x "$(command -v "$cmd")" ]]; then + log_test_skip "$cmd not installed" + return $EXIT_STATUS + fi +} + +require_command() +{ + local cmd=$1; shift + + if ! check_command "$cmd"; then + exit $EXIT_STATUS + fi +} + ip_link_add() { local name=$1; shift diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 54d8f5eba810..8697bd27dc30 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -2,8 +2,8 @@ from .consts import KSRC from .ksft import * -from .netns import NetNS +from .netns import NetNS, NetNSEnter from .nsim import * from .utils import * -from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily +from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily from .ynl import NetshaperFamily diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 3efe005436cd..3cfad0fd4570 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -71,6 +71,11 @@ def ksft_in(a, b, comment=""): _fail("Check failed", a, "not in", b, comment) +def ksft_not_in(a, b, comment=""): + if a in b: + _fail("Check failed", a, "in", b, comment) + + def ksft_is(a, b, comment=""): if a is not b: _fail("Check failed", a, "is not", b, comment) @@ -202,7 +207,7 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} - print("KTAP version 1") + print("TAP version 13") print("1.." + str(len(cases))) global KSFT_RESULT diff --git a/tools/testing/selftests/net/lib/py/netns.py b/tools/testing/selftests/net/lib/py/netns.py index ecff85f9074f..8e9317044eef 100644 --- a/tools/testing/selftests/net/lib/py/netns.py +++ b/tools/testing/selftests/net/lib/py/netns.py @@ -1,9 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 from .utils import ip +import ctypes import random import string +libc = ctypes.cdll.LoadLibrary('libc.so.6') + class NetNS: def __init__(self, name=None): @@ -29,3 +32,18 @@ class NetNS: def __repr__(self): return f"NetNS({self.name})" + + +class NetNSEnter: + def __init__(self, ns_name): + self.ns_path = f"/run/netns/{ns_name}" + + def __enter__(self): + self.saved = open("/proc/thread-self/ns/net") + with open(self.ns_path) as ns_file: + libc.setns(ns_file.fileno(), 0) + return self + + def __exit__(self, exc_type, exc_value, traceback): + libc.setns(self.saved.fileno(), 0) + self.saved.close() diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 9e3bcddcf3e8..34470d65d871 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -2,8 +2,10 @@ import errno import json as _json +import os import random import re +import select import socket import subprocess import time @@ -15,21 +17,56 @@ class CmdExitFailure(Exception): self.cmd = cmd_obj +def fd_read_timeout(fd, timeout): + rlist, _, _ = select.select([fd], [], [], timeout) + if rlist: + return os.read(fd, 1024) + else: + raise TimeoutError("Timeout waiting for fd read") + + class cmd: - def __init__(self, comm, shell=True, fail=True, ns=None, background=False, host=None, timeout=5): + """ + Execute a command on local or remote host. + + Use bkg() instead to run a command in the background. + """ + def __init__(self, comm, shell=True, fail=True, ns=None, background=False, + host=None, timeout=5, ksft_wait=None): if ns: comm = f'ip netns exec {ns} ' + comm self.stdout = None self.stderr = None self.ret = None + self.ksft_term_fd = None self.comm = comm if host: self.proc = host.cmd(comm) else: + # ksft_wait lets us wait for the background process to fully start, + # we pass an FD to the child process, and wait for it to write back. + # Similarly term_fd tells child it's time to exit. + pass_fds = () + env = os.environ.copy() + if ksft_wait is not None: + rfd, ready_fd = os.pipe() + wait_fd, self.ksft_term_fd = os.pipe() + pass_fds = (ready_fd, wait_fd, ) + env["KSFT_READY_FD"] = str(ready_fd) + env["KSFT_WAIT_FD"] = str(wait_fd) + self.proc = subprocess.Popen(comm, shell=shell, stdout=subprocess.PIPE, - stderr=subprocess.PIPE) + stderr=subprocess.PIPE, pass_fds=pass_fds, + env=env) + if ksft_wait is not None: + os.close(ready_fd) + os.close(wait_fd) + msg = fd_read_timeout(rfd, ksft_wait) + os.close(rfd) + if not msg: + raise Exception("Did not receive ready message") if not background: self.process(terminate=False, fail=fail, timeout=timeout) @@ -37,6 +74,8 @@ class cmd: if fail is None: fail = not terminate + if self.ksft_term_fd: + os.write(self.ksft_term_fd, b"1") if terminate: self.proc.terminate() stdout, stderr = self.proc.communicate(timeout) @@ -54,13 +93,36 @@ class cmd: class bkg(cmd): + """ + Run a command in the background. + + Examples usage: + + Run a command on remote host, and wait for it to finish. + This is usually paired with wait_port_listen() to make sure + the command has initialized: + + with bkg("socat ...", exit_wait=True, host=cfg.remote) as nc: + ... + + Run a command and expect it to let us know that it's ready + by writing to a special file descriptor passed via KSFT_READY_FD. + Command will be terminated when we exit the context manager: + + with bkg("my_binary", ksft_wait=5): + """ def __init__(self, comm, shell=True, fail=None, ns=None, host=None, - exit_wait=False): + exit_wait=False, ksft_wait=None): super().__init__(comm, background=True, - shell=shell, fail=fail, ns=ns, host=host) - self.terminate = not exit_wait + shell=shell, fail=fail, ns=ns, host=host, + ksft_wait=ksft_wait) + self.terminate = not exit_wait and not ksft_wait self.check_fail = fail + if shell and self.terminate: + print("# Warning: combining shell and terminate is risky!") + print("# SIGTERM may not reach the child on zsh/ksh!") + def __enter__(self): return self @@ -123,20 +185,13 @@ def ethtool(args, json=None, ns=None, host=None): return tool('ethtool', args, json=json, ns=ns, host=host) -def rand_port(): +def rand_port(type=socket.SOCK_STREAM): """ - Get a random unprivileged port, try to make sure it's not already used. + Get a random unprivileged port. """ - for _ in range(1000): - port = random.randint(10000, 65535) - try: - with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s: - s.bind(("", port)) - return port - except OSError as e: - if e.errno != errno.EADDRINUSE: - raise - raise Exception("Can't find any free unprivileged port") + with socket.socket(socket.AF_INET6, type) as s: + s.bind(("", 0)) + return s.getsockname()[1] def wait_port_listen(port, proto="tcp", ns=None, host=None, sleep=0.005, deadline=5): diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index ad1e36baee2a..8986c584cb37 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -42,6 +42,10 @@ class RtnlFamily(YnlFamily): super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(), schema='', recv_size=recv_size) +class RtnlAddrFamily(YnlFamily): + def __init__(self, recv_size=0): + super().__init__((SPEC_PATH / Path('rt_addr.yaml')).as_posix(), + schema='', recv_size=recv_size) class NetdevFamily(YnlFamily): def __init__(self, recv_size=0): diff --git a/tools/testing/selftests/net/link_netns.py b/tools/testing/selftests/net/link_netns.py new file mode 100755 index 000000000000..aab043c59d69 --- /dev/null +++ b/tools/testing/selftests/net/link_netns.py @@ -0,0 +1,141 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import time + +from lib.py import ksft_run, ksft_exit, ksft_true +from lib.py import ip +from lib.py import NetNS, NetNSEnter +from lib.py import RtnlFamily + + +LINK_NETNSID = 100 + + +def test_event() -> None: + with NetNS() as ns1, NetNS() as ns2: + with NetNSEnter(str(ns2)): + rtnl = RtnlFamily() + + rtnl.ntf_subscribe("rtnlgrp-link") + + ip(f"netns set {ns2} {LINK_NETNSID}", ns=str(ns1)) + ip(f"link add netns {ns1} link-netnsid {LINK_NETNSID} dummy1 type dummy") + ip(f"link add netns {ns1} dummy2 type dummy", ns=str(ns2)) + + ip("link del dummy1", ns=str(ns1)) + ip("link del dummy2", ns=str(ns1)) + + time.sleep(1) + rtnl.check_ntf() + ksft_true(rtnl.async_msg_queue.empty(), + "Received unexpected link notification") + + +def validate_link_netns(netns, ifname, link_netnsid) -> bool: + link_info = ip(f"-d link show dev {ifname}", ns=netns, json=True) + if not link_info: + return False + return link_info[0].get("link_netnsid") == link_netnsid + + +def test_link_net() -> None: + configs = [ + # type, common args, type args, fallback to dev_net + ("ipvlan", "link dummy1", "", False), + ("macsec", "link dummy1", "", False), + ("macvlan", "link dummy1", "", False), + ("macvtap", "link dummy1", "", False), + ("vlan", "link dummy1", "id 100", False), + ("gre", "", "local 192.0.2.1", True), + ("vti", "", "local 192.0.2.1", True), + ("ipip", "", "local 192.0.2.1", True), + ("ip6gre", "", "local 2001:db8::1", True), + ("ip6tnl", "", "local 2001:db8::1", True), + ("vti6", "", "local 2001:db8::1", True), + ("sit", "", "local 192.0.2.1", True), + ("xfrm", "", "if_id 1", True), + ] + + with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3: + net1, net2, net3 = str(ns1), str(ns2), str(ns3) + + # prepare link netnsid and a dummy link needed by certain drivers + ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2)) + ip("link add dummy1 type dummy", ns=net3) + + cases = [ + # source, "netns", "link-netns", expected link-netns + (net3, None, None, None, None), + (net3, net2, None, None, LINK_NETNSID), + (net2, None, net3, LINK_NETNSID, LINK_NETNSID), + (net1, net2, net3, LINK_NETNSID, LINK_NETNSID), + ] + + for src_net, netns, link_netns, exp1, exp2 in cases: + tgt_net = netns or src_net + for typ, cargs, targs, fb_dev_net in configs: + cmd = "link add" + if netns: + cmd += f" netns {netns}" + if link_netns: + cmd += f" link-netns {link_netns}" + cmd += f" {cargs} foo type {typ} {targs}" + ip(cmd, ns=src_net) + if fb_dev_net: + ksft_true(validate_link_netns(tgt_net, "foo", exp1), + f"{typ} link_netns validation failed") + else: + ksft_true(validate_link_netns(tgt_net, "foo", exp2), + f"{typ} link_netns validation failed") + ip(f"link del foo", ns=tgt_net) + + +def test_peer_net() -> None: + types = [ + "vxcan", + "netkit", + "veth", + ] + + with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3, NetNS() as ns4: + net1, net2, net3, net4 = str(ns1), str(ns2), str(ns3), str(ns4) + + ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2)) + + cases = [ + # source, "netns", "link-netns", "peer netns", expected + (net1, None, None, None, None), + (net1, net2, None, None, None), + (net2, None, net3, None, LINK_NETNSID), + (net1, net2, net3, None, None), + (net2, None, None, net3, LINK_NETNSID), + (net1, net2, None, net3, LINK_NETNSID), + (net2, None, net2, net3, LINK_NETNSID), + (net1, net2, net4, net3, LINK_NETNSID), + ] + + for src_net, netns, link_netns, peer_netns, exp in cases: + tgt_net = netns or src_net + for typ in types: + cmd = "link add" + if netns: + cmd += f" netns {netns}" + if link_netns: + cmd += f" link-netns {link_netns}" + cmd += f" foo type {typ}" + if peer_netns: + cmd += f" peer netns {peer_netns}" + ip(cmd, ns=src_net) + ksft_true(validate_link_netns(tgt_net, "foo", exp), + f"{typ} peer_netns validation failed") + ip(f"link del foo", ns=tgt_net) + + +def main() -> None: + ksft_run([test_event, test_link_net, test_peer_net]) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index c76525fe2b84..340e1a777e16 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -7,7 +7,7 @@ CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INC TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh -TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq +TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag TEST_FILES := mptcp_lib.sh settings diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 2bd0c1eb70c5..4f55477ffe08 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -200,6 +200,32 @@ chk_msk_cestab() "${expected}" "${msg}" "" } +chk_dump_one() +{ + local ss_token + local token + local msg + + ss_token="$(ss -inmHMN $ns | grep 'token:' |\ + head -n 1 |\ + sed 's/.*token:\([0-9a-f]*\).*/\1/')" + + token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\ + awk -F':[ \t]+' '/^token/ {print $2}')" + + msg="....chk dump_one" + + mptcp_lib_print_title "$msg" + if [ -n "$ss_token" ] && [ "$ss_token" = "$token" ]; then + mptcp_lib_pr_ok + mptcp_lib_result_pass "${msg}" + else + mptcp_lib_pr_fail "expected $ss_token found $token" + mptcp_lib_result_fail "${msg}" + ret=${KSFT_FAIL} + fi +} + msk_info_get_value() { local port="${1}" @@ -290,6 +316,7 @@ chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" chk_msk_inuse 2 chk_msk_cestab 2 +chk_dump_one flush_pids chk_msk_inuse 0 "2->0" diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c new file mode 100644 index 000000000000..284286c524cf --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025, Kylin Software */ + +#include <linux/sock_diag.h> +#include <linux/rtnetlink.h> +#include <linux/inet_diag.h> +#include <linux/netlink.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <linux/tcp.h> + +#include <unistd.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <stdio.h> + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif + +struct mptcp_info { + __u8 mptcpi_subflows; + __u8 mptcpi_add_addr_signal; + __u8 mptcpi_add_addr_accepted; + __u8 mptcpi_subflows_max; + __u8 mptcpi_add_addr_signal_max; + __u8 mptcpi_add_addr_accepted_max; + __u32 mptcpi_flags; + __u32 mptcpi_token; + __u64 mptcpi_write_seq; + __u64 mptcpi_snd_una; + __u64 mptcpi_rcv_nxt; + __u8 mptcpi_local_addr_used; + __u8 mptcpi_local_addr_max; + __u8 mptcpi_csum_enabled; + __u32 mptcpi_retransmits; + __u64 mptcpi_bytes_retrans; + __u64 mptcpi_bytes_sent; + __u64 mptcpi_bytes_received; + __u64 mptcpi_bytes_acked; + __u8 mptcpi_subflows_total; + __u8 reserved[3]; + __u32 mptcpi_last_data_sent; + __u32 mptcpi_last_data_recv; + __u32 mptcpi_last_ack_recv; +}; + +static void die_perror(const char *msg) +{ + perror(msg); + exit(1); +} + +static void die_usage(int r) +{ + fprintf(stderr, "Usage: mptcp_diag -t\n"); + exit(r); +} + +static void send_query(int fd, __u32 token) +{ + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK + }; + struct { + struct nlmsghdr nlh; + struct inet_diag_req_v2 r; + } req = { + .nlh = { + .nlmsg_len = sizeof(req), + .nlmsg_type = SOCK_DIAG_BY_FAMILY, + .nlmsg_flags = NLM_F_REQUEST + }, + .r = { + .sdiag_family = AF_INET, + /* Real proto is set via INET_DIAG_REQ_PROTOCOL */ + .sdiag_protocol = IPPROTO_TCP, + .id.idiag_cookie[0] = token, + } + }; + struct rtattr rta_proto; + struct iovec iov[6]; + int iovlen = 1; + __u32 proto; + + req.r.idiag_ext |= (1 << (INET_DIAG_INFO - 1)); + proto = IPPROTO_MPTCP; + rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL; + rta_proto.rta_len = RTA_LENGTH(sizeof(proto)); + + iov[0] = (struct iovec) { + .iov_base = &req, + .iov_len = sizeof(req) + }; + iov[iovlen] = (struct iovec){ &rta_proto, sizeof(rta_proto)}; + iov[iovlen + 1] = (struct iovec){ &proto, sizeof(proto)}; + req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto)); + iovlen += 2; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = iov, + .msg_iovlen = iovlen + }; + + for (;;) { + if (sendmsg(fd, &msg, 0) < 0) { + if (errno == EINTR) + continue; + die_perror("sendmsg"); + } + break; + } +} + +static void parse_rtattr_flags(struct rtattr *tb[], int max, struct rtattr *rta, + int len, unsigned short flags) +{ + unsigned short type; + + memset(tb, 0, sizeof(struct rtattr *) * (max + 1)); + while (RTA_OK(rta, len)) { + type = rta->rta_type & ~flags; + if (type <= max && !tb[type]) + tb[type] = rta; + rta = RTA_NEXT(rta, len); + } +} + +static void print_info_msg(struct mptcp_info *info) +{ + printf("Token & Flags\n"); + printf("token: %x\n", info->mptcpi_token); + printf("flags: %x\n", info->mptcpi_flags); + printf("csum_enabled: %u\n", info->mptcpi_csum_enabled); + + printf("\nBasic Info\n"); + printf("subflows: %u\n", info->mptcpi_subflows); + printf("subflows_max: %u\n", info->mptcpi_subflows_max); + printf("subflows_total: %u\n", info->mptcpi_subflows_total); + printf("local_addr_used: %u\n", info->mptcpi_local_addr_used); + printf("local_addr_max: %u\n", info->mptcpi_local_addr_max); + printf("add_addr_signal: %u\n", info->mptcpi_add_addr_signal); + printf("add_addr_accepted: %u\n", info->mptcpi_add_addr_accepted); + printf("add_addr_signal_max: %u\n", info->mptcpi_add_addr_signal_max); + printf("add_addr_accepted_max: %u\n", info->mptcpi_add_addr_accepted_max); + + printf("\nTransmission Info\n"); + printf("write_seq: %llu\n", info->mptcpi_write_seq); + printf("snd_una: %llu\n", info->mptcpi_snd_una); + printf("rcv_nxt: %llu\n", info->mptcpi_rcv_nxt); + printf("last_data_sent: %u\n", info->mptcpi_last_data_sent); + printf("last_data_recv: %u\n", info->mptcpi_last_data_recv); + printf("last_ack_recv: %u\n", info->mptcpi_last_ack_recv); + printf("retransmits: %u\n", info->mptcpi_retransmits); + printf("retransmit bytes: %llu\n", info->mptcpi_bytes_retrans); + printf("bytes_sent: %llu\n", info->mptcpi_bytes_sent); + printf("bytes_received: %llu\n", info->mptcpi_bytes_received); + printf("bytes_acked: %llu\n", info->mptcpi_bytes_acked); +} + +static void parse_nlmsg(struct nlmsghdr *nlh) +{ + struct inet_diag_msg *r = NLMSG_DATA(nlh); + struct rtattr *tb[INET_DIAG_MAX + 1]; + + parse_rtattr_flags(tb, INET_DIAG_MAX, (struct rtattr *)(r + 1), + nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)), + NLA_F_NESTED); + + if (tb[INET_DIAG_INFO]) { + int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]); + struct mptcp_info *info; + + /* workaround fort older kernels with less fields */ + if (len < sizeof(*info)) { + info = alloca(sizeof(*info)); + memcpy(info, RTA_DATA(tb[INET_DIAG_INFO]), len); + memset((char *)info + len, 0, sizeof(*info) - len); + } else { + info = RTA_DATA(tb[INET_DIAG_INFO]); + } + print_info_msg(info); + } +} + +static void recv_nlmsg(int fd, struct nlmsghdr *nlh) +{ + char rcv_buff[8192]; + struct sockaddr_nl rcv_nladdr = { + .nl_family = AF_NETLINK + }; + struct iovec rcv_iov = { + .iov_base = rcv_buff, + .iov_len = sizeof(rcv_buff) + }; + struct msghdr rcv_msg = { + .msg_name = &rcv_nladdr, + .msg_namelen = sizeof(rcv_nladdr), + .msg_iov = &rcv_iov, + .msg_iovlen = 1 + }; + int len; + + len = recvmsg(fd, &rcv_msg, 0); + nlh = (struct nlmsghdr *)rcv_buff; + + while (NLMSG_OK(nlh, len)) { + if (nlh->nlmsg_type == NLMSG_DONE) { + printf("NLMSG_DONE\n"); + break; + } else if (nlh->nlmsg_type == NLMSG_ERROR) { + struct nlmsgerr *err; + + err = (struct nlmsgerr *)NLMSG_DATA(nlh); + printf("Error %d:%s\n", + -(err->error), strerror(-(err->error))); + break; + } + parse_nlmsg(nlh); + nlh = NLMSG_NEXT(nlh, len); + } +} + +static void get_mptcpinfo(__u32 token) +{ + struct nlmsghdr *nlh = NULL; + int fd; + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG); + if (fd < 0) + die_perror("Netlink socket"); + + send_query(fd, token); + recv_nlmsg(fd, nlh); + + close(fd); +} + +static void parse_opts(int argc, char **argv, __u32 *target_token) +{ + int c; + + if (argc < 2) + die_usage(1); + + while ((c = getopt(argc, argv, "ht:")) != -1) { + switch (c) { + case 'h': + die_usage(0); + break; + case 't': + sscanf(optarg, "%x", target_token); + break; + default: + die_usage(1); + break; + } + } +} + +int main(int argc, char *argv[]) +{ + __u32 target_token; + + parse_opts(argc, argv, &target_token); + get_mptcpinfo(target_token); + + return 0; +} + diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 9c2a415976cb..2329c2f8519b 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -28,7 +28,7 @@ size=0 usage() { echo "Usage: $0 [ -b ] [ -c ] [ -d ] [ -i]" - echo -e "\t-b: bail out after first error, otherwise runs al testcases" + echo -e "\t-b: bail out after first error, otherwise runs all testcases" echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" echo -e "\t-d: debug this script" echo -e "\t-i: use 'ip mptcp' instead of 'pm_nl_ctl'" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 3651f73451cf..333064b0b5ac 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -117,7 +117,36 @@ cleanup() trap cleanup EXIT # Create and configure network namespaces for testing +print_title "Init" mptcp_lib_ns_init ns1 ns2 + +# check path_manager and pm_type sysctl mapping +if [ -f /proc/sys/net/mptcp/path_manager ]; then + ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=userspace + pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)" + if [ "${pm_type}" != "1" ]; then + test_fail "unexpected pm_type: ${pm_type}" + mptcp_lib_result_print_all_tap + exit ${KSFT_FAIL} + fi + + ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=error 2>/dev/null + pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)" + if [ "${pm_type}" != "1" ]; then + test_fail "unexpected pm_type after error: ${pm_type}" + mptcp_lib_result_print_all_tap + exit ${KSFT_FAIL} + fi + + ip netns exec "$ns1" sysctl -q net.mptcp.pm_type=0 + pm_name="$(ip netns exec "$ns1" sysctl -n net.mptcp.path_manager)" + if [ "${pm_name}" != "kernel" ]; then + test_fail "unexpected path-manager: ${pm_name}" + mptcp_lib_result_print_all_tap + exit ${KSFT_FAIL} + fi +fi + for i in "$ns1" "$ns2" ;do ip netns exec "$i" sysctl -q net.mptcp.pm_type=1 done @@ -152,7 +181,6 @@ mptcp_lib_events "${ns1}" "${server_evts}" server_evts_pid sleep 0.5 mptcp_lib_subtests_last_ts_reset -print_title "Init" print_test "Created network namespaces ns1, ns2" test_pass diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh index 6974474c26f3..0be1905d1f2f 100755 --- a/tools/testing/selftests/net/netns-name.sh +++ b/tools/testing/selftests/net/netns-name.sh @@ -78,6 +78,16 @@ ip -netns $NS link show dev $ALT_NAME 2> /dev/null && fail "Can still find alt-name after move" ip -netns $test_ns link del $DEV || fail +# +# Test no conflict of the same name/ifindex in different netns +# +ip -netns $NS link add name $DEV index 100 type dummy || fail +ip -netns $NS link add netns $test_ns name $DEV index 100 type dummy || + fail "Can create in netns without moving" +ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found" +ip -netns $NS link del $DEV || fail +ip -netns $test_ns link del $DEV || fail + echo -ne "$(basename $0) \t\t\t\t" if [ $RET_CODE -eq 0 ]; then echo "[ OK ]" diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py index 93e8cb671c3d..beaee5e4e2aa 100755 --- a/tools/testing/selftests/net/nl_netdev.py +++ b/tools/testing/selftests/net/nl_netdev.py @@ -35,6 +35,21 @@ def napi_list_check(nf) -> None: comment=f"queue count after reset queue {q} mode {i}") +def nsim_rxq_reset_down(nf) -> None: + """ + Test that the queue API supports resetting a queue + while the interface is down. We should convert this + test to testing real HW once more devices support + queue API. + """ + with NetdevSimDev(queue_count=4) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} down") + for i in [0, 2, 3]: + nsim.dfs_write("queue_reset", f"1 {i}") + + def page_pool_check(nf) -> None: with NetdevSimDev() as nsimdev: nsim = nsimdev.nsims[0] @@ -106,7 +121,8 @@ def page_pool_check(nf) -> None: def main() -> None: nf = NetdevFamily() - ksft_run([empty_check, lo_check, page_pool_check, napi_list_check], + ksft_run([empty_check, lo_check, page_pool_check, napi_list_check, + nsim_rxq_reset_down], args=(nf, )) ksft_exit() diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 960e1ab4dd04..3c8d3455d8e7 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -330,6 +330,11 @@ test_psample() { # - drop packets and verify the right drop reason is reported test_drop_reason() { which perf >/dev/null 2>&1 || return $ksft_skip + which pahole >/dev/null 2>&1 || return $ksft_skip + + ovs_drop_subsys=$(pahole -C skb_drop_reason_subsys | + awk '/OPENVSWITCH/ { print $3; }' | + tr -d ,) sbx_add "test_drop_reason" || return $? @@ -373,7 +378,7 @@ test_drop_reason() { "in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20,proto=1),icmp()" 'drop' ovs_drop_record_and_run "test_drop_reason" ip netns exec client ping -c 2 172.31.110.20 - ovs_drop_reason_count 0x30001 # OVS_DROP_FLOW_ACTION + ovs_drop_reason_count 0x${ovs_drop_subsys}0001 # OVS_DROP_FLOW_ACTION if [[ "$?" -ne "2" ]]; then info "Did not detect expected drops: $?" return 1 @@ -390,7 +395,7 @@ test_drop_reason() { ovs_drop_record_and_run \ "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 6000 - ovs_drop_reason_count 0x30004 # OVS_DROP_EXPLICIT_ACTION_ERROR + ovs_drop_reason_count 0x${ovs_drop_subsys}0004 # OVS_DROP_EXPLICIT_ACTION_ERROR if [[ "$?" -ne "1" ]]; then info "Did not detect expected explicit error drops: $?" return 1 @@ -398,7 +403,7 @@ test_drop_reason() { ovs_drop_record_and_run \ "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 7000 - ovs_drop_reason_count 0x30003 # OVS_DROP_EXPLICIT_ACTION + ovs_drop_reason_count 0x${ovs_drop_subsys}0003 # OVS_DROP_EXPLICIT_ACTION if [[ "$?" -ne "1" ]]; then info "Did not detect expected explicit drops: $?" return 1 diff --git a/tools/testing/selftests/net/proc_net_pktgen.c b/tools/testing/selftests/net/proc_net_pktgen.c new file mode 100644 index 000000000000..69444fb29577 --- /dev/null +++ b/tools/testing/selftests/net/proc_net_pktgen.c @@ -0,0 +1,690 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * proc_net_pktgen: kselftest for /proc/net/pktgen interface + * + * Copyright (c) 2025 Peter Seiderer <ps.report@gmx.net> + * + */ +#include <errno.h> +#include <fcntl.h> +#include <stdlib.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +static const char ctrl_cmd_stop[] = "stop"; +static const char ctrl_cmd_start[] = "start"; +static const char ctrl_cmd_reset[] = "reset"; + +static const char wrong_ctrl_cmd[] = "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789"; + +static const char thr_cmd_add_loopback_0[] = "add_device lo@0"; +static const char thr_cmd_rm_loopback_0[] = "rem_device_all"; + +static const char wrong_thr_cmd[] = "forsureawrongcommand"; +static const char legacy_thr_cmd[] = "max_before_softirq"; + +static const char wrong_dev_cmd[] = "forsurewrongcommand"; +static const char dev_cmd_min_pkt_size_0[] = "min_pkt_size"; +static const char dev_cmd_min_pkt_size_1[] = "min_pkt_size "; +static const char dev_cmd_min_pkt_size_2[] = "min_pkt_size 0"; +static const char dev_cmd_min_pkt_size_3[] = "min_pkt_size 1"; +static const char dev_cmd_min_pkt_size_4[] = "min_pkt_size 100"; +static const char dev_cmd_min_pkt_size_5[] = "min_pkt_size=1001"; +static const char dev_cmd_min_pkt_size_6[] = "min_pkt_size =2002"; +static const char dev_cmd_min_pkt_size_7[] = "min_pkt_size= 3003"; +static const char dev_cmd_min_pkt_size_8[] = "min_pkt_size = 4004"; +static const char dev_cmd_max_pkt_size_0[] = "max_pkt_size 200"; +static const char dev_cmd_pkt_size_0[] = "pkt_size 300"; +static const char dev_cmd_imix_weights_0[] = "imix_weights 0,7 576,4 1500,1"; +static const char dev_cmd_imix_weights_1[] = "imix_weights 101,1 102,2 103,3 104,4 105,5 106,6 107,7 108,8 109,9 110,10 111,11 112,12 113,13 114,14 115,15 116,16 117,17 118,18 119,19 120,20"; +static const char dev_cmd_imix_weights_2[] = "imix_weights 100,1 102,2 103,3 104,4 105,5 106,6 107,7 108,8 109,9 110,10 111,11 112,12 113,13 114,14 115,15 116,16 117,17 118,18 119,19 120,20 121,21"; +static const char dev_cmd_imix_weights_3[] = "imix_weights"; +static const char dev_cmd_imix_weights_4[] = "imix_weights "; +static const char dev_cmd_imix_weights_5[] = "imix_weights 0"; +static const char dev_cmd_imix_weights_6[] = "imix_weights 0,"; +static const char dev_cmd_debug_0[] = "debug 1"; +static const char dev_cmd_debug_1[] = "debug 0"; +static const char dev_cmd_frags_0[] = "frags 100"; +static const char dev_cmd_delay_0[] = "delay 100"; +static const char dev_cmd_delay_1[] = "delay 2147483647"; +static const char dev_cmd_rate_0[] = "rate 0"; +static const char dev_cmd_rate_1[] = "rate 100"; +static const char dev_cmd_ratep_0[] = "ratep 0"; +static const char dev_cmd_ratep_1[] = "ratep 200"; +static const char dev_cmd_udp_src_min_0[] = "udp_src_min 1"; +static const char dev_cmd_udp_dst_min_0[] = "udp_dst_min 2"; +static const char dev_cmd_udp_src_max_0[] = "udp_src_max 3"; +static const char dev_cmd_udp_dst_max_0[] = "udp_dst_max 4"; +static const char dev_cmd_clone_skb_0[] = "clone_skb 1"; +static const char dev_cmd_clone_skb_1[] = "clone_skb 0"; +static const char dev_cmd_count_0[] = "count 100"; +static const char dev_cmd_src_mac_count_0[] = "src_mac_count 100"; +static const char dev_cmd_dst_mac_count_0[] = "dst_mac_count 100"; +static const char dev_cmd_burst_0[] = "burst 0"; +static const char dev_cmd_node_0[] = "node 100"; +static const char dev_cmd_xmit_mode_0[] = "xmit_mode start_xmit"; +static const char dev_cmd_xmit_mode_1[] = "xmit_mode netif_receive"; +static const char dev_cmd_xmit_mode_2[] = "xmit_mode queue_xmit"; +static const char dev_cmd_xmit_mode_3[] = "xmit_mode nonsense"; +static const char dev_cmd_flag_0[] = "flag UDPCSUM"; +static const char dev_cmd_flag_1[] = "flag !UDPCSUM"; +static const char dev_cmd_flag_2[] = "flag nonsense"; +static const char dev_cmd_dst_min_0[] = "dst_min 101.102.103.104"; +static const char dev_cmd_dst_0[] = "dst 101.102.103.104"; +static const char dev_cmd_dst_max_0[] = "dst_max 201.202.203.204"; +static const char dev_cmd_dst6_0[] = "dst6 2001:db38:1234:0000:0000:0000:0000:0000"; +static const char dev_cmd_dst6_min_0[] = "dst6_min 2001:db8:1234:0000:0000:0000:0000:0000"; +static const char dev_cmd_dst6_max_0[] = "dst6_max 2001:db8:1234:0000:0000:0000:0000:0000"; +static const char dev_cmd_src6_0[] = "src6 2001:db38:1234:0000:0000:0000:0000:0000"; +static const char dev_cmd_src_min_0[] = "src_min 101.102.103.104"; +static const char dev_cmd_src_max_0[] = "src_max 201.202.203.204"; +static const char dev_cmd_dst_mac_0[] = "dst_mac 01:02:03:04:05:06"; +static const char dev_cmd_src_mac_0[] = "src_mac 11:12:13:14:15:16"; +static const char dev_cmd_clear_counters_0[] = "clear_counters"; +static const char dev_cmd_flows_0[] = "flows 100"; +static const char dev_cmd_spi_0[] = "spi 100"; +static const char dev_cmd_flowlen_0[] = "flowlen 100"; +static const char dev_cmd_queue_map_min_0[] = "queue_map_min 1"; +static const char dev_cmd_queue_map_max_0[] = "queue_map_max 2"; +static const char dev_cmd_mpls_0[] = "mpls 00000001"; +static const char dev_cmd_mpls_1[] = "mpls 00000001,000000f2"; +static const char dev_cmd_mpls_2[] = "mpls 00000f00,00000f01,00000f02,00000f03,00000f04,00000f05,00000f06,00000f07,00000f08,00000f09,00000f0a,00000f0b,00000f0c,00000f0d,00000f0e,00000f0f"; +static const char dev_cmd_mpls_3[] = "mpls 00000f00,00000f01,00000f02,00000f03,00000f04,00000f05,00000f06,00000f07,00000f08,00000f09,00000f0a,00000f0b,00000f0c,00000f0d,00000f0e,00000f0f,00000f10"; +static const char dev_cmd_vlan_id_0[] = "vlan_id 1"; +static const char dev_cmd_vlan_p_0[] = "vlan_p 1"; +static const char dev_cmd_vlan_cfi_0[] = "vlan_cfi 1"; +static const char dev_cmd_vlan_id_1[] = "vlan_id 4096"; +static const char dev_cmd_svlan_id_0[] = "svlan_id 1"; +static const char dev_cmd_svlan_p_0[] = "svlan_p 1"; +static const char dev_cmd_svlan_cfi_0[] = "svlan_cfi 1"; +static const char dev_cmd_svlan_id_1[] = "svlan_id 4096"; +static const char dev_cmd_tos_0[] = "tos 0"; +static const char dev_cmd_tos_1[] = "tos 0f"; +static const char dev_cmd_tos_2[] = "tos 0ff"; +static const char dev_cmd_traffic_class_0[] = "traffic_class f0"; +static const char dev_cmd_skb_priority_0[] = "skb_priority 999"; + +FIXTURE(proc_net_pktgen) { + int ctrl_fd; + int thr_fd; + int dev_fd; +}; + +FIXTURE_SETUP(proc_net_pktgen) { + int r; + ssize_t len; + + r = system("modprobe pktgen"); + ASSERT_EQ(r, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?"); + + self->ctrl_fd = open("/proc/net/pktgen/pgctrl", O_RDWR); + ASSERT_GE(self->ctrl_fd, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?"); + + self->thr_fd = open("/proc/net/pktgen/kpktgend_0", O_RDWR); + ASSERT_GE(self->thr_fd, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?"); + + len = write(self->thr_fd, thr_cmd_add_loopback_0, sizeof(thr_cmd_add_loopback_0)); + ASSERT_EQ(len, sizeof(thr_cmd_add_loopback_0)) TH_LOG("device lo@0 already registered?"); + + self->dev_fd = open("/proc/net/pktgen/lo@0", O_RDWR); + ASSERT_GE(self->dev_fd, 0) TH_LOG("device entry for lo@0 missing?"); +} + +FIXTURE_TEARDOWN(proc_net_pktgen) { + int ret; + ssize_t len; + + ret = close(self->dev_fd); + EXPECT_EQ(ret, 0); + + len = write(self->thr_fd, thr_cmd_rm_loopback_0, sizeof(thr_cmd_rm_loopback_0)); + EXPECT_EQ(len, sizeof(thr_cmd_rm_loopback_0)); + + ret = close(self->thr_fd); + EXPECT_EQ(ret, 0); + + ret = close(self->ctrl_fd); + EXPECT_EQ(ret, 0); +} + +TEST_F(proc_net_pktgen, wrong_ctrl_cmd) { + for (int i = 0; i <= sizeof(wrong_ctrl_cmd); i++) { + ssize_t len; + + len = write(self->ctrl_fd, wrong_ctrl_cmd, i); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + } +} + +TEST_F(proc_net_pktgen, ctrl_cmd) { + ssize_t len; + + len = write(self->ctrl_fd, ctrl_cmd_stop, sizeof(ctrl_cmd_stop)); + EXPECT_EQ(len, sizeof(ctrl_cmd_stop)); + + len = write(self->ctrl_fd, ctrl_cmd_stop, sizeof(ctrl_cmd_stop) - 1); + EXPECT_EQ(len, sizeof(ctrl_cmd_stop) - 1); + + len = write(self->ctrl_fd, ctrl_cmd_start, sizeof(ctrl_cmd_start)); + EXPECT_EQ(len, sizeof(ctrl_cmd_start)); + + len = write(self->ctrl_fd, ctrl_cmd_start, sizeof(ctrl_cmd_start) - 1); + EXPECT_EQ(len, sizeof(ctrl_cmd_start) - 1); + + len = write(self->ctrl_fd, ctrl_cmd_reset, sizeof(ctrl_cmd_reset)); + EXPECT_EQ(len, sizeof(ctrl_cmd_reset)); + + len = write(self->ctrl_fd, ctrl_cmd_reset, sizeof(ctrl_cmd_reset) - 1); + EXPECT_EQ(len, sizeof(ctrl_cmd_reset) - 1); +} + +TEST_F(proc_net_pktgen, wrong_thr_cmd) { + for (int i = 0; i <= sizeof(wrong_thr_cmd); i++) { + ssize_t len; + + len = write(self->thr_fd, wrong_thr_cmd, i); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + } +} + +TEST_F(proc_net_pktgen, legacy_thr_cmd) { + for (int i = 0; i <= sizeof(legacy_thr_cmd); i++) { + ssize_t len; + + len = write(self->thr_fd, legacy_thr_cmd, i); + if (i < (sizeof(legacy_thr_cmd) - 1)) { + /* incomplete command string */ + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + } else { + /* complete command string without/with trailing '\0' */ + EXPECT_EQ(len, i); + } + } +} + +TEST_F(proc_net_pktgen, wrong_dev_cmd) { + for (int i = 0; i <= sizeof(wrong_dev_cmd); i++) { + ssize_t len; + + len = write(self->dev_fd, wrong_dev_cmd, i); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + } +} + +TEST_F(proc_net_pktgen, dev_cmd_min_pkt_size) { + ssize_t len; + + /* with trailing '\0' */ + len = write(self->dev_fd, dev_cmd_min_pkt_size_0, sizeof(dev_cmd_min_pkt_size_0)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_0)); + + /* without trailing '\0' */ + len = write(self->dev_fd, dev_cmd_min_pkt_size_0, sizeof(dev_cmd_min_pkt_size_0) - 1); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_0) - 1); + + /* with trailing '\0' */ + len = write(self->dev_fd, dev_cmd_min_pkt_size_1, sizeof(dev_cmd_min_pkt_size_1)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_1)); + + /* without trailing '\0' */ + len = write(self->dev_fd, dev_cmd_min_pkt_size_1, sizeof(dev_cmd_min_pkt_size_1) - 1); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_1) - 1); + + /* with trailing '\0' */ + len = write(self->dev_fd, dev_cmd_min_pkt_size_2, sizeof(dev_cmd_min_pkt_size_2)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_2)); + + /* without trailing '\0' */ + len = write(self->dev_fd, dev_cmd_min_pkt_size_2, sizeof(dev_cmd_min_pkt_size_2) - 1); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_2) - 1); + + len = write(self->dev_fd, dev_cmd_min_pkt_size_3, sizeof(dev_cmd_min_pkt_size_3)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_3)); + + len = write(self->dev_fd, dev_cmd_min_pkt_size_4, sizeof(dev_cmd_min_pkt_size_4)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_4)); + + len = write(self->dev_fd, dev_cmd_min_pkt_size_5, sizeof(dev_cmd_min_pkt_size_5)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_5)); + + len = write(self->dev_fd, dev_cmd_min_pkt_size_6, sizeof(dev_cmd_min_pkt_size_6)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_6)); + + len = write(self->dev_fd, dev_cmd_min_pkt_size_7, sizeof(dev_cmd_min_pkt_size_7)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_7)); + + len = write(self->dev_fd, dev_cmd_min_pkt_size_8, sizeof(dev_cmd_min_pkt_size_8)); + EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_8)); +} + +TEST_F(proc_net_pktgen, dev_cmd_max_pkt_size) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_max_pkt_size_0, sizeof(dev_cmd_max_pkt_size_0)); + EXPECT_EQ(len, sizeof(dev_cmd_max_pkt_size_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_pkt_size) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_pkt_size_0, sizeof(dev_cmd_pkt_size_0)); + EXPECT_EQ(len, sizeof(dev_cmd_pkt_size_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_imix_weights) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_imix_weights_0, sizeof(dev_cmd_imix_weights_0)); + EXPECT_EQ(len, sizeof(dev_cmd_imix_weights_0)); + + len = write(self->dev_fd, dev_cmd_imix_weights_1, sizeof(dev_cmd_imix_weights_1)); + EXPECT_EQ(len, sizeof(dev_cmd_imix_weights_1)); + + len = write(self->dev_fd, dev_cmd_imix_weights_2, sizeof(dev_cmd_imix_weights_2)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, E2BIG); + + /* with trailing '\0' */ + len = write(self->dev_fd, dev_cmd_imix_weights_3, sizeof(dev_cmd_imix_weights_3)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + /* without trailing '\0' */ + len = write(self->dev_fd, dev_cmd_imix_weights_3, sizeof(dev_cmd_imix_weights_3) - 1); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + /* with trailing '\0' */ + len = write(self->dev_fd, dev_cmd_imix_weights_4, sizeof(dev_cmd_imix_weights_4)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + /* without trailing '\0' */ + len = write(self->dev_fd, dev_cmd_imix_weights_4, sizeof(dev_cmd_imix_weights_4) - 1); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + /* with trailing '\0' */ + len = write(self->dev_fd, dev_cmd_imix_weights_5, sizeof(dev_cmd_imix_weights_5)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + /* without trailing '\0' */ + len = write(self->dev_fd, dev_cmd_imix_weights_5, sizeof(dev_cmd_imix_weights_5) - 1); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + /* with trailing '\0' */ + len = write(self->dev_fd, dev_cmd_imix_weights_6, sizeof(dev_cmd_imix_weights_6)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + /* without trailing '\0' */ + len = write(self->dev_fd, dev_cmd_imix_weights_6, sizeof(dev_cmd_imix_weights_6) - 1); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); +} + +TEST_F(proc_net_pktgen, dev_cmd_debug) { + ssize_t len; + + /* debug on */ + len = write(self->dev_fd, dev_cmd_debug_0, sizeof(dev_cmd_debug_0)); + EXPECT_EQ(len, sizeof(dev_cmd_debug_0)); + + /* debug off */ + len = write(self->dev_fd, dev_cmd_debug_1, sizeof(dev_cmd_debug_1)); + EXPECT_EQ(len, sizeof(dev_cmd_debug_1)); +} + +TEST_F(proc_net_pktgen, dev_cmd_frags) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_frags_0, sizeof(dev_cmd_frags_0)); + EXPECT_EQ(len, sizeof(dev_cmd_frags_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_delay) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_delay_0, sizeof(dev_cmd_delay_0)); + EXPECT_EQ(len, sizeof(dev_cmd_delay_0)); + + len = write(self->dev_fd, dev_cmd_delay_1, sizeof(dev_cmd_delay_1)); + EXPECT_EQ(len, sizeof(dev_cmd_delay_1)); +} + +TEST_F(proc_net_pktgen, dev_cmd_rate) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_rate_0, sizeof(dev_cmd_rate_0)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + len = write(self->dev_fd, dev_cmd_rate_1, sizeof(dev_cmd_rate_1)); + EXPECT_EQ(len, sizeof(dev_cmd_rate_1)); +} + +TEST_F(proc_net_pktgen, dev_cmd_ratep) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_ratep_0, sizeof(dev_cmd_ratep_0)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EINVAL); + + len = write(self->dev_fd, dev_cmd_ratep_1, sizeof(dev_cmd_ratep_1)); + EXPECT_EQ(len, sizeof(dev_cmd_ratep_1)); +} + +TEST_F(proc_net_pktgen, dev_cmd_udp_src_min) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_udp_src_min_0, sizeof(dev_cmd_udp_src_min_0)); + EXPECT_EQ(len, sizeof(dev_cmd_udp_src_min_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_udp_dst_min) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_udp_dst_min_0, sizeof(dev_cmd_udp_dst_min_0)); + EXPECT_EQ(len, sizeof(dev_cmd_udp_dst_min_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_udp_src_max) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_udp_src_max_0, sizeof(dev_cmd_udp_src_max_0)); + EXPECT_EQ(len, sizeof(dev_cmd_udp_src_max_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_udp_dst_max) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_udp_dst_max_0, sizeof(dev_cmd_udp_dst_max_0)); + EXPECT_EQ(len, sizeof(dev_cmd_udp_dst_max_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_clone_skb) { + ssize_t len; + + /* clone_skb on (gives EOPNOTSUPP on lo device) */ + len = write(self->dev_fd, dev_cmd_clone_skb_0, sizeof(dev_cmd_clone_skb_0)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, EOPNOTSUPP); + + /* clone_skb off */ + len = write(self->dev_fd, dev_cmd_clone_skb_1, sizeof(dev_cmd_clone_skb_1)); + EXPECT_EQ(len, sizeof(dev_cmd_clone_skb_1)); +} + +TEST_F(proc_net_pktgen, dev_cmd_count) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_count_0, sizeof(dev_cmd_count_0)); + EXPECT_EQ(len, sizeof(dev_cmd_count_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_src_mac_count) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_src_mac_count_0, sizeof(dev_cmd_src_mac_count_0)); + EXPECT_EQ(len, sizeof(dev_cmd_src_mac_count_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_dst_mac_count) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_dst_mac_count_0, sizeof(dev_cmd_dst_mac_count_0)); + EXPECT_EQ(len, sizeof(dev_cmd_dst_mac_count_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_burst) { + ssize_t len; + + /* burst off */ + len = write(self->dev_fd, dev_cmd_burst_0, sizeof(dev_cmd_burst_0)); + EXPECT_EQ(len, sizeof(dev_cmd_burst_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_node) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_node_0, sizeof(dev_cmd_node_0)); + EXPECT_EQ(len, sizeof(dev_cmd_node_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_xmit_mode) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_xmit_mode_0, sizeof(dev_cmd_xmit_mode_0)); + EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_0)); + + len = write(self->dev_fd, dev_cmd_xmit_mode_1, sizeof(dev_cmd_xmit_mode_1)); + EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_1)); + + len = write(self->dev_fd, dev_cmd_xmit_mode_2, sizeof(dev_cmd_xmit_mode_2)); + EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_2)); + + len = write(self->dev_fd, dev_cmd_xmit_mode_3, sizeof(dev_cmd_xmit_mode_3)); + EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_3)); +} + +TEST_F(proc_net_pktgen, dev_cmd_flag) { + ssize_t len; + + /* flag UDPCSUM on */ + len = write(self->dev_fd, dev_cmd_flag_0, sizeof(dev_cmd_flag_0)); + EXPECT_EQ(len, sizeof(dev_cmd_flag_0)); + + /* flag UDPCSUM off */ + len = write(self->dev_fd, dev_cmd_flag_1, sizeof(dev_cmd_flag_1)); + EXPECT_EQ(len, sizeof(dev_cmd_flag_1)); + + /* flag invalid */ + len = write(self->dev_fd, dev_cmd_flag_2, sizeof(dev_cmd_flag_2)); + EXPECT_EQ(len, sizeof(dev_cmd_flag_2)); +} + +TEST_F(proc_net_pktgen, dev_cmd_dst_min) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_dst_min_0, sizeof(dev_cmd_dst_min_0)); + EXPECT_EQ(len, sizeof(dev_cmd_dst_min_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_dst) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_dst_0, sizeof(dev_cmd_dst_0)); + EXPECT_EQ(len, sizeof(dev_cmd_dst_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_dst_max) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_dst_max_0, sizeof(dev_cmd_dst_max_0)); + EXPECT_EQ(len, sizeof(dev_cmd_dst_max_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_dst6) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_dst6_0, sizeof(dev_cmd_dst6_0)); + EXPECT_EQ(len, sizeof(dev_cmd_dst6_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_dst6_min) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_dst6_min_0, sizeof(dev_cmd_dst6_min_0)); + EXPECT_EQ(len, sizeof(dev_cmd_dst6_min_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_dst6_max) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_dst6_max_0, sizeof(dev_cmd_dst6_max_0)); + EXPECT_EQ(len, sizeof(dev_cmd_dst6_max_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_src6) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_src6_0, sizeof(dev_cmd_src6_0)); + EXPECT_EQ(len, sizeof(dev_cmd_src6_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_src_min) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_src_min_0, sizeof(dev_cmd_src_min_0)); + EXPECT_EQ(len, sizeof(dev_cmd_src_min_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_src_max) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_src_max_0, sizeof(dev_cmd_src_max_0)); + EXPECT_EQ(len, sizeof(dev_cmd_src_max_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_dst_mac) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_dst_mac_0, sizeof(dev_cmd_dst_mac_0)); + EXPECT_EQ(len, sizeof(dev_cmd_dst_mac_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_src_mac) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_src_mac_0, sizeof(dev_cmd_src_mac_0)); + EXPECT_EQ(len, sizeof(dev_cmd_src_mac_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_clear_counters) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_clear_counters_0, sizeof(dev_cmd_clear_counters_0)); + EXPECT_EQ(len, sizeof(dev_cmd_clear_counters_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_flows) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_flows_0, sizeof(dev_cmd_flows_0)); + EXPECT_EQ(len, sizeof(dev_cmd_flows_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_spi) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_spi_0, sizeof(dev_cmd_spi_0)); + EXPECT_EQ(len, sizeof(dev_cmd_spi_0)) TH_LOG("CONFIG_XFRM not enabled?"); +} + +TEST_F(proc_net_pktgen, dev_cmd_flowlen) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_flowlen_0, sizeof(dev_cmd_flowlen_0)); + EXPECT_EQ(len, sizeof(dev_cmd_flowlen_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_queue_map_min) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_queue_map_min_0, sizeof(dev_cmd_queue_map_min_0)); + EXPECT_EQ(len, sizeof(dev_cmd_queue_map_min_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_queue_map_max) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_queue_map_max_0, sizeof(dev_cmd_queue_map_max_0)); + EXPECT_EQ(len, sizeof(dev_cmd_queue_map_max_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_mpls) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_mpls_0, sizeof(dev_cmd_mpls_0)); + EXPECT_EQ(len, sizeof(dev_cmd_mpls_0)); + + len = write(self->dev_fd, dev_cmd_mpls_1, sizeof(dev_cmd_mpls_1)); + EXPECT_EQ(len, sizeof(dev_cmd_mpls_1)); + + len = write(self->dev_fd, dev_cmd_mpls_2, sizeof(dev_cmd_mpls_2)); + EXPECT_EQ(len, sizeof(dev_cmd_mpls_2)); + + len = write(self->dev_fd, dev_cmd_mpls_3, sizeof(dev_cmd_mpls_3)); + EXPECT_EQ(len, -1); + EXPECT_EQ(errno, E2BIG); +} + +TEST_F(proc_net_pktgen, dev_cmd_vlan_id) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_vlan_id_0, sizeof(dev_cmd_vlan_id_0)); + EXPECT_EQ(len, sizeof(dev_cmd_vlan_id_0)); + + len = write(self->dev_fd, dev_cmd_vlan_p_0, sizeof(dev_cmd_vlan_p_0)); + EXPECT_EQ(len, sizeof(dev_cmd_vlan_p_0)); + + len = write(self->dev_fd, dev_cmd_vlan_cfi_0, sizeof(dev_cmd_vlan_cfi_0)); + EXPECT_EQ(len, sizeof(dev_cmd_vlan_cfi_0)); + + len = write(self->dev_fd, dev_cmd_vlan_id_1, sizeof(dev_cmd_vlan_id_1)); + EXPECT_EQ(len, sizeof(dev_cmd_vlan_id_1)); +} + +TEST_F(proc_net_pktgen, dev_cmd_svlan_id) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_svlan_id_0, sizeof(dev_cmd_svlan_id_0)); + EXPECT_EQ(len, sizeof(dev_cmd_svlan_id_0)); + + len = write(self->dev_fd, dev_cmd_svlan_p_0, sizeof(dev_cmd_svlan_p_0)); + EXPECT_EQ(len, sizeof(dev_cmd_svlan_p_0)); + + len = write(self->dev_fd, dev_cmd_svlan_cfi_0, sizeof(dev_cmd_svlan_cfi_0)); + EXPECT_EQ(len, sizeof(dev_cmd_svlan_cfi_0)); + + len = write(self->dev_fd, dev_cmd_svlan_id_1, sizeof(dev_cmd_svlan_id_1)); + EXPECT_EQ(len, sizeof(dev_cmd_svlan_id_1)); +} + + +TEST_F(proc_net_pktgen, dev_cmd_tos) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_tos_0, sizeof(dev_cmd_tos_0)); + EXPECT_EQ(len, sizeof(dev_cmd_tos_0)); + + len = write(self->dev_fd, dev_cmd_tos_1, sizeof(dev_cmd_tos_1)); + EXPECT_EQ(len, sizeof(dev_cmd_tos_1)); + + len = write(self->dev_fd, dev_cmd_tos_2, sizeof(dev_cmd_tos_2)); + EXPECT_EQ(len, sizeof(dev_cmd_tos_2)); +} + + +TEST_F(proc_net_pktgen, dev_cmd_traffic_class) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_traffic_class_0, sizeof(dev_cmd_traffic_class_0)); + EXPECT_EQ(len, sizeof(dev_cmd_traffic_class_0)); +} + +TEST_F(proc_net_pktgen, dev_cmd_skb_priority) { + ssize_t len; + + len = write(self->dev_fd, dev_cmd_skb_priority_0, sizeof(dev_cmd_skb_priority_0)); + EXPECT_EQ(len, sizeof(dev_cmd_skb_priority_0)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c index 404a2ce759ab..221270cee3ea 100644 --- a/tools/testing/selftests/net/psock_tpacket.c +++ b/tools/testing/selftests/net/psock_tpacket.c @@ -12,7 +12,7 @@ * * Datapath: * Open a pair of packet sockets and send resp. receive an a priori known - * packet pattern accross the sockets and check if it was received resp. + * packet pattern across the sockets and check if it was received resp. * sent correctly. Fanout in combination with RX_RING is currently not * tested here. * diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c index 066efd30e294..7b9bf8a7bbe1 100644 --- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c +++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c @@ -112,7 +112,7 @@ TEST(reuseaddr_ports_exhausted_reusable_same_euid) ASSERT_NE(-1, fd[0]) TH_LOG("failed to bind."); if (opts->reuseport[0] && opts->reuseport[1]) { - EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets succeed to be listened."); + EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets successfully listened."); } else { EXPECT_NE(-1, fd[1]) TH_LOG("should succeed to bind to connect to different destinations."); } diff --git a/tools/testing/selftests/net/rtnetlink.py b/tools/testing/selftests/net/rtnetlink.py new file mode 100755 index 000000000000..80950888800b --- /dev/null +++ b/tools/testing/selftests/net/rtnetlink.py @@ -0,0 +1,30 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +from lib.py import ksft_exit, ksft_run, ksft_ge, RtnlAddrFamily +import socket + +IPV4_ALL_HOSTS_MULTICAST = b'\xe0\x00\x00\x01' + +def dump_mcaddr_check(rtnl: RtnlAddrFamily) -> None: + """ + Verify that at least one interface has the IPv4 all-hosts multicast address. + At least the loopback interface should have this address. + """ + + addresses = rtnl.getmaddrs({"ifa-family": socket.AF_INET}, dump=True) + + all_host_multicasts = [ + addr for addr in addresses if addr['ifa-multicast'] == IPV4_ALL_HOSTS_MULTICAST + ] + + ksft_ge(len(all_host_multicasts), 1, + "No interface found with the IPv4 all-hosts multicast address") + +def main() -> None: + rtnl = RtnlAddrFamily() + ksft_run([dump_mcaddr_check], args=(rtnl, )) + ksft_exit() + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh index 1f78a87f6f37..152bf4c65747 100644 --- a/tools/testing/selftests/net/setup_veth.sh +++ b/tools/testing/selftests/net/setup_veth.sh @@ -11,7 +11,8 @@ setup_veth_ns() { local -r ns_mac="$4" [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + echo 200000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + echo 1 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs" ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 ip -netns "${ns_name}" link set dev "${ns_dev}" up diff --git a/tools/testing/selftests/net/so_rcv_listener.c b/tools/testing/selftests/net/so_rcv_listener.c new file mode 100644 index 000000000000..bc5841192aa6 --- /dev/null +++ b/tools/testing/selftests/net/so_rcv_listener.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <errno.h> +#include <netdb.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <linux/types.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <arpa/inet.h> + +#ifndef SO_RCVPRIORITY +#define SO_RCVPRIORITY 82 +#endif + +struct options { + __u32 val; + int name; + int rcvname; + const char *host; + const char *service; +} opt; + +static void __attribute__((noreturn)) usage(const char *bin) +{ + printf("Usage: %s [opts] <dst host> <dst port / service>\n", bin); + printf("Options:\n" + "\t\t-M val Test SO_RCVMARK\n" + "\t\t-P val Test SO_RCVPRIORITY\n" + ""); + exit(EXIT_FAILURE); +} + +static void parse_args(int argc, char *argv[]) +{ + int o; + + while ((o = getopt(argc, argv, "M:P:")) != -1) { + switch (o) { + case 'M': + opt.val = atoi(optarg); + opt.name = SO_MARK; + opt.rcvname = SO_RCVMARK; + break; + case 'P': + opt.val = atoi(optarg); + opt.name = SO_PRIORITY; + opt.rcvname = SO_RCVPRIORITY; + break; + default: + usage(argv[0]); + break; + } + } + + if (optind != argc - 2) + usage(argv[0]); + + opt.host = argv[optind]; + opt.service = argv[optind + 1]; +} + +int main(int argc, char *argv[]) +{ + int err = 0; + int recv_fd = -1; + int ret_value = 0; + __u32 recv_val; + struct cmsghdr *cmsg; + char cbuf[CMSG_SPACE(sizeof(__u32))]; + char recv_buf[CMSG_SPACE(sizeof(__u32))]; + struct iovec iov[1]; + struct msghdr msg; + struct sockaddr_in recv_addr4; + struct sockaddr_in6 recv_addr6; + + parse_args(argc, argv); + + int family = strchr(opt.host, ':') ? AF_INET6 : AF_INET; + + recv_fd = socket(family, SOCK_DGRAM, IPPROTO_UDP); + if (recv_fd < 0) { + perror("Can't open recv socket"); + ret_value = -errno; + goto cleanup; + } + + err = setsockopt(recv_fd, SOL_SOCKET, opt.rcvname, &opt.val, sizeof(opt.val)); + if (err < 0) { + perror("Recv setsockopt error"); + ret_value = -errno; + goto cleanup; + } + + if (family == AF_INET) { + memset(&recv_addr4, 0, sizeof(recv_addr4)); + recv_addr4.sin_family = family; + recv_addr4.sin_port = htons(atoi(opt.service)); + + if (inet_pton(family, opt.host, &recv_addr4.sin_addr) <= 0) { + perror("Invalid IPV4 address"); + ret_value = -errno; + goto cleanup; + } + + err = bind(recv_fd, (struct sockaddr *)&recv_addr4, sizeof(recv_addr4)); + } else { + memset(&recv_addr6, 0, sizeof(recv_addr6)); + recv_addr6.sin6_family = family; + recv_addr6.sin6_port = htons(atoi(opt.service)); + + if (inet_pton(family, opt.host, &recv_addr6.sin6_addr) <= 0) { + perror("Invalid IPV6 address"); + ret_value = -errno; + goto cleanup; + } + + err = bind(recv_fd, (struct sockaddr *)&recv_addr6, sizeof(recv_addr6)); + } + + if (err < 0) { + perror("Recv bind error"); + ret_value = -errno; + goto cleanup; + } + + iov[0].iov_base = recv_buf; + iov[0].iov_len = sizeof(recv_buf); + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = iov; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + + err = recvmsg(recv_fd, &msg, 0); + if (err < 0) { + perror("Message receive error"); + ret_value = -errno; + goto cleanup; + } + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == opt.name) { + recv_val = *(__u32 *)CMSG_DATA(cmsg); + printf("Received value: %u\n", recv_val); + + if (recv_val != opt.val) { + fprintf(stderr, "Error: expected value: %u, got: %u\n", + opt.val, recv_val); + ret_value = -EINVAL; + } + goto cleanup; + } + } + + fprintf(stderr, "Error: No matching cmsg received\n"); + ret_value = -ENOMSG; + +cleanup: + if (recv_fd >= 0) + close(recv_fd); + + return ret_value; +} diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c index d418162d335f..93b61e9a36f1 100644 --- a/tools/testing/selftests/net/tcp_ao/connect-deny.c +++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c @@ -4,6 +4,7 @@ #include "aolib.h" #define fault(type) (inj == FAULT_ ## type) +static volatile int sk_pair; static inline int test_add_key_maclen(int sk, const char *key, uint8_t maclen, union tcp_addr in_addr, uint8_t prefix, @@ -34,10 +35,10 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd, const char *cnt_name, test_cnt cnt_expected, fault_t inj) { - struct tcp_ao_counters ao_cnt1, ao_cnt2; + struct tcp_counters cnt1, cnt2; uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */ + test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected; int lsk, err, sk = 0; - time_t timeout; lsk = test_listen_socket(this_ip_addr, port, 1); @@ -46,21 +47,24 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd, if (cnt_name) before_cnt = netstat_get_one(cnt_name, NULL); - if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt1)) - test_error("test_get_tcp_ao_counters()"); + if (pwd && test_get_tcp_counters(lsk, &cnt1)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* preparations done */ - timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; - err = test_wait_fd(lsk, timeout, 0); + err = test_skpair_wait_poll(lsk, 0, poll_cnt, &sk_pair); if (err == -ETIMEDOUT) { + sk_pair = err; if (!fault(TIMEOUT)) - test_fail("timed out for accept()"); + test_fail("%s: timed out for accept()", tst_name); + } else if (err == -EKEYREJECTED) { + if (!fault(KEYREJECT)) + test_fail("%s: key was rejected", tst_name); } else if (err < 0) { - test_error("test_wait_fd()"); + test_error("test_skpair_wait_poll()"); } else { if (fault(TIMEOUT)) - test_fail("ready to accept"); + test_fail("%s: ready to accept", tst_name); sk = accept(lsk, NULL, NULL); if (sk < 0) { @@ -72,13 +76,13 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd, } synchronize_threads(); /* before counter checks */ - if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt2)) - test_error("test_get_tcp_ao_counters()"); + if (pwd && test_get_tcp_counters(lsk, &cnt2)) + test_error("test_get_tcp_counters()"); close(lsk); if (pwd) - test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected); + test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected); if (!cnt_name) goto out; @@ -109,7 +113,7 @@ static void *server_fn(void *arg) try_accept("Non-AO server + AO client", port++, NULL, this_ip_dest, -1, 100, 100, 0, - "TCPAOKeyNotFound", 0, FAULT_TIMEOUT); + "TCPAOKeyNotFound", TEST_CNT_NS_KEY_NOT_FOUND, FAULT_TIMEOUT); try_accept("AO server + Non-AO client", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100, 0, @@ -135,8 +139,9 @@ static void *server_fn(void *arg) wrong_addr, -1, 100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND, FAULT_TIMEOUT); + /* Key rejected by the other side, failing short through skpair */ try_accept("Client: Wrong addr", port++, NULL, - this_ip_dest, -1, 100, 100, 0, NULL, 0, FAULT_TIMEOUT); + this_ip_dest, -1, 100, 100, 0, NULL, 0, FAULT_KEYREJECT); try_accept("rcv id != snd id", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 200, 100, 0, @@ -163,8 +168,7 @@ static void try_connect(const char *tst_name, unsigned int port, uint8_t sndid, uint8_t rcvid, test_cnt cnt_expected, fault_t inj) { - struct tcp_ao_counters ao_cnt1, ao_cnt2; - time_t timeout; + struct tcp_counters cnt1, cnt2; int sk, ret; sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP); @@ -174,16 +178,15 @@ static void try_connect(const char *tst_name, unsigned int port, if (pwd && test_add_key(sk, pwd, addr, prefix, sndid, rcvid)) test_error("setsockopt(TCP_AO_ADD_KEY)"); - if (pwd && test_get_tcp_ao_counters(sk, &ao_cnt1)) - test_error("test_get_tcp_ao_counters()"); + if (pwd && test_get_tcp_counters(sk, &cnt1)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* preparations done */ - timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; - ret = _test_connect_socket(sk, this_ip_dest, port, timeout); - + ret = test_skpair_connect_poll(sk, this_ip_dest, port, cnt_expected, &sk_pair); synchronize_threads(); /* before counter checks */ if (ret < 0) { + sk_pair = ret; if (fault(KEYREJECT) && ret == -EKEYREJECTED) { test_ok("%s: connect() was prevented", tst_name); } else if (ret == -ETIMEDOUT && fault(TIMEOUT)) { @@ -202,9 +205,11 @@ static void try_connect(const char *tst_name, unsigned int port, else test_ok("%s: connected", tst_name); if (pwd && ret > 0) { - if (test_get_tcp_ao_counters(sk, &ao_cnt2)) - test_error("test_get_tcp_ao_counters()"); - test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected); + if (test_get_tcp_counters(sk, &cnt2)) + test_error("test_get_tcp_counters()"); + test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected); + } else if (pwd) { + test_tcp_counters_free(&cnt1); } out: synchronize_threads(); /* close() */ @@ -241,6 +246,11 @@ static void *client_fn(void *arg) try_connect("Wrong rcv id", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT); + /* + * XXX: The test doesn't increase any counters, see tcp_make_synack(). + * Potentially, it can be speed up by setting sk_pair = -ETIMEDOUT + * but the price would be increased complexity of the tracer thread. + */ trace_ao_event_sk_expect(TCP_AO_SYNACK_NO_KEY, this_ip_dest, addr_any, port, 0, 100, 100); try_connect("Wrong snd id", port++, DEFAULT_TEST_PASSWORD, diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c index f1d8d29e393f..340f00e979ea 100644 --- a/tools/testing/selftests/net/tcp_ao/connect.c +++ b/tools/testing/selftests/net/tcp_ao/connect.c @@ -35,7 +35,7 @@ static void *client_fn(void *arg) uint64_t before_aogood, after_aogood; const size_t nr_packets = 20; struct netstat *ns_before, *ns_after; - struct tcp_ao_counters ao1, ao2; + struct tcp_counters ao1, ao2; if (sk < 0) test_error("socket()"); @@ -50,18 +50,18 @@ static void *client_fn(void *arg) ns_before = netstat_read(); before_aogood = netstat_get(ns_before, "TCPAOGood", NULL); - if (test_get_tcp_ao_counters(sk, &ao1)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &ao1)) + test_error("test_get_tcp_counters()"); - if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) { + if (test_client_verify(sk, 100, nr_packets)) { test_fail("verify failed"); return NULL; } ns_after = netstat_read(); after_aogood = netstat_get(ns_after, "TCPAOGood", NULL); - if (test_get_tcp_ao_counters(sk, &ao2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &ao2)) + test_error("test_get_tcp_counters()"); netstat_print_diff(ns_before, ns_after); netstat_free(ns_before); netstat_free(ns_after); @@ -71,14 +71,14 @@ static void *client_fn(void *arg) nr_packets, after_aogood, before_aogood); return NULL; } - if (test_tcp_ao_counters_cmp("connect", &ao1, &ao2, TEST_CNT_GOOD)) + if (test_assert_counters("connect", &ao1, &ao2, TEST_CNT_GOOD)) return NULL; test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %zu", - before_aogood, ao1.ao_info_pkt_good, - ao1.key_cnts[0].pkt_good, - after_aogood, ao2.ao_info_pkt_good, - ao2.key_cnts[0].pkt_good, + before_aogood, ao1.ao.ao_info_pkt_good, + ao1.ao.key_cnts[0].pkt_good, + after_aogood, ao2.ao.ao_info_pkt_good, + ao2.ao.key_cnts[0].pkt_good, nr_packets); return NULL; } diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c index a1614f0d8c44..85c1a1e958c6 100644 --- a/tools/testing/selftests/net/tcp_ao/icmps-discard.c +++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c @@ -53,7 +53,7 @@ static void serve_interfered(int sk) ssize_t test_quota = packet_size * packets_nr * 10; uint64_t dest_unreach_a, dest_unreach_b; uint64_t icmp_ignored_a, icmp_ignored_b; - struct tcp_ao_counters ao_cnt1, ao_cnt2; + struct tcp_counters cnt1, cnt2; bool counter_not_found; struct netstat *ns_after, *ns_before; ssize_t bytes; @@ -61,16 +61,16 @@ static void serve_interfered(int sk) ns_before = netstat_read(); dest_unreach_a = netstat_get(ns_before, dst_unreach, NULL); icmp_ignored_a = netstat_get(ns_before, tcpao_icmps, NULL); - if (test_get_tcp_ao_counters(sk, &ao_cnt1)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt1)) + test_error("test_get_tcp_counters()"); bytes = test_server_run(sk, test_quota, 0); ns_after = netstat_read(); netstat_print_diff(ns_before, ns_after); dest_unreach_b = netstat_get(ns_after, dst_unreach, NULL); icmp_ignored_b = netstat_get(ns_after, tcpao_icmps, &counter_not_found); - if (test_get_tcp_ao_counters(sk, &ao_cnt2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt2)) + test_error("test_get_tcp_counters()"); netstat_free(ns_before); netstat_free(ns_after); @@ -91,9 +91,9 @@ static void serve_interfered(int sk) return; } #ifdef TEST_ICMPS_ACCEPT - test_tcp_ao_counters_cmp(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD); + test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD); #else - test_tcp_ao_counters_cmp(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP); + test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP); #endif if (icmp_ignored_a >= icmp_ignored_b) { test_icmps_fail("%s counter didn't change: %" PRIu64 " >= %" PRIu64, @@ -395,7 +395,6 @@ static void icmp_interfere(const size_t nr, uint32_t rcv_nxt, void *src, void *d static void send_interfered(int sk) { - const unsigned int timeout = TEST_TIMEOUT_SEC; struct sockaddr_in6 src, dst; socklen_t addr_sz; @@ -409,7 +408,7 @@ static void send_interfered(int sk) while (1) { uint32_t rcv_nxt; - if (test_client_verify(sk, packet_size, packets_nr, timeout)) { + if (test_client_verify(sk, packet_size, packets_nr)) { test_fail("client: connection is broken"); return; } diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c index d4385b52c10b..69d9a7a05d5c 100644 --- a/tools/testing/selftests/net/tcp_ao/key-management.c +++ b/tools/testing/selftests/net/tcp_ao/key-management.c @@ -629,11 +629,11 @@ static int key_collection_socket(bool server, unsigned int port) } static void verify_counters(const char *tst_name, bool is_listen_sk, bool server, - struct tcp_ao_counters *a, struct tcp_ao_counters *b) + struct tcp_counters *a, struct tcp_counters *b) { unsigned int i; - __test_tcp_ao_counters_cmp(tst_name, a, b, TEST_CNT_GOOD); + test_assert_counters_sk(tst_name, a, b, TEST_CNT_GOOD); for (i = 0; i < collection.nr_keys; i++) { struct test_key *key = &collection.keys[i]; @@ -652,12 +652,12 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server rx_cnt_expected = key->used_on_server_tx; } - test_tcp_ao_key_counters_cmp(tst_name, a, b, - rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0, - sndid, rcvid); + test_assert_counters_key(tst_name, &a->ao, &b->ao, + rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0, + sndid, rcvid); } - test_tcp_ao_counters_free(a); - test_tcp_ao_counters_free(b); + test_tcp_counters_free(a); + test_tcp_counters_free(b); test_ok("%s: passed counters checks", tst_name); } @@ -791,17 +791,17 @@ out: } static int start_server(const char *tst_name, unsigned int port, size_t quota, - struct tcp_ao_counters *begin, + struct tcp_counters *begin, unsigned int current_index, unsigned int rnext_index) { - struct tcp_ao_counters lsk_c1, lsk_c2; + struct tcp_counters lsk_c1, lsk_c2; ssize_t bytes; int sk, lsk; synchronize_threads(); /* 1: key collection initialized */ lsk = key_collection_socket(true, port); - if (test_get_tcp_ao_counters(lsk, &lsk_c1)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(lsk, &lsk_c1)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* 2: MKTs added => connect() */ if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0)) test_error("test_wait_fd()"); @@ -809,12 +809,12 @@ static int start_server(const char *tst_name, unsigned int port, size_t quota, sk = accept(lsk, NULL, NULL); if (sk < 0) test_error("accept()"); - if (test_get_tcp_ao_counters(sk, begin)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, begin)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* 3: accepted => send data */ - if (test_get_tcp_ao_counters(lsk, &lsk_c2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(lsk, &lsk_c2)) + test_error("test_get_tcp_counters()"); verify_keys(tst_name, lsk, true, true); close(lsk); @@ -830,12 +830,12 @@ static int start_server(const char *tst_name, unsigned int port, size_t quota, } static void end_server(const char *tst_name, int sk, - struct tcp_ao_counters *begin) + struct tcp_counters *begin) { - struct tcp_ao_counters end; + struct tcp_counters end; - if (test_get_tcp_ao_counters(sk, &end)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &end)) + test_error("test_get_tcp_counters()"); verify_keys(tst_name, sk, false, true); synchronize_threads(); /* 4: verified => closed */ @@ -848,7 +848,7 @@ static void end_server(const char *tst_name, int sk, static void try_server_run(const char *tst_name, unsigned int port, size_t quota, unsigned int current_index, unsigned int rnext_index) { - struct tcp_ao_counters tmp; + struct tcp_counters tmp; int sk; sk = start_server(tst_name, port, quota, &tmp, @@ -860,7 +860,7 @@ static void server_rotations(const char *tst_name, unsigned int port, size_t quota, unsigned int rotations, unsigned int current_index, unsigned int rnext_index) { - struct tcp_ao_counters tmp; + struct tcp_counters tmp; unsigned int i; int sk; @@ -886,7 +886,7 @@ static void server_rotations(const char *tst_name, unsigned int port, static int run_client(const char *tst_name, unsigned int port, unsigned int nr_keys, int current_index, int rnext_index, - struct tcp_ao_counters *before, + struct tcp_counters *before, const size_t msg_sz, const size_t msg_nr) { int sk; @@ -904,8 +904,8 @@ static int run_client(const char *tst_name, unsigned int port, if (test_set_key(sk, sndid, rcvid)) test_error("failed to set current/rnext keys"); } - if (before && test_get_tcp_ao_counters(sk, before)) - test_error("test_get_tcp_ao_counters()"); + if (before && test_get_tcp_counters(sk, before)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* 2: MKTs added => connect() */ if (test_connect_socket(sk, this_ip_dest, port++) <= 0) @@ -918,11 +918,11 @@ static int run_client(const char *tst_name, unsigned int port, collection.keys[rnext_index].used_on_server_tx = 1; synchronize_threads(); /* 3: accepted => send data */ - if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) { + if (test_client_verify(sk, msg_sz, msg_nr)) { test_fail("verify failed"); close(sk); if (before) - test_tcp_ao_counters_free(before); + test_tcp_counters_free(before); return -1; } @@ -931,7 +931,7 @@ static int run_client(const char *tst_name, unsigned int port, static int start_client(const char *tst_name, unsigned int port, unsigned int nr_keys, int current_index, int rnext_index, - struct tcp_ao_counters *before, + struct tcp_counters *before, const size_t msg_sz, const size_t msg_nr) { if (init_default_key_collection(nr_keys, true)) @@ -943,9 +943,9 @@ static int start_client(const char *tst_name, unsigned int port, static void end_client(const char *tst_name, int sk, unsigned int nr_keys, int current_index, int rnext_index, - struct tcp_ao_counters *start) + struct tcp_counters *start) { - struct tcp_ao_counters end; + struct tcp_counters end; /* Some application may become dependent on this kernel choice */ if (current_index < 0) @@ -955,8 +955,8 @@ static void end_client(const char *tst_name, int sk, unsigned int nr_keys, verify_current_rnext(tst_name, sk, collection.keys[current_index].client_keyid, collection.keys[rnext_index].server_keyid); - if (start && test_get_tcp_ao_counters(sk, &end)) - test_error("test_get_tcp_ao_counters()"); + if (start && test_get_tcp_counters(sk, &end)) + test_error("test_get_tcp_counters()"); verify_keys(tst_name, sk, false, false); synchronize_threads(); /* 4: verify => closed */ close(sk); @@ -1016,7 +1016,7 @@ static void try_unmatched_keys(int sk, int *rnext_index, unsigned int port) trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, this_ip_addr, this_ip_dest, -1, port, 0, -1, -1, -1, -1, -1, -1, key->server_keyid, -1); - if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk, msg_len, nr_packets)) test_fail("verify failed"); *rnext_index = i; } @@ -1048,7 +1048,7 @@ static void check_current_back(const char *tst_name, unsigned int port, unsigned int current_index, unsigned int rnext_index, unsigned int rotate_to_index) { - struct tcp_ao_counters tmp; + struct tcp_counters tmp; int sk; sk = start_client(tst_name, port, nr_keys, current_index, rnext_index, @@ -1061,7 +1061,7 @@ static void check_current_back(const char *tst_name, unsigned int port, port, -1, 0, -1, -1, -1, -1, -1, collection.keys[rotate_to_index].client_keyid, collection.keys[current_index].client_keyid, -1); - if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk, msg_len, nr_packets)) test_fail("verify failed"); /* There is a race here: between setting the current_key with * setsockopt(TCP_AO_INFO) and starting to send some data - there @@ -1081,7 +1081,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port, unsigned int nr_keys, unsigned int rotations, unsigned int current_index, unsigned int rnext_index) { - struct tcp_ao_counters tmp; + struct tcp_counters tmp; unsigned int i; int sk; @@ -1099,10 +1099,10 @@ static void roll_over_keys(const char *tst_name, unsigned int port, collection.keys[i].server_keyid, -1); if (test_set_key(sk, -1, collection.keys[i].server_keyid)) test_error("Can't change the Rnext key"); - if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) { + if (test_client_verify(sk, msg_len, nr_packets)) { test_fail("verify failed"); close(sk); - test_tcp_ao_counters_free(&tmp); + test_tcp_counters_free(&tmp); return; } verify_current_rnext(tst_name, sk, -1, @@ -1116,7 +1116,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port, static void try_client_run(const char *tst_name, unsigned int port, unsigned int nr_keys, int current_index, int rnext_index) { - struct tcp_ao_counters tmp; + struct tcp_counters tmp; int sk; sk = start_client(tst_name, port, nr_keys, current_index, rnext_index, diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h index 5db2f65cddc4..ebb2899c12fe 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h +++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h @@ -289,7 +289,7 @@ extern int link_set_up(const char *intf); extern const unsigned int test_server_port; extern int test_wait_fd(int sk, time_t sec, bool write); extern int __test_connect_socket(int sk, const char *device, - void *addr, size_t addr_sz, time_t timeout); + void *addr, size_t addr_sz, bool async); extern int __test_listen_socket(int backlog, void *addr, size_t addr_sz); static inline int test_listen_socket(const union tcp_addr taddr, @@ -331,25 +331,26 @@ static inline int test_listen_socket(const union tcp_addr taddr, * If set to 0 - kernel will try to retransmit SYN number of times, set in * /proc/sys/net/ipv4/tcp_syn_retries * By default set to 1 to make tests pass faster on non-busy machine. + * [in process of removal, don't use in new tests] */ #ifndef TEST_RETRANSMIT_SEC #define TEST_RETRANSMIT_SEC 1 #endif static inline int _test_connect_socket(int sk, const union tcp_addr taddr, - unsigned int port, time_t timeout) + unsigned int port, bool async) { sockaddr_af addr; tcp_addr_to_sockaddr_in(&addr, &taddr, htons(port)); return __test_connect_socket(sk, veth_name, - (void *)&addr, sizeof(addr), timeout); + (void *)&addr, sizeof(addr), async); } static inline int test_connect_socket(int sk, const union tcp_addr taddr, unsigned int port) { - return _test_connect_socket(sk, taddr, port, TEST_TIMEOUT_SEC); + return _test_connect_socket(sk, taddr, port, false); } extern int __test_set_md5(int sk, void *addr, size_t addr_sz, @@ -483,10 +484,7 @@ static inline int test_set_ao_flags(int sk, bool ao_required, bool accept_icmps) } extern ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec); -extern ssize_t test_client_loop(int sk, char *buf, size_t buf_sz, - const size_t msg_len, time_t timeout_sec); -extern int test_client_verify(int sk, const size_t msg_len, const size_t nr, - time_t timeout_sec); +extern int test_client_verify(int sk, const size_t msg_len, const size_t nr); struct tcp_ao_key_counters { uint8_t sndid; @@ -512,7 +510,15 @@ struct tcp_ao_counters { size_t nr_keys; struct tcp_ao_key_counters *key_cnts; }; -extern int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out); + +struct tcp_counters { + struct tcp_ao_counters ao; + uint64_t netns_md5_notfound; + uint64_t netns_md5_unexpected; + uint64_t netns_md5_failure; +}; + +extern int test_get_tcp_counters(int sk, struct tcp_counters *out); #define TEST_CNT_KEY_GOOD BIT(0) #define TEST_CNT_KEY_BAD BIT(1) @@ -526,8 +532,31 @@ extern int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out); #define TEST_CNT_NS_KEY_NOT_FOUND BIT(9) #define TEST_CNT_NS_AO_REQUIRED BIT(10) #define TEST_CNT_NS_DROPPED_ICMP BIT(11) +#define TEST_CNT_NS_MD5_NOT_FOUND BIT(12) +#define TEST_CNT_NS_MD5_UNEXPECTED BIT(13) +#define TEST_CNT_NS_MD5_FAILURE BIT(14) typedef uint16_t test_cnt; +#define _for_each_counter(f) \ +do { \ + /* per-netns */ \ + f(ao.netns_ao_good, TEST_CNT_NS_GOOD); \ + f(ao.netns_ao_bad, TEST_CNT_NS_BAD); \ + f(ao.netns_ao_key_not_found, TEST_CNT_NS_KEY_NOT_FOUND); \ + f(ao.netns_ao_required, TEST_CNT_NS_AO_REQUIRED); \ + f(ao.netns_ao_dropped_icmp, TEST_CNT_NS_DROPPED_ICMP); \ + /* per-socket */ \ + f(ao.ao_info_pkt_good, TEST_CNT_SOCK_GOOD); \ + f(ao.ao_info_pkt_bad, TEST_CNT_SOCK_BAD); \ + f(ao.ao_info_pkt_key_not_found, TEST_CNT_SOCK_KEY_NOT_FOUND); \ + f(ao.ao_info_pkt_ao_required, TEST_CNT_SOCK_AO_REQUIRED); \ + f(ao.ao_info_pkt_dropped_icmp, TEST_CNT_SOCK_DROPPED_ICMP); \ + /* non-AO */ \ + f(netns_md5_notfound, TEST_CNT_NS_MD5_NOT_FOUND); \ + f(netns_md5_unexpected, TEST_CNT_NS_MD5_UNEXPECTED); \ + f(netns_md5_failure, TEST_CNT_NS_MD5_FAILURE); \ +} while (0) + #define TEST_CNT_AO_GOOD (TEST_CNT_SOCK_GOOD | TEST_CNT_NS_GOOD) #define TEST_CNT_AO_BAD (TEST_CNT_SOCK_BAD | TEST_CNT_NS_BAD) #define TEST_CNT_AO_KEY_NOT_FOUND (TEST_CNT_SOCK_KEY_NOT_FOUND | \ @@ -539,34 +568,71 @@ typedef uint16_t test_cnt; #define TEST_CNT_GOOD (TEST_CNT_KEY_GOOD | TEST_CNT_AO_GOOD) #define TEST_CNT_BAD (TEST_CNT_KEY_BAD | TEST_CNT_AO_BAD) -extern int __test_tcp_ao_counters_cmp(const char *tst_name, - struct tcp_ao_counters *before, struct tcp_ao_counters *after, +extern test_cnt test_cmp_counters(struct tcp_counters *before, + struct tcp_counters *after); +extern int test_assert_counters_sk(const char *tst_name, + struct tcp_counters *before, struct tcp_counters *after, test_cnt expected); -extern int test_tcp_ao_key_counters_cmp(const char *tst_name, +extern int test_assert_counters_key(const char *tst_name, struct tcp_ao_counters *before, struct tcp_ao_counters *after, test_cnt expected, int sndid, int rcvid); -extern void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts); +extern void test_tcp_counters_free(struct tcp_counters *cnts); + +/* + * Polling for netns and socket counters during select()/connect() and also + * client/server messaging. Instead of constant timeout on underlying select(), + * check the counters and return early. This allows to pass the tests where + * timeout is expected without waiting for that fixing timeout (tests speed-up). + * Previously shorter timeouts were used for tests expecting to time out, + * but that leaded to sporadic false positives on counter checks failures, + * as one second timeouts aren't enough for TCP retransmit. + * + * Two sides of the socketpair (client/server) should synchronize failures + * using a shared variable *err, so that they can detect the other side's + * failure. + */ +extern int test_skpair_wait_poll(int sk, bool write, test_cnt cond, + volatile int *err); +extern int _test_skpair_connect_poll(int sk, const char *device, + void *addr, size_t addr_sz, + test_cnt cond, volatile int *err); +static inline int test_skpair_connect_poll(int sk, const union tcp_addr taddr, + unsigned int port, + test_cnt cond, volatile int *err) +{ + sockaddr_af addr; + + tcp_addr_to_sockaddr_in(&addr, &taddr, htons(port)); + return _test_skpair_connect_poll(sk, veth_name, + (void *)&addr, sizeof(addr), cond, err); +} + +extern int test_skpair_client(int sk, const size_t msg_len, const size_t nr, + test_cnt cond, volatile int *err); +extern int test_skpair_server(int sk, ssize_t quota, + test_cnt cond, volatile int *err); + /* - * Frees buffers allocated in test_get_tcp_ao_counters(). + * Frees buffers allocated in test_get_tcp_counters(). * The function doesn't expect new keys or keys removed between calls - * to test_get_tcp_ao_counters(). Check key counters manually if they + * to test_get_tcp_counters(). Check key counters manually if they * may change. */ -static inline int test_tcp_ao_counters_cmp(const char *tst_name, - struct tcp_ao_counters *before, - struct tcp_ao_counters *after, - test_cnt expected) +static inline int test_assert_counters(const char *tst_name, + struct tcp_counters *before, + struct tcp_counters *after, + test_cnt expected) { int ret; - ret = __test_tcp_ao_counters_cmp(tst_name, before, after, expected); + ret = test_assert_counters_sk(tst_name, before, after, expected); if (ret) goto out; - ret = test_tcp_ao_key_counters_cmp(tst_name, before, after, - expected, -1, -1); + ret = test_assert_counters_key(tst_name, &before->ao, &after->ao, + expected, -1, -1); out: - test_tcp_ao_counters_free(before); - test_tcp_ao_counters_free(after); + test_tcp_counters_free(before); + test_tcp_counters_free(after); return ret; } diff --git a/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c index 24380c68fec6..27403f875054 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c +++ b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c @@ -427,11 +427,8 @@ static void dump_trace_event(struct expected_trace_point *e) test_print("trace event filter %s [%s:%d => %s:%d, L3index %d, flags: %s%s%s%s%s, keyid: %d, rnext: %d, maclen: %d, sne: %d] = %zu", trace_event_names[e->type], src, e->src_port, dst, e->dst_port, e->L3index, - (e->fin > 0) ? "F" : (e->fin == 0) ? "!F" : "", - (e->syn > 0) ? "S" : (e->syn == 0) ? "!S" : "", - (e->rst > 0) ? "R" : (e->rst == 0) ? "!R" : "", - (e->psh > 0) ? "P" : (e->psh == 0) ? "!P" : "", - (e->ack > 0) ? "." : (e->ack == 0) ? "!." : "", + e->fin ? "F" : "", e->syn ? "S" : "", e->rst ? "R" : "", + e->psh ? "P" : "", e->ack ? "." : "", e->keyid, e->rnext, e->maclen, e->sne, e->matched); } diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c index 0ffda966c677..ef8e9031d47a 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/sock.c +++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c @@ -34,10 +34,8 @@ int __test_listen_socket(int backlog, void *addr, size_t addr_sz) return sk; } -int test_wait_fd(int sk, time_t sec, bool write) +static int __test_wait_fd(int sk, struct timeval *tv, bool write) { - struct timeval tv = { .tv_sec = sec }; - struct timeval *ptv = NULL; fd_set fds, efds; int ret; socklen_t slen = sizeof(ret); @@ -47,14 +45,11 @@ int test_wait_fd(int sk, time_t sec, bool write) FD_ZERO(&efds); FD_SET(sk, &efds); - if (sec) - ptv = &tv; - errno = 0; if (write) - ret = select(sk + 1, NULL, &fds, &efds, ptv); + ret = select(sk + 1, NULL, &fds, &efds, tv); else - ret = select(sk + 1, &fds, NULL, &efds, ptv); + ret = select(sk + 1, &fds, NULL, &efds, tv); if (ret < 0) return -errno; if (ret == 0) { @@ -69,8 +64,54 @@ int test_wait_fd(int sk, time_t sec, bool write) return 0; } +int test_wait_fd(int sk, time_t sec, bool write) +{ + struct timeval tv = { .tv_sec = sec, }; + + return __test_wait_fd(sk, sec ? &tv : NULL, write); +} + +static bool __skpair_poll_should_stop(int sk, struct tcp_counters *c, + test_cnt condition) +{ + struct tcp_counters c2; + test_cnt diff; + + if (test_get_tcp_counters(sk, &c2)) + test_error("test_get_tcp_counters()"); + + diff = test_cmp_counters(c, &c2); + test_tcp_counters_free(&c2); + return (diff & condition) == condition; +} + +/* How often wake up and check netns counters & paired (*err) */ +#define POLL_USEC 150 +static int __test_skpair_poll(int sk, bool write, uint64_t timeout, + struct tcp_counters *c, test_cnt cond, + volatile int *err) +{ + uint64_t t; + + for (t = 0; t <= timeout * 1000000; t += POLL_USEC) { + struct timeval tv = { .tv_usec = POLL_USEC, }; + int ret; + + ret = __test_wait_fd(sk, &tv, write); + if (ret != -ETIMEDOUT) + return ret; + if (c && cond && __skpair_poll_should_stop(sk, c, cond)) + break; + if (err && *err) + return *err; + } + if (err) + *err = -ETIMEDOUT; + return -ETIMEDOUT; +} + int __test_connect_socket(int sk, const char *device, - void *addr, size_t addr_sz, time_t timeout) + void *addr, size_t addr_sz, bool async) { long flags; int err; @@ -82,15 +123,6 @@ int __test_connect_socket(int sk, const char *device, test_error("setsockopt(SO_BINDTODEVICE, %s)", device); } - if (!timeout) { - err = connect(sk, addr, addr_sz); - if (err) { - err = -errno; - goto out; - } - return 0; - } - flags = fcntl(sk, F_GETFL); if ((flags < 0) || (fcntl(sk, F_SETFL, flags | O_NONBLOCK) < 0)) test_error("fcntl()"); @@ -100,9 +132,9 @@ int __test_connect_socket(int sk, const char *device, err = -errno; goto out; } - if (timeout < 0) + if (async) return sk; - err = test_wait_fd(sk, timeout, 1); + err = test_wait_fd(sk, TEST_TIMEOUT_SEC, 1); if (err) goto out; } @@ -113,6 +145,45 @@ out: return err; } +int test_skpair_wait_poll(int sk, bool write, + test_cnt cond, volatile int *err) +{ + struct tcp_counters c; + int ret; + + *err = 0; + if (test_get_tcp_counters(sk, &c)) + test_error("test_get_tcp_counters()"); + synchronize_threads(); /* 1: init skpair & read nscounters */ + + ret = __test_skpair_poll(sk, write, TEST_TIMEOUT_SEC, &c, cond, err); + test_tcp_counters_free(&c); + return ret; +} + +int _test_skpair_connect_poll(int sk, const char *device, + void *addr, size_t addr_sz, + test_cnt condition, volatile int *err) +{ + struct tcp_counters c; + int ret; + + *err = 0; + if (test_get_tcp_counters(sk, &c)) + test_error("test_get_tcp_counters()"); + synchronize_threads(); /* 1: init skpair & read nscounters */ + ret = __test_connect_socket(sk, device, addr, addr_sz, true); + if (ret < 0) { + test_tcp_counters_free(&c); + return (*err = ret); + } + ret = __test_skpair_poll(sk, 1, TEST_TIMEOUT_SEC, &c, condition, err); + if (ret < 0) + close(sk); + test_tcp_counters_free(&c); + return ret; +} + int __test_set_md5(int sk, void *addr, size_t addr_sz, uint8_t prefix, int vrf, const char *password) { @@ -333,12 +404,12 @@ do { \ return 0; } -int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out) +int test_get_tcp_counters(int sk, struct tcp_counters *out) { struct tcp_ao_getsockopt *key_dump; socklen_t key_dump_sz = sizeof(*key_dump); struct tcp_ao_info_opt info = {}; - bool c1, c2, c3, c4, c5; + bool c1, c2, c3, c4, c5, c6, c7, c8; struct netstat *ns; int err, nr_keys; @@ -346,25 +417,30 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out) /* per-netns */ ns = netstat_read(); - out->netns_ao_good = netstat_get(ns, "TCPAOGood", &c1); - out->netns_ao_bad = netstat_get(ns, "TCPAOBad", &c2); - out->netns_ao_key_not_found = netstat_get(ns, "TCPAOKeyNotFound", &c3); - out->netns_ao_required = netstat_get(ns, "TCPAORequired", &c4); - out->netns_ao_dropped_icmp = netstat_get(ns, "TCPAODroppedIcmps", &c5); + out->ao.netns_ao_good = netstat_get(ns, "TCPAOGood", &c1); + out->ao.netns_ao_bad = netstat_get(ns, "TCPAOBad", &c2); + out->ao.netns_ao_key_not_found = netstat_get(ns, "TCPAOKeyNotFound", &c3); + out->ao.netns_ao_required = netstat_get(ns, "TCPAORequired", &c4); + out->ao.netns_ao_dropped_icmp = netstat_get(ns, "TCPAODroppedIcmps", &c5); + out->netns_md5_notfound = netstat_get(ns, "TCPMD5NotFound", &c6); + out->netns_md5_unexpected = netstat_get(ns, "TCPMD5Unexpected", &c7); + out->netns_md5_failure = netstat_get(ns, "TCPMD5Failure", &c8); netstat_free(ns); - if (c1 || c2 || c3 || c4 || c5) + if (c1 || c2 || c3 || c4 || c5 || c6 || c7 || c8) return -EOPNOTSUPP; err = test_get_ao_info(sk, &info); + if (err == -ENOENT) + return 0; if (err) return err; /* per-socket */ - out->ao_info_pkt_good = info.pkt_good; - out->ao_info_pkt_bad = info.pkt_bad; - out->ao_info_pkt_key_not_found = info.pkt_key_not_found; - out->ao_info_pkt_ao_required = info.pkt_ao_required; - out->ao_info_pkt_dropped_icmp = info.pkt_dropped_icmp; + out->ao.ao_info_pkt_good = info.pkt_good; + out->ao.ao_info_pkt_bad = info.pkt_bad; + out->ao.ao_info_pkt_key_not_found = info.pkt_key_not_found; + out->ao.ao_info_pkt_ao_required = info.pkt_ao_required; + out->ao.ao_info_pkt_dropped_icmp = info.pkt_dropped_icmp; /* per-key */ nr_keys = test_get_ao_keys_nr(sk); @@ -372,7 +448,7 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out) return nr_keys; if (nr_keys == 0) test_error("test_get_ao_keys_nr() == 0"); - out->nr_keys = (size_t)nr_keys; + out->ao.nr_keys = (size_t)nr_keys; key_dump = calloc(nr_keys, key_dump_sz); if (!key_dump) return -errno; @@ -386,72 +462,84 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out) return -errno; } - out->key_cnts = calloc(nr_keys, sizeof(out->key_cnts[0])); - if (!out->key_cnts) { + out->ao.key_cnts = calloc(nr_keys, sizeof(out->ao.key_cnts[0])); + if (!out->ao.key_cnts) { free(key_dump); return -errno; } while (nr_keys--) { - out->key_cnts[nr_keys].sndid = key_dump[nr_keys].sndid; - out->key_cnts[nr_keys].rcvid = key_dump[nr_keys].rcvid; - out->key_cnts[nr_keys].pkt_good = key_dump[nr_keys].pkt_good; - out->key_cnts[nr_keys].pkt_bad = key_dump[nr_keys].pkt_bad; + out->ao.key_cnts[nr_keys].sndid = key_dump[nr_keys].sndid; + out->ao.key_cnts[nr_keys].rcvid = key_dump[nr_keys].rcvid; + out->ao.key_cnts[nr_keys].pkt_good = key_dump[nr_keys].pkt_good; + out->ao.key_cnts[nr_keys].pkt_bad = key_dump[nr_keys].pkt_bad; } free(key_dump); return 0; } -int __test_tcp_ao_counters_cmp(const char *tst_name, - struct tcp_ao_counters *before, - struct tcp_ao_counters *after, - test_cnt expected) +test_cnt test_cmp_counters(struct tcp_counters *before, + struct tcp_counters *after) +{ +#define __cmp(cnt, e_cnt) \ +do { \ + if (before->cnt > after->cnt) \ + test_error("counter " __stringify(cnt) " decreased"); \ + if (before->cnt != after->cnt) \ + ret |= e_cnt; \ +} while (0) + + test_cnt ret = 0; + size_t i; + + if (before->ao.nr_keys != after->ao.nr_keys) + test_error("the number of keys has changed"); + + _for_each_counter(__cmp); + + i = before->ao.nr_keys; + while (i--) { + __cmp(ao.key_cnts[i].pkt_good, TEST_CNT_KEY_GOOD); + __cmp(ao.key_cnts[i].pkt_bad, TEST_CNT_KEY_BAD); + } +#undef __cmp + return ret; +} + +int test_assert_counters_sk(const char *tst_name, + struct tcp_counters *before, + struct tcp_counters *after, + test_cnt expected) { -#define __cmp_ao(cnt, expecting_inc) \ +#define __cmp_ao(cnt, e_cnt) \ do { \ if (before->cnt > after->cnt) { \ test_fail("%s: Decreased counter " __stringify(cnt) " %" PRIu64 " > %" PRIu64, \ - tst_name ?: "", before->cnt, after->cnt); \ + tst_name ?: "", before->cnt, after->cnt); \ return -1; \ } \ - if ((before->cnt != after->cnt) != (expecting_inc)) { \ + if ((before->cnt != after->cnt) != !!(expected & e_cnt)) { \ test_fail("%s: Counter " __stringify(cnt) " was %sexpected to increase %" PRIu64 " => %" PRIu64, \ - tst_name ?: "", (expecting_inc) ? "" : "not ", \ + tst_name ?: "", (expected & e_cnt) ? "" : "not ", \ before->cnt, after->cnt); \ return -1; \ } \ -} while(0) +} while (0) errno = 0; - /* per-netns */ - __cmp_ao(netns_ao_good, !!(expected & TEST_CNT_NS_GOOD)); - __cmp_ao(netns_ao_bad, !!(expected & TEST_CNT_NS_BAD)); - __cmp_ao(netns_ao_key_not_found, - !!(expected & TEST_CNT_NS_KEY_NOT_FOUND)); - __cmp_ao(netns_ao_required, !!(expected & TEST_CNT_NS_AO_REQUIRED)); - __cmp_ao(netns_ao_dropped_icmp, - !!(expected & TEST_CNT_NS_DROPPED_ICMP)); - /* per-socket */ - __cmp_ao(ao_info_pkt_good, !!(expected & TEST_CNT_SOCK_GOOD)); - __cmp_ao(ao_info_pkt_bad, !!(expected & TEST_CNT_SOCK_BAD)); - __cmp_ao(ao_info_pkt_key_not_found, - !!(expected & TEST_CNT_SOCK_KEY_NOT_FOUND)); - __cmp_ao(ao_info_pkt_ao_required, !!(expected & TEST_CNT_SOCK_AO_REQUIRED)); - __cmp_ao(ao_info_pkt_dropped_icmp, - !!(expected & TEST_CNT_SOCK_DROPPED_ICMP)); + _for_each_counter(__cmp_ao); return 0; #undef __cmp_ao } -int test_tcp_ao_key_counters_cmp(const char *tst_name, - struct tcp_ao_counters *before, - struct tcp_ao_counters *after, - test_cnt expected, - int sndid, int rcvid) +int test_assert_counters_key(const char *tst_name, + struct tcp_ao_counters *before, + struct tcp_ao_counters *after, + test_cnt expected, int sndid, int rcvid) { size_t i; -#define __cmp_ao(i, cnt, expecting_inc) \ +#define __cmp_ao(i, cnt, e_cnt) \ do { \ if (before->key_cnts[i].cnt > after->key_cnts[i].cnt) { \ test_fail("%s: Decreased counter " __stringify(cnt) " %" PRIu64 " > %" PRIu64 " for key %u:%u", \ @@ -461,16 +549,16 @@ do { \ before->key_cnts[i].rcvid); \ return -1; \ } \ - if ((before->key_cnts[i].cnt != after->key_cnts[i].cnt) != (expecting_inc)) { \ + if ((before->key_cnts[i].cnt != after->key_cnts[i].cnt) != !!(expected & e_cnt)) { \ test_fail("%s: Counter " __stringify(cnt) " was %sexpected to increase %" PRIu64 " => %" PRIu64 " for key %u:%u", \ - tst_name ?: "", (expecting_inc) ? "" : "not ",\ + tst_name ?: "", (expected & e_cnt) ? "" : "not ",\ before->key_cnts[i].cnt, \ after->key_cnts[i].cnt, \ before->key_cnts[i].sndid, \ before->key_cnts[i].rcvid); \ return -1; \ } \ -} while(0) +} while (0) if (before->nr_keys != after->nr_keys) { test_fail("%s: Keys changed on the socket %zu != %zu", @@ -485,20 +573,22 @@ do { \ continue; if (rcvid >= 0 && before->key_cnts[i].rcvid != rcvid) continue; - __cmp_ao(i, pkt_good, !!(expected & TEST_CNT_KEY_GOOD)); - __cmp_ao(i, pkt_bad, !!(expected & TEST_CNT_KEY_BAD)); + __cmp_ao(i, pkt_good, TEST_CNT_KEY_GOOD); + __cmp_ao(i, pkt_bad, TEST_CNT_KEY_BAD); } return 0; #undef __cmp_ao } -void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts) +void test_tcp_counters_free(struct tcp_counters *cnts) { - free(cnts->key_cnts); + free(cnts->ao.key_cnts); } #define TEST_BUF_SIZE 4096 -ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec) +static ssize_t _test_server_run(int sk, ssize_t quota, struct tcp_counters *c, + test_cnt cond, volatile int *err, + time_t timeout_sec) { ssize_t total = 0; @@ -507,7 +597,7 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec) ssize_t bytes, sent; int ret; - ret = test_wait_fd(sk, timeout_sec, 0); + ret = __test_skpair_poll(sk, 0, timeout_sec, c, cond, err); if (ret) return ret; @@ -518,7 +608,7 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec) if (bytes == 0) break; - ret = test_wait_fd(sk, timeout_sec, 1); + ret = __test_skpair_poll(sk, 1, timeout_sec, c, cond, err); if (ret) return ret; @@ -533,13 +623,41 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec) return total; } -ssize_t test_client_loop(int sk, char *buf, size_t buf_sz, - const size_t msg_len, time_t timeout_sec) +ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec) +{ + return _test_server_run(sk, quota, NULL, 0, NULL, + timeout_sec ?: TEST_TIMEOUT_SEC); +} + +int test_skpair_server(int sk, ssize_t quota, test_cnt cond, volatile int *err) +{ + struct tcp_counters c; + ssize_t ret; + + *err = 0; + if (test_get_tcp_counters(sk, &c)) + test_error("test_get_tcp_counters()"); + synchronize_threads(); /* 1: init skpair & read nscounters */ + + ret = _test_server_run(sk, quota, &c, cond, err, TEST_TIMEOUT_SEC); + test_tcp_counters_free(&c); + return ret; +} + +static ssize_t test_client_loop(int sk, size_t buf_sz, const size_t msg_len, + struct tcp_counters *c, test_cnt cond, + volatile int *err) { char msg[msg_len]; int nodelay = 1; + char *buf; size_t i; + buf = alloca(buf_sz); + if (!buf) + return -ENOMEM; + randomize_buffer(buf, buf_sz); + if (setsockopt(sk, IPPROTO_TCP, TCP_NODELAY, &nodelay, sizeof(nodelay))) test_error("setsockopt(TCP_NODELAY)"); @@ -547,7 +665,7 @@ ssize_t test_client_loop(int sk, char *buf, size_t buf_sz, size_t sent, bytes = min(msg_len, buf_sz - i); int ret; - ret = test_wait_fd(sk, timeout_sec, 1); + ret = __test_skpair_poll(sk, 1, TEST_TIMEOUT_SEC, c, cond, err); if (ret) return ret; @@ -561,7 +679,8 @@ ssize_t test_client_loop(int sk, char *buf, size_t buf_sz, do { ssize_t got; - ret = test_wait_fd(sk, timeout_sec, 0); + ret = __test_skpair_poll(sk, 0, TEST_TIMEOUT_SEC, + c, cond, err); if (ret) return ret; @@ -580,15 +699,31 @@ ssize_t test_client_loop(int sk, char *buf, size_t buf_sz, return i; } -int test_client_verify(int sk, const size_t msg_len, const size_t nr, - time_t timeout_sec) +int test_client_verify(int sk, const size_t msg_len, const size_t nr) { size_t buf_sz = msg_len * nr; - char *buf = alloca(buf_sz); ssize_t ret; - randomize_buffer(buf, buf_sz); - ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec); + ret = test_client_loop(sk, buf_sz, msg_len, NULL, 0, NULL); + if (ret < 0) + return (int)ret; + return ret != buf_sz ? -1 : 0; +} + +int test_skpair_client(int sk, const size_t msg_len, const size_t nr, + test_cnt cond, volatile int *err) +{ + struct tcp_counters c; + size_t buf_sz = msg_len * nr; + ssize_t ret; + + *err = 0; + if (test_get_tcp_counters(sk, &c)) + test_error("test_get_tcp_counters()"); + synchronize_threads(); /* 1: init skpair & read nscounters */ + + ret = test_client_loop(sk, buf_sz, msg_len, &c, cond, err); + test_tcp_counters_free(&c); if (ret < 0) return (int)ret; return ret != buf_sz ? -1 : 0; diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c index ecc6f1e3a414..9a059b6c4523 100644 --- a/tools/testing/selftests/net/tcp_ao/restore.c +++ b/tools/testing/selftests/net/tcp_ao/restore.c @@ -16,11 +16,11 @@ const size_t quota = nr_packets * msg_len; static void try_server_run(const char *tst_name, unsigned int port, fault_t inj, test_cnt cnt_expected) { + test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected; const char *cnt_name = "TCPAOGood"; - struct tcp_ao_counters ao1, ao2; + struct tcp_counters cnt1, cnt2; uint64_t before_cnt, after_cnt; - int sk, lsk; - time_t timeout; + int sk, lsk, dummy; ssize_t bytes; if (fault(TIMEOUT)) @@ -48,11 +48,10 @@ static void try_server_run(const char *tst_name, unsigned int port, } before_cnt = netstat_get_one(cnt_name, NULL); - if (test_get_tcp_ao_counters(sk, &ao1)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt1)) + test_error("test_get_tcp_counters()"); - timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; - bytes = test_server_run(sk, quota, timeout); + bytes = test_skpair_server(sk, quota, poll_cnt, &dummy); if (fault(TIMEOUT)) { if (bytes > 0) test_fail("%s: server served: %zd", tst_name, bytes); @@ -65,17 +64,17 @@ static void try_server_run(const char *tst_name, unsigned int port, test_ok("%s: server alive", tst_name); } synchronize_threads(); /* 3: counters checks */ - if (test_get_tcp_ao_counters(sk, &ao2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt2)) + test_error("test_get_tcp_counters()"); after_cnt = netstat_get_one(cnt_name, NULL); - test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected); + test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected); if (after_cnt <= before_cnt) { - test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64, - tst_name, cnt_name, after_cnt, before_cnt); + test_fail("%s(server): %s counter did not increase: %" PRIu64 " <= %" PRIu64, + tst_name, cnt_name, after_cnt, before_cnt); } else { - test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64, + test_ok("%s(server): counter %s increased %" PRIu64 " => %" PRIu64, tst_name, cnt_name, before_cnt, after_cnt); } @@ -92,16 +91,16 @@ static void *server_fn(void *arg) { unsigned int port = test_server_port; - try_server_run("TCP-AO migrate to another socket", port++, + try_server_run("TCP-AO migrate to another socket (server)", port++, 0, TEST_CNT_GOOD); - try_server_run("TCP-AO with wrong send ISN", port++, + try_server_run("TCP-AO with wrong send ISN (server)", port++, FAULT_TIMEOUT, TEST_CNT_BAD); - try_server_run("TCP-AO with wrong receive ISN", port++, + try_server_run("TCP-AO with wrong receive ISN (server)", port++, FAULT_TIMEOUT, TEST_CNT_BAD); - try_server_run("TCP-AO with wrong send SEQ ext number", port++, + try_server_run("TCP-AO with wrong send SEQ ext number (server)", port++, FAULT_TIMEOUT, TEST_CNT_BAD); - try_server_run("TCP-AO with wrong receive SEQ ext number", port++, - FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD); + try_server_run("TCP-AO with wrong receive SEQ ext number (server)", + port++, FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD); synchronize_threads(); /* don't race to exit: client exits */ return NULL; @@ -125,7 +124,7 @@ static void test_get_sk_checkpoint(unsigned int server_port, sockaddr_af *saddr, test_error("failed to connect()"); synchronize_threads(); /* 2: accepted => send data */ - if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk, msg_len, nr_packets)) test_fail("pre-migrate verify failed"); test_enable_repair(sk); @@ -139,11 +138,11 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port, struct tcp_ao_repair *ao_img, fault_t inj, test_cnt cnt_expected) { + test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected; const char *cnt_name = "TCPAOGood"; - struct tcp_ao_counters ao1, ao2; + struct tcp_counters cnt1, cnt2; uint64_t before_cnt, after_cnt; - time_t timeout; - int sk; + int sk, dummy; if (fault(TIMEOUT)) cnt_name = "TCPAOBad"; @@ -159,30 +158,30 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port, test_error("setsockopt(TCP_AO_ADD_KEY)"); test_ao_restore(sk, ao_img); - if (test_get_tcp_ao_counters(sk, &ao1)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt1)) + test_error("test_get_tcp_counters()"); test_disable_repair(sk); test_sock_state_free(img); - timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; - if (test_client_verify(sk, msg_len, nr_packets, timeout)) { + if (test_skpair_client(sk, msg_len, nr_packets, poll_cnt, &dummy)) { if (fault(TIMEOUT)) test_ok("%s: post-migrate connection is broken", tst_name); else test_fail("%s: post-migrate connection is working", tst_name); } else { if (fault(TIMEOUT)) - test_fail("%s: post-migrate connection still working", tst_name); + test_fail("%s: post-migrate connection is working", tst_name); else test_ok("%s: post-migrate connection is alive", tst_name); } + synchronize_threads(); /* 3: counters checks */ - if (test_get_tcp_ao_counters(sk, &ao2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt2)) + test_error("test_get_tcp_counters()"); after_cnt = netstat_get_one(cnt_name, NULL); - test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected); + test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected); if (after_cnt <= before_cnt) { test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64, @@ -203,7 +202,7 @@ static void *client_fn(void *arg) sockaddr_af saddr; test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); - test_sk_restore("TCP-AO migrate to another socket", port++, + test_sk_restore("TCP-AO migrate to another socket (client)", port++, &saddr, &tcp_img, &ao_img, 0, TEST_CNT_GOOD); test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); @@ -212,7 +211,7 @@ static void *client_fn(void *arg) -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1); trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr, port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1); - test_sk_restore("TCP-AO with wrong send ISN", port++, + test_sk_restore("TCP-AO with wrong send ISN (client)", port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD); test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); @@ -221,7 +220,7 @@ static void *client_fn(void *arg) -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1); trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr, port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1); - test_sk_restore("TCP-AO with wrong receive ISN", port++, + test_sk_restore("TCP-AO with wrong receive ISN (client)", port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD); test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); @@ -229,8 +228,8 @@ static void *client_fn(void *arg) trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest, -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1); /* not expecting server => client mismatches as only snd sne is broken */ - test_sk_restore("TCP-AO with wrong send SEQ ext number", port++, - &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, + test_sk_restore("TCP-AO with wrong send SEQ ext number (client)", + port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD); test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); @@ -238,8 +237,8 @@ static void *client_fn(void *arg) /* not expecting client => server mismatches as only rcv sne is broken */ trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr, port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1); - test_sk_restore("TCP-AO with wrong receive SEQ ext number", port++, - &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, + test_sk_restore("TCP-AO with wrong receive SEQ ext number (client)", + port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_NS_GOOD | TEST_CNT_BAD); return NULL; diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index 6364facaa63e..883cddf377cf 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -84,15 +84,15 @@ static void close_forced(int sk) static void test_server_active_rst(unsigned int port) { - struct tcp_ao_counters cnt1, cnt2; + struct tcp_counters cnt1, cnt2; ssize_t bytes; int sk, lsk; lsk = test_listen_socket(this_ip_addr, port, backlog); if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100)) test_error("setsockopt(TCP_AO_ADD_KEY)"); - if (test_get_tcp_ao_counters(lsk, &cnt1)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(lsk, &cnt1)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* 1: MKT added */ if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0)) @@ -103,8 +103,8 @@ static void test_server_active_rst(unsigned int port) test_error("accept()"); synchronize_threads(); /* 2: connection accept()ed, another queued */ - if (test_get_tcp_ao_counters(lsk, &cnt2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(lsk, &cnt2)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* 3: close listen socket */ close(lsk); @@ -120,7 +120,7 @@ static void test_server_active_rst(unsigned int port) synchronize_threads(); /* 5: closed active sk */ synchronize_threads(); /* 6: counters checks */ - if (test_tcp_ao_counters_cmp("active RST server", &cnt1, &cnt2, TEST_CNT_GOOD)) + if (test_assert_counters("active RST server", &cnt1, &cnt2, TEST_CNT_GOOD)) test_fail("MKT counters (server) have not only good packets"); else test_ok("MKT counters are good on server"); @@ -128,7 +128,7 @@ static void test_server_active_rst(unsigned int port) static void test_server_passive_rst(unsigned int port) { - struct tcp_ao_counters ao1, ao2; + struct tcp_counters cnt1, cnt2; int sk, lsk; ssize_t bytes; @@ -147,8 +147,8 @@ static void test_server_passive_rst(unsigned int port) synchronize_threads(); /* 2: accepted => send data */ close(lsk); - if (test_get_tcp_ao_counters(sk, &ao1)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt1)) + test_error("test_get_tcp_counters()"); bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC); if (bytes != quota) { @@ -160,12 +160,12 @@ static void test_server_passive_rst(unsigned int port) synchronize_threads(); /* 3: checkpoint the client */ synchronize_threads(); /* 4: close the server, creating twsk */ - if (test_get_tcp_ao_counters(sk, &ao2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt2)) + test_error("test_get_tcp_counters()"); close(sk); synchronize_threads(); /* 5: restore the socket, send more data */ - test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD); + test_assert_counters("passive RST server", &cnt1, &cnt2, TEST_CNT_GOOD); synchronize_threads(); /* 6: server exits */ } @@ -271,8 +271,7 @@ static void test_client_active_rst(unsigned int port) synchronize_threads(); /* 1: MKT added */ for (i = 0; i < last; i++) { - err = _test_connect_socket(sk[i], this_ip_dest, port, - (i == 0) ? TEST_TIMEOUT_SEC : -1); + err = _test_connect_socket(sk[i], this_ip_dest, port, i != 0); if (err < 0) test_error("failed to connect()"); } @@ -283,12 +282,12 @@ static void test_client_active_rst(unsigned int port) test_error("test_wait_fds(): %d", err); /* async connect() with third sk to get into request_sock_queue */ - err = _test_connect_socket(sk[last], this_ip_dest, port, -1); + err = _test_connect_socket(sk[last], this_ip_dest, port, 1); if (err < 0) test_error("failed to connect()"); synchronize_threads(); /* 3: close listen socket */ - if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk[0], packet_sz, quota / packet_sz)) test_fail("Failed to send data on connected socket"); else test_ok("Verified established tcp connection"); @@ -323,7 +322,7 @@ static void test_client_active_rst(unsigned int port) static void test_client_passive_rst(unsigned int port) { - struct tcp_ao_counters ao1, ao2; + struct tcp_counters cnt1, cnt2; struct tcp_ao_repair ao_img; struct tcp_sock_state img; sockaddr_af saddr; @@ -341,7 +340,7 @@ static void test_client_passive_rst(unsigned int port) test_error("failed to connect()"); synchronize_threads(); /* 2: accepted => send data */ - if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk, packet_sz, quota / packet_sz)) test_fail("Failed to send data on connected socket"); else test_ok("Verified established tcp connection"); @@ -397,8 +396,8 @@ static void test_client_passive_rst(unsigned int port) test_error("setsockopt(TCP_AO_ADD_KEY)"); test_ao_restore(sk, &ao_img); - if (test_get_tcp_ao_counters(sk, &ao1)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt1)) + test_error("test_get_tcp_counters()"); test_disable_repair(sk); test_sock_state_free(&img); @@ -417,7 +416,7 @@ static void test_client_passive_rst(unsigned int port) * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0, * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0 */ - err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC); + err = test_client_verify(sk, packet_sz, quota / packet_sz); /* Make sure that the connection was reset, not timeouted */ if (err && err == -ECONNRESET) test_ok("client sock was passively reset post-seq-adjust"); @@ -426,12 +425,12 @@ static void test_client_passive_rst(unsigned int port) else test_fail("client sock is yet connected post-seq-adjust"); - if (test_get_tcp_ao_counters(sk, &ao2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt2)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* 6: server exits */ close(sk); - test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD); + test_assert_counters("client passive RST", &cnt1, &cnt2, TEST_CNT_GOOD); } static void *client_fn(void *arg) diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c index 3ecd2b58de6a..73b2f2276f3f 100644 --- a/tools/testing/selftests/net/tcp_ao/self-connect.c +++ b/tools/testing/selftests/net/tcp_ao/self-connect.c @@ -30,7 +30,7 @@ static void setup_lo_intf(const char *lo_intf) static void tcp_self_connect(const char *tst, unsigned int port, bool different_keyids, bool check_restore) { - struct tcp_ao_counters before_ao, after_ao; + struct tcp_counters before, after; uint64_t before_aogood, after_aogood; struct netstat *ns_before, *ns_after; const size_t nr_packets = 20; @@ -60,17 +60,17 @@ static void tcp_self_connect(const char *tst, unsigned int port, ns_before = netstat_read(); before_aogood = netstat_get(ns_before, "TCPAOGood", NULL); - if (test_get_tcp_ao_counters(sk, &before_ao)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &before)) + test_error("test_get_tcp_counters()"); if (__test_connect_socket(sk, "lo", (struct sockaddr *)&addr, - sizeof(addr), TEST_TIMEOUT_SEC) < 0) { + sizeof(addr), 0) < 0) { ns_after = netstat_read(); netstat_print_diff(ns_before, ns_after); test_error("failed to connect()"); } - if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) { + if (test_client_verify(sk, 100, nr_packets)) { test_fail("%s: tcp connection verify failed", tst); close(sk); return; @@ -78,8 +78,8 @@ static void tcp_self_connect(const char *tst, unsigned int port, ns_after = netstat_read(); after_aogood = netstat_get(ns_after, "TCPAOGood", NULL); - if (test_get_tcp_ao_counters(sk, &after_ao)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &after)) + test_error("test_get_tcp_counters()"); if (!check_restore) { /* to debug: netstat_print_diff(ns_before, ns_after); */ netstat_free(ns_before); @@ -93,7 +93,7 @@ static void tcp_self_connect(const char *tst, unsigned int port, return; } - if (test_tcp_ao_counters_cmp(tst, &before_ao, &after_ao, TEST_CNT_GOOD)) { + if (test_assert_counters(tst, &before, &after, TEST_CNT_GOOD)) { close(sk); return; } @@ -136,7 +136,7 @@ static void tcp_self_connect(const char *tst, unsigned int port, test_ao_restore(sk, &ao_img); test_disable_repair(sk); test_sock_state_free(&img); - if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) { + if (test_client_verify(sk, 100, nr_packets)) { test_fail("%s: tcp connection verify failed", tst); close(sk); return; diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c index 8901a6785dc8..f00245263b20 100644 --- a/tools/testing/selftests/net/tcp_ao/seq-ext.c +++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c @@ -40,7 +40,7 @@ static void test_adjust_seqs(struct tcp_sock_state *img, static int test_sk_restore(struct tcp_sock_state *img, struct tcp_ao_repair *ao_img, sockaddr_af *saddr, const union tcp_addr daddr, unsigned int dport, - struct tcp_ao_counters *cnt) + struct tcp_counters *cnt) { int sk; @@ -54,8 +54,8 @@ static int test_sk_restore(struct tcp_sock_state *img, test_error("setsockopt(TCP_AO_ADD_KEY)"); test_ao_restore(sk, ao_img); - if (test_get_tcp_ao_counters(sk, cnt)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, cnt)) + test_error("test_get_tcp_counters()"); test_disable_repair(sk); test_sock_state_free(img); @@ -65,7 +65,7 @@ static int test_sk_restore(struct tcp_sock_state *img, static void *server_fn(void *arg) { uint64_t before_good, after_good, after_bad; - struct tcp_ao_counters ao1, ao2; + struct tcp_counters cnt1, cnt2; struct tcp_sock_state img; struct tcp_ao_repair ao_img; sockaddr_af saddr; @@ -114,7 +114,7 @@ static void *server_fn(void *arg) test_adjust_seqs(&img, &ao_img, true); synchronize_threads(); /* 4: dump finished */ sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest, - client_new_port, &ao1); + client_new_port, &cnt1); trace_ao_event_sne_expect(TCP_AO_SND_SNE_UPDATE, this_ip_addr, this_ip_dest, test_server_port + 1, client_new_port, 1); @@ -136,11 +136,11 @@ static void *server_fn(void *arg) } synchronize_threads(); /* 6: verify counters after SEQ-number rollover */ - if (test_get_tcp_ao_counters(sk, &ao2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt2)) + test_error("test_get_tcp_counters()"); after_good = netstat_get_one("TCPAOGood", NULL); - test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD); + test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD); if (after_good <= before_good) { test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64, @@ -173,7 +173,7 @@ out: static void *client_fn(void *arg) { uint64_t before_good, after_good, after_bad; - struct tcp_ao_counters ao1, ao2; + struct tcp_counters cnt1, cnt2; struct tcp_sock_state img; struct tcp_ao_repair ao_img; sockaddr_af saddr; @@ -191,7 +191,7 @@ static void *client_fn(void *arg) test_error("failed to connect()"); synchronize_threads(); /* 2: accepted => send data */ - if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) { + if (test_client_verify(sk, msg_len, nr_packets)) { test_fail("pre-migrate verify failed"); return NULL; } @@ -213,20 +213,20 @@ static void *client_fn(void *arg) test_adjust_seqs(&img, &ao_img, false); synchronize_threads(); /* 4: dump finished */ sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest, - test_server_port + 1, &ao1); + test_server_port + 1, &cnt1); synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */ - if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk, msg_len, nr_packets)) test_fail("post-migrate verify failed"); else test_ok("post-migrate connection alive"); synchronize_threads(); /* 5: verify counters after SEQ-number rollover */ - if (test_get_tcp_ao_counters(sk, &ao2)) - test_error("test_get_tcp_ao_counters()"); + if (test_get_tcp_counters(sk, &cnt2)) + test_error("test_get_tcp_counters()"); after_good = netstat_get_one("TCPAOGood", NULL); - test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD); + test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD); if (after_good <= before_good) { test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64, diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c index f779e5892bc1..a1467b64390a 100644 --- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c +++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c @@ -6,6 +6,7 @@ #define fault(type) (inj == FAULT_ ## type) static const char *md5_password = "Some evil genius, enemy to mankind, must have been the first contriver."; static const char *ao_password = DEFAULT_TEST_PASSWORD; +static volatile int sk_pair; static union tcp_addr client2; static union tcp_addr client3; @@ -41,10 +42,10 @@ static void try_accept(const char *tst_name, unsigned int port, const char *cnt_name, test_cnt cnt_expected, int needs_tcp_md5, fault_t inj) { - struct tcp_ao_counters ao_cnt1, ao_cnt2; + struct tcp_counters cnt1, cnt2; uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */ - int lsk, err, sk = 0; - time_t timeout; + test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected; + int lsk, err, sk = -1; if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5)) return; @@ -63,22 +64,25 @@ static void try_accept(const char *tst_name, unsigned int port, if (cnt_name) before_cnt = netstat_get_one(cnt_name, NULL); - if (ao_addr && test_get_tcp_ao_counters(lsk, &ao_cnt1)) - test_error("test_get_tcp_ao_counters()"); + if (ao_addr && test_get_tcp_counters(lsk, &cnt1)) + test_error("test_get_tcp_counters()"); synchronize_threads(); /* preparations done */ - timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; - err = test_wait_fd(lsk, timeout, 0); + err = test_skpair_wait_poll(lsk, 0, poll_cnt, &sk_pair); synchronize_threads(); /* connect()/accept() timeouts */ if (err == -ETIMEDOUT) { + sk_pair = err; if (!fault(TIMEOUT)) - test_fail("timed out for accept()"); + test_fail("%s: timed out for accept()", tst_name); + } else if (err == -EKEYREJECTED) { + if (!fault(KEYREJECT)) + test_fail("%s: key was rejected", tst_name); } else if (err < 0) { - test_error("test_wait_fd()"); + test_error("test_skpair_wait_poll()"); } else { if (fault(TIMEOUT)) - test_fail("ready to accept"); + test_fail("%s: ready to accept", tst_name); sk = accept(lsk, NULL, NULL); if (sk < 0) { @@ -89,8 +93,8 @@ static void try_accept(const char *tst_name, unsigned int port, } } - if (ao_addr && test_get_tcp_ao_counters(lsk, &ao_cnt2)) - test_error("test_get_tcp_ao_counters()"); + if (ao_addr && test_get_tcp_counters(lsk, &cnt2)) + test_error("test_get_tcp_counters()"); close(lsk); if (!cnt_name) { @@ -108,11 +112,11 @@ static void try_accept(const char *tst_name, unsigned int port, tst_name, cnt_name, before_cnt, after_cnt); } if (ao_addr) - test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected); + test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected); out: synchronize_threads(); /* test_kill_sk() */ - if (sk > 0) + if (sk >= 0) test_kill_sk(sk); } @@ -153,78 +157,82 @@ static void *server_fn(void *arg) server_add_routes(); - try_accept("AO server (INADDR_ANY): AO client", port++, NULL, 0, + try_accept("[server] AO server (INADDR_ANY): AO client", port++, NULL, 0, &addr_any, 0, 0, 100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 0, 0); - try_accept("AO server (INADDR_ANY): MD5 client", port++, NULL, 0, + try_accept("[server] AO server (INADDR_ANY): MD5 client", port++, NULL, 0, &addr_any, 0, 0, 100, 100, 0, "TCPMD5Unexpected", - 0, 1, FAULT_TIMEOUT); - try_accept("AO server (INADDR_ANY): no sign client", port++, NULL, 0, + TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT); + try_accept("[server] AO server (INADDR_ANY): no sign client", port++, NULL, 0, &addr_any, 0, 0, 100, 100, 0, "TCPAORequired", TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT); - try_accept("AO server (AO_REQUIRED): AO client", port++, NULL, 0, + try_accept("[server] AO server (AO_REQUIRED): AO client", port++, NULL, 0, &this_ip_dest, TEST_PREFIX, true, 100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 0, 0); - try_accept("AO server (AO_REQUIRED): unsigned client", port++, NULL, 0, + try_accept("[server] AO server (AO_REQUIRED): unsigned client", port++, NULL, 0, &this_ip_dest, TEST_PREFIX, true, 100, 100, 0, "TCPAORequired", TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT); - try_accept("MD5 server (INADDR_ANY): AO client", port++, &addr_any, 0, + try_accept("[server] MD5 server (INADDR_ANY): AO client", port++, &addr_any, 0, NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound", - 0, 1, FAULT_TIMEOUT); - try_accept("MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0, + TEST_CNT_NS_KEY_NOT_FOUND, 1, FAULT_TIMEOUT); + try_accept("[server] MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0, NULL, 0, 0, 0, 0, 0, NULL, 0, 1, 0); - try_accept("MD5 server (INADDR_ANY): no sign client", port++, &addr_any, + try_accept("[server] MD5 server (INADDR_ANY): no sign client", port++, &addr_any, 0, NULL, 0, 0, 0, 0, 0, "TCPMD5NotFound", - 0, 1, FAULT_TIMEOUT); + TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT); - try_accept("no sign server: AO client", port++, NULL, 0, + try_accept("[server] no sign server: AO client", port++, NULL, 0, NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound", - TEST_CNT_AO_KEY_NOT_FOUND, 0, FAULT_TIMEOUT); - try_accept("no sign server: MD5 client", port++, NULL, 0, + TEST_CNT_NS_KEY_NOT_FOUND, 0, FAULT_TIMEOUT); + try_accept("[server] no sign server: MD5 client", port++, NULL, 0, NULL, 0, 0, 0, 0, 0, "TCPMD5Unexpected", - 0, 1, FAULT_TIMEOUT); - try_accept("no sign server: no sign client", port++, NULL, 0, + TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT); + try_accept("[server] no sign server: no sign client", port++, NULL, 0, NULL, 0, 0, 0, 0, 0, "CurrEstab", 0, 0, 0); - try_accept("AO+MD5 server: AO client (matching)", port++, + try_accept("[server] AO+MD5 server: AO client (matching)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, 100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 1, 0); - try_accept("AO+MD5 server: AO client (misconfig, matching MD5)", port++, + try_accept("[server] AO+MD5 server: AO client (misconfig, matching MD5)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, 100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND, 1, FAULT_TIMEOUT); - try_accept("AO+MD5 server: AO client (misconfig, non-matching)", port++, + try_accept("[server] AO+MD5 server: AO client (misconfig, non-matching)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, 100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND, 1, FAULT_TIMEOUT); - try_accept("AO+MD5 server: MD5 client (matching)", port++, + try_accept("[server] AO+MD5 server: MD5 client (matching)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, 100, 100, 0, NULL, 0, 1, 0); - try_accept("AO+MD5 server: MD5 client (misconfig, matching AO)", port++, + try_accept("[server] AO+MD5 server: MD5 client (misconfig, matching AO)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, - 100, 100, 0, "TCPMD5Unexpected", 0, 1, FAULT_TIMEOUT); - try_accept("AO+MD5 server: MD5 client (misconfig, non-matching)", port++, + 100, 100, 0, "TCPMD5Unexpected", + TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT); + try_accept("[server] AO+MD5 server: MD5 client (misconfig, non-matching)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, - 100, 100, 0, "TCPMD5Unexpected", 0, 1, FAULT_TIMEOUT); - try_accept("AO+MD5 server: no sign client (unmatched)", port++, + 100, 100, 0, "TCPMD5Unexpected", + TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT); + try_accept("[server] AO+MD5 server: no sign client (unmatched)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, 100, 100, 0, "CurrEstab", 0, 1, 0); - try_accept("AO+MD5 server: no sign client (misconfig, matching AO)", + try_accept("[server] AO+MD5 server: no sign client (misconfig, matching AO)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, 100, 100, 0, "TCPAORequired", TEST_CNT_AO_REQUIRED, 1, FAULT_TIMEOUT); - try_accept("AO+MD5 server: no sign client (misconfig, matching MD5)", + try_accept("[server] AO+MD5 server: no sign client (misconfig, matching MD5)", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, - 100, 100, 0, "TCPMD5NotFound", 0, 1, FAULT_TIMEOUT); + 100, 100, 0, "TCPMD5NotFound", + TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT); - try_accept("AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys", + /* Key rejected by the other side, failing short through skpair */ + try_accept("[server] AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, - 100, 100, 0, NULL, 0, 1, FAULT_TIMEOUT); - try_accept("AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys", + 100, 100, 0, NULL, 0, 1, FAULT_KEYREJECT); + try_accept("[server] AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys", port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0, - 100, 100, 0, NULL, 0, 1, FAULT_TIMEOUT); + 100, 100, 0, NULL, 0, 1, FAULT_KEYREJECT); server_add_fail_tests(&port); @@ -259,7 +267,6 @@ static void try_connect(const char *tst_name, unsigned int port, uint8_t sndid, uint8_t rcvid, uint8_t vrf, fault_t inj, int needs_tcp_md5, union tcp_addr *bind_addr) { - time_t timeout; int sk, ret; if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5)) @@ -281,11 +288,10 @@ static void try_connect(const char *tst_name, unsigned int port, synchronize_threads(); /* preparations done */ - timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; - ret = _test_connect_socket(sk, this_ip_dest, port, timeout); - + ret = test_skpair_connect_poll(sk, this_ip_dest, port, 0, &sk_pair); synchronize_threads(); /* connect()/accept() timeouts */ if (ret < 0) { + sk_pair = ret; if (fault(KEYREJECT) && ret == -EKEYREJECTED) test_ok("%s: connect() was prevented", tst_name); else if (ret == -ETIMEDOUT && fault(TIMEOUT)) @@ -305,8 +311,7 @@ static void try_connect(const char *tst_name, unsigned int port, out: synchronize_threads(); /* test_kill_sk() */ - /* _test_connect_socket() cleans up on failure */ - if (ret > 0) + if (ret > 0) /* test_skpair_connect_poll() cleans up on failure */ test_kill_sk(sk); } @@ -437,7 +442,6 @@ static void try_to_add(const char *tst_name, unsigned int port, int ao_vrf, uint8_t sndid, uint8_t rcvid, int needs_tcp_md5, fault_t inj) { - time_t timeout; int sk, ret; if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5)) @@ -450,11 +454,10 @@ static void try_to_add(const char *tst_name, unsigned int port, synchronize_threads(); /* preparations done */ - timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; - ret = _test_connect_socket(sk, this_ip_dest, port, timeout); + ret = test_skpair_connect_poll(sk, this_ip_dest, port, 0, &sk_pair); synchronize_threads(); /* connect()/accept() timeouts */ - if (ret <= 0) { + if (ret < 0) { test_error("%s: connect() returned %d", tst_name, ret); goto out; } @@ -490,8 +493,7 @@ static void try_to_add(const char *tst_name, unsigned int port, out: synchronize_threads(); /* test_kill_sk() */ - /* _test_connect_socket() cleans up on failure */ - if (ret > 0) + if (ret > 0) /* test_skpair_connect_poll() cleans up on failure */ test_kill_sk(sk); } diff --git a/tools/testing/selftests/net/test_blackhole_dev.sh b/tools/testing/selftests/net/test_blackhole_dev.sh deleted file mode 100755 index 3119b80e711f..000000000000 --- a/tools/testing/selftests/net/test_blackhole_dev.sh +++ /dev/null @@ -1,11 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# Runs blackhole-dev test using blackhole-dev kernel module - -if /sbin/modprobe -q test_blackhole_dev ; then - /sbin/modprobe -q -r test_blackhole_dev; - echo "test_blackhole_dev: ok"; -else - echo "test_blackhole_dev: [FAIL]"; - exit 1; -fi diff --git a/tools/testing/selftests/net/test_so_rcv.sh b/tools/testing/selftests/net/test_so_rcv.sh new file mode 100755 index 000000000000..d8aa4362879d --- /dev/null +++ b/tools/testing/selftests/net/test_so_rcv.sh @@ -0,0 +1,73 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +HOSTS=("127.0.0.1" "::1") +PORT=1234 +TOTAL_TESTS=0 +FAILED_TESTS=0 + +declare -A TESTS=( + ["SO_RCVPRIORITY"]="-P 2" + ["SO_RCVMARK"]="-M 3" +) + +check_result() { + ((TOTAL_TESTS++)) + if [ "$1" -ne 0 ]; then + ((FAILED_TESTS++)) + fi +} + +cleanup() +{ + cleanup_ns $NS +} + +trap cleanup EXIT + +setup_ns NS + +for HOST in "${HOSTS[@]}"; do + PROTOCOL="IPv4" + if [[ "$HOST" == "::1" ]]; then + PROTOCOL="IPv6" + fi + for test_name in "${!TESTS[@]}"; do + echo "Running $test_name test, $PROTOCOL" + arg=${TESTS[$test_name]} + + ip netns exec $NS ./so_rcv_listener $arg $HOST $PORT & + LISTENER_PID=$! + + sleep 0.5 + + if ! ip netns exec $NS ./cmsg_sender $arg $HOST $PORT; then + echo "Sender failed for $test_name, $PROTOCOL" + kill "$LISTENER_PID" 2>/dev/null + wait "$LISTENER_PID" + check_result 1 + continue + fi + + wait "$LISTENER_PID" + LISTENER_EXIT_CODE=$? + + if [ "$LISTENER_EXIT_CODE" -eq 0 ]; then + echo "Rcv test OK for $test_name, $PROTOCOL" + check_result 0 + else + echo "Rcv test FAILED for $test_name, $PROTOCOL" + check_result 1 + fi + done +done + +if [ "$FAILED_TESTS" -ne 0 ]; then + echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed" + exit ${KSFT_FAIL} +else + echo "OK - All $TOTAL_TESTS tests passed" + exit ${KSFT_PASS} +fi diff --git a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh index 2d442cdab11e..062f957950af 100755 --- a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh +++ b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh @@ -1,29 +1,114 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Check FDB default-remote handling across "ip link set". +ALL_TESTS=" + test_set_remote + test_change_mc_remote +" +source lib.sh check_remotes() { local what=$1; shift local N=$(bridge fdb sh dev vx | grep 00:00:00:00:00:00 | wc -l) - echo -ne "expected two remotes after $what\t" - if [[ $N != 2 ]]; then - echo "[FAIL]" - EXIT_STATUS=1 + ((N == 2)) + check_err $? "expected 2 remotes after $what, got $N" +} + +# Check FDB default-remote handling across "ip link set". +test_set_remote() +{ + RET=0 + + ip_link_add vx up type vxlan id 2000 dstport 4789 + bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent + bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent + check_remotes "fdb append" + + ip link set dev vx type vxlan remote 192.0.2.30 + check_remotes "link set" + + log_test 'FDB default-remote handling across "ip link set"' +} + +fmt_remote() +{ + local addr=$1; shift + + if [[ $addr == 224.* ]]; then + echo "group $addr" else - echo "[ OK ]" + echo "remote $addr" fi } -ip link add name vx up type vxlan id 2000 dstport 4789 -bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent -bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent -check_remotes "fdb append" +change_remote() +{ + local remote=$1; shift + + ip link set dev vx type vxlan $(fmt_remote $remote) dev v1 +} + +check_membership() +{ + local check_vec=("$@") + + local memberships + memberships=$( + netstat -n --groups | + sed -n '/^v1\b/p' | + grep -o '[^ ]*$' + ) + check_err $? "Couldn't obtain group memberships" + + local item + for item in "${check_vec[@]}"; do + eval "local $item" + echo "$memberships" | grep -q "\b$group\b" + check_err_fail $fail $? "$group is_ex reported in IGMP query response" + done +} + +test_change_mc_remote() +{ + check_command netstat || return + + ip_link_add v1 up type veth peer name v2 + ip_link_set_up v2 + + RET=0 + + ip_link_add vx up type vxlan dstport 4789 \ + local 192.0.2.1 $(fmt_remote 224.1.1.1) dev v1 vni 1000 + + check_membership "group=224.1.1.1 fail=0" \ + "group=224.1.1.2 fail=1" \ + "group=224.1.1.3 fail=1" + + log_test "MC group report after VXLAN creation" + + RET=0 + + change_remote 224.1.1.2 + check_membership "group=224.1.1.1 fail=1" \ + "group=224.1.1.2 fail=0" \ + "group=224.1.1.3 fail=1" + + log_test "MC group report after changing VXLAN remote MC->MC" + + RET=0 + + change_remote 192.0.2.2 + check_membership "group=224.1.1.1 fail=1" \ + "group=224.1.1.2 fail=1" \ + "group=224.1.1.3 fail=1" + + log_test "MC group report after changing VXLAN remote MC->UC" +} + +trap defer_scopes_cleanup EXIT -ip link set dev vx type vxlan remote 192.0.2.30 -check_remotes "link set" +tests_run -ip link del dev vx exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk index 12e7cae251be..e907c2751956 100644 --- a/tools/testing/selftests/net/ynl.mk +++ b/tools/testing/selftests/net/ynl.mk @@ -27,7 +27,8 @@ $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig: $(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig $(Q)rm -f $(top_srcdir)/tools/net/ynl/libynl.a - $(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl GENS="$(YNL_GENS)" libynl.a + $(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl \ + GENS="$(YNL_GENS)" RSTS="" libynl.a $(Q)cp $(top_srcdir)/tools/net/ynl/libynl.a $(OUTPUT)/libynl.a EXTRA_CLEAN += \ diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index 58064151f2c8..edc08a4433fd 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -140,6 +140,7 @@ static void usage(char *progname) " -H val set output phase to 'val' nanoseconds (requires -p)\n" " -w val set output pulse width to 'val' nanoseconds (requires -p)\n" " -P val enable or disable (val=1|0) the system clock PPS\n" + " -r open the ptp clock in readonly mode\n" " -s set the ptp clock time from the system time\n" " -S set the system time from the ptp clock time\n" " -t val shift the ptp clock time by 'val' seconds\n" @@ -188,6 +189,7 @@ int main(int argc, char *argv[]) int pin_index = -1, pin_func; int pps = -1; int seconds = 0; + int readonly = 0; int settime = 0; int channel = -1; clockid_t ext_clockid = CLOCK_REALTIME; @@ -200,7 +202,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xy:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xy:z"))) { switch (c) { case 'c': capabilities = 1; @@ -252,6 +254,9 @@ int main(int argc, char *argv[]) case 'P': pps = atoi(optarg); break; + case 'r': + readonly = 1; + break; case 's': settime = 1; break; @@ -308,7 +313,7 @@ int main(int argc, char *argv[]) } } - fd = open(device, O_RDWR); + fd = open(device, readonly ? O_RDONLY : O_RDWR); if (fd < 0) { fprintf(stderr, "opening %s: %s\n", device, strerror(errno)); return -1; @@ -436,14 +441,16 @@ int main(int argc, char *argv[]) } if (extts) { - memset(&extts_request, 0, sizeof(extts_request)); - extts_request.index = index; - extts_request.flags = PTP_ENABLE_FEATURE; - if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) { - perror("PTP_EXTTS_REQUEST"); - extts = 0; - } else { - puts("external time stamp request okay"); + if (!readonly) { + memset(&extts_request, 0, sizeof(extts_request)); + extts_request.index = index; + extts_request.flags = PTP_ENABLE_FEATURE; + if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) { + perror("PTP_EXTTS_REQUEST"); + extts = 0; + } else { + puts("external time stamp request okay"); + } } for (; extts; extts--) { cnt = read(fd, &event, sizeof(event)); @@ -455,10 +462,12 @@ int main(int argc, char *argv[]) event.t.sec, event.t.nsec); fflush(stdout); } - /* Disable the feature again. */ - extts_request.flags = 0; - if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) { - perror("PTP_EXTTS_REQUEST"); + if (!readonly) { + /* Disable the feature again. */ + extts_request.flags = 0; + if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) { + perror("PTP_EXTTS_REQUEST"); + } } } diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json index dd8109768f8f..5596f4df0e9f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -689,7 +689,7 @@ "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m continue index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action police index 1", - "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action continue", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action continue", "matchCount": "1", "teardown": [ "$TC actions flush action police" @@ -716,7 +716,7 @@ "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m drop index 1", "expExitCode": "0", "verifyCmd": "$TC actions ls action police", - "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action drop", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action drop", "matchCount": "1", "teardown": [ "$TC actions flush action police" @@ -743,7 +743,7 @@ "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m ok index 1", "expExitCode": "0", "verifyCmd": "$TC actions ls action police", - "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pass", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action pass", "matchCount": "1", "teardown": [ "$TC actions flush action police" @@ -770,7 +770,7 @@ "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m reclassify index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action police index 1", - "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action reclassify", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action reclassify", "matchCount": "1", "teardown": [ "$TC actions flush action police" @@ -797,7 +797,7 @@ "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m pipe index 1", "expExitCode": "0", "verifyCmd": "$TC actions ls action police", - "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pipe", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action pipe", "matchCount": "1", "teardown": [ "$TC actions flush action police" |