diff options
Diffstat (limited to 'tools/testing/selftests/drivers')
25 files changed, 1125 insertions, 380 deletions
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index f5c71d993750..8154d6d429d3 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -15,12 +15,6 @@ TEST_PROGS := \ hds.py \ napi_id.py \ napi_threaded.py \ - netcons_basic.sh \ - netcons_cmdline.sh \ - netcons_fragmented_msg.sh \ - netcons_overflow.sh \ - netcons_sysdata.sh \ - netcons_torture.sh \ netpoll_basic.py \ ping.py \ psp.py \ diff --git a/tools/testing/selftests/drivers/net/gro.c b/tools/testing/selftests/drivers/net/gro.c index e894037d2e3e..3c0745b68bfa 100644 --- a/tools/testing/selftests/drivers/net/gro.c +++ b/tools/testing/selftests/drivers/net/gro.c @@ -3,26 +3,45 @@ * This testsuite provides conformance testing for GRO coalescing. * * Test cases: - * 1.data + * + * data_*: * Data packets of the same size and same header setup with correct * sequence numbers coalesce. The one exception being the last data * packet coalesced: it can be smaller than the rest and coalesced * as long as it is in the same flow. - * 2.ack + * - data_same: same size packets coalesce + * - data_lrg_sml: large then small coalesces + * - data_sml_lrg: small then large doesn't coalesce + * + * ack: * Pure ACK does not coalesce. - * 3.flags - * Specific test cases: no packets with PSH, SYN, URG, RST set will - * be coalesced. - * 4.tcp + * + * flags_*: + * No packets with PSH, SYN, URG, RST, CWR set will be coalesced. + * - flags_psh, flags_syn, flags_rst, flags_urg, flags_cwr + * + * tcp_*: * Packets with incorrect checksum, non-consecutive seqno and * different TCP header options shouldn't coalesce. Nit: given that * some extension headers have paddings, such as timestamp, headers - * that are padding differently would not be coalesced. - * 5.ip: - * Packets with different (ECN, TTL, TOS) header, ip options or - * ip fragments (ipv6) shouldn't coalesce. - * 6.large: + * that are padded differently would not be coalesced. + * - tcp_csum: incorrect checksum + * - tcp_seq: non-consecutive sequence numbers + * - tcp_ts: different timestamps + * - tcp_opt: different TCP options + * + * ip_*: + * Packets with different (ECN, TTL, TOS) header, IP options or + * IP fragments shouldn't coalesce. + * - ip_ecn, ip_tos: shared between IPv4/IPv6 + * - ip_ttl, ip_opt, ip_frag4: IPv4 only + * - ip_id_df*: IPv4 IP ID field coalescing tests + * - ip_frag6, ip_v6ext_*: IPv6 only + * + * large_*: * Packets larger than GRO_MAX_SIZE packets shouldn't coalesce. + * - large_max: exceeding max size + * - large_rem: remainder handling * * MSS is defined as 4096 - header because if it is too small * (i.e. 1500 MTU - header), it will result in many packets, @@ -79,6 +98,15 @@ #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) /* calculate IPv6 extension header len */ #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) +enum flush_id_case { + FLUSH_ID_DF1_INC, + FLUSH_ID_DF1_FIXED, + FLUSH_ID_DF0_INC, + FLUSH_ID_DF0_FIXED, + FLUSH_ID_DF1_INC_FIXED, + FLUSH_ID_DF1_FIXED_INC, +}; + static const char *addr6_src = "fdaa::2"; static const char *addr6_dst = "fdaa::1"; static const char *addr4_src = "192.168.1.200"; @@ -95,7 +123,6 @@ static int tcp_offset = -1; static int total_hdr_len = -1; static int ethhdr_proto = -1; static bool ipip; -static const int num_flush_id_cases = 6; static void vlog(const char *fmt, ...) { @@ -127,19 +154,19 @@ static void setup_sock_filter(int fd) /* Overridden later if exthdrs are used: */ opt_ipproto_off = ipproto_off; - if (strcmp(testname, "ip") == 0) { - if (proto == PF_INET) - optlen = sizeof(struct ip_timestamp); - else { - BUILD_BUG_ON(sizeof(struct ip6_hbh) > MIN_EXTHDR_SIZE); - BUILD_BUG_ON(sizeof(struct ip6_dest) > MIN_EXTHDR_SIZE); - BUILD_BUG_ON(sizeof(struct ip6_frag) > MIN_EXTHDR_SIZE); - - /* same size for HBH and Fragment extension header types */ - optlen = MIN_EXTHDR_SIZE; - opt_ipproto_off = ETH_HLEN + sizeof(struct ipv6hdr) - + offsetof(struct ip6_ext, ip6e_nxt); - } + if (strcmp(testname, "ip_opt") == 0) { + optlen = sizeof(struct ip_timestamp); + } else if (strcmp(testname, "ip_frag6") == 0 || + strcmp(testname, "ip_v6ext_same") == 0 || + strcmp(testname, "ip_v6ext_diff") == 0) { + BUILD_BUG_ON(sizeof(struct ip6_hbh) > MIN_EXTHDR_SIZE); + BUILD_BUG_ON(sizeof(struct ip6_dest) > MIN_EXTHDR_SIZE); + BUILD_BUG_ON(sizeof(struct ip6_frag) > MIN_EXTHDR_SIZE); + + /* same size for HBH and Fragment extension header types */ + optlen = MIN_EXTHDR_SIZE; + opt_ipproto_off = ETH_HLEN + sizeof(struct ipv6hdr) + + offsetof(struct ip6_ext, ip6e_nxt); } /* this filter validates the following: @@ -333,32 +360,58 @@ static void create_packet(void *buf, int seq_offset, int ack_offset, fill_datalinklayer(buf); } -/* send one extra flag, not first and not last pkt */ -static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn, - int rst, int urg) +#ifndef TH_CWR +#define TH_CWR 0x80 +#endif +static void set_flags(struct tcphdr *tcph, int payload_len, int psh, int syn, + int rst, int urg, int cwr) { - static char flag_buf[MAX_HDR_LEN + PAYLOAD_LEN]; - static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; - int payload_len, pkt_size, flag, i; - struct tcphdr *tcph; - - payload_len = PAYLOAD_LEN * psh; - pkt_size = total_hdr_len + payload_len; - flag = NUM_PACKETS / 2; - - create_packet(flag_buf, flag * payload_len, 0, payload_len, 0); - - tcph = (struct tcphdr *)(flag_buf + tcp_offset); tcph->psh = psh; tcph->syn = syn; tcph->rst = rst; tcph->urg = urg; + if (cwr) + tcph->th_flags |= TH_CWR; + else + tcph->th_flags &= ~TH_CWR; tcph->check = 0; tcph->check = tcp_checksum(tcph, payload_len); +} + +/* send extra flags of the (NUM_PACKETS / 2) and (NUM_PACKETS / 2 - 1) + * pkts, not first and not last pkt + */ +static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn, + int rst, int urg, int cwr) +{ + static char flag_buf[2][MAX_HDR_LEN + PAYLOAD_LEN]; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + int payload_len, pkt_size, i; + struct tcphdr *tcph; + int flag[2]; + + payload_len = PAYLOAD_LEN * (psh || cwr); + pkt_size = total_hdr_len + payload_len; + flag[0] = NUM_PACKETS / 2; + flag[1] = NUM_PACKETS / 2 - 1; + + /* Create and configure packets with flags + */ + for (i = 0; i < 2; i++) { + if (flag[i] > 0) { + create_packet(flag_buf[i], flag[i] * payload_len, 0, + payload_len, 0); + tcph = (struct tcphdr *)(flag_buf[i] + tcp_offset); + set_flags(tcph, payload_len, psh, syn, rst, urg, cwr); + } + } for (i = 0; i < NUM_PACKETS + 1; i++) { - if (i == flag) { - write_packet(fd, flag_buf, pkt_size, daddr); + if (i == flag[0]) { + write_packet(fd, flag_buf[0], pkt_size, daddr); + continue; + } else if (i == flag[1] && cwr) { + write_packet(fd, flag_buf[1], pkt_size, daddr); continue; } create_packet(buf, i * PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); @@ -648,7 +701,8 @@ static void fix_ip4_checksum(struct iphdr *iph) iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); } -static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) +static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, + enum flush_id_case tcase) { static char buf1[MAX_HDR_LEN + PAYLOAD_LEN]; static char buf2[MAX_HDR_LEN + PAYLOAD_LEN]; @@ -667,7 +721,7 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) create_packet(buf3, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); switch (tcase) { - case 0: /* DF=1, Incrementing - should coalesce */ + case FLUSH_ID_DF1_INC: /* DF=1, Incrementing - should coalesce */ iph1->frag_off |= htons(IP_DF); iph1->id = htons(8); @@ -675,7 +729,7 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) iph2->id = htons(9); break; - case 1: /* DF=1, Fixed - should coalesce */ + case FLUSH_ID_DF1_FIXED: /* DF=1, Fixed - should coalesce */ iph1->frag_off |= htons(IP_DF); iph1->id = htons(8); @@ -683,7 +737,7 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) iph2->id = htons(8); break; - case 2: /* DF=0, Incrementing - should coalesce */ + case FLUSH_ID_DF0_INC: /* DF=0, Incrementing - should coalesce */ iph1->frag_off &= ~htons(IP_DF); iph1->id = htons(8); @@ -691,7 +745,7 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) iph2->id = htons(9); break; - case 3: /* DF=0, Fixed - should coalesce */ + case FLUSH_ID_DF0_FIXED: /* DF=0, Fixed - should coalesce */ iph1->frag_off &= ~htons(IP_DF); iph1->id = htons(8); @@ -699,9 +753,10 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) iph2->id = htons(8); break; - case 4: /* DF=1, two packets incrementing, and one fixed - should - * coalesce only the first two packets - */ + case FLUSH_ID_DF1_INC_FIXED: /* DF=1, two packets incrementing, and + * one fixed - should coalesce only the + * first two packets + */ iph1->frag_off |= htons(IP_DF); iph1->id = htons(8); @@ -713,9 +768,10 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) send_three = true; break; - case 5: /* DF=1, two packets fixed, and one incrementing - should - * coalesce only the first two packets - */ + case FLUSH_ID_DF1_FIXED_INC: /* DF=1, two packets fixed, and one + * incrementing - should coalesce only + * the first two packets + */ iph1->frag_off |= htons(IP_DF); iph1->id = htons(8); @@ -739,16 +795,6 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase) } } -static void test_flush_id(int fd, struct sockaddr_ll *daddr, char *fin_pkt) -{ - for (int i = 0; i < num_flush_id_cases; i++) { - sleep(1); - send_flush_id_case(fd, daddr, i); - sleep(1); - write_packet(fd, fin_pkt, total_hdr_len, daddr); - } -} - static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr, char *ext_data1, char *ext_data2) { static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; @@ -926,6 +972,28 @@ static void set_timeout(int fd) error(1, errno, "cannot set timeout, setsockopt failed"); } +static void set_rcvbuf(int fd) +{ + int bufsize = 1 * 1024 * 1024; /* 1 MB */ + + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &bufsize, sizeof(bufsize))) + error(1, errno, "cannot set rcvbuf size, setsockopt failed"); +} + +static void recv_error(int fd, int rcv_errno) +{ + struct tpacket_stats stats; + socklen_t len; + + len = sizeof(stats); + if (getsockopt(fd, SOL_PACKET, PACKET_STATISTICS, &stats, &len)) + error(1, errno, "can't get stats"); + + fprintf(stderr, "Socket stats: packets=%u, drops=%u\n", + stats.tp_packets, stats.tp_drops); + error(1, rcv_errno, "could not receive"); +} + static void check_recv_pkts(int fd, int *correct_payload, int correct_num_pkts) { @@ -950,7 +1018,7 @@ static void check_recv_pkts(int fd, int *correct_payload, ip_ext_len = 0; pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0); if (pkt_size < 0) - error(1, errno, "could not receive"); + recv_error(fd, errno); if (iph->version == 4) ip_ext_len = (iph->ihl - 5) * 4; @@ -1008,108 +1076,131 @@ static void gro_sender(void) daddr.sll_halen = ETH_ALEN; create_packet(fin_pkt, PAYLOAD_LEN * 2, 0, 0, 1); - if (strcmp(testname, "data") == 0) { + /* data sub-tests */ + if (strcmp(testname, "data_same") == 0) { send_data_pkts(txfd, &daddr, PAYLOAD_LEN, PAYLOAD_LEN); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - + } else if (strcmp(testname, "data_lrg_sml") == 0) { send_data_pkts(txfd, &daddr, PAYLOAD_LEN, PAYLOAD_LEN / 2); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - + } else if (strcmp(testname, "data_sml_lrg") == 0) { send_data_pkts(txfd, &daddr, PAYLOAD_LEN / 2, PAYLOAD_LEN); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* ack test */ } else if (strcmp(testname, "ack") == 0) { send_ack(txfd, &daddr); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - } else if (strcmp(testname, "flags") == 0) { - send_flags(txfd, &daddr, 1, 0, 0, 0); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - send_flags(txfd, &daddr, 0, 1, 0, 0); + /* flags sub-tests */ + } else if (strcmp(testname, "flags_psh") == 0) { + send_flags(txfd, &daddr, 1, 0, 0, 0, 0); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - send_flags(txfd, &daddr, 0, 0, 1, 0); + } else if (strcmp(testname, "flags_syn") == 0) { + send_flags(txfd, &daddr, 0, 1, 0, 0, 0); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - send_flags(txfd, &daddr, 0, 0, 0, 1); + } else if (strcmp(testname, "flags_rst") == 0) { + send_flags(txfd, &daddr, 0, 0, 1, 0, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "flags_urg") == 0) { + send_flags(txfd, &daddr, 0, 0, 0, 1, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "flags_cwr") == 0) { + send_flags(txfd, &daddr, 0, 0, 0, 0, 1); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - } else if (strcmp(testname, "tcp") == 0) { + + /* tcp sub-tests */ + } else if (strcmp(testname, "tcp_csum") == 0) { send_changed_checksum(txfd, &daddr); - /* Adding sleep before sending FIN so that it is not - * received prior to other packets. - */ usleep(fin_delay_us); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - + } else if (strcmp(testname, "tcp_seq") == 0) { send_changed_seq(txfd, &daddr); usleep(fin_delay_us); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - + } else if (strcmp(testname, "tcp_ts") == 0) { send_changed_ts(txfd, &daddr); usleep(fin_delay_us); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - + } else if (strcmp(testname, "tcp_opt") == 0) { send_diff_opt(txfd, &daddr); usleep(fin_delay_us); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - } else if (strcmp(testname, "ip") == 0) { + + /* ip sub-tests - shared between IPv4 and IPv6 */ + } else if (strcmp(testname, "ip_ecn") == 0) { send_changed_ECN(txfd, &daddr); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - + } else if (strcmp(testname, "ip_tos") == 0) { send_changed_tos(txfd, &daddr); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - if (proto == PF_INET) { - /* Modified packets may be received out of order. - * Sleep function added to enforce test boundaries - * so that fin pkts are not received prior to other pkts. - */ - sleep(1); - send_changed_ttl(txfd, &daddr); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - sleep(1); - send_ip_options(txfd, &daddr); - sleep(1); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - sleep(1); - send_fragment4(txfd, &daddr); - sleep(1); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - test_flush_id(txfd, &daddr, fin_pkt); - } else if (proto == PF_INET6) { - sleep(1); - send_fragment6(txfd, &daddr); - sleep(1); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - sleep(1); - /* send IPv6 packets with ext header with same payload */ - send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_1); - sleep(1); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - - sleep(1); - /* send IPv6 packets with ext header with different payload */ - send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_2); - sleep(1); - write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - } - } else if (strcmp(testname, "large") == 0) { - /* 20 is the difference between min iphdr size - * and min ipv6hdr size. Like MAX_HDR_SIZE, - * MAX_PAYLOAD is defined with the larger header of the two. - */ + + /* ip sub-tests - IPv4 only */ + } else if (strcmp(testname, "ip_ttl") == 0) { + send_changed_ttl(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_opt") == 0) { + send_ip_options(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_frag4") == 0) { + send_fragment4(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df1_inc") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF1_INC); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df1_fixed") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF1_FIXED); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df0_inc") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF0_INC); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df0_fixed") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF0_FIXED); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df1_inc_fixed") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF1_INC_FIXED); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df1_fixed_inc") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF1_FIXED_INC); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* ip sub-tests - IPv6 only */ + } else if (strcmp(testname, "ip_frag6") == 0) { + send_fragment6(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_v6ext_same") == 0) { + send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_1); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_v6ext_diff") == 0) { + send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_2); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* large sub-tests */ + } else if (strcmp(testname, "large_max") == 0) { int offset = (proto == PF_INET && !ipip) ? 20 : 0; int remainder = (MAX_PAYLOAD + offset) % MSS; send_large(txfd, &daddr, remainder); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "large_rem") == 0) { + int offset = (proto == PF_INET && !ipip) ? 20 : 0; + int remainder = (MAX_PAYLOAD + offset) % MSS; send_large(txfd, &daddr, remainder + 1); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else { - error(1, 0, "Unknown testcase"); + error(1, 0, "Unknown testcase: %s", testname); } if (close(txfd)) @@ -1126,132 +1217,166 @@ static void gro_receiver(void) error(1, 0, "socket creation"); setup_sock_filter(rxfd); set_timeout(rxfd); + set_rcvbuf(rxfd); bind_packetsocket(rxfd); ksft_ready(); memset(correct_payload, 0, sizeof(correct_payload)); - if (strcmp(testname, "data") == 0) { + /* data sub-tests */ + if (strcmp(testname, "data_same") == 0) { printf("pure data packet of same size: "); correct_payload[0] = PAYLOAD_LEN * 2; check_recv_pkts(rxfd, correct_payload, 1); - + } else if (strcmp(testname, "data_lrg_sml") == 0) { printf("large data packets followed by a smaller one: "); correct_payload[0] = PAYLOAD_LEN * 1.5; check_recv_pkts(rxfd, correct_payload, 1); - + } else if (strcmp(testname, "data_sml_lrg") == 0) { printf("small data packets followed by a larger one: "); correct_payload[0] = PAYLOAD_LEN / 2; correct_payload[1] = PAYLOAD_LEN; check_recv_pkts(rxfd, correct_payload, 2); + + /* ack test */ } else if (strcmp(testname, "ack") == 0) { printf("duplicate ack and pure ack: "); check_recv_pkts(rxfd, correct_payload, 3); - } else if (strcmp(testname, "flags") == 0) { + + /* flags sub-tests */ + } else if (strcmp(testname, "flags_psh") == 0) { correct_payload[0] = PAYLOAD_LEN * 3; correct_payload[1] = PAYLOAD_LEN * 2; - printf("psh flag ends coalescing: "); check_recv_pkts(rxfd, correct_payload, 2); - + } else if (strcmp(testname, "flags_syn") == 0) { correct_payload[0] = PAYLOAD_LEN * 2; correct_payload[1] = 0; correct_payload[2] = PAYLOAD_LEN * 2; printf("syn flag ends coalescing: "); check_recv_pkts(rxfd, correct_payload, 3); - + } else if (strcmp(testname, "flags_rst") == 0) { + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = 0; + correct_payload[2] = PAYLOAD_LEN * 2; printf("rst flag ends coalescing: "); check_recv_pkts(rxfd, correct_payload, 3); - + } else if (strcmp(testname, "flags_urg") == 0) { + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = 0; + correct_payload[2] = PAYLOAD_LEN * 2; printf("urg flag ends coalescing: "); check_recv_pkts(rxfd, correct_payload, 3); - } else if (strcmp(testname, "tcp") == 0) { + } else if (strcmp(testname, "flags_cwr") == 0) { correct_payload[0] = PAYLOAD_LEN; - correct_payload[1] = PAYLOAD_LEN; - correct_payload[2] = PAYLOAD_LEN; - correct_payload[3] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN * 2; + correct_payload[2] = PAYLOAD_LEN * 2; + printf("cwr flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); + /* tcp sub-tests */ + } else if (strcmp(testname, "tcp_csum") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; printf("changed checksum does not coalesce: "); check_recv_pkts(rxfd, correct_payload, 2); - + } else if (strcmp(testname, "tcp_seq") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; printf("Wrong Seq number doesn't coalesce: "); check_recv_pkts(rxfd, correct_payload, 2); - - printf("Different timestamp doesn't coalesce: "); + } else if (strcmp(testname, "tcp_ts") == 0) { correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + correct_payload[3] = PAYLOAD_LEN; + printf("Different timestamp doesn't coalesce: "); check_recv_pkts(rxfd, correct_payload, 4); - - printf("Different options doesn't coalesce: "); + } else if (strcmp(testname, "tcp_opt") == 0) { correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + printf("Different options doesn't coalesce: "); check_recv_pkts(rxfd, correct_payload, 2); - } else if (strcmp(testname, "ip") == 0) { + + /* ip sub-tests - shared between IPv4 and IPv6 */ + } else if (strcmp(testname, "ip_ecn") == 0) { correct_payload[0] = PAYLOAD_LEN; correct_payload[1] = PAYLOAD_LEN; - printf("different ECN doesn't coalesce: "); check_recv_pkts(rxfd, correct_payload, 2); - + } else if (strcmp(testname, "ip_tos") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; printf("different tos doesn't coalesce: "); check_recv_pkts(rxfd, correct_payload, 2); - if (proto == PF_INET) { - printf("different ttl doesn't coalesce: "); - check_recv_pkts(rxfd, correct_payload, 2); - - printf("ip options doesn't coalesce: "); - correct_payload[2] = PAYLOAD_LEN; - check_recv_pkts(rxfd, correct_payload, 3); - - printf("fragmented ip4 doesn't coalesce: "); - check_recv_pkts(rxfd, correct_payload, 2); - - /* is_atomic checks */ - printf("DF=1, Incrementing - should coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("DF=1, Fixed - should coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("DF=0, Incrementing - should coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("DF=0, Fixed - should coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("DF=1, 2 Incrementing and one fixed - should coalesce only first 2 packets: "); - correct_payload[0] = PAYLOAD_LEN * 2; - correct_payload[1] = PAYLOAD_LEN; - check_recv_pkts(rxfd, correct_payload, 2); - - printf("DF=1, 2 Fixed and one incrementing - should coalesce only first 2 packets: "); - correct_payload[0] = PAYLOAD_LEN * 2; - correct_payload[1] = PAYLOAD_LEN; - check_recv_pkts(rxfd, correct_payload, 2); - } else if (proto == PF_INET6) { - /* GRO doesn't check for ipv6 hop limit when flushing. - * Hence no corresponding test to the ipv4 case. - */ - printf("fragmented ip6 doesn't coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - correct_payload[1] = PAYLOAD_LEN; - correct_payload[2] = PAYLOAD_LEN; - check_recv_pkts(rxfd, correct_payload, 3); - - printf("ipv6 with ext header does coalesce: "); - correct_payload[0] = PAYLOAD_LEN * 2; - check_recv_pkts(rxfd, correct_payload, 1); - - printf("ipv6 with ext header with different payloads doesn't coalesce: "); - correct_payload[0] = PAYLOAD_LEN; - correct_payload[1] = PAYLOAD_LEN; - check_recv_pkts(rxfd, correct_payload, 2); - } - } else if (strcmp(testname, "large") == 0) { + /* ip sub-tests - IPv4 only */ + } else if (strcmp(testname, "ip_ttl") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + printf("different ttl doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ip_opt") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + printf("ip options doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "ip_frag4") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + printf("fragmented ip4 doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ip_id_df1_inc") == 0) { + printf("DF=1, Incrementing - should coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_id_df1_fixed") == 0) { + printf("DF=1, Fixed - should coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_id_df0_inc") == 0) { + printf("DF=0, Incrementing - should coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_id_df0_fixed") == 0) { + printf("DF=0, Fixed - should coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_id_df1_inc_fixed") == 0) { + printf("DF=1, 2 Incrementing and one fixed - should coalesce only first 2 packets: "); + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ip_id_df1_fixed_inc") == 0) { + printf("DF=1, 2 Fixed and one incrementing - should coalesce only first 2 packets: "); + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 2); + + /* ip sub-tests - IPv6 only */ + } else if (strcmp(testname, "ip_frag6") == 0) { + /* GRO doesn't check for ipv6 hop limit when flushing. + * Hence no corresponding test to the ipv4 case. + */ + printf("fragmented ip6 doesn't coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "ip_v6ext_same") == 0) { + printf("ipv6 with ext header does coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_v6ext_diff") == 0) { + printf("ipv6 with ext header with different payloads doesn't coalesce: "); + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 2); + + /* large sub-tests */ + } else if (strcmp(testname, "large_max") == 0) { int offset = (proto == PF_INET && !ipip) ? 20 : 0; int remainder = (MAX_PAYLOAD + offset) % MSS; @@ -1259,14 +1384,18 @@ static void gro_receiver(void) correct_payload[1] = remainder; printf("Shouldn't coalesce if exceed IP max pkt size: "); check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "large_rem") == 0) { + int offset = (proto == PF_INET && !ipip) ? 20 : 0; + int remainder = (MAX_PAYLOAD + offset) % MSS; /* last segment sent individually, doesn't start new segment */ - correct_payload[0] = correct_payload[0] - remainder; + correct_payload[0] = (MAX_PAYLOAD + offset) - remainder; correct_payload[1] = remainder + 1; correct_payload[2] = remainder + 1; + printf("last segment sent individually: "); check_recv_pkts(rxfd, correct_payload, 3); } else { - error(1, 0, "Test case error, should never trigger"); + error(1, 0, "Test case error: unknown testname %s", testname); } if (close(rxfd)) diff --git a/tools/testing/selftests/drivers/net/gro.py b/tools/testing/selftests/drivers/net/gro.py index ba83713bf7b5..cbc1b19dbc91 100755 --- a/tools/testing/selftests/drivers/net/gro.py +++ b/tools/testing/selftests/drivers/net/gro.py @@ -9,18 +9,36 @@ binary in different configurations and checking for correct packet coalescing behavior. Test cases: - - data: Data packets with same size/headers and correct seq numbers coalesce + - data_same: Same size data packets coalesce + - data_lrg_sml: Large packet followed by smaller one coalesces + - data_sml_lrg: Small packet followed by larger one doesn't coalesce - ack: Pure ACK packets do not coalesce - - flags: Packets with PSH, SYN, URG, RST flags do not coalesce - - tcp: Packets with incorrect checksum, non-consecutive seqno don't coalesce - - ip: Packets with different ECN, TTL, TOS, or IP options don't coalesce - - large: Packets larger than GRO_MAX_SIZE don't coalesce + - flags_psh: Packets with PSH flag don't coalesce + - flags_syn: Packets with SYN flag don't coalesce + - flags_rst: Packets with RST flag don't coalesce + - flags_urg: Packets with URG flag don't coalesce + - flags_cwr: Packets with CWR flag don't coalesce + - tcp_csum: Packets with incorrect checksum don't coalesce + - tcp_seq: Packets with non-consecutive seqno don't coalesce + - tcp_ts: Packets with different timestamp options don't coalesce + - tcp_opt: Packets with different TCP options don't coalesce + - ip_ecn: Packets with different ECN don't coalesce + - ip_tos: Packets with different TOS don't coalesce + - ip_ttl: (IPv4) Packets with different TTL don't coalesce + - ip_opt: (IPv4) Packets with IP options don't coalesce + - ip_frag4: (IPv4) IPv4 fragments don't coalesce + - ip_id_df*: (IPv4) IP ID field coalescing tests + - ip_frag6: (IPv6) IPv6 fragments don't coalesce + - ip_v6ext_same: (IPv6) IPv6 ext header with same payload coalesces + - ip_v6ext_diff: (IPv6) IPv6 ext header with different payload doesn't coalesce + - large_max: Packets exceeding GRO_MAX_SIZE don't coalesce + - large_rem: Large packet remainder handling """ import os from lib.py import ksft_run, ksft_exit, ksft_pr from lib.py import NetDrvEpEnv, KsftXfailEx -from lib.py import cmd, defer, bkg, ip +from lib.py import bkg, cmd, defer, ethtool, ip from lib.py import ksft_variants @@ -70,49 +88,150 @@ def _set_mtu_restore(dev, mtu, host): defer(ip, f"link set dev {dev['ifname']} mtu {dev['mtu']}", host=host) -def _setup(cfg, test_name): +def _set_ethtool_feat(dev, current, feats, host=None): + s2n = {True: "on", False: "off"} + + new = ["-K", dev] + old = ["-K", dev] + no_change = True + for name, state in feats.items(): + new += [name, s2n[state]] + old += [name, s2n[current[name]["active"]]] + + if current[name]["active"] != state: + no_change = False + if current[name]["fixed"]: + raise KsftXfailEx(f"Device does not support {name}") + if no_change: + return + + eth_cmd = ethtool(" ".join(new), host=host) + defer(ethtool, " ".join(old), host=host) + + # If ethtool printed something kernel must have modified some features + if eth_cmd.stdout: + ksft_pr(eth_cmd) + + +def _setup(cfg, mode, test_name): """ Setup hardware loopback mode for GRO testing. """ if not hasattr(cfg, "bin_remote"): cfg.bin_local = cfg.test_dir / "gro" cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) - # "large" test needs at least 4k MTU - if test_name == "large": + if not hasattr(cfg, "feat"): + cfg.feat = ethtool(f"-k {cfg.ifname}", json=True)[0] + cfg.remote_feat = ethtool(f"-k {cfg.remote_ifname}", + host=cfg.remote, json=True)[0] + + # "large_*" tests need at least 4k MTU + if test_name.startswith("large_"): _set_mtu_restore(cfg.dev, 4096, None) _set_mtu_restore(cfg.remote_dev, 4096, cfg.remote) - flush_path = f"/sys/class/net/{cfg.ifname}/gro_flush_timeout" - irq_path = f"/sys/class/net/{cfg.ifname}/napi_defer_hard_irqs" - - _write_defer_restore(cfg, flush_path, "200000", defer_undo=True) - _write_defer_restore(cfg, irq_path, "10", defer_undo=True) + if mode == "sw": + flush_path = f"/sys/class/net/{cfg.ifname}/gro_flush_timeout" + irq_path = f"/sys/class/net/{cfg.ifname}/napi_defer_hard_irqs" + + _write_defer_restore(cfg, flush_path, "200000", defer_undo=True) + _write_defer_restore(cfg, irq_path, "10", defer_undo=True) + + _set_ethtool_feat(cfg.ifname, cfg.feat, + {"generic-receive-offload": True, + "rx-gro-hw": False, + "large-receive-offload": False}) + elif mode == "hw": + _set_ethtool_feat(cfg.ifname, cfg.feat, + {"generic-receive-offload": False, + "rx-gro-hw": True, + "large-receive-offload": False}) + + # Some NICs treat HW GRO as a GRO sub-feature so disabling GRO + # will also clear HW GRO. Use a hack of installing XDP generic + # to skip SW GRO, even when enabled. + feat = ethtool(f"-k {cfg.ifname}", json=True)[0] + if not feat["rx-gro-hw"]["active"]: + ksft_pr("Driver clears HW GRO and SW GRO is cleared, using generic XDP workaround") + prog = cfg.net_lib_dir / "xdp_dummy.bpf.o" + ip(f"link set dev {cfg.ifname} xdpgeneric obj {prog} sec xdp") + defer(ip, f"link set dev {cfg.ifname} xdpgeneric off") + + # Attaching XDP may change features, fetch the latest state + feat = ethtool(f"-k {cfg.ifname}", json=True)[0] + + _set_ethtool_feat(cfg.ifname, feat, + {"generic-receive-offload": True, + "rx-gro-hw": True, + "large-receive-offload": False}) + elif mode == "lro": + # netdevsim advertises LRO for feature inheritance testing with + # bonding/team tests but it doesn't actually perform the offload + cfg.require_nsim(nsim_test=False) + + _set_ethtool_feat(cfg.ifname, cfg.feat, + {"generic-receive-offload": False, + "rx-gro-hw": False, + "large-receive-offload": True}) try: # Disable TSO for local tests cfg.require_nsim() # will raise KsftXfailEx if not running on nsim - cmd(f"ethtool -K {cfg.ifname} gro on tso off") - cmd(f"ethtool -K {cfg.remote_ifname} gro on tso off", host=cfg.remote) + _set_ethtool_feat(cfg.remote_ifname, cfg.remote_feat, + {"tcp-segmentation-offload": False}, + host=cfg.remote) except KsftXfailEx: pass + def _gro_variants(): """Generator that yields all combinations of protocol and test types.""" - for protocol in ["ipv4", "ipv6", "ipip"]: - for test_name in ["data", "ack", "flags", "tcp", "ip", "large"]: - yield protocol, test_name + # Tests that work for all protocols + common_tests = [ + "data_same", "data_lrg_sml", "data_sml_lrg", + "ack", + "flags_psh", "flags_syn", "flags_rst", "flags_urg", "flags_cwr", + "tcp_csum", "tcp_seq", "tcp_ts", "tcp_opt", + "ip_ecn", "ip_tos", + "large_max", "large_rem", + ] + + # Tests specific to IPv4 + ipv4_tests = [ + "ip_ttl", "ip_opt", "ip_frag4", + "ip_id_df1_inc", "ip_id_df1_fixed", + "ip_id_df0_inc", "ip_id_df0_fixed", + "ip_id_df1_inc_fixed", "ip_id_df1_fixed_inc", + ] + + # Tests specific to IPv6 + ipv6_tests = [ + "ip_frag6", "ip_v6ext_same", "ip_v6ext_diff", + ] + + for mode in ["sw", "hw", "lro"]: + for protocol in ["ipv4", "ipv6", "ipip"]: + for test_name in common_tests: + yield mode, protocol, test_name + + if protocol in ["ipv4", "ipip"]: + for test_name in ipv4_tests: + yield mode, protocol, test_name + elif protocol == "ipv6": + for test_name in ipv6_tests: + yield mode, protocol, test_name @ksft_variants(_gro_variants()) -def test(cfg, protocol, test_name): +def test(cfg, mode, protocol, test_name): """Run a single GRO test with retries.""" ipver = "6" if protocol[-1] == "6" else "4" cfg.require_ipver(ipver) - _setup(cfg, test_name) + _setup(cfg, mode, test_name) base_cmd_args = [ f"--{protocol}", @@ -142,10 +261,9 @@ def test(cfg, protocol, test_name): if rx_proc.ret == 0: return - ksft_pr(rx_proc.stdout.strip().replace('\n', '\n# ')) - ksft_pr(rx_proc.stderr.strip().replace('\n', '\n# ')) + ksft_pr(rx_proc) - if test_name == "large" and os.environ.get("KSFT_MACHINE_SLOW"): + if test_name.startswith("large_") and os.environ.get("KSFT_MACHINE_SLOW"): ksft_pr(f"Ignoring {protocol}/{test_name} failure due to slow environment") return diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 9c163ba6feee..a64140333a46 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -35,6 +35,7 @@ TEST_PROGS = \ pp_alloc_fail.py \ rss_api.py \ rss_ctx.py \ + rss_drv.py \ rss_flow_label.py \ rss_input_xfrm.py \ toeplitz.py \ diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c index 62456df947bc..240d13dbc54e 100644 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c @@ -12,6 +12,7 @@ #include <unistd.h> #include <arpa/inet.h> +#include <linux/mman.h> #include <linux/errqueue.h> #include <linux/if_packet.h> #include <linux/ipv6.h> @@ -37,6 +38,23 @@ #include <liburing.h> +#define SKIP_CODE 42 + +struct t_io_uring_zcrx_ifq_reg { + __u32 if_idx; + __u32 if_rxq; + __u32 rq_entries; + __u32 flags; + + __u64 area_ptr; /* pointer to struct io_uring_zcrx_area_reg */ + __u64 region_ptr; /* struct io_uring_region_desc * */ + + struct io_uring_zcrx_offsets offsets; + __u32 zcrx_id; + __u32 rx_buf_len; + __u64 __resv[3]; +}; + static long page_size; #define AREA_SIZE (8192 * page_size) #define SEND_SIZE (512 * 4096) @@ -65,6 +83,8 @@ static bool cfg_oneshot; static int cfg_oneshot_recvs; static int cfg_send_size = SEND_SIZE; static struct sockaddr_in6 cfg_addr; +static unsigned int cfg_rx_buf_len; +static bool cfg_dry_run; static char *payload; static void *area_ptr; @@ -128,14 +148,28 @@ static void setup_zcrx(struct io_uring *ring) if (!ifindex) error(1, 0, "bad interface name: %s", cfg_ifname); - area_ptr = mmap(NULL, - AREA_SIZE, - PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, - 0, - 0); - if (area_ptr == MAP_FAILED) - error(1, 0, "mmap(): zero copy area"); + if (cfg_rx_buf_len && cfg_rx_buf_len != page_size) { + area_ptr = mmap(NULL, + AREA_SIZE, + PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE | + MAP_HUGETLB | MAP_HUGE_2MB, + -1, + 0); + if (area_ptr == MAP_FAILED) { + printf("Can't allocate huge pages\n"); + exit(SKIP_CODE); + } + } else { + area_ptr = mmap(NULL, + AREA_SIZE, + PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, + 0, + 0); + if (area_ptr == MAP_FAILED) + error(1, 0, "mmap(): zero copy area"); + } ring_size = get_refill_ring_size(rq_entries); ring_ptr = mmap(NULL, @@ -157,17 +191,23 @@ static void setup_zcrx(struct io_uring *ring) .flags = 0, }; - struct io_uring_zcrx_ifq_reg reg = { + struct t_io_uring_zcrx_ifq_reg reg = { .if_idx = ifindex, .if_rxq = cfg_queue_id, .rq_entries = rq_entries, .area_ptr = (__u64)(unsigned long)&area_reg, .region_ptr = (__u64)(unsigned long)®ion_reg, + .rx_buf_len = cfg_rx_buf_len, }; - ret = io_uring_register_ifq(ring, ®); - if (ret) + ret = io_uring_register_ifq(ring, (void *)®); + if (cfg_rx_buf_len && (ret == -EINVAL || ret == -EOPNOTSUPP || + ret == -ERANGE)) { + printf("Large chunks are not supported %i\n", ret); + exit(SKIP_CODE); + } else if (ret) { error(1, 0, "io_uring_register_ifq(): %d", ret); + } rq_ring.khead = (unsigned int *)((char *)ring_ptr + reg.offsets.head); rq_ring.ktail = (unsigned int *)((char *)ring_ptr + reg.offsets.tail); @@ -323,6 +363,8 @@ static void run_server(void) io_uring_queue_init(512, &ring, flags); setup_zcrx(&ring); + if (cfg_dry_run) + return; add_accept(&ring, fd); @@ -383,7 +425,7 @@ static void parse_opts(int argc, char **argv) usage(argv[0]); cfg_payload_len = max_payload_len; - while ((c = getopt(argc, argv, "sch:p:l:i:q:o:z:")) != -1) { + while ((c = getopt(argc, argv, "sch:p:l:i:q:o:z:x:d")) != -1) { switch (c) { case 's': if (cfg_client) @@ -418,6 +460,12 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_send_size = strtoul(optarg, NULL, 0); break; + case 'x': + cfg_rx_buf_len = page_size * strtoul(optarg, NULL, 0); + break; + case 'd': + cfg_dry_run = true; + break; } } diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py index 712c806508b5..c63d6d6450d2 100755 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py @@ -3,104 +3,121 @@ import re from os import path -from lib.py import ksft_run, ksft_exit, KsftSkipEx +from lib.py import ksft_run, ksft_exit, KsftSkipEx, ksft_variants, KsftNamedVariant from lib.py import NetDrvEpEnv from lib.py import bkg, cmd, defer, ethtool, rand_port, wait_port_listen +from lib.py import EthtoolFamily +SKIP_CODE = 42 -def _get_current_settings(cfg): - output = ethtool(f"-g {cfg.ifname}", json=True)[0] - return (output['rx'], output['hds-thresh']) - - -def _get_combined_channels(cfg): - output = ethtool(f"-l {cfg.ifname}").stdout - values = re.findall(r'Combined:\s+(\d+)', output) - return int(values[1]) - - -def _create_rss_ctx(cfg, chan): - output = ethtool(f"-X {cfg.ifname} context new start {chan} equal 1").stdout +def create_rss_ctx(cfg): + output = ethtool(f"-X {cfg.ifname} context new start {cfg.target} equal 1").stdout values = re.search(r'New RSS context is (\d+)', output).group(1) - ctx_id = int(values) - return (ctx_id, defer(ethtool, f"-X {cfg.ifname} delete context {ctx_id}")) + return int(values) -def _set_flow_rule(cfg, port, chan): - output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} action {chan}").stdout +def set_flow_rule(cfg): + output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {cfg.port} action {cfg.target}").stdout values = re.search(r'ID (\d+)', output).group(1) return int(values) -def _set_flow_rule_rss(cfg, port, ctx_id): - output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} context {ctx_id}").stdout +def set_flow_rule_rss(cfg, rss_ctx_id): + output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {cfg.port} context {rss_ctx_id}").stdout values = re.search(r'ID (\d+)', output).group(1) return int(values) -def test_zcrx(cfg) -> None: - cfg.require_ipver('6') - - combined_chans = _get_combined_channels(cfg) - if combined_chans < 2: - raise KsftSkipEx('at least 2 combined channels required') - (rx_ring, hds_thresh) = _get_current_settings(cfg) - port = rand_port() - - ethtool(f"-G {cfg.ifname} tcp-data-split on") - defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto") +def single(cfg): + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + channels = channels['combined-count'] + if channels < 2: + raise KsftSkipEx('Test requires NETIF with at least 2 combined channels') - ethtool(f"-G {cfg.ifname} hds-thresh 0") - defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}") + rings = cfg.ethnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + rx_rings = rings['rx'] + hds_thresh = rings.get('hds-thresh', 0) - ethtool(f"-G {cfg.ifname} rx 64") - defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}") + cfg.ethnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled', + 'hds-thresh': 0, + 'rx': 64}) + defer(cfg.ethnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown', + 'hds-thresh': hds_thresh, + 'rx': rx_rings}) - ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") + cfg.target = channels - 1 + ethtool(f"-X {cfg.ifname} equal {cfg.target}") defer(ethtool, f"-X {cfg.ifname} default") - flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1) + flow_rule_id = set_flow_rule(cfg) defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" - tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840" - with bkg(rx_cmd, exit_wait=True): - wait_port_listen(port, proto="tcp") - cmd(tx_cmd, host=cfg.remote) +def rss(cfg): + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + channels = channels['combined-count'] + if channels < 2: + raise KsftSkipEx('Test requires NETIF with at least 2 combined channels') -def test_zcrx_oneshot(cfg) -> None: - cfg.require_ipver('6') + rings = cfg.ethnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + rx_rings = rings['rx'] + hds_thresh = rings.get('hds-thresh', 0) - combined_chans = _get_combined_channels(cfg) - if combined_chans < 2: - raise KsftSkipEx('at least 2 combined channels required') - (rx_ring, hds_thresh) = _get_current_settings(cfg) - port = rand_port() + cfg.ethnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled', + 'hds-thresh': 0, + 'rx': 64}) + defer(cfg.ethnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown', + 'hds-thresh': hds_thresh, + 'rx': rx_rings}) - ethtool(f"-G {cfg.ifname} tcp-data-split on") - defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto") + cfg.target = channels - 1 + ethtool(f"-X {cfg.ifname} equal {cfg.target}") + defer(ethtool, f"-X {cfg.ifname} default") - ethtool(f"-G {cfg.ifname} hds-thresh 0") - defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}") + rss_ctx_id = create_rss_ctx(cfg) + defer(ethtool, f"-X {cfg.ifname} delete context {rss_ctx_id}") - ethtool(f"-G {cfg.ifname} rx 64") - defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}") + flow_rule_id = set_flow_rule_rss(cfg, rss_ctx_id) + defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") - defer(ethtool, f"-X {cfg.ifname} default") - flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1) - defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") +@ksft_variants([ + KsftNamedVariant("single", single), + KsftNamedVariant("rss", rss), +]) +def test_zcrx(cfg, setup) -> None: + cfg.require_ipver('6') - rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -o 4" - tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 4096 -z 16384" + setup(cfg) + rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target}" + tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {cfg.port} -l 12840" with bkg(rx_cmd, exit_wait=True): - wait_port_listen(port, proto="tcp") + wait_port_listen(cfg.port, proto="tcp") cmd(tx_cmd, host=cfg.remote) -def test_zcrx_rss(cfg) -> None: +@ksft_variants([ + KsftNamedVariant("single", single), + KsftNamedVariant("rss", rss), +]) +def test_zcrx_oneshot(cfg, setup) -> None: + cfg.require_ipver('6') + + setup(cfg) + rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target} -o 4" + tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {cfg.port} -l 4096 -z 16384" + with bkg(rx_cmd, exit_wait=True): + wait_port_listen(cfg.port, proto="tcp") + cmd(tx_cmd, host=cfg.remote) + + +def test_zcrx_large_chunks(cfg) -> None: + """Test zcrx with large buffer chunks.""" + cfg.require_ipver('6') combined_chans = _get_combined_channels(cfg) @@ -121,12 +138,16 @@ def test_zcrx_rss(cfg) -> None: ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") defer(ethtool, f"-X {cfg.ifname} default") - (ctx_id, delete_ctx) = _create_rss_ctx(cfg, combined_chans - 1) - flow_rule_id = _set_flow_rule_rss(cfg, port, ctx_id) + flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1) defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" + rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -x 2" tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840" + + probe = cmd(rx_cmd + " -d", fail=False) + if probe.ret == SKIP_CODE: + raise KsftSkipEx(probe.stdout) + with bkg(rx_cmd, exit_wait=True): wait_port_listen(port, proto="tcp") cmd(tx_cmd, host=cfg.remote) @@ -137,7 +158,9 @@ def main() -> None: cfg.bin_local = path.abspath(path.dirname(__file__) + "/../../../drivers/net/hw/iou-zcrx") cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) - ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, )) + cfg.ethnl = EthtoolFamily() + cfg.port = rand_port() + ksft_run(globs=globals(), cases=[test_zcrx, test_zcrx_oneshot], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 3288ed04ce08..16864c844108 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -48,6 +48,7 @@ #include <errno.h> #define __iovec_defined #include <fcntl.h> +#include <limits.h> #include <malloc.h> #include <error.h> #include <poll.h> diff --git a/tools/testing/selftests/drivers/net/hw/nic_timestamp.py b/tools/testing/selftests/drivers/net/hw/nic_timestamp.py index c1e943d53f19..c632b41e7a23 100755 --- a/tools/testing/selftests/drivers/net/hw/nic_timestamp.py +++ b/tools/testing/selftests/drivers/net/hw/nic_timestamp.py @@ -1,15 +1,38 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +# pylint: disable=locally-disabled, invalid-name, attribute-defined-outside-init, too-few-public-methods """ Tests related to configuration of HW timestamping """ import errno +import ctypes +import fcntl +import socket from lib.py import ksft_run, ksft_exit, ksft_ge, ksft_eq, KsftSkipEx from lib.py import NetDrvEnv, EthtoolFamily, NlError +SIOCSHWTSTAMP = 0x89b0 +SIOCGHWTSTAMP = 0x89b1 +class hwtstamp_config(ctypes.Structure): + """ Python copy of struct hwtstamp_config """ + _fields_ = [ + ("flags", ctypes.c_int), + ("tx_type", ctypes.c_int), + ("rx_filter", ctypes.c_int), + ] + + +class ifreq(ctypes.Structure): + """ Python copy of struct ifreq """ + _fields_ = [ + ("ifr_name", ctypes.c_char * 16), + ("ifr_data", ctypes.POINTER(hwtstamp_config)), + ] + + def __get_hwtimestamp_support(cfg): """ Retrieve supported configuration information """ @@ -31,8 +54,29 @@ def __get_hwtimestamp_support(cfg): return ctx +def __get_hwtimestamp_config_ioctl(cfg): + """ Retrieve current TS configuration information (via ioctl) """ + + config = hwtstamp_config() + + req = ifreq() + req.ifr_name = cfg.ifname.encode() + req.ifr_data = ctypes.pointer(config) + + try: + sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM) + fcntl.ioctl(sock.fileno(), SIOCGHWTSTAMP, req) + sock.close() + + except OSError as e: + if e.errno == errno.EOPNOTSUPP: + raise KsftSkipEx("timestamping configuration is not supported via ioctl") from e + raise + return config + + def __get_hwtimestamp_config(cfg): - """ Retrieve current TS configuration information """ + """ Retrieve current TS configuration information (via netLink) """ try: tscfg = cfg.ethnl.tsconfig_get({'header': {'dev-name': cfg.ifname}}) @@ -43,8 +87,27 @@ def __get_hwtimestamp_config(cfg): return tscfg +def __set_hwtimestamp_config_ioctl(cfg, ts): + """ Setup new TS configuration information (via ioctl) """ + config = hwtstamp_config() + config.rx_filter = ts['rx-filters']['bits']['bit'][0]['index'] + config.tx_type = ts['tx-types']['bits']['bit'][0]['index'] + req = ifreq() + req.ifr_name = cfg.ifname.encode() + req.ifr_data = ctypes.pointer(config) + try: + sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM) + fcntl.ioctl(sock.fileno(), SIOCSHWTSTAMP, req) + sock.close() + + except OSError as e: + if e.errno == errno.EOPNOTSUPP: + raise KsftSkipEx("timestamping configuration is not supported via ioctl") from e + raise + + def __set_hwtimestamp_config(cfg, ts): - """ Setup new TS configuration information """ + """ Setup new TS configuration information (via netlink) """ ts['header'] = {'dev-name': cfg.ifname} try: @@ -56,9 +119,9 @@ def __set_hwtimestamp_config(cfg, ts): return res -def test_hwtstamp_tx(cfg): +def __perform_hwtstamp_tx(cfg, is_ioctl): """ - Test TX timestamp configuration. + Test TX timestamp configuration via either netlink or ioctl. The driver should apply provided config and report back proper state. """ @@ -66,16 +129,37 @@ def test_hwtstamp_tx(cfg): ts = __get_hwtimestamp_support(cfg) tx = ts['tx'] for t in tx: + res = None tscfg = orig_tscfg tscfg['tx-types']['bits']['bit'] = [t] - res = __set_hwtimestamp_config(cfg, tscfg) + if is_ioctl: + __set_hwtimestamp_config_ioctl(cfg, tscfg) + else: + res = __set_hwtimestamp_config(cfg, tscfg) if res is None: res = __get_hwtimestamp_config(cfg) + resioctl = __get_hwtimestamp_config_ioctl(cfg) ksft_eq(res['tx-types']['bits']['bit'], [t]) + ksft_eq(resioctl.tx_type, t['index']) __set_hwtimestamp_config(cfg, orig_tscfg) +def test_hwtstamp_tx_netlink(cfg): + """ + Test TX timestamp configuration setup via netlink. + The driver should apply provided config and report back proper state. + """ + __perform_hwtstamp_tx(cfg, False) + + +def test_hwtstamp_tx_ioctl(cfg): + """ + Test TX timestamp configuration setup via ioctl. + The driver should apply provided config and report back proper state. + """ + __perform_hwtstamp_tx(cfg, True) + -def test_hwtstamp_rx(cfg): +def __perform_hwtstamp_rx(cfg, is_ioctl): """ Test RX timestamp configuration. The filter configuration is taken from the list of supported filters. @@ -87,11 +171,17 @@ def test_hwtstamp_rx(cfg): ts = __get_hwtimestamp_support(cfg) rx = ts['rx'] for r in rx: + res = None tscfg = orig_tscfg tscfg['rx-filters']['bits']['bit'] = [r] - res = __set_hwtimestamp_config(cfg, tscfg) + if is_ioctl: + __set_hwtimestamp_config_ioctl(cfg, tscfg) + else: + res = __set_hwtimestamp_config(cfg, tscfg) if res is None: res = __get_hwtimestamp_config(cfg) + resioctl = __get_hwtimestamp_config_ioctl(cfg) + ksft_eq(resioctl.rx_filter, res['rx-filters']['bits']['bit'][0]['index']) if r['index'] == 0 or r['index'] == 1: ksft_eq(res['rx-filters']['bits']['bit'][0]['index'], r['index']) else: @@ -100,12 +190,34 @@ def test_hwtstamp_rx(cfg): __set_hwtimestamp_config(cfg, orig_tscfg) +def test_hwtstamp_rx_netlink(cfg): + """ + Test RX timestamp configuration via netlink. + The filter configuration is taken from the list of supported filters. + The driver should apply the config without error and report back proper state. + Some extension of the timestamping scope is allowed for PTP filters. + """ + __perform_hwtstamp_rx(cfg, False) + + +def test_hwtstamp_rx_ioctl(cfg): + """ + Test RX timestamp configuration via ioctl. + The filter configuration is taken from the list of supported filters. + The driver should apply the config without error and report back proper state. + Some extension of the timestamping scope is allowed for PTP filters. + """ + __perform_hwtstamp_rx(cfg, True) + + def main() -> None: """ Ksft boiler plate main """ with NetDrvEnv(__file__, nsim_test=False) as cfg: cfg.ethnl = EthtoolFamily() - ksft_run([test_hwtstamp_tx, test_hwtstamp_rx], args=(cfg,)) + ksft_run([test_hwtstamp_tx_ioctl, test_hwtstamp_tx_netlink, + test_hwtstamp_rx_ioctl, test_hwtstamp_rx_netlink], + args=(cfg,)) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/rss_drv.py b/tools/testing/selftests/drivers/net/hw/rss_drv.py new file mode 100755 index 000000000000..2d1a33189076 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/rss_drv.py @@ -0,0 +1,88 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Driver-related behavior tests for RSS. +""" + +from lib.py import ksft_run, ksft_exit, ksft_ge +from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx +from lib.py import defer, ethtool +from lib.py import EthtoolFamily, NlError +from lib.py import NetDrvEnv + + +def _is_power_of_two(n): + return n > 0 and (n & (n - 1)) == 0 + + +def _get_rss(cfg, context=0): + return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0] + + +def _test_rss_indir_size(cfg, qcnt, context=0): + """Test that indirection table size is at least 4x queue count.""" + ethtool(f"-L {cfg.ifname} combined {qcnt}") + + rss = _get_rss(cfg, context=context) + indir = rss['rss-indirection-table'] + ksft_ge(len(indir), 4 * qcnt, "Table smaller than 4x") + return len(indir) + + +def _maybe_create_context(cfg, create_context): + """ Either create a context and return its ID or return 0 for main ctx """ + if not create_context: + return 0 + try: + ctx = cfg.ethnl.rss_create_act({'header': {'dev-index': cfg.ifindex}}) + ctx_id = ctx['context'] + defer(cfg.ethnl.rss_delete_act, + {'header': {'dev-index': cfg.ifindex}, 'context': ctx_id}) + except NlError: + raise KsftSkipEx("Device does not support additional RSS contexts") + + return ctx_id + + +@ksft_variants([ + KsftNamedVariant("main", False), + KsftNamedVariant("ctx", True), +]) +def indir_size_4x(cfg, create_context): + """ + Test that the indirection table has at least 4 entries per queue. + Empirically network-heavy workloads like memcache suffer with the 33% + imbalance of a 2x indirection table size. + 4x table translates to a 16% imbalance. + """ + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + ch_max = channels.get('combined-max', 0) + qcnt = channels['combined-count'] + + if ch_max < 3: + raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}") + + defer(ethtool, f"-L {cfg.ifname} combined {qcnt}") + ethtool(f"-L {cfg.ifname} combined 3") + + ctx_id = _maybe_create_context(cfg, create_context) + + indir_sz = _test_rss_indir_size(cfg, 3, context=ctx_id) + + # Test with max queue count (max - 1 if max is a power of two) + test_max = ch_max - 1 if _is_power_of_two(ch_max) else ch_max + if test_max > 3 and indir_sz < test_max * 4: + _test_rss_indir_size(cfg, test_max, context=ctx_id) + + +def main() -> None: + """ Ksft boiler plate main """ + with NetDrvEnv(__file__) as cfg: + cfg.ethnl = EthtoolFamily() + ksft_run([indir_size_4x], args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/rss_flow_label.py b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py index 6fa95fe27c47..7dc80070884a 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_flow_label.py +++ b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py @@ -145,9 +145,14 @@ def test_rss_flow_label_6only(cfg): # Try to enable Flow Labels and check again, in case it leaks thru initial = _ethtool_get_cfg(cfg, "udp6") - changed = initial.replace("l", "") if "l" in initial else initial + "l" - - cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {changed}") + no_lbl = initial.replace("l", "") + if "l" not in initial: + try: + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 l{no_lbl}") + except CmdExitFailure as exc: + raise KsftSkipEx("Device doesn't support Flow Label for UDP6") from exc + else: + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {no_lbl}") restore = defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}") _check_v4_flow_types(cfg) diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py index 72880e388478..503f1a2a2872 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py +++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py @@ -5,9 +5,9 @@ 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 EthtoolFamily, NetdevFamily, NlError from lib.py import KsftSkipEx, KsftFailEx -from lib.py import rand_port +from lib.py import defer, ksft_pr, rand_port def traffic(cfg, local_port, remote_port, ipver): @@ -21,6 +21,40 @@ def traffic(cfg, local_port, remote_port, ipver): return sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU) +def _rss_input_xfrm_try_enable(cfg): + """ + Check if symmetric input-xfrm is already enabled, if not try to enable it + and register a cleanup. + """ + rss = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}) + orig_xfrm = rss.get('input-xfrm', set()) + sym_xfrm = set(filter(lambda x: 'sym' in x, orig_xfrm)) + + if sym_xfrm: + ksft_pr("Sym input xfrm already enabled:", sym_xfrm) + return sym_xfrm + + for xfrm in cfg.ethnl.consts["input-xfrm"].entries: + # Skip non-symmetric transforms + if "sym" not in xfrm: + continue + + try_xfrm = {xfrm} | orig_xfrm + try: + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "input-xfrm": try_xfrm}) + except NlError: + continue + + ksft_pr("Sym input xfrm configured:", try_xfrm) + defer(cfg.ethnl.rss_set, + {"header": {"dev-index": cfg.ifindex}, + "input-xfrm": orig_xfrm}) + return {xfrm} + + return set() + + def test_rss_input_xfrm(cfg, ipver): """ Test symmetric input_xfrm. @@ -37,12 +71,10 @@ def test_rss_input_xfrm(cfg, ipver): if not hasattr(socket, "SO_INCOMING_CPU"): raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11") - rss = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}) - input_xfrm = set(filter(lambda x: 'sym' in x, rss.get('input-xfrm', {}))) - # Check for symmetric xor/or-xor + input_xfrm = _rss_input_xfrm_try_enable(cfg) if not input_xfrm: - raise KsftSkipEx("Symmetric RSS hash not requested") + raise KsftSkipEx("Symmetric RSS hash not supported by device") cpus = set() successful = 0 diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.c b/tools/testing/selftests/drivers/net/hw/toeplitz.c index 285bb17df9c2..035bf908d8d9 100644 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.c +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.c @@ -59,7 +59,7 @@ #include "../../../net/lib/ksft.h" #define TOEPLITZ_KEY_MIN_LEN 40 -#define TOEPLITZ_KEY_MAX_LEN 60 +#define TOEPLITZ_KEY_MAX_LEN 256 #define TOEPLITZ_STR_LEN(K) (((K) * 3) - 1) /* hex encoded: AA:BB:CC:...:ZZ */ #define TOEPLITZ_STR_MIN_LEN TOEPLITZ_STR_LEN(TOEPLITZ_KEY_MIN_LEN) @@ -72,6 +72,8 @@ #define RPS_MAX_CPUS 16UL /* must be a power of 2 */ +#define MIN_PKT_SAMPLES 40 /* minimum number of packets to receive */ + /* configuration options (cmdline arguments) */ static uint16_t cfg_dport = 8000; static int cfg_family = AF_INET6; @@ -251,15 +253,31 @@ static bool recv_block(struct ring_state *ring) return true; } -/* simple test: sleep once unconditionally and then process all rings */ +/* simple test: process all rings until MIN_PKT_SAMPLES packets are received, + * or the test times out. + */ static void process_rings(void) { + struct timeval start, now; + bool pkts_found = true; + long elapsed_usec; int i; - usleep(1000 * cfg_timeout_msec); + gettimeofday(&start, NULL); - for (i = 0; i < num_cpus; i++) - do {} while (recv_block(&rings[i])); + do { + if (!pkts_found) + usleep(100); + + pkts_found = false; + for (i = 0; i < num_cpus; i++) + pkts_found |= recv_block(&rings[i]); + + gettimeofday(&now, NULL); + elapsed_usec = (now.tv_sec - start.tv_sec) * 1000000 + + (now.tv_usec - start.tv_usec); + } while (frames_received - frames_nohash < MIN_PKT_SAMPLES && + elapsed_usec < cfg_timeout_msec * 1000); fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n", frames_received - frames_nohash - frames_error, diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index 8b644fd84ff2..41cc248ac848 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -170,6 +170,7 @@ class NetDrvEpEnv(NetDrvEnvBase): self.remote_ifname = self.resolve_remote_ifc() self.remote_dev = ip("-d link show dev " + self.remote_ifname, host=self.remote, json=True)[0] + self.remote_ifindex = self.remote_dev['ifindex'] self._required_cmd = {} @@ -247,9 +248,12 @@ class NetDrvEpEnv(NetDrvEnvBase): if not self.addr_v[ipver] or not self.remote_addr_v[ipver]: raise KsftSkipEx(f"Test requires IPv{ipver} connectivity") - def require_nsim(self): - if self._ns is None: + def require_nsim(self, nsim_test=True): + """Require or exclude netdevsim for this test""" + if nsim_test and self._ns is None: raise KsftXfailEx("Test only works on netdevsim") + if nsim_test is False and self._ns is not None: + raise KsftXfailEx("Test does not work on netdevsim") 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 ae8abff4be40..b6093bcf2b06 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -203,19 +203,21 @@ function do_cleanup() { function cleanup_netcons() { # delete netconsole dynamic reconfiguration # do not fail if the target is already disabled - if [[ ! -d "${NETCONS_PATH}" ]] + local TARGET_PATH=${1:-${NETCONS_PATH}} + + if [[ ! -d "${TARGET_PATH}" ]] then # in some cases this is called before netcons path is created return fi - if [[ $(cat "${NETCONS_PATH}"/enabled) != 0 ]] + if [[ $(cat "${TARGET_PATH}"/enabled) != 0 ]] then - echo 0 > "${NETCONS_PATH}"/enabled || true + echo 0 > "${TARGET_PATH}"/enabled || true fi # Remove all the keys that got created during the selftest - find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete + find "${TARGET_PATH}/userdata/" -mindepth 1 -type d -delete # Remove the configfs entry - rmdir "${NETCONS_PATH}" + rmdir "${TARGET_PATH}" } function cleanup() { @@ -377,6 +379,29 @@ function check_netconsole_module() { fi } +function wait_target_state() { + local TARGET=${1} + local STATE=${2} + local TARGET_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" + local ENABLED=0 + + if [ "${STATE}" == "enabled" ] + then + ENABLED=1 + fi + + if [ ! -d "$TARGET_PATH" ]; then + echo "FAIL: Target does not exist." >&2 + exit "${ksft_fail}" + fi + + local CHECK_CMD="grep \"$ENABLED\" \"$TARGET_PATH/enabled\"" + slowwait 2 sh -c "test -n \"\$($CHECK_CMD)\"" || { + echo "FAIL: ${TARGET} is not ${STATE}." >&2 + exit "${ksft_fail}" + } +} + # A wrapper to translate protocol version to udp version function wait_for_port() { local NAMESPACE=${1} diff --git a/tools/testing/selftests/drivers/net/netconsole/Makefile b/tools/testing/selftests/drivers/net/netconsole/Makefile new file mode 100644 index 000000000000..b56c70b7e274 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netconsole/Makefile @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_INCLUDES := \ + ../../../net/lib.sh \ + ../lib/sh/lib_netcons.sh \ +# end of TEST_INCLUDES + +TEST_PROGS := \ + netcons_basic.sh \ + netcons_cmdline.sh \ + netcons_fragmented_msg.sh \ + netcons_overflow.sh \ + netcons_resume.sh \ + netcons_sysdata.sh \ + netcons_torture.sh \ +# end of TEST_PROGS + +include ../../../lib.mk + diff --git a/tools/testing/selftests/drivers/net/netconsole/config b/tools/testing/selftests/drivers/net/netconsole/config new file mode 100644 index 000000000000..a3f6b0fd44ef --- /dev/null +++ b/tools/testing/selftests/drivers/net/netconsole/config @@ -0,0 +1,6 @@ +CONFIG_CONFIGFS_FS=y +CONFIG_IPV6=y +CONFIG_NETCONSOLE=m +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_NETCONSOLE_EXTENDED_LOG=y +CONFIG_NETDEVSIM=m diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_basic.sh index 2022f3061738..59cf10013ecd 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_basic.sh @@ -18,7 +18,7 @@ set -euo pipefail SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh +source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh modprobe netdevsim 2> /dev/null || true modprobe netconsole 2> /dev/null || true diff --git a/tools/testing/selftests/drivers/net/netcons_cmdline.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh index d1d23dc67f99..96d704b8d9d9 100755 --- a/tools/testing/selftests/drivers/net/netcons_cmdline.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh @@ -12,7 +12,7 @@ set -euo pipefail SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh +source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh check_netconsole_module diff --git a/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh index 4a71e01a230c..0dc7280c3080 100755 --- a/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh @@ -16,7 +16,7 @@ set -euo pipefail SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh +source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh modprobe netdevsim 2> /dev/null || true modprobe netconsole 2> /dev/null || true diff --git a/tools/testing/selftests/drivers/net/netcons_overflow.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_overflow.sh index 06089643b771..a8e43d08c166 100755 --- a/tools/testing/selftests/drivers/net/netcons_overflow.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_overflow.sh @@ -13,7 +13,7 @@ set -euo pipefail SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh +source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh # This is coming from netconsole code. Check for it in drivers/net/netconsole.c MAX_USERDATA_ITEMS=256 diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh new file mode 100755 index 000000000000..cb59cf436dd0 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh @@ -0,0 +1,124 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This test validates that netconsole is able to resume a target that was +# deactivated when its interface was removed when the interface is brought +# back up. +# +# The test configures a netconsole target and then removes netdevsim module to +# cause the interface to disappear. Targets are configured via cmdline to ensure +# targets bound by interface name and mac address can be resumed. +# The test verifies that the target moved to disabled state before adding +# netdevsim and the interface back. +# +# Finally, the test verifies that the target is re-enabled automatically and +# the message is received on the destination interface. +# +# Author: Andre Carvalho <asantostc@gmail.com> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh + +SAVED_SRCMAC="" # to be populated later +SAVED_DSTMAC="" # to be populated later + +modprobe netdevsim 2> /dev/null || true +rmmod netconsole 2> /dev/null || true + +check_netconsole_module + +function cleanup() { + cleanup_netcons "${NETCONS_CONFIGFS}/cmdline0" + do_cleanup + rmmod netconsole +} + +function trigger_reactivation() { + # Add back low level module + modprobe netdevsim + # Recreate namespace and two interfaces + set_network + # Restore MACs + ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" \ + address "${SAVED_DSTMAC}" + if [ "${BINDMODE}" == "mac" ]; then + ip link set dev "${SRCIF}" down + ip link set dev "${SRCIF}" address "${SAVED_SRCMAC}" + # Rename device in order to trigger target resume, as initial + # when device was recreated it didn't have correct mac address. + ip link set dev "${SRCIF}" name "${TARGET}" + fi +} + +function trigger_deactivation() { + # Start by storing mac addresses so we can be restored in reactivate + SAVED_DSTMAC=$(ip netns exec "${NAMESPACE}" \ + cat /sys/class/net/"$DSTIF"/address) + SAVED_SRCMAC=$(mac_get "${SRCIF}") + # Remove low level module + rmmod netdevsim +} + +trap cleanup EXIT + +# Run the test twice, with different cmdline parameters +for BINDMODE in "ifname" "mac" +do + echo "Running with bind mode: ${BINDMODE}" >&2 + # Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) + echo "6 5" > /proc/sys/kernel/printk + + # Create one namespace and two interfaces + set_network + + # Create the command line for netconsole, with the configuration from + # the function above + CMDLINE=$(create_cmdline_str "${BINDMODE}") + + # The content of kmsg will be save to the following file + OUTPUT_FILE="/tmp/${TARGET}-${BINDMODE}" + + # Load the module, with the cmdline set + modprobe netconsole "${CMDLINE}" + # Expose cmdline target in configfs + mkdir "${NETCONS_CONFIGFS}/cmdline0" + + # Target should be enabled + wait_target_state "cmdline0" "enabled" + + # Trigger deactivation by unloading netdevsim module. Target should be + # disabled. + trigger_deactivation + wait_target_state "cmdline0" "disabled" + + # Trigger reactivation by loading netdevsim, recreating the network and + # restoring mac addresses. Target should be re-enabled. + trigger_reactivation + wait_target_state "cmdline0" "enabled" + + # Listen for netconsole port inside the namespace and destination + # interface + listen_port_and_save_to "${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 "${OUTPUT_FILE}" + # Make sure the message was received in the dst part + # and exit + validate_msg "${OUTPUT_FILE}" + + # kill socat in case it is still running + pkill_socat + # Cleanup & unload the module + cleanup + + echo "${BINDMODE} : Test passed" >&2 +done + +trap - EXIT +exit "${EXIT_STATUS}" diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh index baf69031089e..3fb8c4afe3d2 100755 --- a/tools/testing/selftests/drivers/net/netcons_sysdata.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh @@ -18,7 +18,7 @@ set -euo pipefail SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh +source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh # Enable the sysdata cpu_nr feature function set_cpu_nr() { diff --git a/tools/testing/selftests/drivers/net/netcons_torture.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_torture.sh index 2ce9ee3719d1..33a44adb6f8f 100755 --- a/tools/testing/selftests/drivers/net/netcons_torture.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_torture.sh @@ -17,7 +17,7 @@ set -euo pipefail SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh +source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh # Number of times the main loop run ITERATIONS=${1:-150} diff --git a/tools/testing/selftests/drivers/net/psp.py b/tools/testing/selftests/drivers/net/psp.py index 52523bdad240..864d9fce1094 100755 --- a/tools/testing/selftests/drivers/net/psp.py +++ b/tools/testing/selftests/drivers/net/psp.py @@ -266,6 +266,7 @@ def assoc_sk_only_mismatch(cfg): the_exception = cm.exception ksft_eq(the_exception.nl_msg.extack['bad-attr'], ".dev-id") ksft_eq(the_exception.nl_msg.error, -errno.EINVAL) + _close_conn(cfg, s) def assoc_sk_only_mismatch_tx(cfg): @@ -283,6 +284,7 @@ def assoc_sk_only_mismatch_tx(cfg): the_exception = cm.exception ksft_eq(the_exception.nl_msg.extack['bad-attr'], ".dev-id") ksft_eq(the_exception.nl_msg.error, -errno.EINVAL) + _close_conn(cfg, s) def assoc_sk_only_unconn(cfg): @@ -601,8 +603,8 @@ def main() -> None: cfg.comm_port = rand_port() srv = None try: - with bkg(responder + f" -p {cfg.comm_port}", host=cfg.remote, - exit_wait=True) as srv: + with bkg(responder + f" -p {cfg.comm_port} -i {cfg.remote_ifindex}", + host=cfg.remote, exit_wait=True) as srv: wait_port_listen(cfg.comm_port, host=cfg.remote) cfg.comm_sock = socket.create_connection((cfg.remote_addr, diff --git a/tools/testing/selftests/drivers/net/psp_responder.c b/tools/testing/selftests/drivers/net/psp_responder.c index f309e0d73cbf..a26e7628bbb1 100644 --- a/tools/testing/selftests/drivers/net/psp_responder.c +++ b/tools/testing/selftests/drivers/net/psp_responder.c @@ -22,7 +22,7 @@ static bool should_quit; struct opts { int port; - int devid; + int ifindex; bool verbose; }; @@ -360,7 +360,7 @@ static void usage(const char *name, const char *miss) if (miss) fprintf(stderr, "Missing argument: %s\n", miss); - fprintf(stderr, "Usage: %s -p port [-v] [-d psp-dev-id]\n", name); + fprintf(stderr, "Usage: %s -p port [-v] [-i ifindex]\n", name); exit(EXIT_FAILURE); } @@ -368,7 +368,7 @@ static void parse_cmd_opts(int argc, char **argv, struct opts *opts) { int opt; - while ((opt = getopt(argc, argv, "vp:d:")) != -1) { + while ((opt = getopt(argc, argv, "vp:i:")) != -1) { switch (opt) { case 'v': opts->verbose = 1; @@ -376,8 +376,8 @@ static void parse_cmd_opts(int argc, char **argv, struct opts *opts) case 'p': opts->port = atoi(optarg); break; - case 'd': - opts->devid = atoi(optarg); + case 'i': + opts->ifindex = atoi(optarg); break; default: usage(argv[0], NULL); @@ -410,12 +410,11 @@ static int psp_dev_set_ena(struct ynl_sock *ys, __u32 dev_id, __u32 versions) int main(int argc, char **argv) { struct psp_dev_get_list *dev_list; - bool devid_found = false; __u32 ver_ena, ver_cap; struct opts opts = {}; struct ynl_error yerr; struct ynl_sock *ys; - int first_id = 0; + int devid = -1; int ret; parse_cmd_opts(argc, argv, &opts); @@ -429,20 +428,19 @@ int main(int argc, char **argv) } dev_list = psp_dev_get_dump(ys); - if (ynl_dump_empty(dev_list)) { - if (ys->err.code) - goto err_close; - fprintf(stderr, "No PSP devices\n"); - goto err_close_silent; - } + if (ynl_dump_empty(dev_list) && ys->err.code) + goto err_close; ynl_dump_foreach(dev_list, d) { - if (opts.devid) { - devid_found = true; + if (opts.ifindex) { + if (d->ifindex != opts.ifindex) + continue; + devid = d->id; ver_ena = d->psp_versions_ena; ver_cap = d->psp_versions_cap; - } else if (!first_id) { - first_id = d->id; + break; + } else if (devid < 0) { + devid = d->id; ver_ena = d->psp_versions_ena; ver_cap = d->psp_versions_cap; } else { @@ -452,23 +450,21 @@ int main(int argc, char **argv) } psp_dev_get_list_free(dev_list); - if (opts.devid && !devid_found) { - fprintf(stderr, "PSP device %d requested on cmdline, not found\n", - opts.devid); - goto err_close_silent; - } else if (!opts.devid) { - opts.devid = first_id; - } + if (opts.ifindex && devid < 0) + fprintf(stderr, + "WARN: PSP device with ifindex %d requested on cmdline, not found\n", + opts.ifindex); - if (ver_ena != ver_cap) { - ret = psp_dev_set_ena(ys, opts.devid, ver_cap); + if (devid >= 0 && ver_ena != ver_cap) { + ret = psp_dev_set_ena(ys, devid, ver_cap); if (ret) goto err_close; } ret = run_responder(ys, &opts); - if (ver_ena != ver_cap && psp_dev_set_ena(ys, opts.devid, ver_ena)) + if (devid >= 0 && ver_ena != ver_cap && + psp_dev_set_ena(ys, devid, ver_ena)) fprintf(stderr, "WARN: failed to set the PSP versions back\n"); ynl_sock_destroy(ys); |