diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index af1f49ad8b88..db6bdc375126 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -17,7 +17,7 @@ #define BPF_ALU64 0x07 /* alu mode in double word width */ /* ld/ldx fields */ -#define BPF_DW 0x18 /* double word */ +#define BPF_DW 0x18 /* double word (64-bit) */ #define BPF_XADD 0xc0 /* exclusive add */ /* alu/jmp fields */ @@ -642,6 +642,14 @@ union bpf_attr { * @optlen: length of optval in bytes * Return: 0 or negative error * + * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) + * Set callback flags for sock_ops + * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct + * @flags: flags value + * Return: 0 for no error + * -EINVAL if there is no full tcp socket + * bits in flags that are not supported by current kernel + * * int bpf_skb_adjust_room(skb, len_diff, mode, flags) * Grow or shrink room in sk_buff. * @skb: pointer to skb @@ -748,7 +756,8 @@ union bpf_attr { FN(perf_event_read_value), \ FN(perf_prog_read_value), \ FN(getsockopt), \ - FN(override_return), + FN(override_return), \ + FN(sock_ops_cb_flags_set), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -952,8 +961,9 @@ struct bpf_map_info { struct bpf_sock_ops { __u32 op; union { - __u32 reply; - __u32 replylong[4]; + __u32 args[4]; /* Optionally passed to bpf program */ + __u32 reply; /* Returned by bpf program */ + __u32 replylong[4]; /* Optionally returned by bpf prog */ }; __u32 family; __u32 remote_ip4; /* Stored in network byte order */ @@ -968,8 +978,39 @@ struct bpf_sock_ops { */ __u32 snd_cwnd; __u32 srtt_us; /* Averaged RTT << 3 in usecs */ + __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */ + __u32 state; + __u32 rtt_min; + __u32 snd_ssthresh; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 mss_cache; + __u32 ecn_flags; + __u32 rate_delivered; + __u32 rate_interval_us; + __u32 packets_out; + __u32 retrans_out; + __u32 total_retrans; + __u32 segs_in; + __u32 data_segs_in; + __u32 segs_out; + __u32 data_segs_out; + __u32 lost_out; + __u32 sacked_out; + __u32 sk_txhash; + __u64 bytes_received; + __u64 bytes_acked; }; +/* Definitions for bpf_sock_ops_cb_flags */ +#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) +#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) +#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently + * supported cb flags + */ + /* List of known BPF sock_ops operators. * New entries can only be added at the end */ @@ -1003,6 +1044,43 @@ enum { * a congestion threshold. RTTs above * this indicate congestion */ + BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered. + * Arg1: value of icsk_retransmits + * Arg2: value of icsk_rto + * Arg3: whether RTO has expired + */ + BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted. + * Arg1: sequence number of 1st byte + * Arg2: # segments + * Arg3: return value of + * tcp_transmit_skb (0 => success) + */ + BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state. + * Arg1: old_state + * Arg2: new_state + */ +}; + +/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect + * changes between the TCP and BPF versions. Ideally this should never happen. + * If it does, we need to add code to convert them before calling + * the BPF sock_ops function. + */ +enum { + BPF_TCP_ESTABLISHED = 1, + BPF_TCP_SYN_SENT, + BPF_TCP_SYN_RECV, + BPF_TCP_FIN_WAIT1, + BPF_TCP_FIN_WAIT2, + BPF_TCP_TIME_WAIT, + BPF_TCP_CLOSE, + BPF_TCP_CLOSE_WAIT, + BPF_TCP_LAST_ACK, + BPF_TCP_LISTEN, + BPF_TCP_CLOSING, /* Now a valid state */ + BPF_TCP_NEW_SYN_RECV, + + BPF_TCP_MAX_STATES /* Leave at the end! */ }; #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 3a44b655d852..98688352208b 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -14,13 +14,13 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i LDLIBS += -lcap -lelf -lrt TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ - test_align test_verifier_log test_dev_cgroup + test_align test_verifier_log test_dev_cgroup test_tcpbpf_user TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ - sample_map_ret0.o + sample_map_ret0.o test_tcpbpf_kern.o TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \ test_offload.py diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 33cb00e46c49..dde2c11d7771 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -71,6 +71,8 @@ static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval, int optlen) = (void *) BPF_FUNC_getsockopt; +static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) = + (void *) BPF_FUNC_sock_ops_cb_flags_set; static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) = (void *) BPF_FUNC_sk_redirect_map; static int (*bpf_sock_map_update)(void *map, void *key, void *value, diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py new file mode 100755 index 000000000000..481dccdf140c --- /dev/null +++ b/tools/testing/selftests/bpf/tcp_client.py @@ -0,0 +1,51 @@ +#!/usr/bin/env python2 +# +# SPDX-License-Identifier: GPL-2.0 +# + +import sys, os, os.path, getopt +import socket, time +import subprocess +import select + +def read(sock, n): + buf = '' + while len(buf) < n: + rem = n - len(buf) + try: s = sock.recv(rem) + except (socket.error), e: return '' + buf += s + return buf + +def send(sock, s): + total = len(s) + count = 0 + while count < total: + try: n = sock.send(s) + except (socket.error), e: n = 0 + if n == 0: + return count; + count += n + return count + + +serverPort = int(sys.argv[1]) +HostName = socket.gethostname() + +# create active socket +sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) +try: + sock.connect((HostName, serverPort)) +except socket.error as e: + sys.exit(1) + +buf = '' +n = 0 +while n < 1000: + buf += '+' + n += 1 + +sock.settimeout(1); +n = send(sock, buf) +n = read(sock, 500) +sys.exit(0) diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py new file mode 100755 index 000000000000..bc454d7d0be2 --- /dev/null +++ b/tools/testing/selftests/bpf/tcp_server.py @@ -0,0 +1,83 @@ +#!/usr/bin/env python2 +# +# SPDX-License-Identifier: GPL-2.0 +# + +import sys, os, os.path, getopt +import socket, time +import subprocess +import select + +def read(sock, n): + buf = '' + while len(buf) < n: + rem = n - len(buf) + try: s = sock.recv(rem) + except (socket.error), e: return '' + buf += s + return buf + +def send(sock, s): + total = len(s) + count = 0 + while count < total: + try: n = sock.send(s) + except (socket.error), e: n = 0 + if n == 0: + return count; + count += n + return count + + +SERVER_PORT = 12877 +MAX_PORTS = 2 + +serverPort = SERVER_PORT +serverSocket = None + +HostName = socket.gethostname() + +# create passive socket +serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) +host = socket.gethostname() + +try: serverSocket.bind((host, 0)) +except socket.error as msg: + print 'bind fails: ', msg + +sn = serverSocket.getsockname() +serverPort = sn[1] + +cmdStr = ("./tcp_client.py %d &") % (serverPort) +os.system(cmdStr) + +buf = '' +n = 0 +while n < 500: + buf += '.' + n += 1 + +serverSocket.listen(MAX_PORTS) +readList = [serverSocket] + +while True: + readyRead, readyWrite, inError = \ + select.select(readList, [], [], 2) + + if len(readyRead) > 0: + waitCount = 0 + for sock in readyRead: + if sock == serverSocket: + (clientSocket, address) = serverSocket.accept() + address = str(address[0]) + readList.append(clientSocket) + else: + sock.settimeout(1); + s = read(sock, 1000) + n = send(sock, buf) + sock.close() + serverSocket.close() + sys.exit(0) + else: + print 'Select timeout!' + sys.exit(1) diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h new file mode 100644 index 000000000000..2fe43289943c --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpbpf.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef _TEST_TCPBPF_H +#define _TEST_TCPBPF_H + +struct tcpbpf_globals { + __u32 event_map; + __u32 total_retrans; + __u32 data_segs_in; + __u32 data_segs_out; + __u32 bad_cb_test_rv; + __u32 good_cb_test_rv; + __u64 bytes_received; + __u64 bytes_acked; +}; +#endif diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c new file mode 100644 index 000000000000..66bf71541903 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" +#include "bpf_endian.h" +#include "test_tcpbpf.h" + +struct bpf_map_def SEC("maps") global_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct tcpbpf_globals), + .max_entries = 2, +}; + +static inline void update_event_map(int event) +{ + __u32 key = 0; + struct tcpbpf_globals g, *gp; + + gp = bpf_map_lookup_elem(&global_map, &key); + if (gp == NULL) { + struct tcpbpf_globals g = {0}; + + g.event_map |= (1 << event); + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + } else { + g = *gp; + g.event_map |= (1 << event); + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + } +} + +int _version SEC("version") = 1; + +SEC("sockops") +int bpf_testcb(struct bpf_sock_ops *skops) +{ + int rv = -1; + int bad_call_rv = 0; + int good_call_rv = 0; + int op; + int v = 0; + + op = (int) skops->op; + + update_event_map(op); + + switch (op) { + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + /* Test failure to set largest cb flag (assumes not defined) */ + bad_call_rv = bpf_sock_ops_cb_flags_set(skops, 0x80); + /* Set callback */ + good_call_rv = bpf_sock_ops_cb_flags_set(skops, + BPF_SOCK_OPS_STATE_CB_FLAG); + /* Update results */ + { + __u32 key = 0; + struct tcpbpf_globals g, *gp; + + gp = bpf_map_lookup_elem(&global_map, &key); + if (!gp) + break; + g = *gp; + g.bad_cb_test_rv = bad_call_rv; + g.good_cb_test_rv = good_call_rv; + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + } + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + /* Set callback */ +// good_call_rv = bpf_sock_ops_cb_flags_set(skops, +// BPF_SOCK_OPS_STATE_CB_FLAG); + skops->sk_txhash = 0x12345f; + v = 0xff; + rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, + sizeof(v)); + break; + case BPF_SOCK_OPS_RTO_CB: + break; + case BPF_SOCK_OPS_RETRANS_CB: + break; + case BPF_SOCK_OPS_STATE_CB: + if (skops->args[1] == BPF_TCP_CLOSE) { + __u32 key = 0; + struct tcpbpf_globals g, *gp; + + gp = bpf_map_lookup_elem(&global_map, &key); + if (!gp) + break; + g = *gp; + g.total_retrans = skops->total_retrans; + g.data_segs_in = skops->data_segs_in; + g.data_segs_out = skops->data_segs_out; + g.bytes_received = skops->bytes_received; + g.bytes_acked = skops->bytes_acked; + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + } + break; + default: + rv = -1; + } + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c new file mode 100644 index 000000000000..95a370f3d378 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_util.h" +#include +#include "test_tcpbpf.h" + +static int bpf_find_map(const char *test, struct bpf_object *obj, + const char *name) +{ + struct bpf_map *map; + + map = bpf_object__find_map_by_name(obj, name); + if (!map) { + printf("%s:FAIL:map '%s' not found\n", test, name); + return -1; + } + return bpf_map__fd(map); +} + +#define SYSTEM(CMD) \ + do { \ + if (system(CMD)) { \ + printf("system(%s) FAILS!\n", CMD); \ + } \ + } while (0) + +int main(int argc, char **argv) +{ + const char *file = "test_tcpbpf_kern.o"; + struct tcpbpf_globals g = {0}; + int cg_fd, prog_fd, map_fd; + bool debug_flag = false; + int error = EXIT_FAILURE; + struct bpf_object *obj; + char cmd[100], *dir; + struct stat buffer; + __u32 key = 0; + int pid; + int rv; + + if (argc > 1 && strcmp(argv[1], "-d") == 0) + debug_flag = true; + + dir = "/tmp/cgroupv2/foo"; + + if (stat(dir, &buffer) != 0) { + SYSTEM("mkdir -p /tmp/cgroupv2"); + SYSTEM("mount -t cgroup2 none /tmp/cgroupv2"); + SYSTEM("mkdir -p /tmp/cgroupv2/foo"); + } + pid = (int) getpid(); + sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid); + SYSTEM(cmd); + + cg_fd = open(dir, O_DIRECTORY, O_RDONLY); + if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) { + printf("FAILED: load_bpf_file failed for: %s\n", file); + goto err; + } + + rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0); + if (rv) { + printf("FAILED: bpf_prog_attach: %d (%s)\n", + error, strerror(errno)); + goto err; + } + + SYSTEM("./tcp_server.py"); + + map_fd = bpf_find_map(__func__, obj, "global_map"); + if (map_fd < 0) + goto err; + + rv = bpf_map_lookup_elem(map_fd, &key, &g); + if (rv != 0) { + printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); + goto err; + } + + if (g.bytes_received != 501 || g.bytes_acked != 1002 || + g.data_segs_in != 1 || g.data_segs_out != 1 || + (g.event_map ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 || + g.good_cb_test_rv != 0) { + printf("FAILED: Wrong stats\n"); + if (debug_flag) { + printf("\n"); + printf("bytes_received: %d (expecting 501)\n", + (int)g.bytes_received); + printf("bytes_acked: %d (expecting 1002)\n", + (int)g.bytes_acked); + printf("data_segs_in: %d (expecting 1)\n", + g.data_segs_in); + printf("data_segs_out: %d (expecting 1)\n", + g.data_segs_out); + printf("event_map: 0x%x (at least 0x47e)\n", + g.event_map); + printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n", + g.bad_cb_test_rv); + printf("good_cb_test_rv:0x%x (expecting 0)\n", + g.good_cb_test_rv); + } + goto err; + } + printf("PASSED!\n"); + error = 0; +err: + bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); + return error; + +}