aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/include/uapi/asm-generic/socket.h2
-rwxr-xr-xtools/net/ynl/ynl-gen-c.py147
-rw-r--r--tools/testing/selftests/drivers/net/hw/ncdevmem.c3
-rw-r--r--tools/testing/selftests/drivers/net/lib/py/env.py9
-rw-r--r--tools/testing/selftests/net/Makefile2
-rw-r--r--tools/testing/selftests/net/busy_poller.c88
-rw-r--r--tools/testing/selftests/net/cmsg_sender.c11
-rwxr-xr-xtools/testing/selftests/net/cmsg_so_priority.sh151
-rwxr-xr-xtools/testing/selftests/net/fdb_notify.sh6
-rwxr-xr-xtools/testing/selftests/net/fib_rule_tests.sh31
-rw-r--r--tools/testing/selftests/net/forwarding/Makefile1
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh25
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh7
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_reserved.sh352
-rw-r--r--tools/testing/selftests/net/lib.sh68
-rw-r--r--tools/testing/selftests/net/lib/py/utils.py6
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt18
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt13
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt29
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt35
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt23
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt21
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt36
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt21
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt38
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt72
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt36
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt66
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt72
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt50
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt43
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt41
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt53
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt50
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt40
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt66
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt43
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt37
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt64
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt66
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt62
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt26
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt20
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt42
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt30
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt25
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt20
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt54
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt38
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt92
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt91
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt145
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt23
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt25
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt25
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt37
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt32
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt24
-rw-r--r--tools/testing/selftests/net/tls.c478
-rwxr-xr-xtools/testing/selftests/net/udpgso_bench.sh3
-rwxr-xr-xtools/testing/selftests/net/vlan_bridge_binding.sh256
-rwxr-xr-xtools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py21
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json20
-rw-r--r--tools/testing/vsock/README15
-rw-r--r--tools/testing/vsock/util.c33
-rw-r--r--tools/testing/vsock/util.h2
-rw-r--r--tools/testing/vsock/vsock_test.c265
67 files changed, 3734 insertions, 112 deletions
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index 281df9139d2b..ffff554a5230 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -126,6 +126,8 @@
#define SCM_TS_OPT_ID 78
+#define SO_RCVPRIORITY 79
+
#if !defined(__KERNEL__)
#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index d8201c4b1520..ec2288948795 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -801,6 +801,8 @@ class EnumSet(SpecEnumSet):
self.user_type = 'int'
self.value_pfx = yaml.get('name-prefix', f"{family.ident_name}-{yaml['name']}-")
+ self.header = yaml.get('header', None)
+ self.enum_cnt_name = yaml.get('enum-cnt-name', None)
super().__init__(family, yaml)
@@ -2417,6 +2419,87 @@ def uapi_enum_start(family, cw, obj, ckey='', enum_name='enum-name'):
cw.block_start(line=start_line)
+def render_uapi_unified(family, cw, max_by_define, separate_ntf):
+ max_name = c_upper(family.get('cmd-max-name', f"{family.op_prefix}MAX"))
+ cnt_name = c_upper(family.get('cmd-cnt-name', f"__{family.op_prefix}MAX"))
+ max_value = f"({cnt_name} - 1)"
+
+ uapi_enum_start(family, cw, family['operations'], 'enum-name')
+ val = 0
+ for op in family.msgs.values():
+ if separate_ntf and ('notify' in op or 'event' in op):
+ continue
+
+ suffix = ','
+ if op.value != val:
+ suffix = f" = {op.value},"
+ val = op.value
+ cw.p(op.enum_name + suffix)
+ val += 1
+ cw.nl()
+ cw.p(cnt_name + ('' if max_by_define else ','))
+ if not max_by_define:
+ cw.p(f"{max_name} = {max_value}")
+ cw.block_end(line=';')
+ if max_by_define:
+ cw.p(f"#define {max_name} {max_value}")
+ cw.nl()
+
+
+def render_uapi_directional(family, cw, max_by_define):
+ max_name = f"{family.op_prefix}USER_MAX"
+ cnt_name = f"__{family.op_prefix}USER_CNT"
+ max_value = f"({cnt_name} - 1)"
+
+ cw.block_start(line='enum')
+ cw.p(c_upper(f'{family.name}_MSG_USER_NONE = 0,'))
+ val = 0
+ for op in family.msgs.values():
+ if 'do' in op and 'event' not in op:
+ suffix = ','
+ if op.value and op.value != val:
+ suffix = f" = {op.value},"
+ val = op.value
+ cw.p(op.enum_name + suffix)
+ val += 1
+ cw.nl()
+ cw.p(cnt_name + ('' if max_by_define else ','))
+ if not max_by_define:
+ cw.p(f"{max_name} = {max_value}")
+ cw.block_end(line=';')
+ if max_by_define:
+ cw.p(f"#define {max_name} {max_value}")
+ cw.nl()
+
+ max_name = f"{family.op_prefix}KERNEL_MAX"
+ cnt_name = f"__{family.op_prefix}KERNEL_CNT"
+ max_value = f"({cnt_name} - 1)"
+
+ cw.block_start(line='enum')
+ cw.p(c_upper(f'{family.name}_MSG_KERNEL_NONE = 0,'))
+ val = 0
+ for op in family.msgs.values():
+ if ('do' in op and 'reply' in op['do']) or 'notify' in op or 'event' in op:
+ enum_name = op.enum_name
+ if 'event' not in op and 'notify' not in op:
+ enum_name = f'{enum_name}_REPLY'
+
+ suffix = ','
+ if op.value and op.value != val:
+ suffix = f" = {op.value},"
+ val = op.value
+ cw.p(enum_name + suffix)
+ val += 1
+ cw.nl()
+ cw.p(cnt_name + ('' if max_by_define else ','))
+ if not max_by_define:
+ cw.p(f"{max_name} = {max_value}")
+ cw.block_end(line=';')
+ if max_by_define:
+ cw.p(f"#define {max_name} {max_value}")
+ cw.nl()
+
+
def render_uapi(family, cw):
hdr_prot = f"_UAPI_LINUX_{c_upper(family.uapi_header_name)}_H"
hdr_prot = hdr_prot.replace('/', '_')
@@ -2440,6 +2523,9 @@ def render_uapi(family, cw):
if const['type'] == 'enum' or const['type'] == 'flags':
enum = family.consts[const['name']]
+ if enum.header:
+ continue
+
if enum.has_doc():
if enum.has_entry_doc():
cw.p('/**')
@@ -2472,9 +2558,12 @@ def render_uapi(family, cw):
max_val = f' = {enum.get_mask()},'
cw.p(max_name + max_val)
else:
+ cnt_name = enum.enum_cnt_name
max_name = c_upper(name_pfx + 'max')
- cw.p('__' + max_name + ',')
- cw.p(max_name + ' = (__' + max_name + ' - 1)')
+ if not cnt_name:
+ cnt_name = '__' + name_pfx + 'max'
+ cw.p(c_upper(cnt_name) + ',')
+ cw.p(max_name + ' = (' + c_upper(cnt_name) + ' - 1)')
cw.block_end(line=';')
cw.nl()
elif const['type'] == 'const':
@@ -2515,30 +2604,12 @@ def render_uapi(family, cw):
# Commands
separate_ntf = 'async-prefix' in family['operations']
- max_name = c_upper(family.get('cmd-max-name', f"{family.op_prefix}MAX"))
- cnt_name = c_upper(family.get('cmd-cnt-name', f"__{family.op_prefix}MAX"))
- max_value = f"({cnt_name} - 1)"
-
- uapi_enum_start(family, cw, family['operations'], 'enum-name')
- val = 0
- for op in family.msgs.values():
- if separate_ntf and ('notify' in op or 'event' in op):
- continue
-
- suffix = ','
- if op.value != val:
- suffix = f" = {op.value},"
- val = op.value
- cw.p(op.enum_name + suffix)
- val += 1
- cw.nl()
- cw.p(cnt_name + ('' if max_by_define else ','))
- if not max_by_define:
- cw.p(f"{max_name} = {max_value}")
- cw.block_end(line=';')
- if max_by_define:
- cw.p(f"#define {max_name} {max_value}")
- cw.nl()
+ if family.msg_id_model == 'unified':
+ render_uapi_unified(family, cw, max_by_define, separate_ntf)
+ elif family.msg_id_model == 'directional':
+ render_uapi_directional(family, cw, max_by_define)
+ else:
+ raise Exception(f'Unsupported message enum-model {family.msg_id_model}')
if separate_ntf:
uapi_enum_start(family, cw, family['operations'], enum_name='async-enum')
@@ -2635,7 +2706,8 @@ def find_kernel_root(full_path):
def main():
parser = argparse.ArgumentParser(description='Netlink simple parsing generator')
- parser.add_argument('--mode', dest='mode', type=str, required=True)
+ parser.add_argument('--mode', dest='mode', type=str, required=True,
+ choices=('user', 'kernel', 'uapi'))
parser.add_argument('--spec', dest='spec', type=str, required=True)
parser.add_argument('--header', dest='header', action='store_true', default=None)
parser.add_argument('--source', dest='header', action='store_false')
@@ -2662,13 +2734,6 @@ def main():
os.sys.exit(1)
return
- supported_models = ['unified']
- if args.mode in ['user', 'kernel']:
- supported_models += ['directional']
- if parsed.msg_id_model not in supported_models:
- print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation')
- os.sys.exit(1)
-
cw = CodeWriter(BaseNlLib(), args.out_file, overwrite=(not args.cmp_out))
_, spec_kernel = find_kernel_root(args.spec)
@@ -2696,7 +2761,10 @@ def main():
cw.p('#define ' + hdr_prot)
cw.nl()
- hdr_file=os.path.basename(args.out_file[:-2]) + ".h"
+ if args.out_file:
+ hdr_file = os.path.basename(args.out_file[:-2]) + ".h"
+ else:
+ hdr_file = "generated_header_file.h"
if args.mode == 'kernel':
cw.p('#include <net/netlink.h>')
@@ -2718,12 +2786,17 @@ def main():
else:
cw.p(f'#include "{hdr_file}"')
cw.p('#include "ynl.h"')
- headers = [parsed.uapi_header]
+ headers = []
for definition in parsed['definitions']:
if 'header' in definition:
headers.append(definition['header'])
+ if args.mode == 'user':
+ headers.append(parsed.uapi_header)
+ seen_header = []
for one in headers:
- cw.p(f"#include <{one}>")
+ if one not in seen_header:
+ cw.p(f"#include <{one}>")
+ seen_header.append(one)
cw.nl()
if args.mode == "user":
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 8e502a1f8f9b..19a6969643f4 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -619,9 +619,6 @@ int do_server(struct memory_buffer *mem)
fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
page_aligned_frags, non_page_aligned_frags);
- fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
- page_aligned_frags, non_page_aligned_frags);
-
cleanup:
free(tmp_mem);
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 1ea9bb695e94..fea343f209ea 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -5,7 +5,7 @@ import time
from pathlib import Path
from lib.py import KsftSkipEx, KsftXfailEx
from lib.py import ksft_setup
-from lib.py import cmd, ethtool, ip
+from lib.py import cmd, ethtool, ip, CmdExitFailure
from lib.py import NetNS, NetdevSimDev
from .remote import Remote
@@ -234,7 +234,12 @@ class NetDrvEpEnv:
Good drivers will tell us via ethtool what their sync period is.
"""
if self._stats_settle_time is None:
- data = ethtool("-c " + self.ifname, json=True)[0]
+ data = {}
+ try:
+ data = ethtool("-c " + self.ifname, json=True)[0]
+ except CmdExitFailure as e:
+ if "Operation not supported" not in e.cmd.stderr:
+ raise
self._stats_settle_time = 0.025 + \
data.get('stats-block-usecs', 0) / 1000 / 1000
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index cb2fc601de66..73ee88d6b043 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -32,6 +32,7 @@ TEST_PROGS += ioam6.sh
TEST_PROGS += gro.sh
TEST_PROGS += gre_gso.sh
TEST_PROGS += cmsg_so_mark.sh
+TEST_PROGS += cmsg_so_priority.sh
TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
TEST_PROGS += netns-name.sh
TEST_PROGS += nl_netdev.py
@@ -95,6 +96,7 @@ TEST_PROGS += test_bridge_backup_port.sh
TEST_PROGS += fdb_flush.sh fdb_notify.sh
TEST_PROGS += fq_band_pktlimit.sh
TEST_PROGS += vlan_hw_filter.sh
+TEST_PROGS += vlan_bridge_binding.sh
TEST_PROGS += bpf_offload.py
TEST_PROGS += ipv6_route_update_soft_lockup.sh
TEST_PROGS += busy_poll_test.sh
diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c
index 99b0e8c17fca..04c7ff577bb8 100644
--- a/tools/testing/selftests/net/busy_poller.c
+++ b/tools/testing/selftests/net/busy_poller.c
@@ -54,16 +54,16 @@ struct epoll_params {
#define EPIOCGPARAMS _IOR(EPOLL_IOC_TYPE, 0x02, struct epoll_params)
#endif
-static uint32_t cfg_port = 8000;
+static uint16_t cfg_port = 8000;
static struct in_addr cfg_bind_addr = { .s_addr = INADDR_ANY };
static char *cfg_outfile;
static int cfg_max_events = 8;
-static int cfg_ifindex;
+static uint32_t cfg_ifindex;
/* busy poll params */
static uint32_t cfg_busy_poll_usecs;
-static uint32_t cfg_busy_poll_budget;
-static uint32_t cfg_prefer_busy_poll;
+static uint16_t cfg_busy_poll_budget;
+static uint8_t cfg_prefer_busy_poll;
/* IRQ params */
static uint32_t cfg_defer_hard_irqs;
@@ -79,6 +79,7 @@ static void usage(const char *filepath)
static void parse_opts(int argc, char **argv)
{
+ unsigned long long tmp;
int ret;
int c;
@@ -86,31 +87,40 @@ static void parse_opts(int argc, char **argv)
usage(argv[0]);
while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) {
+ /* most options take integer values, except o and b, so reduce
+ * code duplication a bit for the common case by calling
+ * strtoull here and leave bounds checking and casting per
+ * option below.
+ */
+ if (c != 'o' && c != 'b')
+ tmp = strtoull(optarg, NULL, 0);
+
switch (c) {
case 'u':
- cfg_busy_poll_usecs = strtoul(optarg, NULL, 0);
- if (cfg_busy_poll_usecs == ULONG_MAX ||
- cfg_busy_poll_usecs > UINT32_MAX)
+ if (tmp == ULLONG_MAX || tmp > UINT32_MAX)
error(1, ERANGE, "busy_poll_usecs too large");
+
+ cfg_busy_poll_usecs = (uint32_t)tmp;
break;
case 'P':
- cfg_prefer_busy_poll = strtoul(optarg, NULL, 0);
- if (cfg_prefer_busy_poll == ULONG_MAX ||
- cfg_prefer_busy_poll > 1)
+ if (tmp == ULLONG_MAX || tmp > 1)
error(1, ERANGE,
"prefer busy poll should be 0 or 1");
+
+ cfg_prefer_busy_poll = (uint8_t)tmp;
break;
case 'g':
- cfg_busy_poll_budget = strtoul(optarg, NULL, 0);
- if (cfg_busy_poll_budget == ULONG_MAX ||
- cfg_busy_poll_budget > UINT16_MAX)
+ if (tmp == ULLONG_MAX || tmp > UINT16_MAX)
error(1, ERANGE,
"busy poll budget must be [0, UINT16_MAX]");
+
+ cfg_busy_poll_budget = (uint16_t)tmp;
break;
case 'p':
- cfg_port = strtoul(optarg, NULL, 0);
- if (cfg_port > UINT16_MAX)
+ if (tmp == ULLONG_MAX || tmp > UINT16_MAX)
error(1, ERANGE, "port must be <= 65535");
+
+ cfg_port = (uint16_t)tmp;
break;
case 'b':
ret = inet_aton(optarg, &cfg_bind_addr);
@@ -124,41 +134,39 @@ static void parse_opts(int argc, char **argv)
error(1, 0, "outfile invalid");
break;
case 'm':
- cfg_max_events = strtol(optarg, NULL, 0);
-
- if (cfg_max_events == LONG_MIN ||
- cfg_max_events == LONG_MAX ||
- cfg_max_events <= 0)
+ if (tmp == ULLONG_MAX || tmp > INT_MAX)
error(1, ERANGE,
- "max events must be > 0 and < LONG_MAX");
+ "max events must be > 0 and <= INT_MAX");
+
+ cfg_max_events = (int)tmp;
break;
case 'd':
- cfg_defer_hard_irqs = strtoul(optarg, NULL, 0);
-
- if (cfg_defer_hard_irqs == ULONG_MAX ||
- cfg_defer_hard_irqs > INT32_MAX)
+ if (tmp == ULLONG_MAX || tmp > INT32_MAX)
error(1, ERANGE,
"defer_hard_irqs must be <= INT32_MAX");
+
+ cfg_defer_hard_irqs = (uint32_t)tmp;
break;
case 'r':
- cfg_gro_flush_timeout = strtoull(optarg, NULL, 0);
-
- if (cfg_gro_flush_timeout == ULLONG_MAX)
+ if (tmp == ULLONG_MAX || tmp > UINT64_MAX)
error(1, ERANGE,
- "gro_flush_timeout must be < ULLONG_MAX");
+ "gro_flush_timeout must be < UINT64_MAX");
+
+ cfg_gro_flush_timeout = (uint64_t)tmp;
break;
case 's':
- cfg_irq_suspend_timeout = strtoull(optarg, NULL, 0);
-
- if (cfg_irq_suspend_timeout == ULLONG_MAX)
+ if (tmp == ULLONG_MAX || tmp > UINT64_MAX)
error(1, ERANGE,
"irq_suspend_timeout must be < ULLONG_MAX");
+
+ cfg_irq_suspend_timeout = (uint64_t)tmp;
break;
case 'i':
- cfg_ifindex = strtoul(optarg, NULL, 0);
- if (cfg_ifindex == ULONG_MAX)
+ if (tmp == ULLONG_MAX || tmp > INT_MAX)
error(1, ERANGE,
- "ifindex must be < ULONG_MAX");
+ "ifindex must be <= INT_MAX");
+
+ cfg_ifindex = (int)tmp;
break;
}
}
@@ -215,7 +223,7 @@ static void setup_queue(void)
struct netdev_napi_set_req *set_req = NULL;
struct ynl_sock *ys;
struct ynl_error yerr;
- uint32_t napi_id;
+ uint32_t napi_id = 0;
ys = ynl_sock_create(&ynl_netdev_family, &yerr);
if (!ys)
@@ -277,8 +285,8 @@ static void run_poller(void)
* here
*/
epoll_params.busy_poll_usecs = cfg_busy_poll_usecs;
- epoll_params.busy_poll_budget = (uint16_t)cfg_busy_poll_budget;
- epoll_params.prefer_busy_poll = (uint8_t)cfg_prefer_busy_poll;
+ epoll_params.busy_poll_budget = cfg_busy_poll_budget;
+ epoll_params.prefer_busy_poll = cfg_prefer_busy_poll;
epoll_params.__pad = 0;
val = 1;
@@ -342,5 +350,9 @@ int main(int argc, char *argv[])
parse_opts(argc, argv);
setup_queue();
run_poller();
+
+ if (cfg_outfile)
+ free(cfg_outfile);
+
return 0;
}
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index 876c2db02a63..bc314382e4e1 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -59,6 +59,7 @@ struct options {
unsigned int proto;
} sock;
struct option_cmsg_u32 mark;
+ struct option_cmsg_u32 priority;
struct {
bool ena;
unsigned int delay;
@@ -97,6 +98,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin)
"\n"
"\t\t-m val Set SO_MARK with given value\n"
"\t\t-M val Set SO_MARK via setsockopt\n"
+ "\t\t-P val Set SO_PRIORITY via setsockopt\n"
+ "\t\t-Q val Set SO_PRIORITY via cmsg\n"
"\t\t-d val Set SO_TXTIME with given delay (usec)\n"
"\t\t-t Enable time stamp reporting\n"
"\t\t-f val Set don't fragment via cmsg\n"
@@ -115,7 +118,7 @@ static void cs_parse_args(int argc, char *argv[])
{
int o;
- while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:")) != -1) {
+ while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:Q:")) != -1) {
switch (o) {
case 's':
opt.silent_send = true;
@@ -148,6 +151,10 @@ static void cs_parse_args(int argc, char *argv[])
opt.mark.ena = true;
opt.mark.val = atoi(optarg);
break;
+ case 'Q':
+ opt.priority.ena = true;
+ opt.priority.val = atoi(optarg);
+ break;
case 'M':
opt.sockopt.mark = atoi(optarg);
break;
@@ -253,6 +260,8 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
SOL_SOCKET, SO_MARK, &opt.mark);
ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+ SOL_SOCKET, SO_PRIORITY, &opt.priority);
+ ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag);
ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
SOL_IPV6, IPV6_TCLASS, &opt.v6.tclass);
diff --git a/tools/testing/selftests/net/cmsg_so_priority.sh b/tools/testing/selftests/net/cmsg_so_priority.sh
new file mode 100755
index 000000000000..ee07d8653262
--- /dev/null
+++ b/tools/testing/selftests/net/cmsg_so_priority.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+readonly KSFT_SKIP=4
+
+IP4=192.0.2.1/24
+TGT4=192.0.2.2
+TGT4_RAW=192.0.2.3
+IP6=2001:db8::1/64
+TGT6=2001:db8::2
+TGT6_RAW=2001:db8::3
+PORT=1234
+TOTAL_TESTS=0
+FAILED_TESTS=0
+
+if ! command -v jq &> /dev/null; then
+ echo "SKIP cmsg_so_priroity.sh test: jq is not installed." >&2
+ exit "$KSFT_SKIP"
+fi
+
+check_result() {
+ ((TOTAL_TESTS++))
+ if [ "$1" -ne 0 ]; then
+ ((FAILED_TESTS++))
+ fi
+}
+
+cleanup()
+{
+ cleanup_ns $NS
+}
+
+trap cleanup EXIT
+
+setup_ns NS
+
+create_filter() {
+ local handle=$1
+ local vlan_prio=$2
+ local ip_type=$3
+ local proto=$4
+ local dst_ip=$5
+ local ip_proto
+
+ if [[ "$proto" == "u" ]]; then
+ ip_proto="udp"
+ elif [[ "$ip_type" == "ipv4" && "$proto" == "i" ]]; then
+ ip_proto="icmp"
+ elif [[ "$ip_type" == "ipv6" && "$proto" == "i" ]]; then
+ ip_proto="icmpv6"
+ fi
+
+ tc -n $NS filter add dev dummy1 \
+ egress pref 1 handle "$handle" proto 802.1q \
+ flower vlan_prio "$vlan_prio" vlan_ethtype "$ip_type" \
+ dst_ip "$dst_ip" ${ip_proto:+ip_proto $ip_proto} \
+ action pass
+}
+
+ip -n $NS link set dev lo up
+ip -n $NS link add name dummy1 up type dummy
+
+ip -n $NS link add link dummy1 name dummy1.10 up type vlan id 10 \
+ egress-qos-map 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+ip -n $NS address add $IP4 dev dummy1.10
+ip -n $NS address add $IP6 dev dummy1.10 nodad
+
+ip netns exec $NS sysctl -wq net.ipv4.ping_group_range='0 2147483647'
+
+ip -n $NS neigh add $TGT4 lladdr 00:11:22:33:44:55 nud permanent \
+ dev dummy1.10
+ip -n $NS neigh add $TGT6 lladdr 00:11:22:33:44:55 nud permanent \
+ dev dummy1.10
+ip -n $NS neigh add $TGT4_RAW lladdr 00:11:22:33:44:66 nud permanent \
+ dev dummy1.10
+ip -n $NS neigh add $TGT6_RAW lladdr 00:11:22:33:44:66 nud permanent \
+ dev dummy1.10
+
+tc -n $NS qdisc add dev dummy1 clsact
+
+FILTER_COUNTER=10
+
+for i in 4 6; do
+ for proto in u i r; do
+ echo "Test IPV$i, prot: $proto"
+ for priority in {0..7}; do
+ if [[ $i == 4 && $proto == "r" ]]; then
+ TGT=$TGT4_RAW
+ elif [[ $i == 6 && $proto == "r" ]]; then
+ TGT=$TGT6_RAW
+ elif [ $i == 4 ]; then
+ TGT=$TGT4
+ else
+ TGT=$TGT6
+ fi
+
+ handle="${FILTER_COUNTER}${priority}"
+
+ create_filter $handle $priority ipv$i $proto $TGT
+
+ pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \
+ | jq ".[] | select(.options.handle == ${handle}) | \
+ .options.actions[0].stats.packets")
+
+ if [[ $pkts == 0 ]]; then
+ check_result 0
+ else
+ echo "prio $priority: expected 0, got $pkts"
+ check_result 1
+ fi
+
+ ip netns exec $NS ./cmsg_sender -$i -Q $priority \
+ -p $proto $TGT $PORT
+
+ pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \
+ | jq ".[] | select(.options.handle == ${handle}) | \
+ .options.actions[0].stats.packets")
+ if [[ $pkts == 1 ]]; then
+ check_result 0
+ else
+ echo "prio $priority -Q: expected 1, got $pkts"
+ check_result 1
+ fi
+
+ ip netns exec $NS ./cmsg_sender -$i -P $priority \
+ -p $proto $TGT $PORT
+
+ pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \
+ | jq ".[] | select(.options.handle == ${handle}) | \
+ .options.actions[0].stats.packets")
+ if [[ $pkts == 2 ]]; then
+ check_result 0
+ else
+ echo "prio $priority -P: expected 2, got $pkts"
+ check_result 1
+ fi
+ done
+ FILTER_COUNTER=$((FILTER_COUNTER + 10))
+ done
+done
+
+if [ $FAILED_TESTS -ne 0 ]; then
+ echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed"
+ exit 1
+else
+ echo "OK - All $TOTAL_TESTS tests passed"
+ exit 0
+fi
diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh
index c03151e7791c..c159230c9b62 100755
--- a/tools/testing/selftests/net/fdb_notify.sh
+++ b/tools/testing/selftests/net/fdb_notify.sh
@@ -49,7 +49,7 @@ test_dup_vxlan_self()
{
ip_link_add br up type bridge vlan_filtering 1
ip_link_add vx up type vxlan id 2000 dstport 4789
- ip_link_master vx br
+ ip_link_set_master vx br
do_test_dup add "vxlan" dev vx self dst 192.0.2.1
do_test_dup del "vxlan" dev vx self dst 192.0.2.1
@@ -59,7 +59,7 @@ test_dup_vxlan_master()
{
ip_link_add br up type bridge vlan_filtering 1
ip_link_add vx up type vxlan id 2000 dstport 4789
- ip_link_master vx br
+ ip_link_set_master vx br
do_test_dup add "vxlan master" dev vx master
do_test_dup del "vxlan master" dev vx master
@@ -79,7 +79,7 @@ test_dup_macvlan_master()
ip_link_add br up type bridge vlan_filtering 1
ip_link_add dd up type dummy
ip_link_add mv up link dd type macvlan mode passthru
- ip_link_master mv br
+ ip_link_set_master mv br
do_test_dup add "macvlan master" dev mv self
do_test_dup del "macvlan master" dev mv self
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 1d58b3b87465..847936363a12 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -291,6 +291,37 @@ fib_rule6_test()
"$getnomatch" "iif dscp redirect to table" \
"iif dscp no redirect to table"
fi
+
+ fib_check_iproute_support "flowlabel" "flowlabel"
+ if [ $? -eq 0 ]; then
+ match="flowlabel 0xfffff"
+ getmatch="flowlabel 0xfffff"
+ getnomatch="flowlabel 0xf"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "flowlabel redirect to table" \
+ "flowlabel no redirect to table"
+
+ match="flowlabel 0xfffff"
+ getmatch="from $SRC_IP6 iif $DEV flowlabel 0xfffff"
+ getnomatch="from $SRC_IP6 iif $DEV flowlabel 0xf"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "iif flowlabel redirect to table" \
+ "iif flowlabel no redirect to table"
+
+ match="flowlabel 0x08000/0x08000"
+ getmatch="flowlabel 0xfffff"
+ getnomatch="flowlabel 0xf7fff"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "flowlabel masked redirect to table" \
+ "flowlabel masked no redirect to table"
+
+ match="flowlabel 0x08000/0x08000"
+ getmatch="from $SRC_IP6 iif $DEV flowlabel 0xfffff"
+ getnomatch="from $SRC_IP6 iif $DEV flowlabel 0xf7fff"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "iif flowlabel masked redirect to table" \
+ "iif flowlabel masked no redirect to table"
+ fi
}
fib_rule6_vrf_test()
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 7d885cff8d79..00bde7b6f39e 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -105,6 +105,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \
vxlan_bridge_1q_port_8472_ipv6.sh \
vxlan_bridge_1q_port_8472.sh \
vxlan_bridge_1q.sh \
+ vxlan_reserved.sh \
vxlan_symmetric_ipv6.sh \
vxlan_symmetric.sh
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
index 1c8a26046589..2b5700b61ffa 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
@@ -1,7 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding pvid_change"
NUM_NETIFS=4
source lib.sh
@@ -77,12 +77,16 @@ cleanup()
ping_ipv4()
{
- ping_test $h1 192.0.2.2
+ local msg=$1
+
+ ping_test $h1 192.0.2.2 "$msg"
}
ping_ipv6()
{
- ping6_test $h1 2001:db8:1::2
+ local msg=$1
+
+ ping6_test $h1 2001:db8:1::2 "$msg"
}
learning()
@@ -95,6 +99,21 @@ flooding()
flood_test $swp2 $h1 $h2
}
+pvid_change()
+{
+ # Test that the changing of the VLAN-aware PVID does not affect
+ # VLAN-unaware forwarding
+ bridge vlan add vid 3 dev $swp1 pvid untagged
+
+ ping_ipv4 " with bridge port $swp1 PVID changed"
+ ping_ipv6 " with bridge port $swp1 PVID changed"
+
+ bridge vlan del vid 3 dev $swp1
+
+ ping_ipv4 " with bridge port $swp1 PVID deleted"
+ ping_ipv6 " with bridge port $swp1 PVID deleted"
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 7337f398f9cc..1fd40bada694 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -932,13 +932,6 @@ packets_rate()
echo $(((t1 - t0) / interval))
}
-mac_get()
-{
- local if_name=$1
-
- ip -j link show dev $if_name | jq -r '.[]["address"]'
-}
-
ether_addr_to_u64()
{
local addr="$1"
diff --git a/tools/testing/selftests/net/forwarding/vxlan_reserved.sh b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh
new file mode 100755
index 000000000000..46c31794b91b
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh
@@ -0,0 +1,352 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +--------------------+
+# | H1 (vrf) |
+# | + $h1 |
+# | | 192.0.2.1/28 |
+# +----|---------------+
+# |
+# +----|--------------------------------+
+# | SW | |
+# | +--|------------------------------+ |
+# | | + $swp1 BR1 (802.1d) | |
+# | | | |
+# | | + vx1 (vxlan) | |
+# | | local 192.0.2.17 | |
+# | | id 1000 dstport $VXPORT | |
+# | +---------------------------------+ |
+# | |
+# | 192.0.2.32/28 via 192.0.2.18 |
+# | |
+# | + $rp1 |
+# | | 192.0.2.17/28 |
+# +--|----------------------------------+
+# |
+# +--|----------------------------------+
+# | | |
+# | + $rp2 |
+# | 192.0.2.18/28 |
+# | |
+# | VRP2 (vrf) |
+# +-------------------------------------+
+
+: ${VXPORT:=4789}
+: ${ALL_TESTS:="
+ default_test
+ plain_test
+ reserved_0_test
+ reserved_10_test
+ reserved_31_test
+ reserved_56_test
+ reserved_63_test
+ "}
+
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+ defer simple_if_fini $h1 192.0.2.1/28
+
+ tc qdisc add dev $h1 clsact
+ defer tc qdisc del dev $h1 clsact
+
+ tc filter add dev $h1 ingress pref 77 \
+ prot ip flower skip_hw ip_proto icmp action drop
+ defer tc filter del dev $h1 ingress pref 77
+}
+
+switch_create()
+{
+ ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0
+ # Make sure the bridge uses the MAC address of the local port and not
+ # that of the VxLAN's device.
+ ip_link_set_addr br1 $(mac_get $swp1)
+ ip_link_set_up br1
+
+ ip_link_set_up $rp1
+ ip_addr_add $rp1 192.0.2.17/28
+ ip_route_add 192.0.2.32/28 nexthop via 192.0.2.18
+
+ ip_link_set_master $swp1 br1
+ ip_link_set_up $swp1
+}
+
+vrp2_create()
+{
+ simple_if_init $rp2 192.0.2.18/28
+ defer simple_if_fini $rp2 192.0.2.18/28
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ rp1=${NETIFS[p3]}
+ rp2=${NETIFS[p4]}
+
+ vrf_prepare
+ defer vrf_cleanup
+
+ forwarding_enable
+ defer forwarding_restore
+
+ h1_create
+ switch_create
+
+ vrp2_create
+}
+
+vxlan_header_bytes()
+{
+ local vni=$1; shift
+ local -a extra_bits=("$@")
+ local -a bits
+ local i
+
+ for ((i=0; i < 64; i++)); do
+ bits[i]=0
+ done
+
+ # Bit 4 is the I flag and is always on.
+ bits[4]=1
+
+ for i in ${extra_bits[@]}; do
+ bits[i]=1
+ done
+
+ # Bits 32..55 carry the VNI
+ local mask=0x800000
+ for ((i=0; i < 24; i++)); do
+ bits[$((i + 32))]=$(((vni & mask) != 0))
+ ((mask >>= 1))
+ done
+
+ local bytes
+ for ((i=0; i < 8; i++)); do
+ local byte=0
+ local j
+ for ((j=0; j < 8; j++)); do
+ local bit=${bits[8 * i + j]}
+ ((byte += bit << (7 - j)))
+ done
+ bytes+=$(printf %02x $byte):
+ done
+
+ echo ${bytes%:}
+}
+
+neg_bytes()
+{
+ local bytes=$1; shift
+
+ local -A neg=([0]=f [1]=e [2]=d [3]=c [4]=b [5]=a [6]=9 [7]=8
+ [8]=7 [9]=6 [a]=5 [b]=4 [c]=3 [d]=2 [e]=1 [f]=0 [:]=:)
+ local out
+ local i
+
+ for ((i=0; i < ${#bytes}; i++)); do
+ local c=${bytes:$i:1}
+ out+=${neg[$c]}
+ done
+ echo $out
+}
+
+vxlan_ping_do()
+{
+ local count=$1; shift
+ local dev=$1; shift
+ local next_hop_mac=$1; shift
+ local dest_ip=$1; shift
+ local dest_mac=$1; shift
+ local vni=$1; shift
+ local reserved_bits=$1; shift
+
+ local vxlan_header=$(vxlan_header_bytes $vni $reserved_bits)
+
+ $MZ $dev -c $count -d 100msec -q \
+ -b $next_hop_mac -B $dest_ip \
+ -t udp sp=23456,dp=$VXPORT,p=$(:
+ )"$vxlan_header:"$( : VXLAN
+ )"$dest_mac:"$( : ETH daddr
+ )"00:11:22:33:44:55:"$( : ETH saddr
+ )"08:00:"$( : ETH type
+ )"45:"$( : IP version + IHL
+ )"00:"$( : IP TOS
+ )"00:54:"$( : IP total length
+ )"99:83:"$( : IP identification
+ )"40:00:"$( : IP flags + frag off
+ )"40:"$( : IP TTL
+ )"01:"$( : IP proto
+ )"00:00:"$( : IP header csum
+ )"$(ipv4_to_bytes 192.0.2.3):"$( : IP saddr
+ )"$(ipv4_to_bytes 192.0.2.1):"$( : IP daddr
+ )"08:"$( : ICMP type
+ )"00:"$( : ICMP code
+ )"8b:f2:"$( : ICMP csum
+ )"1f:6a:"$( : ICMP request identifier
+ )"00:01:"$( : ICMP request seq. number
+ )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload
+ )"6d:74:0b:00:00:00:00:00:"$( :
+ )"10:11:12:13:14:15:16:17:"$( :
+ )"18:19:1a:1b:1c:1d:1e:1f:"$( :
+ )"20:21:22:23:24:25:26:27:"$( :
+ )"28:29:2a:2b:2c:2d:2e:2f:"$( :
+ )"30:31:32:33:34:35:36:37"
+}
+
+vxlan_device_add()
+{
+ ip_link_add vx1 up type vxlan id 1000 \
+ local 192.0.2.17 dstport "$VXPORT" \
+ nolearning noudpcsum tos inherit ttl 100 "$@"
+ ip_link_set_master vx1 br1
+}
+
+vxlan_all_reserved_bits()
+{
+ local i
+
+ for ((i=0; i < 64; i++)); do
+ if ((i == 4 || i >= 32 && i < 56)); then
+ continue
+ fi
+ echo $i
+ done
+}
+
+vxlan_ping_vanilla()
+{
+ vxlan_ping_do 10 $rp2 $(mac_get $rp1) 192.0.2.17 $(mac_get $h1) 1000
+}
+
+vxlan_ping_reserved()
+{
+ for bit in $(vxlan_all_reserved_bits); do
+ vxlan_ping_do 1 $rp2 $(mac_get $rp1) \
+ 192.0.2.17 $(mac_get $h1) 1000 "$bit"
+ ((n++))
+ done
+}
+
+vxlan_ping_test()
+{
+ local what=$1; shift
+ local get_stat=$1; shift
+ local expect=$1; shift
+
+ RET=0
+
+ local t0=$($get_stat)
+
+ "$@"
+ check_err $? "Failure when running $@"
+
+ local t1=$($get_stat)
+ local delta=$((t1 - t0))
+
+ ((expect == delta))
+ check_err $? "Expected to capture $expect packets, got $delta."
+
+ log_test "$what"
+}
+
+__default_test_do()
+{
+ local n_allowed_bits=$1; shift
+ local what=$1; shift
+
+ vxlan_ping_test "$what: clean packets" \
+ "tc_rule_stats_get $h1 77 ingress" \
+ 10 vxlan_ping_vanilla
+
+ local t0=$(link_stats_get vx1 rx errors)
+ vxlan_ping_test "$what: mangled packets" \
+ "tc_rule_stats_get $h1 77 ingress" \
+ $n_allowed_bits vxlan_ping_reserved
+ local t1=$(link_stats_get vx1 rx errors)
+
+ RET=0
+ local expect=$((39 - n_allowed_bits))
+ local delta=$((t1 - t0))
+ ((expect == delta))
+ check_err $? "Expected $expect error packets, got $delta."
+ log_test "$what: drops reported"
+}
+
+default_test_do()
+{
+ vxlan_device_add
+ __default_test_do 0 "Default"
+}
+
+default_test()
+{
+ in_defer_scope \
+ default_test_do
+}
+
+plain_test_do()
+{
+ vxlan_device_add reserved_bits 0xf7ffffff000000ff
+ __default_test_do 0 "reserved_bits 0xf7ffffff000000ff"
+}
+
+plain_test()
+{
+ in_defer_scope \
+ plain_test_do
+}
+
+reserved_test()
+{
+ local bit=$1; shift
+
+ local allowed_bytes=$(vxlan_header_bytes 0xffffff $bit)
+ local reserved_bytes=$(neg_bytes $allowed_bytes)
+ local reserved_bits=${reserved_bytes//:/}
+
+ vxlan_device_add reserved_bits 0x$reserved_bits
+ __default_test_do 1 "reserved_bits 0x$reserved_bits"
+}
+
+reserved_0_test()
+{
+ in_defer_scope \
+ reserved_test 0
+}
+
+reserved_10_test()
+{
+ in_defer_scope \
+ reserved_test 10
+}
+
+reserved_31_test()
+{
+ in_defer_scope \
+ reserved_test 31
+}
+
+reserved_56_test()
+{
+ in_defer_scope \
+ reserved_test 56
+}
+
+reserved_63_test()
+{
+ in_defer_scope \
+ reserved_test 63
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 8994fec1c38f..0bd9a038a1f0 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -435,6 +435,13 @@ xfail_on_veth()
fi
}
+mac_get()
+{
+ local if_name=$1
+
+ ip -j link show dev $if_name | jq -r '.[]["address"]'
+}
+
kill_process()
{
local pid=$1; shift
@@ -451,7 +458,7 @@ ip_link_add()
defer ip link del dev "$name"
}
-ip_link_master()
+ip_link_set_master()
{
local member=$1; shift
local master=$1; shift
@@ -459,3 +466,62 @@ ip_link_master()
ip link set dev "$member" master "$master"
defer ip link set dev "$member" nomaster
}
+
+ip_link_set_addr()
+{
+ local name=$1; shift
+ local addr=$1; shift
+
+ local old_addr=$(mac_get "$name")
+ ip link set dev "$name" address "$addr"
+ defer ip link set dev "$name" address "$old_addr"
+}
+
+ip_link_is_up()
+{
+ local name=$1; shift
+
+ local state=$(ip -j link show "$name" |
+ jq -r '(.[].flags[] | select(. == "UP")) // "DOWN"')
+ [[ $state == "UP" ]]
+}
+
+ip_link_set_up()
+{
+ local name=$1; shift
+
+ if ! ip_link_is_up "$name"; then
+ ip link set dev "$name" up
+ defer ip link set dev "$name" down
+ fi
+}
+
+ip_link_set_down()
+{
+ local name=$1; shift
+
+ if ip_link_is_up "$name"; then
+ ip link set dev "$name" down
+ defer ip link set dev "$name" up
+ fi
+}
+
+ip_addr_add()
+{
+ local name=$1; shift
+
+ ip addr add dev "$name" "$@"
+ defer ip addr del dev "$name" "$@"
+}
+
+ip_route_add()
+{
+ ip route add "$@"
+ defer ip route del "$@"
+}
+
+bridge_vlan_add()
+{
+ bridge vlan add "$@"
+ defer bridge vlan del "$@"
+}
diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py
index 72590c3f90f1..9e3bcddcf3e8 100644
--- a/tools/testing/selftests/net/lib/py/utils.py
+++ b/tools/testing/selftests/net/lib/py/utils.py
@@ -10,7 +10,9 @@ import time
class CmdExitFailure(Exception):
- pass
+ def __init__(self, msg, cmd_obj):
+ super().__init__(msg)
+ self.cmd = cmd_obj
class cmd:
@@ -48,7 +50,7 @@ class cmd:
if len(stderr) > 0 and stderr[-1] == "\n":
stderr = stderr[:-1]
raise CmdExitFailure("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" %
- (self.proc.args, stdout, stderr))
+ (self.proc.args, stdout, stderr), self)
class bkg(cmd):
diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt
new file mode 100644
index 000000000000..38535701656e
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test for blocking accept.
+
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+ +0...0.200 accept(3, ..., ...) = 4
+
+ +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 257
+
+ +.1 write(4, ..., 2000) = 2000
+ +0 > P. 1:2001(2000) ack 1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt
new file mode 100644
index 000000000000..3692ef102381
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test for blocking connect.
+
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+
+ +.1...0.200 connect(3, ..., ...) = 0
+
+ +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
+ +.1 < S. 0:0(0) ack 1 win 5792 <mss 1460,nop,wscale 2,nop,nop,sackOK>
+ +0 > . 1:1(0) ack 1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt
new file mode 100644
index 000000000000..914eabab367a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test for blocking read.
+--tolerance_usecs=10000
+
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 257
+ +0 accept(3, ..., ...) = 4
+
+ +0...0.100 read(4, ..., 2000) = 2000
+ +.1 < P. 1:2001(2000) ack 1 win 257
+ +0 > . 1:1(0) ack 2001
+
+ +.1...0.200 read(4, ..., 2000) = 2000
+ +.1 < P. 2001:4001(2000) ack 1 win 257
+ +0 > . 1:1(0) ack 4001
+
+ +.1 < P. 4001:6001(2000) ack 1 win 257
+ +0 > . 1:1(0) ack 6001
+ +0...0.000 read(4, ..., 1000) = 1000
+ +0...0.000 read(4, ..., 1000) = 1000
diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt
new file mode 100644
index 000000000000..cec5a0725d95
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test for blocking write.
+--tolerance_usecs=10000
+
+`./defaults.sh
+./set_sysctls.py /proc/sys/net/ipv4/tcp_min_tso_segs=10
+`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +.1 < S 0:0(0) win 50000 <mss 1000,nop,wscale 0>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 50000
+ +0 accept(3, ..., ...) = 4
+
+// Kernel doubles our value -> sk->sk_sndbuf is set to 42000
+ +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [21000], 4) = 0
+ +0 getsockopt(4, SOL_SOCKET, SO_SNDBUF, [42000], [4]) = 0
+
+// A write of 60000 does not block.
+ +0...0.300 write(4, ..., 61000) = 61000 // this write() blocks
+
+ +.1 < . 1:1(0) ack 10001 win 50000
+
+ +.1 < . 1:1(0) ack 30001 win 50000
+
+// This ACK should wakeup the write(). An ACK of 35001 does not.
+ +.1 < . 1:1(0) ack 36001 win 50000
+
+// Reset to sysctls defaults.
+`/tmp/sysctl_restore_${PPID}.sh`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt
new file mode 100644
index 000000000000..8514d6bdbb6d
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test basic connection teardown where local process closes first:
+// the local process calls close() first, so we send a FIN, and receive an ACK.
+// Then we receive a FIN and ACK it.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +.01...0.011 connect(3, ..., ...) = 0
+ +0 > S 0:0(0) <...>
+ +0 < S. 0:0(0) ack 1 win 32768 <mss 1000,nop,wscale 6,nop,nop,sackOK>
+ +0 > . 1:1(0) ack 1
+
+ +0 write(3, ..., 1000) = 1000
+ +0 > P. 1:1001(1000) ack 1
+ +0 < . 1:1(0) ack 1001 win 257
+
+ +0 close(3) = 0
+ +0 > F. 1001:1001(0) ack 1
+ +0 < . 1:1(0) ack 1002 win 257
+
+ +0 < F. 1:1(0) ack 1002 win 257
+ +0 > . 1002:1002(0) ack 2
diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt
new file mode 100644
index 000000000000..04103134bd99
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test to make sure no RST is being sent when close()
+// is called on a socket with SYN_SENT state.
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
+ +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+ +0 > S 0:0(0) <...>
+
+// Application decideds to close the socket in SYN_SENT state
+// Make sure no RST is sent after close().
+ +0 close(3) = 0
+
+// Receive syn-ack to trigger the send side packet examination:
+// If a RESET were sent right after close(), it would have failed with
+// a mismatched timestamp.
+ +.1 < S. 0:0(0) ack 1 win 32000 <mss 1460,nop,wscale 7>
+ +0 > R 1:1(0)
diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt
new file mode 100644
index 000000000000..5f3a2914213a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+// Verify behavior for the sequence: remote side sends FIN, then we close().
+// Since the remote side (client) closes first, we test our LAST_ACK code path.
+
+`./defaults.sh`
+
+// Initialize a server socket.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +0 < . 1:1(0) ack 1 win 257
+
+ +0 accept(3, ..., ...) = 4
+
+// Client closes first.
+ +.01 < F. 1:1(0) ack 1 win 257
+ +0 > . 1:1(0) ack 2
+
+// App notices that client closed.
+ +0 read(4, ..., 1000) = 0
+
+// Then we close.
+ +.01 close(4) = 0
+ +0 > F. 1:1(0) ack 2
+
+// Client ACKs our FIN.
+ +.01 < . 2:2(0) ack 2 win 257
+
+// Verify that we send RST in response to any incoming segments
+// (because the kernel no longer has any record of this socket).
+ +.01 < . 2:2(0) ack 2 win 257
+ +0 > R 2:2(0)
diff --git a/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt b/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt
new file mode 100644
index 000000000000..643baf3267cf
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test ECN: verify that Linux TCP ECN sending code uses ECT0 (not ECT1).
+//
+`./defaults.sh
+sysctl -q net.ipv4.tcp_ecn=1 # fully enabled
+`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+
+// ECN handshake: send EW flags in SYN packet, E flag in SYN-ACK response
++.002 ... 0.004 connect(4, ..., ...) = 0
+
+ +0 > SEW 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
++.002 < SE. 0:0(0) ack 1 win 32767 <mss 1000,nop,wscale 6,nop,nop,sackOK>
+ +0 > . 1:1(0) ack 1
+
+// Write 1 MSS.
++.002 write(4, ..., 1000) = 1000
+// Send 1 MSS with ect0.
+ +0 > [ect0] P. 1:1001(1000) ack 1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt
new file mode 100644
index 000000000000..f95b9b3c9fa1
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP does not append any data from consequent writes to the tail
+// skb created for the chunk. The large chunk itself should be packetized as
+// usual.
+`./defaults.sh
+`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.01 < . 1:1(0) ack 1 win 514
+
+ +0 accept(3, ..., ...) = 4
+
+// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on
+// the tail.
+ +0 write(4, ..., 10400) = 10400
+
+// Write another 10040B chunk with no coalescing options.
+ +0 send(4, ..., 10400, MSG_EOR) = 10400
+
+// Write a 2KB chunk. This chunk should not be appended to the packets created
+// the previous chunk.
+ +0 write(4, ..., 2000) = 2000
+
+ +0 > P. 1:10001(10000) ack 1
++.001 < . 1:1(0) ack 10001 win 514
+// Now we have enough room to send out the 2 x 400B packets out.
+ +0 > P. 10001:20801(10800) ack 1
++.001 < . 1:1(0) ack 20801 win 514
+// This 2KB packet should be sent alone.
+ +0 > P. 20801:22801(2000) ack 1
++.001 < . 1:1(0) ack 22801 win 514
diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt
new file mode 100644
index 000000000000..2ff66075288e
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP does not append any data from consequent writes to the tail
+// skb created for the chunk. Also, when packets are retransmitted, they
+// will not be coalesce into the same skb.
+`./defaults.sh
+`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.01 < . 1:1(0) ack 1 win 514
+
+ +0 accept(3, ..., ...) = 4
+
+// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on
+// the tail.
+ +0 write(4, ..., 10400) = 10400
+
+// Write 10 400B chunks with no coalescing options.
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+// This chunk should not be appended to the skbs created for the previous chunk.
+ +0 write(4, ..., 10000) = 10000
+
+ +0 > P. 1:10001(10000) ack 1
++.001 < . 1:1(0) ack 10001 win 514
+// Now we have enough room to send out the 2 x 400B packets out.
+ +0 > P. 10001:10801(800) ack 1
+// The 9 remaining 400B chunks should be sent as individual packets.
+ +0 > P. 10801:11201(400) ack 1
+ +0 > P. 11201:11601(400) ack 1
+ +0 > P. 11601:12001(400) ack 1
+ +0 > P. 12001:12401(400) ack 1
+ +0 > P. 12401:12801(400) ack 1
+ +0 > P. 12801:13201(400) ack 1
+ +0 > P. 13201:13601(400) ack 1
+ +0 > P. 13601:14001(400) ack 1
+ +0 > P. 14001:14401(400) ack 1
+// The last 10KB chunk should be sent separately.
+ +0 > P. 14401:24401(10000) ack 1
+
++.001 < . 1:1(0) ack 10401 win 514
++.001 < . 1:1(0) ack 10801 win 514
++.001 < . 1:1(0) ack 11201 win 514
++.001 < . 1:1(0) ack 11601 win 514
++.001 < . 1:1(0) ack 12001 win 514 <sack 13201:14401,nop,nop>
+// TCP should fill the hole but no coalescing should happen, and all
+// retransmissions should be sent out as individual packets.
+
+// Note : This is timeout based retransmit.
+// Do not put +0 here or flakes will come back.
++.004~+.008 > P. 12001:12401(400) ack 1
+
++.001 < . 1:1(0) ack 12401 win 514 <sack 13201:14401,nop,nop>
+ +0 > P. 12401:12801(400) ack 1
+ +0 > P. 12801:13201(400) ack 1
++.001 < . 1:1(0) ack 12801 win 514 <sack 13201:14401,nop,nop>
++.001 < . 1:1(0) ack 14401 win 514
++.001 < . 1:1(0) ack 24401 win 514
diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt
new file mode 100644
index 000000000000..77039c5aac39
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP does not append any data from consequent writes to the tail
+// skb created for the chunk.
+`./defaults.sh
+`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.01 < . 1:1(0) ack 1 win 514
+
+ +0 accept(3, ..., ...) = 4
+
+// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on
+// the tail.
+ +0 write(4, ..., 10400) = 10400
+
+// Write a 400B chunk with no coalescing options.
+ +0 send(4, ..., 400, MSG_EOR) = 400
+
+// This chunk should not be appended to the skbs created for the previous chunk.
+ +0 write(4, ..., 10000) = 10000
+
+ +0 > P. 1:10001(10000) ack 1
++.001 < . 1:1(0) ack 10001 win 514
+// Now we have enough room to send out the 2 x 400B packets out.
+ +0 > P. 10001:10801(800) ack 1
+ +0 > P. 10801:20801(10000) ack 1
++.001 < . 1:1(0) ack 10401 win 514
++.001 < . 1:1(0) ack 10801 win 514
++.001 < . 1:1(0) ack 20801 win 514
diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt
new file mode 100644
index 000000000000..dd5a06250595
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP does not append any data from consequent writes to the tail
+// skb created for the chunk even though we have 10 back-to-back small
+// writes.
+`./defaults.sh
+`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.01 < . 1:1(0) ack 1 win 514
+
+ +0 accept(3, ..., ...) = 4
+
+// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on
+// the tail.
+ +0 write(4, ..., 10400) = 10400
+
+// Write 10 400B chunks with no coalescing options.
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+ +0 send(4, ..., 400, MSG_EOR) = 400
+// This chunk should not be appended to the skbs created for the previous chunk.
+ +0 write(4, ..., 10000) = 10000
+
+ +0 > P. 1:10001(10000) ack 1
++.001 < . 1:1(0) ack 10001 win 514
+// Now we have enough room to send out the 2 x 400B packets out.
+ +0 > P. 10001:10801(800) ack 1
+// The 9 remaining 400B chunks should be sent as individual packets.
+ +0 > P. 10801:11201(400) ack 1
+ +0 > P. 11201:11601(400) ack 1
+ +0 > P. 11601:12001(400) ack 1
+ +0 > P. 12001:12401(400) ack 1
+ +0 > P. 12401:12801(400) ack 1
+ +0 > P. 12801:13201(400) ack 1
+ +0 > P. 13201:13601(400) ack 1
+ +0 > P. 13601:14001(400) ack 1
+ +0 > P. 14001:14401(400) ack 1
+// The last 10KB chunk should be sent separately.
+ +0 > P. 14401:24401(10000) ack 1
+
++.001 < . 1:1(0) ack 10401 win 514
++.001 < . 1:1(0) ack 10801 win 514
++.001 < . 1:1(0) ack 11201 win 514
++.001 < . 1:1(0) ack 11601 win 514
++.001 < . 1:1(0) ack 12001 win 514
++.001 < . 1:1(0) ack 12401 win 514
++.001 < . 1:1(0) ack 12801 win 514
++.001 < . 1:1(0) ack 13201 win 514
++.001 < . 1:1(0) ack 13601 win 514
++.001 < . 1:1(0) ack 14001 win 514
++.001 < . 1:1(0) ack 14401 win 514
++.001 < . 1:1(0) ack 24401 win 514
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt
new file mode 100644
index 000000000000..0d3c8077e830
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test PRR-slowstart implementation.
+// In this variant we test a simple case where in-flight == ssthresh
+// all the way through recovery, so during fast recovery we send one segment
+// for each segment SACKed/ACKed.
+
+// Set up config.
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+// RTT 100ms
+ +.1 < . 1:1(0) ack 1 win 320
+ +0 accept(3, ..., ...) = 4
+
+// Send 10 data segments.
+ +0 write(4, ..., 10000) = 10000
+ +0 > P. 1:10001(10000) ack 1
+
+// Lost packet 1:1001.
+ +.11 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop>
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop>
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:4001,nop,nop>
+// Enter fast recovery.
+ +0 > . 1:1001(1000) ack 1
+ +.01 %{
+assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state
+assert tcpi_snd_cwnd == 7, tcpi_snd_cwnd
+assert tcpi_snd_ssthresh == 7, tcpi_snd_ssthresh
+}%
+
+// Write some more, which we will send 1 MSS at a time,
+// as in-flight segments are SACKed or ACKed.
+ +.01 write(4, ..., 7000) = 7000
+
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:5001,nop,nop>
+ +0 > . 10001:11001(1000) ack 1
+
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:6001,nop,nop>
+ +0 > . 11001:12001(1000) ack 1
+
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:7001,nop,nop>
+ +0 > . 12001:13001(1000) ack 1
+
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:8001,nop,nop>
+ +0 > . 13001:14001(1000) ack 1
+
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:9001,nop,nop>
+ +0 > . 14001:15001(1000) ack 1
+
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:10001,nop,nop>
+ +0 > . 15001:16001(1000) ack 1
+
+ +.02 < . 1:1(0) ack 10001 win 320
+ +0 > P. 16001:17001(1000) ack 1
+// Leave fast recovery.
+ +.01 %{
+assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state
+assert tcpi_snd_cwnd == 7, tcpi_snd_cwnd
+assert tcpi_snd_ssthresh == 7, tcpi_snd_ssthresh
+}%
+
+ +.03 < . 1:1(0) ack 12001 win 320
+ +.02 < . 1:1(0) ack 14001 win 320
+ +.02 < . 1:1(0) ack 16001 win 320
+ +.02 < . 1:1(0) ack 17001 win 320
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt
new file mode 100644
index 000000000000..7842a10b6967
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test PRR-slowstart implementation. The sender sends 20 packets. Packet
+// 1 to 4, and 11 to 16 are dropped.
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+
+ +.01 < . 1:1(0) ack 1 win 320
+ +0 accept(3, ..., ...) = 4
+
+// Write 20 data segments.
+ +0 write(4, ..., 20000) = 20000
+ +0 > P. 1:10001(10000) ack 1
+
+// Receive first DUPACK, entering PRR part
+ +.01 < . 1:1(0) ack 1 win 320 <sack 4001:5001,nop,nop>
+ +0 > . 10001:11001(1000) ack 1
++.002 < . 1:1(0) ack 1 win 320 <sack 4001:6001,nop,nop>
+ +0 > . 11001:12001(1000) ack 1
++.002 < . 1:1(0) ack 1 win 320 <sack 4001:7001,nop,nop>
+ +0 > . 1:1001(1000) ack 1
++.002 < . 1:1(0) ack 1 win 320 <sack 4001:8001,nop,nop>
+ +0 > . 1001:2001(1000) ack 1
++.002 < . 1:1(0) ack 1 win 320 <sack 4001:9001,nop,nop>
+ +0 > . 2001:3001(1000) ack 1
++.002 < . 1:1(0) ack 1 win 320 <sack 4001:10001,nop,nop>
+ +0 > . 3001:4001(1000) ack 1
+// Enter PRR CRB
++.002 < . 1:1(0) ack 1 win 320 <sack 4001:11001,nop,nop>
+ +0 > . 12001:13001(1000) ack 1
++.002 < . 1:1(0) ack 1 win 320 <sack 4001:12001,nop,nop>
+ +0 > . 13001:14001(1000) ack 1
+// Enter PRR slow start
+ +.01 < . 1:1(0) ack 1001 win 320 <sack 4001:12001,nop,nop>
+ +0 > P. 14001:16001(2000) ack 1
++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:12001,nop,nop>
+ +0 > . 1001:2001(1000) ack 1
+ +0 > . 16001:17001(1000) ack 1
+// inflight reaches ssthresh, goes into packet conservation mode
++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:13001,nop,nop>
+ +0 > . 17001:18001(1000) ack 1
++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:14001,nop,nop>
+ +0 > . 18001:19001(1000) ack 1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt
new file mode 100644
index 000000000000..b66d7644c3b6
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test PRR-slowstart implementation. The sender sends 20 packets. Packet
+// 1 to 4 are lost. The sender writes another 10 packets.
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+
+ +.01 < . 1:1(0) ack 1 win 320
+ +0 accept(3, ..., ...) = 4
+
+// Send 20 data segments.
+ +0 write(4, ..., 10000) = 10000
+ +0 > P. 1:10001(10000) ack 1
+
+// Lost packet 1,2,3,4
+ +.01 < . 1:1(0) ack 1 win 320 <sack 4001:5001,nop,nop>
++.002 < . 1:1(0) ack 1 win 320 <sack 4001:6001,nop,nop>
+ +0 < . 1:1(0) ack 1 win 320 <sack 4001:7001,nop,nop>
+ +0 > . 1:1001(1000) ack 1
+ +0 < . 1:1(0) ack 1 win 320 <sack 4001:8001,nop,nop>
+ +0 > . 1001:2001(1000) ack 1
+ +0 < . 1:1(0) ack 1 win 320 <sack 4001:9001,nop,nop>
+ +0 > . 2001:3001(1000) ack 1
+ +0 < . 1:1(0) ack 1 win 320 <sack 4001:10001,nop,nop>
+ +0 > . 3001:4001(1000) ack 1
+
+// Receiver ACKs all data.
+ +.01 < . 1:1(0) ack 1001 win 320 <sack 4001:10001,nop,nop>
+ +0 < . 1:1(0) ack 2001 win 320 <sack 4001:10001,nop,nop>
+ +0 < . 1:1(0) ack 3001 win 320 <sack 4001:10001,nop,nop>
+ +0 < . 1:1(0) ack 10001 win 320
+
+// Writes another 10 packets, which the ssthresh*mss amount
+// should be sent right away
+ +.01 write(4, ..., 10000) = 10000
+ +0 > . 10001:17001(7000) ack 1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt
new file mode 100644
index 000000000000..8e87bfecabb5
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test PRR-slowstart implementation.
+// In this variant we verify that the sender uses SACK info on an ACK
+// below snd_una.
+
+// Set up config.
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 8>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+// RTT 10ms
+ +.01 < . 1:1(0) ack 1 win 320
+ +0 accept(3, ..., ...) = 4
+
+// Send 10 data segments.
+ +0 write(4, ..., 10000) = 10000
+ +0 > P. 1:10001(10000) ack 1
+
+// Lost packet 1:1001,4001:5001,7001:8001.
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop>
+ +0 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop>
+ +0 < . 1:1(0) ack 1 win 320 <sack 1001:3001 8001:9001,nop,nop>
+ +0 > . 1:1001(1000) ack 1
+
++.012 < . 1:1(0) ack 4001 win 320 <sack 8001:9001,nop,nop>
+ +0 > . 4001:7001(3000) ack 1
+
+ +0 write(4, ..., 10000) = 10000
+
+// The following ACK was reordered - delayed so that it arrives with
+// an ACK field below snd_una. Here we check that the newly-SACKed
+// 2MSS at 5001:7001 cause us to send out 2 more MSS.
++.002 < . 1:1(0) ack 3001 win 320 <sack 5001:7001,nop,nop>
+ +0 > . 7001:8001(1000) ack 1
+ +0 > . 10001:11001(1000) ack 1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt
new file mode 100644
index 000000000000..96b01eb5b7a4
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test RFC 3042 "Limited Transmit": "sending a new data segment in
+// response to each of the first two duplicate acknowledgments that
+// arrive at the sender".
+// This variation tests a receiver that doesn't support SACK.
+
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 320
+ +0 accept(3, ..., ...) = 4
+
+// Write some data, and send the initial congestion window.
+ +0 write(4, ..., 15000) = 15000
+ +0 > P. 1:10001(10000) ack 1
+
+// Limited transmit: on first dupack, send a new data segment.
+ +.11 < . 1:1(0) ack 1 win 320
+ +0 > . 10001:11001(1000) ack 1
+
+// Limited transmit: on second dupack, send a new data segment.
+ +.01 < . 1:1(0) ack 1 win 320
+ +0 > . 11001:12001(1000) ack 1
+
+// It turned out to be reordering, not loss.
+// We have one packet newly acked (1001:3001 were DUP-ACK'd)
+// So we revert state back to Open. Slow start cwnd from 10 to 11
+// and send 11 - 9 = 2 packets
+ +.01 < . 1:1(0) ack 3001 win 320
+ +0 > P. 12001:14001(2000) ack 1
+
+ +.02 < . 1:1(0) ack 5001 win 320
+ +0 > P. 14001:15001(1000) ack 1
+
+// Client gradually ACKs all data.
+ +.02 < . 1:1(0) ack 7001 win 320
+ +.02 < . 1:1(0) ack 9001 win 320
+ +.02 < . 1:1(0) ack 11001 win 320
+ +.02 < . 1:1(0) ack 13001 win 320
+ +.02 < . 1:1(0) ack 15001 win 320
+
+// Clean up.
+ +.17 close(4) = 0
+ +0 > F. 15001:15001(0) ack 1
+ +.1 < F. 1:1(0) ack 15002 win 257
+ +0 > . 15002:15002(0) ack 2
diff --git a/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt
new file mode 100644
index 000000000000..642da51ec3a4
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test RFC 3042 "Limited Transmit": "sending a new data segment in
+// response to each of the first two duplicate acknowledgments that
+// arrive at the sender".
+// This variation tests a receiver that supports SACK.
+
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 320
+ +0 accept(3, ..., ...) = 4
+
+// Write some data, and send the initial congestion window.
+ +0 write(4, ..., 15000) = 15000
+ +0 > P. 1:10001(10000) ack 1
+
+// Limited transmit: on first dupack, send a new data segment.
+ +.11 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop>
+ +0 > . 10001:11001(1000) ack 1
+
+// Limited transmit: on second dupack, send a new data segment.
+ +.01 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop>
+ +0 > . 11001:12001(1000) ack 1
+
+// It turned out to be reordering, not loss.
+ +.01 < . 1:1(0) ack 3001 win 320
+ +0 > P. 12001:14001(2000) ack 1
+
+ +.02 < . 1:1(0) ack 5001 win 320
+ +0 > P. 14001:15001(1000) ack 1
+
+// Client gradually ACKs all data.
+ +.02 < . 1:1(0) ack 7001 win 320
+ +.02 < . 1:1(0) ack 9001 win 320
+ +.02 < . 1:1(0) ack 11001 win 320
+ +.02 < . 1:1(0) ack 13001 win 320
+ +.02 < . 1:1(0) ack 15001 win 320
+
+// Clean up.
+ +.17 close(4) = 0
+ +0 > F. 15001:15001(0) ack 1
+ +.1 < F. 1:1(0) ack 15002 win 257
+ +0 > . 15002:15002(0) ack 2
diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt
new file mode 100644
index 000000000000..7adae7a9ef4a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+// This is a test inspired by an Android client app using SSL. This
+// test verifies using TCP_NODELAY would save application latency
+// (Perhaps even better with TCP_NAGLE).
+//
+`./defaults.sh
+ethtool -K tun0 tso off gso off
+./set_sysctls.py /proc/sys/net/ipv4/tcp_timestamps=0`
+
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+ +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+ +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0
+
+ +0 connect(4, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+ +0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.1 < S. 0:0(0) ack 1 win 5792 <mss 974,nop,nop,sackOK,nop,wscale 7>
+ +0 > . 1:1(0) ack 1
+
+// SSL handshake (resumed session)
+ +0 write(4, ..., 517) = 517
+ +0 > P. 1:518(517) ack 1
+ +.1 < . 1:1(0) ack 518 win 229
+
+ +0 < P. 1:144(143) ack 1 win 229
+ +0 > . 518:518(0) ack 144
+ +0 read(4, ..., 1000) = 143
+
+// Application POST header (51B) and body (2002B)
+ +0 write(4, ..., 51) = 51
+ +0 > P. 518:569(51) ack 144
+ +.03 write(4, ..., 2002) = 2002
+ +0 > . 569:1543(974) ack 144
+ +0 > P. 1543:2517(974) ack 144
+// Without disabling Nagle, this packet will not happen until the remote ACK.
+ +0 > P. 2517:2571(54) ack 144
+
+ +.1 < . 1:1(0) ack 2571 win 229
+
+// Reset sysctls
+`/tmp/sysctl_restore_${PPID}.sh`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt
new file mode 100644
index 000000000000..fa9c01813996
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test the MSG_MORE flag will correctly corks the tiny writes
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
+ +.01 < . 1:1(0) ack 1 win 257
+ +0 accept(3, ..., ...) = 4
+// Disable Nagle by default on this socket.
+ +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0
+
+// Test the basic case: MSG_MORE overwrites TCP_NODELAY and enables Nagle.
+ +0 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 40}], msg_flags=0}, MSG_MORE) = 40
+ +.21~+.215 > P. 1:41(40) ack 1
+ +.01 < . 1:1(0) ack 41 win 257
+
+// Test unsetting MSG_MORE releases the packet
+ +0 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 100}], msg_flags=0}, MSG_MORE) = 100
++.005 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 160}], msg_flags=0}, MSG_MORE) = 160
+ +.01 sendmsg(4, {msg_name(...)=...,
+ msg_iov(3)=[{..., 100}, {..., 200}, {..., 195}],
+ msg_flags=0}, MSG_MORE) = 495
++.008 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 5}], msg_flags=0}, 0) = 5
+ +0 > P. 41:801(760) ack 1
+ +.02 < . 1:1(0) ack 801 win 257
+
+
+// Test >MSS write will unleash MSS packets but hold on the remaining data.
+ +.1 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 3100}], msg_flags=0}, MSG_MORE) = 3100
+ +0 > . 801:3801(3000) ack 1
++.003 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 50}], msg_flags=0}, MSG_MORE) = 50
+
+ +.01 < . 1:1(0) ack 2801 win 257
+// Err... we relase the remaining right after the ACK? note that PUSH is reset
+ +0 > . 3801:3951(150) ack 1
+
+// Test we'll hold on the subsequent writes when inflight (3801:3951) > 0
++.001 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 1}], msg_flags=0}, MSG_MORE) = 1
++.002 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 2}], msg_flags=0}, MSG_MORE) = 2
++.003 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 3}], msg_flags=0}, MSG_MORE) = 3
++.004 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 4}], msg_flags=0}, MSG_MORE) = 4
+ +.02 < . 1:1(0) ack 3951 win 257
+ +0 > . 3951:3961(10) ack 1
+ +.02 < . 1:1(0) ack 3961 win 257
+
+
+// Test the case a MSG_MORE send followed by a write flushes the data
+ +0 sendmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{..., 20}], msg_flags=0}, MSG_MORE) = 20
+ +.05 write(4, ..., 20) = 20
+ +0 > P. 3961:4001(40) ack 1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt
new file mode 100644
index 000000000000..0ddec5f7dc1a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP_CORK and TCP_NODELAY sockopt behavior
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
+ +.01 < . 1:1(0) ack 1 win 257
+ +0 accept(3, ..., ...) = 4
+// Set TCP_CORK sockopt to hold small packets
+ +0 setsockopt(4, SOL_TCP, TCP_CORK, [1], 4) = 0
+
+ +0 write(4, ..., 40) = 40
+ +.05 write(4, ..., 40) = 40
+
+// Unset TCP_CORK should push pending bytes out
+ +.01 setsockopt(4, SOL_TCP, TCP_CORK, [0], 4) = 0
+ +0 > P. 1:81(80) ack 1
+ +.01 < . 1:1(0) ack 81 win 257
+
+// Set TCP_CORK sockopt to hold small packets
+ +0 setsockopt(4, SOL_TCP, TCP_CORK, [1], 4) = 0
+
+ +0 write(4, ..., 40) = 40
+ +.05 write(4, ..., 40) = 40
+
+// Set TCP_NODELAY sockopt should push pending bytes out
+ +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0
+ +0 > P. 81:161(80) ack 1
+ +.01 < . 1:1(0) ack 161 win 257
+
+// Set MSG_MORE to hold small packets
+ +0 send(4, ..., 40, MSG_MORE) = 40
+ +.05 send(4, ..., 40, MSG_MORE) = 40
+
+// Set TCP_NODELAY sockopt should push pending bytes out
+ +.01 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0
+ +0 > . 161:241(80) ack 1
+ +.01 < . 1:1(0) ack 241 win 257
diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt
new file mode 100644
index 000000000000..310ef31518da
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+// Verify that setsockopt calls that force a route refresh do not
+// cause problems matching SACKs with packets in the write queue.
+// This variant tests IP_TOS.
+
+`./defaults.sh`
+
+// Establish a connection.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_IP, IP_MTU_DISCOVER, [IP_PMTUDISC_DONT], 1) = 0
+ +0...0.010 connect(3, ..., ...) = 0
+
+ +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
+ +.01 < S. 0:0(0) ack 1 win 65535 <mss 1460,nop,wscale 2,nop,nop,sackOK>
+ +0 > . 1:1(0) ack 1
+
+ +.01 write(3, ..., 5840) = 5840
+ +0 > P. 1:5841(5840) ack 1
+ +.01 < . 1:1(0) ack 5841 win 65535
+
+ +.01 write(3, ..., 5840) = 5840
+ +0 > P. 5841:11681(5840) ack 1
+ +.01 < . 1:1(0) ack 11681 win 65535
+
+ +.01 write(3, ..., 14600) = 14600
+ +0 > P. 11681:26281(14600) ack 1
+
+// Try the socket option that we know can force a route refresh.
+ +0 setsockopt(3, SOL_IP, IP_TOS, [4], 1) = 0
+// Then revert to avoid routing/mangling/etc implications of that setting.
+ +0 setsockopt(3, SOL_IP, IP_TOS, [0], 1) = 0
+
+// Verify that we do not retransmit the SACKed segments.
+ +.01 < . 1:1(0) ack 13141 win 65535 <sack 16061:17521 20441:26281,nop,nop>
+ +0 > . 13141:16061(2920) ack 1
+ +0 > P. 17521:20441(2920) ack 1
+ +.01 < . 1:1(0) ack 26281 win 65535
diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt
new file mode 100644
index 000000000000..f185e1ac57ea
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb.
+// This variant tests non-FACK SACK with SACKs coming in the order
+// 2 6 8 3 9, to test what happens when we get a new SACKed range
+// (for packet 3) that is on the right of an existing SACKed range
+// (for packet 2).
+
+`./defaults.sh`
+
+// Establish a connection and send 10 MSS.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 1024
+ +0 accept(3, ..., ...) = 4
+
+ +0 write(4, ..., 10000) = 10000
+ +0 > P. 1:10001(10000) ack 1
+
+ +.1 < . 1:1(0) ack 1 win 257 <sack 2001:3001,nop,nop>
++.001 < . 1:1(0) ack 1 win 257 <sack 2001:3001 6001:7001,nop,nop>
++.001 < . 1:1(0) ack 1 win 257 <sack 2001:3001 6001:7001 8001:9001,nop,nop>
+
+// 3 SACKed packets, so we enter Fast Recovery.
+ +0 > . 1:1001(1000) ack 1
+ +0 %{ assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state }%
+ +0 %{ assert tcpi_lost == 6, tcpi_lost }%
+
+// SACK for 3001:4001.
+// This SACK for an adjacent range causes the sender to
+// shift the newly-SACKed range onto the previous skb.
++.007 < . 1:1(0) ack 1 win 257 <sack 2001:4001 6001:7001 8001:9001,nop,nop>
+ +0 > . 1001:2001(1000) ack 1
+ +0 %{ assert tcpi_lost == 5, tcpi_lost }%
+ +0 %{ assert tcpi_reordering == 6, tcpi_reordering }% // 8001:9001 -> 3001:4001 is 6
+
+// SACK for 9001:10001.
+ +.01 < . 1:1(0) ack 1 win 257 <sack 2001:4001 6001:7001 8001:10001,nop,nop>
+ +0 %{ assert tcpi_lost == 5, tcpi_lost }%
+
+// ACK for 1:1001 as packets from t=0.303 arrive.
++.083 < . 1:1(0) ack 1001 win 257 <sack 2001:4001 6001:7001 8001:10001,nop,nop>
+ +0 %{ assert tcpi_lost == 4,tcpi_lost }%
+
+// ACK for 1:4001 as packets from t=0.310 arrive.
++.017 < . 1:1(0) ack 4001 win 257 <sack 6001:7001 8001:10001,nop,nop>
+ +0 %{ assert tcpi_lost == 3,tcpi_lost }%
+
+// ACK for 1:7001 as packets from t=0.320 arrive.
+ +.01 < . 1:1(0) ack 7001 win 257 <sack 8001:10001,nop,nop>
+
+// ACK for all data as packets from t=0.403 arrive.
+ +.1 < . 1:1(0) ack 10001 win 257
+ +0 %{
+assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state
+assert tcpi_unacked == 0, tcpi_unacked
+assert tcpi_sacked == 0, tcpi_sacked
+assert tcpi_lost == 0, tcpi_lost
+assert tcpi_retrans == 0, tcpi_retrans
+}%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt
new file mode 100644
index 000000000000..0093b4973934
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb.
+// This variant tests the case where we mark packets 0-4 lost, then
+// get a SACK for 3, and then a SACK for 4.
+
+`./defaults.sh`
+
+// Establish a connection and send 10 MSS.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 1024
+ +0 accept(3, ..., ...) = 4
+
+ +0 write(4, ..., 10000) = 10000
+ +0 > P. 1:10001(10000) ack 1
+
+// SACK for 7001:8001. Using RACK we delay the fast retransmit.
+ +.1 < . 1:1(0) ack 1 win 257 <sack 7001:8001,nop,nop>
+// RACK reordering timer
++.027 > . 1:1001(1000) ack 1
+ +0 %{
+assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state
+assert tcpi_lost == 7, tcpi_lost # RACK thinks 1:7001 are lost
+assert tcpi_reordering == 3, tcpi_reordering
+}%
+
+// SACK for 3001:4001.
++.002 < . 1:1(0) ack 1 win 257 <sack 3001:4001 7001:8001,nop,nop>
+ +0 > . 1001:2001(1000) ack 1
+ +0 %{
+assert tcpi_lost == 6, tcpi_lost # since 3001:4001 is no longer lost
+assert tcpi_reordering == 5, tcpi_reordering # 7001:8001 -> 3001:4001
+}%
+
+// SACK for 4001:5001.
+// This SACK for an adjacent range causes the sender to
+// shift the newly-SACKed range onto the previous skb.
+// It uses the RFC3517 algorithm to mark 1:3001 lost
+// because >=3 higher-sequence packets are SACKed.
++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:8001,nop,nop>
+ +0 > . 2001:3001(1000) ack 1
+ +0 %{
+assert tcpi_lost == 5,tcpi_lost # SACK/RFC3517 thinks 1:3001 are lost
+}%
+
+// SACK for 8001:9001.
++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:9001,nop,nop>
+
+// SACK for 9001:10001.
++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:10001,nop,nop>
+ +0 > . 5001:6001(1000) ack 1
+
+// To simplify clean-up, say we get an ACK for all data.
+ +.1 < . 1:1(0) ack 10001 win 257
+ +0 %{
+assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state
+assert tcpi_unacked == 0, tcpi_unacked
+assert tcpi_sacked == 0, tcpi_sacked
+assert tcpi_lost == 0, tcpi_lost
+assert tcpi_retrans == 0, tcpi_retrans
+}%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt
new file mode 100644
index 000000000000..980a832dc81c
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb.
+// This variant tests the case where we mark packets 0-4 lost, then
+// get a SACK for 5, and then a SACK for 6.
+
+`./defaults.sh`
+
+// Establish a connection and send 10 MSS.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 1024
+ +0 accept(3, ..., ...) = 4
+
+ +0 write(4, ..., 10000) = 10000
+ +0 > P. 1:10001(10000) ack 1
+
+// SACK for 7001:8001. Using RACK we delay a fast retransmit.
+ +.1 < . 1:1(0) ack 1 win 257 <sack 7001:8001,nop,nop>
++.027 > . 1:1001(1000) ack 1
+ +0 %{
+assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state
+assert tcpi_lost == 7,tcpi_lost # RACK thinks 1:7001 are lost
+assert tcpi_reordering == 3, tcpi_reordering
+}%
+
+// SACK for 5001:6001.
+ +0 < . 1:1(0) ack 1 win 257 <sack 5001:6001 7001:8001,nop,nop>
+ +0 > . 1001:2001(1000) ack 1
+ +0 %{
+assert tcpi_lost == 6, tcpi_lost
+assert tcpi_reordering == 3, tcpi_reordering # 7001:8001 -> 5001:6001 is 3
+}%
+
+// SACK for 6001:7001.
+// This SACK for an adjacent range causes the sender to
+// shift the newly-SACKed range onto the previous skb.
+ +0 < . 1:1(0) ack 1 win 257 <sack 5001:8001,nop,nop>
+ +0 > . 2001:3001(1000) ack 1
+ +0 %{ assert tcpi_lost == 5, tcpi_lost }%
+
+// SACK for 8001:9001.
+ +0 < . 1:1(0) ack 1 win 257 <sack 5001:9001,nop,nop>
+ +0 > . 3001:4001(1000) ack 1
+
+// SACK for 9001:10001.
+ +0 < . 1:1(0) ack 1 win 257 <sack 5001:10001,nop,nop>
+ +0 > . 4001:5001(1000) ack 1
+
+// To simplify clean-up, say we get an ACK for all data.
+ +.1 < . 1:1(0) ack 10001 win 257
+ +0 %{
+assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state
+assert tcpi_unacked == 0, tcpi_unacked
+assert tcpi_sacked == 0, tcpi_sacked
+assert tcpi_lost == 0, tcpi_lost
+assert tcpi_retrans == 0, tcpi_retrans
+}%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt b/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt
new file mode 100644
index 000000000000..6740859a1360
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+// Simplest possible test of open() and then sendfile().
+// We write some zeroes into a file (since packetdrill expects payloads
+// to be all zeroes) and then open() the file, then use sendfile()
+// and verify that the correct number of zeroes goes out.
+
+`./defaults.sh
+/bin/rm -f /tmp/testfile
+/bin/dd bs=1 count=5 if=/dev/zero of=/tmp/testfile status=none
+`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +0 < . 1:1(0) ack 1 win 514
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 open("/tmp/testfile", O_RDONLY) = 5
+ +0 sendfile(4, 5, [0], 5) = 5
+ +0 > P. 1:6(5) ack 1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt b/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt
new file mode 100644
index 000000000000..0cbd43253236
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+`./defaults.sh`
+
+// Initialize a server socket
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 setsockopt(3, SOL_IP, IP_FREEBIND, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+// Connection should get accepted
+ +0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <...>
+ +0 < . 1:1(0) ack 1 win 257
+ +0 accept(3, ..., ...) = 4
+
+ +0 pipe([5, 6]) = 0
+ +0 < U. 1:101(100) ack 1 win 257 urg 100
+ +0 splice(4, NULL, 6, NULL, 99, 0) = 99
+ +0 splice(4, NULL, 6, NULL, 1, 0) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt
new file mode 100644
index 000000000000..8940726a3ec2
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP fastopen behavior with NULL as buffer pointer, but a non-zero
+// buffer length.
+`./defaults.sh
+./set_sysctls.py /proc/sys/net/ipv4/tcp_timestamps=0`
+
+// Cache warmup: send a Fast Open cookie request
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
++0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
++0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
++0 connect(3, ..., ...) = -1 EINPROGRESS (Operation is now in progress)
++0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8,FO,nop,nop>
++0 < S. 123:123(0) ack 1 win 14600 <mss 1460,nop,nop,sackOK,nop,wscale 6,FO abcd1234,nop,nop>
++0 > . 1:1(0) ack 1
++0 close(3) = 0
++0 > F. 1:1(0) ack 1
++0 < F. 1:1(0) ack 2 win 92
++0 > . 2:2(0) ack 2
+
+// Test with MSG_FASTOPEN without TCP_FASTOPEN_CONNECT.
++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
++0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
++0 sendto(4, NULL, 1, MSG_FASTOPEN, ..., ...) = -1
++0 close(4) = 0
+
+// Test with TCP_FASTOPEN_CONNECT without MSG_FASTOPEN.
++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 5
++0 fcntl(5, F_SETFL, O_RDWR|O_NONBLOCK) = 0
++0 setsockopt(5, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
++0 connect(5, ..., ...) = 0
++0 sendto(5, NULL, 1, 0, ..., ...) = -1
++0 close(5) = 0
+
+// Test with both TCP_FASTOPEN_CONNECT and MSG_FASTOPEN.
++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 6
++0 fcntl(6, F_SETFL, O_RDWR|O_NONBLOCK) = 0
++0 setsockopt(6, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
++0 connect(6, ..., ...) = 0
++0 sendto(6, NULL, 1, MSG_FASTOPEN, ..., ...) = -1
++0 close(6) = 0
+
+`/tmp/sysctl_restore_${PPID}.sh`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt
new file mode 100644
index 000000000000..b2b2cdf27e20
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test that we correctly skip zero-length IOVs.
+`./defaults.sh`
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
+ +.01 < . 1:1(0) ack 1 win 257
+ +0 accept(3, ..., ...) = 4
+ +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0
+
+ +0 sendmsg(4, {msg_name(...)=...,
+ msg_iov(4)=[{..., 0}, {..., 40}, {..., 0}, {..., 20}],
+ msg_flags=0}, 0) = 60
+ +0 > P. 1:61(60) ack 1
+ +.01 < . 1:1(0) ack 61 win 257
+
+ +0 sendmsg(4, {msg_name(...)=...,
+ msg_iov(4)=[{..., 0}, {..., 0}, {..., 0}, {..., 0}],
+ msg_flags=0}, MSG_ZEROCOPY) = 0
+
+ +0 sendmsg(4, {msg_name(...)=...,
+ msg_iov(4)=[{..., 0}, {..., 10}, {..., 0}, {..., 50}],
+ msg_flags=0}, MSG_ZEROCOPY) = 60
+ +0 > P. 61:121(60) ack 1
+ +.01 < . 1:1(0) ack 121 win 257
diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt
new file mode 100644
index 000000000000..59f5903f285c
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test kernel behavior with NULL as buffer pointer
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.2 < . 1:1(0) ack 1 win 514
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 write(4, NULL, 1000) = -1 EFAULT (Bad address)
+ +0 send(4, NULL, 1000, 0) = -1 EFAULT (Bad address)
+ +0 sendto(4, NULL, 1000, 0, ..., ...) = -1 EFAULT (Bad address)
+
+ +0 < . 1:1001(1000) ack 1 win 200
+ +0 read(4, NULL, 1000) = -1 EFAULT (Bad address)
+ +0 recv(4, NULL, 1000, 0) = -1 EFAULT (Bad address)
+ +0 recvfrom(4, NULL, 1000, 0, ..., ...) = -1 EFAULT (Bad address)
diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt
new file mode 100644
index 000000000000..d7fdb43a8e89
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test tcpi_last_data_recv for active session
+`./defaults.sh`
+
+// Create a socket and set it to non-blocking.
++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
++0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR)
++0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
++0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
++0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
++.030 < S. 0:0(0) ack 1 win 10000 <mss 1000,sackOK,nop,nop,nop,wscale 8>
++0 > . 1:1(0) ack 1
+
++1 %{ assert 990 <= tcpi_last_data_recv <= 1010, tcpi_last_data_recv }%
+
++0 < . 1:1001(1000) ack 1 win 300
++0 > . 1:1(0) ack 1001
+
++0 %{ assert tcpi_last_data_recv <= 10, tcpi_last_data_recv }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt
new file mode 100644
index 000000000000..a9bcd46f6cb6
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test rwnd limited time in tcp_info for client side.
+
+`./defaults.sh`
+
+// Create a socket and set it to non-blocking.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR)
+ +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
+ +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+ +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
+
+// Server advertises 0 receive window.
+ +.01 < S. 0:0(0) ack 1 win 0 <mss 1000,nop,nop,sackOK>
+
+ +0 > . 1:1(0) ack 1
+ +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0
+ +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking
+
+// Make sure that initial rwnd limited time is 0.
+ +0 %{ assert tcpi_rwnd_limited == 0, tcpi_rwnd_limited }%
+
+// Receive window limited time starts here.
+ +0 write(3, ..., 1000) = 1000
+
+// Check that rwnd limited time in tcp_info is around 0.1s.
+ +.1 %{ assert 98000 <= tcpi_rwnd_limited <= 110000, tcpi_rwnd_limited }%
+
+// Server opens the receive window.
+ +.1 < . 1:1(0) ack 1 win 2000
+
+// Check that rwnd limited time in tcp_info is around 0.2s.
+ +0 %{ assert 198000 <= tcpi_rwnd_limited <= 210000, tcpi_rwnd_limited }%
+
+ +0 > P. 1:1001(1000) ack 1
+
+// Server advertises a very small receive window.
+ +.03 < . 1:1(0) ack 1001 win 10
+
+// Receive window limited time starts again.
+ +0 write(3, ..., 1000) = 1000
+
+// Server opens the receive window again.
+ +.1 < . 1:1(0) ack 1001 win 2000
+// Check that rwnd limited time in tcp_info is around 0.3s
+// and busy time is 0.3 + 0.03 (server opened small window temporarily).
+ +0 %{ assert 298000 <= tcpi_rwnd_limited <= 310000, tcpi_rwnd_limited;\
+ assert 328000 <= tcpi_busy_time <= 340000, tcpi_busy_time;\
+}%
+
+ +0 > P. 1001:2001(1000) ack 1
+ +.02 < . 1:1(0) ack 2001 win 2000
+ +0 %{ assert 348000 <= tcpi_busy_time <= 360000, tcpi_busy_time }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt
new file mode 100644
index 000000000000..f0de2acd0f8e
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test send-buffer-limited time in tcp_info for client side.
+`./defaults.sh`
+
+// Create a socket and set it to non-blocking.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR)
+ +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
+ +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+ +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
+ +.01 < S. 0:0(0) ack 1 win 10000 <mss 1000,sackOK,nop,nop,nop,wscale 8>
+ +0 > . 1:1(0) ack 1
+ +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0
+ +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking
+ +0 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [10000], 4) = 0
+ +0 getsockopt(3, SOL_SOCKET, SO_SNDBUF, [20000], [4]) = 0
+
+ +.09...0.14 write(3, ..., 150000) = 150000
+
+ +.01 < . 1:1(0) ack 10001 win 10000
+
+ +.01 < . 1:1(0) ack 30001 win 10000
+
+// cwnd goes from 40(60KB) to 80(120KB), and that we hit the tiny sndbuf limit 10KB
+ +.01 < . 1:1(0) ack 70001 win 10000
+
+ +.02 < . 1:1(0) ack 95001 win 10000
+ +0 %{ assert 19000 <= tcpi_sndbuf_limited <= 21000, tcpi_sndbuf_limited; \
+ assert 49000 <= tcpi_busy_time <= 52000, tcpi_busy_time; \
+ assert 0 == tcpi_rwnd_limited, tcpi_rwnd_limited }%
+
+// This ack frees up enough buffer so we are no longer
+// buffer limited (socket flag SOCK_NOSPACE is cleared)
+ +.02 < . 1:1(0) ack 150001 win 10000
+ +0 %{ assert 19000 <= tcpi_sndbuf_limited <= 21000, tcpi_sndbuf_limited;\
+ assert 69000 <= tcpi_busy_time <= 73000, tcpi_busy_time;\
+ assert 0 == tcpi_rwnd_limited, tcpi_rwnd_limited }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt
new file mode 100644
index 000000000000..2087ec0c746a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test that tx timestamping sends timestamps only for
+// the last byte of each sendmsg.
+`./defaults.sh
+`
+
+// Create a socket and set it to non-blocking.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR)
+ +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
+// Establish connection and verify that there was no error.
+ +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+ +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
+ +.01 < S. 0:0(0) ack 1 win 20000 <mss 1000,nop,nop,sackOK>
+ +0 > . 1:1(0) ack 1
+ +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0
+ +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking
+
+ +0 setsockopt(3, SOL_SOCKET, SO_TIMESTAMPING,
+ [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE |
+ SOF_TIMESTAMPING_OPT_ID], 4) = 0
+
+ +0 write(3, ..., 11000) = 11000
+ +0 > P. 1:10001(10000) ack 1
+ +.01 < . 1:1(0) ack 10001 win 4000
+ +0 > P. 10001:11001(1000) ack 1
+ +.01 < . 1:1(0) ack 11001 win 4000
+
+// Make sure that internal TCP timestamps are not overwritten and we have sane
+// RTT measurement.
+ +0 %{
+assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt
+}%
+
+// SCM_TSTAMP_SCHED for the last byte should be received almost immediately
+// once 10001 is acked at t=20ms.
+// setsockopt(..., [SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_OPT_ID], ...)
+// is called after when SYN is acked. So, we expect the last byte of the first
+// chunk to have a timestamp key of 10999 (i.e., 11000 - 1).
+ +0 recvmsg(3, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=20000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_SCHED,
+ ee_data=10999}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_SND for the last byte should be received almost immediately
+// once 10001 is acked at t=20ms.
+ +0 recvmsg(3, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=20000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_SND,
+ ee_data=10999}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_ACK for the last byte should be received at t=30ms.
+ +0 recvmsg(3, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=30000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_ACK,
+ ee_data=10999}}
+ ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt
new file mode 100644
index 000000000000..876024a31110
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test tx timestamping for partial writes (IPv4).
+`./defaults.sh
+`
+
+// Create a socket and set it to non-blocking.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR)
+ +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
+// Establish connection and verify that there was no error.
+ +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+ +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
+ +.01 < S. 0:0(0) ack 1 win 2000 <mss 1000,sackOK,TS val 700 ecr 100,nop,wscale 7>
+ +0 > . 1:1(0) ack 1 <nop,nop,TS val 200 ecr 700>
+ +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0
+
+ +0 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [1000], 4) = 0
+ +0 setsockopt(3, SOL_SOCKET, SO_TIMESTAMPING,
+ [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE |
+ SOF_TIMESTAMPING_OPT_ID], 4) = 0
+
+// We have a partial write.
+ +0 write(3, ..., 10000) = 2964
+ +0 > . 1:989(988) ack 1 <nop,nop,TS val 110 ecr 700>
+ +0 > P. 989:1977(988) ack 1 <nop,nop,TS val 110 ecr 700>
+ +.01 < . 1:1(0) ack 1977 win 92 <nop,nop,TS val 800 ecr 200>
+ +0 > P. 1977:2965(988) ack 1 <nop,nop,TS val 114 ecr 800>
+ +.01 < . 1:1(0) ack 2965 win 92 <nop,nop,TS val 800 ecr 200>
+
+// Make sure that internal TCP timestamps are not overwritten and we have sane
+// RTT measurement.
+ +0 %{
+assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt
+}%
+
+// SCM_TSTAMP_SCHED for the first chunk should be received almost immediately
+// after the first ack at t=20ms.
+ +0 recvmsg(3, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=20000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_SCHED,
+ ee_data=2963}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_SND for the first chunk should be received almost immediately
+// after the first ack at t=20ms.
+ +0 recvmsg(3, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=20000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_SND,
+ ee_data=2963}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_ACK for the first chunk should be received after the last ack at
+// t=30ms.
+ +0 recvmsg(3, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=30000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_ACK,
+ ee_data=2963}}
+ ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt
new file mode 100644
index 000000000000..84d94780e6be
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test tx timestamping for server-side (IPv4).
+`./defaults.sh
+`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.01 < . 1:1(0) ack 1 win 514
+
+ +0 accept(3, ..., ...) = 4
+ +0 setsockopt(4, SOL_SOCKET, SO_TIMESTAMPING,
+ [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE |
+ SOF_TIMESTAMPING_OPT_ID], 4) = 0
+
+// Write two 2KB chunks.
+// setsockopt(..., [SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_OPT_ID], ...)
+// is called after when SYN is acked. So, we expect the last byte of the first
+// and the second chunks to have timestamp keys of 1999 (i.e., 2000 - 1) and
+// 3999 (i.e., 4000 - 1) respectively.
+ +0 write(4, ..., 2000) = 2000
+ +0 write(4, ..., 2000) = 2000
+ +0 > P. 1:2001(2000) ack 1
+ +0 > P. 2001:4001(2000) ack 1
+ +.01 < . 1:1(0) ack 2001 win 514
+ +.01 < . 1:1(0) ack 4001 win 514
+
+// Make sure that internal TCP timestamps are not overwritten and we have sane
+// RTT measurement.
+ +0 %{
+assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt
+}%
+
+// SCM_TSTAMP_SCHED for the first chunk should be received almost immediately
+// after write at t=10ms.
+ +0 recvmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=10000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_SCHED,
+ ee_data=1999}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_SND for the first chunk should be received almost immediately
+// after write at t=10ms.
+ +0 recvmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=10000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_SND,
+ ee_data=1999}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_SCHED for the second chunk should be received almost immediately
+// after that at t=10ms.
+ +0 recvmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=10000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_SCHED,
+ ee_data=3999}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_SND for the second chunk should be received almost immediately
+// after that at t=10ms.
+ +0 recvmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=10000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_SND,
+ ee_data=3999}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_ACK for the first chunk should be received at t=20ms.
+ +0 recvmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=20000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_ACK,
+ ee_data=1999}}
+ ]}, MSG_ERRQUEUE) = 0
+// SCM_TSTAMP_ACK for the second chunk should be received at t=30ms.
+ +0 recvmsg(4, {msg_name(...)=...,
+ msg_iov(1)=[{...,0}],
+ msg_flags=MSG_ERRQUEUE|MSG_TRUNC,
+ msg_control=[
+ {cmsg_level=SOL_SOCKET,
+ cmsg_type=SCM_TIMESTAMPING,
+ cmsg_data={scm_sec=0,scm_nsec=30000000}},
+ {cmsg_level=CMSG_LEVEL_IP,
+ cmsg_type=CMSG_TYPE_RECVERR,
+ cmsg_data={ee_errno=ENOMSG,
+ ee_origin=SO_EE_ORIGIN_TIMESTAMPING,
+ ee_type=0,
+ ee_code=0,
+ ee_info=SCM_TSTAMP_ACK,
+ ee_data=3999}}
+ ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt
new file mode 100644
index 000000000000..e61424a7bd0a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test that we send FIN packet with correct TSval
+--tcp_ts_tick_usecs=1000
+--tolerance_usecs=7000
+
+`./defaults.sh`
+
+// Create a socket.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+// Establish a connection.
+ +0 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0>
+ +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100>
+ +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100>
+ +0 accept(3, ..., ...) = 4
+
+ +1 close(4) = 0
+// Check that FIN TSval is updated properly, one second has passed since last sent packet.
+ +0 > F. 1:1(0) ack 1 <nop,nop,TS val 1200 ecr 200>
diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt
new file mode 100644
index 000000000000..174ce9a1bfc0
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test that we reject TS val updates on a packet with invalid ACK sequence
+
+`./defaults.sh
+`
+
+// Create a socket.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+// Establish a connection.
+ +.1 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0>
+ +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100>
+ +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100>
+ +0 accept(3, ..., ...) = 4
+
+// bad packet with high tsval (its ACK sequence is above our sndnxt)
+ +0 < F. 1:1(0) ack 9999 win 20000 <nop,nop,TS val 200000 ecr 100>
+
+
+ +0 < . 1:1001(1000) ack 1 win 20000 <nop,nop,TS val 201 ecr 100>
+ +0 > . 1:1(0) ack 1001 <nop,nop,TS val 200 ecr 201>
diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt
new file mode 100644
index 000000000000..2e3b3bb7493a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test that we send RST packet with correct TSval
+--tcp_ts_tick_usecs=1000
+
+`./defaults.sh`
+
+// Create a socket.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+// Establish a connection.
+ +0 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0>
+ +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100>
+ +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100>
+ +0 accept(3, ..., ...) = 4
+
+ +0 < . 1:1001(1000) ack 1 win 20000 <nop,nop,TS val 201 ecr 100>
+ +0 > . 1:1(0) ack 1001 <nop,nop,TS val 200 ecr 201>
+
+ +1 close(4) = 0
+// Check that RST TSval is updated properly, one second has passed since last sent packet.
+ +0 > R. 1:1(0) ack 1001 <nop,nop,TS val 1200 ecr 201>
diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt
new file mode 100644
index 000000000000..183051ba0cae
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+
+`./defaults.sh`
+
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+
+ +0 < S 0:0(0) win 0 <mss 1460>
+ +0 > S. 0:0(0) ack 1 <mss 1460>
+
+ +.1 < . 1:1(0) ack 1 win 65530
+ +0 accept(3, ..., ...) = 4
+
+ +0 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0
+ +0 write(4, ..., 24) = 24
+ +0 > P. 1:25(24) ack 1
+ +.1 < . 1:1(0) ack 25 win 65530
+ +0 %{ assert tcpi_probes == 0, tcpi_probes; \
+ assert tcpi_backoff == 0, tcpi_backoff }%
+
+// install a qdisc dropping all packets
+ +0 `tc qdisc delete dev tun0 root 2>/dev/null ; tc qdisc add dev tun0 root pfifo limit 0`
+ +0 write(4, ..., 24) = 24
+ // When qdisc is congested we retry every 500ms
+ // (TCP_RESOURCE_PROBE_INTERVAL) and therefore
+ // we retry 6 times before hitting 3s timeout.
+ // First verify that the connection is alive:
++3.250 write(4, ..., 24) = 24
+ // Now verify that shortly after that the socket is dead:
+ +.100 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out)
+
+ +0 %{ assert tcpi_probes == 6, tcpi_probes; \
+ assert tcpi_backoff == 0, tcpi_backoff }%
+ +0 close(4) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt
new file mode 100644
index 000000000000..2efe02bfba9c
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+`./defaults.sh`
+
+// Initialize connection
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
+ +.1 < . 1:1(0) ack 1 win 32792
+
+
+ +0 accept(3, ..., ...) = 4
+
+// Okay, we received nothing, and decide to close this idle socket.
+// We set TCP_USER_TIMEOUT to 3 seconds because really it is not worth
+// trying hard to cleanly close this flow, at the price of keeping
+// a TCP structure in kernel for about 1 minute !
+ +2 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0
+ +0 close(4) = 0
+
+ +0 > F. 1:1(0) ack 1
+ +.3~+.400 > F. 1:1(0) ack 1
+ +.3~+.400 > F. 1:1(0) ack 1
+ +.6~+.800 > F. 1:1(0) ack 1
+
+// We finally receive something from the peer, but it is way too late
+// Our socket vanished because TCP_USER_TIMEOUT was really small
+ +0 < . 1:2(1) ack 1 win 32792
+ +0 > R 1:1(0)
diff --git a/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt b/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt
new file mode 100644
index 000000000000..8bd60226ccfc
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Verify that established connections drop a segment without the ACK flag set.
+
+`./defaults.sh`
+
+// Create a socket.
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+// Establish a connection.
+ +0 < S 0:0(0) win 20000 <mss 1000,sackOK,nop,nop>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
+ +.01 < . 1:1(0) ack 1 win 20000
+ +0 accept(3, ..., ...) = 4
+
+// Receive a segment with no flags set, verify that it's not enqueued.
+ +.01 < - 1:1001(1000) win 20000
+ +0 ioctl(4, SIOCINQ, [0]) = 0
+
+// Receive a segment with ACK flag set, verify that it is enqueued.
+ +.01 < . 1:1001(1000) ack 1 win 20000
+ +0 ioctl(4, SIOCINQ, [1000]) = 0
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 1a706d03bb6b..9a85f93c33d8 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -44,9 +44,11 @@ struct tls_crypto_info_keys {
};
static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type,
- struct tls_crypto_info_keys *tls12)
+ struct tls_crypto_info_keys *tls12,
+ char key_generation)
{
- memset(tls12, 0, sizeof(*tls12));
+ memset(tls12, key_generation, sizeof(*tls12));
+ memset(tls12, 0, sizeof(struct tls_crypto_info));
switch (cipher_type) {
case TLS_CIPHER_CHACHA20_POLY1305:
@@ -275,7 +277,7 @@ TEST_F(tls_basic, recseq_wrap)
if (self->notls)
SKIP(return, "no TLS support");
- tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12);
+ tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12, 0);
memset(&tls12.aes128.rec_seq, 0xff, sizeof(tls12.aes128.rec_seq));
ASSERT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
@@ -391,7 +393,7 @@ FIXTURE_SETUP(tls)
SKIP(return, "Unsupported cipher in FIPS mode");
tls_crypto_info_init(variant->tls_version, variant->cipher_type,
- &tls12);
+ &tls12, 0);
ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
@@ -1175,7 +1177,7 @@ TEST_F(tls, bidir)
struct tls_crypto_info_keys tls12;
tls_crypto_info_init(variant->tls_version, variant->cipher_type,
- &tls12);
+ &tls12, 0);
ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12,
tls12.len);
@@ -1614,7 +1616,7 @@ TEST_F(tls, getsockopt)
EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type);
/* get the full crypto_info */
- tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect);
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect, 0);
len = expect.len;
memrnd(&get, sizeof(get));
EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0);
@@ -1668,6 +1670,464 @@ TEST_F(tls, recv_efault)
EXPECT_EQ(memcmp(rec2, recv_mem + 9, ret - 9), 0);
}
+#define TLS_RECORD_TYPE_HANDSHAKE 0x16
+/* key_update, length 1, update_not_requested */
+static const char key_update_msg[] = "\x18\x00\x00\x01\x00";
+static void tls_send_keyupdate(struct __test_metadata *_metadata, int fd)
+{
+ size_t len = sizeof(key_update_msg);
+
+ EXPECT_EQ(tls_send_cmsg(fd, TLS_RECORD_TYPE_HANDSHAKE,
+ (char *)key_update_msg, len, 0),
+ len);
+}
+
+static void tls_recv_keyupdate(struct __test_metadata *_metadata, int fd, int flags)
+{
+ char buf[100];
+
+ EXPECT_EQ(tls_recv_cmsg(_metadata, fd, TLS_RECORD_TYPE_HANDSHAKE, buf, sizeof(buf), flags),
+ sizeof(key_update_msg));
+ EXPECT_EQ(memcmp(buf, key_update_msg, sizeof(key_update_msg)), 0);
+}
+
+/* set the key to 0 then 1 for RX, immediately to 1 for TX */
+TEST_F(tls_basic, rekey_rx)
+{
+ struct tls_crypto_info_keys tls12_0, tls12_1;
+ char const *test_str = "test_message";
+ int send_len = strlen(test_str) + 1;
+ char buf[20];
+ int ret;
+
+ if (self->notls)
+ return;
+
+ tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+ &tls12_0, 0);
+ tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+ &tls12_1, 1);
+
+ ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_1, tls12_1.len);
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_0, tls12_0.len);
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_1, tls12_1.len);
+ EXPECT_EQ(ret, 0);
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+/* set the key to 0 then 1 for TX, immediately to 1 for RX */
+TEST_F(tls_basic, rekey_tx)
+{
+ struct tls_crypto_info_keys tls12_0, tls12_1;
+ char const *test_str = "test_message";
+ int send_len = strlen(test_str) + 1;
+ char buf[20];
+ int ret;
+
+ if (self->notls)
+ return;
+
+ tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+ &tls12_0, 0);
+ tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+ &tls12_1, 1);
+
+ ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_0, tls12_0.len);
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_1, tls12_1.len);
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_1, tls12_1.len);
+ EXPECT_EQ(ret, 0);
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, rekey)
+{
+ char const *test_str_1 = "test_message_before_rekey";
+ char const *test_str_2 = "test_message_after_rekey";
+ struct tls_crypto_info_keys tls12;
+ int send_len;
+ char buf[100];
+
+ if (variant->tls_version != TLS_1_3_VERSION)
+ return;
+
+ /* initial send/recv */
+ send_len = strlen(test_str_1) + 1;
+ EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+ /* update TX key */
+ tls_send_keyupdate(_metadata, self->fd);
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+ /* send after rekey */
+ send_len = strlen(test_str_2) + 1;
+ EXPECT_EQ(send(self->fd, test_str_2, send_len, 0), send_len);
+
+ /* can't receive the KeyUpdate without a control message */
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+
+ /* get KeyUpdate */
+ tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+ /* recv blocking -> -EKEYEXPIRED */
+ EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), 0), -1);
+ EXPECT_EQ(errno, EKEYEXPIRED);
+
+ /* recv non-blocking -> -EKEYEXPIRED */
+ EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1);
+ EXPECT_EQ(errno, EKEYEXPIRED);
+
+ /* update RX key */
+ EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+ /* recv after rekey */
+ EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(buf, test_str_2, send_len), 0);
+}
+
+TEST_F(tls, rekey_fail)
+{
+ char const *test_str_1 = "test_message_before_rekey";
+ char const *test_str_2 = "test_message_after_rekey";
+ struct tls_crypto_info_keys tls12;
+ int send_len;
+ char buf[100];
+
+ /* initial send/recv */
+ send_len = strlen(test_str_1) + 1;
+ EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+ /* update TX key */
+ tls_send_keyupdate(_metadata, self->fd);
+
+ if (variant->tls_version != TLS_1_3_VERSION) {
+ /* just check that rekey is not supported and return */
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1);
+ EXPECT_EQ(errno, EBUSY);
+ return;
+ }
+
+ /* successful update */
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+ /* invalid update: change of version */
+ tls_crypto_info_init(TLS_1_2_VERSION, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* invalid update (RX socket): change of version */
+ tls_crypto_info_init(TLS_1_2_VERSION, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* invalid update: change of cipher */
+ if (variant->cipher_type == TLS_CIPHER_AES_GCM_256)
+ tls_crypto_info_init(variant->tls_version, TLS_CIPHER_CHACHA20_POLY1305, &tls12, 1);
+ else
+ tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_256, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* send after rekey, the invalid updates shouldn't have an effect */
+ send_len = strlen(test_str_2) + 1;
+ EXPECT_EQ(send(self->fd, test_str_2, send_len, 0), send_len);
+
+ /* can't receive the KeyUpdate without a control message */
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+
+ /* get KeyUpdate */
+ tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+ /* recv blocking -> -EKEYEXPIRED */
+ EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), 0), -1);
+ EXPECT_EQ(errno, EKEYEXPIRED);
+
+ /* recv non-blocking -> -EKEYEXPIRED */
+ EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1);
+ EXPECT_EQ(errno, EKEYEXPIRED);
+
+ /* update RX key */
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+ /* recv after rekey */
+ EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(buf, test_str_2, send_len), 0);
+}
+
+TEST_F(tls, rekey_peek)
+{
+ char const *test_str_1 = "test_message_before_rekey";
+ struct tls_crypto_info_keys tls12;
+ int send_len;
+ char buf[100];
+
+ if (variant->tls_version != TLS_1_3_VERSION)
+ return;
+
+ send_len = strlen(test_str_1) + 1;
+ EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len);
+
+ /* update TX key */
+ tls_send_keyupdate(_metadata, self->fd);
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+ EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+ EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+ /* can't receive the KeyUpdate without a control message */
+ EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_PEEK), -1);
+
+ /* peek KeyUpdate */
+ tls_recv_keyupdate(_metadata, self->cfd, MSG_PEEK);
+
+ /* get KeyUpdate */
+ tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+ /* update RX key */
+ EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+}
+
+TEST_F(tls, splice_rekey)
+{
+ int send_len = TLS_PAYLOAD_MAX_LEN / 2;
+ char mem_send[TLS_PAYLOAD_MAX_LEN];
+ char mem_recv[TLS_PAYLOAD_MAX_LEN];
+ struct tls_crypto_info_keys tls12;
+ int p[2];
+
+ if (variant->tls_version != TLS_1_3_VERSION)
+ return;
+
+ memrnd(mem_send, sizeof(mem_send));
+
+ ASSERT_GE(pipe(p), 0);
+ EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len);
+
+ /* update TX key */
+ tls_send_keyupdate(_metadata, self->fd);
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+ EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len);
+
+ EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len);
+ EXPECT_EQ(read(p[0], mem_recv, send_len), send_len);
+ EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+
+ /* can't splice the KeyUpdate */
+ EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* peek KeyUpdate */
+ tls_recv_keyupdate(_metadata, self->cfd, MSG_PEEK);
+
+ /* get KeyUpdate */
+ tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+ /* can't splice before updating the key */
+ EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), -1);
+ EXPECT_EQ(errno, EKEYEXPIRED);
+
+ /* update RX key */
+ EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+ EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len);
+ EXPECT_EQ(read(p[0], mem_recv, send_len), send_len);
+ EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, rekey_peek_splice)
+{
+ char const *test_str_1 = "test_message_before_rekey";
+ struct tls_crypto_info_keys tls12;
+ int send_len;
+ char buf[100];
+ char mem_recv[TLS_PAYLOAD_MAX_LEN];
+ int p[2];
+
+ if (variant->tls_version != TLS_1_3_VERSION)
+ return;
+
+ ASSERT_GE(pipe(p), 0);
+
+ send_len = strlen(test_str_1) + 1;
+ EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len);
+
+ /* update TX key */
+ tls_send_keyupdate(_metadata, self->fd);
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+ EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+ EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+ EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len);
+ EXPECT_EQ(read(p[0], mem_recv, send_len), send_len);
+ EXPECT_EQ(memcmp(mem_recv, test_str_1, send_len), 0);
+}
+
+TEST_F(tls, rekey_getsockopt)
+{
+ struct tls_crypto_info_keys tls12;
+ struct tls_crypto_info_keys tls12_get;
+ socklen_t len;
+
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 0);
+
+ len = tls12.len;
+ EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_get, &len), 0);
+ EXPECT_EQ(len, tls12.len);
+ EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0);
+
+ len = tls12.len;
+ EXPECT_EQ(getsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_get, &len), 0);
+ EXPECT_EQ(len, tls12.len);
+ EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0);
+
+ if (variant->tls_version != TLS_1_3_VERSION)
+ return;
+
+ tls_send_keyupdate(_metadata, self->fd);
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+ tls_recv_keyupdate(_metadata, self->cfd, 0);
+ EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+ len = tls12.len;
+ EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_get, &len), 0);
+ EXPECT_EQ(len, tls12.len);
+ EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0);
+
+ len = tls12.len;
+ EXPECT_EQ(getsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_get, &len), 0);
+ EXPECT_EQ(len, tls12.len);
+ EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0);
+}
+
+TEST_F(tls, rekey_poll_pending)
+{
+ char const *test_str = "test_message_after_rekey";
+ struct tls_crypto_info_keys tls12;
+ struct pollfd pfd = { };
+ int send_len;
+ int ret;
+
+ if (variant->tls_version != TLS_1_3_VERSION)
+ return;
+
+ /* update TX key */
+ tls_send_keyupdate(_metadata, self->fd);
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+ /* get KeyUpdate */
+ tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+ /* send immediately after rekey */
+ send_len = strlen(test_str) + 1;
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+
+ /* key hasn't been updated, expect cfd to be non-readable */
+ pfd.fd = self->cfd;
+ pfd.events = POLLIN;
+ EXPECT_EQ(poll(&pfd, 1, 0), 0);
+
+ ret = fork();
+ ASSERT_GE(ret, 0);
+
+ if (ret) {
+ int pid2, status;
+
+ /* wait before installing the new key */
+ sleep(1);
+
+ /* update RX key while poll() is sleeping */
+ EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+ pid2 = wait(&status);
+ EXPECT_EQ(pid2, ret);
+ EXPECT_EQ(status, 0);
+ } else {
+ pfd.fd = self->cfd;
+ pfd.events = POLLIN;
+ EXPECT_EQ(poll(&pfd, 1, 5000), 1);
+
+ exit(!__test_passed(_metadata));
+ }
+}
+
+TEST_F(tls, rekey_poll_delay)
+{
+ char const *test_str = "test_message_after_rekey";
+ struct tls_crypto_info_keys tls12;
+ struct pollfd pfd = { };
+ int send_len;
+ int ret;
+
+ if (variant->tls_version != TLS_1_3_VERSION)
+ return;
+
+ /* update TX key */
+ tls_send_keyupdate(_metadata, self->fd);
+ tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+ EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+ /* get KeyUpdate */
+ tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+ ret = fork();
+ ASSERT_GE(ret, 0);
+
+ if (ret) {
+ int pid2, status;
+
+ /* wait before installing the new key */
+ sleep(1);
+
+ /* update RX key while poll() is sleeping */
+ EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+ sleep(1);
+ send_len = strlen(test_str) + 1;
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+
+ pid2 = wait(&status);
+ EXPECT_EQ(pid2, ret);
+ EXPECT_EQ(status, 0);
+ } else {
+ pfd.fd = self->cfd;
+ pfd.events = POLLIN;
+ EXPECT_EQ(poll(&pfd, 1, 5000), 1);
+ exit(!__test_passed(_metadata));
+ }
+}
+
FIXTURE(tls_err)
{
int fd, cfd;
@@ -1696,7 +2156,7 @@ FIXTURE_SETUP(tls_err)
int ret;
tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128,
- &tls12);
+ &tls12, 0);
ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls);
@@ -2118,7 +2578,7 @@ TEST(tls_v6ops) {
int sfd, ret, fd;
socklen_t len, len2;
- tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12);
+ tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12, 0);
addr.sin6_family = AF_INET6;
addr.sin6_addr = in6addr_any;
@@ -2177,7 +2637,7 @@ TEST(prequeue) {
len = sizeof(addr);
memrnd(buf, sizeof(buf));
- tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls12);
+ tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls12, 0);
addr.sin_family = AF_INET;
addr.sin_addr.s_addr = htonl(INADDR_ANY);
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 640bc43452fa..88fa1d53ba2b 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -92,6 +92,9 @@ run_udp() {
echo "udp"
run_in_netns ${args}
+ echo "udp sendmmsg"
+ run_in_netns ${args} -m
+
echo "udp gso"
run_in_netns ${args} -S 0
diff --git a/tools/testing/selftests/net/vlan_bridge_binding.sh b/tools/testing/selftests/net/vlan_bridge_binding.sh
new file mode 100755
index 000000000000..e7cb8c678bde
--- /dev/null
+++ b/tools/testing/selftests/net/vlan_bridge_binding.sh
@@ -0,0 +1,256 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+ALL_TESTS="
+ test_binding_on
+ test_binding_off
+ test_binding_toggle_on
+ test_binding_toggle_off
+ test_binding_toggle_on_when_upper_down
+ test_binding_toggle_off_when_upper_down
+ test_binding_toggle_on_when_lower_down
+ test_binding_toggle_off_when_lower_down
+"
+
+setup_prepare()
+{
+ local port
+
+ ip_link_add br up type bridge vlan_filtering 1
+
+ for port in d1 d2 d3; do
+ ip_link_add $port type veth peer name r$port
+ ip_link_set_up $port
+ ip_link_set_up r$port
+ ip_link_set_master $port br
+ done
+
+ bridge_vlan_add vid 11 dev br self
+ bridge_vlan_add vid 11 dev d1 master
+
+ bridge_vlan_add vid 12 dev br self
+ bridge_vlan_add vid 12 dev d2 master
+
+ bridge_vlan_add vid 13 dev br self
+ bridge_vlan_add vid 13 dev d1 master
+ bridge_vlan_add vid 13 dev d2 master
+
+ bridge_vlan_add vid 14 dev br self
+ bridge_vlan_add vid 14 dev d1 master
+ bridge_vlan_add vid 14 dev d2 master
+ bridge_vlan_add vid 14 dev d3 master
+}
+
+operstate_is()
+{
+ local dev=$1; shift
+ local expect=$1; shift
+
+ local operstate=$(ip -j link show $dev | jq -r .[].operstate)
+ if [[ $operstate == UP ]]; then
+ operstate=1
+ elif [[ $operstate == DOWN || $operstate == LOWERLAYERDOWN ]]; then
+ operstate=0
+ fi
+ echo -n $operstate
+ [[ $operstate == $expect ]]
+}
+
+check_operstate()
+{
+ local dev=$1; shift
+ local expect=$1; shift
+ local operstate
+
+ operstate=$(busywait 1000 \
+ operstate_is "$dev" "$expect")
+ check_err $? "Got operstate of $operstate, expected $expect"
+}
+
+add_one_vlan()
+{
+ local link=$1; shift
+ local id=$1; shift
+
+ ip_link_add $link.$id link $link type vlan id $id "$@"
+}
+
+add_vlans()
+{
+ add_one_vlan br 11 "$@"
+ add_one_vlan br 12 "$@"
+ add_one_vlan br 13 "$@"
+ add_one_vlan br 14 "$@"
+}
+
+set_vlans()
+{
+ ip link set dev br.11 "$@"
+ ip link set dev br.12 "$@"
+ ip link set dev br.13 "$@"
+ ip link set dev br.14 "$@"
+}
+
+down_netdevs()
+{
+ local dev
+
+ for dev in "$@"; do
+ ip_link_set_down $dev
+ done
+}
+
+check_operstates()
+{
+ local opst_11=$1; shift
+ local opst_12=$1; shift
+ local opst_13=$1; shift
+ local opst_14=$1; shift
+
+ check_operstate br.11 $opst_11
+ check_operstate br.12 $opst_12
+ check_operstate br.13 $opst_13
+ check_operstate br.14 $opst_14
+}
+
+do_test_binding()
+{
+ local inject=$1; shift
+ local what=$1; shift
+ local opsts_d1=$1; shift
+ local opsts_d2=$1; shift
+ local opsts_d12=$1; shift
+ local opsts_d123=$1; shift
+
+ RET=0
+
+ defer_scope_push
+ down_netdevs d1
+ $inject
+ check_operstates $opsts_d1
+ defer_scope_pop
+
+ defer_scope_push
+ down_netdevs d2
+ $inject
+ check_operstates $opsts_d2
+ defer_scope_pop
+
+ defer_scope_push
+ down_netdevs d1 d2
+ $inject
+ check_operstates $opsts_d12
+ defer_scope_pop
+
+ defer_scope_push
+ down_netdevs d1 d2 d3
+ $inject
+ check_operstates $opsts_d123
+ defer_scope_pop
+
+ log_test "Test bridge_binding $what"
+}
+
+do_test_binding_on()
+{
+ local inject=$1; shift
+ local what=$1; shift
+
+ do_test_binding "$inject" "$what" \
+ "0 1 1 1" \
+ "1 0 1 1" \
+ "0 0 0 1" \
+ "0 0 0 0"
+}
+
+do_test_binding_off()
+{
+ local inject=$1; shift
+ local what=$1; shift
+
+ do_test_binding "$inject" "$what" \
+ "1 1 1 1" \
+ "1 1 1 1" \
+ "1 1 1 1" \
+ "0 0 0 0"
+}
+
+test_binding_on()
+{
+ add_vlans bridge_binding on
+ set_vlans up
+ do_test_binding_on : "on"
+}
+
+test_binding_off()
+{
+ add_vlans bridge_binding off
+ set_vlans up
+ do_test_binding_off : "off"
+}
+
+test_binding_toggle_on()
+{
+ add_vlans bridge_binding off
+ set_vlans up
+ set_vlans type vlan bridge_binding on
+ do_test_binding_on : "off->on"
+}
+
+test_binding_toggle_off()
+{
+ add_vlans bridge_binding on
+ set_vlans up
+ set_vlans type vlan bridge_binding off
+ do_test_binding_off : "on->off"
+}
+
+dfr_set_binding_on()
+{
+ set_vlans type vlan bridge_binding on
+ defer set_vlans type vlan bridge_binding off
+}
+
+dfr_set_binding_off()
+{
+ set_vlans type vlan bridge_binding off
+ defer set_vlans type vlan bridge_binding on
+}
+
+test_binding_toggle_on_when_lower_down()
+{
+ add_vlans bridge_binding off
+ set_vlans up
+ do_test_binding_on dfr_set_binding_on "off->on when lower down"
+}
+
+test_binding_toggle_off_when_lower_down()
+{
+ add_vlans bridge_binding on
+ set_vlans up
+ do_test_binding_off dfr_set_binding_off "on->off when lower down"
+}
+
+test_binding_toggle_on_when_upper_down()
+{
+ add_vlans bridge_binding off
+ set_vlans type vlan bridge_binding on
+ set_vlans up
+ do_test_binding_on : "off->on when upper down"
+}
+
+test_binding_toggle_off_when_upper_down()
+{
+ add_vlans bridge_binding on
+ set_vlans type vlan bridge_binding off
+ set_vlans up
+ do_test_binding_off : "on->off when upper down"
+}
+
+trap defer_scopes_cleanup EXIT
+setup_prepare
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py b/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py
new file mode 100755
index 000000000000..0f44a6199495
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py
@@ -0,0 +1,21 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Script that checks that SFQ rejects a limit of 1 at the kernel
+# level. We can't use iproute2's tc because it does not accept a limit
+# of 1.
+
+import sys
+import os
+
+from pyroute2 import IPRoute
+from pyroute2.netlink.exceptions import NetlinkError
+
+ip = IPRoute()
+ifidx = ip.link_lookup(ifname=sys.argv[1])
+
+try:
+ ip.tc('add', 'sfq', ifidx, limit=1)
+ sys.exit(1)
+except NetlinkError:
+ sys.exit(0)
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
index 16d51936b385..50e8d72781cb 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
@@ -208,5 +208,25 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "4d6f",
+ "name": "Check that limit of 1 is rejected",
+ "category": [
+ "qdisc",
+ "sfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ ],
+ "cmdUnderTest": "./scripts/sfq_rejects_limit_1.py $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "sfq",
+ "matchCount": "0",
+ "teardown": [
+ ]
}
]
diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README
index 84ee217ba8ee..680ce666ceb5 100644
--- a/tools/testing/vsock/README
+++ b/tools/testing/vsock/README
@@ -36,6 +36,21 @@ Invoke test binaries in both directions as follows:
--control-port=1234 \
--peer-cid=3
+Some tests are designed to produce kernel memory leaks. Leaks detection,
+however, is deferred to Kernel Memory Leak Detector. It is recommended to enable
+kmemleak (CONFIG_DEBUG_KMEMLEAK=y) and explicitly trigger a scan after each test
+suite run, e.g.
+
+ # echo clear > /sys/kernel/debug/kmemleak
+ # $TEST_BINARY ...
+ # echo "wait for any grace periods" && sleep 2
+ # echo scan > /sys/kernel/debug/kmemleak
+ # echo "wait for kmemleak" && sleep 5
+ # echo scan > /sys/kernel/debug/kmemleak
+ # cat /sys/kernel/debug/kmemleak
+
+For more information see Documentation/dev-tools/kmemleak.rst.
+
vsock_perf utility
-------------------
'vsock_perf' is a simple tool to measure vsock performance. It works in
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 34e9dac0a105..7058dc614c25 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -401,7 +401,7 @@ void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret)
*/
void send_byte(int fd, int expected_ret, int flags)
{
- const uint8_t byte = 'A';
+ static const uint8_t byte = 'A';
send_buf(fd, &byte, sizeof(byte), flags, expected_ret);
}
@@ -420,7 +420,7 @@ void recv_byte(int fd, int expected_ret, int flags)
recv_buf(fd, &byte, sizeof(byte), flags, expected_ret);
if (byte != 'A') {
- fprintf(stderr, "unexpected byte read %c\n", byte);
+ fprintf(stderr, "unexpected byte read 0x%02x\n", byte);
exit(EXIT_FAILURE);
}
}
@@ -486,8 +486,7 @@ void list_tests(const struct test_case *test_cases)
exit(EXIT_FAILURE);
}
-void skip_test(struct test_case *test_cases, size_t test_cases_len,
- const char *test_id_str)
+static unsigned long parse_test_id(const char *test_id_str, size_t test_cases_len)
{
unsigned long test_id;
char *endptr = NULL;
@@ -505,9 +504,35 @@ void skip_test(struct test_case *test_cases, size_t test_cases_len,
exit(EXIT_FAILURE);
}
+ return test_id;
+}
+
+void skip_test(struct test_case *test_cases, size_t test_cases_len,
+ const char *test_id_str)
+{
+ unsigned long test_id = parse_test_id(test_id_str, test_cases_len);
test_cases[test_id].skip = true;
}
+void pick_test(struct test_case *test_cases, size_t test_cases_len,
+ const char *test_id_str)
+{
+ static bool skip_all = true;
+ unsigned long test_id;
+
+ if (skip_all) {
+ unsigned long i;
+
+ for (i = 0; i < test_cases_len; ++i)
+ test_cases[i].skip = true;
+
+ skip_all = false;
+ }
+
+ test_id = parse_test_id(test_id_str, test_cases_len);
+ test_cases[test_id].skip = false;
+}
+
unsigned long hash_djb2(const void *data, size_t len)
{
unsigned long hash = 5381;
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index ba84d296d8b7..e62f46b2b92a 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -62,6 +62,8 @@ void run_tests(const struct test_case *test_cases,
void list_tests(const struct test_case *test_cases);
void skip_test(struct test_case *test_cases, size_t test_cases_len,
const char *test_id_str);
+void pick_test(struct test_case *test_cases, size_t test_cases_len,
+ const char *test_id_str);
unsigned long hash_djb2(const void *data, size_t len);
size_t iovec_bytes(const struct iovec *iov, size_t iovnum);
unsigned long iovec_hash_djb2(const struct iovec *iov, size_t iovnum);
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 48f17641ca50..1eebbc0d5f61 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -22,12 +22,17 @@
#include <signal.h>
#include <sys/ioctl.h>
#include <linux/sockios.h>
+#include <linux/time64.h>
#include "vsock_test_zerocopy.h"
#include "timeout.h"
#include "control.h"
#include "util.h"
+/* Basic messages for control_writeulong(), control_readulong() */
+#define CONTROL_CONTINUE 1
+#define CONTROL_DONE 0
+
static void test_stream_connection_reset(const struct test_opts *opts)
{
union {
@@ -559,7 +564,7 @@ static time_t current_nsec(void)
exit(EXIT_FAILURE);
}
- return (ts.tv_sec * 1000000000ULL) + ts.tv_nsec;
+ return (ts.tv_sec * NSEC_PER_SEC) + ts.tv_nsec;
}
#define RCVTIMEO_TIMEOUT_SEC 1
@@ -599,7 +604,7 @@ static void test_seqpacket_timeout_client(const struct test_opts *opts)
}
read_overhead_ns = current_nsec() - read_enter_ns -
- 1000000000ULL * RCVTIMEO_TIMEOUT_SEC;
+ NSEC_PER_SEC * RCVTIMEO_TIMEOUT_SEC;
if (read_overhead_ns > READ_OVERHEAD_NSEC) {
fprintf(stderr,
@@ -1473,6 +1478,236 @@ static void test_stream_cred_upd_on_set_rcvlowat(const struct test_opts *opts)
test_stream_credit_update_test(opts, false);
}
+/* The goal of test leak_acceptq is to stress the race between connect() and
+ * close(listener). Implementation of client/server loops boils down to:
+ *
+ * client server
+ * ------ ------
+ * write(CONTINUE)
+ * expect(CONTINUE)
+ * listen()
+ * write(LISTENING)
+ * expect(LISTENING)
+ * connect() close()
+ */
+#define ACCEPTQ_LEAK_RACE_TIMEOUT 2 /* seconds */
+
+static void test_stream_leak_acceptq_client(const struct test_opts *opts)
+{
+ time_t tout;
+ int fd;
+
+ tout = current_nsec() + ACCEPTQ_LEAK_RACE_TIMEOUT * NSEC_PER_SEC;
+ do {
+ control_writeulong(CONTROL_CONTINUE);
+
+ fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+ if (fd >= 0)
+ close(fd);
+ } while (current_nsec() < tout);
+
+ control_writeulong(CONTROL_DONE);
+}
+
+/* Test for a memory leak. User is expected to run kmemleak scan, see README. */
+static void test_stream_leak_acceptq_server(const struct test_opts *opts)
+{
+ int fd;
+
+ while (control_readulong() == CONTROL_CONTINUE) {
+ fd = vsock_stream_listen(VMADDR_CID_ANY, opts->peer_port);
+ control_writeln("LISTENING");
+ close(fd);
+ }
+}
+
+/* Test for a memory leak. User is expected to run kmemleak scan, see README. */
+static void test_stream_msgzcopy_leak_errq_client(const struct test_opts *opts)
+{
+ struct pollfd fds = { 0 };
+ int fd;
+
+ fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+ if (fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ enable_so_zerocopy_check(fd);
+ send_byte(fd, 1, MSG_ZEROCOPY);
+
+ fds.fd = fd;
+ fds.events = 0;
+ if (poll(&fds, 1, -1) < 0) {
+ perror("poll");
+ exit(EXIT_FAILURE);
+ }
+
+ close(fd);
+}
+
+static void test_stream_msgzcopy_leak_errq_server(const struct test_opts *opts)
+{
+ int fd;
+
+ fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+ if (fd < 0) {
+ perror("accept");
+ exit(EXIT_FAILURE);
+ }
+
+ recv_byte(fd, 1, 0);
+ vsock_wait_remote_close(fd);
+ close(fd);
+}
+
+/* Test msgzcopy_leak_zcskb is meant to exercise sendmsg() error handling path,
+ * that might leak an skb. The idea is to fail virtio_transport_init_zcopy_skb()
+ * by hitting net.core.optmem_max limit in sock_omalloc(), specifically
+ *
+ * vsock_connectible_sendmsg
+ * virtio_transport_stream_enqueue
+ * virtio_transport_send_pkt_info
+ * virtio_transport_init_zcopy_skb
+ * . msg_zerocopy_realloc
+ * . msg_zerocopy_alloc
+ * . sock_omalloc
+ * . sk_omem_alloc + size > sysctl_optmem_max
+ * return -ENOMEM
+ *
+ * We abuse the implementation detail of net/socket.c:____sys_sendmsg().
+ * sk_omem_alloc can be precisely bumped by sock_kmalloc(), as it is used to
+ * fetch user-provided control data.
+ *
+ * While this approach works for now, it relies on assumptions regarding the
+ * implementation and configuration (for example, order of net.core.optmem_max
+ * can not exceed MAX_PAGE_ORDER), which may not hold in the future. A more
+ * resilient testing could be implemented by leveraging the Fault injection
+ * framework (CONFIG_FAULT_INJECTION), e.g.
+ *
+ * client# echo N > /sys/kernel/debug/failslab/ignore-gfp-wait
+ * client# echo 0 > /sys/kernel/debug/failslab/verbose
+ *
+ * void client(const struct test_opts *opts)
+ * {
+ * char buf[16];
+ * int f, s, i;
+ *
+ * f = open("/proc/self/fail-nth", O_WRONLY);
+ *
+ * for (i = 1; i < 32; i++) {
+ * control_writeulong(CONTROL_CONTINUE);
+ *
+ * s = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+ * enable_so_zerocopy_check(s);
+ *
+ * sprintf(buf, "%d", i);
+ * write(f, buf, strlen(buf));
+ *
+ * send(s, &(char){ 0 }, 1, MSG_ZEROCOPY);
+ *
+ * write(f, "0", 1);
+ * close(s);
+ * }
+ *
+ * control_writeulong(CONTROL_DONE);
+ * close(f);
+ * }
+ *
+ * void server(const struct test_opts *opts)
+ * {
+ * int fd;
+ *
+ * while (control_readulong() == CONTROL_CONTINUE) {
+ * fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+ * vsock_wait_remote_close(fd);
+ * close(fd);
+ * }
+ * }
+ *
+ * Refer to Documentation/fault-injection/fault-injection.rst.
+ */
+#define MAX_PAGE_ORDER 10 /* usually */
+#define PAGE_SIZE 4096
+
+/* Test for a memory leak. User is expected to run kmemleak scan, see README. */
+static void test_stream_msgzcopy_leak_zcskb_client(const struct test_opts *opts)
+{
+ size_t optmem_max, ctl_len, chunk_size;
+ struct msghdr msg = { 0 };
+ struct iovec iov;
+ char *chunk;
+ int fd, res;
+ FILE *f;
+
+ f = fopen("/proc/sys/net/core/optmem_max", "r");
+ if (!f) {
+ perror("fopen(optmem_max)");
+ exit(EXIT_FAILURE);
+ }
+
+ if (fscanf(f, "%zu", &optmem_max) != 1) {
+ fprintf(stderr, "fscanf(optmem_max) failed\n");
+ exit(EXIT_FAILURE);
+ }
+
+ fclose(f);
+
+ fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+ if (fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ enable_so_zerocopy_check(fd);
+
+ ctl_len = optmem_max - 1;
+ if (ctl_len > PAGE_SIZE << MAX_PAGE_ORDER) {
+ fprintf(stderr, "Try with net.core.optmem_max = 100000\n");
+ exit(EXIT_FAILURE);
+ }
+
+ chunk_size = CMSG_SPACE(ctl_len);
+ chunk = malloc(chunk_size);
+ if (!chunk) {
+ perror("malloc");
+ exit(EXIT_FAILURE);
+ }
+ memset(chunk, 0, chunk_size);
+
+ iov.iov_base = &(char){ 0 };
+ iov.iov_len = 1;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = chunk;
+ msg.msg_controllen = ctl_len;
+
+ errno = 0;
+ res = sendmsg(fd, &msg, MSG_ZEROCOPY);
+ if (res >= 0 || errno != ENOMEM) {
+ fprintf(stderr, "Expected ENOMEM, got errno=%d res=%d\n",
+ errno, res);
+ exit(EXIT_FAILURE);
+ }
+
+ close(fd);
+}
+
+static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts)
+{
+ int fd;
+
+ fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+ if (fd < 0) {
+ perror("accept");
+ exit(EXIT_FAILURE);
+ }
+
+ vsock_wait_remote_close(fd);
+ close(fd);
+}
+
static struct test_case test_cases[] = {
{
.name = "SOCK_STREAM connection reset",
@@ -1603,6 +1838,21 @@ static struct test_case test_cases[] = {
.run_client = test_seqpacket_unsent_bytes_client,
.run_server = test_seqpacket_unsent_bytes_server,
},
+ {
+ .name = "SOCK_STREAM leak accept queue",
+ .run_client = test_stream_leak_acceptq_client,
+ .run_server = test_stream_leak_acceptq_server,
+ },
+ {
+ .name = "SOCK_STREAM MSG_ZEROCOPY leak MSG_ERRQUEUE",
+ .run_client = test_stream_msgzcopy_leak_errq_client,
+ .run_server = test_stream_msgzcopy_leak_errq_server,
+ },
+ {
+ .name = "SOCK_STREAM MSG_ZEROCOPY leak completion skb",
+ .run_client = test_stream_msgzcopy_leak_zcskb_client,
+ .run_server = test_stream_msgzcopy_leak_zcskb_server,
+ },
{},
};
@@ -1644,6 +1894,11 @@ static const struct option longopts[] = {
.val = 's',
},
{
+ .name = "pick",
+ .has_arg = required_argument,
+ .val = 't',
+ },
+ {
.name = "help",
.has_arg = no_argument,
.val = '?',
@@ -1680,6 +1935,8 @@ static void usage(void)
" --peer-cid <cid> CID of the other side\n"
" --peer-port <port> AF_VSOCK port used for the test [default: %d]\n"
" --list List of tests that will be executed\n"
+ " --pick <test_id> Test ID to execute selectively;\n"
+ " use multiple --pick options to select more tests\n"
" --skip <test_id> Test ID to skip;\n"
" use multiple --skip options to skip more tests\n",
DEFAULT_PEER_PORT
@@ -1736,6 +1993,10 @@ int main(int argc, char **argv)
skip_test(test_cases, ARRAY_SIZE(test_cases) - 1,
optarg);
break;
+ case 't':
+ pick_test(test_cases, ARRAY_SIZE(test_cases) - 1,
+ optarg);
+ break;
case '?':
default:
usage();