diff options
Diffstat (limited to 'tools/testing/selftests/net/packetdrill')
15 files changed, 654 insertions, 3 deletions
diff --git a/tools/testing/selftests/net/packetdrill/config b/tools/testing/selftests/net/packetdrill/config index c4a19a785521..b7df8bf30920 100644 --- a/tools/testing/selftests/net/packetdrill/config +++ b/tools/testing/selftests/net/packetdrill/config @@ -4,8 +4,8 @@ CONFIG_IPV6=y CONFIG_NET_NS=y CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_FQ=y -CONFIG_PROC_SYSCTL=y CONFIG_SYN_COOKIES=y +CONFIG_SYSCTL=y CONFIG_TCP_CONG_CUBIC=y CONFIG_TCP_MD5SIG=y CONFIG_TUN=y diff --git a/tools/testing/selftests/net/packetdrill/tcp_advmss_pmtu_ipv4.pkt b/tools/testing/selftests/net/packetdrill/tcp_advmss_pmtu_ipv4.pkt new file mode 100644 index 000000000000..f2ef931b77a1 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_advmss_pmtu_ipv4.pkt @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Test that IPv4 advertised MSS in SYN-ACK is derived from the configured +// interface MTU (1500 -> MSS 1460), not the ICMP-learned Path MTU. + +--ip_version=ipv4 + +`./defaults.sh +ethtool -K tun0 tso off +` + +// +// Connection 1: Learn PMTU exception (MTU 1200 -> MSS 1160) +// + 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 65535 <mss 1460,sackOK,nop,nop,nop,wscale 8> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 + +// Send a full 1460-byte segment + +0 write(4, ..., 1460) = 1460 + +0 > P. 1:1461(1460) ack 1 + +// ICMP Fragmentation Needed arrives indicating next-hop MTU 1200 + +0 < icmp unreachable frag_needed mtu 1200 [1:1461(1460)] + +// Local host retransmits using the learned MTU 1200 (MSS = 1200 - 40 = 1160) + +0 > . 1:1161(1160) ack 1 + +0 > P. 1161:1461(300) ack 1 + +0 < R 1:1(0) ack 1461 win 0 + +// Close connection 1 and listener + +0 close(4) = 0 + +0 close(3) = 0 + +// +// Connection 2: New connection from the same peer +// + +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 65535 <mss 1460,sackOK,nop,nop,nop,wscale 8> + +// Verify: SYN-ACK MUST advertise configured MSS 1460, NOT the learned PMTU MSS 1160 + +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 + +// Verify: Outgoing transmit MSS is still constrained by the learned PMTU 1200 + +0 write(4, ..., 1460) = 1460 + +0 > . 1:1161(1160) ack 1 + +0 > P. 1161:1461(300) ack 1 + +0 < . 1:1(0) ack 1461 win 257 + +// Clean up + +0 close(4) = 0 + +0 > F. 1461:1461(0) ack 1 + +0 < F. 1:1(0) ack 1462 win 257 + +0 > . 1462:1462(0) ack 2 + +0 close(3) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_advmss_pmtu_ipv6.pkt b/tools/testing/selftests/net/packetdrill/tcp_advmss_pmtu_ipv6.pkt new file mode 100644 index 000000000000..c7638b11a815 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_advmss_pmtu_ipv6.pkt @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Test that IPv6 advertised MSS in SYN-ACK is derived from the configured +// interface MTU (1520 -> MSS 1460), not the ICMPv6-learned Path MTU. + +--ip_version=ipv6 + +`./defaults.sh +ethtool -K tun0 tso off +` + +// +// Connection 1: Learn PMTU exception (MTU 1280 -> MSS 1220) +// + 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 65535 <mss 1460,sackOK,nop,nop,nop,wscale 8> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 + +// Send a full 1460-byte segment + +0 write(4, ..., 1460) = 1460 + +0 > P. 1:1461(1460) ack 1 + +// ICMPv6 Packet Too Big arrives indicating next-hop MTU 1280 + +0 < icmp packet_too_big mtu 1280 [1:1461(1460)] + +// Local host retransmits using the learned MTU 1280 (MSS = 1280 - 40 - 20 = 1220) + +0 > . 1:1221(1220) ack 1 + +0 > P. 1221:1461(240) ack 1 + +0 < R 1:1(0) ack 1461 win 0 + +// Close connection 1 and listener + +0 close(4) = 0 + +0 close(3) = 0 + +// +// Connection 2: New connection from the same peer +// + +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 65535 <mss 1460,sackOK,nop,nop,nop,wscale 8> + +// Verify: SYN-ACK MUST advertise configured MSS 1460, NOT the learned PMTU MSS 1220 + +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 + +// Verify: Outgoing transmit MSS is still constrained by the learned PMTU 1280 + +0 write(4, ..., 1460) = 1460 + +0 > . 1:1221(1220) ack 1 + +0 > P. 1221:1461(240) ack 1 + +0 < . 1:1(0) ack 1461 win 257 + +// Clean up + +0 close(4) = 0 + +0 > F. 1461:1461(0) ack 1 + +0 < F. 1:1(0) ack 1462 win 257 + +0 > . 1462:1462(0) ack 2 + +0 close(3) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_disorder_fin_in_FIN_WAIT.pkt b/tools/testing/selftests/net/packetdrill/tcp_disorder_fin_in_FIN_WAIT.pkt new file mode 100644 index 000000000000..336cbf7815c8 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_disorder_fin_in_FIN_WAIT.pkt @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Check fix in 795a7dfbc3d9 ("net: tcp: accept old ack during closing") + +// Set up config. +`./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 65535 <mss 1000,sackOK,nop,nop,nop,wscale 7> + * > 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 + + +0 shutdown(4, SHUT_WR) = 0 + * > F. 1:1(0) ack 1 + +// We expect to receive one ACK. +// But what happens if a FIN was already in transmt and received out-of-order ? + + +0 < . 2:2(0) ack 2 win 257 + +// This FIN packet was sent before the prior ACK (see ack 1). + +0 < F. 1:1(0) ack 1 win 257 + +// Even if the FIN is received out-of-order, we should ACK it. + + * > . 2:2(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt index 6c0f32c40f19..12882be10f2e 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -36,7 +36,7 @@ +0 read(4, ..., 100000) = 4000 -// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd +// If queue is empty, accept a packet even if its end_seq is above rcv_mwnd_seq +0 < P. 4001:54001(50000) ack 1 win 257 * > . 1:1(0) ack 54001 win 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_neg_window.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_neg_window.pkt new file mode 100644 index 000000000000..b9ab264b2a11 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_neg_window.pkt @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test maximum advertised window limit when rcv_nxt advances past +// rcv_mwnd_seq. The "usable window" must be properly clamped to zero +// rather than becoming negative. + +--mss=1000 + +`./defaults.sh` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 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 win 18980 <mss 1460,nop,wscale 0> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + +// A too big packet is accepted if the receive queue is empty. It +// does not trigger an immediate ACK. + +0 < P. 1:20001(20000) ack 1 win 257 + +0 %{ assert tcpi_bytes_received == 20000, tcpi_bytes_received; }% + +// Send a RST immediately so that there is no rcv_wup/rcv_mwnd_seq update yet + +0 < R. 20001:20001(0) ack 1 win 257 + +// Verify that the RST was accepted. Indirectly this also verifies that no +// immediate ACK was sent for the data packet above. + +0 < . 20001:20001(0) ack 1 win 257 + +0 > R 1:1(0) diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_allowed.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_allowed.pkt new file mode 100644 index 000000000000..6af0e0eb183a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_allowed.pkt @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_shrink_window=1 +sysctl -q net.ipv4.tcp_rmem="4096 32768 $((32*1024*1024))"` + + 0 `nstat -n` + +// 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,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 10> + +0 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:10001(10000) ack 1 win 257 + * > . 1:1(0) ack 10001 win 15 + + +0 < P. 10001:11024(1023) ack 1 win 257 + * > . 1:1(0) ack 11024 win 13 + +// Max window seq advertised 10001 + 15*1024 = 25361, last advertised: 11024 + 13*1024 = 24336 + +// Segment beyond the max window is dropped + +0 < P. 11024:25362(14338) ack 1 win 257 + * > . 1:1(0) ack 11024 win 13 + +// Segment using the max window is accepted + +0 < P. 11024:25361(14337) ack 1 win 257 + * > . 1:1(0) ack 25361 win 0 + +// Check LINUX_MIB_BEYOND_WINDOW has been incremented once + +0 `nstat | grep TcpExtBeyondWindow | grep -q " 1 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_nomem.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_nomem.pkt new file mode 100644 index 000000000000..a80eb55dc69a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_nomem.pkt @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +// When tcp_receive_window() < tcp_max_receive_window(), tcp_sequence() accepts +// packets that would be dropped under normal conditions (i.e. tcp_receive_window() +// equal to tcp_max_receive_window()). +// Test that such packets are handled as expected for RWIN == 0 and for RWIN > 0. + +--mss=1000 + +`./defaults.sh` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [1000000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 4> + +0 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + +// Put 1040000 bytes into the receive buffer + +0 < P. 1:65001(65000) ack 1 win 257 + * > . 1:1(0) ack 65001 + +0 < P. 65001:130001(65000) ack 1 win 257 + * > . 1:1(0) ack 130001 + +0 < P. 130001:195001(65000) ack 1 win 257 + * > . 1:1(0) ack 195001 + +0 < P. 195001:260001(65000) ack 1 win 257 + * > . 1:1(0) ack 260001 + +0 < P. 260001:325001(65000) ack 1 win 257 + * > . 1:1(0) ack 325001 + +0 < P. 325001:390001(65000) ack 1 win 257 + * > . 1:1(0) ack 390001 + +0 < P. 390001:455001(65000) ack 1 win 257 + * > . 1:1(0) ack 455001 + +0 < P. 455001:520001(65000) ack 1 win 257 + * > . 1:1(0) ack 520001 + +0 < P. 520001:585001(65000) ack 1 win 257 + * > . 1:1(0) ack 585001 + +0 < P. 585001:650001(65000) ack 1 win 257 + * > . 1:1(0) ack 650001 + +0 < P. 650001:715001(65000) ack 1 win 257 + * > . 1:1(0) ack 715001 + +0 < P. 715001:780001(65000) ack 1 win 257 + * > . 1:1(0) ack 780001 + +0 < P. 780001:845001(65000) ack 1 win 257 + * > . 1:1(0) ack 845001 + +0 < P. 845001:910001(65000) ack 1 win 257 + * > . 1:1(0) ack 910001 + +0 < P. 910001:975001(65000) ack 1 win 257 + * > . 1:1(0) ack 975001 + +0 < P. 975001:1040001(65000) ack 1 win 257 + * > . 1:1(0) ack 1040001 + +// Trigger an extreme memory squeeze by shrinking SO_RCVBUF + +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [16000], 4) = 0 + + +0 < P. 1040001:1105001(65000) ack 1 win 257 + * > . 1:1(0) ack 1040001 win 0 +// Check LINUX_MIB_TCPRCVQDROP has been incremented + +0 `nstat -s | grep TcpExtTCPRcvQDrop| grep -q " 1 "` + +// RWIN == 0: rcv_wup = 1040001, rcv_wnd = 0, rcv_mwnd_seq > 1105001 (significantly larger, typically ~1970000) + +// Accept pure ack with seq in max adv. window + +0 write(4, ..., 1000) = 1000 + +0 > P. 1:1001(1000) ack 1040001 win 0 + +0 < . 1105001:1105001(0) ack 1001 win 257 + +// In order segment, in max adv. window -> drop (SKB_DROP_REASON_TCP_ZEROWINDOW) + +0 < P. 1040001:1041001(1000) ack 1001 win 257 + +0 > . 1001:1001(0) ack 1040001 win 0 +// Ooo partial segment, in max adv. window -> drop (SKB_DROP_REASON_TCP_ZEROWINDOW) + +0 < P. 1039001:1041001(2000) ack 1001 win 257 + +0 > . 1001:1001(0) ack 1040001 win 0 <nop,nop,sack 1039001:1040001> +// Check LINUX_MIB_TCPZEROWINDOWDROP has been incremented twice + +0 `nstat -s | grep TcpExtTCPZeroWindowDrop| grep -q " 2 "` + +// Ooo segment, in max adv. window -> drop (SKB_DROP_REASON_TCP_OVERWINDOW) + +0 < P. 1105001:1106001(1000) ack 1001 win 257 + +0 > . 1001:1001(0) ack 1040001 win 0 +// Ooo segment, beyond max adv. window -> drop (SKB_DROP_REASON_TCP_INVALID_SEQUENCE) + +0 < P. 2000001:2001001(1000) ack 1001 win 257 + +0 > . 1001:1001(0) ack 1040001 win 0 +// Check LINUX_MIB_BEYOND_WINDOW has been incremented twice + +0 `nstat -s | grep TcpExtBeyondWindow | grep -q " 2 "` + +// Read all data + +0 read(4, ..., 2000000) = 1040000 + * > . 1001:1001(0) ack 1040001 + +// RWIN > 0: rcv_wup = 1040001, 0 < rcv_wnd < 32000, rcv_mwnd_seq > 1105001 (significantly larger, typically ~1970000) + +// Accept pure ack with seq in max adv. window, beyond adv. window + +0 write(4, ..., 1000) = 1000 + +0 > P. 1001:2001(1000) ack 1040001 + +0 < . 1105001:1105001(0) ack 2001 win 257 + +// In order segment, in max adv. window, in adv. window -> accept +// Note: This also ensures that we cannot hit the empty queue exception in tcp_sequence() in the following tests + +0 < P. 1040001:1041001(1000) ack 2001 win 257 + * > . 2001:2001(0) ack 1041001 + +// Ooo partial segment, in adv. window -> accept + +0 < P. 1040001:1042001(2000) ack 2001 win 257 + +0 > . 2001:2001(0) ack 1042001 <nop,nop,sack 1040001:1041001> + +// Ooo segment, in max adv. window, beyond adv. window -> drop (SKB_DROP_REASON_TCP_OVERWINDOW) + +0 < P. 1105001:1106001(1000) ack 2001 win 257 + +0 > . 2001:2001(0) ack 1042001 +// Ooo segment, beyond max adv. window, beyond adv. window -> drop (SKB_DROP_REASON_TCP_INVALID_SEQUENCE) + +0 < P. 2000001:2001001(1000) ack 2001 win 257 + +0 > . 2001:2001(0) ack 1042001 +// Check LINUX_MIB_BEYOND_WINDOW has been incremented twice + +0 `nstat -s | grep TcpExtBeyondWindow | grep -q " 4 "` + +// We are allowed to go beyond the window and buffer with one packet + +0 < P. 1042001:1062001(20000) ack 2001 win 257 + * > . 2001:2001(0) ack 1062001 + +0 < P. 1062001:1082001(20000) ack 2001 win 257 + * > . 2001:2001(0) ack 1082001 win 0 + +// But not more: In order segment, in max adv. window -> drop (SKB_DROP_REASON_TCP_ZEROWINDOW) + +0 < P. 1082001:1083001(1000) ack 2001 win 257 + * > . 2001:2001(0) ack 1082001 +// Check LINUX_MIB_TCPZEROWINDOWDROP has been incremented again + +0 `nstat -s | grep TcpExtTCPZeroWindowDrop| grep -q " 3 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rfc5961_ack-out-of-window.pkt b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_ack-out-of-window.pkt new file mode 100644 index 000000000000..2776b8728085 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_ack-out-of-window.pkt @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// RFC 5961 Section 5.2 / RFC 793 Section 3.9: an incoming segment's +// ACK value must lie in [SND.UNA - MAX.SND.WND, SND.NXT]; otherwise +// the receiver MUST discard the segment and send a challenge ACK +// back. Exercise both edges of that window in a single connection. + +`./defaults.sh +sysctl -q net.ipv4.tcp_invalid_ratelimit=0 +` + + 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 + +// Three-way handshake. Peer advertises rwnd = 1000 (no wscale), so +// MAX.SND.WND is tracked as 1000. + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> ++.1 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +// ---- Upper edge: SEG.ACK > SND.NXT -------------------------------- +// Server has sent nothing yet, so SND.UNA = SND.NXT = 1. +// Peer sends a pure ACK with SEG.ACK = 2, beyond SND.NXT. + +0 < . 1:1(0) ack 2 win 1000 +// Expect a challenge ACK: <SEQ = SND.NXT = 1, ACK = RCV.NXT = 1>. + +0 > . 1:1(0) ack 1 + +// Advance SND.UNA past MAX.SND.WND so that the lower edge becomes +// reachable. Issue two 1-MSS writes so each skb is exactly one MSS +// and PSH is set by tcp_push() at the end of each sendmsg, keeping +// the setup independent of the TSO / tcp_fragment split path. + +0 write(4, ..., 1000) = 1000 + +0 > P. 1:1001(1000) ack 1 ++.01 < . 1:1(0) ack 1001 win 1000 + +0 write(4, ..., 1000) = 1000 + +0 > P. 1001:2001(1000) ack 1 ++.01 < . 1:1(0) ack 2001 win 1000 +// Now SND.UNA = SND.NXT = 2001, MAX.SND.WND = 1000, bytes_acked = 2000. + +// ---- Lower edge: SEG.ACK < SND.UNA - MAX.SND.WND ------------------ +// SND.UNA - MAX.SND.WND = 2001 - 1000 = 1001, so SEG.ACK = 1000 falls +// below the acceptable range. + +0 < . 1:1(0) ack 1000 win 1000 +// Expect a challenge ACK: <SEQ = SND.NXT = 2001, ACK = RCV.NXT = 1>. + +0 > . 2001:2001(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_rfc5961_reject-old-ack.pkt b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_reject-old-ack.pkt new file mode 100644 index 000000000000..32dd9de1d366 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_reject-old-ack.pkt @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +`./defaults.sh +sysctl -q net.ipv4.tcp_invalid_ratelimit=0 +` + +// Test rejection of data segments carrying excessively old ACKs + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 ++0 bind(3, ..., ...) = 0 ++0 listen(3, 1024) = 0 + +// ---------------- Handshake ------------------- // ++0 < S 0:0(0) win 65535 ++0 > S. 0:0(0) ack 1 <...> ++0 < . 1:1(0) ack 1 win 65535 ++0 accept(3, ..., ...) = 4 + +// Populate receive memory so the following segment can use +// header prediction. ++0 < P. 1:501(500) ack 1 win 65535 ++0 > . 1:1(0) ack 501 + +// Send an in-sequence data segment carrying an excessively old ACK. ++0 < P. 501:1501(1000) ack 2794967397 win 65535 + +// Challenge ACK; RCV.NXT must remain 501. ++0 > . 1:1(0) ack 501 diff --git a/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt new file mode 100644 index 000000000000..3fc2de03658a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// RFC 9293 Section 3.10.7.4: in SYN-RECEIVED, an exact RST resets +// the connection. A non-exact in-window RST elicits a challenge ACK, +// while an out-of-window RST is silently discarded. + +`./defaults.sh` + +// An exact RST removes the request socket. + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, 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 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 1:1(0) win 1000 + +.1 < . 1:1(0) ack 1 win 1000 + +0 > R 1:1(0) + +0 close(3) = 0 + +// A non-exact in-window RST gets a challenge ACK and the request survives. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, 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 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 2:2(0) win 1000 + +0 > . 1:1(0) ack 1 + +0 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 + +// RST sequence validation precedes ACK validation. Even an RST|ACK +// with an unacceptable ACK value gets a challenge ACK. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, 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 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R. 2:2(0) ack 100 win 1000 + +0 > . 1:1(0) ack 1 + +0 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 + +// An out-of-window RST is silent and does not remove the request. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, 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 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 100001:100001(0) win 1000 + +.1 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_syncookies_ip4_9k.pkt b/tools/testing/selftests/net/packetdrill/tcp_syncookies_ip4_9k.pkt new file mode 100644 index 000000000000..60910069b3d7 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_syncookies_ip4_9k.pkt @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Check syncookies. +// +// Check we are able to rebuild client sack, wscale, ecn and mss options. +// IPv4 msstab[4] = { 536, 1300, 1440, 1460 } + +--ip_version=ipv4 + +`./defaults.sh +sysctl -q net.ipv4.tcp_syncookies=2 +ip link set dev tun0 mtu 9000 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 10) = 0 + + +0 < S 0:0(0) win 32792 <mss 8960,sackOK,TS val 100 ecr 0,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 8960,sackOK,TS val 4000 ecr 100,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 1024 <nop,nop,TS val 110 ecr 4000> + + +0 accept(3, ..., ...) = 4 + +// Check we properly infer from the final packet the other peer wanted mss >= 1460, wscale 10, sackOK and no ECN. +// Note that mss is limited to 1460 - 12 because of IPv4 msstab[] +// This is only possible because TCP TS option was used. +// Linux uses the SYNACK TS.val 6 low order bits to encode the options. + + +0 %{ assert tcpi_snd_mss == 1460 - 12, tcpi_snd_mss; \ + assert tcpi_snd_wscale == 10, tcpi_snd_wscale; \ + assert (tcpi_options & TCPI_OPT_SACK) != 0, tcpi_options; \ + assert (tcpi_options & TCPI_OPT_TIMESTAMPS) != 0, tcpi_options; \ + assert (tcpi_options & TCPI_OPT_WSCALE) != 0, tcpi_options; \ + assert (tcpi_options & TCPI_OPT_ECN) == 0, tcpi_options +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_syncookies_ip6_9k.pkt b/tools/testing/selftests/net/packetdrill/tcp_syncookies_ip6_9k.pkt new file mode 100644 index 000000000000..f333c61044bc --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_syncookies_ip6_9k.pkt @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Check syncookies. +// +// Check we are able to rebuild client sack, wscale, ecn and mss options. +// IPv6 msstab[4] = { 1280 - 60, 1480 - 60, 1500 - 60, 9000 - 60 } + +--ip_version=ipv6 + +`./defaults.sh +sysctl -q net.ipv4.tcp_syncookies=2 +ip link set dev tun0 mtu 9000 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 10) = 0 + + +0 < S 0:0(0) win 32792 <mss 8940,sackOK,TS val 100 ecr 0,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 8940,sackOK,TS val 4000 ecr 100,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 1024 <nop,nop,TS val 110 ecr 4000> + + +0 accept(3, ..., ...) = 4 + +// Check we properly infer from the final packet the other peer wanted mss >= 8940, wscale 10, sackOK and no ECN. +// This is only possible because TCP TS option was used. +// Linux uses the SYNACK TS.val 6 low order bits to encode the options. + + +0 %{ assert tcpi_snd_mss == 8940 - 12, tcpi_snd_mss; \ + assert tcpi_snd_wscale == 10, tcpi_snd_wscale; \ + assert (tcpi_options & TCPI_OPT_SACK) != 0, tcpi_options; \ + assert (tcpi_options & TCPI_OPT_TIMESTAMPS) != 0, tcpi_options; \ + assert (tcpi_options & TCPI_OPT_WSCALE) != 0, tcpi_options; \ + assert (tcpi_options & TCPI_OPT_ECN) == 0, tcpi_options +}% 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 index 174ce9a1bfc0..ee6baf7c36cf 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt @@ -19,7 +19,9 @@ // 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> - +// Challenge ACK for SEG.ACK > SND.NXT (RFC 5961 5.2 / RFC 793 3.9). +// ecr=200 (not 200000) proves ts_recent was not updated from the bad packet. + +0 > . 1:1(0) ack 1 <nop,nop,TS val 200 ecr 200> +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_urg_ptr_retransmit.pkt b/tools/testing/selftests/net/packetdrill/tcp_urg_ptr_retransmit.pkt new file mode 100644 index 000000000000..22f750ce09c1 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_urg_ptr_retransmit.pkt @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +--ip_version=ipv4 +// +// Reproduce urg_ptr being copied across segments on a multi-segment retransmit +// in urgent mode (regression since 10d3be569243). +// +// server (kernel, under test) client (packetdrill) +// | write(5000): 1:1001 .. 4001:5001 | mss 1000 from +// | -------------------------------------------> | the client SYN +// | send(MSG_OOB): 5001:5002 urg 1 | snd_up = 5002 +// | -------------------------------------------> | +// | SACK 2001:5002, leaving hole 1:2001| +// | <------------------------------------------- | +// | retransmit hole 1:2001 as ONE skb: | +// | seq=1, 2 segments, urg_ptr = 5002-1 = 5001| +// | tun tso off -> software GSO splits it: | +// | seg A 1:1001 urg_ptr 5001 (correct) | +// | seg B 1001:2001 urg_ptr ? | +// | want 5002-1001 = 4001 | +// | bug inherits 5001 <- caught here | +// | -------------------------------------------> | +// + +`./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 + +// 1. client force mss=1000 + +.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 + +// 2. server sends 5000 bytes; TSO on, so packetdrill sees whole super-skbs + +0 write(4, ..., 5000) = 5000 + +0 > P. 1:5001(5000) ack 1 + +// 3. server send OOB + +0 send(4, ..., 1, MSG_OOB) = 1 + +0 > PU. 5001:5002(1) ack 1 urg 1 + +// We could disable GSO at the start of the script, but then the PSH flag on +// the 5 initial server segments is not deterministic and hard to match. Keep +// TSO on for the initial send (one super-skb, stable PSH) and disable it only +// here, so software GSO splits the retransmit and each segment's urg_ptr is +// checked on the wire. + +0 `ethtool -K tun0 tso off gso off gro off lro off 2>/dev/null` + +// 4. SACKed blocks reach dupthresh -> fast retransmit of the 1:2001 hole. + +.05 < . 1:1(0) ack 1 win 320 <sack 2001:3001,nop,nop> + +0 < . 1:1(0) ack 1 win 320 <sack 2001:4001,nop,nop> + +0 < . 1:1(0) ack 1 win 320 <sack 2001:5002,nop,nop> + +// Retransmit must keep a per-segment urg_ptr (5002 - seg.seq): seg A 5001, +// seg B 4001. The fix sends the hole as two independent skbs, so seg B has +// no PSH. Unpatched it goes out as one super-skb whose GSO split copies +// urg_ptr onto seg B and also adds PSH there, so on an unpatched kernel the +// mismatch shows up on the PSH bit before the urg_ptr. + +0 > U. 1:1001(1000) ack 1 urg 5001 + +0 > U. 1001:2001(1000) ack 1 urg 4001 + + +.1 < . 1:1(0) ack 5002 win 320 |