summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/net/mptcp/mptcp_connect.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-10-04 13:38:03 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-10-04 13:38:03 -0700
commit0326074ff4652329f2a1a9c8685104576bd8d131 (patch)
tree9a7574c7ccb05bf4c7cb34fc5a65457bb8f495cb /tools/testing/selftests/net/mptcp/mptcp_connect.c
parent522667b24f08009591c90e75bfe2ffb67f555498 (diff)
parent681bf011b9b5989c6e9db6beb64494918aab9a43 (diff)
Merge tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - Introduce and use a single page frag cache for allocating small skb heads, clawing back the 10-20% performance regression in UDP flood test from previous fixes. - Run packets which already went thru HW coalescing thru SW GRO. This significantly improves TCP segment coalescing and simplifies deployments as different workloads benefit from HW or SW GRO. - Shrink the size of the base zero-copy send structure. - Move TCP init under a new slow / sleepable version of DO_ONCE(). BPF: - Add BPF-specific, any-context-safe memory allocator. - Add helpers/kfuncs for PKCS#7 signature verification from BPF programs. - Define a new map type and related helpers for user space -> kernel communication over a ring buffer (BPF_MAP_TYPE_USER_RINGBUF). - Allow targeting BPF iterators to loop through resources of one task/thread. - Add ability to call selected destructive functions. Expose crash_kexec() to allow BPF to trigger a kernel dump. Use CAP_SYS_BOOT check on the loading process to judge permissions. - Enable BPF to collect custom hierarchical cgroup stats efficiently by integrating with the rstat framework. - Support struct arguments for trampoline based programs. Only structs with size <= 16B and x86 are supported. - Invoke cgroup/connect{4,6} programs for unprivileged ICMP ping sockets (instead of just TCP and UDP sockets). - Add a helper for accessing CLOCK_TAI for time sensitive network related programs. - Support accessing network tunnel metadata's flags. - Make TCP SYN ACK RTO tunable by BPF programs with TCP Fast Open. - Add support for writing to Netfilter's nf_conn:mark. Protocols: - WiFi: more Extremely High Throughput (EHT) and Multi-Link Operation (MLO) work (802.11be, WiFi 7). - vsock: improve support for SO_RCVLOWAT. - SMC: support SO_REUSEPORT. - Netlink: define and document how to use netlink in a "modern" way. Support reporting missing attributes via extended ACK. - IPSec: support collect metadata mode for xfrm interfaces. - TCPv6: send consistent autoflowlabel in SYN_RECV state and RST packets. - TCP: introduce optional per-netns connection hash table to allow better isolation between namespaces (opt-in, at the cost of memory and cache pressure). - MPTCP: support TCP_FASTOPEN_CONNECT. - Add NEXT-C-SID support in Segment Routing (SRv6) End behavior. - Adjust IP_UNICAST_IF sockopt behavior for connected UDP sockets. - Open vSwitch: - Allow specifying ifindex of new interfaces. - Allow conntrack and metering in non-initial user namespace. - TLS: support the Korean ARIA-GCM crypto algorithm. - Remove DECnet support. Driver API: - Allow selecting the conduit interface used by each port in DSA switches, at runtime. - Ethernet Power Sourcing Equipment and Power Device support. - Add tc-taprio support for queueMaxSDU parameter, i.e. setting per traffic class max frame size for time-based packet schedules. - Support PHY rate matching - adapting between differing host-side and link-side speeds. - Introduce QUSGMII PHY mode and 1000BASE-KX interface mode. - Validate OF (device tree) nodes for DSA shared ports; make phylink-related properties mandatory on DSA and CPU ports. Enforcing more uniformity should allow transitioning to phylink. - Require that flash component name used during update matches one of the components for which version is reported by info_get(). - Remove "weight" argument from driver-facing NAPI API as much as possible. It's one of those magic knobs which seemed like a good idea at the time but is too indirect to use in practice. - Support offload of TLS connections with 256 bit keys. New hardware / drivers: - Ethernet: - Microchip KSZ9896 6-port Gigabit Ethernet Switch - Renesas Ethernet AVB (EtherAVB-IF) Gen4 SoCs - Analog Devices ADIN1110 and ADIN2111 industrial single pair Ethernet (10BASE-T1L) MAC+PHY. - Rockchip RV1126 Gigabit Ethernet (a version of stmmac IP). - Ethernet SFPs / modules: - RollBall / Hilink / Turris 10G copper SFPs - HALNy GPON module - WiFi: - CYW43439 SDIO chipset (brcmfmac) - CYW89459 PCIe chipset (brcmfmac) - BCM4378 on Apple platforms (brcmfmac) Drivers: - CAN: - gs_usb: HW timestamp support - Ethernet PHYs: - lan8814: cable diagnostics - Ethernet NICs: - Intel (100G): - implement control of FCS/CRC stripping - port splitting via devlink - L2TPv3 filtering offload - nVidia/Mellanox: - tunnel offload for sub-functions - MACSec offload, w/ Extended packet number and replay window offload - significantly restructure, and optimize the AF_XDP support, align the behavior with other vendors - Huawei: - configuring DSCP map for traffic class selection - querying standard FEC statistics - querying SerDes lane number via ethtool - Marvell/Cavium: - egress priority flow control - MACSec offload - AMD/SolarFlare: - PTP over IPv6 and raw Ethernet - small / embedded: - ax88772: convert to phylink (to support SFP cages) - altera: tse: convert to phylink - ftgmac100: support fixed link - enetc: standard Ethtool counters - macb: ZynqMP SGMII dynamic configuration support - tsnep: support multi-queue and use page pool - lan743x: Rx IP & TCP checksum offload - igc: add xdp frags support to ndo_xdp_xmit - Ethernet high-speed switches: - Marvell (prestera): - support SPAN port features (traffic mirroring) - nexthop object offloading - Microchip (sparx5): - multicast forwarding offload - QoS queuing offload (tc-mqprio, tc-tbf, tc-ets) - Ethernet embedded switches: - Marvell (mv88e6xxx): - support RGMII cmode - NXP (felix): - standardized ethtool counters - Microchip (lan966x): - QoS queuing offload (tc-mqprio, tc-tbf, tc-cbs, tc-ets) - traffic policing and mirroring - link aggregation / bonding offload - QUSGMII PHY mode support - Qualcomm 802.11ax WiFi (ath11k): - cold boot calibration support on WCN6750 - support to connect to a non-transmit MBSSID AP profile - enable remain-on-channel support on WCN6750 - Wake-on-WLAN support for WCN6750 - support to provide transmit power from firmware via nl80211 - support to get power save duration for each client - spectral scan support for 160 MHz - MediaTek WiFi (mt76): - WiFi-to-Ethernet bridging offload for MT7986 chips - RealTek WiFi (rtw89): - P2P support" * tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1864 commits) eth: pse: add missing static inlines once: rename _SLOW to _SLEEPABLE net: pse-pd: add regulator based PSE driver dt-bindings: net: pse-dt: add bindings for regulator based PoDL PSE controller ethtool: add interface to interact with Ethernet Power Equipment net: mdiobus: search for PSE nodes by parsing PHY nodes. net: mdiobus: fwnode_mdiobus_register_phy() rework error handling net: add framework to support Ethernet PSE and PDs devices dt-bindings: net: phy: add PoDL PSE property net: marvell: prestera: Propagate nh state from hw to kernel net: marvell: prestera: Add neighbour cache accounting net: marvell: prestera: add stub handler neighbour events net: marvell: prestera: Add heplers to interact with fib_notifier_info net: marvell: prestera: Add length macros for prestera_ip_addr net: marvell: prestera: add delayed wq and flush wq on deinit net: marvell: prestera: Add strict cleanup of fib arbiter net: marvell: prestera: Add cleanup of allocated fib_nodes net: marvell: prestera: Add router nexthops ABI eth: octeon: fix build after netif_napi_add() changes net/mlx5: E-Switch, Return EBUSY if can't get mode lock ...
Diffstat (limited to 'tools/testing/selftests/net/mptcp/mptcp_connect.c')
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c65
1 files changed, 57 insertions, 8 deletions
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 24d4e9cb617e..e54653ea2ed4 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -72,6 +72,8 @@ static int cfg_wait;
static uint32_t cfg_mark;
static char *cfg_input;
static int cfg_repeat = 1;
+static int cfg_truncate;
+static int cfg_rcv_trunc;
struct cfg_cmsg_types {
unsigned int cmsg_enabled:1;
@@ -95,11 +97,15 @@ static struct cfg_sockopt_types cfg_sockopt_types;
static void die_usage(void)
{
- fprintf(stderr, "Usage: mptcp_connect [-6] [-c cmsg] [-i file] [-I num] [-j] [-l] "
+ fprintf(stderr, "Usage: mptcp_connect [-6] [-c cmsg] [-f offset] [-i file] [-I num] [-j] [-l] "
"[-m mode] [-M mark] [-o option] [-p port] [-P mode] [-j] [-l] [-r num] "
"[-s MPTCP|TCP] [-S num] [-r num] [-t num] [-T num] [-u] [-w sec] connect_address\n");
fprintf(stderr, "\t-6 use ipv6\n");
fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n");
+ fprintf(stderr, "\t-f offset -- stop the I/O after receiving and sending the specified amount "
+ "of bytes. If there are unread bytes in the receive queue, that will cause a MPTCP "
+ "fastclose at close/shutdown. If offset is negative, expect the peer to close before "
+ "all the local data as been sent, thus toleration errors on write and EPIPE signals\n");
fprintf(stderr, "\t-i file -- read the data to send from the given file instead of stdin");
fprintf(stderr, "\t-I num -- repeat the transfer 'num' times. In listen mode accepts num "
"incoming connections, in client mode, disconnect and reconnect to the server\n");
@@ -382,7 +388,7 @@ static size_t do_rnd_write(const int fd, char *buf, const size_t len)
bw = write(fd, buf, do_w);
if (bw < 0)
- perror("write");
+ return bw;
/* let the join handshake complete, before going on */
if (cfg_join && first) {
@@ -571,7 +577,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after
.fd = peerfd,
.events = POLLIN | POLLOUT,
};
- unsigned int woff = 0, wlen = 0;
+ unsigned int woff = 0, wlen = 0, total_wlen = 0, total_rlen = 0;
char wbuf[8192];
set_nonblock(peerfd, true);
@@ -597,7 +603,16 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after
}
if (fds.revents & POLLIN) {
- len = do_rnd_read(peerfd, rbuf, sizeof(rbuf));
+ ssize_t rb = sizeof(rbuf);
+
+ /* limit the total amount of read data to the trunc value*/
+ if (cfg_truncate > 0) {
+ if (rb + total_rlen > cfg_truncate)
+ rb = cfg_truncate - total_rlen;
+ len = read(peerfd, rbuf, rb);
+ } else {
+ len = do_rnd_read(peerfd, rbuf, sizeof(rbuf));
+ }
if (len == 0) {
/* no more data to receive:
* peer has closed its write side
@@ -612,10 +627,13 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after
/* Else, still have data to transmit */
} else if (len < 0) {
+ if (cfg_rcv_trunc)
+ return 0;
perror("read");
return 3;
}
+ total_rlen += len;
do_write(outfd, rbuf, len);
}
@@ -628,12 +646,21 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after
if (wlen > 0) {
ssize_t bw;
+ /* limit the total amount of written data to the trunc value */
+ if (cfg_truncate > 0 && wlen + total_wlen > cfg_truncate)
+ wlen = cfg_truncate - total_wlen;
+
bw = do_rnd_write(peerfd, wbuf + woff, wlen);
- if (bw < 0)
+ if (bw < 0) {
+ if (cfg_rcv_trunc)
+ return 0;
+ perror("write");
return 111;
+ }
woff += bw;
wlen -= bw;
+ total_wlen += bw;
} else if (wlen == 0) {
/* We have no more data to send. */
fds.events &= ~POLLOUT;
@@ -652,10 +679,16 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after
}
if (fds.revents & (POLLERR | POLLNVAL)) {
+ if (cfg_rcv_trunc)
+ return 0;
fprintf(stderr, "Unexpected revents: "
"POLLERR/POLLNVAL(%x)\n", fds.revents);
return 5;
}
+
+ if (cfg_truncate > 0 && total_wlen >= cfg_truncate &&
+ total_rlen >= cfg_truncate)
+ break;
}
/* leave some time for late join/announce */
@@ -1160,11 +1193,13 @@ again:
}
/* close the client socket open only if we are not going to reconnect */
- ret = copyfd_io(fd_in, fd, 1, cfg_repeat == 1);
+ ret = copyfd_io(fd_in, fd, 1, 0);
if (ret)
return ret;
- if (--cfg_repeat > 0) {
+ if (cfg_truncate > 0) {
+ xdisconnect(fd, peer->ai_addrlen);
+ } else if (--cfg_repeat > 0) {
xdisconnect(fd, peer->ai_addrlen);
/* the socket could be unblocking at this point, we need the
@@ -1176,7 +1211,10 @@ again:
if (cfg_input)
close(fd_in);
goto again;
+ } else {
+ close(fd);
}
+
return 0;
}
@@ -1262,8 +1300,19 @@ static void parse_opts(int argc, char **argv)
{
int c;
- while ((c = getopt(argc, argv, "6c:hi:I:jlm:M:o:p:P:r:R:s:S:t:T:w:")) != -1) {
+ while ((c = getopt(argc, argv, "6c:f:hi:I:jlm:M:o:p:P:r:R:s:S:t:T:w:")) != -1) {
switch (c) {
+ case 'f':
+ cfg_truncate = atoi(optarg);
+
+ /* when receiving a fastclose, ignore PIPE signals and
+ * all the I/O errors later in the code
+ */
+ if (cfg_truncate < 0) {
+ cfg_rcv_trunc = true;
+ signal(SIGPIPE, handle_signal);
+ }
+ break;
case 'j':
cfg_join = true;
cfg_mode = CFG_MODE_POLL;