From d3836052fe098798b7a61a59c0032da473d801c4 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 1 May 2025 12:45:21 +0100 Subject: [PATCH 01/16] net: stmmac: intel: convert speed_mode_2500() to get_interfaces() TGL platforms support either SGMII or 2500BASE-X, which is determined by reading a SERDES register. Thus, plat->phy_interface (and phylink's supported_interfaces) depend on this. Use the new .get_interfaces() method to set both plat->phy_interface and the supported_interfaces bitmap. This removes the only user of the .speed_mode_2500() method. Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/E1uASLx-0021Qs-Uz@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- .../net/ethernet/stmicro/stmmac/dwmac-intel.c | 30 ++++++++++--------- .../net/ethernet/stmicro/stmmac/dwmac-intel.h | 1 - 2 files changed, 16 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 4b263a3c65a4..9a47015254bb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -284,25 +284,28 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data) } } -static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data) +static void tgl_get_interfaces(struct stmmac_priv *priv, void *bsp_priv, + unsigned long *interfaces) { - struct intel_priv_data *intel_priv = intel_data; - struct stmmac_priv *priv = netdev_priv(ndev); - int serdes_phy_addr = 0; - u32 data = 0; - - serdes_phy_addr = intel_priv->mdio_adhoc_addr; + struct intel_priv_data *intel_priv = bsp_priv; + phy_interface_t interface; + int data; /* Determine the link speed mode: 2.5Gbps/1Gbps */ - data = mdiobus_read(priv->mii, serdes_phy_addr, - SERDES_GCR); + data = mdiobus_read(priv->mii, intel_priv->mdio_adhoc_addr, SERDES_GCR); + if (data < 0) + return; - if (((data & SERDES_LINK_MODE_MASK) >> SERDES_LINK_MODE_SHIFT) == - SERDES_LINK_MODE_2G5) { + if (FIELD_GET(SERDES_LINK_MODE_MASK, data) == SERDES_LINK_MODE_2G5) { dev_info(priv->device, "Link Speed Mode: 2.5Gbps\n"); - priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX; priv->plat->mdio_bus_data->default_an_inband = false; + interface = PHY_INTERFACE_MODE_2500BASEX; + } else { + interface = PHY_INTERFACE_MODE_SGMII; } + + __set_bit(interface, interfaces); + priv->plat->phy_interface = interface; } /* Program PTP Clock Frequency for different variant of @@ -929,8 +932,7 @@ static int tgl_common_data(struct pci_dev *pdev, plat->rx_queues_to_use = 6; plat->tx_queues_to_use = 4; plat->clk_ptp_rate = 204800000; - plat->phy_interface = PHY_INTERFACE_MODE_SGMII; - plat->speed_mode_2500 = intel_speed_mode_2500; + plat->get_interfaces = tgl_get_interfaces; plat->safety_feat_cfg->tsoee = 1; plat->safety_feat_cfg->mrxpee = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h index a12f8e65f89f..7511c224b312 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h @@ -21,7 +21,6 @@ #define SERDES_RATE_MASK GENMASK(9, 8) #define SERDES_PCLK_MASK GENMASK(14, 12) /* PCLK rate to PHY */ #define SERDES_LINK_MODE_MASK GENMASK(2, 1) -#define SERDES_LINK_MODE_SHIFT 1 #define SERDES_PWR_ST_SHIFT 4 #define SERDES_PWR_ST_P0 0x0 #define SERDES_PWR_ST_P3 0x3 -- 2.51.0 From 9d165dc58055d98658941a33fef9e5da866af3e9 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 1 May 2025 12:45:27 +0100 Subject: [PATCH 02/16] net: stmmac: remove speed_mode_2500() method Remove the speed_mode_2500() platform method which is no longer used or necessary, being superseded by the more flexible get_interfaces() method. Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/E1uASM3-0021R3-2B@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 --- include/linux/stmmac.h | 1 - 2 files changed, 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5f66f816a249..28b62bd73e23 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7736,9 +7736,6 @@ int stmmac_dvr_probe(struct device *device, goto error_mdio_register; } - if (priv->plat->speed_mode_2500) - priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv); - ret = stmmac_pcs_setup(ndev); if (ret) goto error_pcs_setup; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 537bced69c46..26ddf95d23f9 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -241,7 +241,6 @@ struct plat_stmmacenet_data { int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); - void (*speed_mode_2500)(struct net_device *ndev, void *priv); int (*mac_finish)(struct net_device *ndev, void *priv, unsigned int mode, -- 2.51.0 From a2f6476ed18a3e96e65d47a757d5755421ae8f91 Mon Sep 17 00:00:00 2001 From: Pedro Falcato Date: Wed, 30 Apr 2025 16:45:41 +0100 Subject: [PATCH 03/16] mptcp: Align mptcp_inet6_sk with other protocols Ever since commit f5f80e32de12 ("ipv6: remove hard coded limitation on ipv6_pinfo") that protocols stopped using the old "obj_size - sizeof(struct ipv6_pinfo)" way of grabbing ipv6_pinfo, that severely restricted struct layout and caused fun, hard to see issues. However, mptcp_inet6_sk wasn't fixed (unlike tcp_inet6_sk). Do so. The non-cloned sockets already do the right thing using ipv6_pinfo_offset + the generic IPv6 code. Signed-off-by: Pedro Falcato Reviewed-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250430154541.1038561-1-pfalcato@suse.de Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 26ffa06c21e8..c4fd558307f2 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3142,9 +3142,9 @@ static int mptcp_disconnect(struct sock *sk, int flags) #if IS_ENABLED(CONFIG_MPTCP_IPV6) static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) { - unsigned int offset = sizeof(struct mptcp6_sock) - sizeof(struct ipv6_pinfo); + struct mptcp6_sock *msk6 = container_of(mptcp_sk(sk), struct mptcp6_sock, msk); - return (struct ipv6_pinfo *)(((u8 *)sk) + offset); + return &msk6->np; } static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk) -- 2.51.0 From 586ceac9acb71c4caf84552bd29b36c799c102a0 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 30 Apr 2025 17:53:29 -0700 Subject: [PATCH 04/16] ipv6: Restore fib6_config validation for SIOCADDRT. syzkaller reported out-of-bounds read in ipv6_addr_prefix(), where the prefix length was over 128. The cited commit accidentally removed some fib6_config validation from the ioctl path. Let's restore the validation. [0]: BUG: KASAN: slab-out-of-bounds in ip6_route_info_create (./include/net/ipv6.h:616 net/ipv6/route.c:3814) Read of size 1 at addr ff11000138020ad4 by task repro/261 CPU: 3 UID: 0 PID: 261 Comm: repro Not tainted 6.15.0-rc3-00614-g0d15a26b247d #87 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:409 mm/kasan/report.c:521) kasan_report (mm/kasan/report.c:636) ip6_route_info_create (./include/net/ipv6.h:616 net/ipv6/route.c:3814) ip6_route_add (net/ipv6/route.c:3902) ipv6_route_ioctl (net/ipv6/route.c:4523) inet6_ioctl (net/ipv6/af_inet6.c:577) sock_do_ioctl (net/socket.c:1190) sock_ioctl (net/socket.c:1314) __x64_sys_ioctl (fs/ioctl.c:51 fs/ioctl.c:906 fs/ioctl.c:892 fs/ioctl.c:892) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) RIP: 0033:0x7f518fb2de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 73 9f 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007fff14f38d18 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f518fb2de5d RDX: 00000000200015c0 RSI: 000000000000890b RDI: 0000000000000003 RBP: 00007fff14f38d30 R08: 0000000000000800 R09: 0000000000000800 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff14f38e48 R13: 0000000000401136 R14: 0000000000403df0 R15: 00007f518fd3c000 Fixes: fa76c1674f2e ("ipv6: Move some validation from ip6_route_info_create() to rtm_to_fib6_config().") Reported-by: syzkaller Reported-by: Yi Lai Closes: https://lore.kernel.org/netdev/aBAcKDEFoN%2FLntBF@ly-workstation/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: David Ahern Link: https://patch.msgid.link/20250501005335.53683-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv6/route.c | 97 +++++++++++++++++++++++++++--------------------- 1 file changed, 55 insertions(+), 42 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index aa6b45bd3515..44300962230b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4503,6 +4503,53 @@ void rt6_purge_dflt_routers(struct net *net) rcu_read_unlock(); } +static int fib6_config_validate(struct fib6_config *cfg, + struct netlink_ext_ack *extack) +{ + /* RTF_PCPU is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_PCPU) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); + goto errout; + } + + /* RTF_CACHE is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_CACHE) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); + goto errout; + } + + if (cfg->fc_type > RTN_MAX) { + NL_SET_ERR_MSG(extack, "Invalid route type"); + goto errout; + } + + if (cfg->fc_dst_len > 128) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + goto errout; + } + +#ifdef CONFIG_IPV6_SUBTREES + if (cfg->fc_src_len > 128) { + NL_SET_ERR_MSG(extack, "Invalid source address length"); + goto errout; + } + + if (cfg->fc_nh_id && cfg->fc_src_len) { + NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); + goto errout; + } +#else + if (cfg->fc_src_len) { + NL_SET_ERR_MSG(extack, + "Specifying source address requires IPV6_SUBTREES to be enabled"); + goto errout; + } +#endif + return 0; +errout: + return -EINVAL; +} + static void rtmsg_to_fib6_config(struct net *net, struct in6_rtmsg *rtmsg, struct fib6_config *cfg) @@ -4540,6 +4587,10 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) switch (cmd) { case SIOCADDRT: + err = fib6_config_validate(&cfg, NULL); + if (err) + break; + /* Only do the default setting of fc_metric in route adding */ if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; @@ -5274,48 +5325,6 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, } } - if (newroute) { - /* RTF_PCPU is an internal flag; can not be set by userspace */ - if (cfg->fc_flags & RTF_PCPU) { - NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); - goto errout; - } - - /* RTF_CACHE is an internal flag; can not be set by userspace */ - if (cfg->fc_flags & RTF_CACHE) { - NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); - goto errout; - } - - if (cfg->fc_type > RTN_MAX) { - NL_SET_ERR_MSG(extack, "Invalid route type"); - goto errout; - } - - if (cfg->fc_dst_len > 128) { - NL_SET_ERR_MSG(extack, "Invalid prefix length"); - goto errout; - } - -#ifdef CONFIG_IPV6_SUBTREES - if (cfg->fc_src_len > 128) { - NL_SET_ERR_MSG(extack, "Invalid source address length"); - goto errout; - } - - if (cfg->fc_nh_id && cfg->fc_src_len) { - NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); - goto errout; - } -#else - if (cfg->fc_src_len) { - NL_SET_ERR_MSG(extack, - "Specifying source address requires IPV6_SUBTREES to be enabled"); - goto errout; - } -#endif - } - err = 0; errout: return err; @@ -5710,6 +5719,10 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; + err = fib6_config_validate(&cfg, extack); + if (err) + return err; + if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; -- 2.51.0 From 836b313a14a316290886dcc2ce7e78bf5ecc8658 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 30 Apr 2025 13:02:40 +0300 Subject: [PATCH 05/16] ipv4: Honor "ignore_routes_with_linkdown" sysctl in nexthop selection Commit 32607a332cfe ("ipv4: prefer multipath nexthop that matches source address") changed IPv4 nexthop selection to prefer a nexthop whose nexthop device is assigned the specified source address for locally generated traffic. While the selection honors the "fib_multipath_use_neigh" sysctl and will not choose a nexthop with an invalid neighbour, it does not honor the "ignore_routes_with_linkdown" sysctl and can choose a nexthop without a carrier: $ sysctl net.ipv4.conf.all.ignore_routes_with_linkdown net.ipv4.conf.all.ignore_routes_with_linkdown = 1 $ ip route show 198.51.100.0/24 198.51.100.0/24 nexthop via 192.0.2.2 dev dummy1 weight 1 nexthop via 192.0.2.18 dev dummy2 weight 1 dead linkdown $ ip route get 198.51.100.1 from 192.0.2.17 198.51.100.1 from 192.0.2.17 via 192.0.2.18 dev dummy2 uid 0 Solve this by skipping over nexthops whose assigned hash upper bound is minus one, which is the value assigned to nexthops that do not have a carrier when the "ignore_routes_with_linkdown" sysctl is set. In practice, this probably does not matter a lot as the initial route lookup for the source address would not choose a nexthop that does not have a carrier in the first place, but the change does make the code clearer. Signed-off-by: Ido Schimmel Reviewed-by: Willem de Bruijn Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 03959c60d128..dabe2b7044ab 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -2188,7 +2188,14 @@ void fib_select_multipath(struct fib_result *res, int hash, saddr = fl4 ? fl4->saddr : 0; change_nexthops(fi) { - if (use_neigh && !fib_good_nh(nexthop_nh)) + int nh_upper_bound; + + /* Nexthops without a carrier are assigned an upper bound of + * minus one when "ignore_routes_with_linkdown" is set. + */ + nh_upper_bound = atomic_read(&nexthop_nh->fib_nh_upper_bound); + if (nh_upper_bound == -1 || + (use_neigh && !fib_good_nh(nexthop_nh))) continue; if (!found) { @@ -2197,7 +2204,7 @@ void fib_select_multipath(struct fib_result *res, int hash, found = !saddr || nexthop_nh->nh_saddr == saddr; } - if (hash > atomic_read(&nexthop_nh->fib_nh_upper_bound)) + if (hash > nh_upper_bound) continue; if (!saddr || nexthop_nh->nh_saddr == saddr) { -- 2.51.0 From 320a66f84022028f1277bf568a5e8987eac6e797 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Thu, 1 May 2025 01:24:02 +0100 Subject: [PATCH 06/16] strparser: Remove unused __strp_unpause The last use of __strp_unpause() was removed in 2022 by commit 84c61fe1a75b ("tls: rx: do not use the standard strparser") Remove it. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250501002402.308843-1-linux@treblig.org Signed-off-by: Jakub Kicinski --- include/net/strparser.h | 2 -- net/strparser/strparser.c | 13 ------------- 2 files changed, 15 deletions(-) diff --git a/include/net/strparser.h b/include/net/strparser.h index 0a83010b3a64..0ed73e364faa 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -114,8 +114,6 @@ static inline void strp_pause(struct strparser *strp) /* May be called without holding lock for attached socket */ void strp_unpause(struct strparser *strp); -/* Must be called with process lock held (lock_sock) */ -void __strp_unpause(struct strparser *strp); static inline void save_strp_stats(struct strparser *strp, struct strp_aggr_stats *agg_stats) diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 95696f42647e..d946bfb424c7 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -485,19 +485,6 @@ int strp_init(struct strparser *strp, struct sock *sk, } EXPORT_SYMBOL_GPL(strp_init); -/* Sock process lock held (lock_sock) */ -void __strp_unpause(struct strparser *strp) -{ - strp->paused = 0; - - if (strp->need_bytes) { - if (strp_peek_len(strp) < strp->need_bytes) - return; - } - strp_read_sock(strp); -} -EXPORT_SYMBOL_GPL(__strp_unpause); - void strp_unpause(struct strparser *strp) { strp->paused = 0; -- 2.51.0 From 1f586017f517f677586ec3853258419f731569a0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Apr 2025 17:38:02 +0300 Subject: [PATCH 07/16] net: phy: Refactor fwnode_get_phy_node() Refactor to check if the fwnode we got is correct and return if so, otherwise do additional checks. Using same pattern in all conditionals makes it slightly easier to read and understand. Signed-off-by: Andy Shevchenko Link: https://patch.msgid.link/20250430143802.3714405-1-andriy.shevchenko@linux.intel.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy_device.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index f85c172c446c..2eb735e68dd8 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3265,12 +3265,12 @@ struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode) /* Only phy-handle is used for ACPI */ phy_node = fwnode_find_reference(fwnode, "phy-handle", 0); - if (is_acpi_node(fwnode) || !IS_ERR(phy_node)) + if (!IS_ERR(phy_node) || is_acpi_node(fwnode)) return phy_node; phy_node = fwnode_find_reference(fwnode, "phy", 0); - if (IS_ERR(phy_node)) - phy_node = fwnode_find_reference(fwnode, "phy-device", 0); - return phy_node; + if (!IS_ERR(phy_node)) + return phy_node; + return fwnode_find_reference(fwnode, "phy-device", 0); } EXPORT_SYMBOL_GPL(fwnode_get_phy_node); -- 2.51.0 From ac8f09b9210c48934c78fdc6bc167e660eaac928 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Fri, 2 May 2025 00:38:15 +0100 Subject: [PATCH 08/16] sctp: Remove unused sctp_assoc_del_peer and sctp_chunk_iif sctp_assoc_del_peer() last use was removed in 2015 by commit 73e6742027f5 ("sctp: Do not try to search for the transport twice") which now uses rm_peer instead of del_peer. sctp_chunk_iif() last use was removed in 2016 by commit 1f45f78f8e51 ("sctp: allow GSO frags to access the chunk too") Remove them. Signed-off-by: Dr. David Alan Gilbert Acked-by: Xin Long Link: https://patch.msgid.link/20250501233815.99832-1-linux@treblig.org Signed-off-by: Jakub Kicinski --- include/net/sctp/sm.h | 1 - include/net/sctp/structs.h | 2 -- net/sctp/associola.c | 18 ------------------ net/sctp/sm_make_chunk.c | 8 -------- 4 files changed, 29 deletions(-) diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 64c42bd56bb2..3bfd261a53cc 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -161,7 +161,6 @@ const struct sctp_sm_table_entry *sctp_sm_lookup_event( enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype); -int sctp_chunk_iif(const struct sctp_chunk *); struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *, struct sctp_chunk *, gfp_t gfp); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index dcd288fa1bb6..1ad7ce71d0a7 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -2152,8 +2152,6 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *, const union sctp_addr *address, const gfp_t gfp, const int peer_state); -void sctp_assoc_del_peer(struct sctp_association *asoc, - const union sctp_addr *addr); void sctp_assoc_rm_peer(struct sctp_association *asoc, struct sctp_transport *peer); void sctp_assoc_control_transport(struct sctp_association *asoc, diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 760152e751c7..5793d71852b8 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -736,24 +736,6 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, return peer; } -/* Delete a transport address from an association. */ -void sctp_assoc_del_peer(struct sctp_association *asoc, - const union sctp_addr *addr) -{ - struct list_head *pos; - struct list_head *temp; - struct sctp_transport *transport; - - list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { - transport = list_entry(pos, struct sctp_transport, transports); - if (sctp_cmp_addr_exact(addr, &transport->ipaddr)) { - /* Do book keeping for removing the peer and free it. */ - sctp_assoc_rm_peer(asoc, transport); - break; - } - } -} - /* Lookup a transport by address. */ struct sctp_transport *sctp_assoc_lookup_paddr( const struct sctp_association *asoc, diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index f80208edd6a5..3ead591c72fd 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -115,14 +115,6 @@ static void sctp_control_set_owner_w(struct sctp_chunk *chunk) skb->destructor = sctp_control_release_owner; } -/* What was the inbound interface for this chunk? */ -int sctp_chunk_iif(const struct sctp_chunk *chunk) -{ - struct sk_buff *skb = chunk->skb; - - return SCTP_INPUT_CB(skb)->af->skb_iif(skb); -} - /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 2: The ECN capable field is reserved for future use of -- 2.51.0 From 6d0eb15c65019b2b17bd6db9b32a60a219e40078 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 2 May 2025 14:29:21 +0200 Subject: [PATCH 09/16] selftests: mptcp: info: hide 'grep: write error' warnings mptcp_lib_get_info_value() will only print the first entry that match the filter because of the ';q' at the end. As a consequence, the 'sed' command could finish before the previous 'grep' one and print a 'write error' warning because it is trying to write data to the closed pipe. Such warnings are not interesting, they can be hidden by muting stderr here for grep. While at it, clearly indicate that mptcp_lib_get_info_value() will only print the first matched entry to avoid confusions later on. Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250502-net-next-mptcp-sft-inc-cover-v1-1-68eec95898fb@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 051e289d7967..99c87cd6e255 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -331,12 +331,15 @@ mptcp_lib_result_print_all_tap() { # get the value of keyword $1 in the line marked by keyword $2 mptcp_lib_get_info_value() { - grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q' + grep "${2}" 2>/dev/null | + sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q' + # the ';q' at the end limits to the first matched entry. } # $1: info name ; $2: evts_ns ; [$3: event type; [$4: addr]] mptcp_lib_evts_get_info() { - grep "${4:-}" "${2}" | mptcp_lib_get_info_value "${1}" "^type:${3:-1}," + grep "${4:-}" "${2}" 2>/dev/null | + mptcp_lib_get_info_value "${1}" "^type:${3:-1}," } # $1: PID -- 2.51.0 From dd367e81b79a68a080c5f03f690fe829b093bd21 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 2 May 2025 14:29:22 +0200 Subject: [PATCH 10/16] selftests: mptcp: sockopt: use IPPROTO_MPTCP for getaddrinfo getaddrinfo MPTCP is recently supported in glibc and IPPROTO_MPTCP for getaddrinfo is used in mptcp_connect.c. But in mptcp_sockopt.c and mptcp_inq.c, IPPROTO_TCP are still used for getaddrinfo, So this patch updates them. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250502-net-next-mptcp-sft-inc-cover-v1-2-68eec95898fb@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_inq.c | 16 ++++++++++++---- .../testing/selftests/net/mptcp/mptcp_sockopt.c | 16 ++++++++++++---- 2 files changed, 24 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index 218aac467321..3cf1e2a612ce 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -72,13 +72,21 @@ static const char *getxinfo_strerr(int err) } static void xgetaddrinfo(const char *node, const char *service, - const struct addrinfo *hints, + struct addrinfo *hints, struct addrinfo **res) { +again: int err = getaddrinfo(node, service, hints, res); if (err) { - const char *errstr = getxinfo_strerr(err); + const char *errstr; + + if (err == EAI_SOCKTYPE) { + hints->ai_protocol = IPPROTO_TCP; + goto again; + } + + errstr = getxinfo_strerr(err); fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n", node ? node : "", service ? service : "", errstr); @@ -91,7 +99,7 @@ static int sock_listen_mptcp(const char * const listenaddr, { int sock = -1; struct addrinfo hints = { - .ai_protocol = IPPROTO_TCP, + .ai_protocol = IPPROTO_MPTCP, .ai_socktype = SOCK_STREAM, .ai_flags = AI_PASSIVE | AI_NUMERICHOST }; @@ -136,7 +144,7 @@ static int sock_connect_mptcp(const char * const remoteaddr, const char * const port, int proto) { struct addrinfo hints = { - .ai_protocol = IPPROTO_TCP, + .ai_protocol = IPPROTO_MPTCP, .ai_socktype = SOCK_STREAM, }; struct addrinfo *a, *addr; diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index 926b0be87c99..9934a68df237 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -159,13 +159,21 @@ static const char *getxinfo_strerr(int err) } static void xgetaddrinfo(const char *node, const char *service, - const struct addrinfo *hints, + struct addrinfo *hints, struct addrinfo **res) { +again: int err = getaddrinfo(node, service, hints, res); if (err) { - const char *errstr = getxinfo_strerr(err); + const char *errstr; + + if (err == EAI_SOCKTYPE) { + hints->ai_protocol = IPPROTO_TCP; + goto again; + } + + errstr = getxinfo_strerr(err); fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n", node ? node : "", service ? service : "", errstr); @@ -178,7 +186,7 @@ static int sock_listen_mptcp(const char * const listenaddr, { int sock = -1; struct addrinfo hints = { - .ai_protocol = IPPROTO_TCP, + .ai_protocol = IPPROTO_MPTCP, .ai_socktype = SOCK_STREAM, .ai_flags = AI_PASSIVE | AI_NUMERICHOST }; @@ -223,7 +231,7 @@ static int sock_connect_mptcp(const char * const remoteaddr, const char * const port, int proto) { struct addrinfo hints = { - .ai_protocol = IPPROTO_TCP, + .ai_protocol = IPPROTO_MPTCP, .ai_socktype = SOCK_STREAM, }; struct addrinfo *a, *addr; -- 2.51.0 From cd732d5110a22ea6d555c69a60a440b59ba281e3 Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Fri, 2 May 2025 14:29:23 +0200 Subject: [PATCH 11/16] selftests: mptcp: add struct params in mptcp_diag This patch adds a struct named 'params' to save 'target_token' and other future parameters. This structure facilitates future function expansions. Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250502-net-next-mptcp-sft-inc-cover-v1-3-68eec95898fb@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_diag.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c index 37d5015ad08c..ea7cb1128044 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_diag.c +++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c @@ -19,6 +19,10 @@ #define IPPROTO_MPTCP 262 #endif +struct params { + __u32 target_token; +}; + struct mptcp_info { __u8 mptcpi_subflows; __u8 mptcpi_add_addr_signal; @@ -237,7 +241,7 @@ static void get_mptcpinfo(__u32 token) close(fd); } -static void parse_opts(int argc, char **argv, __u32 *target_token) +static void parse_opts(int argc, char **argv, struct params *p) { int c; @@ -250,7 +254,7 @@ static void parse_opts(int argc, char **argv, __u32 *target_token) die_usage(0); break; case 't': - sscanf(optarg, "%x", target_token); + sscanf(optarg, "%x", &p->target_token); break; default: die_usage(1); @@ -261,10 +265,12 @@ static void parse_opts(int argc, char **argv, __u32 *target_token) int main(int argc, char *argv[]) { - __u32 target_token; + struct params p = { 0 }; + + parse_opts(argc, argv, &p); - parse_opts(argc, argv, &target_token); - get_mptcpinfo(target_token); + if (p.target_token) + get_mptcpinfo(p.target_token); return 0; } -- 2.51.0 From 3fea468dca4f53fa0942661a0fc61dab8d6b0dc9 Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Fri, 2 May 2025 14:29:24 +0200 Subject: [PATCH 12/16] selftests: mptcp: refactor send_query parameters for code clarity This patch use 'inet_diag_req_v2' instead of 'token' as parameters of send_query, and construct the req in 'get_mptcpinfo'. This modification enhances the clarity of the code, and prepare for the dump_subflow_info. Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250502-net-next-mptcp-sft-inc-cover-v1-4-68eec95898fb@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_diag.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c index ea7cb1128044..76135aba71ad 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_diag.c +++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c @@ -62,7 +62,7 @@ static void die_usage(int r) exit(r); } -static void send_query(int fd, __u32 token) +static void send_query(int fd, struct inet_diag_req_v2 *r) { struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK @@ -76,19 +76,13 @@ static void send_query(int fd, __u32 token) .nlmsg_type = SOCK_DIAG_BY_FAMILY, .nlmsg_flags = NLM_F_REQUEST }, - .r = { - .sdiag_family = AF_INET, - /* Real proto is set via INET_DIAG_REQ_PROTOCOL */ - .sdiag_protocol = IPPROTO_TCP, - .id.idiag_cookie[0] = token, - } + .r = *r }; struct rtattr rta_proto; struct iovec iov[6]; int iovlen = 1; __u32 proto; - req.r.idiag_ext |= (1 << (INET_DIAG_INFO - 1)); proto = IPPROTO_MPTCP; rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL; rta_proto.rta_len = RTA_LENGTH(sizeof(proto)); @@ -229,13 +223,20 @@ static void recv_nlmsg(int fd) static void get_mptcpinfo(__u32 token) { + struct inet_diag_req_v2 r = { + .sdiag_family = AF_INET, + /* Real proto is set via INET_DIAG_REQ_PROTOCOL */ + .sdiag_protocol = IPPROTO_TCP, + .idiag_ext = 1 << (INET_DIAG_INFO - 1), + .id.idiag_cookie[0] = token, + }; int fd; fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG); if (fd < 0) die_perror("Netlink socket"); - send_query(fd, token); + send_query(fd, &r); recv_nlmsg(fd); close(fd); -- 2.51.0 From caa6811ccaed911f3b46e98b8e9f9d9c864d348e Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Fri, 2 May 2025 14:29:25 +0200 Subject: [PATCH 13/16] selftests: mptcp: refactor NLMSG handling with 'proto' This patch introduces the '__u32 proto' variable to the 'send_query' and 'recv_nlmsg' functions for further extending function. In the 'send_query' function, the inclusion of this variable makes the structure clearer and more readable. In the 'recv_nlmsg' function, the '__u32 proto' variable ensures that the 'diag_info' field remains unmodified when processing IPPROTO_TCP data, thereby preventing unintended transformation into 'mptcp_info' format. While at it, increment iovlen directly when an item is added to simplify this portion of the code and improve its readaility. Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250502-net-next-mptcp-sft-inc-cover-v1-5-68eec95898fb@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_diag.c | 38 ++++++++++--------- 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c index 76135aba71ad..cc0326548e4e 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_diag.c +++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c @@ -62,7 +62,7 @@ static void die_usage(int r) exit(r); } -static void send_query(int fd, struct inet_diag_req_v2 *r) +static void send_query(int fd, struct inet_diag_req_v2 *r, __u32 proto) { struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK @@ -80,21 +80,22 @@ static void send_query(int fd, struct inet_diag_req_v2 *r) }; struct rtattr rta_proto; struct iovec iov[6]; - int iovlen = 1; - __u32 proto; + int iovlen = 0; - proto = IPPROTO_MPTCP; - rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL; - rta_proto.rta_len = RTA_LENGTH(sizeof(proto)); - - iov[0] = (struct iovec) { + iov[iovlen++] = (struct iovec) { .iov_base = &req, .iov_len = sizeof(req) }; - iov[iovlen] = (struct iovec){ &rta_proto, sizeof(rta_proto)}; - iov[iovlen + 1] = (struct iovec){ &proto, sizeof(proto)}; - req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto)); - iovlen += 2; + + if (proto == IPPROTO_MPTCP) { + rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL; + rta_proto.rta_len = RTA_LENGTH(sizeof(proto)); + + iov[iovlen++] = (struct iovec){ &rta_proto, sizeof(rta_proto)}; + iov[iovlen++] = (struct iovec){ &proto, sizeof(proto)}; + req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto)); + } + struct msghdr msg = { .msg_name = &nladdr, .msg_namelen = sizeof(nladdr), @@ -158,7 +159,7 @@ static void print_info_msg(struct mptcp_info *info) printf("bytes_acked: %llu\n", info->mptcpi_bytes_acked); } -static void parse_nlmsg(struct nlmsghdr *nlh) +static void parse_nlmsg(struct nlmsghdr *nlh, __u32 proto) { struct inet_diag_msg *r = NLMSG_DATA(nlh); struct rtattr *tb[INET_DIAG_MAX + 1]; @@ -167,7 +168,7 @@ static void parse_nlmsg(struct nlmsghdr *nlh) nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)), NLA_F_NESTED); - if (tb[INET_DIAG_INFO]) { + if (proto == IPPROTO_MPTCP && tb[INET_DIAG_INFO]) { int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]); struct mptcp_info *info; @@ -183,7 +184,7 @@ static void parse_nlmsg(struct nlmsghdr *nlh) } } -static void recv_nlmsg(int fd) +static void recv_nlmsg(int fd, __u32 proto) { char rcv_buff[8192]; struct nlmsghdr *nlh = (struct nlmsghdr *)rcv_buff; @@ -216,7 +217,7 @@ static void recv_nlmsg(int fd) -(err->error), strerror(-(err->error))); break; } - parse_nlmsg(nlh); + parse_nlmsg(nlh, proto); nlh = NLMSG_NEXT(nlh, len); } } @@ -230,14 +231,15 @@ static void get_mptcpinfo(__u32 token) .idiag_ext = 1 << (INET_DIAG_INFO - 1), .id.idiag_cookie[0] = token, }; + __u32 proto = IPPROTO_MPTCP; int fd; fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG); if (fd < 0) die_perror("Netlink socket"); - send_query(fd, &r); - recv_nlmsg(fd); + send_query(fd, &r, proto); + recv_nlmsg(fd, proto); close(fd); } -- 2.51.0 From c7ac7452df70569a196527743d465c2522abbee6 Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Fri, 2 May 2025 14:29:26 +0200 Subject: [PATCH 14/16] selftests: mptcp: add helpers to get subflow_info This patch adds 'get_subflow_info' in 'mptcp_diag', which can check whether a TCP connection is an MPTCP subflow based on the "INET_ULP_INFO_MPTCP" with tcp_diag method. The helper 'print_subflow_info' in 'mptcp_diag' can print the subflow_filed of an MPTCP subflow for further checking the 'subflow_info' through inet_diag method. The example of the whole output should be: $ ./mptcp_diag -s "127.0.0.1:10000 127.0.0.1:38984" 127.0.0.1:10000 -> 127.0.0.1:38984 It's a mptcp subflow, the subflow info: flags:Mec token:0000(id:0)/4278e77e(id:0) seq:9288466187236176036 \ sfseq:1 ssnoff:2317083055 maplen:215 Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250502-net-next-mptcp-sft-inc-cover-v1-6-68eec95898fb@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_diag.c | 159 +++++++++++++++++- 1 file changed, 157 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c index cc0326548e4e..e084796e804d 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_diag.c +++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -19,8 +20,13 @@ #define IPPROTO_MPTCP 262 #endif +#define parse_rtattr_nested(tb, max, rta) \ + (parse_rtattr_flags((tb), (max), RTA_DATA(rta), RTA_PAYLOAD(rta), \ + NLA_F_NESTED)) + struct params { __u32 target_token; + char subflow_addrs[1024]; }; struct mptcp_info { @@ -50,6 +56,37 @@ struct mptcp_info { __u32 mptcpi_last_ack_recv; }; +enum { + MPTCP_SUBFLOW_ATTR_UNSPEC, + MPTCP_SUBFLOW_ATTR_TOKEN_REM, + MPTCP_SUBFLOW_ATTR_TOKEN_LOC, + MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ, + MPTCP_SUBFLOW_ATTR_MAP_SEQ, + MPTCP_SUBFLOW_ATTR_MAP_SFSEQ, + MPTCP_SUBFLOW_ATTR_SSN_OFFSET, + MPTCP_SUBFLOW_ATTR_MAP_DATALEN, + MPTCP_SUBFLOW_ATTR_FLAGS, + MPTCP_SUBFLOW_ATTR_ID_REM, + MPTCP_SUBFLOW_ATTR_ID_LOC, + MPTCP_SUBFLOW_ATTR_PAD, + + __MPTCP_SUBFLOW_ATTR_MAX +}; + +#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1) + +#define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0) +#define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1) +#define MPTCP_SUBFLOW_FLAG_JOIN_REM _BITUL(2) +#define MPTCP_SUBFLOW_FLAG_JOIN_LOC _BITUL(3) +#define MPTCP_SUBFLOW_FLAG_BKUP_REM _BITUL(4) +#define MPTCP_SUBFLOW_FLAG_BKUP_LOC _BITUL(5) +#define MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED _BITUL(6) +#define MPTCP_SUBFLOW_FLAG_CONNECTED _BITUL(7) +#define MPTCP_SUBFLOW_FLAG_MAPVALID _BITUL(8) + +#define rta_getattr(type, value) (*(type *)RTA_DATA(value)) + static void die_perror(const char *msg) { perror(msg); @@ -58,7 +95,9 @@ static void die_perror(const char *msg) static void die_usage(int r) { - fprintf(stderr, "Usage: mptcp_diag -t\n"); + fprintf(stderr, "Usage:\n" + "mptcp_diag -t \n" + "mptcp_diag -s \": :\"\n"); exit(r); } @@ -159,6 +198,66 @@ static void print_info_msg(struct mptcp_info *info) printf("bytes_acked: %llu\n", info->mptcpi_bytes_acked); } +/* + * 'print_subflow_info' is from 'mptcp_subflow_info' + * which is a function in 'misc/ss.c' of iproute2. + */ +static void print_subflow_info(struct rtattr *tb[]) +{ + u_int32_t flags = 0; + + printf("It's a mptcp subflow, the subflow info:\n"); + if (tb[MPTCP_SUBFLOW_ATTR_FLAGS]) { + char caps[32 + 1] = { 0 }, *cap = &caps[0]; + + flags = rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_FLAGS]); + + if (flags & MPTCP_SUBFLOW_FLAG_MCAP_REM) + *cap++ = 'M'; + if (flags & MPTCP_SUBFLOW_FLAG_MCAP_LOC) + *cap++ = 'm'; + if (flags & MPTCP_SUBFLOW_FLAG_JOIN_REM) + *cap++ = 'J'; + if (flags & MPTCP_SUBFLOW_FLAG_JOIN_LOC) + *cap++ = 'j'; + if (flags & MPTCP_SUBFLOW_FLAG_BKUP_REM) + *cap++ = 'B'; + if (flags & MPTCP_SUBFLOW_FLAG_BKUP_LOC) + *cap++ = 'b'; + if (flags & MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED) + *cap++ = 'e'; + if (flags & MPTCP_SUBFLOW_FLAG_CONNECTED) + *cap++ = 'c'; + if (flags & MPTCP_SUBFLOW_FLAG_MAPVALID) + *cap++ = 'v'; + + if (flags) + printf(" flags:%s", caps); + } + if (tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM] && + tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC] && + tb[MPTCP_SUBFLOW_ATTR_ID_REM] && + tb[MPTCP_SUBFLOW_ATTR_ID_LOC]) + printf(" token:%04x(id:%u)/%04x(id:%u)", + rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM]), + rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_REM]), + rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC]), + rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_LOC])); + if (tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ]) + printf(" seq:%llu", + rta_getattr(__u64, tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ])); + if (tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ]) + printf(" sfseq:%u", + rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ])); + if (tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET]) + printf(" ssnoff:%u", + rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET])); + if (tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN]) + printf(" maplen:%u", + rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN])); + printf("\n"); +} + static void parse_nlmsg(struct nlmsghdr *nlh, __u32 proto) { struct inet_diag_msg *r = NLMSG_DATA(nlh); @@ -182,6 +281,22 @@ static void parse_nlmsg(struct nlmsghdr *nlh, __u32 proto) } print_info_msg(info); } + if (proto == IPPROTO_TCP && tb[INET_DIAG_ULP_INFO]) { + struct rtattr *ulpinfo[INET_ULP_INFO_MAX + 1] = { 0 }; + + parse_rtattr_nested(ulpinfo, INET_ULP_INFO_MAX, + tb[INET_DIAG_ULP_INFO]); + + if (ulpinfo[INET_ULP_INFO_MPTCP]) { + struct rtattr *sfinfo[MPTCP_SUBFLOW_ATTR_MAX + 1] = { 0 }; + + parse_rtattr_nested(sfinfo, MPTCP_SUBFLOW_ATTR_MAX, + ulpinfo[INET_ULP_INFO_MPTCP]); + print_subflow_info(sfinfo); + } else { + printf("It's a normal TCP!\n"); + } + } } static void recv_nlmsg(int fd, __u32 proto) @@ -244,6 +359,39 @@ static void get_mptcpinfo(__u32 token) close(fd); } +static void get_subflow_info(char *subflow_addrs) +{ + struct inet_diag_req_v2 r = { + .sdiag_family = AF_INET, + .sdiag_protocol = IPPROTO_TCP, + .idiag_ext = 1 << (INET_DIAG_INFO - 1), + .id.idiag_cookie[0] = INET_DIAG_NOCOOKIE, + .id.idiag_cookie[1] = INET_DIAG_NOCOOKIE, + }; + char saddr[64], daddr[64]; + int sport, dport; + int ret; + int fd; + + ret = sscanf(subflow_addrs, "%[^:]:%d %[^:]:%d", saddr, &sport, daddr, &dport); + if (ret != 4) + die_perror("IP PORT Pairs has style problems!"); + + printf("%s:%d -> %s:%d\n", saddr, sport, daddr, dport); + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG); + if (fd < 0) + die_perror("Netlink socket"); + + r.id.idiag_sport = htons(sport); + r.id.idiag_dport = htons(dport); + + inet_pton(AF_INET, saddr, &r.id.idiag_src); + inet_pton(AF_INET, daddr, &r.id.idiag_dst); + send_query(fd, &r, IPPROTO_TCP); + recv_nlmsg(fd, IPPROTO_TCP); +} + static void parse_opts(int argc, char **argv, struct params *p) { int c; @@ -251,7 +399,7 @@ static void parse_opts(int argc, char **argv, struct params *p) if (argc < 2) die_usage(1); - while ((c = getopt(argc, argv, "ht:")) != -1) { + while ((c = getopt(argc, argv, "ht:s:")) != -1) { switch (c) { case 'h': die_usage(0); @@ -259,6 +407,10 @@ static void parse_opts(int argc, char **argv, struct params *p) case 't': sscanf(optarg, "%x", &p->target_token); break; + case 's': + strncpy(p->subflow_addrs, optarg, + sizeof(p->subflow_addrs) - 1); + break; default: die_usage(1); break; @@ -275,6 +427,9 @@ int main(int argc, char *argv[]) if (p.target_token) get_mptcpinfo(p.target_token); + if (p.subflow_addrs[0] != '\0') + get_subflow_info(p.subflow_addrs); + return 0; } -- 2.51.0 From 110f8f77fd8d48bb1c5590bd53065c0288f29ea7 Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Fri, 2 May 2025 14:29:27 +0200 Subject: [PATCH 15/16] selftests: mptcp: add chk_sublfow in diag.sh This patch aims to add chk_dump_subflow in diag.sh. The subflow's info can be obtained through "ss -tin", then use the 'mptcp_diag' to verify the token in subflow_info. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/524 Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250502-net-next-mptcp-sft-inc-cover-v1-7-68eec95898fb@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/diag.sh | 32 +++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index e7a75341f0f3..7a3cb4c09e45 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -225,6 +225,37 @@ chk_dump_one() fi } +chk_dump_subflow() +{ + local inet_diag_token + local subflow_line + local ss_output + local ss_token + local msg + + ss_output=$(ss -tniN $ns) + + subflow_line=$(echo "$ss_output" | \ + grep -m1 -Eo '[0-9.]+:[0-9].+ +[0-9.]+:[0-9.]+') + + ss_token=$(echo "$ss_output" | grep -m1 -Eo 'token:[^ ]+') + + inet_diag_token=$(ip netns exec $ns ./mptcp_diag -s "$subflow_line" | \ + grep -Eo 'token:[^ ]+') + + msg="....chk dump_subflow" + + mptcp_lib_print_title "$msg" + if [ -n "$ss_token" ] && [ "$ss_token" = "$inet_diag_token" ]; then + mptcp_lib_pr_ok + mptcp_lib_result_pass "${msg}" + else + mptcp_lib_pr_fail "expected $ss_token found $inet_diag_token" + mptcp_lib_result_fail "${msg}" + ret=${KSFT_FAIL} + fi +} + msk_info_get_value() { local port="${1}" @@ -316,6 +347,7 @@ chk_msk_fallback_nr 0 "....chk no fallback" chk_msk_inuse 2 chk_msk_cestab 2 chk_dump_one +chk_dump_subflow flush_pids chk_msk_inuse 0 "2->0" -- 2.51.0 From 953d9480f7d1bee0ec00c7c23ec4d3b33f585ed1 Mon Sep 17 00:00:00 2001 From: Haiyue Wang Date: Sat, 3 May 2025 01:50:25 +0800 Subject: [PATCH 16/16] selftests: iou-zcrx: Clean up build warnings for error format MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Clean up two build warnings: [1] iou-zcrx.c: In function ‘process_recvzc’: iou-zcrx.c:263:37: warning: too many arguments for format [-Wformat-extra-args] 263 | error(1, 0, "payload mismatch at ", i); | ^~~~~~~~~~~~~~~~~~~~~~ [2] Use "%zd" for ssize_t type as better iou-zcrx.c: In function ‘run_client’: iou-zcrx.c:357:47: warning: format ‘%d’ expects argument of type ‘int’, but argument 4 has type ‘ssize_t’ {aka ‘long int’} [-Wformat=] 357 | error(1, 0, "send(): %d", sent); | ~^ ~~~~ | | | | int ssize_t {aka long int} | %ld Signed-off-by: Haiyue Wang Reviewed-by: David Wei Link: https://patch.msgid.link/20250502175136.1122-1-haiyuewa@163.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/drivers/net/hw/iou-zcrx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c index 8aa426014c87..62456df947bc 100644 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c @@ -260,7 +260,7 @@ static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe) for (i = 0; i < n; i++) { if (*(data + i) != payload[(received + i)]) - error(1, 0, "payload mismatch at ", i); + error(1, 0, "payload mismatch at %d", i); } received += n; @@ -354,7 +354,7 @@ static void run_client(void) chunk = min_t(ssize_t, cfg_payload_len, to_send); res = send(fd, src, chunk, 0); if (res < 0) - error(1, 0, "send(): %d", sent); + error(1, 0, "send(): %zd", sent); sent += res; to_send -= res; } -- 2.51.0