From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- net/sctp/sysctl.c | 644 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 644 insertions(+) create mode 100644 net/sctp/sysctl.c (limited to 'net/sctp/sysctl.c') diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c new file mode 100644 index 000000000..a7a913619 --- /dev/null +++ b/net/sctp/sysctl.c @@ -0,0 +1,644 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* SCTP kernel implementation + * (C) Copyright IBM Corp. 2002, 2004 + * Copyright (c) 2002 Intel Corp. + * + * This file is part of the SCTP kernel implementation + * + * Sysctl related interfaces for SCTP. + * + * Please send any bug reports or fixes you make to the + * email address(es): + * lksctp developers + * + * Written or modified by: + * Mingqin Liu + * Jon Grimm + * Ardelle Fan + * Ryan Layer + * Sridhar Samudrala + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +static int timer_max = 86400000; /* ms in one day */ +static int sack_timer_min = 1; +static int sack_timer_max = 500; +static int addr_scope_max = SCTP_SCOPE_POLICY_MAX; +static int rwnd_scale_max = 16; +static int rto_alpha_min = 0; +static int rto_beta_min = 0; +static int rto_alpha_max = 1000; +static int rto_beta_max = 1000; +static int pf_expose_max = SCTP_PF_EXPOSE_MAX; +static int ps_retrans_max = SCTP_PS_RETRANS_MAX; +static int udp_port_max = 65535; + +static unsigned long max_autoclose_min = 0; +static unsigned long max_autoclose_max = + (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) + ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; + +static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer, + size_t *lenp, loff_t *ppos); +static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, + size_t *lenp, loff_t *ppos); +static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_auth(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos); + +static struct ctl_table sctp_table[] = { + { + .procname = "sctp_mem", + .data = &sysctl_sctp_mem, + .maxlen = sizeof(sysctl_sctp_mem), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax + }, + { + .procname = "sctp_rmem", + .data = &sysctl_sctp_rmem, + .maxlen = sizeof(sysctl_sctp_rmem), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sctp_wmem", + .data = &sysctl_sctp_wmem, + .maxlen = sizeof(sysctl_sctp_wmem), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + + { /* sentinel */ } +}; + +/* The following index defines are used in sctp_sysctl_net_register(). + * If you add new items to the sctp_net_table, please ensure that + * the index values of these defines hold the same meaning indicated by + * their macro names when they appear in sctp_net_table. + */ +#define SCTP_RTO_MIN_IDX 0 +#define SCTP_RTO_MAX_IDX 1 +#define SCTP_PF_RETRANS_IDX 2 +#define SCTP_PS_RETRANS_IDX 3 + +static struct ctl_table sctp_net_table[] = { + [SCTP_RTO_MIN_IDX] = { + .procname = "rto_min", + .data = &init_net.sctp.rto_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_sctp_do_rto_min, + .extra1 = SYSCTL_ONE, + .extra2 = &init_net.sctp.rto_max + }, + [SCTP_RTO_MAX_IDX] = { + .procname = "rto_max", + .data = &init_net.sctp.rto_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_sctp_do_rto_max, + .extra1 = &init_net.sctp.rto_min, + .extra2 = &timer_max + }, + [SCTP_PF_RETRANS_IDX] = { + .procname = "pf_retrans", + .data = &init_net.sctp.pf_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &init_net.sctp.ps_retrans, + }, + [SCTP_PS_RETRANS_IDX] = { + .procname = "ps_retrans", + .data = &init_net.sctp.ps_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.sctp.pf_retrans, + .extra2 = &ps_retrans_max, + }, + { + .procname = "rto_initial", + .data = &init_net.sctp.rto_initial, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = &timer_max + }, + { + .procname = "rto_alpha_exp_divisor", + .data = &init_net.sctp.rto_alpha, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_alpha_beta, + .extra1 = &rto_alpha_min, + .extra2 = &rto_alpha_max, + }, + { + .procname = "rto_beta_exp_divisor", + .data = &init_net.sctp.rto_beta, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_alpha_beta, + .extra1 = &rto_beta_min, + .extra2 = &rto_beta_max, + }, + { + .procname = "max_burst", + .data = &init_net.sctp.max_burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, + }, + { + .procname = "cookie_preserve_enable", + .data = &init_net.sctp.cookie_preserve_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "cookie_hmac_alg", + .data = &init_net.sctp.sctp_hmac_alg, + .maxlen = 8, + .mode = 0644, + .proc_handler = proc_sctp_do_hmac_alg, + }, + { + .procname = "valid_cookie_life", + .data = &init_net.sctp.valid_cookie_life, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = &timer_max + }, + { + .procname = "sack_timeout", + .data = &init_net.sctp.sack_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &sack_timer_min, + .extra2 = &sack_timer_max, + }, + { + .procname = "hb_interval", + .data = &init_net.sctp.hb_interval, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = &timer_max + }, + { + .procname = "association_max_retrans", + .data = &init_net.sctp.max_retrans_association, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, + }, + { + .procname = "path_max_retrans", + .data = &init_net.sctp.max_retrans_path, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, + }, + { + .procname = "max_init_retransmits", + .data = &init_net.sctp.max_retrans_init, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, + }, + { + .procname = "sndbuf_policy", + .data = &init_net.sctp.sndbuf_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "rcvbuf_policy", + .data = &init_net.sctp.rcvbuf_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "default_auto_asconf", + .data = &init_net.sctp.default_auto_asconf, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "addip_enable", + .data = &init_net.sctp.addip_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "addip_noauth_enable", + .data = &init_net.sctp.addip_noauth, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "prsctp_enable", + .data = &init_net.sctp.prsctp_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "reconf_enable", + .data = &init_net.sctp.reconf_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "auth_enable", + .data = &init_net.sctp.auth_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_auth, + }, + { + .procname = "intl_enable", + .data = &init_net.sctp.intl_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "ecn_enable", + .data = &init_net.sctp.ecn_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "plpmtud_probe_interval", + .data = &init_net.sctp.probe_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_probe_interval, + }, + { + .procname = "udp_port", + .data = &init_net.sctp.udp_port, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_udp_port, + .extra1 = SYSCTL_ZERO, + .extra2 = &udp_port_max, + }, + { + .procname = "encap_port", + .data = &init_net.sctp.encap_port, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &udp_port_max, + }, + { + .procname = "addr_scope_policy", + .data = &init_net.sctp.scope_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &addr_scope_max, + }, + { + .procname = "rwnd_update_shift", + .data = &init_net.sctp.rwnd_upd_shift, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = &rwnd_scale_max, + }, + { + .procname = "max_autoclose", + .data = &init_net.sctp.max_autoclose, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + .extra1 = &max_autoclose_min, + .extra2 = &max_autoclose_max, + }, +#ifdef CONFIG_NET_L3_MASTER_DEV + { + .procname = "l3mdev_accept", + .data = &init_net.sctp.l3mdev_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif + { + .procname = "pf_enable", + .data = &init_net.sctp.pf_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "pf_expose", + .data = &init_net.sctp.pf_expose, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &pf_expose_max, + }, + + { /* sentinel */ } +}; + +static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + bool changed = false; + char *none = "none"; + char tmp[8] = {0}; + int ret; + + memset(&tbl, 0, sizeof(struct ctl_table)); + + if (write) { + tbl.data = tmp; + tbl.maxlen = sizeof(tmp); + } else { + tbl.data = net->sctp.sctp_hmac_alg ? : none; + tbl.maxlen = strlen(tbl.data); + } + + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { +#ifdef CONFIG_CRYPTO_MD5 + if (!strncmp(tmp, "md5", 3)) { + net->sctp.sctp_hmac_alg = "md5"; + changed = true; + } +#endif +#ifdef CONFIG_CRYPTO_SHA1 + if (!strncmp(tmp, "sha1", 4)) { + net->sctp.sctp_hmac_alg = "sha1"; + changed = true; + } +#endif + if (!strncmp(tmp, "none", 4)) { + net->sctp.sctp_hmac_alg = NULL; + changed = true; + } + if (!changed) + ret = -EINVAL; + } + + return ret; +} + +static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + unsigned int min = *(unsigned int *) ctl->extra1; + unsigned int max = *(unsigned int *) ctl->extra2; + struct ctl_table tbl; + int ret, new_value; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.rto_min; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + if (new_value > max || new_value < min) + return -EINVAL; + + net->sctp.rto_min = new_value; + } + + return ret; +} + +static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + unsigned int min = *(unsigned int *) ctl->extra1; + unsigned int max = *(unsigned int *) ctl->extra2; + struct ctl_table tbl; + int ret, new_value; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.rto_max; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + if (new_value > max || new_value < min) + return -EINVAL; + + net->sctp.rto_max = new_value; + } + + return ret; +} + +static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + if (write) + pr_warn_once("Changing rto_alpha or rto_beta may lead to " + "suboptimal rtt/srtt estimations!\n"); + + return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); +} + +static int proc_sctp_do_auth(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + int new_value, ret; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.auth_enable; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + struct sock *sk = net->sctp.ctl_sock; + + net->sctp.auth_enable = new_value; + /* Update the value in the control socket */ + lock_sock(sk); + sctp_sk(sk)->ep->auth_enable = new_value; + release_sock(sk); + } + + return ret; +} + +static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + unsigned int min = *(unsigned int *)ctl->extra1; + unsigned int max = *(unsigned int *)ctl->extra2; + struct ctl_table tbl; + int ret, new_value; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.udp_port; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + struct sock *sk = net->sctp.ctl_sock; + + if (new_value > max || new_value < min) + return -EINVAL; + + net->sctp.udp_port = new_value; + sctp_udp_sock_stop(net); + if (new_value) { + ret = sctp_udp_sock_start(net); + if (ret) + net->sctp.udp_port = 0; + } + + /* Update the value in the control socket */ + lock_sock(sk); + sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); + release_sock(sk); + } + + return ret; +} + +static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + int ret, new_value; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.probe_interval; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + if (new_value && new_value < SCTP_PROBE_TIMER_MIN) + return -EINVAL; + + net->sctp.probe_interval = new_value; + } + + return ret; +} + +int sctp_sysctl_net_register(struct net *net) +{ + struct ctl_table *table; + int i; + + table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + for (i = 0; table[i].data; i++) + table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + + table[SCTP_RTO_MIN_IDX].extra2 = &net->sctp.rto_max; + table[SCTP_RTO_MAX_IDX].extra1 = &net->sctp.rto_min; + table[SCTP_PF_RETRANS_IDX].extra2 = &net->sctp.ps_retrans; + table[SCTP_PS_RETRANS_IDX].extra1 = &net->sctp.pf_retrans; + + net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table); + if (net->sctp.sysctl_header == NULL) { + kfree(table); + return -ENOMEM; + } + return 0; +} + +void sctp_sysctl_net_unregister(struct net *net) +{ + struct ctl_table *table; + + table = net->sctp.sysctl_header->ctl_table_arg; + unregister_net_sysctl_table(net->sctp.sysctl_header); + kfree(table); +} + +static struct ctl_table_header *sctp_sysctl_header; + +/* Sysctl registration. */ +void sctp_sysctl_register(void) +{ + sctp_sysctl_header = register_net_sysctl(&init_net, "net/sctp", sctp_table); +} + +/* Sysctl deregistration. */ +void sctp_sysctl_unregister(void) +{ + unregister_net_sysctl_table(sctp_sysctl_header); +} -- cgit v1.2.3