diff options
author | Scott Wood <scottwood@freescale.com> | 2013-12-14 01:15:24 (GMT) |
---|---|---|
committer | Scott Wood <scottwood@freescale.com> | 2013-12-14 01:15:24 (GMT) |
commit | b7c81aa3ab2ac2c140e278b6d0e9a0b95112cf0b (patch) | |
tree | 87828aaf5f82c7042bfc0307bc4ac499e10f93fb /net/ipv6 | |
parent | 22c782a4b14773fab7eab3c1db54ad7ad077e9b8 (diff) | |
parent | 78fd82238d0e5716578c326404184a27ba67fd6e (diff) | |
download | linux-fsl-qoriq-b7c81aa3ab2ac2c140e278b6d0e9a0b95112cf0b.tar.xz |
Merge remote-tracking branch 'linus/master' into merge
Conflicts:
Documentation/hwmon/ina2xx
arch/powerpc/Kconfig
arch/powerpc/boot/dts/b4860emu.dts
arch/powerpc/boot/dts/b4qds.dtsi
arch/powerpc/boot/dts/fsl/b4si-post.dtsi
arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi
arch/powerpc/boot/dts/p1023rdb.dts
arch/powerpc/boot/dts/t4240emu.dts
arch/powerpc/boot/dts/t4240qds.dts
arch/powerpc/configs/85xx/p1023_defconfig
arch/powerpc/configs/corenet32_smp_defconfig
arch/powerpc/configs/corenet64_smp_defconfig
arch/powerpc/configs/mpc85xx_smp_defconfig
arch/powerpc/include/asm/cputable.h
arch/powerpc/include/asm/device.h
arch/powerpc/include/asm/epapr_hcalls.h
arch/powerpc/include/asm/kvm_host.h
arch/powerpc/include/asm/mpic.h
arch/powerpc/include/asm/pci.h
arch/powerpc/include/asm/ppc-opcode.h
arch/powerpc/include/asm/ppc_asm.h
arch/powerpc/include/asm/reg_booke.h
arch/powerpc/kernel/epapr_paravirt.c
arch/powerpc/kernel/process.c
arch/powerpc/kernel/prom.c
arch/powerpc/kernel/setup-common.c
arch/powerpc/kernel/setup_32.c
arch/powerpc/kernel/setup_64.c
arch/powerpc/kernel/smp.c
arch/powerpc/kernel/swsusp_asm64.S
arch/powerpc/kernel/swsusp_booke.S
arch/powerpc/kvm/book3s_pr.c
arch/powerpc/kvm/booke.c
arch/powerpc/kvm/booke.h
arch/powerpc/kvm/e500.c
arch/powerpc/kvm/e500.h
arch/powerpc/kvm/e500_emulate.c
arch/powerpc/kvm/e500mc.c
arch/powerpc/kvm/powerpc.c
arch/powerpc/perf/e6500-pmu.c
arch/powerpc/platforms/85xx/Kconfig
arch/powerpc/platforms/85xx/Makefile
arch/powerpc/platforms/85xx/b4_qds.c
arch/powerpc/platforms/85xx/c293pcie.c
arch/powerpc/platforms/85xx/corenet_ds.c
arch/powerpc/platforms/85xx/corenet_ds.h
arch/powerpc/platforms/85xx/p1023_rds.c
arch/powerpc/platforms/85xx/p2041_rdb.c
arch/powerpc/platforms/85xx/p3041_ds.c
arch/powerpc/platforms/85xx/p4080_ds.c
arch/powerpc/platforms/85xx/p5020_ds.c
arch/powerpc/platforms/85xx/p5040_ds.c
arch/powerpc/platforms/85xx/smp.c
arch/powerpc/platforms/85xx/t4240_qds.c
arch/powerpc/platforms/Kconfig
arch/powerpc/sysdev/Makefile
arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
arch/powerpc/sysdev/fsl_msi.c
arch/powerpc/sysdev/fsl_pci.c
arch/powerpc/sysdev/fsl_pci.h
arch/powerpc/sysdev/fsl_soc.h
arch/powerpc/sysdev/mpic.c
arch/powerpc/sysdev/mpic_timer.c
drivers/Kconfig
drivers/clk/Kconfig
drivers/clk/clk-ppc-corenet.c
drivers/cpufreq/Kconfig.powerpc
drivers/cpufreq/Makefile
drivers/cpufreq/ppc-corenet-cpufreq.c
drivers/crypto/caam/Kconfig
drivers/crypto/caam/Makefile
drivers/crypto/caam/ctrl.c
drivers/crypto/caam/desc_constr.h
drivers/crypto/caam/intern.h
drivers/crypto/caam/jr.c
drivers/crypto/caam/regs.h
drivers/dma/fsldma.c
drivers/hwmon/ina2xx.c
drivers/iommu/Kconfig
drivers/iommu/fsl_pamu.c
drivers/iommu/fsl_pamu.h
drivers/iommu/fsl_pamu_domain.c
drivers/iommu/fsl_pamu_domain.h
drivers/misc/Makefile
drivers/mmc/card/block.c
drivers/mmc/core/core.c
drivers/mmc/host/sdhci-esdhc.h
drivers/mmc/host/sdhci-pltfm.c
drivers/mtd/nand/fsl_ifc_nand.c
drivers/net/ethernet/freescale/gianfar.c
drivers/net/ethernet/freescale/gianfar.h
drivers/net/ethernet/freescale/gianfar_ethtool.c
drivers/net/phy/at803x.c
drivers/net/phy/phy_device.c
drivers/net/phy/vitesse.c
drivers/pci/msi.c
drivers/staging/Kconfig
drivers/staging/Makefile
drivers/uio/Kconfig
drivers/uio/Makefile
drivers/uio/uio.c
drivers/usb/host/ehci-fsl.c
drivers/vfio/Kconfig
drivers/vfio/Makefile
include/crypto/algapi.h
include/linux/iommu.h
include/linux/mmc/sdhci.h
include/linux/msi.h
include/linux/netdev_features.h
include/linux/phy.h
include/linux/skbuff.h
include/net/ip.h
include/uapi/linux/vfio.h
net/core/ethtool.c
net/ipv4/route.c
net/ipv6/route.c
Diffstat (limited to 'net/ipv6')
66 files changed, 4932 insertions, 1595 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 11b13ea..d92e558 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -21,24 +21,6 @@ menuconfig IPV6 if IPV6 -config IPV6_PRIVACY - bool "IPv6: Privacy Extensions (RFC 3041) support" - ---help--- - Privacy Extensions for Stateless Address Autoconfiguration in IPv6 - support. With this option, additional periodically-altered - pseudo-random global-scope unicast address(es) will be assigned to - your interface(s). - - We use our standard pseudo-random algorithm to generate the - randomized interface identifier, instead of one described in RFC 3041. - - By default the kernel does not generate temporary addresses. - To use temporary addresses, do - - echo 2 >/proc/sys/net/ipv6/conf/all/use_tempaddr - - See <file:Documentation/networking/ip-sysctl.txt> for details. - config IPV6_ROUTER_PREF bool "IPv6: Router Preference (RFC 4191) support" ---help--- @@ -153,6 +135,17 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION ---help--- Support for MIPv6 route optimization mode. +config IPV6_VTI +tristate "Virtual (secure) IPv6: tunneling" + select IPV6_TUNNEL + depends on INET6_XFRM_MODE_TUNNEL + ---help--- + Tunneling means encapsulating data of one protocol type within + another protocol and sending it over a channel that understands the + encapsulating protocol. This can be used with xfrm mode tunnel to give + the notion of a secure tunnel for IPSEC and then use routing protocol + on top. + config IPV6_SIT tristate "IPv6: IPv6-in-IPv4 tunnel (SIT driver)" select INET_TUNNEL diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 9af088d..17bb830 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_IPV6) += ipv6.o ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ addrlabel.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ - raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ + raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o @@ -36,6 +36,7 @@ obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o obj-$(CONFIG_IPV6_MIP6) += mip6.o obj-$(CONFIG_NETFILTER) += netfilter/ +obj-$(CONFIG_IPV6_VTI) += ip6_vti.o obj-$(CONFIG_IPV6_SIT) += sit.o obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-$(CONFIG_IPV6_GRE) += ip6_gre.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4ab4c38..12c97d8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -83,11 +83,7 @@ #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> #include <linux/netconf.h> - -#ifdef CONFIG_IPV6_PRIVACY #include <linux/random.h> -#endif - #include <linux/uaccess.h> #include <asm/unaligned.h> @@ -99,9 +95,9 @@ #define ACONF_DEBUG 2 #if ACONF_DEBUG >= 3 -#define ADBG(x) printk x +#define ADBG(fmt, ...) printk(fmt, ##__VA_ARGS__) #else -#define ADBG(x) +#define ADBG(fmt, ...) do { if (0) printk(fmt, ##__VA_ARGS__); } while (0) #endif #define INFINITY_LIFE_TIME 0xFFFFFFFF @@ -124,11 +120,9 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) } #endif -#ifdef CONFIG_IPV6_PRIVACY static void __ipv6_regen_rndid(struct inet6_dev *idev); static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); static void ipv6_regen_rndid(unsigned long data); -#endif static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(struct inet6_dev *idev); @@ -177,17 +171,17 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_redirects = 1, .autoconf = 1, .force_mld_version = 0, + .mldv1_unsolicited_report_interval = 10 * HZ, + .mldv2_unsolicited_report_interval = HZ, .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, -#ifdef CONFIG_IPV6_PRIVACY .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, -#endif .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_pinfo = 1, @@ -202,6 +196,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, .accept_dad = 1, + .suppress_frag_ndisc = 1, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -211,17 +206,18 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .accept_ra = 1, .accept_redirects = 1, .autoconf = 1, + .force_mld_version = 0, + .mldv1_unsolicited_report_interval = 10 * HZ, + .mldv2_unsolicited_report_interval = HZ, .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, -#ifdef CONFIG_IPV6_PRIVACY .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, -#endif .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_pinfo = 1, @@ -236,62 +232,63 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, .accept_dad = 1, + .suppress_frag_ndisc = 1, }; -/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ -const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; -const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; -const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; -const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; -const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; -const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; -const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; - /* Check if a valid qdisc is available */ static inline bool addrconf_qdisc_ok(const struct net_device *dev) { return !qdisc_tx_is_noop(dev); } -static void addrconf_del_timer(struct inet6_ifaddr *ifp) +static void addrconf_del_rs_timer(struct inet6_dev *idev) +{ + if (del_timer(&idev->rs_timer)) + __in6_dev_put(idev); +} + +static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp) { - if (del_timer(&ifp->timer)) + if (del_timer(&ifp->dad_timer)) __in6_ifa_put(ifp); } -enum addrconf_timer_t { - AC_NONE, - AC_DAD, - AC_RS, -}; +static void addrconf_mod_rs_timer(struct inet6_dev *idev, + unsigned long when) +{ + if (!timer_pending(&idev->rs_timer)) + in6_dev_hold(idev); + mod_timer(&idev->rs_timer, jiffies + when); +} -static void addrconf_mod_timer(struct inet6_ifaddr *ifp, - enum addrconf_timer_t what, - unsigned long when) +static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp, + unsigned long when) { - if (!del_timer(&ifp->timer)) + if (!timer_pending(&ifp->dad_timer)) in6_ifa_hold(ifp); - - switch (what) { - case AC_DAD: - ifp->timer.function = addrconf_dad_timer; - break; - case AC_RS: - ifp->timer.function = addrconf_rs_timer; - break; - default: - break; - } - ifp->timer.expires = jiffies + when; - add_timer(&ifp->timer); + mod_timer(&ifp->dad_timer, jiffies + when); } static int snmp6_alloc_dev(struct inet6_dev *idev) { + int i; + if (snmp_mib_init((void __percpu **)idev->stats.ipv6, sizeof(struct ipstats_mib), __alignof__(struct ipstats_mib)) < 0) goto err_ip; + + for_each_possible_cpu(i) { + struct ipstats_mib *addrconf_stats; + addrconf_stats = per_cpu_ptr(idev->stats.ipv6[0], i); + u64_stats_init(&addrconf_stats->syncp); +#if SNMP_ARRAY_SZ == 2 + addrconf_stats = per_cpu_ptr(idev->stats.ipv6[1], i); + u64_stats_init(&addrconf_stats->syncp); +#endif + } + + idev->stats.icmpv6dev = kzalloc(sizeof(struct icmpv6_mib_device), GFP_KERNEL); if (!idev->stats.icmpv6dev) @@ -311,35 +308,6 @@ err_ip: return -ENOMEM; } -static void snmp6_free_dev(struct inet6_dev *idev) -{ - kfree(idev->stats.icmpv6msgdev); - kfree(idev->stats.icmpv6dev); - snmp_mib_free((void __percpu **)idev->stats.ipv6); -} - -/* Nobody refers to this device, we may destroy it. */ - -void in6_dev_finish_destroy(struct inet6_dev *idev) -{ - struct net_device *dev = idev->dev; - - WARN_ON(!list_empty(&idev->addr_list)); - WARN_ON(idev->mc_list != NULL); - -#ifdef NET_REFCNT_DEBUG - pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); -#endif - dev_put(dev); - if (!idev->dead) { - pr_warn("Freeing alive inet6 device %p\n", idev); - return; - } - snmp6_free_dev(idev); - kfree_rcu(idev, rcu); -} -EXPORT_SYMBOL(in6_dev_finish_destroy); - static struct inet6_dev *ipv6_add_dev(struct net_device *dev) { struct inet6_dev *ndev; @@ -357,7 +325,8 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) rwlock_init(&ndev->lock); ndev->dev = dev; INIT_LIST_HEAD(&ndev->addr_list); - + setup_timer(&ndev->rs_timer, addrconf_rs_timer, + (unsigned long)ndev); memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; @@ -372,9 +341,9 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) dev_hold(dev); if (snmp6_alloc_dev(ndev) < 0) { - ADBG((KERN_WARNING + ADBG(KERN_WARNING "%s: cannot allocate memory for statistics; dev=%s.\n", - __func__, dev->name)); + __func__, dev->name); neigh_parms_release(&nd_tbl, ndev->nd_parms); dev_put(dev); kfree(ndev); @@ -382,9 +351,9 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) } if (snmp6_register_dev(ndev) < 0) { - ADBG((KERN_WARNING + ADBG(KERN_WARNING "%s: cannot create /proc/net/dev_snmp6/%s\n", - __func__, dev->name)); + __func__, dev->name); neigh_parms_release(&nd_tbl, ndev->nd_parms); ndev->dead = 1; in6_dev_finish_destroy(ndev); @@ -406,7 +375,6 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) } #endif -#ifdef CONFIG_IPV6_PRIVACY INIT_LIST_HEAD(&ndev->tempaddr_list); setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev); if ((dev->flags&IFF_LOOPBACK) || @@ -419,7 +387,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) in6_dev_hold(ndev); ipv6_regen_rndid((unsigned long) ndev); } -#endif + ndev->token = in6addr_any; if (netif_running(dev) && addrconf_qdisc_ok(dev)) @@ -776,7 +744,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) in6_dev_put(ifp->idev); - if (del_timer(&ifp->timer)) + if (del_timer(&ifp->dad_timer)) pr_notice("Timer is still running, when freeing ifa=%p\n", ifp); if (ifp->state != INET6_IFADDR_STATE_DEAD) { @@ -816,8 +784,9 @@ static u32 inet6_addr_hash(const struct in6_addr *addr) /* On success it returns ifp with increased reference count */ static struct inet6_ifaddr * -ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, - int scope, u32 flags) +ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, + const struct in6_addr *peer_addr, int pfxlen, + int scope, u32 flags, u32 valid_lft, u32 prefered_lft) { struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; @@ -846,7 +815,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, /* Ignore adding duplicate addresses on an interface */ if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { - ADBG(("ipv6_add_addr: already assigned\n")); + ADBG("ipv6_add_addr: already assigned\n"); err = -EEXIST; goto out; } @@ -854,7 +823,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); if (ifa == NULL) { - ADBG(("ipv6_add_addr: malloc failed\n")); + ADBG("ipv6_add_addr: malloc failed\n"); err = -ENOBUFS; goto out; } @@ -866,15 +835,19 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, } ifa->addr = *addr; + if (peer_addr) + ifa->peer_addr = *peer_addr; spin_lock_init(&ifa->lock); spin_lock_init(&ifa->state_lock); - init_timer(&ifa->timer); + setup_timer(&ifa->dad_timer, addrconf_dad_timer, + (unsigned long)ifa); INIT_HLIST_NODE(&ifa->addr_lst); - ifa->timer.data = (unsigned long) ifa; ifa->scope = scope; ifa->prefix_len = pfxlen; ifa->flags = flags | IFA_F_TENTATIVE; + ifa->valid_lft = valid_lft; + ifa->prefered_lft = prefered_lft; ifa->cstamp = ifa->tstamp = jiffies; ifa->tokenized = false; @@ -895,12 +868,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, /* Add to inet6_dev unicast addr list. */ ipv6_link_dev_addr(idev, ifa); -#ifdef CONFIG_IPV6_PRIVACY if (ifa->flags&IFA_F_TEMPORARY) { list_add(&ifa->tmp_list, &idev->tempaddr_list); in6_ifa_hold(ifa); } -#endif in6_ifa_hold(ifa); write_unlock(&idev->lock); @@ -943,7 +914,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) spin_unlock_bh(&addrconf_hash_lock); write_lock_bh(&idev->lock); -#ifdef CONFIG_IPV6_PRIVACY + if (ifp->flags&IFA_F_TEMPORARY) { list_del(&ifp->tmp_list); if (ifp->ifpub) { @@ -952,7 +923,6 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } __in6_ifa_put(ifp); } -#endif list_for_each_entry_safe(ifa, ifn, &idev->addr_list, if_list) { if (ifa == ifp) { @@ -994,7 +964,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } write_unlock_bh(&idev->lock); - addrconf_del_timer(ifp); + addrconf_del_dad_timer(ifp); ipv6_ifa_notify(RTM_DELADDR, ifp); @@ -1043,7 +1013,6 @@ out: in6_ifa_put(ifp); } -#ifdef CONFIG_IPV6_PRIVACY static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *ift) { struct inet6_dev *idev = ifp->idev; @@ -1052,7 +1021,6 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i unsigned long regen_advance; int tmp_plen; int ret = 0; - int max_addresses; u32 addr_flags; unsigned long now = jiffies; @@ -1098,7 +1066,6 @@ retry: idev->cnf.temp_prefered_lft + age - idev->cnf.max_desync_factor); tmp_plen = ifp->prefix_len; - max_addresses = idev->cnf.max_addresses; tmp_tstamp = ifp->tstamp; spin_unlock_bh(&ifp->lock); @@ -1124,12 +1091,10 @@ retry: if (ifp->flags & IFA_F_OPTIMISTIC) addr_flags |= IFA_F_OPTIMISTIC; - ift = !max_addresses || - ipv6_count_addresses(idev) < max_addresses ? - ipv6_add_addr(idev, &addr, tmp_plen, - ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, - addr_flags) : NULL; - if (IS_ERR_OR_NULL(ift)) { + ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen, + ipv6_addr_scope(&addr), addr_flags, + tmp_valid_lft, tmp_prefered_lft); + if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); pr_info("%s: retry temporary address regeneration\n", __func__); @@ -1140,8 +1105,6 @@ retry: spin_lock_bh(&ift->lock); ift->ifpub = ifp; - ift->valid_lft = tmp_valid_lft; - ift->prefered_lft = tmp_prefered_lft; ift->cstamp = now; ift->tstamp = tmp_tstamp; spin_unlock_bh(&ift->lock); @@ -1152,7 +1115,6 @@ retry: out: return ret; } -#endif /* * Choose an appropriate source address (RFC3484) @@ -1167,9 +1129,7 @@ enum { #endif IPV6_SADDR_RULE_OIF, IPV6_SADDR_RULE_LABEL, -#ifdef CONFIG_IPV6_PRIVACY IPV6_SADDR_RULE_PRIVACY, -#endif IPV6_SADDR_RULE_ORCHID, IPV6_SADDR_RULE_PREFIX, IPV6_SADDR_RULE_MAX @@ -1283,7 +1243,6 @@ static int ipv6_get_saddr_eval(struct net *net, &score->ifa->addr, score->addr_type, score->ifa->idev->dev->ifindex) == dst->label; break; -#ifdef CONFIG_IPV6_PRIVACY case IPV6_SADDR_RULE_PRIVACY: { /* Rule 7: Prefer public address @@ -1295,7 +1254,6 @@ static int ipv6_get_saddr_eval(struct net *net, ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp; break; } -#endif case IPV6_SADDR_RULE_ORCHID: /* Rule 8-: Prefer ORCHID vs ORCHID or * non-ORCHID vs non-ORCHID @@ -1448,6 +1406,23 @@ try_nextdev: } EXPORT_SYMBOL(ipv6_dev_get_saddr); +int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, + unsigned char banned_flags) +{ + struct inet6_ifaddr *ifp; + int err = -EADDRNOTAVAIL; + + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & banned_flags)) { + *addr = ifp->addr; + err = 0; + break; + } + } + return err; +} + int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, unsigned char banned_flags) { @@ -1457,17 +1432,8 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - struct inet6_ifaddr *ifp; - read_lock_bh(&idev->lock); - list_for_each_entry(ifp, &idev->addr_list, if_list) { - if (ifp->scope == IFA_LINK && - !(ifp->flags & banned_flags)) { - *addr = ifp->addr; - err = 0; - break; - } - } + err = __ipv6_get_lladdr(idev, addr, banned_flags); read_unlock_bh(&idev->lock); } rcu_read_unlock(); @@ -1527,6 +1493,33 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, return false; } +/* Compares an address/prefix_len with addresses on device @dev. + * If one is found it returns true. + */ +bool ipv6_chk_custom_prefix(const struct in6_addr *addr, + const unsigned int prefix_len, struct net_device *dev) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + bool ret = false; + + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); + if (ret) + break; + } + read_unlock_bh(&idev->lock); + } + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(ipv6_chk_custom_prefix); + int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { struct inet6_dev *idev; @@ -1581,7 +1574,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { if (ifp->flags&IFA_F_PERMANENT) { spin_lock_bh(&ifp->lock); - addrconf_del_timer(ifp); + addrconf_del_dad_timer(ifp); ifp->flags |= IFA_F_TENTATIVE; if (dad_failed) ifp->flags |= IFA_F_DADFAILED; @@ -1589,7 +1582,6 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) if (dad_failed) ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); -#ifdef CONFIG_IPV6_PRIVACY } else if (ifp->flags&IFA_F_TEMPORARY) { struct inet6_ifaddr *ifpub; spin_lock_bh(&ifp->lock); @@ -1603,7 +1595,6 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); -#endif } else ipv6_del_addr(ifp); } @@ -1801,6 +1792,16 @@ static int addrconf_ifid_gre(u8 *eui, struct net_device *dev) return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); } +static int addrconf_ifid_ip6tnl(u8 *eui, struct net_device *dev) +{ + memcpy(eui, dev->perm_addr, 3); + memcpy(eui + 5, dev->perm_addr + 3, 3); + eui[3] = 0xFF; + eui[4] = 0xFE; + eui[0] ^= 2; + return 0; +} + static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) { switch (dev->type) { @@ -1819,6 +1820,8 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) return addrconf_ifid_eui64(eui, dev); case ARPHRD_IEEE1394: return addrconf_ifid_ieee1394(eui, dev); + case ARPHRD_TUNNEL6: + return addrconf_ifid_ip6tnl(eui, dev); } return -1; } @@ -1840,7 +1843,6 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) return err; } -#ifdef CONFIG_IPV6_PRIVACY /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */ static void __ipv6_regen_rndid(struct inet6_dev *idev) { @@ -1908,7 +1910,6 @@ static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmp if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0) __ipv6_regen_rndid(idev); } -#endif /* * Add prefix route. @@ -1995,23 +1996,6 @@ static void addrconf_add_mroute(struct net_device *dev) ip6_route_add(&cfg); } -#if IS_ENABLED(CONFIG_IPV6_SIT) -static void sit_route_add(struct net_device *dev) -{ - struct fib6_config cfg = { - .fc_table = RT6_TABLE_MAIN, - .fc_metric = IP6_RT_PRIO_ADDRCONF, - .fc_ifindex = dev->ifindex, - .fc_dst_len = 96, - .fc_flags = RTF_UP | RTF_NONEXTHOP, - .fc_nlinfo.nl_net = dev_net(dev), - }; - - /* prefix length - 96 bits "::d.d.d.d" */ - ip6_route_add(&cfg); -} -#endif - static struct inet6_dev *addrconf_add_dev(struct net_device *dev) { struct inet6_dev *idev; @@ -2044,7 +2028,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) pinfo = (struct prefix_info *) opt; if (len < sizeof(struct prefix_info)) { - ADBG(("addrconf: prefix option too short\n")); + ADBG("addrconf: prefix option too short\n"); return; } @@ -2175,16 +2159,19 @@ ok: */ if (!max_addresses || ipv6_count_addresses(in6_dev) < max_addresses) - ifp = ipv6_add_addr(in6_dev, &addr, pinfo->prefix_len, + ifp = ipv6_add_addr(in6_dev, &addr, NULL, + pinfo->prefix_len, addr_type&IPV6_ADDR_SCOPE_MASK, - addr_flags); + addr_flags, valid_lft, + prefered_lft); if (IS_ERR_OR_NULL(ifp)) { in6_dev_put(in6_dev); return; } - update_lft = create = 1; + update_lft = 0; + create = 1; ifp->cstamp = jiffies; ifp->tokenized = tokenized; addrconf_dad_start(ifp); @@ -2193,9 +2180,7 @@ ok: if (ifp) { int flags; unsigned long now; -#ifdef CONFIG_IPV6_PRIVACY struct inet6_ifaddr *ift; -#endif u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ @@ -2205,44 +2190,22 @@ ok: stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; - if (!update_lft && stored_lft) { - if (valid_lft > MIN_VALID_LIFETIME || - valid_lft > stored_lft) - update_lft = 1; - else if (stored_lft <= MIN_VALID_LIFETIME) { - /* valid_lft <= stored_lft is always true */ - /* - * RFC 4862 Section 5.5.3e: - * "Note that the preferred lifetime of - * the corresponding address is always - * reset to the Preferred Lifetime in - * the received Prefix Information - * option, regardless of whether the - * valid lifetime is also reset or - * ignored." - * - * So if the preferred lifetime in - * this advertisement is different - * than what we have stored, but the - * valid lifetime is invalid, just - * reset prefered_lft. - * - * We must set the valid lifetime - * to the stored lifetime since we'll - * be updating the timestamp below, - * else we'll set it back to the - * minimum. - */ - if (prefered_lft != ifp->prefered_lft) { - valid_lft = stored_lft; - update_lft = 1; - } - } else { - valid_lft = MIN_VALID_LIFETIME; - if (valid_lft < prefered_lft) - prefered_lft = valid_lft; - update_lft = 1; - } + if (!update_lft && !create && stored_lft) { + const u32 minimum_lft = min( + stored_lft, (u32)MIN_VALID_LIFETIME); + valid_lft = max(valid_lft, minimum_lft); + + /* RFC4862 Section 5.5.3e: + * "Note that the preferred lifetime of the + * corresponding address is always reset to + * the Preferred Lifetime in the received + * Prefix Information option, regardless of + * whether the valid lifetime is also reset or + * ignored." + * + * So we should always update prefered_lft here. + */ + update_lft = 1; } if (update_lft) { @@ -2258,7 +2221,6 @@ ok: } else spin_unlock(&ifp->lock); -#ifdef CONFIG_IPV6_PRIVACY read_lock_bh(&in6_dev->lock); /* update all temporary addresses in the list */ list_for_each_entry(ift, &in6_dev->tempaddr_list, @@ -2323,7 +2285,7 @@ ok: } else { read_unlock_bh(&in6_dev->lock); } -#endif + in6_ifa_put(ifp); addrconf_verify(0); } @@ -2402,6 +2364,7 @@ err_exit: * Manual configuration of address on an interface */ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx, + const struct in6_addr *peer_pfx, unsigned int plen, __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft) { @@ -2450,15 +2413,10 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *p prefered_lft = timeout; } - ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags); + ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags, + valid_lft, prefered_lft); if (!IS_ERR(ifp)) { - spin_lock_bh(&ifp->lock); - ifp->valid_lft = valid_lft; - ifp->prefered_lft = prefered_lft; - ifp->tstamp = jiffies; - spin_unlock_bh(&ifp->lock); - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, expires, flags); /* @@ -2500,12 +2458,6 @@ static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *p read_unlock_bh(&idev->lock); ipv6_del_addr(ifp); - - /* If the last address is deleted administratively, - disable IPv6 on this interface. - */ - if (list_empty(&idev->addr_list)) - addrconf_ifdown(idev->dev, 1); return 0; } } @@ -2526,7 +2478,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) return -EFAULT; rtnl_lock(); - err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, + err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL, ireq.ifr6_prefixlen, IFA_F_PERMANENT, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); rtnl_unlock(); @@ -2556,7 +2508,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, { struct inet6_ifaddr *ifp; - ifp = ipv6_add_addr(idev, addr, plen, scope, IFA_F_PERMANENT); + ifp = ipv6_add_addr(idev, addr, NULL, plen, + scope, IFA_F_PERMANENT, 0, 0); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; @@ -2572,7 +2525,8 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) struct in6_addr addr; struct net_device *dev; struct net *net = dev_net(idev->dev); - int scope; + int scope, plen; + u32 pflags = 0; ASSERT_RTNL(); @@ -2582,12 +2536,16 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) if (idev->dev->flags&IFF_POINTOPOINT) { addr.s6_addr32[0] = htonl(0xfe800000); scope = IFA_LINK; + plen = 64; } else { scope = IPV6_ADDR_COMPATv4; + plen = 96; + pflags |= RTF_NONEXTHOP; } if (addr.s6_addr32[3]) { - add_addr(idev, &addr, 128, scope); + add_addr(idev, &addr, plen, scope); + addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags); return; } @@ -2599,7 +2557,6 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) int flag = scope; for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { - int plen; addr.s6_addr32[3] = ifa->ifa_local; @@ -2610,12 +2567,10 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) continue; flag |= IFA_HOST; } - if (idev->dev->flags&IFF_POINTOPOINT) - plen = 64; - else - plen = 96; add_addr(idev, &addr, plen, flag); + addrconf_prefix_route(&addr, plen, idev->dev, 0, + pflags); } } } @@ -2682,7 +2637,7 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr #endif - ifp = ipv6_add_addr(idev, addr, 64, IFA_LINK, addr_flags); + ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, 0, 0); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); addrconf_dad_start(ifp); @@ -2702,7 +2657,8 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_ARCNET) && (dev->type != ARPHRD_INFINIBAND) && (dev->type != ARPHRD_IEEE802154) && - (dev->type != ARPHRD_IEEE1394)) { + (dev->type != ARPHRD_IEEE1394) && + (dev->type != ARPHRD_TUNNEL6)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } @@ -2740,7 +2696,6 @@ static void addrconf_sit_config(struct net_device *dev) struct in6_addr addr; ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - addrconf_prefix_route(&addr, 64, dev, 0, 0); if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) addrconf_add_linklocal(idev, &addr); return; @@ -2750,8 +2705,6 @@ static void addrconf_sit_config(struct net_device *dev) if (dev->flags&IFF_POINTOPOINT) addrconf_add_mroute(dev); - else - sit_route_add(dev); } #endif @@ -2761,8 +2714,6 @@ static void addrconf_gre_config(struct net_device *dev) struct inet6_dev *idev; struct in6_addr addr; - pr_info("%s(%s)\n", __func__, dev->name); - ASSERT_RTNL(); if ((idev = ipv6_find_idev(dev)) == NULL) { @@ -2771,8 +2722,6 @@ static void addrconf_gre_config(struct net_device *dev) } ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - addrconf_prefix_route(&addr, 64, dev, 0, 0); - if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) addrconf_add_linklocal(idev, &addr); } @@ -2790,48 +2739,10 @@ ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev) return -1; } -static void ip6_tnl_add_linklocal(struct inet6_dev *idev) -{ - struct net_device *link_dev; - struct net *net = dev_net(idev->dev); - - /* first try to inherit the link-local address from the link device */ - if (idev->dev->iflink && - (link_dev = __dev_get_by_index(net, idev->dev->iflink))) { - if (!ipv6_inherit_linklocal(idev, link_dev)) - return; - } - /* then try to inherit it from any device */ - for_each_netdev(net, link_dev) { - if (!ipv6_inherit_linklocal(idev, link_dev)) - return; - } - pr_debug("init ip6-ip6: add_linklocal failed\n"); -} - -/* - * Autoconfigure tunnel with a link-local address so routing protocols, - * DHCPv6, MLD etc. can be run over the virtual link - */ - -static void addrconf_ip6_tnl_config(struct net_device *dev) -{ - struct inet6_dev *idev; - - ASSERT_RTNL(); - - idev = addrconf_add_dev(dev); - if (IS_ERR(idev)) { - pr_debug("init ip6-ip6: add_dev failed\n"); - return; - } - ip6_tnl_add_linklocal(idev); -} - static int addrconf_notify(struct notifier_block *this, unsigned long event, - void *data) + void *ptr) { - struct net_device *dev = (struct net_device *) data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); int run_pending = 0; int err; @@ -2895,9 +2806,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, addrconf_gre_config(dev); break; #endif - case ARPHRD_TUNNEL6: - addrconf_ip6_tnl_config(dev); - break; case ARPHRD_LOOPBACK: init_loopback(dev); break; @@ -3039,7 +2947,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { hlist_del_init_rcu(&ifa->addr_lst); - addrconf_del_timer(ifa); + addrconf_del_dad_timer(ifa); goto restart; } } @@ -3048,11 +2956,12 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_lock_bh(&idev->lock); + addrconf_del_rs_timer(idev); + /* Step 2: clear flags for stateless addrconf */ if (!how) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); -#ifdef CONFIG_IPV6_PRIVACY if (how && del_timer(&idev->regen_timer)) in6_dev_put(idev); @@ -3072,12 +2981,11 @@ static int addrconf_ifdown(struct net_device *dev, int how) in6_ifa_put(ifa); write_lock_bh(&idev->lock); } -#endif while (!list_empty(&idev->addr_list)) { ifa = list_first_entry(&idev->addr_list, struct inet6_ifaddr, if_list); - addrconf_del_timer(ifa); + addrconf_del_dad_timer(ifa); list_del(&ifa->if_list); @@ -3119,10 +3027,11 @@ static int addrconf_ifdown(struct net_device *dev, int how) static void addrconf_rs_timer(unsigned long data) { - struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data; - struct inet6_dev *idev = ifp->idev; + struct inet6_dev *idev = (struct inet6_dev *)data; + struct net_device *dev = idev->dev; + struct in6_addr lladdr; - read_lock(&idev->lock); + write_lock(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) goto out; @@ -3133,18 +3042,21 @@ static void addrconf_rs_timer(unsigned long data) if (idev->if_flags & IF_RA_RCVD) goto out; - spin_lock(&ifp->lock); - if (ifp->probes++ < idev->cnf.rtr_solicits) { - /* The wait after the last probe can be shorter */ - addrconf_mod_timer(ifp, AC_RS, - (ifp->probes == idev->cnf.rtr_solicits) ? - idev->cnf.rtr_solicit_delay : - idev->cnf.rtr_solicit_interval); - spin_unlock(&ifp->lock); + if (idev->rs_probes++ < idev->cnf.rtr_solicits) { + write_unlock(&idev->lock); + if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) + ndisc_send_rs(dev, &lladdr, + &in6addr_linklocal_allrouters); + else + goto put; - ndisc_send_rs(idev->dev, &ifp->addr, &in6addr_linklocal_allrouters); + write_lock(&idev->lock); + /* The wait after the last probe can be shorter */ + addrconf_mod_rs_timer(idev, (idev->rs_probes == + idev->cnf.rtr_solicits) ? + idev->cnf.rtr_solicit_delay : + idev->cnf.rtr_solicit_interval); } else { - spin_unlock(&ifp->lock); /* * Note: we do not support deprecated "all on-link" * assumption any longer. @@ -3153,8 +3065,9 @@ static void addrconf_rs_timer(unsigned long data) } out: - read_unlock(&idev->lock); - in6_ifa_put(ifp); + write_unlock(&idev->lock); +put: + in6_dev_put(idev); } /* @@ -3170,8 +3083,8 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) else rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1); - ifp->probes = idev->cnf.dad_transmits; - addrconf_mod_timer(ifp, AC_DAD, rand_num); + ifp->dad_probes = idev->cnf.dad_transmits; + addrconf_mod_dad_timer(ifp, rand_num); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) @@ -3232,40 +3145,40 @@ static void addrconf_dad_timer(unsigned long data) struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; - if (!ifp->probes && addrconf_dad_end(ifp)) + if (!ifp->dad_probes && addrconf_dad_end(ifp)) goto out; - read_lock(&idev->lock); + write_lock(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) { - read_unlock(&idev->lock); + write_unlock(&idev->lock); goto out; } spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) { spin_unlock(&ifp->lock); - read_unlock(&idev->lock); + write_unlock(&idev->lock); goto out; } - if (ifp->probes == 0) { + if (ifp->dad_probes == 0) { /* * DAD was successful */ ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); - read_unlock(&idev->lock); + write_unlock(&idev->lock); addrconf_dad_completed(ifp); goto out; } - ifp->probes--; - addrconf_mod_timer(ifp, AC_DAD, ifp->idev->nd_parms->retrans_time); + ifp->dad_probes--; + addrconf_mod_dad_timer(ifp, ifp->idev->nd_parms->retrans_time); spin_unlock(&ifp->lock); - read_unlock(&idev->lock); + write_unlock(&idev->lock); /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); @@ -3277,6 +3190,10 @@ out: static void addrconf_dad_completed(struct inet6_ifaddr *ifp) { struct net_device *dev = ifp->idev->dev; + struct in6_addr lladdr; + bool send_rs, send_mld; + + addrconf_del_dad_timer(ifp); /* * Configure the address for reception. Now it is valid. @@ -3288,22 +3205,41 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) router advertisements, start sending router solicitations. */ - if (ipv6_accept_ra(ifp->idev) && - ifp->idev->cnf.rtr_solicits > 0 && - (dev->flags&IFF_LOOPBACK) == 0 && - (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) { + read_lock_bh(&ifp->idev->lock); + spin_lock(&ifp->lock); + send_mld = ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL && + ifp->idev->valid_ll_addr_cnt == 1; + send_rs = send_mld && + ipv6_accept_ra(ifp->idev) && + ifp->idev->cnf.rtr_solicits > 0 && + (dev->flags&IFF_LOOPBACK) == 0; + spin_unlock(&ifp->lock); + read_unlock_bh(&ifp->idev->lock); + + /* While dad is in progress mld report's source address is in6_addrany. + * Resend with proper ll now. + */ + if (send_mld) + ipv6_mc_dad_complete(ifp->idev); + + if (send_rs) { /* * If a host as already performed a random delay * [...] as part of DAD [...] there is no need * to delay again before sending the first RS */ - ndisc_send_rs(ifp->idev->dev, &ifp->addr, &in6addr_linklocal_allrouters); + if (ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) + return; + ndisc_send_rs(dev, &lladdr, &in6addr_linklocal_allrouters); - spin_lock_bh(&ifp->lock); - ifp->probes = 1; + write_lock_bh(&ifp->idev->lock); + spin_lock(&ifp->lock); + ifp->idev->rs_probes = 1; ifp->idev->if_flags |= IF_RS_SENT; - addrconf_mod_timer(ifp, AC_RS, ifp->idev->cnf.rtr_solicit_interval); - spin_unlock_bh(&ifp->lock); + addrconf_mod_rs_timer(ifp->idev, + ifp->idev->cnf.rtr_solicit_interval); + spin_unlock(&ifp->lock); + write_unlock_bh(&ifp->idev->lock); } } @@ -3557,7 +3493,6 @@ restart: in6_ifa_put(ifp); goto restart; } -#ifdef CONFIG_IPV6_PRIVACY } else if ((ifp->flags&IFA_F_TEMPORARY) && !(ifp->flags&IFA_F_TENTATIVE)) { unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * @@ -3585,7 +3520,6 @@ restart: } else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ; spin_unlock(&ifp->lock); -#endif } else { /* ifp->prefered_lft <= ifp->valid_lft */ if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) @@ -3606,8 +3540,8 @@ restart: if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX; - ADBG((KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", - now, next, next_sec, next_sched)); + ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", + now, next, next_sec, next_sched); addr_chk_timer.expires = next_sched; add_timer(&addr_chk_timer); @@ -3615,18 +3549,20 @@ restart: rcu_read_unlock_bh(); } -static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local) +static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, + struct in6_addr **peer_pfx) { struct in6_addr *pfx = NULL; + *peer_pfx = NULL; + if (addr) pfx = nla_data(addr); if (local) { if (pfx && nla_memcmp(local, pfx, sizeof(*pfx))) - pfx = NULL; - else - pfx = nla_data(local); + *peer_pfx = pfx; + pfx = nla_data(local); } return pfx; @@ -3644,7 +3580,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; - struct in6_addr *pfx; + struct in6_addr *pfx, *peer_pfx; int err; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); @@ -3652,7 +3588,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) return err; ifm = nlmsg_data(nlh); - pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); + pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (pfx == NULL) return -EINVAL; @@ -3710,7 +3646,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; - struct in6_addr *pfx; + struct in6_addr *pfx, *peer_pfx; struct inet6_ifaddr *ifa; struct net_device *dev; u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME; @@ -3722,7 +3658,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) return err; ifm = nlmsg_data(nlh); - pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); + pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (pfx == NULL) return -EINVAL; @@ -3750,7 +3686,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) * It would be best to check for !NLM_F_CREATE here but * userspace alreay relies on not having to provide this. */ - return inet6_addr_add(net, ifm->ifa_index, pfx, + return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx, ifm->ifa_prefixlen, ifa_flags, preferred_lft, valid_lft); } @@ -3807,6 +3743,7 @@ static inline int rt_scope(int ifa_scope) static inline int inet6_ifaddr_msgsize(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(16) /* IFA_LOCAL */ + nla_total_size(16) /* IFA_ADDRESS */ + nla_total_size(sizeof(struct ifa_cacheinfo)); } @@ -3845,13 +3782,22 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, valid = INFINITY_LIFE_TIME; } - if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0 || - put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) { - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; - } + if (!ipv6_addr_any(&ifa->peer_addr)) { + if (nla_put(skb, IFA_LOCAL, 16, &ifa->addr) < 0 || + nla_put(skb, IFA_ADDRESS, 16, &ifa->peer_addr) < 0) + goto error; + } else + if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0) + goto error; + + if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) + goto error; return nlmsg_end(skb, nlh); + +error: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, @@ -4051,7 +3997,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh) struct net *net = sock_net(in_skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; - struct in6_addr *addr = NULL; + struct in6_addr *addr = NULL, *peer; struct net_device *dev = NULL; struct inet6_ifaddr *ifa; struct sk_buff *skb; @@ -4061,7 +4007,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); + addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); if (addr == NULL) { err = -EINVAL; goto errout; @@ -4141,13 +4087,15 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_RTR_SOLICIT_DELAY] = jiffies_to_msecs(cnf->rtr_solicit_delay); array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version; -#ifdef CONFIG_IPV6_PRIVACY + array[DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL] = + jiffies_to_msecs(cnf->mldv1_unsolicited_report_interval); + array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] = + jiffies_to_msecs(cnf->mldv2_unsolicited_report_interval); array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr; array[DEVCONF_TEMP_VALID_LFT] = cnf->temp_valid_lft; array[DEVCONF_TEMP_PREFERED_LFT] = cnf->temp_prefered_lft; array[DEVCONF_REGEN_MAX_RETRY] = cnf->regen_max_retry; array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; -#endif array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; @@ -4171,6 +4119,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; + array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; } static inline size_t inet6_ifla6_size(void) @@ -4339,8 +4288,11 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) write_lock_bh(&idev->lock); - if (update_rs) + if (update_rs) { idev->if_flags |= IF_RS_SENT; + idev->rs_probes = 1; + addrconf_mod_rs_timer(idev, idev->cnf.rtr_solicit_interval); + } /* Well, that's kinda nasty ... */ list_for_each_entry(ifp, &idev->addr_list, if_list) { @@ -4353,6 +4305,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) } write_unlock_bh(&idev->lock); + addrconf_verify(0); return 0; } @@ -4550,6 +4503,19 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); } +static void update_valid_ll_addr_cnt(struct inet6_ifaddr *ifp, int count) +{ + write_lock_bh(&ifp->idev->lock); + spin_lock(&ifp->lock); + if (((ifp->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|IFA_F_OPTIMISTIC| + IFA_F_DADFAILED)) == IFA_F_PERMANENT) && + (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) + ifp->idev->valid_ll_addr_cnt += count; + WARN_ON(ifp->idev->valid_ll_addr_cnt < 0); + spin_unlock(&ifp->lock); + write_unlock_bh(&ifp->idev->lock); +} + static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); @@ -4558,6 +4524,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) switch (event) { case RTM_NEWADDR: + update_valid_ll_addr_cnt(ifp, 1); + /* * If the address was optimistic * we inserted the route at the start of @@ -4568,11 +4536,28 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) ip6_ins_rt(ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); + if (!ipv6_addr_any(&ifp->peer_addr)) + addrconf_prefix_route(&ifp->peer_addr, 128, + ifp->idev->dev, 0, 0); break; case RTM_DELADDR: + update_valid_ll_addr_cnt(ifp, -1); + if (ifp->idev->cnf.forwarding) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); + if (!ipv6_addr_any(&ifp->peer_addr)) { + struct rt6_info *rt; + struct net_device *dev = ifp->idev->dev; + + rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL, + dev->ifindex, 1); + if (rt) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } + } dst_hold(&ifp->rt->dst); if (ip6_del_rt(ifp->rt)) @@ -4580,6 +4565,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) break; } atomic_inc(&net->ipv6.dev_addr_genid); + rt_genid_bump_ipv6(net); } static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) @@ -4593,13 +4579,13 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) #ifdef CONFIG_SYSCTL static -int addrconf_sysctl_forward(ctl_table *ctl, int write, +int addrconf_sysctl_forward(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; - ctl_table lctl; + struct ctl_table lctl; int ret; /* @@ -4620,13 +4606,16 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, static void dev_disable_change(struct inet6_dev *idev) { + struct netdev_notifier_info info; + if (!idev || !idev->dev) return; + netdev_notifier_info_init(&info, idev->dev); if (idev->cnf.disable_ipv6) - addrconf_notify(NULL, NETDEV_DOWN, idev->dev); + addrconf_notify(NULL, NETDEV_DOWN, &info); else - addrconf_notify(NULL, NETDEV_UP, idev->dev); + addrconf_notify(NULL, NETDEV_UP, &info); } static void addrconf_disable_change(struct net *net, __s32 newf) @@ -4675,13 +4664,13 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) } static -int addrconf_sysctl_disable(ctl_table *ctl, int write, +int addrconf_sysctl_disable(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; - ctl_table lctl; + struct ctl_table lctl; int ret; /* @@ -4703,7 +4692,7 @@ int addrconf_sysctl_disable(ctl_table *ctl, int write, static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; - ctl_table addrconf_vars[DEVCONF_MAX+1]; + struct ctl_table addrconf_vars[DEVCONF_MAX+1]; } addrconf_sysctl __read_mostly = { .sysctl_header = NULL, .addrconf_vars = { @@ -4784,7 +4773,22 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, -#ifdef CONFIG_IPV6_PRIVACY + { + .procname = "mldv1_unsolicited_report_interval", + .data = + &ipv6_devconf.mldv1_unsolicited_report_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + }, + { + .procname = "mldv2_unsolicited_report_interval", + .data = + &ipv6_devconf.mldv2_unsolicited_report_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + }, { .procname = "use_tempaddr", .data = &ipv6_devconf.use_tempaddr, @@ -4820,7 +4824,6 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, -#endif { .procname = "max_addresses", .data = &ipv6_devconf.max_addresses, @@ -4929,6 +4932,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec }, { + .procname = "suppress_frag_ndisc", + .data = &ipv6_devconf.suppress_frag_ndisc, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { /* sentinel */ } }, diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 7210456..4c11cbc 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -5,6 +5,8 @@ #include <linux/export.h> #include <net/ipv6.h> +#include <net/addrconf.h> +#include <net/ip.h> #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) @@ -97,3 +99,52 @@ int inet6addr_notifier_call_chain(unsigned long val, void *v) return atomic_notifier_call_chain(&inet6addr_chain, val, v); } EXPORT_SYMBOL(inet6addr_notifier_call_chain); + +const struct ipv6_stub *ipv6_stub __read_mostly; +EXPORT_SYMBOL_GPL(ipv6_stub); + +/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ +const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +EXPORT_SYMBOL(in6addr_loopback); +const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +EXPORT_SYMBOL(in6addr_any); +const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +EXPORT_SYMBOL(in6addr_linklocal_allnodes); +const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +EXPORT_SYMBOL(in6addr_linklocal_allrouters); +const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); +const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); +const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; +EXPORT_SYMBOL(in6addr_sitelocal_allrouters); + +static void snmp6_free_dev(struct inet6_dev *idev) +{ + kfree(idev->stats.icmpv6msgdev); + kfree(idev->stats.icmpv6dev); + snmp_mib_free((void __percpu **)idev->stats.ipv6); +} + +/* Nobody refers to this device, we may destroy it. */ + +void in6_dev_finish_destroy(struct inet6_dev *idev) +{ + struct net_device *dev = idev->dev; + + WARN_ON(!list_empty(&idev->addr_list)); + WARN_ON(idev->mc_list != NULL); + WARN_ON(timer_pending(&idev->rs_timer)); + +#ifdef NET_REFCNT_DEBUG + pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); +#endif + dev_put(dev); + if (!idev->dead) { + pr_warn("Freeing alive inet6 device %p\n", idev); + return; + } + snmp6_free_dev(idev); + kfree_rcu(idev, rcu); +} +EXPORT_SYMBOL(in6_dev_finish_destroy); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f083a58..b30ad37 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -251,38 +251,36 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, /* add a label */ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) { + struct hlist_node *n; + struct ip6addrlbl_entry *last = NULL, *p = NULL; int ret = 0; - ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", - __func__, - newp, replace); + ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp, + replace); - if (hlist_empty(&ip6addrlbl_table.head)) { - hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); - } else { - struct hlist_node *n; - struct ip6addrlbl_entry *p = NULL; - hlist_for_each_entry_safe(p, n, - &ip6addrlbl_table.head, list) { - if (p->prefixlen == newp->prefixlen && - net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && - p->ifindex == newp->ifindex && - ipv6_addr_equal(&p->prefix, &newp->prefix)) { - if (!replace) { - ret = -EEXIST; - goto out; - } - hlist_replace_rcu(&p->list, &newp->list); - ip6addrlbl_put(p); - goto out; - } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || - (p->prefixlen < newp->prefixlen)) { - hlist_add_before_rcu(&newp->list, &p->list); + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + if (p->prefixlen == newp->prefixlen && + net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && + p->ifindex == newp->ifindex && + ipv6_addr_equal(&p->prefix, &newp->prefix)) { + if (!replace) { + ret = -EEXIST; goto out; } + hlist_replace_rcu(&p->list, &newp->list); + ip6addrlbl_put(p); + goto out; + } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || + (p->prefixlen < newp->prefixlen)) { + hlist_add_before_rcu(&newp->list, &p->list); + goto out; } - hlist_add_after_rcu(&p->list, &newp->list); + last = p; } + if (last) + hlist_add_after_rcu(&last->list, &newp->list); + else + hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); out: if (!ret) ip6addrlbl_table.seq++; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index ab5c7ad..4fbdb70 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -49,12 +49,14 @@ #include <net/udp.h> #include <net/udplite.h> #include <net/tcp.h> +#include <net/ping.h> #include <net/protocol.h> #include <net/inet_common.h> #include <net/route.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> +#include <net/ndisc.h> #ifdef CONFIG_IPV6_TUNNEL #include <net/ip6_tunnel.h> #endif @@ -108,11 +110,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, int try_loading_module = 0; int err; - if (sock->type != SOCK_RAW && - sock->type != SOCK_DGRAM && - !inet_ehash_secret) - build_ehash_secret(); - /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; @@ -362,7 +359,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) inet->inet_rcv_saddr = v4addr; inet->inet_saddr = v4addr; - np->rcv_saddr = addr->sin6_addr; + sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; @@ -459,14 +456,14 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, peer == 1) return -ENOTCONN; sin->sin6_port = inet->inet_dport; - sin->sin6_addr = np->daddr; + sin->sin6_addr = sk->sk_v6_daddr; if (np->sndflow) sin->sin6_flowinfo = np->flow_label; } else { - if (ipv6_addr_any(&np->rcv_saddr)) + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sin->sin6_addr = np->saddr; else - sin->sin6_addr = np->rcv_saddr; + sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; } @@ -653,7 +650,7 @@ int inet6_sk_rebuild_header(struct sock *sk) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; fl6.saddr = np->saddr; fl6.flowlabel = np->flow_label; fl6.flowi6_oif = sk->sk_bound_dev_if; @@ -717,6 +714,8 @@ static void ipv6_packet_cleanup(void) static int __net_init ipv6_init_mibs(struct net *net) { + int i; + if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6, sizeof(struct udp_mib), __alignof__(struct udp_mib)) < 0) @@ -729,6 +728,18 @@ static int __net_init ipv6_init_mibs(struct net *net) sizeof(struct ipstats_mib), __alignof__(struct ipstats_mib)) < 0) goto err_ip_mib; + + for_each_possible_cpu(i) { + struct ipstats_mib *af_inet6_stats; + af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[0], i); + u64_stats_init(&af_inet6_stats->syncp); +#if SNMP_ARRAY_SZ == 2 + af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[1], i); + u64_stats_init(&af_inet6_stats->syncp); +#endif + } + + if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics, sizeof(struct icmpv6_mib), __alignof__(struct icmpv6_mib)) < 0) @@ -765,6 +776,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; + atomic_set(&net->ipv6.rt_genid, 0); err = ipv6_init_mibs(net); if (err) @@ -808,6 +820,15 @@ static struct pernet_operations inet6_net_ops = { .exit = inet6_net_exit, }; +static const struct ipv6_stub ipv6_stub_impl = { + .ipv6_sock_mc_join = ipv6_sock_mc_join, + .ipv6_sock_mc_drop = ipv6_sock_mc_drop, + .ipv6_dst_lookup = ip6_dst_lookup, + .udpv6_encap_enable = udpv6_encap_enable, + .ndisc_send_na = ndisc_send_na, + .nd_tbl = &nd_tbl, +}; + static int __init inet6_init(void) { struct list_head *r; @@ -840,6 +861,9 @@ static int __init inet6_init(void) if (err) goto out_unregister_udplite_proto; + err = proto_register(&pingv6_prot, 1); + if (err) + goto out_unregister_ping_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. @@ -855,8 +879,6 @@ static int __init inet6_init(void) if (err) goto out_sock_register_fail; - tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem; - /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance @@ -879,6 +901,9 @@ static int __init inet6_init(void) err = igmp6_init(); if (err) goto igmp_fail; + + ipv6_stub = &ipv6_stub_impl; + err = ipv6_netfilter_init(); if (err) goto netfilter_fail; @@ -897,6 +922,9 @@ static int __init inet6_init(void) err = ip6_route_init(); if (err) goto ip6_route_fail; + err = ndisc_late_init(); + if (err) + goto ndisc_late_fail; err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; @@ -930,6 +958,10 @@ static int __init inet6_init(void) if (err) goto ipv6_packet_fail; + err = pingv6_init(); + if (err) + goto pingv6_fail; + #ifdef CONFIG_SYSCTL err = ipv6_sysctl_register(); if (err) @@ -940,8 +972,10 @@ out: #ifdef CONFIG_SYSCTL sysctl_fail: - ipv6_packet_cleanup(); + pingv6_exit(); #endif +pingv6_fail: + ipv6_packet_cleanup(); ipv6_packet_fail: tcpv6_exit(); tcpv6_fail: @@ -957,6 +991,8 @@ ipv6_exthdrs_fail: addrconf_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: + ndisc_late_cleanup(); +ndisc_late_fail: ip6_route_cleanup(); ip6_route_fail: #ifdef CONFIG_PROC_FS @@ -985,6 +1021,8 @@ register_pernet_fail: rtnl_unregister_all(PF_INET6); out_sock_register_fail: rawv6_exit(); +out_unregister_ping_proto: + proto_unregister(&pingv6_prot); out_unregister_raw_proto: proto_unregister(&rawv6_prot); out_unregister_udplite_proto: @@ -997,50 +1035,4 @@ out_unregister_tcp_proto: } module_init(inet6_init); -static void __exit inet6_exit(void) -{ - if (disable_ipv6_mod) - return; - - /* First of all disallow new sockets creation. */ - sock_unregister(PF_INET6); - /* Disallow any further netlink messages */ - rtnl_unregister_all(PF_INET6); - - udpv6_exit(); - udplitev6_exit(); - tcpv6_exit(); - - /* Cleanup code parts. */ - ipv6_packet_cleanup(); - ipv6_frag_exit(); - ipv6_exthdrs_exit(); - addrconf_cleanup(); - ip6_flowlabel_cleanup(); - ip6_route_cleanup(); -#ifdef CONFIG_PROC_FS - - /* Cleanup code parts. */ - if6_proc_exit(); - ipv6_misc_proc_exit(); - udplite6_proc_exit(); - raw6_proc_exit(); -#endif - ipv6_netfilter_fini(); - igmp6_cleanup(); - ndisc_cleanup(); - ip6_mr_cleanup(); - icmpv6_cleanup(); - rawv6_exit(); - - unregister_pernet_subsys(&inet6_net_ops); - proto_unregister(&rawv6_prot); - proto_unregister(&udplitev6_prot); - proto_unregister(&udpv6_prot); - proto_unregister(&tcpv6_prot); - - rcu_barrier(); /* Wait for completion of call_rcu()'s */ -} -module_exit(inet6_exit); - MODULE_ALIAS_NETPROTO(PF_INET6); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index bb02e17..82e1da3 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -618,8 +618,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; @@ -628,7 +627,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; if (type == NDISC_REDIRECT) - ip6_redirect(skb, net, 0, 0); + ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 4b56cbb..8dfe1f4 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -107,16 +107,16 @@ ipv4_connected: if (err) goto out; - ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr); + ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr); if (ipv6_addr_any(&np->saddr) || ipv6_mapped_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr) || - ipv6_mapped_addr_any(&np->rcv_saddr)) { + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || + ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, - &np->rcv_saddr); + &sk->sk_v6_rcv_saddr); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } @@ -145,7 +145,7 @@ ipv4_connected: } } - np->daddr = *daddr; + sk->sk_v6_daddr = *daddr; np->flow_label = fl6.flowlabel; inet->inet_dport = usin->sin6_port; @@ -156,7 +156,7 @@ ipv4_connected: */ fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; @@ -183,16 +183,16 @@ ipv4_connected: if (ipv6_addr_any(&np->saddr)) np->saddr = fl6.saddr; - if (ipv6_addr_any(&np->rcv_saddr)) { - np->rcv_saddr = fl6.saddr; + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + sk->sk_v6_rcv_saddr = fl6.saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &np->daddr) ? - &np->daddr : NULL, + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6.saddr, &np->saddr) ? &np->saddr : @@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) /* * Handle MSG_ERRQUEUE */ -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; @@ -369,6 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) &sin->sin6_addr); sin->sin6_scope_id = 0; } + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); @@ -377,6 +378,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; + sin->sin6_port = 0; if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) @@ -423,7 +425,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ -int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -457,6 +460,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; + *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); @@ -879,3 +883,29 @@ exit_f: return err; } EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); + +void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, + __u16 srcp, __u16 destp, int bucket) +{ + const struct in6_addr *dest, *src; + + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; + seq_printf(seq, + "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " + "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n", + bucket, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp, + sp->sk_state, + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), + 0, 0L, 0, + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + 0, + sock_i_ino(sp), + atomic_read(&sp->sk_refcnt), sp, + atomic_read(&sp->sk_drops)); +} diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 40ffd72..b8719df 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -164,10 +164,9 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) u8 *iv; u8 *tail; __be32 *seqhi; - struct esp_data *esp = x->data; /* skb is pure payload to encrypt */ - aead = esp->aead; + aead = x->data; alen = crypto_aead_authsize(aead); tfclen = 0; @@ -181,8 +180,6 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) } blksize = ALIGN(crypto_aead_blocksize(aead), 4); clen = ALIGN(skb->len + 2 + tfclen, blksize); - if (esp->padlen) - clen = ALIGN(clen, esp->padlen); plen = clen - skb->len - tfclen; err = skb_cow_data(skb, tfclen + plen + alen, &trailer); @@ -271,8 +268,7 @@ error: static int esp_input_done2(struct sk_buff *skb, int err) { struct xfrm_state *x = xfrm_input_state(skb); - struct esp_data *esp = x->data; - struct crypto_aead *aead = esp->aead; + struct crypto_aead *aead = x->data; int alen = crypto_aead_authsize(aead); int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); int elen = skb->len - hlen; @@ -325,8 +321,7 @@ static void esp_input_done(struct crypto_async_request *base, int err) static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) { struct ip_esp_hdr *esph; - struct esp_data *esp = x->data; - struct crypto_aead *aead = esp->aead; + struct crypto_aead *aead = x->data; struct aead_request *req; struct sk_buff *trailer; int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead); @@ -414,9 +409,8 @@ out: static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) { - struct esp_data *esp = x->data; - u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4); - u32 align = max_t(u32, blksize, esp->padlen); + struct crypto_aead *aead = x->data; + u32 blksize = ALIGN(crypto_aead_blocksize(aead), 4); unsigned int net_adj; if (x->props.mode != XFRM_MODE_TUNNEL) @@ -424,8 +418,8 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) else net_adj = 0; - return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - - net_adj) & ~(align - 1)) + (net_adj - 2); + return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - + net_adj) & ~(blksize - 1)) + net_adj - 2; } static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, @@ -436,8 +430,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; @@ -447,7 +440,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; if (type == NDISC_REDIRECT) - ip6_redirect(skb, net, 0, 0); + ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); @@ -455,18 +448,16 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, static void esp6_destroy(struct xfrm_state *x) { - struct esp_data *esp = x->data; + struct crypto_aead *aead = x->data; - if (!esp) + if (!aead) return; - crypto_free_aead(esp->aead); - kfree(esp); + crypto_free_aead(aead); } static int esp_init_aead(struct xfrm_state *x) { - struct esp_data *esp = x->data; struct crypto_aead *aead; int err; @@ -475,7 +466,7 @@ static int esp_init_aead(struct xfrm_state *x) if (IS_ERR(aead)) goto error; - esp->aead = aead; + x->data = aead; err = crypto_aead_setkey(aead, x->aead->alg_key, (x->aead->alg_key_len + 7) / 8); @@ -492,7 +483,6 @@ error: static int esp_init_authenc(struct xfrm_state *x) { - struct esp_data *esp = x->data; struct crypto_aead *aead; struct crypto_authenc_key_param *param; struct rtattr *rta; @@ -527,7 +517,7 @@ static int esp_init_authenc(struct xfrm_state *x) if (IS_ERR(aead)) goto error; - esp->aead = aead; + x->data = aead; keylen = (x->aalg ? (x->aalg->alg_key_len + 7) / 8 : 0) + (x->ealg->alg_key_len + 7) / 8 + RTA_SPACE(sizeof(*param)); @@ -582,7 +572,6 @@ error: static int esp6_init_state(struct xfrm_state *x) { - struct esp_data *esp; struct crypto_aead *aead; u32 align; int err; @@ -590,11 +579,7 @@ static int esp6_init_state(struct xfrm_state *x) if (x->encap) return -EINVAL; - esp = kzalloc(sizeof(*esp), GFP_KERNEL); - if (esp == NULL) - return -ENOMEM; - - x->data = esp; + x->data = NULL; if (x->aead) err = esp_init_aead(x); @@ -604,9 +589,7 @@ static int esp6_init_state(struct xfrm_state *x) if (err) goto error; - aead = esp->aead; - - esp->padlen = 0; + aead = x->data; x->props.header_len = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); @@ -626,9 +609,7 @@ static int esp6_init_state(struct xfrm_state *x) } align = ALIGN(crypto_aead_blocksize(aead), 4); - if (esp->padlen) - align = max_t(u32, align, esp->padlen); - x->props.trailer_len = align + 1 + crypto_aead_authsize(esp->aead); + x->props.trailer_len = align + 1 + crypto_aead_authsize(aead); error: return err; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 07a7d65..8d67900 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -162,12 +162,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) off += optlen; len -= optlen; } - /* This case will not be caught by above check since its padding - * length is smaller than 7: - * 1 byte NH + 1 byte Length + 6 bytes Padding - */ - if ((padlen == 6) && ((off - skb_network_header_len(skb)) == 8)) - goto bad; if (len == 0) return true; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index c5e83fa..140748d 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -115,7 +115,7 @@ EXPORT_SYMBOL(ipv6_skip_exthdr); int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) { const unsigned char *nh = skb_network_header(skb); - int packet_len = skb->tail - skb->network_header; + int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); struct ipv6_opt_hdr *hdr; int len; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2e1a432..e275916 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -55,26 +55,33 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, struct fib6_table *table; struct net *net = rule->fr_net; pol_lookup_t lookup = arg->lookup_ptr; + int err = 0; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: + err = -ENETUNREACH; rt = net->ipv6.ip6_null_entry; goto discard_pkt; default: case FR_ACT_BLACKHOLE: + err = -EINVAL; rt = net->ipv6.ip6_blk_hole_entry; goto discard_pkt; case FR_ACT_PROHIBIT: + err = -EACCES; rt = net->ipv6.ip6_prohibit_entry; goto discard_pkt; } table = fib6_get_table(net, rule->table); - if (table) - rt = lookup(net, table, flp6, flags); + if (!table) { + err = -EAGAIN; + goto out; + } + rt = lookup(net, table, flp6, flags); if (rt != net->ipv6.ip6_null_entry) { struct fib6_rule *r = (struct fib6_rule *)rule; @@ -101,6 +108,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, } again: ip6_rt_put(rt); + err = -EAGAIN; rt = NULL; goto out; @@ -108,9 +116,31 @@ discard_pkt: dst_hold(&rt->dst); out: arg->result = rt; - return rt == NULL ? -EAGAIN : 0; + return err; } +static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +{ + struct rt6_info *rt = (struct rt6_info *) arg->result; + struct net_device *dev = rt->rt6i_idev->dev; + /* do not accept result if the route does + * not meet the required prefix length + */ + if (rt->rt6i_dst.plen <= rule->suppress_prefixlen) + goto suppress_route; + + /* do not accept result if the route uses a device + * belonging to a forbidden interface group + */ + if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) + goto suppress_route; + + return false; + +suppress_route: + ip6_rt_put(rt); + return true; +} static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { @@ -244,6 +274,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .addr_size = sizeof(struct in6_addr), .action = fib6_rule_action, .match = fib6_rule_match, + .suppress = fib6_rule_suppress, .configure = fib6_rule_configure, .compare = fib6_rule_compare, .fill = fib6_rule_fill, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index b4ff0a4..eef8d94 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -57,6 +57,7 @@ #include <net/ipv6.h> #include <net/ip6_checksum.h> +#include <net/ping.h> #include <net/protocol.h> #include <net/raw.h> #include <net/rawv6.h> @@ -84,12 +85,18 @@ static inline struct sock *icmpv6_sk(struct net *net) static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { + /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */ + struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset); struct net *net = dev_net(skb->dev); if (type == ICMPV6_PKT_TOOBIG) ip6_update_pmtu(skb, net, info, 0, 0); else if (type == NDISC_REDIRECT) - ip6_redirect(skb, net, 0, 0); + ip6_redirect(skb, net, skb->dev->ifindex, 0); + + if (!(type & ICMPV6_INFOMSG_MASK)) + if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST) + ping_err(skb, offset, info); } static int icmpv6_rcv(struct sk_buff *skb); @@ -224,7 +231,8 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset) return (*op & 0xC0) == 0x80; } -static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len) +int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, + struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; @@ -307,8 +315,8 @@ static void mip6_addr_swap(struct sk_buff *skb) static inline void mip6_addr_swap(struct sk_buff *skb) {} #endif -static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, - struct sock *sk, struct flowi6 *fl6) +struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, + struct sock *sk, struct flowi6 *fl6) { struct dst_entry *dst, *dst2; struct flowi6 fl2; @@ -391,7 +399,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) int err = 0; if ((u8 *)hdr < skb->head || - (skb->network_header + sizeof(*hdr)) > skb->tail) + (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; /* @@ -697,7 +705,8 @@ static int icmpv6_rcv(struct sk_buff *skb) skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, 0)); if (__skb_checksum_complete(skb)) { - LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%pI6 > %pI6]\n", + LIMIT_NETDEBUG(KERN_DEBUG + "ICMPv6 checksum failed [%pI6c > %pI6c]\n", saddr, daddr); goto csum_error; } @@ -718,7 +727,7 @@ static int icmpv6_rcv(struct sk_buff *skb) break; case ICMPV6_ECHO_REPLY: - /* we couldn't care less */ + ping_rcv(skb); break; case ICMPV6_PKT_TOOBIG: @@ -931,6 +940,14 @@ static const struct icmp6_err { .err = ECONNREFUSED, .fatal = 1, }, + { /* POLICY_FAIL */ + .err = EACCES, + .fatal = 1, + }, + { /* REJECT_ROUTE */ + .err = EACCES, + .fatal = 1, + }, }; int icmpv6_err_convert(u8 type, u8 code, int *err) @@ -942,7 +959,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err) switch (type) { case ICMPV6_DEST_UNREACH: fatal = 1; - if (code <= ICMPV6_PORT_UNREACH) { + if (code < ARRAY_SIZE(tab_unreach)) { *err = tab_unreach[code].err; fatal = tab_unreach[code].fatal; } @@ -967,7 +984,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err) EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL -ctl_table ipv6_icmp_table_template[] = { +struct ctl_table ipv6_icmp_table_template[] = { { .procname = "ratelimit", .data = &init_net.ipv6.sysctl.icmpv6_time, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index e4311cb..77bb8af 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -70,20 +70,20 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, const struct request_sock *req) { - struct inet6_request_sock *treq = inet6_rsk(req); + struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = IPPROTO_TCP; - fl6->daddr = treq->rmt_addr; + fl6->daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(fl6, np->opt, &final); - fl6->saddr = treq->loc_addr; - fl6->flowi6_oif = treq->iif; + fl6->saddr = ireq->ir_v6_loc_addr; + fl6->flowi6_oif = ireq->ir_iif; fl6->flowi6_mark = sk->sk_mark; - fl6->fl6_dport = inet_rsk(req)->rmt_port; - fl6->fl6_sport = inet_rsk(req)->loc_port; + fl6->fl6_dport = ireq->ir_rmt_port; + fl6->fl6_sport = htons(ireq->ir_num); security_req_classify_flow(req, flowi6_to_flowi(fl6)); dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); @@ -129,13 +129,13 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk, lopt->nr_table_entries)]; (req = *prev) != NULL; prev = &req->dl_next) { - const struct inet6_request_sock *treq = inet6_rsk(req); + const struct inet_request_sock *ireq = inet_rsk(req); - if (inet_rsk(req)->rmt_port == rport && + if (ireq->ir_rmt_port == rport && req->rsk_ops->family == AF_INET6 && - ipv6_addr_equal(&treq->rmt_addr, raddr) && - ipv6_addr_equal(&treq->loc_addr, laddr) && - (!treq->iif || treq->iif == iif)) { + ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) && + ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) && + (!ireq->ir_iif || ireq->ir_iif == iif)) { WARN_ON(req->sk != NULL); *prevp = prev; return req; @@ -153,8 +153,8 @@ void inet6_csk_reqsk_queue_hash_add(struct sock *sk, { struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - const u32 h = inet6_synq_hash(&inet6_rsk(req)->rmt_addr, - inet_rsk(req)->rmt_port, + const u32 h = inet6_synq_hash(&inet_rsk(req)->ir_v6_rmt_addr, + inet_rsk(req)->ir_rmt_port, lopt->hash_rnd, lopt->nr_table_entries); reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout); @@ -165,11 +165,10 @@ EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add); void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) { - struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; sin6->sin6_family = AF_INET6; - sin6->sin6_addr = np->daddr; + sin6->sin6_addr = sk->sk_v6_daddr; sin6->sin6_port = inet_sk(sk)->inet_dport; /* We do not store received flowlabel for TCP */ sin6->sin6_flowinfo = 0; @@ -203,7 +202,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = sk->sk_protocol; - fl6->daddr = np->daddr; + fl6->daddr = sk->sk_v6_daddr; fl6->saddr = np->saddr; fl6->flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl6->flowlabel); @@ -245,7 +244,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) skb_dst_set_noref(skb, dst); /* Restore final destination back after routing done */ - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); rcu_read_unlock(); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 32b4a16..262e13c 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -23,6 +23,39 @@ #include <net/secure_seq.h> #include <net/ip.h> +static unsigned int inet6_ehashfn(struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) +{ + static u32 inet6_ehash_secret __read_mostly; + static u32 ipv6_hash_secret __read_mostly; + + u32 lhash, fhash; + + net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); + net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); + + lhash = (__force u32)laddr->s6_addr32[3]; + fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret); + + return __inet6_ehashfn(lhash, lport, fhash, fport, + inet6_ehash_secret + net_hash_mix(net)); +} + +static int inet6_sk_ehashfn(const struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr; + const struct in6_addr *faddr = &sk->sk_v6_daddr; + const __u16 lport = inet->inet_num; + const __be16 fport = inet->inet_dport; + struct net *net = sock_net(sk); + + return inet6_ehashfn(net, laddr, lport, faddr, fport); +} + int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; @@ -89,43 +122,22 @@ begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) continue; - if (likely(INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { - if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) - goto begintw; - if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, - ports, dif))) { - sock_put(sk); - goto begin; - } - goto out; - } - } - if (get_nulls_value(node) != slot) - goto begin; - -begintw: - /* Must check for a TIME_WAIT'er before going to listener hash. */ - sk_nulls_for_each_rcu(sk, node, &head->twchain) { - if (sk->sk_hash != hash) + if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif)) continue; - if (likely(INET6_TW_MATCH(sk, net, saddr, daddr, - ports, dif))) { - if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) { - sk = NULL; - goto out; - } - if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr, - ports, dif))) { - sock_put(sk); - goto begintw; - } + if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) goto out; + + if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { + sock_gen_put(sk); + goto begin; } + goto found; } if (get_nulls_value(node) != slot) - goto begintw; - sk = NULL; + goto begin; out: + sk = NULL; +found: rcu_read_unlock(); return sk; } @@ -140,11 +152,10 @@ static inline int compute_score(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && sk->sk_family == PF_INET6) { - const struct ipv6_pinfo *np = inet6_sk(sk); score = 1; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; score++; } @@ -236,9 +247,8 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - const struct in6_addr *daddr = &np->rcv_saddr; - const struct in6_addr *saddr = &np->daddr; + const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; + const struct in6_addr *saddr = &sk->sk_v6_daddr; const int dif = sk->sk_bound_dev_if; const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct net *net = sock_net(sk); @@ -248,38 +258,28 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_nulls_node *node; - struct inet_timewait_sock *tw; + struct inet_timewait_sock *tw = NULL; int twrefcnt = 0; spin_lock(lock); - /* Check TIME-WAIT sockets first. */ - sk_nulls_for_each(sk2, node, &head->twchain) { - if (sk2->sk_hash != hash) - continue; - - if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr, - ports, dif))) { - tw = inet_twsk(sk2); - if (twsk_unique(sk, sk2, twp)) - goto unique; - else - goto not_unique; - } - } - tw = NULL; - - /* And established part... */ sk_nulls_for_each(sk2, node, &head->chain) { if (sk2->sk_hash != hash) continue; - if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) + + if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) { + if (sk2->sk_state == TCP_TIME_WAIT) { + tw = inet_twsk(sk2); + if (twsk_unique(sk, sk2, twp)) + break; + } goto not_unique; + } } -unique: /* Must record num and sport now. Otherwise we will see - * in hash table socket with a funny identity. */ + * in hash table socket with a funny identity. + */ inet->inet_num = lport; inet->inet_sport = htons(lport); sk->sk_hash = hash; @@ -312,9 +312,9 @@ not_unique: static inline u32 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32, - np->daddr.s6_addr32, + + return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, inet->inet_dport); } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 192dd1a..5550a81 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -425,8 +425,8 @@ out: * node. */ -static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, - int addrlen, int plen, +static struct fib6_node *fib6_add_1(struct fib6_node *root, + struct in6_addr *addr, int plen, int offset, int allow_create, int replace_required) { @@ -543,7 +543,7 @@ insert_above: but if it is >= plen, the value is ignored in any case. */ - bit = __ipv6_addr_diff(addr, &key->addr, addrlen); + bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] @@ -632,6 +632,12 @@ insert_above: return ln; } +static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) +{ + return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + RTF_GATEWAY; +} + /* * Insert routing information in a node. */ @@ -646,6 +652,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); ins = &fn->leaf; @@ -691,9 +698,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, * To avoid long list, we only had siblings if the * route have a gateway. */ - if (rt->rt6i_flags & RTF_GATEWAY && - !(rt->rt6i_flags & RTF_EXPIRES) && - !(iter->rt6i_flags & RTF_EXPIRES)) + if (rt_can_ecmp && + rt6_qualify_for_ecmp(iter)) rt->rt6i_nsiblings++; } @@ -715,7 +721,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, /* Find the first route that have the same metric */ sibling = fn->leaf; while (sibling) { - if (sibling->rt6i_metric == rt->rt6i_metric) { + if (sibling->rt6i_metric == rt->rt6i_metric && + rt6_qualify_for_ecmp(sibling)) { list_add_tail(&rt->rt6i_siblings, &sibling->rt6i_siblings); break; @@ -815,12 +822,12 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), - rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), - allow_create, replace_required); - + fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + offsetof(struct rt6_info, rt6i_dst), allow_create, + replace_required); if (IS_ERR(fn)) { err = PTR_ERR(fn); + fn = NULL; goto out; } @@ -856,7 +863,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) /* Now add the first leaf node to new subtree */ sn = fib6_add_1(sfn, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, + rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required); @@ -875,7 +882,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) fn->subtree = sfn; } else { sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, + rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required); @@ -986,14 +993,22 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) - fn = fib6_lookup_1(fn->subtree, args + 1); + if (fn->subtree) { + struct fib6_node *sfn; + sfn = fib6_lookup_1(fn->subtree, + args + 1); + if (!sfn) + goto backtrack; + fn = sfn; + } #endif - if (!fn || fn->fn_flags & RTN_RTINFO) + if (fn->fn_flags & RTN_RTINFO) return fn; } } - +#ifdef CONFIG_IPV6_SUBTREES +backtrack: +#endif if (fn->fn_flags & RTN_ROOT) break; @@ -1514,25 +1529,6 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, fib6_walk(&c.w); } -void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg), - int prune, void *arg) -{ - struct fib6_table *table; - struct hlist_head *head; - unsigned int h; - - rcu_read_lock(); - for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { - head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, head, tb6_hlist) { - read_lock_bh(&table->tb6_lock); - fib6_clean_tree(net, &table->tb6_root, - func, prune, arg); - read_unlock_bh(&table->tb6_lock); - } - } - rcu_read_unlock(); -} void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), int prune, void *arg) { @@ -1625,27 +1621,28 @@ static int fib6_age(struct rt6_info *rt, void *arg) static DEFINE_SPINLOCK(fib6_gc_lock); -void fib6_run_gc(unsigned long expires, struct net *net) +void fib6_run_gc(unsigned long expires, struct net *net, bool force) { - if (expires != ~0UL) { + unsigned long now; + + if (force) { spin_lock_bh(&fib6_gc_lock); - gc_args.timeout = expires ? (int)expires : - net->ipv6.sysctl.ip6_rt_gc_interval; - } else { - if (!spin_trylock_bh(&fib6_gc_lock)) { - mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); - return; - } - gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval; + } else if (!spin_trylock_bh(&fib6_gc_lock)) { + mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); + return; } + gc_args.timeout = expires ? (int)expires : + net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = icmp6_dst_gc(); fib6_clean_all(net, fib6_age, 0, NULL); + now = jiffies; + net->ipv6.ip6_rt_last_gc = now; if (gc_args.more) mod_timer(&net->ipv6.ip6_fib_timer, - round_jiffies(jiffies + round_jiffies(now + net->ipv6.sysctl.ip6_rt_gc_interval)); else del_timer(&net->ipv6.ip6_fib_timer); @@ -1654,7 +1651,7 @@ void fib6_run_gc(unsigned long expires, struct net *net) static void fib6_gc_timer_cb(unsigned long arg) { - fib6_run_gc(0, (struct net *)arg); + fib6_run_gc(0, (struct net *)arg, true); } static int __net_init fib6_net_init(struct net *net) @@ -1766,3 +1763,189 @@ void fib6_gc_cleanup(void) unregister_pernet_subsys(&fib6_net_ops); kmem_cache_destroy(fib6_node_kmem); } + +#ifdef CONFIG_PROC_FS + +struct ipv6_route_iter { + struct seq_net_private p; + struct fib6_walker_t w; + loff_t skip; + struct fib6_table *tbl; + __u32 sernum; +}; + +static int ipv6_route_seq_show(struct seq_file *seq, void *v) +{ + struct rt6_info *rt = v; + struct ipv6_route_iter *iter = seq->private; + + seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); + +#ifdef CONFIG_IPV6_SUBTREES + seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); +#else + seq_puts(seq, "00000000000000000000000000000000 00 "); +#endif + if (rt->rt6i_flags & RTF_GATEWAY) + seq_printf(seq, "%pi6", &rt->rt6i_gateway); + else + seq_puts(seq, "00000000000000000000000000000000"); + + seq_printf(seq, " %08x %08x %08x %08x %8s\n", + rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), + rt->dst.__use, rt->rt6i_flags, + rt->dst.dev ? rt->dst.dev->name : ""); + iter->w.leaf = NULL; + return 0; +} + +static int ipv6_route_yield(struct fib6_walker_t *w) +{ + struct ipv6_route_iter *iter = w->args; + + if (!iter->skip) + return 1; + + do { + iter->w.leaf = iter->w.leaf->dst.rt6_next; + iter->skip--; + if (!iter->skip && iter->w.leaf) + return 1; + } while (iter->w.leaf); + + return 0; +} + +static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter) +{ + memset(&iter->w, 0, sizeof(iter->w)); + iter->w.func = ipv6_route_yield; + iter->w.root = &iter->tbl->tb6_root; + iter->w.state = FWS_INIT; + iter->w.node = iter->w.root; + iter->w.args = iter; + iter->sernum = iter->w.root->fn_sernum; + INIT_LIST_HEAD(&iter->w.lh); + fib6_walker_link(&iter->w); +} + +static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, + struct net *net) +{ + unsigned int h; + struct hlist_node *node; + + if (tbl) { + h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; + node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + } else { + h = 0; + node = NULL; + } + + while (!node && h < FIB6_TABLE_HASHSZ) { + node = rcu_dereference_bh( + hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); + } + return hlist_entry_safe(node, struct fib6_table, tb6_hlist); +} + +static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) +{ + if (iter->sernum != iter->w.root->fn_sernum) { + iter->sernum = iter->w.root->fn_sernum; + iter->w.state = FWS_INIT; + iter->w.node = iter->w.root; + WARN_ON(iter->w.skip); + iter->w.skip = iter->w.count; + } +} + +static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + int r; + struct rt6_info *n; + struct net *net = seq_file_net(seq); + struct ipv6_route_iter *iter = seq->private; + + if (!v) + goto iter_table; + + n = ((struct rt6_info *)v)->dst.rt6_next; + if (n) { + ++*pos; + return n; + } + +iter_table: + ipv6_route_check_sernum(iter); + read_lock(&iter->tbl->tb6_lock); + r = fib6_walk_continue(&iter->w); + read_unlock(&iter->tbl->tb6_lock); + if (r > 0) { + if (v) + ++*pos; + return iter->w.leaf; + } else if (r < 0) { + fib6_walker_unlink(&iter->w); + return NULL; + } + fib6_walker_unlink(&iter->w); + + iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); + if (!iter->tbl) + return NULL; + + ipv6_route_seq_setup_walk(iter); + goto iter_table; +} + +static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU_BH) +{ + struct net *net = seq_file_net(seq); + struct ipv6_route_iter *iter = seq->private; + + rcu_read_lock_bh(); + iter->tbl = ipv6_route_seq_next_table(NULL, net); + iter->skip = *pos; + + if (iter->tbl) { + ipv6_route_seq_setup_walk(iter); + return ipv6_route_seq_next(seq, NULL, pos); + } else { + return NULL; + } +} + +static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) +{ + struct fib6_walker_t *w = &iter->w; + return w->node && !(w->state == FWS_U && w->node == w->root); +} + +static void ipv6_route_seq_stop(struct seq_file *seq, void *v) + __releases(RCU_BH) +{ + struct ipv6_route_iter *iter = seq->private; + + if (ipv6_route_iter_active(iter)) + fib6_walker_unlink(&iter->w); + + rcu_read_unlock_bh(); +} + +static const struct seq_operations ipv6_route_seq_ops = { + .start = ipv6_route_seq_start, + .next = ipv6_route_seq_next, + .stop = ipv6_route_seq_stop, + .show = ipv6_route_seq_show +}; + +int ipv6_route_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ipv6_route_seq_ops, + sizeof(struct ipv6_route_iter)); +} + +#endif /* CONFIG_PROC_FS */ diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 46e8843..e7fb710 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -41,7 +41,7 @@ #define FL_MIN_LINGER 6 /* Minimal linger. It is set to 6sec specified in old IPv6 RFC. Well, it was reasonable value. */ -#define FL_MAX_LINGER 60 /* Maximal linger timeout */ +#define FL_MAX_LINGER 150 /* Maximal linger timeout */ /* FL hash table */ @@ -345,6 +345,8 @@ static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned lo expires = check_linger(expires); if (!expires) return -EPERM; + + spin_lock_bh(&ip6_fl_lock); fl->lastuse = jiffies; if (time_before(fl->linger, linger)) fl->linger = linger; @@ -352,6 +354,8 @@ static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned lo expires = fl->linger; if (time_before(fl->expires, fl->lastuse + expires)) fl->expires = fl->lastuse + expires; + spin_unlock_bh(&ip6_fl_lock); + return 0; } @@ -453,8 +457,10 @@ static int mem_check(struct sock *sk) if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; + rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) count++; + rcu_read_unlock_bh(); if (room <= 0 || ((count >= FL_MAX_PER_SOCK || @@ -465,34 +471,6 @@ static int mem_check(struct sock *sk) return 0; } -static bool ipv6_hdr_cmp(struct ipv6_opt_hdr *h1, struct ipv6_opt_hdr *h2) -{ - if (h1 == h2) - return false; - if (h1 == NULL || h2 == NULL) - return true; - if (h1->hdrlen != h2->hdrlen) - return true; - return memcmp(h1+1, h2+1, ((h1->hdrlen+1)<<3) - sizeof(*h1)); -} - -static bool ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2) -{ - if (o1 == o2) - return false; - if (o1 == NULL || o2 == NULL) - return true; - if (o1->opt_nflen != o2->opt_nflen) - return true; - if (ipv6_hdr_cmp(o1->hopopt, o2->hopopt)) - return true; - if (ipv6_hdr_cmp(o1->dst0opt, o2->dst0opt)) - return true; - if (ipv6_hdr_cmp((struct ipv6_opt_hdr *)o1->srcrt, (struct ipv6_opt_hdr *)o2->srcrt)) - return true; - return false; -} - static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, struct ip6_flowlabel *fl) { @@ -503,6 +481,32 @@ static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, spin_unlock_bh(&ip6_sk_fl_lock); } +int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_fl_socklist *sfl; + + rcu_read_lock_bh(); + + for_each_sk_fl_rcu(np, sfl) { + if (sfl->fl->label == (np->flow_label & IPV6_FLOWLABEL_MASK)) { + spin_lock_bh(&ip6_fl_lock); + freq->flr_label = sfl->fl->label; + freq->flr_dst = sfl->fl->dst; + freq->flr_share = sfl->fl->share; + freq->flr_expires = (sfl->fl->expires - jiffies) / HZ; + freq->flr_linger = sfl->fl->linger / HZ; + + spin_unlock_bh(&ip6_fl_lock); + rcu_read_unlock_bh(); + return 0; + } + } + rcu_read_unlock_bh(); + + return -ENOENT; +} + int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) { int uninitialized_var(err); @@ -603,11 +607,6 @@ recheck: uid_eq(fl1->owner.uid, fl->owner.uid))) goto release; - err = -EINVAL; - if (!ipv6_addr_equal(&fl1->dst, &fl->dst) || - ipv6_opt_cmp(fl1->opt, fl->opt)) - goto release; - err = -ENOMEM; if (sfl1 == NULL) goto release; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index ecd6073..8acb286 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -335,6 +335,7 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, dev->rtnl_link_ops = &ip6gre_link_ops; nt->dev = dev; + nt->net = dev_net(dev); ip6gre_tnl_link_config(nt, 1); if (register_netdevice(dev) < 0) @@ -508,8 +509,6 @@ static int ip6gre_rcv(struct sk_buff *skb) goto drop; } - secpath_reset(skb); - skb->protocol = gre_proto; /* WCCP version 1 and 2 protocol decoding. * - Change protocol to IP @@ -524,7 +523,6 @@ static int ip6gre_rcv(struct sk_buff *skb) skb->mac_header = skb->network_header; __pskb_pull(skb, offset); skb_postpull_rcsum(skb, skb_transport_header(skb), offset); - skb->pkt_type = PACKET_HOST; if (((flags&GRE_CSUM) && csum) || (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) { @@ -556,7 +554,7 @@ static int ip6gre_rcv(struct sk_buff *skb) skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } - __skb_tunnel_rx(skb, tunnel->dev); + __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); skb_reset_network_header(skb); @@ -620,7 +618,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, struct ip6_tnl *tunnel = netdev_priv(dev); struct net_device *tdev; /* Device to other host */ struct ipv6hdr *ipv6h; /* Our new IP header */ - unsigned int max_headroom; /* The extra header space needed */ + unsigned int max_headroom = 0; /* The extra header space needed */ int gre_hlen; struct ipv6_tel_txoption opt; int mtu; @@ -693,7 +691,9 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, tunnel->err_count = 0; } - max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); + + max_headroom += LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { @@ -709,8 +709,6 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb = new_skb; } - skb_dst_drop(skb); - if (fl6->flowi6_mark) { skb_dst_set(skb, dst); ndst = NULL; @@ -724,6 +722,11 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); } + if (likely(!skb->encapsulation)) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + skb_push(skb, gre_hlen); skb_reset_network_header(skb); skb_set_transport_header(skb, sizeof(*ipv6h)); @@ -973,6 +976,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) if (t->parms.o_flags&GRE_SEQ) addend += 4; } + t->hlen = addend; if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & @@ -999,8 +1003,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) } ip6_rt_put(rt); } - - t->hlen = addend; } static int ip6gre_tnl_change(struct ip6_tnl *t, @@ -1170,9 +1172,8 @@ done: static int ip6gre_tunnel_change_mtu(struct net_device *dev, int new_mtu) { - struct ip6_tnl *tunnel = netdev_priv(dev); if (new_mtu < 68 || - new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen) + new_mtu > 0xFFF8 - dev->hard_header_len) return -EINVAL; dev->mtu = new_mtu; return 0; @@ -1251,10 +1252,12 @@ static void ip6gre_tunnel_setup(struct net_device *dev) static int ip6gre_tunnel_init(struct net_device *dev) { struct ip6_tnl *tunnel; + int i; tunnel = netdev_priv(dev); tunnel->dev = dev; + tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr)); @@ -1267,6 +1270,13 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + for_each_possible_cpu(i) { + struct pcpu_tstats *ip6gre_tunnel_stats; + ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i); + u64_stats_init(&ip6gre_tunnel_stats->syncp); + } + + return 0; } @@ -1275,6 +1285,7 @@ static void ip6gre_fb_tunnel_init(struct net_device *dev) struct ip6_tnl *tunnel = netdev_priv(dev); tunnel->dev = dev; + tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); tunnel->hlen = sizeof(struct ipv6hdr) + 4; @@ -1446,10 +1457,12 @@ static void ip6gre_netlink_parms(struct nlattr *data[], static int ip6gre_tap_init(struct net_device *dev) { struct ip6_tnl *tunnel; + int i; tunnel = netdev_priv(dev); tunnel->dev = dev; + tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); ip6gre_tnl_link_config(tunnel, 1); @@ -1458,6 +1471,12 @@ static int ip6gre_tap_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + for_each_possible_cpu(i) { + struct pcpu_tstats *ip6gre_tap_stats; + ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i); + u64_stats_init(&ip6gre_tap_stats->syncp); + } + return 0; } @@ -1501,6 +1520,7 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev, eth_hw_addr_random(dev); nt->dev = dev; + nt->net = dev_net(dev); ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); /* Can use a lockless transmit, unless we generate output sequences */ diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 2bab2aa..302d6fb 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -44,7 +44,7 @@ #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/xfrm.h> - +#include <net/inet_ecn.h> int ip6_rcv_finish(struct sk_buff *skb) @@ -109,6 +109,10 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (hdr->version != 6) goto err; + IP6_ADD_STATS_BH(dev_net(dev), idev, + IPSTATS_MIB_NOECTPKTS + + (ipv6_get_dsfield(hdr) & INET_ECN_MASK), + max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs)); /* * RFC4291 2.5.3 * A packet received on an interface with a destination address diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 71b766e..4b85169 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -66,7 +66,6 @@ static int ipv6_gso_send_check(struct sk_buff *skb) __skb_pull(skb, sizeof(*ipv6h)); err = -EPROTONOSUPPORT; - rcu_read_lock(); ops = rcu_dereference(inet6_offloads[ ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); @@ -74,7 +73,6 @@ static int ipv6_gso_send_check(struct sk_buff *skb) skb_reset_transport_header(skb); err = ops->callbacks.gso_send_check(skb); } - rcu_read_unlock(); out: return err; @@ -91,44 +89,59 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, unsigned int unfrag_ip6hlen; u8 *prevhdr; int offset = 0; + bool tunnel; + int nhoff; if (unlikely(skb_shinfo(skb)->gso_type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_GRE | + SKB_GSO_IPIP | + SKB_GSO_SIT | SKB_GSO_UDP_TUNNEL | + SKB_GSO_MPLS | SKB_GSO_TCPV6 | 0))) goto out; + skb_reset_network_header(skb); + nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; + tunnel = SKB_GSO_CB(skb)->encap_level > 0; + if (tunnel) + features = skb->dev->hw_enc_features & netif_skb_features(skb); + SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h); + ipv6h = ipv6_hdr(skb); __skb_pull(skb, sizeof(*ipv6h)); segs = ERR_PTR(-EPROTONOSUPPORT); proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); - rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); segs = ops->callbacks.gso_segment(skb, features); } - rcu_read_unlock(); if (IS_ERR(segs)) goto out; for (skb = segs; skb; skb = skb->next) { - ipv6h = ipv6_hdr(skb); - ipv6h->payload_len = htons(skb->len - skb->mac_len - - sizeof(*ipv6h)); - if (proto == IPPROTO_UDP) { + ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); + ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h)); + if (tunnel) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + skb->network_header = (u8 *)ipv6h - skb->head; + + if (!tunnel && proto == IPPROTO_UDP) { unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - fptr = (struct frag_hdr *)(skb_network_header(skb) + - unfrag_ip6hlen); + fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); fptr->frag_off = htons(offset); if (skb->next != NULL) fptr->frag_off |= htons(IP6_MF); @@ -264,6 +277,13 @@ static struct packet_offload ipv6_packet_offload __read_mostly = { }, }; +static const struct net_offload sit_offload = { + .callbacks = { + .gso_send_check = ipv6_gso_send_check, + .gso_segment = ipv6_gso_segment, + }, +}; + static int __init ipv6_offload_init(void) { @@ -275,6 +295,9 @@ static int __init ipv6_offload_init(void) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); dev_add_offload(&ipv6_packet_offload); + + inet_add_offload(&sit_offload, IPPROTO_IPV6); + return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 52a53fa..584a3a9 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -56,31 +56,6 @@ #include <net/checksum.h> #include <linux/mroute6.h> -int __ip6_local_out(struct sk_buff *skb) -{ - int len; - - len = skb->len - sizeof(struct ipv6hdr); - if (len > IPV6_MAXPLEN) - len = 0; - ipv6_hdr(skb)->payload_len = htons(len); - - return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, - skb_dst(skb)->dev, dst_output); -} - -int ip6_local_out(struct sk_buff *skb) -{ - int err; - - err = __ip6_local_out(skb); - if (likely(err == 1)) - err = dst_output(skb); - - return err; -} -EXPORT_SYMBOL_GPL(ip6_local_out); - static int ip6_finish_output2(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -130,7 +105,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + nexthop = rt6_nexthop((struct rt6_info *)dst); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -141,8 +116,8 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_unlock_bh(); - IP6_INC_STATS_BH(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } @@ -150,7 +125,8 @@ static int ip6_finish_output2(struct sk_buff *skb) static int ip6_finish_output(struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb))) + dst_allfrag(skb_dst(skb)) || + (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(skb, ip6_finish_output2); else return ip6_finish_output2(skb); @@ -238,6 +214,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hdr->saddr = fl6->saddr; hdr->daddr = *first_hop; + skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -899,7 +876,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); @@ -934,7 +911,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, out_err_release: if (err == -ENETUNREACH) - IP6_INC_STATS_BH(net, NULL, IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES); dst_release(*dst); *dst = NULL; return err; @@ -1033,6 +1010,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, { struct sk_buff *skb; + struct frag_hdr fhdr; int err; /* There is support for UDP large send offload by network @@ -1058,33 +1036,27 @@ static inline int ip6_ufo_append_data(struct sock *sk, /* initialize protocol header pointer */ skb->transport_header = skb->network_header + fragheaderlen; - skb->ip_summed = CHECKSUM_PARTIAL; + skb->protocol = htons(ETH_P_IPV6); skb->csum = 0; - } - err = skb_append_datato_frags(sk,skb, getfrag, from, - (length - transhdrlen)); - if (!err) { - struct frag_hdr fhdr; - - /* Specify the length of each IPv6 datagram fragment. - * It has to be a multiple of 8. - */ - skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - - sizeof(struct frag_hdr)) & ~7; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(&fhdr, rt); - skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); - - return 0; + } else if (skb_is_gso(skb)) { + goto append; } - /* There is not enough support do UPD LSO, - * so follow normal path - */ - kfree_skb(skb); - return err; + skb->ip_summed = CHECKSUM_PARTIAL; + /* Specify the length of each IPv6 datagram fragment. + * It has to be a multiple of 8. + */ + skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - + sizeof(struct frag_hdr)) & ~7; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + ipv6_select_ident(&fhdr, rt); + skb_shinfo(skb)->ip6_frag_id = fhdr.identification; + +append: + return skb_append_datato_frags(sk, skb, getfrag, from, + (length - transhdrlen)); } static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, @@ -1099,11 +1071,12 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } -static void ip6_append_data_mtu(int *mtu, +static void ip6_append_data_mtu(unsigned int *mtu, int *maxfraglen, unsigned int fragheaderlen, struct sk_buff *skb, - struct rt6_info *rt) + struct rt6_info *rt, + bool pmtuprobe) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (skb == NULL) { @@ -1115,7 +1088,9 @@ static void ip6_append_data_mtu(int *mtu, * this fragment is not first, the headers * space is regarded as data space. */ - *mtu = dst_mtu(rt->dst.path); + *mtu = min(*mtu, pmtuprobe ? + rt->dst.dev->mtu : + dst_mtu(rt->dst.path)); } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); @@ -1132,11 +1107,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_cork *cork; struct sk_buff *skb, *skb_prev = NULL; - unsigned int maxfraglen, fragheaderlen; + unsigned int maxfraglen, fragheaderlen, mtu; int exthdrlen; int dst_exthdrlen; int hh_len; - int mtu; int copy; int err; int offset = 0; @@ -1249,27 +1223,27 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * --yoshfuji */ - cork->length += length; - if (length > mtu) { - int proto = sk->sk_protocol; - if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ - ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); - return -EMSGSIZE; - } - - if (proto == IPPROTO_UDP && - (rt->dst.dev->features & NETIF_F_UFO)) { + if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_RAW)) { + ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); + return -EMSGSIZE; + } - err = ip6_ufo_append_data(sk, getfrag, from, length, - hh_len, fragheaderlen, - transhdrlen, mtu, flags, rt); - if (err) - goto error; - return 0; - } + skb = skb_peek_tail(&sk->sk_write_queue); + cork->length += length; + if (((length > mtu) || + (skb && skb_is_gso(skb))) && + (sk->sk_protocol == IPPROTO_UDP) && + (rt->dst.dev->features & NETIF_F_UFO)) { + err = ip6_ufo_append_data(sk, getfrag, from, length, + hh_len, fragheaderlen, + transhdrlen, mtu, flags, rt); + if (err) + goto error; + return 0; } - if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) + if (!skb) goto alloc_new_skb; while (length > 0) { @@ -1293,7 +1267,9 @@ alloc_new_skb: /* update mtu and maxfraglen if necessary */ if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, - fragheaderlen, skb, rt); + fragheaderlen, skb, rt, + np->pmtudisc == + IPV6_PMTUDISC_PROBE); skb_prev = skb; @@ -1356,6 +1332,7 @@ alloc_new_skb: /* * Fill in the control structures */ + skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; /* reserve for fragmentation and ipsec header */ diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 1e55866..d606232 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -41,6 +41,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> +#include <linux/etherdevice.h> #include <asm/uaccess.h> #include <linux/atomic.h> @@ -315,6 +316,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) t = netdev_priv(dev); t->parms = *p; + t->net = dev_net(dev); err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; @@ -374,7 +376,7 @@ static void ip6_tnl_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net *net = dev_net(dev); + struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) @@ -741,7 +743,7 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; - struct net *net = dev_net(t->dev); + struct net *net = t->net; if ((p->flags & IP6_TNL_F_CAP_RCV) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && @@ -800,14 +802,12 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, rcu_read_unlock(); goto discard; } - secpath_reset(skb); skb->mac_header = skb->network_header; skb_reset_network_header(skb); skb->protocol = htons(protocol); - skb->pkt_type = PACKET_HOST; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); - __skb_tunnel_rx(skb, t->dev); + __skb_tunnel_rx(skb, t->dev, t->net); err = dscp_ecn_decapsulate(t, ipv6h, skb); if (unlikely(err)) { @@ -895,7 +895,7 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; - struct net *net = dev_net(t->dev); + struct net *net = t->net; if (p->flags & IP6_TNL_F_CAP_XMIT) { struct net_device *ldev = NULL; @@ -945,8 +945,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, int encap_limit, __u32 *pmtu) { - struct net *net = dev_net(dev); struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; struct net_device_stats *stats = &t->dev->stats; struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct ipv6_tel_txoption opt; @@ -996,6 +996,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, goto tx_err_dst_release; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + /* * Okay, now see if we can stuff it in the buffer as-is. */ @@ -1013,7 +1015,6 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, consume_skb(skb); skb = new_skb; } - skb_dst_drop(skb); if (fl6->flowi6_mark) { skb_dst_set(skb, dst); ndst = NULL; @@ -1027,6 +1028,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, init_tel_txopt(&opt, encap_limit); ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); } + + if (likely(!skb->encapsulation)) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); @@ -1202,7 +1209,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); - struct rt6_info *rt = rt6_lookup(dev_net(dev), + struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, strict); @@ -1251,7 +1258,7 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { - struct net *net = dev_net(t->dev); + struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); int err; @@ -1423,9 +1430,17 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu < IPV6_MIN_MTU) { - return -EINVAL; + struct ip6_tnl *tnl = netdev_priv(dev); + + if (tnl->parms.proto == IPPROTO_IPIP) { + if (new_mtu < 68) + return -EINVAL; + } else { + if (new_mtu < IPV6_MIN_MTU) + return -EINVAL; } + if (new_mtu > 0xFFF8 - dev->hard_header_len) + return -EINVAL; dev->mtu = new_mtu; return 0; } @@ -1463,8 +1478,10 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->mtu-=8; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + /* This perm addr will be used as interface identifier by IPv6 */ + dev->addr_assign_type = NET_ADDR_RANDOM; + eth_random_addr(dev->perm_addr); } @@ -1477,11 +1494,19 @@ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + int i; t->dev = dev; + t->net = dev_net(dev); dev->tstats = alloc_percpu(struct pcpu_tstats); if (!dev->tstats) return -ENOMEM; + + for_each_possible_cpu(i) { + struct pcpu_tstats *ip6_tnl_stats; + ip6_tnl_stats = per_cpu_ptr(dev->tstats, i); + u64_stats_init(&ip6_tnl_stats->syncp); + } return 0; } @@ -1596,9 +1621,9 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct ip6_tnl *t; + struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; - struct net *net = dev_net(dev); + struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) @@ -1617,6 +1642,15 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], return ip6_tnl_update(t, &p); } +static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + static size_t ip6_tnl_get_size(const struct net_device *dev) { return @@ -1646,9 +1680,9 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), - &parm->raddr) || - nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), &parm->laddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || @@ -1681,6 +1715,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = { .validate = ip6_tnl_validate, .newlink = ip6_tnl_newlink, .changelink = ip6_tnl_changelink, + .dellink = ip6_tnl_dellink, .get_size = ip6_tnl_get_size, .fill_info = ip6_tnl_fill_info, }; @@ -1697,22 +1732,30 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .priority = 1, }; -static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) +static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) { + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct net_device *dev, *aux; int h; struct ip6_tnl *t; LIST_HEAD(list); + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &ip6_link_ops) + unregister_netdevice_queue(dev, &list); + for (h = 0; h < HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t != NULL) { - unregister_netdevice_queue(t->dev, &list); + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, &list); t = rtnl_dereference(t->next); } } - t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, &list); unregister_netdevice_many(&list); } @@ -1732,6 +1775,11 @@ static int __net_init ip6_tnl_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; + /* FB netdevice is special: we have one, and only one per netns. + * Allowing to move it to another netns is clearly unsafe. + */ + ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) @@ -1754,10 +1802,8 @@ err_alloc_dev: static void __net_exit ip6_tnl_exit_net(struct net *net) { - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - rtnl_lock(); - ip6_tnl_destroy_tunnels(ip6n); + ip6_tnl_destroy_tunnels(net); rtnl_unlock(); } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c new file mode 100644 index 0000000..ed94ba6 --- /dev/null +++ b/net/ipv6/ip6_vti.c @@ -0,0 +1,1056 @@ +/* + * IPv6 virtual tunneling interface + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv6/ip6_tunnel.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/capability.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/sockios.h> +#include <linux/icmp.h> +#include <linux/if.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/if_tunnel.h> +#include <linux/net.h> +#include <linux/in6.h> +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include <linux/icmpv6.h> +#include <linux/init.h> +#include <linux/route.h> +#include <linux/rtnetlink.h> +#include <linux/netfilter_ipv6.h> +#include <linux/slab.h> +#include <linux/hash.h> + +#include <linux/uaccess.h> +#include <linux/atomic.h> + +#include <net/icmp.h> +#include <net/ip.h> +#include <net/ip_tunnels.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/addrconf.h> +#include <net/ip6_tunnel.h> +#include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> + +#define HASH_SIZE_SHIFT 5 +#define HASH_SIZE (1 << HASH_SIZE_SHIFT) + +static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) +{ + u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); + + return hash_32(hash, HASH_SIZE_SHIFT); +} + +static int vti6_dev_init(struct net_device *dev); +static void vti6_dev_setup(struct net_device *dev); +static struct rtnl_link_ops vti6_link_ops __read_mostly; + +static int vti6_net_id __read_mostly; +struct vti6_net { + /* the vti6 tunnel fallback device */ + struct net_device *fb_tnl_dev; + /* lists for storing tunnels in use */ + struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE]; + struct ip6_tnl __rcu *tnls_wc[1]; + struct ip6_tnl __rcu **tnls[2]; +}; + +static struct net_device_stats *vti6_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} + +#define for_each_vti6_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + +/** + * vti6_tnl_lookup - fetch tunnel matching the end-point addresses + * @net: network namespace + * @remote: the address of the tunnel exit-point + * @local: the address of the tunnel entry-point + * + * Return: + * tunnel matching given end-points if found, + * else fallback tunnel if its device is up, + * else %NULL + **/ +static struct ip6_tnl * +vti6_tnl_lookup(struct net *net, const struct in6_addr *remote, + const struct in6_addr *local) +{ + unsigned int hash = HASH(remote, local); + struct ip6_tnl *t; + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { + if (ipv6_addr_equal(local, &t->parms.laddr) && + ipv6_addr_equal(remote, &t->parms.raddr) && + (t->dev->flags & IFF_UP)) + return t; + } + t = rcu_dereference(ip6n->tnls_wc[0]); + if (t && (t->dev->flags & IFF_UP)) + return t; + + return NULL; +} + +/** + * vti6_tnl_bucket - get head of list matching given tunnel parameters + * @p: parameters containing tunnel end-points + * + * Description: + * vti6_tnl_bucket() returns the head of the list matching the + * &struct in6_addr entries laddr and raddr in @p. + * + * Return: head of IPv6 tunnel list + **/ +static struct ip6_tnl __rcu ** +vti6_tnl_bucket(struct vti6_net *ip6n, const struct __ip6_tnl_parm *p) +{ + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + unsigned int h = 0; + int prio = 0; + + if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { + prio = 1; + h = HASH(remote, local); + } + return &ip6n->tnls[prio][h]; +} + +static void +vti6_tnl_link(struct vti6_net *ip6n, struct ip6_tnl *t) +{ + struct ip6_tnl __rcu **tp = vti6_tnl_bucket(ip6n, &t->parms); + + rcu_assign_pointer(t->next , rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); +} + +static void +vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t) +{ + struct ip6_tnl __rcu **tp; + struct ip6_tnl *iter; + + for (tp = vti6_tnl_bucket(ip6n, &t->parms); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); + break; + } + } +} + +static void vti6_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + +static int vti6_tnl_create2(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + int err; + + err = vti6_dev_init(dev); + if (err < 0) + goto out; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &vti6_link_ops; + + dev_hold(dev); + vti6_tnl_link(ip6n, t); + + return 0; + +out: + return err; +} + +static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) +{ + struct net_device *dev; + struct ip6_tnl *t; + char name[IFNAMSIZ]; + int err; + + if (p->name[0]) + strlcpy(name, p->name, IFNAMSIZ); + else + sprintf(name, "ip6_vti%%d"); + + dev = alloc_netdev(sizeof(*t), name, vti6_dev_setup); + if (dev == NULL) + goto failed; + + dev_net_set(dev, net); + + t = netdev_priv(dev); + t->parms = *p; + t->net = dev_net(dev); + + err = vti6_tnl_create2(dev); + if (err < 0) + goto failed_free; + + return t; + +failed_free: + vti6_dev_free(dev); +failed: + return NULL; +} + +/** + * vti6_locate - find or create tunnel matching given parameters + * @net: network namespace + * @p: tunnel parameters + * @create: != 0 if allowed to create new tunnel if no match found + * + * Description: + * vti6_locate() first tries to locate an existing tunnel + * based on @parms. If this is unsuccessful, but @create is set a new + * tunnel device is created and registered for use. + * + * Return: + * matching tunnel or NULL + **/ +static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p, + int create) +{ + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + struct ip6_tnl __rcu **tp; + struct ip6_tnl *t; + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + for (tp = vti6_tnl_bucket(ip6n, p); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { + if (ipv6_addr_equal(local, &t->parms.laddr) && + ipv6_addr_equal(remote, &t->parms.raddr)) + return t; + } + if (!create) + return NULL; + return vti6_tnl_create(net, p); +} + +/** + * vti6_dev_uninit - tunnel device uninitializer + * @dev: the device to be destroyed + * + * Description: + * vti6_dev_uninit() removes tunnel from its list + **/ +static void vti6_dev_uninit(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + if (dev == ip6n->fb_tnl_dev) + RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); + else + vti6_tnl_unlink(ip6n, t); + ip6_tnl_dst_reset(t); + dev_put(dev); +} + +static int vti6_rcv(struct sk_buff *skb) +{ + struct ip6_tnl *t; + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + + rcu_read_lock(); + + if ((t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, + &ipv6h->daddr)) != NULL) { + struct pcpu_tstats *tstats; + + if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { + rcu_read_unlock(); + goto discard; + } + + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { + rcu_read_unlock(); + return 0; + } + + if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { + t->dev->stats.rx_dropped++; + rcu_read_unlock(); + goto discard; + } + + tstats = this_cpu_ptr(t->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + skb->mark = 0; + secpath_reset(skb); + skb->dev = t->dev; + + rcu_read_unlock(); + return 0; + } + rcu_read_unlock(); + return 1; + +discard: + kfree_skb(skb); + return 0; +} + +/** + * vti6_addr_conflict - compare packet addresses to tunnel's own + * @t: the outgoing tunnel device + * @hdr: IPv6 header from the incoming packet + * + * Description: + * Avoid trivial tunneling loop by checking that tunnel exit-point + * doesn't match source of incoming packet. + * + * Return: + * 1 if conflict, + * 0 else + **/ +static inline bool +vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) +{ + return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); +} + +/** + * vti6_xmit - send a packet + * @skb: the outgoing socket buffer + * @dev: the outgoing tunnel device + **/ +static int vti6_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct ip6_tnl *t = netdev_priv(dev); + struct net_device_stats *stats = &t->dev->stats; + struct dst_entry *dst = NULL, *ndst = NULL; + struct flowi6 fl6; + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct net_device *tdev; + int err = -1; + + if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || + !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h)) + return err; + + dst = ip6_tnl_dst_check(t); + if (!dst) { + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + + ndst = ip6_route_output(net, NULL, &fl6); + + if (ndst->error) + goto tx_err_link_failure; + ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); + ndst = NULL; + goto tx_err_link_failure; + } + dst = ndst; + } + + if (!dst->xfrm || dst->xfrm->props.mode != XFRM_MODE_TUNNEL) + goto tx_err_link_failure; + + tdev = dst->dev; + + if (tdev == dev) { + stats->collisions++; + net_warn_ratelimited("%s: Local routing loop detected!\n", + t->parms.name); + goto tx_err_dst_release; + } + + + skb_dst_drop(skb); + skb_dst_set_noref(skb, dst); + + ip6tunnel_xmit(skb, dev); + if (ndst) { + dev->mtu = dst_mtu(ndst); + ip6_tnl_dst_store(t, ndst); + } + + return 0; +tx_err_link_failure: + stats->tx_carrier_errors++; + dst_link_failure(skb); +tx_err_dst_release: + dst_release(ndst); + return err; +} + +static netdev_tx_t +vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net_device_stats *stats = &t->dev->stats; + int ret; + + switch (skb->protocol) { + case htons(ETH_P_IPV6): + ret = vti6_xmit(skb, dev); + break; + default: + goto tx_err; + } + + if (ret < 0) + goto tx_err; + + return NETDEV_TX_OK; + +tx_err: + stats->tx_errors++; + stats->tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static void vti6_link_config(struct ip6_tnl *t) +{ + struct dst_entry *dst; + struct net_device *dev = t->dev; + struct __ip6_tnl_parm *p = &t->parms; + struct flowi6 *fl6 = &t->fl.u.ip6; + + memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); + + /* Set up flowi template */ + fl6->saddr = p->laddr; + fl6->daddr = p->raddr; + fl6->flowi6_oif = p->link; + fl6->flowi6_mark = be32_to_cpu(p->i_key); + fl6->flowi6_proto = p->proto; + fl6->flowlabel = 0; + + p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | + IP6_TNL_F_CAP_PER_PACKET); + p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); + + if (p->flags & IP6_TNL_F_CAP_XMIT && p->flags & IP6_TNL_F_CAP_RCV) + dev->flags |= IFF_POINTOPOINT; + else + dev->flags &= ~IFF_POINTOPOINT; + + dev->iflink = p->link; + + if (p->flags & IP6_TNL_F_CAP_XMIT) { + + dst = ip6_route_output(dev_net(dev), NULL, fl6); + if (dst->error) + return; + + dst = xfrm_lookup(dev_net(dev), dst, flowi6_to_flowi(fl6), + NULL, 0); + if (IS_ERR(dst)) + return; + + if (dst->dev) { + dev->hard_header_len = dst->dev->hard_header_len; + + dev->mtu = dst_mtu(dst); + + if (dev->mtu < IPV6_MIN_MTU) + dev->mtu = IPV6_MIN_MTU; + } + dst_release(dst); + } +} + +/** + * vti6_tnl_change - update the tunnel parameters + * @t: tunnel to be changed + * @p: tunnel configuration parameters + * + * Description: + * vti6_tnl_change() updates the tunnel parameters + **/ +static int +vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) +{ + t->parms.laddr = p->laddr; + t->parms.raddr = p->raddr; + t->parms.link = p->link; + t->parms.i_key = p->i_key; + t->parms.o_key = p->o_key; + t->parms.proto = p->proto; + ip6_tnl_dst_reset(t); + vti6_link_config(t); + return 0; +} + +static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +{ + struct net *net = dev_net(t->dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + int err; + + vti6_tnl_unlink(ip6n, t); + synchronize_net(); + err = vti6_tnl_change(t, p); + vti6_tnl_link(ip6n, t); + netdev_state_change(t->dev); + return err; +} + +static void +vti6_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm2 *u) +{ + p->laddr = u->laddr; + p->raddr = u->raddr; + p->link = u->link; + p->i_key = u->i_key; + p->o_key = u->o_key; + p->proto = u->proto; + + memcpy(p->name, u->name, sizeof(u->name)); +} + +static void +vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) +{ + u->laddr = p->laddr; + u->raddr = p->raddr; + u->link = p->link; + u->i_key = p->i_key; + u->o_key = p->o_key; + u->proto = p->proto; + + memcpy(u->name, p->name, sizeof(u->name)); +} + +/** + * vti6_tnl_ioctl - configure vti6 tunnels from userspace + * @dev: virtual device associated with tunnel + * @ifr: parameters passed from userspace + * @cmd: command to be performed + * + * Description: + * vti6_ioctl() is used for managing vti6 tunnels + * from userspace. + * + * The possible commands are the following: + * %SIOCGETTUNNEL: get tunnel parameters for device + * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters + * %SIOCCHGTUNNEL: change tunnel parameters to those given + * %SIOCDELTUNNEL: delete tunnel + * + * The fallback device "ip6_vti0", created during module + * initialization, can be used for creating other tunnel devices. + * + * Return: + * 0 on success, + * %-EFAULT if unable to copy data to or from userspace, + * %-EPERM if current process hasn't %CAP_NET_ADMIN set + * %-EINVAL if passed tunnel parameters are invalid, + * %-EEXIST if changing a tunnel's parameters would cause a conflict + * %-ENODEV if attempting to change or delete a nonexisting device + **/ +static int +vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + int err = 0; + struct ip6_tnl_parm2 p; + struct __ip6_tnl_parm p1; + struct ip6_tnl *t = NULL; + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + switch (cmd) { + case SIOCGETTUNNEL: + if (dev == ip6n->fb_tnl_dev) { + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { + err = -EFAULT; + break; + } + vti6_parm_from_user(&p1, &p); + t = vti6_locate(net, &p1, 0); + } else { + memset(&p, 0, sizeof(p)); + } + if (t == NULL) + t = netdev_priv(dev); + vti6_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + break; + case SIOCADDTUNNEL: + case SIOCCHGTUNNEL: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + break; + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + break; + err = -EINVAL; + if (p.proto != IPPROTO_IPV6 && p.proto != 0) + break; + vti6_parm_from_user(&p1, &p); + t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL); + if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) { + if (t != NULL) { + if (t->dev != dev) { + err = -EEXIST; + break; + } + } else + t = netdev_priv(dev); + + err = vti6_update(t, &p1); + } + if (t) { + err = 0; + vti6_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + + } else + err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + break; + case SIOCDELTUNNEL: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + break; + + if (dev == ip6n->fb_tnl_dev) { + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + break; + err = -ENOENT; + vti6_parm_from_user(&p1, &p); + t = vti6_locate(net, &p1, 0); + if (t == NULL) + break; + err = -EPERM; + if (t->dev == ip6n->fb_tnl_dev) + break; + dev = t->dev; + } + err = 0; + unregister_netdevice(dev); + break; + default: + err = -EINVAL; + } + return err; +} + +/** + * vti6_tnl_change_mtu - change mtu manually for tunnel device + * @dev: virtual device associated with tunnel + * @new_mtu: the new mtu + * + * Return: + * 0 on success, + * %-EINVAL if mtu too small + **/ +static int vti6_change_mtu(struct net_device *dev, int new_mtu) +{ + if (new_mtu < IPV6_MIN_MTU) + return -EINVAL; + + dev->mtu = new_mtu; + return 0; +} + +static const struct net_device_ops vti6_netdev_ops = { + .ndo_uninit = vti6_dev_uninit, + .ndo_start_xmit = vti6_tnl_xmit, + .ndo_do_ioctl = vti6_ioctl, + .ndo_change_mtu = vti6_change_mtu, + .ndo_get_stats = vti6_get_stats, +}; + +/** + * vti6_dev_setup - setup virtual tunnel device + * @dev: virtual device associated with tunnel + * + * Description: + * Initialize function pointers and device parameters + **/ +static void vti6_dev_setup(struct net_device *dev) +{ + struct ip6_tnl *t; + + dev->netdev_ops = &vti6_netdev_ops; + dev->destructor = vti6_dev_free; + + dev->type = ARPHRD_TUNNEL6; + dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr); + dev->mtu = ETH_DATA_LEN; + t = netdev_priv(dev); + dev->flags |= IFF_NOARP; + dev->addr_len = sizeof(struct in6_addr); + dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; +} + +/** + * vti6_dev_init_gen - general initializer for all tunnel devices + * @dev: virtual device associated with tunnel + **/ +static inline int vti6_dev_init_gen(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + + t->dev = dev; + t->net = dev_net(dev); + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + return 0; +} + +/** + * vti6_dev_init - initializer for all non fallback tunnel devices + * @dev: virtual device associated with tunnel + **/ +static int vti6_dev_init(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + int err = vti6_dev_init_gen(dev); + + if (err) + return err; + vti6_link_config(t); + return 0; +} + +/** + * vti6_fb_tnl_dev_init - initializer for fallback tunnel device + * @dev: fallback device + * + * Return: 0 + **/ +static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + int err = vti6_dev_init_gen(dev); + + if (err) + return err; + + t->parms.proto = IPPROTO_IPV6; + dev_hold(dev); + + vti6_link_config(t); + + rcu_assign_pointer(ip6n->tnls_wc[0], t); + return 0; +} + +static int vti6_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + return 0; +} + +static void vti6_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_VTI_LINK]) + parms->link = nla_get_u32(data[IFLA_VTI_LINK]); + + if (data[IFLA_VTI_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_VTI_LOCAL], + sizeof(struct in6_addr)); + + if (data[IFLA_VTI_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_VTI_REMOTE], + sizeof(struct in6_addr)); + + if (data[IFLA_VTI_IKEY]) + parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); + + if (data[IFLA_VTI_OKEY]) + parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); +} + +static int vti6_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip6_tnl *nt; + + nt = netdev_priv(dev); + vti6_netlink_parms(data, &nt->parms); + + nt->parms.proto = IPPROTO_IPV6; + + if (vti6_locate(net, &nt->parms, 0)) + return -EEXIST; + + return vti6_tnl_create2(dev); +} + +static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t; + struct __ip6_tnl_parm p; + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + if (dev == ip6n->fb_tnl_dev) + return -EINVAL; + + vti6_netlink_parms(data, &p); + + t = vti6_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + return vti6_update(t, &p); +} + +static size_t vti6_get_size(const struct net_device *dev) +{ + return + /* IFLA_VTI_LINK */ + nla_total_size(4) + + /* IFLA_VTI_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_VTI_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_VTI_IKEY */ + nla_total_size(4) + + /* IFLA_VTI_OKEY */ + nla_total_size(4) + + 0; +} + +static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + struct __ip6_tnl_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) || + nla_put(skb, IFLA_VTI_LOCAL, sizeof(struct in6_addr), + &parm->laddr) || + nla_put(skb, IFLA_VTI_REMOTE, sizeof(struct in6_addr), + &parm->raddr) || + nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) || + nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy vti6_policy[IFLA_VTI_MAX + 1] = { + [IFLA_VTI_LINK] = { .type = NLA_U32 }, + [IFLA_VTI_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFLA_VTI_REMOTE] = { .len = sizeof(struct in6_addr) }, + [IFLA_VTI_IKEY] = { .type = NLA_U32 }, + [IFLA_VTI_OKEY] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops vti6_link_ops __read_mostly = { + .kind = "vti6", + .maxtype = IFLA_VTI_MAX, + .policy = vti6_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = vti6_dev_setup, + .validate = vti6_validate, + .newlink = vti6_newlink, + .changelink = vti6_changelink, + .get_size = vti6_get_size, + .fill_info = vti6_fill_info, +}; + +static struct xfrm_tunnel_notifier vti6_handler __read_mostly = { + .handler = vti6_rcv, + .priority = 1, +}; + +static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n) +{ + int h; + struct ip6_tnl *t; + LIST_HEAD(list); + + for (h = 0; h < HASH_SIZE; h++) { + t = rtnl_dereference(ip6n->tnls_r_l[h]); + while (t != NULL) { + unregister_netdevice_queue(t->dev, &list); + t = rtnl_dereference(t->next); + } + } + + t = rtnl_dereference(ip6n->tnls_wc[0]); + unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_many(&list); +} + +static int __net_init vti6_init_net(struct net *net) +{ + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + struct ip6_tnl *t = NULL; + int err; + + ip6n->tnls[0] = ip6n->tnls_wc; + ip6n->tnls[1] = ip6n->tnls_r_l; + + err = -ENOMEM; + ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0", + vti6_dev_setup); + + if (!ip6n->fb_tnl_dev) + goto err_alloc_dev; + dev_net_set(ip6n->fb_tnl_dev, net); + + err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + if (err < 0) + goto err_register; + + err = register_netdev(ip6n->fb_tnl_dev); + if (err < 0) + goto err_register; + + t = netdev_priv(ip6n->fb_tnl_dev); + + strcpy(t->parms.name, ip6n->fb_tnl_dev->name); + return 0; + +err_register: + vti6_dev_free(ip6n->fb_tnl_dev); +err_alloc_dev: + return err; +} + +static void __net_exit vti6_exit_net(struct net *net) +{ + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + rtnl_lock(); + vti6_destroy_tunnels(ip6n); + rtnl_unlock(); +} + +static struct pernet_operations vti6_net_ops = { + .init = vti6_init_net, + .exit = vti6_exit_net, + .id = &vti6_net_id, + .size = sizeof(struct vti6_net), +}; + +/** + * vti6_tunnel_init - register protocol and reserve needed resources + * + * Return: 0 on success + **/ +static int __init vti6_tunnel_init(void) +{ + int err; + + err = register_pernet_device(&vti6_net_ops); + if (err < 0) + goto out_pernet; + + err = xfrm6_mode_tunnel_input_register(&vti6_handler); + if (err < 0) { + pr_err("%s: can't register vti6\n", __func__); + goto out; + } + err = rtnl_link_register(&vti6_link_ops); + if (err < 0) + goto rtnl_link_failed; + + return 0; + +rtnl_link_failed: + xfrm6_mode_tunnel_input_deregister(&vti6_handler); +out: + unregister_pernet_device(&vti6_net_ops); +out_pernet: + return err; +} + +/** + * vti6_tunnel_cleanup - free resources and unregister protocol + **/ +static void __exit vti6_tunnel_cleanup(void) +{ + rtnl_link_unregister(&vti6_link_ops); + if (xfrm6_mode_tunnel_input_deregister(&vti6_handler)) + pr_info("%s: can't deregister vti6\n", __func__); + + unregister_pernet_device(&vti6_net_ops); +} + +module_init(vti6_tunnel_init); +module_exit(vti6_tunnel_cleanup); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("vti6"); +MODULE_ALIAS_NETDEV("ip6_vti0"); +MODULE_AUTHOR("Steffen Klassert"); +MODULE_DESCRIPTION("IPv6 virtual tunnel interface"); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 241fb8a..f365310 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -110,8 +110,8 @@ static struct kmem_cache *mrt_cachep __read_mostly; static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); static void ip6mr_free_table(struct mr6_table *mrt); -static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, - struct sk_buff *skb, struct mfc6_cache *cache); +static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache); static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, @@ -259,10 +259,12 @@ static void __net_exit ip6mr_rules_exit(struct net *net) { struct mr6_table *mrt, *next; + rtnl_lock(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { list_del(&mrt->list); ip6mr_free_table(mrt); } + rtnl_unlock(); fib_rules_unregister(net->ipv6.mr6_rules_ops); } #else @@ -289,7 +291,10 @@ static int __net_init ip6mr_rules_init(struct net *net) static void __net_exit ip6mr_rules_exit(struct net *net) { + rtnl_lock(); ip6mr_free_table(net->ipv6.mrt6); + net->ipv6.mrt6 = NULL; + rtnl_unlock(); } #endif @@ -667,9 +672,8 @@ static int pim6_rcv(struct sk_buff *skb) skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = CHECKSUM_NONE; - skb->pkt_type = PACKET_HOST; - skb_tunnel_rx(skb, reg_dev); + skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); netif_rx(skb); @@ -1319,7 +1323,7 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, static int ip6mr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr6_table *mrt; struct mif_device *v; @@ -2069,8 +2073,8 @@ static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) return ct; } -static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, - struct sk_buff *skb, struct mfc6_cache *cache) +static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache) { int psend = -1; int vif, ct; @@ -2151,12 +2155,11 @@ forward: last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, cache, psend); - return 0; + return; } dont_forward: kfree_skb(skb); - return 0; } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 7af5aee..ce507d9 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -64,8 +64,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; @@ -76,7 +75,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; if (type == NDISC_REDIRECT) - ip6_redirect(skb, net, 0, 0); + ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d1e2e8e..1c6ce31 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -174,7 +174,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, } if (ipv6_only_sock(sk) || - !ipv6_addr_v4mapped(&np->daddr)) { + !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { retv = -EADDRNOTAVAIL; break; } @@ -1011,7 +1011,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : np->sticky_pktinfo.ipi6_ifindex; - src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr; + src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxhlim) { @@ -1026,7 +1026,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : np->sticky_pktinfo.ipi6_ifindex; - src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr; + src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : + np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { @@ -1211,6 +1212,34 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->sndflow; break; + case IPV6_FLOWLABEL_MGR: + { + struct in6_flowlabel_req freq; + + if (len < sizeof(freq)) + return -EINVAL; + + if (copy_from_user(&freq, optval, sizeof(freq))) + return -EFAULT; + + if (freq.flr_action != IPV6_FL_A_GET) + return -EINVAL; + + len = sizeof(freq); + memset(&freq, 0, sizeof(freq)); + + val = ipv6_flowlabel_opt_get(sk, &freq); + if (val < 0) + return val; + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &freq, len)) + return -EFAULT; + + return 0; + } + case IPV6_ADDR_PREFERENCES: val = 0; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index bfa6cc3..d18f9f9 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -44,6 +44,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/pkt_sched.h> #include <net/mld.h> #include <linux/netfilter.h> @@ -94,6 +95,7 @@ static void mld_ifc_event(struct inet6_dev *idev); static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc); static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *addr); static void mld_clear_delrec(struct inet6_dev *idev); +static bool mld_in_v1_mode(const struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); static void sf_markstate(struct ifmcaddr6 *pmc); static void ip6_mc_clear_src(struct ifmcaddr6 *pmc); @@ -106,14 +108,15 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); - -#define IGMP6_UNSOLICITED_IVAL (10*HZ) #define MLD_QRV_DEFAULT 2 +/* RFC3810, 9.2. Query Interval */ +#define MLD_QI_DEFAULT (125 * HZ) +/* RFC3810, 9.3. Query Response Interval */ +#define MLD_QRI_DEFAULT (10 * HZ) -#define MLD_V1_SEEN(idev) (dev_net((idev)->dev)->ipv6.devconf_all->force_mld_version == 1 || \ - (idev)->cnf.force_mld_version == 1 || \ - ((idev)->mc_v1_seen && \ - time_before(jiffies, (idev)->mc_v1_seen))) +/* RFC3810, 8.1 Query Version Distinctions */ +#define MLD_V1_QUERY_LEN 24 +#define MLD_V2_QUERY_LEN_MIN 28 #define IPV6_MLD_MAX_MSF 64 @@ -128,6 +131,18 @@ int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; pmc != NULL; \ pmc = rcu_dereference(pmc->next)) +static int unsolicited_report_interval(struct inet6_dev *idev) +{ + int iv; + + if (mld_in_v1_mode(idev)) + iv = idev->cnf.mldv1_unsolicited_report_interval; + else + iv = idev->cnf.mldv2_unsolicited_report_interval; + + return iv > 0 ? iv : 1; +} + int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct net_device *dev = NULL; @@ -676,7 +691,7 @@ static void igmp6_group_added(struct ifmcaddr6 *mc) if (!(dev->flags & IFF_UP) || (mc->mca_flags & MAF_NOREPORT)) return; - if (MLD_V1_SEEN(mc->idev)) { + if (mld_in_v1_mode(mc->idev)) { igmp6_join_group(mc); return; } @@ -984,21 +999,49 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, static void mld_gq_start_timer(struct inet6_dev *idev) { - int tv = net_random() % idev->mc_maxdelay; + unsigned long tv = net_random() % idev->mc_maxdelay; idev->mc_gq_running = 1; if (!mod_timer(&idev->mc_gq_timer, jiffies+tv+2)) in6_dev_hold(idev); } -static void mld_ifc_start_timer(struct inet6_dev *idev, int delay) +static void mld_gq_stop_timer(struct inet6_dev *idev) +{ + idev->mc_gq_running = 0; + if (del_timer(&idev->mc_gq_timer)) + __in6_dev_put(idev); +} + +static void mld_ifc_start_timer(struct inet6_dev *idev, unsigned long delay) { - int tv = net_random() % delay; + unsigned long tv = net_random() % delay; if (!mod_timer(&idev->mc_ifc_timer, jiffies+tv+2)) in6_dev_hold(idev); } +static void mld_ifc_stop_timer(struct inet6_dev *idev) +{ + idev->mc_ifc_count = 0; + if (del_timer(&idev->mc_ifc_timer)) + __in6_dev_put(idev); +} + +static void mld_dad_start_timer(struct inet6_dev *idev, unsigned long delay) +{ + unsigned long tv = net_random() % delay; + + if (!mod_timer(&idev->mc_dad_timer, jiffies+tv+2)) + in6_dev_hold(idev); +} + +static void mld_dad_stop_timer(struct inet6_dev *idev) +{ + if (del_timer(&idev->mc_dad_timer)) + __in6_dev_put(idev); +} + /* * IGMP handling (alias multicast ICMPv6 messages) */ @@ -1017,12 +1060,9 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) delay = ma->mca_timer.expires - jiffies; } - if (delay >= resptime) { - if (resptime) - delay = net_random() % resptime; - else - delay = 1; - } + if (delay >= resptime) + delay = net_random() % resptime; + ma->mca_timer.expires = jiffies + delay; if (!mod_timer(&ma->mca_timer, jiffies + delay)) atomic_inc(&ma->mca_refcnt); @@ -1089,6 +1129,158 @@ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, return true; } +static int mld_force_mld_version(const struct inet6_dev *idev) +{ + /* Normally, both are 0 here. If enforcement to a particular is + * being used, individual device enforcement will have a lower + * precedence over 'all' device (.../conf/all/force_mld_version). + */ + + if (dev_net(idev->dev)->ipv6.devconf_all->force_mld_version != 0) + return dev_net(idev->dev)->ipv6.devconf_all->force_mld_version; + else + return idev->cnf.force_mld_version; +} + +static bool mld_in_v2_mode_only(const struct inet6_dev *idev) +{ + return mld_force_mld_version(idev) == 2; +} + +static bool mld_in_v1_mode_only(const struct inet6_dev *idev) +{ + return mld_force_mld_version(idev) == 1; +} + +static bool mld_in_v1_mode(const struct inet6_dev *idev) +{ + if (mld_in_v2_mode_only(idev)) + return false; + if (mld_in_v1_mode_only(idev)) + return true; + if (idev->mc_v1_seen && time_before(jiffies, idev->mc_v1_seen)) + return true; + + return false; +} + +static void mld_set_v1_mode(struct inet6_dev *idev) +{ + /* RFC3810, relevant sections: + * - 9.1. Robustness Variable + * - 9.2. Query Interval + * - 9.3. Query Response Interval + * - 9.12. Older Version Querier Present Timeout + */ + unsigned long switchback; + + switchback = (idev->mc_qrv * idev->mc_qi) + idev->mc_qri; + + idev->mc_v1_seen = jiffies + switchback; +} + +static void mld_update_qrv(struct inet6_dev *idev, + const struct mld2_query *mlh2) +{ + /* RFC3810, relevant sections: + * - 5.1.8. QRV (Querier's Robustness Variable) + * - 9.1. Robustness Variable + */ + + /* The value of the Robustness Variable MUST NOT be zero, + * and SHOULD NOT be one. Catch this here if we ever run + * into such a case in future. + */ + WARN_ON(idev->mc_qrv == 0); + + if (mlh2->mld2q_qrv > 0) + idev->mc_qrv = mlh2->mld2q_qrv; + + if (unlikely(idev->mc_qrv < 2)) { + net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", + idev->mc_qrv, MLD_QRV_DEFAULT); + idev->mc_qrv = MLD_QRV_DEFAULT; + } +} + +static void mld_update_qi(struct inet6_dev *idev, + const struct mld2_query *mlh2) +{ + /* RFC3810, relevant sections: + * - 5.1.9. QQIC (Querier's Query Interval Code) + * - 9.2. Query Interval + * - 9.12. Older Version Querier Present Timeout + * (the [Query Interval] in the last Query received) + */ + unsigned long mc_qqi; + + if (mlh2->mld2q_qqic < 128) { + mc_qqi = mlh2->mld2q_qqic; + } else { + unsigned long mc_man, mc_exp; + + mc_exp = MLDV2_QQIC_EXP(mlh2->mld2q_qqic); + mc_man = MLDV2_QQIC_MAN(mlh2->mld2q_qqic); + + mc_qqi = (mc_man | 0x10) << (mc_exp + 3); + } + + idev->mc_qi = mc_qqi * HZ; +} + +static void mld_update_qri(struct inet6_dev *idev, + const struct mld2_query *mlh2) +{ + /* RFC3810, relevant sections: + * - 5.1.3. Maximum Response Code + * - 9.3. Query Response Interval + */ + idev->mc_qri = msecs_to_jiffies(mldv2_mrc(mlh2)); +} + +static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, + unsigned long *max_delay) +{ + unsigned long mldv1_md; + + /* Ignore v1 queries */ + if (mld_in_v2_mode_only(idev)) + return -EINVAL; + + /* MLDv1 router present */ + mldv1_md = ntohs(mld->mld_maxdelay); + *max_delay = max(msecs_to_jiffies(mldv1_md), 1UL); + + mld_set_v1_mode(idev); + + /* cancel MLDv2 report timer */ + mld_gq_stop_timer(idev); + /* cancel the interface change timer */ + mld_ifc_stop_timer(idev); + /* clear deleted report items */ + mld_clear_delrec(idev); + + return 0; +} + +static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, + unsigned long *max_delay) +{ + /* hosts need to stay in MLDv1 mode, discard MLDv2 queries */ + if (mld_in_v1_mode(idev)) + return -EINVAL; + + *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); + + mld_update_qrv(idev, mld); + mld_update_qi(idev, mld); + mld_update_qri(idev, mld); + + idev->mc_maxdelay = *max_delay; + + return 0; +} + /* called with rcu_read_lock() */ int igmp6_event_query(struct sk_buff *skb) { @@ -1100,7 +1292,7 @@ int igmp6_event_query(struct sk_buff *skb) struct mld_msg *mld; int group_type; int mark = 0; - int len; + int len, err; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) return -EINVAL; @@ -1114,7 +1306,6 @@ int igmp6_event_query(struct sk_buff *skb) return -EINVAL; idev = __in6_dev_get(skb->dev); - if (idev == NULL) return 0; @@ -1126,35 +1317,23 @@ int igmp6_event_query(struct sk_buff *skb) !(group_type&IPV6_ADDR_MULTICAST)) return -EINVAL; - if (len == 24) { - int switchback; - /* MLDv1 router present */ - - /* Translate milliseconds to jiffies */ - max_delay = (ntohs(mld->mld_maxdelay)*HZ)/1000; - - switchback = (idev->mc_qrv + 1) * max_delay; - idev->mc_v1_seen = jiffies + switchback; - - /* cancel the interface change timer */ - idev->mc_ifc_count = 0; - if (del_timer(&idev->mc_ifc_timer)) - __in6_dev_put(idev); - /* clear deleted report items */ - mld_clear_delrec(idev); - } else if (len >= 28) { + if (len == MLD_V1_QUERY_LEN) { + err = mld_process_v1(idev, mld, &max_delay); + if (err < 0) + return err; + } else if (len >= MLD_V2_QUERY_LEN_MIN) { int srcs_offset = sizeof(struct mld2_query) - sizeof(struct icmp6hdr); + if (!pskb_may_pull(skb, srcs_offset)) return -EINVAL; mlh2 = (struct mld2_query *)skb_transport_header(skb); - max_delay = (MLDV2_MRC(ntohs(mlh2->mld2q_mrc))*HZ)/1000; - if (!max_delay) - max_delay = 1; - idev->mc_maxdelay = max_delay; - if (mlh2->mld2q_qrv) - idev->mc_qrv = mlh2->mld2q_qrv; + + err = mld_process_v2(idev, mlh2, &max_delay); + if (err < 0) + return err; + if (group_type == IPV6_ADDR_ANY) { /* general query */ if (mlh2->mld2q_nsrcs) return -EINVAL; /* no sources allowed */ @@ -1343,8 +1522,9 @@ static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, hdr->daddr = *daddr; } -static struct sk_buff *mld_newpack(struct net_device *dev, int size) +static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) { + struct net_device *dev = idev->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct sk_buff *skb; @@ -1367,9 +1547,10 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) if (!skb) return NULL; + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); - if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { + if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. @@ -1409,8 +1590,9 @@ static void mld_sendpack(struct sk_buff *skb) idev = __in6_dev_get(skb->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - payload_len = (skb->tail - skb->network_header) - sizeof(*pip6); - mldlen = skb->tail - skb->transport_header; + payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - + sizeof(*pip6); + mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, @@ -1465,7 +1647,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, struct mld2_grec *pgr; if (!skb) - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(pmc->idev, dev->mtu); if (!skb) return NULL; pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec)); @@ -1485,7 +1667,8 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) { - struct net_device *dev = pmc->idev->dev; + struct inet6_dev *idev = pmc->idev; + struct net_device *dev = idev->dev; struct mld2_report *pmr; struct mld2_grec *pgr = NULL; struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list; @@ -1514,7 +1697,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(idev, dev->mtu); } } first = 1; @@ -1541,7 +1724,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(idev, dev->mtu); first = 1; scount = 0; } @@ -1596,8 +1779,8 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) struct sk_buff *skb = NULL; int type; + read_lock_bh(&idev->lock); if (!pmc) { - read_lock_bh(&idev->lock); for (pmc=idev->mc_list; pmc; pmc=pmc->next) { if (pmc->mca_flags & MAF_NOREPORT) continue; @@ -1609,7 +1792,6 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->mca_lock); } - read_unlock_bh(&idev->lock); } else { spin_lock_bh(&pmc->mca_lock); if (pmc->mca_sfcount[MCAST_EXCLUDE]) @@ -1619,6 +1801,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->mca_lock); } + read_unlock_bh(&idev->lock); if (skb) mld_sendpack(skb); } @@ -1758,7 +1941,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) rcu_read_unlock(); return; } - + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { @@ -1814,6 +1997,46 @@ err_out: goto out; } +static void mld_resend_report(struct inet6_dev *idev) +{ + if (mld_in_v1_mode(idev)) { + struct ifmcaddr6 *mcaddr; + read_lock_bh(&idev->lock); + for (mcaddr = idev->mc_list; mcaddr; mcaddr = mcaddr->next) { + if (!(mcaddr->mca_flags & MAF_NOREPORT)) + igmp6_send(&mcaddr->mca_addr, idev->dev, + ICMPV6_MGM_REPORT); + } + read_unlock_bh(&idev->lock); + } else { + mld_send_report(idev, NULL); + } +} + +void ipv6_mc_dad_complete(struct inet6_dev *idev) +{ + idev->mc_dad_count = idev->mc_qrv; + if (idev->mc_dad_count) { + mld_resend_report(idev); + idev->mc_dad_count--; + if (idev->mc_dad_count) + mld_dad_start_timer(idev, idev->mc_maxdelay); + } +} + +static void mld_dad_timer_expire(unsigned long data) +{ + struct inet6_dev *idev = (struct inet6_dev *)data; + + mld_resend_report(idev); + if (idev->mc_dad_count) { + idev->mc_dad_count--; + if (idev->mc_dad_count) + mld_dad_start_timer(idev, idev->mc_maxdelay); + } + in6_dev_put(idev); +} + static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { @@ -1840,7 +2063,7 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, else pmc->mca_sources = psf->sf_next; if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && - !MLD_V1_SEEN(idev)) { + !mld_in_v1_mode(idev)) { psf->sf_crcount = idev->mc_qrv; psf->sf_next = pmc->mca_tomb; pmc->mca_tomb = psf; @@ -2105,7 +2328,7 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = net_random() % IGMP6_UNSOLICITED_IVAL; + delay = net_random() % unsolicited_report_interval(ma->idev); spin_lock_bh(&ma->mca_lock); if (del_timer(&ma->mca_timer)) { @@ -2140,7 +2363,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, static void igmp6_leave_group(struct ifmcaddr6 *ma) { - if (MLD_V1_SEEN(ma->idev)) { + if (mld_in_v1_mode(ma->idev)) { if (ma->mca_flags & MAF_LAST_REPORTER) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REDUCTION); @@ -2156,7 +2379,7 @@ static void mld_gq_timer_expire(unsigned long data) idev->mc_gq_running = 0; mld_send_report(idev, NULL); - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_timer_expire(unsigned long data) @@ -2169,12 +2392,12 @@ static void mld_ifc_timer_expire(unsigned long data) if (idev->mc_ifc_count) mld_ifc_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_event(struct inet6_dev *idev) { - if (MLD_V1_SEEN(idev)) + if (mld_in_v1_mode(idev)) return; idev->mc_ifc_count = idev->mc_qrv; mld_ifc_start_timer(idev, 1); @@ -2185,7 +2408,7 @@ static void igmp6_timer_handler(unsigned long data) { struct ifmcaddr6 *ma = (struct ifmcaddr6 *) data; - if (MLD_V1_SEEN(ma->idev)) + if (mld_in_v1_mode(ma->idev)) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); else mld_send_report(ma->idev, ma); @@ -2225,12 +2448,9 @@ void ipv6_mc_down(struct inet6_dev *idev) /* Withdraw multicast list */ read_lock_bh(&idev->lock); - idev->mc_ifc_count = 0; - if (del_timer(&idev->mc_ifc_timer)) - __in6_dev_put(idev); - idev->mc_gq_running = 0; - if (del_timer(&idev->mc_gq_timer)) - __in6_dev_put(idev); + mld_ifc_stop_timer(idev); + mld_gq_stop_timer(idev); + mld_dad_stop_timer(idev); for (i = idev->mc_list; i; i=i->next) igmp6_group_dropped(i); @@ -2267,8 +2487,14 @@ void ipv6_mc_init_dev(struct inet6_dev *idev) idev->mc_ifc_count = 0; setup_timer(&idev->mc_ifc_timer, mld_ifc_timer_expire, (unsigned long)idev); + setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire, + (unsigned long)idev); + idev->mc_qrv = MLD_QRV_DEFAULT; - idev->mc_maxdelay = IGMP6_UNSOLICITED_IVAL; + idev->mc_qi = MLD_QI_DEFAULT; + idev->mc_qri = MLD_QRI_DEFAULT; + + idev->mc_maxdelay = unsolicited_report_interval(idev); idev->mc_v1_seen = 0; write_unlock_bh(&idev->lock); } diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 0f9bdc5..9ac01dc 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -268,7 +268,8 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; @@ -404,7 +405,8 @@ static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb, struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index ca4ffcc..3512177 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -372,14 +372,11 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, int tlen = dev->needed_tailroom; struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; struct sk_buff *skb; - int err; - skb = sock_alloc_send_skb(sk, - hlen + sizeof(struct ipv6hdr) + len + tlen, - 1, &err); + skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); if (!skb) { - ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb, err=%d\n", - __func__, err); + ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n", + __func__); return NULL; } @@ -389,6 +386,11 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); + /* Manually assign socket ownership as we avoid calling + * sock_alloc_send_pskb() to bypass wmem buffer limits + */ + skb_set_owner_w(skb, sk); + return skb; } @@ -428,7 +430,6 @@ static void ndisc_send_skb(struct sk_buff *skb, type = icmp6h->icmp6_type; if (!dst) { - struct sock *sk = net->ipv6.ndisc_sk; struct flowi6 fl6; icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex); @@ -462,10 +463,10 @@ static void ndisc_send_skb(struct sk_buff *skb, rcu_read_unlock(); } -static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *solicited_addr, - bool router, bool solicited, bool override, bool inc_opt) +void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *solicited_addr, + bool router, bool solicited, bool override, bool inc_opt) { struct sk_buff *skb; struct in6_addr tmpaddr; @@ -479,7 +480,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) - override = 0; + override = false; inc_opt |= ifp->idev->cnf.force_tllao; in6_ifa_put(ifp); } else { @@ -557,7 +558,7 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, } if (ipv6_addr_any(saddr)) - inc_opt = 0; + inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev); @@ -663,9 +664,7 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) } ndisc_send_ns(dev, neigh, target, target, saddr); } else if ((probes -= neigh->parms->app_probes) < 0) { -#ifdef CONFIG_ARPD neigh_app_ns(neigh); -#endif } else { addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(dev, NULL, target, &mcaddr, saddr); @@ -693,7 +692,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; @@ -790,7 +789,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && - inc != 0 && + inc && idev->nd_parms->proxy_delay != 0) { /* * for anycast or proxy, @@ -853,7 +852,7 @@ static void ndisc_recv_na(struct sk_buff *skb) const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; @@ -1069,7 +1068,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) __u8 * opt = (__u8 *)(ra_msg + 1); - optlen = (skb->tail - skb->transport_header) - sizeof(struct ra_msg); + optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - + sizeof(struct ra_msg); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); @@ -1346,7 +1346,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) u8 *hdr; struct ndisc_options ndopts; struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -1368,8 +1368,11 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) return; - if (!ndopts.nd_opts_rh) + if (!ndopts.nd_opts_rh) { + ip6_redirect_no_header(skb, dev_net(skb->dev), + skb->dev->ifindex, 0); return; + } hdr = (u8 *)ndopts.nd_opts_rh; hdr += 8; @@ -1516,10 +1519,27 @@ static void pndisc_redo(struct sk_buff *skb) kfree_skb(skb); } +static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) +{ + struct inet6_dev *idev = __in6_dev_get(skb->dev); + + if (!idev) + return true; + if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && + idev->cnf.suppress_frag_ndisc) { + net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); + return true; + } + return false; +} + int ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; + if (ndisc_suppress_frag_ndisc(skb)) + return 0; + if (skb_linearize(skb)) return 0; @@ -1568,14 +1588,14 @@ int ndisc_rcv(struct sk_buff *skb) static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct inet6_dev *idev; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); idev = in6_dev_get(dev); if (!idev) break; @@ -1585,7 +1605,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); @@ -1706,25 +1726,29 @@ int __init ndisc_init(void) &ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; -#endif - err = register_netdevice_notifier(&ndisc_netdev_notifier); - if (err) - goto out_unregister_sysctl; out: +#endif return err; -out_unregister_sysctl: #ifdef CONFIG_SYSCTL - neigh_sysctl_unregister(&nd_tbl.parms); out_unregister_pernet: -#endif unregister_pernet_subsys(&ndisc_net_ops); goto out; +#endif } -void ndisc_cleanup(void) +int __init ndisc_late_init(void) +{ + return register_netdevice_notifier(&ndisc_netdev_notifier); +} + +void ndisc_late_cleanup(void) { unregister_netdevice_notifier(&ndisc_netdev_notifier); +} + +void ndisc_cleanup(void) +{ #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 4433ab40..7702f9e 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -25,6 +25,19 @@ config NF_CONNTRACK_IPV6 To compile it as a module, choose M here. If unsure, say N. +config NF_TABLES_IPV6 + depends on NF_TABLES + tristate "IPv6 nf_tables support" + +config NFT_CHAIN_ROUTE_IPV6 + depends on NF_TABLES_IPV6 + tristate "IPv6 nf_tables route chain support" + +config NFT_CHAIN_NAT_IPV6 + depends on NF_TABLES_IPV6 + depends on NF_NAT_IPV6 && NFT_NAT + tristate "IPv6 nf_tables nat chain support" + config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 @@ -153,6 +166,19 @@ config IP6_NF_TARGET_REJECT To compile it as a module, choose M here. If unsure, say N. +config IP6_NF_TARGET_SYNPROXY + tristate "SYNPROXY target support" + depends on NF_CONNTRACK && NETFILTER_ADVANCED + select NETFILTER_SYNPROXY + select SYN_COOKIES + help + The SYNPROXY target allows you to intercept TCP connections and + establish them using syncookies before they are passed on to the + server. This allows to avoid conntrack and server resource usage + during SYN-flood attacks. + + To compile it as a module, choose M here. If unsure, say N. + config IP6_NF_MANGLE tristate "Packet mangling" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 2d11fcc..d1b4928 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o # l3 independent conntrack -obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_defrag_ipv6.o +obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_nat_ipv6-y := nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o @@ -23,6 +23,11 @@ obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o +# nf_tables +obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o +obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o +obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o + # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o @@ -37,3 +42,4 @@ obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o +obj-$(CONFIG_IP6_NF_TARGET_SYNPROXY) += ip6t_SYNPROXY.o diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 167cb5a..b7db645 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -361,6 +361,11 @@ ip6t_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); private = table->private; + /* + * Ensure we load private-> members after we've fetched the base + * pointer. + */ + smp_read_barrier_depends(); cpu = smp_processor_id(); table_base = private->entries[cpu]; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 60e9053..3e4e92d 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -71,12 +71,12 @@ static int device_cmp(struct nf_conn *ct, void *ifindex) static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - const struct net_device *dev = ptr; + const struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_DOWN) nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex); + (void *)(long)dev->ifindex, 0, 0); return NOTIFY_DONE; } @@ -89,8 +89,10 @@ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; + struct netdev_notifier_info info; - return masq_device_event(this, event, ifa->idev->dev); + netdev_notifier_info_init(&info, ifa->idev->dev); + return masq_device_event(this, event, &info); } static struct notifier_block masq_inet_notifier = { diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 70f9abc..da00a2e 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -39,7 +39,7 @@ MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6"); MODULE_LICENSE("GPL"); /* Send RST reply */ -static void send_reset(struct net *net, struct sk_buff *oldskb) +static void send_reset(struct net *net, struct sk_buff *oldskb, int hook) { struct sk_buff *nskb; struct tcphdr otcph, *tcph; @@ -88,8 +88,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) } /* Check checksum. */ - if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP, - skb_checksum(oldskb, tcphoff, otcplen, 0))) { + if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) { pr_debug("TCP checksum is invalid\n"); return; } @@ -169,7 +168,25 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) nf_ct_attach(nskb, oldskb); - ip6_local_out(nskb); +#ifdef CONFIG_BRIDGE_NETFILTER + /* If we use ip6_local_out for bridged traffic, the MAC source on + * the RST will be ours, instead of the destination's. This confuses + * some routers/firewalls, and they drop the packet. So we need to + * build the eth header using the original destination's MAC as the + * source, and send the RST packet directly. + */ + if (oldskb->nf_bridge) { + struct ethhdr *oeth = eth_hdr(oldskb); + nskb->dev = oldskb->nf_bridge->physindev; + nskb->protocol = htons(ETH_P_IPV6); + ip6h->payload_len = htons(sizeof(struct tcphdr)); + if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), + oeth->h_source, oeth->h_dest, nskb->len) < 0) + return; + dev_queue_xmit(nskb); + } else +#endif + ip6_local_out(nskb); } static inline void @@ -209,7 +226,7 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) /* Do nothing */ break; case IP6T_TCP_RESET: - send_reset(net, skb); + send_reset(net, skb, par->hooknum); break; default: net_info_ratelimited("case %u not handled yet\n", reject->with); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c new file mode 100644 index 0000000..f78f41a --- /dev/null +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -0,0 +1,504 @@ +/* + * Copyright (c) 2013 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <net/ip6_checksum.h> +#include <net/ip6_route.h> +#include <net/tcp.h> + +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_SYNPROXY.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/nf_conntrack_synproxy.h> + +static struct ipv6hdr * +synproxy_build_ip(struct sk_buff *skb, const struct in6_addr *saddr, + const struct in6_addr *daddr) +{ + struct ipv6hdr *iph; + + skb_reset_network_header(skb); + iph = (struct ipv6hdr *)skb_put(skb, sizeof(*iph)); + ip6_flow_hdr(iph, 0, 0); + iph->hop_limit = 64; //XXX + iph->nexthdr = IPPROTO_TCP; + iph->saddr = *saddr; + iph->daddr = *daddr; + + return iph; +} + +static void +synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb, + struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, + struct ipv6hdr *niph, struct tcphdr *nth, + unsigned int tcp_hdr_size) +{ + struct net *net = nf_ct_net((struct nf_conn *)nfct); + struct dst_entry *dst; + struct flowi6 fl6; + + nth->check = ~tcp_v6_check(tcp_hdr_size, &niph->saddr, &niph->daddr, 0); + nskb->ip_summed = CHECKSUM_PARTIAL; + nskb->csum_start = (unsigned char *)nth - nskb->head; + nskb->csum_offset = offsetof(struct tcphdr, check); + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + fl6.saddr = niph->saddr; + fl6.daddr = niph->daddr; + fl6.fl6_sport = nth->source; + fl6.fl6_dport = nth->dest; + security_skb_classify_flow((struct sk_buff *)skb, flowi6_to_flowi(&fl6)); + dst = ip6_route_output(net, NULL, &fl6); + if (dst == NULL || dst->error) { + dst_release(dst); + goto free_nskb; + } + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(dst)) + goto free_nskb; + + skb_dst_set(nskb, dst); + + if (nfct) { + nskb->nfct = nfct; + nskb->nfctinfo = ctinfo; + nf_conntrack_get(nfct); + } + + ip6_local_out(nskb); + return; + +free_nskb: + kfree_skb(nskb); +} + +static void +synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct ipv6hdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + u16 mss = opts->mss; + + iph = ipv6_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, &iph->daddr, &iph->saddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->dest; + nth->dest = th->source; + nth->seq = htonl(__cookie_v6_init_sequence(iph, th, &mss)); + nth->ack_seq = htonl(ntohl(th->seq) + 1); + tcp_flag_word(nth) = TCP_FLAG_SYN | TCP_FLAG_ACK; + if (opts->options & XT_SYNPROXY_OPT_ECN) + tcp_flag_word(nth) |= TCP_FLAG_ECE; + nth->doff = tcp_hdr_size / 4; + nth->window = 0; + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_server_syn(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts, u32 recv_seq) +{ + struct sk_buff *nskb; + struct ipv6hdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ipv6_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, &iph->saddr, &iph->daddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->source; + nth->dest = th->dest; + nth->seq = htonl(recv_seq - 1); + /* ack_seq is used to relay our ISN to the synproxy hook to initialize + * sequence number translation once a connection tracking entry exists. + */ + nth->ack_seq = htonl(ntohl(th->ack_seq) - 1); + tcp_flag_word(nth) = TCP_FLAG_SYN; + if (opts->options & XT_SYNPROXY_OPT_ECN) + tcp_flag_word(nth) |= TCP_FLAG_ECE | TCP_FLAG_CWR; + nth->doff = tcp_hdr_size / 4; + nth->window = th->window; + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, + niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_server_ack(const struct synproxy_net *snet, + const struct ip_ct_tcp *state, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct ipv6hdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ipv6_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, &iph->daddr, &iph->saddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->dest; + nth->dest = th->source; + nth->seq = htonl(ntohl(th->ack_seq)); + nth->ack_seq = htonl(ntohl(th->seq) + 1); + tcp_flag_word(nth) = TCP_FLAG_ACK; + nth->doff = tcp_hdr_size / 4; + nth->window = htons(state->seen[IP_CT_DIR_ORIGINAL].td_maxwin); + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_client_ack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct ipv6hdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ipv6_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, &iph->saddr, &iph->daddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->source; + nth->dest = th->dest; + nth->seq = htonl(ntohl(th->seq) + 1); + nth->ack_seq = th->ack_seq; + tcp_flag_word(nth) = TCP_FLAG_ACK; + nth->doff = tcp_hdr_size / 4; + nth->window = ntohs(htons(th->window) >> opts->wscale); + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); +} + +static bool +synproxy_recv_client_ack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + struct synproxy_options *opts, u32 recv_seq) +{ + int mss; + + mss = __cookie_v6_check(ipv6_hdr(skb), th, ntohl(th->ack_seq) - 1); + if (mss == 0) { + this_cpu_inc(snet->stats->cookie_invalid); + return false; + } + + this_cpu_inc(snet->stats->cookie_valid); + opts->mss = mss; + opts->options |= XT_SYNPROXY_OPT_MSS; + + if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy_check_timestamp_cookie(opts); + + synproxy_send_server_syn(snet, skb, th, opts, recv_seq); + return true; +} + +static unsigned int +synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_synproxy_info *info = par->targinfo; + struct synproxy_net *snet = synproxy_pernet(dev_net(par->in)); + struct synproxy_options opts = {}; + struct tcphdr *th, _th; + + if (nf_ip6_checksum(skb, par->hooknum, par->thoff, IPPROTO_TCP)) + return NF_DROP; + + th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th); + if (th == NULL) + return NF_DROP; + + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; + + if (th->syn && !(th->ack || th->fin || th->rst)) { + /* Initial SYN from client */ + this_cpu_inc(snet->stats->syn_received); + + if (th->ece && th->cwr) + opts.options |= XT_SYNPROXY_OPT_ECN; + + opts.options &= info->options; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy_init_timestamp_cookie(info, &opts); + else + opts.options &= ~(XT_SYNPROXY_OPT_WSCALE | + XT_SYNPROXY_OPT_SACK_PERM | + XT_SYNPROXY_OPT_ECN); + + synproxy_send_client_synack(skb, th, &opts); + return NF_DROP; + + } else if (th->ack && !(th->fin || th->rst || th->syn)) { + /* ACK from client */ + synproxy_recv_client_ack(snet, skb, th, &opts, ntohl(th->seq)); + return NF_DROP; + } + + return XT_CONTINUE; +} + +static unsigned int ipv6_synproxy_hook(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct synproxy_net *snet = synproxy_pernet(dev_net(in ? : out)); + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + struct nf_conn_synproxy *synproxy; + struct synproxy_options opts = {}; + const struct ip_ct_tcp *state; + struct tcphdr *th, _th; + __be16 frag_off; + u8 nexthdr; + int thoff; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) + return NF_ACCEPT; + + synproxy = nfct_synproxy(ct); + if (synproxy == NULL) + return NF_ACCEPT; + + if (nf_is_loopback_packet(skb)) + return NF_ACCEPT; + + nexthdr = ipv6_hdr(skb)->nexthdr; + thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (thoff < 0) + return NF_ACCEPT; + + th = skb_header_pointer(skb, thoff, sizeof(_th), &_th); + if (th == NULL) + return NF_DROP; + + state = &ct->proto.tcp; + switch (state->state) { + case TCP_CONNTRACK_CLOSE: + if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - + ntohl(th->seq) + 1); + break; + } + + if (!th->syn || th->ack || + CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) + break; + + /* Reopened connection - reset the sequence number and timestamp + * adjustments, they will get initialized once the connection is + * reestablished. + */ + nf_ct_seqadj_init(ct, ctinfo, 0); + synproxy->tsoff = 0; + this_cpu_inc(snet->stats->conn_reopened); + + /* fall through */ + case TCP_CONNTRACK_SYN_SENT: + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + + if (!th->syn && th->ack && + CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + /* Keep-Alives are sent with SEG.SEQ = SND.NXT-1, + * therefore we need to add 1 to make the SYN sequence + * number match the one of first SYN. + */ + if (synproxy_recv_client_ack(snet, skb, th, &opts, + ntohl(th->seq) + 1)) + this_cpu_inc(snet->stats->cookie_retrans); + + return NF_DROP; + } + + synproxy->isn = ntohl(th->ack_seq); + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy->its = opts.tsecr; + break; + case TCP_CONNTRACK_SYN_RECV: + if (!th->syn || !th->ack) + break; + + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy->tsoff = opts.tsval - synproxy->its; + + opts.options &= ~(XT_SYNPROXY_OPT_MSS | + XT_SYNPROXY_OPT_WSCALE | + XT_SYNPROXY_OPT_SACK_PERM); + + swap(opts.tsval, opts.tsecr); + synproxy_send_server_ack(snet, state, skb, th, &opts); + + nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq)); + + swap(opts.tsval, opts.tsecr); + synproxy_send_client_ack(snet, skb, th, &opts); + + consume_skb(skb); + return NF_STOLEN; + default: + break; + } + + synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy); + return NF_ACCEPT; +} + +static int synproxy_tg6_check(const struct xt_tgchk_param *par) +{ + const struct ip6t_entry *e = par->entryinfo; + + if (!(e->ipv6.flags & IP6T_F_PROTO) || + e->ipv6.proto != IPPROTO_TCP || + e->ipv6.invflags & XT_INV_PROTO) + return -EINVAL; + + return nf_ct_l3proto_try_module_get(par->family); +} + +static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par) +{ + nf_ct_l3proto_module_put(par->family); +} + +static struct xt_target synproxy_tg6_reg __read_mostly = { + .name = "SYNPROXY", + .family = NFPROTO_IPV6, + .target = synproxy_tg6, + .targetsize = sizeof(struct xt_synproxy_info), + .checkentry = synproxy_tg6_check, + .destroy = synproxy_tg6_destroy, + .me = THIS_MODULE, +}; + +static struct nf_hook_ops ipv6_synproxy_ops[] __read_mostly = { + { + .hook = ipv6_synproxy_hook, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, + }, + { + .hook = ipv6_synproxy_hook, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, + }, +}; + +static int __init synproxy_tg6_init(void) +{ + int err; + + err = nf_register_hooks(ipv6_synproxy_ops, + ARRAY_SIZE(ipv6_synproxy_ops)); + if (err < 0) + goto err1; + + err = xt_register_target(&synproxy_tg6_reg); + if (err < 0) + goto err2; + + return 0; + +err2: + nf_unregister_hooks(ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops)); +err1: + return err; +} + +static void __exit synproxy_tg6_exit(void) +{ + xt_unregister_target(&synproxy_tg6_reg); + nf_unregister_hooks(ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops)); +} + +module_init(synproxy_tg6_init); +module_exit(synproxy_tg6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index beb5777..ca7f6c1 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -32,13 +32,14 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_filter_hook(unsigned int hook, struct sk_buff *skb, +ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net = dev_net((in != NULL) ? in : out); - return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter); + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_filter); } static struct nf_hook_ops *filter_ops __read_mostly; @@ -61,7 +62,7 @@ static int __net_init ip6table_filter_net_init(struct net *net) net->ipv6.ip6table_filter = ip6t_register_table(net, &packet_filter, repl); kfree(repl); - return PTR_RET(net->ipv6.ip6table_filter); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_filter); } static void __net_exit ip6table_filter_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index e075399..307bbb7 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -76,17 +76,17 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb, +ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_LOCAL_OUT) + if (ops->hooknum == NF_INET_LOCAL_OUT) return ip6t_mangle_out(skb, out); - if (hook == NF_INET_POST_ROUTING) - return ip6t_do_table(skb, hook, in, out, + if (ops->hooknum == NF_INET_POST_ROUTING) + return ip6t_do_table(skb, ops->hooknum, in, out, dev_net(out)->ipv6.ip6table_mangle); /* INPUT/FORWARD */ - return ip6t_do_table(skb, hook, in, out, + return ip6t_do_table(skb, ops->hooknum, in, out, dev_net(in)->ipv6.ip6table_mangle); } @@ -101,7 +101,7 @@ static int __net_init ip6table_mangle_net_init(struct net *net) net->ipv6.ip6table_mangle = ip6t_register_table(net, &packet_mangler, repl); kfree(repl); - return PTR_RET(net->ipv6.ip6table_mangle); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_mangle); } static void __net_exit ip6table_mangle_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 6383f90..84c7f33 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -63,7 +63,7 @@ static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum, } static unsigned int -nf_nat_ipv6_fn(unsigned int hooknum, +nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -72,7 +72,7 @@ nf_nat_ipv6_fn(unsigned int hooknum, struct nf_conn *ct; enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; - enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); + enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); __be16 frag_off; int hdrlen; u8 nexthdr; @@ -111,7 +111,8 @@ nf_nat_ipv6_fn(unsigned int hooknum, if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, - hooknum, hdrlen)) + ops->hooknum, + hdrlen)) return NF_DROP; else return NF_ACCEPT; @@ -124,14 +125,14 @@ nf_nat_ipv6_fn(unsigned int hooknum, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = nf_nat_rule_find(skb, hooknum, in, out, ct); + ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct); if (ret != NF_ACCEPT) return ret; } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); - if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) goto oif_changed; } break; @@ -140,11 +141,11 @@ nf_nat_ipv6_fn(unsigned int hooknum, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) goto oif_changed; } - return nf_nat_packet(ct, ctinfo, hooknum, skb); + return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); oif_changed: nf_ct_kill_acct(ct, ctinfo, skb); @@ -152,7 +153,7 @@ oif_changed: } static unsigned int -nf_nat_ipv6_in(unsigned int hooknum, +nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -161,7 +162,7 @@ nf_nat_ipv6_in(unsigned int hooknum, unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; - ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); @@ -170,7 +171,7 @@ nf_nat_ipv6_in(unsigned int hooknum, } static unsigned int -nf_nat_ipv6_out(unsigned int hooknum, +nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -187,7 +188,7 @@ nf_nat_ipv6_out(unsigned int hooknum, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && @@ -209,7 +210,7 @@ nf_nat_ipv6_out(unsigned int hooknum, } static unsigned int -nf_nat_ipv6_local_fn(unsigned int hooknum, +nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -224,7 +225,7 @@ nf_nat_ipv6_local_fn(unsigned int hooknum, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -293,7 +294,7 @@ static int __net_init ip6table_nat_net_init(struct net *net) return -ENOMEM; net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl); kfree(repl); - return PTR_RET(net->ipv6.ip6table_nat); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_nat); } static void __net_exit ip6table_nat_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 60d1bdd..5274740 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -19,13 +19,14 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_raw_hook(unsigned int hook, struct sk_buff *skb, +ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net = dev_net((in != NULL) ? in : out); - return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw); + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; @@ -40,7 +41,7 @@ static int __net_init ip6table_raw_net_init(struct net *net) net->ipv6.ip6table_raw = ip6t_register_table(net, &packet_raw, repl); kfree(repl); - return PTR_RET(net->ipv6.ip6table_raw); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_raw); } static void __net_exit ip6table_raw_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index db15535..ab3b021 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -36,14 +36,15 @@ static const struct xt_table security_table = { }; static unsigned int -ip6table_security_hook(unsigned int hook, struct sk_buff *skb, +ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net = dev_net((in != NULL) ? in : out); - return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security); + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_security); } static struct nf_hook_ops *sectbl_ops __read_mostly; @@ -58,7 +59,7 @@ static int __net_init ip6table_security_net_init(struct net *net) net->ipv6.ip6table_security = ip6t_register_table(net, &security_table, repl); kfree(repl); - return PTR_RET(net->ipv6.ip6table_security); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_security); } static void __net_exit ip6table_security_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index c9b6a6e..4cbc6b2 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -28,6 +28,7 @@ #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> #include <net/netfilter/nf_nat_helper.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> @@ -94,7 +95,7 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv6_helper(unsigned int hooknum, +static unsigned int ipv6_helper(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -132,7 +133,7 @@ static unsigned int ipv6_helper(unsigned int hooknum, return helper->help(skb, protoff, ct, ctinfo); } -static unsigned int ipv6_confirm(unsigned int hooknum, +static unsigned int ipv6_confirm(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -158,11 +159,7 @@ static unsigned int ipv6_confirm(unsigned int hooknum, /* adjust seqs for loopback traffic only in outgoing direction */ if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && !nf_is_loopback_packet(skb)) { - typeof(nf_nat_seq_adjust_hook) seq_adjust; - - seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook); - if (!seq_adjust || - !seq_adjust(skb, ct, ctinfo, protoff)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); return NF_DROP; } @@ -172,66 +169,16 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int __ipv6_conntrack_in(struct net *net, - unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm = skb->nfct_reasm; - const struct nf_conn_help *help; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - - /* This packet is fragmented and has reassembled packet. */ - if (reasm) { - /* Reassembled packet isn't parsed yet ? */ - if (!reasm->nfct) { - unsigned int ret; - - ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm); - if (ret != NF_ACCEPT) - return ret; - } - - /* Conntrack helpers need the entire reassembled packet in the - * POST_ROUTING hook. In case of unconfirmed connections NAT - * might reassign a helper, so the entire packet is also - * required. - */ - ct = nf_ct_get(reasm, &ctinfo); - if (ct != NULL && !nf_ct_is_untracked(ct)) { - help = nfct_help(ct); - if ((help && help->helper) || !nf_ct_is_confirmed(ct)) { - nf_conntrack_get_reasm(reasm); - NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm, - (struct net_device *)in, - (struct net_device *)out, - okfn, NF_IP6_PRI_CONNTRACK + 1); - return NF_DROP_ERR(-ECANCELED); - } - } - - nf_conntrack_get(reasm->nfct); - skb->nfct = reasm->nfct; - skb->nfctinfo = reasm->nfctinfo; - return NF_ACCEPT; - } - - return nf_conntrack_in(net, PF_INET6, hooknum, skb); -} - -static unsigned int ipv6_conntrack_in(unsigned int hooknum, +static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn); + return nf_conntrack_in(dev_net(in), PF_INET6, ops->hooknum, skb); } -static unsigned int ipv6_conntrack_local(unsigned int hooknum, +static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -242,7 +189,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } - return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn); + return nf_conntrack_in(dev_net(out), PF_INET6, ops->hooknum, skb); } static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { @@ -300,9 +247,9 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; struct nf_conn *ct; - tuple.src.u3.in6 = inet6->rcv_saddr; + tuple.src.u3.in6 = sk->sk_v6_rcv_saddr; tuple.src.u.tcp.port = inet->inet_sport; - tuple.dst.u3.in6 = inet6->daddr; + tuple.dst.u3.in6 = sk->sk_v6_daddr; tuple.dst.u.tcp.port = inet->inet_dport; tuple.dst.protonum = sk->sk_protocol; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index dffdc1a..767ab8d 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -144,12 +144,24 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); } +static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr, + const struct in6_addr *daddr) +{ + u32 c; + + net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd)); + c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), + (__force u32)id, nf_frags.rnd); + return c & (INETFRAGS_HASHSZ - 1); +} + + static unsigned int nf_hashfn(struct inet_frag_queue *q) { const struct frag_queue *nq; nq = container_of(q, struct frag_queue, q); - return inet6_hash_frag(nq->id, &nq->saddr, &nq->daddr, nf_frags.rnd); + return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); } static void nf_skb_free(struct sk_buff *skb) @@ -185,7 +197,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id, arg.ecn = ecn; read_lock_bh(&nf_frags.lock); - hash = inet6_hash_frag(id, src, dst, nf_frags.rnd); + hash = nf_hash_frag(id, src, dst); q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); local_bh_enable(); @@ -621,31 +633,16 @@ ret_orig: return skb; } -void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, - struct net_device *in, struct net_device *out, - int (*okfn)(struct sk_buff *)) +void nf_ct_frag6_consume_orig(struct sk_buff *skb) { struct sk_buff *s, *s2; - unsigned int ret = 0; for (s = NFCT_FRAG6_CB(skb)->orig; s;) { - nf_conntrack_put_reasm(s->nfct_reasm); - nf_conntrack_get_reasm(skb); - s->nfct_reasm = skb; - s2 = s->next; s->next = NULL; - - if (ret != -ECANCELED) - ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, - in, out, okfn, - NF_IP6_PRI_CONNTRACK_DEFRAG + 1); - else - kfree_skb(s); - + consume_skb(s); s = s2; } - nf_conntrack_put_reasm(skb); } static int nf_ct_net_init(struct net *net) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index aacd121..7b9a748 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -52,7 +52,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, } -static unsigned int ipv6_defrag(unsigned int hooknum, +static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -66,7 +66,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, return NF_ACCEPT; #endif - reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(ops->hooknum, skb)); /* queued */ if (reasm == NULL) return NF_STOLEN; @@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (reasm == skb) return NF_ACCEPT; - nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, - (struct net_device *)out, okfn); + nf_ct_frag6_consume_orig(reasm); + + NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, reasm, + (struct net_device *) in, (struct net_device *) out, + okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); return NF_STOLEN; } diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c index 61aaf70..2205e8e 100644 --- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -69,8 +69,8 @@ icmpv6_manip_pkt(struct sk_buff *skb, hdr = (struct icmp6hdr *)(skb->data + hdroff); l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); - if (hdr->icmp6_code == ICMPV6_ECHO_REQUEST || - hdr->icmp6_code == ICMPV6_ECHO_REPLY) { + if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || + hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, tuple->src.u.icmp.id, 0); diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c new file mode 100644 index 0000000..d77db8a --- /dev/null +++ b/net/ipv6/netfilter/nf_tables_ipv6.c @@ -0,0 +1,127 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2012-2013 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/ipv6.h> +#include <linux/netfilter_ipv6.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_ipv6.h> + +static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nft_pktinfo pkt; + + if (unlikely(skb->len < sizeof(struct ipv6hdr))) { + if (net_ratelimit()) + pr_info("nf_tables_ipv6: ignoring short SOCK_RAW " + "packet\n"); + return NF_ACCEPT; + } + if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) + return NF_DROP; + + return nft_do_chain_pktinfo(&pkt, ops); +} + +static struct nft_af_info nft_af_ipv6 __read_mostly = { + .family = NFPROTO_IPV6, + .nhooks = NF_INET_NUMHOOKS, + .owner = THIS_MODULE, + .hooks = { + [NF_INET_LOCAL_OUT] = nft_ipv6_output, + }, +}; + +static int nf_tables_ipv6_init_net(struct net *net) +{ + net->nft.ipv6 = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL); + if (net->nft.ipv6 == NULL) + return -ENOMEM; + + memcpy(net->nft.ipv6, &nft_af_ipv6, sizeof(nft_af_ipv6)); + + if (nft_register_afinfo(net, net->nft.ipv6) < 0) + goto err; + + return 0; +err: + kfree(net->nft.ipv6); + return -ENOMEM; +} + +static void nf_tables_ipv6_exit_net(struct net *net) +{ + nft_unregister_afinfo(net->nft.ipv6); + kfree(net->nft.ipv6); +} + +static struct pernet_operations nf_tables_ipv6_net_ops = { + .init = nf_tables_ipv6_init_net, + .exit = nf_tables_ipv6_exit_net, +}; + +static unsigned int +nft_do_chain_ipv6(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nft_pktinfo pkt; + + /* malformed packet, drop it */ + if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) + return NF_DROP; + + return nft_do_chain_pktinfo(&pkt, ops); +} + +static struct nf_chain_type filter_ipv6 = { + .family = NFPROTO_IPV6, + .name = "filter", + .type = NFT_CHAIN_T_DEFAULT, + .hook_mask = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING), + .fn = { + [NF_INET_LOCAL_IN] = nft_do_chain_ipv6, + [NF_INET_LOCAL_OUT] = nft_ipv6_output, + [NF_INET_FORWARD] = nft_do_chain_ipv6, + [NF_INET_PRE_ROUTING] = nft_do_chain_ipv6, + [NF_INET_POST_ROUTING] = nft_do_chain_ipv6, + }, +}; + +static int __init nf_tables_ipv6_init(void) +{ + nft_register_chain_type(&filter_ipv6); + return register_pernet_subsys(&nf_tables_ipv6_net_ops); +} + +static void __exit nf_tables_ipv6_exit(void) +{ + unregister_pernet_subsys(&nf_tables_ipv6_net_ops); + nft_unregister_chain_type(&filter_ipv6); +} + +module_init(nf_tables_ipv6_init); +module_exit(nf_tables_ipv6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_FAMILY(AF_INET6); diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c new file mode 100644 index 0000000..e86dcd7 --- /dev/null +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -0,0 +1,211 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2012 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_ipv6.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/ipv6.h> + +/* + * IPv6 NAT chains + */ + +static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct nf_conn_nat *nat; + enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); + __be16 frag_off; + int hdrlen; + u8 nexthdr; + struct nft_pktinfo pkt; + unsigned int ret; + + if (ct == NULL || nf_ct_is_untracked(ct)) + return NF_ACCEPT; + + nat = nfct_nat(ct); + if (nat == NULL) { + /* Conntrack module was loaded late, can't add extension. */ + if (nf_ct_is_confirmed(ct)) + return NF_ACCEPT; + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) + return NF_ACCEPT; + } + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED + IP_CT_IS_REPLY: + nexthdr = ipv6_hdr(skb)->nexthdr; + hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, + ops->hooknum, + hdrlen)) + return NF_DROP; + else + return NF_ACCEPT; + } + /* Fall through */ + case IP_CT_NEW: + if (nf_nat_initialized(ct, maniptype)) + break; + + nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out); + + ret = nft_do_chain_pktinfo(&pkt, ops); + if (ret != NF_ACCEPT) + return ret; + if (!nf_nat_initialized(ct, maniptype)) { + ret = nf_nat_alloc_null_binding(ct, ops->hooknum); + if (ret != NF_ACCEPT) + return ret; + } + default: + break; + } + + return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); +} + +static unsigned int nf_nat_ipv6_prerouting(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct in6_addr daddr = ipv6_hdr(skb)->daddr; + unsigned int ret; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) + skb_dst_drop(skb); + + return ret; +} + +static unsigned int nf_nat_ipv6_postrouting(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo __maybe_unused; + const struct nf_conn *ct __maybe_unused; + unsigned int ret; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); +#ifdef CONFIG_XFRM + if (ret != NF_DROP && ret != NF_STOLEN && + !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3) || + (ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all)) + if (nf_xfrm_me_harder(skb, AF_INET6) < 0) + ret = NF_DROP; + } +#endif + return ret; +} + +static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct; + unsigned int ret; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, + &ct->tuplehash[!dir].tuple.src.u3)) { + if (ip6_route_me_harder(skb)) + ret = NF_DROP; + } +#ifdef CONFIG_XFRM + else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) + if (nf_xfrm_me_harder(skb, AF_INET6)) + ret = NF_DROP; +#endif + } + return ret; +} + +static struct nf_chain_type nft_chain_nat_ipv6 = { + .family = NFPROTO_IPV6, + .name = "nat", + .type = NFT_CHAIN_T_NAT, + .hook_mask = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .fn = { + [NF_INET_PRE_ROUTING] = nf_nat_ipv6_prerouting, + [NF_INET_POST_ROUTING] = nf_nat_ipv6_postrouting, + [NF_INET_LOCAL_OUT] = nf_nat_ipv6_output, + [NF_INET_LOCAL_IN] = nf_nat_ipv6_fn, + }, + .me = THIS_MODULE, +}; + +static int __init nft_chain_nat_ipv6_init(void) +{ + int err; + + err = nft_register_chain_type(&nft_chain_nat_ipv6); + if (err < 0) + return err; + + return 0; +} + +static void __exit nft_chain_nat_ipv6_exit(void) +{ + nft_unregister_chain_type(&nft_chain_nat_ipv6); +} + +module_init(nft_chain_nat_ipv6_init); +module_exit(nft_chain_nat_ipv6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); +MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat"); diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c new file mode 100644 index 0000000..3fe40f0 --- /dev/null +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -0,0 +1,88 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_ipv6.h> +#include <net/route.h> + +static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int ret; + struct nft_pktinfo pkt; + struct in6_addr saddr, daddr; + u_int8_t hop_limit; + u32 mark, flowlabel; + + /* malformed packet, drop it */ + if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) + return NF_DROP; + + /* save source/dest address, mark, hoplimit, flowlabel, priority */ + memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); + memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr)); + mark = skb->mark; + hop_limit = ipv6_hdr(skb)->hop_limit; + + /* flowlabel and prio (includes version, which shouldn't change either */ + flowlabel = *((u32 *)ipv6_hdr(skb)); + + ret = nft_do_chain_pktinfo(&pkt, ops); + if (ret != NF_DROP && ret != NF_QUEUE && + (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || + memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || + skb->mark != mark || + ipv6_hdr(skb)->hop_limit != hop_limit || + flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) + return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP; + + return ret; +} + +static struct nf_chain_type nft_chain_route_ipv6 = { + .family = NFPROTO_IPV6, + .name = "route", + .type = NFT_CHAIN_T_ROUTE, + .hook_mask = (1 << NF_INET_LOCAL_OUT), + .fn = { + [NF_INET_LOCAL_OUT] = nf_route_table_hook, + }, + .me = THIS_MODULE, +}; + +static int __init nft_chain_route_init(void) +{ + return nft_register_chain_type(&nft_chain_route_ipv6); +} + +static void __exit nft_chain_route_exit(void) +{ + nft_unregister_chain_type(&nft_chain_route_ipv6); +} + +module_init(nft_chain_route_init); +module_exit(nft_chain_route_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_CHAIN(AF_INET6, "route"); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index c2e73e6..827f795 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -5,6 +5,7 @@ #include <linux/export.h> #include <net/ipv6.h> #include <net/ip6_fib.h> +#include <net/addrconf.h> void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) { @@ -40,7 +41,8 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) u16 offset = sizeof(struct ipv6hdr); struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; @@ -74,3 +76,50 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) return offset; } EXPORT_SYMBOL(ip6_find_1stfragopt); + +#if IS_ENABLED(CONFIG_IPV6) +int ip6_dst_hoplimit(struct dst_entry *dst) +{ + int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); + if (hoplimit == 0) { + struct net_device *dev = dst->dev; + struct inet6_dev *idev; + + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) + hoplimit = idev->cnf.hop_limit; + else + hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit; + rcu_read_unlock(); + } + return hoplimit; +} +EXPORT_SYMBOL(ip6_dst_hoplimit); +#endif + +int __ip6_local_out(struct sk_buff *skb) +{ + int len; + + len = skb->len - sizeof(struct ipv6hdr); + if (len > IPV6_MAXPLEN) + len = 0; + ipv6_hdr(skb)->payload_len = htons(len); + + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, + skb_dst(skb)->dev, dst_output); +} +EXPORT_SYMBOL_GPL(__ip6_local_out); + +int ip6_local_out(struct sk_buff *skb) +{ + int err; + + err = __ip6_local_out(skb); + if (likely(err == 1)) + err = dst_output(skb); + + return err; +} +EXPORT_SYMBOL_GPL(ip6_local_out); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c new file mode 100644 index 0000000..a83243c --- /dev/null +++ b/net/ipv6/ping.c @@ -0,0 +1,278 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * "Ping" sockets + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Based on ipv4/ping.c code. + * + * Authors: Lorenzo Colitti (IPv6 support) + * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6), + * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32) + * + */ + +#include <net/addrconf.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/protocol.h> +#include <net/udp.h> +#include <net/transp_v6.h> +#include <net/ping.h> + +struct proto pingv6_prot = { + .name = "PINGv6", + .owner = THIS_MODULE, + .init = ping_init_sock, + .close = ping_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .sendmsg = ping_v6_sendmsg, + .recvmsg = ping_recvmsg, + .bind = ping_bind, + .backlog_rcv = ping_queue_rcv_skb, + .hash = ping_hash, + .unhash = ping_unhash, + .get_port = ping_get_port, + .obj_size = sizeof(struct raw6_sock), +}; +EXPORT_SYMBOL_GPL(pingv6_prot); + +static struct inet_protosw pingv6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_ICMPV6, + .prot = &pingv6_prot, + .ops = &inet6_dgram_ops, + .no_check = UDP_CSUM_DEFAULT, + .flags = INET_PROTOSW_REUSE, +}; + + +/* Compatibility glue so we can support IPv6 when it's compiled as a module */ +static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) +{ + return -EAFNOSUPPORT; +} +static int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + return -EAFNOSUPPORT; +} +static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) +{ + return -EAFNOSUPPORT; +} +static void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) {} +static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict) +{ + return 0; +} + +int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len) +{ + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct icmp6hdr user_icmph; + int addr_type; + struct in6_addr *daddr; + int iif = 0; + struct flowi6 fl6; + int err; + int hlimit; + struct dst_entry *dst; + struct rt6_info *rt; + struct pingfakehdr pfh; + + pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); + + err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph, + sizeof(user_icmph)); + if (err) + return err; + + if (msg->msg_name) { + struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name; + if (msg->msg_namelen < sizeof(struct sockaddr_in6) || + u->sin6_family != AF_INET6) { + return -EINVAL; + } + if (sk->sk_bound_dev_if && + sk->sk_bound_dev_if != u->sin6_scope_id) { + return -EINVAL; + } + daddr = &(u->sin6_addr); + iif = u->sin6_scope_id; + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + daddr = &sk->sk_v6_daddr; + } + + if (!iif) + iif = sk->sk_bound_dev_if; + + addr_type = ipv6_addr_type(daddr); + if (__ipv6_addr_needs_scope_id(addr_type) && !iif) + return -EINVAL; + if (addr_type & IPV6_ADDR_MAPPED) + return -EINVAL; + + /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ + + memset(&fl6, 0, sizeof(fl6)); + + fl6.flowi6_proto = IPPROTO_ICMPV6; + fl6.saddr = np->saddr; + fl6.daddr = *daddr; + fl6.fl6_icmp_type = user_icmph.icmp6_type; + fl6.fl6_icmp_code = user_icmph.icmp6_code; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + + dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, 1); + if (IS_ERR(dst)) + return PTR_ERR(dst); + rt = (struct rt6_info *) dst; + + np = inet6_sk(sk); + if (!np) + return -EBADF; + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + + pfh.icmph.type = user_icmph.icmp6_type; + pfh.icmph.code = user_icmph.icmp6_code; + pfh.icmph.checksum = 0; + pfh.icmph.un.echo.id = inet->inet_sport; + pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; + pfh.iov = msg->msg_iov; + pfh.wcheck = 0; + pfh.family = AF_INET6; + + if (ipv6_addr_is_multicast(&fl6.daddr)) + hlimit = np->mcast_hops; + else + hlimit = np->hop_limit; + if (hlimit < 0) + hlimit = ip6_dst_hoplimit(dst); + + lock_sock(sk); + err = ip6_append_data(sk, ping_getfrag, &pfh, len, + 0, hlimit, + np->tclass, NULL, &fl6, rt, + MSG_DONTWAIT, np->dontfrag); + + if (err) { + ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev, + ICMP6_MIB_OUTERRORS); + ip6_flush_pending_frames(sk); + } else { + err = icmpv6_push_pending_frames(sk, &fl6, + (struct icmp6hdr *) &pfh.icmph, + len); + } + release_sock(sk); + + if (err) + return err; + + return len; +} + +#ifdef CONFIG_PROC_FS +static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos) +{ + return ping_seq_start(seq, pos, AF_INET6); +} + +static int ping_v6_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + int bucket = ((struct ping_iter_state *) seq->private)->bucket; + struct inet_sock *inet = inet_sk(v); + __u16 srcp = ntohs(inet->inet_sport); + __u16 destp = ntohs(inet->inet_dport); + ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + } + return 0; +} + +static struct ping_seq_afinfo ping_v6_seq_afinfo = { + .name = "icmp6", + .family = AF_INET6, + .seq_fops = &ping_seq_fops, + .seq_ops = { + .start = ping_v6_seq_start, + .show = ping_v6_seq_show, + .next = ping_seq_next, + .stop = ping_seq_stop, + }, +}; + +static int __net_init ping_v6_proc_init_net(struct net *net) +{ + return ping_proc_register(net, &ping_v6_seq_afinfo); +} + +static void __net_init ping_v6_proc_exit_net(struct net *net) +{ + return ping_proc_unregister(net, &ping_v6_seq_afinfo); +} + +static struct pernet_operations ping_v6_net_ops = { + .init = ping_v6_proc_init_net, + .exit = ping_v6_proc_exit_net, +}; +#endif + +int __init pingv6_init(void) +{ +#ifdef CONFIG_PROC_FS + int ret = register_pernet_subsys(&ping_v6_net_ops); + if (ret) + return ret; +#endif + pingv6_ops.ipv6_recv_error = ipv6_recv_error; + pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl; + pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; + pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; + pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; + return inet6_register_protosw(&pingv6_protosw); +} + +/* This never gets called because it's not possible to unload the ipv6 module, + * but just in case. + */ +void pingv6_exit(void) +{ + pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; + pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; + pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; + pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; +#ifdef CONFIG_PROC_FS + unregister_pernet_subsys(&ping_v6_net_ops); +#endif + inet6_unregister_protosw(&pingv6_protosw); +} diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 51c3285..091d066 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -91,6 +91,10 @@ static const struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InBcastOctets", IPSTATS_MIB_INBCASTOCTETS), SNMP_MIB_ITEM("Ip6OutBcastOctets", IPSTATS_MIB_OUTBCASTOCTETS), /* IPSTATS_MIB_CSUMERRORS is not relevant in IPv6 (no checksum) */ + SNMP_MIB_ITEM("Ip6InNoECTPkts", IPSTATS_MIB_NOECTPKTS), + SNMP_MIB_ITEM("Ip6InECT1Pkts", IPSTATS_MIB_ECT1PKTS), + SNMP_MIB_ITEM("Ip6InECT0Pkts", IPSTATS_MIB_ECT0PKTS), + SNMP_MIB_ITEM("Ip6InCEPkts", IPSTATS_MIB_CEPKTS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 22d1bd4..e048cf1 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -36,10 +36,6 @@ int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol } EXPORT_SYMBOL(inet6_add_protocol); -/* - * Remove a protocol from the hash tables. - */ - int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol) { int ret; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index eedff8c..7fb4e14 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -63,6 +63,8 @@ #include <linux/seq_file.h> #include <linux/export.h> +#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ + static struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; @@ -75,20 +77,19 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { - struct ipv6_pinfo *np = inet6_sk(sk); if (!net_eq(sock_net(sk), net)) continue; - if (!ipv6_addr_any(&np->daddr) && - !ipv6_addr_equal(&np->daddr, rmt_addr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) continue; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (ipv6_addr_equal(&np->rcv_saddr, loc_addr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) goto found; if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) @@ -108,11 +109,14 @@ found: */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { - struct icmp6hdr *_hdr; + struct icmp6hdr _hdr; const struct icmp6hdr *hdr; + /* We require only the four bytes of the ICMPv6 header, not any + * additional bytes of message body in "struct icmp6hdr". + */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), - sizeof(_hdr), &_hdr); + ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; @@ -297,7 +301,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; - np->rcv_saddr = addr->sin6_addr; + sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; @@ -330,8 +334,10 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } - if (type == NDISC_REDIRECT) + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + return; + } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) @@ -459,14 +465,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (flags & MSG_OOB) return -EOPNOTSUPP; - if (addr_len) - *addr_len=sizeof(*sin6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -500,6 +503,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, IP6CB(skb)->iif); + *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); @@ -628,6 +632,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, goto error; skb_reserve(skb, hlen); + skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb_dst_set(skb, &rt->dst); @@ -796,8 +801,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; + ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) + daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && @@ -808,7 +813,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, return -EDESTADDRREQ; proto = inet->inet_num; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } @@ -1132,7 +1137,8 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) - amount = skb->tail - skb->transport_header; + amount = skb_tail_pointer(skb) - + skb_transport_header(skb); spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } @@ -1226,45 +1232,16 @@ struct proto rawv6_prot = { }; #ifdef CONFIG_PROC_FS -static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) -{ - struct ipv6_pinfo *np = inet6_sk(sp); - const struct in6_addr *dest, *src; - __u16 destp, srcp; - - dest = &np->daddr; - src = &np->rcv_saddr; - destp = 0; - srcp = inet_sk(sp)->inet_num; - seq_printf(seq, - "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", - i, - src->s6_addr32[0], src->s6_addr32[1], - src->s6_addr32[2], src->s6_addr32[3], srcp, - dest->s6_addr32[0], dest->s6_addr32[1], - dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - sk_wmem_alloc_get(sp), - sk_rmem_alloc_get(sp), - 0, 0L, 0, - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), - 0, - sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); -} - static int raw6_seq_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) - seq_printf(seq, - " sl " - "local_address " - "remote_address " - "st tx_queue rx_queue tr tm->when retrnsmt" - " uid timeout inode ref pointer drops\n"); - else - raw6_sock_seq_show(seq, v, raw_seq_private(seq)->bucket); + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + struct sock *sp = v; + __u16 srcp = inet_sk(sp)->inet_num; + ip6_dgram_sock_seq_show(seq, v, srcp, 0, + raw_seq_private(seq)->bucket); + } return 0; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 790d9f4..cc85a9b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -82,24 +82,24 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, * callers should be careful not to use the hash value outside the ipfrag_lock * as doing so could race with ipfrag_hash_rnd being recalculated. */ -unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, - const struct in6_addr *daddr, u32 rnd) +static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, + const struct in6_addr *daddr) { u32 c; + net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd)); c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), - (__force u32)id, rnd); + (__force u32)id, ip6_frags.rnd); return c & (INETFRAGS_HASHSZ - 1); } -EXPORT_SYMBOL_GPL(inet6_hash_frag); static unsigned int ip6_hashfn(struct inet_frag_queue *q) { struct frag_queue *fq; fq = container_of(q, struct frag_queue, q); - return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd); + return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr); } bool ip6_frag_match(struct inet_frag_queue *q, void *a) @@ -193,7 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, arg.ecn = ecn; read_lock(&ip6_frags.lock); - hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd); + hash = inet6_hash_frag(id, src, dst); q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); if (IS_ERR_OR_NULL(q)) { @@ -490,6 +490,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, ipv6_hdr(head)->payload_len = htons(payload_len); ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); IP6CB(head)->nhoff = nhoff; + IP6CB(head)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ if (head->ip_summed == CHECKSUM_COMPLETE) @@ -524,6 +525,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct net *net = dev_net(skb_dst(skb)->dev); int evicted; + if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) + goto fail_hdr; + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); /* Jumbo payload inhibits frag. header */ @@ -544,6 +548,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS); IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; return 1; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index adcaeca..1e19508 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -69,6 +69,12 @@ static ipv6_route_flush_hook *ipv6_route_flush_fn; #endif +enum rt6_nud_state { + RT6_NUD_FAIL_HARD = -2, + RT6_NUD_FAIL_SOFT = -1, + RT6_NUD_SUCCEED = 1 +}; + static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); @@ -87,6 +93,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); +static int rt6_score_route(struct rt6_info *rt, int oif, int strict); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -280,9 +287,8 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); - rt->rt6i_genid = rt_genid(net); + rt->rt6i_genid = rt_genid_ipv6(net); INIT_LIST_HEAD(&rt->rt6i_siblings); - rt->rt6i_nsiblings = 0; } return rt; } @@ -398,7 +404,8 @@ static int rt6_info_hash_nhsfn(unsigned int candidate_count, } static struct rt6_info *rt6_multipath_select(struct rt6_info *match, - struct flowi6 *fl6) + struct flowi6 *fl6, int oif, + int strict) { struct rt6_info *sibling, *next_sibling; int route_choosen; @@ -412,6 +419,8 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match, &match->rt6i_siblings, rt6i_siblings) { route_choosen--; if (route_choosen == 0) { + if (rt6_score_route(sibling, oif, strict) < 0) + break; match = sibling; break; } @@ -471,6 +480,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -494,17 +521,23 @@ static void rt6_probe(struct rt6_info *rt) if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (neigh) { + if (neigh && work) neigh->updated = jiffies; + + if (neigh) write_unlock(&neigh->lock); - } - target = (struct in6_addr *)&rt->rt6i_gateway; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { out: write_unlock(&neigh->lock); @@ -531,26 +564,29 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) return 0; } -static inline bool rt6_check_neigh(struct rt6_info *rt) +static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) { struct neighbour *neigh; - bool ret = false; + enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) - return true; + return RT6_NUD_SUCCEED; rcu_read_lock_bh(); neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (neigh) { read_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) - ret = true; + ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(neigh->nud_state & NUD_FAILED)) - ret = true; + ret = RT6_NUD_SUCCEED; #endif read_unlock(&neigh->lock); + } else { + ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? + RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT; } rcu_read_unlock_bh(); @@ -564,43 +600,52 @@ static int rt6_score_route(struct rt6_info *rt, int oif, m = rt6_check_dev(rt, oif); if (!m && (strict & RT6_LOOKUP_F_IFACE)) - return -1; + return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; #endif - if (!rt6_check_neigh(rt) && (strict & RT6_LOOKUP_F_REACHABLE)) - return -1; + if (strict & RT6_LOOKUP_F_REACHABLE) { + int n = rt6_check_neigh(rt); + if (n < 0) + return n; + } return m; } static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, - int *mpri, struct rt6_info *match) + int *mpri, struct rt6_info *match, + bool *do_rr) { int m; + bool match_do_rr = false; if (rt6_check_expired(rt)) goto out; m = rt6_score_route(rt, oif, strict); - if (m < 0) + if (m == RT6_NUD_FAIL_SOFT) { + match_do_rr = true; + m = 0; /* lowest valid score */ + } else if (m < 0) { goto out; + } + + if (strict & RT6_LOOKUP_F_REACHABLE) + rt6_probe(rt); if (m > *mpri) { - if (strict & RT6_LOOKUP_F_REACHABLE) - rt6_probe(match); + *do_rr = match_do_rr; *mpri = m; match = rt; - } else if (strict & RT6_LOOKUP_F_REACHABLE) { - rt6_probe(rt); } - out: return match; } static struct rt6_info *find_rr_leaf(struct fib6_node *fn, struct rt6_info *rr_head, - u32 metric, int oif, int strict) + u32 metric, int oif, int strict, + bool *do_rr) { struct rt6_info *rt, *match; int mpri = -1; @@ -608,10 +653,10 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; for (rt = rr_head; rt && rt->rt6i_metric == metric; rt = rt->dst.rt6_next) - match = find_match(rt, oif, strict, &mpri, match); + match = find_match(rt, oif, strict, &mpri, match, do_rr); for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; rt = rt->dst.rt6_next) - match = find_match(rt, oif, strict, &mpri, match); + match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } @@ -620,15 +665,16 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) { struct rt6_info *match, *rt0; struct net *net; + bool do_rr = false; rt0 = fn->rr_ptr; if (!rt0) fn->rr_ptr = rt0 = fn->leaf; - match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict); + match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + &do_rr); - if (!match && - (strict & RT6_LOOKUP_F_REACHABLE)) { + if (do_rr) { struct rt6_info *next = rt0->dst.rt6_next; /* no entries matched; do round-robin */ @@ -689,8 +735,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, prefix = &prefix_buf; } - rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, - dev->ifindex); + if (rinfo->prefix_len == 0) + rt = rt6_get_dflt_router(gwaddr, dev); + else + rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, + gwaddr, dev->ifindex); if (rt && !lifetime) { ip6_del_rt(rt); @@ -747,7 +796,7 @@ restart: rt = fn->leaf; rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(rt, fl6); + rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags); BACKTRACK(net, &fl6->saddr); out: dst_use(&rt->dst, jiffies); @@ -834,12 +883,9 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, rt = ip6_rt_copy(ort, daddr); if (rt) { - if (!(rt->rt6i_flags & RTF_GATEWAY)) { - if (ort->rt6i_dst.plen != 128 && - ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) - rt->rt6i_flags |= RTF_ANYCAST; - rt->rt6i_gateway = *daddr; - } + if (ort->rt6i_dst.plen != 128 && + ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) + rt->rt6i_flags |= RTF_ANYCAST; rt->rt6i_flags |= RTF_CACHE; @@ -884,8 +930,8 @@ restart_2: restart: rt = rt6_select(fn, oif, strict | reachable); - if (rt->rt6i_nsiblings && oif == 0) - rt = rt6_multipath_select(rt, fl6); + if (rt->rt6i_nsiblings) + rt = rt6_multipath_select(rt, fl6, oif, strict | reachable); BACKTRACK(net, &fl6->saddr); if (rt == net->ipv6.ip6_null_entry || rt->rt6i_flags & RTF_CACHE) @@ -1049,13 +1095,16 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) + if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) - return dst; + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; - return NULL; + if (rt6_check_expired(rt)) + return NULL; + + return dst; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -1084,10 +1133,13 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags & RTF_CACHE) - rt6_update_expires(rt, 0); - else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) + if (rt->rt6i_flags & RTF_CACHE) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; + } } } @@ -1122,7 +1174,6 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; fl6.flowi6_mark = mark; - fl6.flowi6_flags = 0; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; fl6.flowlabel = ip6_flowinfo(iph); @@ -1141,6 +1192,77 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); +/* Handle redirects */ +struct ip6rd_flowi { + struct flowi6 fl6; + struct in6_addr gateway; +}; + +static struct rt6_info *__ip6_route_redirect(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + int flags) +{ + struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; + struct rt6_info *rt; + struct fib6_node *fn; + + /* Get the "current" route for this destination and + * check if the redirect has come from approriate router. + * + * RFC 4861 specifies that redirects should only be + * accepted if they come from the nexthop to the target. + * Due to the way the routes are chosen, this notion + * is a bit fuzzy and one might need to check all possible + * routes. + */ + + read_lock_bh(&table->tb6_lock); + fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); +restart: + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if (rt6_check_expired(rt)) + continue; + if (rt->dst.error) + break; + if (!(rt->rt6i_flags & RTF_GATEWAY)) + continue; + if (fl6->flowi6_oif != rt->dst.dev->ifindex) + continue; + if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) + continue; + break; + } + + if (!rt) + rt = net->ipv6.ip6_null_entry; + else if (rt->dst.error) { + rt = net->ipv6.ip6_null_entry; + goto out; + } + BACKTRACK(net, &fl6->saddr); +out: + dst_hold(&rt->dst); + + read_unlock_bh(&table->tb6_lock); + + return rt; +}; + +static struct dst_entry *ip6_route_redirect(struct net *net, + const struct flowi6 *fl6, + const struct in6_addr *gateway) +{ + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct ip6rd_flowi rdfl; + + rdfl.fl6 = *fl6; + rdfl.gateway = *gateway; + + return fib6_rule_lookup(net, &rdfl.fl6, + flags, __ip6_route_redirect); +} + void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; @@ -1150,18 +1272,35 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; fl6.flowi6_mark = mark; - fl6.flowi6_flags = 0; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; fl6.flowlabel = ip6_flowinfo(iph); - dst = ip6_route_output(net, NULL, &fl6); - if (!dst->error) - rt6_do_redirect(dst, NULL, skb); + dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr); + rt6_do_redirect(dst, NULL, skb); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_redirect); +void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, + u32 mark) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb); + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.daddr = msg->dest; + fl6.saddr = iph->daddr; + + dst = ip6_route_redirect(net, &fl6, &iph->saddr); + rt6_do_redirect(dst, NULL, skb); + dst_release(dst); +} + void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark); @@ -1233,6 +1372,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; @@ -1295,7 +1435,6 @@ static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), static int ip6_dst_gc(struct dst_ops *ops) { - unsigned long now = jiffies; struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; @@ -1305,13 +1444,12 @@ static int ip6_dst_gc(struct dst_ops *ops) int entries; entries = dst_entries_get_fast(ops); - if (time_after(rt_last_gc + rt_min_interval, now) && + if (time_after(rt_last_gc + rt_min_interval, jiffies) && entries <= rt_max_size) goto out; net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net); - net->ipv6.ip6_rt_last_gc = now; + fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; @@ -1320,25 +1458,6 @@ out: return entries > rt_max_size; } -int ip6_dst_hoplimit(struct dst_entry *dst) -{ - int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); - if (hoplimit == 0) { - struct net_device *dev = dst->dev; - struct inet6_dev *idev; - - rcu_read_lock(); - idev = __in6_dev_get(dev); - if (idev) - hoplimit = idev->cnf.hop_limit; - else - hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit; - rcu_read_unlock(); - } - return hoplimit; -} -EXPORT_SYMBOL(ip6_dst_hoplimit); - /* * */ @@ -1665,7 +1784,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu int optlen, on_link; u8 *lladdr; - optlen = skb->tail - skb->transport_header; + optlen = skb_tail_pointer(skb) - skb_transport_header(skb); optlen -= sizeof(*msg); if (optlen < 0) { @@ -1795,7 +1914,10 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; + else + rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == (RTF_DEFAULT | RTF_ADDRCONF)) @@ -2082,6 +2204,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, else rt->rt6i_flags |= RTF_LOCAL; + rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); @@ -2697,9 +2820,9 @@ errout: } static int ip6_route_dev_notify(struct notifier_block *this, - unsigned long event, void *data) + unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { @@ -2722,56 +2845,12 @@ static int ip6_route_dev_notify(struct notifier_block *this, #ifdef CONFIG_PROC_FS -struct rt6_proc_arg -{ - char *buffer; - int offset; - int length; - int skip; - int len; -}; - -static int rt6_info_route(struct rt6_info *rt, void *p_arg) -{ - struct seq_file *m = p_arg; - - seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); - -#ifdef CONFIG_IPV6_SUBTREES - seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); -#else - seq_puts(m, "00000000000000000000000000000000 00 "); -#endif - if (rt->rt6i_flags & RTF_GATEWAY) { - seq_printf(m, "%pi6", &rt->rt6i_gateway); - } else { - seq_puts(m, "00000000000000000000000000000000"); - } - seq_printf(m, " %08x %08x %08x %08x %8s\n", - rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), - rt->dst.__use, rt->rt6i_flags, - rt->dst.dev ? rt->dst.dev->name : ""); - return 0; -} - -static int ipv6_route_show(struct seq_file *m, void *v) -{ - struct net *net = (struct net *)m->private; - fib6_clean_all_ro(net, rt6_info_route, 0, m); - return 0; -} - -static int ipv6_route_open(struct inode *inode, struct file *file) -{ - return single_open_net(inode, file, ipv6_route_show); -} - static const struct file_operations ipv6_route_proc_fops = { .owner = THIS_MODULE, .open = ipv6_route_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release_net, + .release = seq_release_net, }; static int rt6_stats_seq_show(struct seq_file *seq, void *v) @@ -2806,7 +2885,7 @@ static const struct file_operations rt6_stats_seq_fops = { #ifdef CONFIG_SYSCTL static -int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, +int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net; @@ -2817,11 +2896,11 @@ int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; proc_dointvec(ctl, write, buffer, lenp, ppos); - fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); + fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } -ctl_table ipv6_route_table_template[] = { +struct ctl_table ipv6_route_table_template[] = { { .procname = "flush", .data = &init_net.ipv6.sysctl.flush_delay, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3353634..366fbba 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -466,26 +466,56 @@ isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t) static void ipip6_tunnel_uninit(struct net_device *dev) { - struct net *net = dev_net(dev); - struct sit_net *sitn = net_generic(net, sit_net_id); + struct ip_tunnel *tunnel = netdev_priv(dev); + struct sit_net *sitn = net_generic(tunnel->net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL); } else { - ipip6_tunnel_unlink(sitn, netdev_priv(dev)); - ipip6_tunnel_del_prl(netdev_priv(dev), NULL); + ipip6_tunnel_unlink(sitn, tunnel); + ipip6_tunnel_del_prl(tunnel, NULL); } dev_put(dev); } +/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH + * if sufficient data bytes are available + */ +static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct rt6_info *rt; + struct sk_buff *skb2; + + if (!pskb_may_pull(skb, iph->ihl * 4 + sizeof(struct ipv6hdr) + 8)) + return 1; + + skb2 = skb_clone(skb, GFP_ATOMIC); + + if (!skb2) + return 1; + + skb_dst_drop(skb2); + skb_pull(skb2, iph->ihl * 4); + skb_reset_network_header(skb2); + + rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0); + + if (rt && rt->dst.dev) + skb2->dev = rt->dst.dev; + + icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); + + if (rt) + ip6_rt_put(rt); + + kfree_skb(skb2); + + return 0; +} static int ipip6_err(struct sk_buff *skb, u32 info) { - -/* All the routers (except for Linux) return only - 8 bytes of packet payload. It means, that precise relaying of - ICMP in the real Internet is absolutely infeasible. - */ const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; @@ -500,7 +530,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: - case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; default: @@ -545,6 +574,9 @@ static int ipip6_err(struct sk_buff *skb, u32 info) goto out; err = 0; + if (!ipip6_err_gen_icmpv6_unreach(skb)) + goto out; + if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; @@ -566,6 +598,70 @@ static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, return false; } +/* Checks if an address matches an address on the tunnel interface. + * Used to detect the NAT of proto 41 packets and let them pass spoofing test. + * Long story: + * This function is called after we considered the packet as spoofed + * in is_spoofed_6rd. + * We may have a router that is doing NAT for proto 41 packets + * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb + * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd + * function will return true, dropping the packet. + * But, we can still check if is spoofed against the IP + * addresses associated with the interface. + */ +static bool only_dnatted(const struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + int prefix_len; + +#ifdef CONFIG_IPV6_SIT_6RD + prefix_len = tunnel->ip6rd.prefixlen + 32 + - tunnel->ip6rd.relay_prefixlen; +#else + prefix_len = 48; +#endif + return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); +} + +/* Returns true if a packet is spoofed */ +static bool packet_is_spoofed(struct sk_buff *skb, + const struct iphdr *iph, + struct ip_tunnel *tunnel) +{ + const struct ipv6hdr *ipv6h; + + if (tunnel->dev->priv_flags & IFF_ISATAP) { + if (!isatap_chksrc(skb, iph, tunnel)) + return true; + + return false; + } + + if (tunnel->dev->flags & IFF_POINTOPOINT) + return false; + + ipv6h = ipv6_hdr(skb); + + if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { + net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; + } + + if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) + return false; + + if (only_dnatted(tunnel, &ipv6h->daddr)) + return false; + + net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; +} + static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); @@ -577,29 +673,21 @@ static int ipip6_rcv(struct sk_buff *skb) if (tunnel != NULL) { struct pcpu_tstats *tstats; - secpath_reset(skb); + if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && + tunnel->parms.iph.protocol != 0) + goto out; + skb->mac_header = skb->network_header; skb_reset_network_header(skb); IPCB(skb)->flags = 0; skb->protocol = htons(ETH_P_IPV6); - skb->pkt_type = PACKET_HOST; - if (tunnel->dev->priv_flags & IFF_ISATAP) { - if (!isatap_chksrc(skb, iph, tunnel)) { - tunnel->dev->stats.rx_errors++; - goto out; - } - } else { - if (is_spoofed_6rd(tunnel, iph->saddr, - &ipv6_hdr(skb)->saddr) || - is_spoofed_6rd(tunnel, iph->daddr, - &ipv6_hdr(skb)->daddr)) { - tunnel->dev->stats.rx_errors++; - goto out; - } + if (packet_is_spoofed(skb, iph, tunnel)) { + tunnel->dev->stats.rx_errors++; + goto out; } - __skb_tunnel_rx(skb, tunnel->dev); + __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { @@ -629,6 +717,38 @@ out: return 0; } +static const struct tnl_ptk_info tpi = { + /* no tunnel info required for ipip. */ + .proto = htons(ETH_P_IP), +}; + +static int ipip_rcv(struct sk_buff *skb) +{ + const struct iphdr *iph; + struct ip_tunnel *tunnel; + + iph = ip_hdr(skb); + tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, + iph->saddr, iph->daddr); + if (tunnel != NULL) { + if (tunnel->parms.iph.protocol != IPPROTO_IPIP && + tunnel->parms.iph.protocol != 0) + goto drop; + + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + if (iptunnel_pull_header(skb, 0, tpi.proto)) + goto drop; + return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + } + + return 1; + +drop: + kfree_skb(skb); + return 0; +} + /* * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function * stores the embedded IPv4 address in v4dst and returns true. @@ -690,13 +810,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ - struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; struct flowi4 fl4; int mtu; const struct in6_addr *addr6; int addr_type; + u8 ttl; + int err; if (skb->protocol != htons(ETH_P_IPV6)) goto tx_error; @@ -713,7 +834,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -742,7 +863,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -764,7 +885,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } - rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, + rt = ip_route_output_ports(tunnel->net, &fl4, NULL, dst, tiph->saddr, 0, 0, IPPROTO_IPV6, RT_TOS(tos), @@ -830,7 +951,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (!new_skb) { ip_rt_put(rt); dev->stats.tx_dropped++; - dev_kfree_skb(skb); + kfree_skb(skb); return NETDEV_TX_OK; } if (skb->sk) @@ -839,44 +960,68 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb = new_skb; iph6 = ipv6_hdr(skb); } + ttl = tiph->ttl; + if (ttl == 0) + ttl = iph6->hop_limit; + tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); - skb->transport_header = skb->network_header; - skb_push(skb, sizeof(struct iphdr)); - skb_reset_network_header(skb); - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags = 0; - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - - /* - * Push down and install the IPIP header. - */ + skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT); + if (IS_ERR(skb)) + goto out; - iph = ip_hdr(skb); - iph->version = 4; - iph->ihl = sizeof(struct iphdr)>>2; - iph->frag_off = df; - iph->protocol = IPPROTO_IPV6; - iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); - iph->daddr = fl4.daddr; - iph->saddr = fl4.saddr; - - if ((iph->ttl = tiph->ttl) == 0) - iph->ttl = iph6->hop_limit; - - skb->ip_summed = CHECKSUM_NONE; - ip_select_ident(iph, skb_dst(skb), NULL); - iptunnel_xmit(skb, dev); + err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos, + ttl, df, !net_eq(tunnel->net, dev_net(dev))); + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: + kfree_skb(skb); +out: + dev->stats.tx_errors++; + return NETDEV_TX_OK; +} + +static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + const struct iphdr *tiph = &tunnel->parms.iph; + + skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP); + if (IS_ERR(skb)) + goto out; + + ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP); + return NETDEV_TX_OK; +out: dev->stats.tx_errors++; - dev_kfree_skb(skb); return NETDEV_TX_OK; } +static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + switch (skb->protocol) { + case htons(ETH_P_IP): + ipip_tunnel_xmit(skb, dev); + break; + case htons(ETH_P_IPV6): + ipip6_tunnel_xmit(skb, dev); + break; + default: + goto tx_err; + } + + return NETDEV_TX_OK; + +tx_err: + dev->stats.tx_errors++; + kfree_skb(skb); + return NETDEV_TX_OK; + +} + static void ipip6_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; @@ -888,7 +1033,8 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) iph = &tunnel->parms.iph; if (iph->daddr) { - struct rtable *rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, + struct rtable *rt = ip_route_output_ports(tunnel->net, &fl4, + NULL, iph->daddr, iph->saddr, 0, 0, IPPROTO_IPV6, @@ -903,7 +1049,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) } if (!tdev && tunnel->parms.link) - tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link); + tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev) { dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); @@ -916,7 +1062,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) { - struct net *net = dev_net(t->dev); + struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); ipip6_tunnel_unlink(sitn, t); @@ -1027,7 +1173,11 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; err = -EINVAL; - if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPV6 || + if (p.iph.protocol != IPPROTO_IPV6 && + p.iph.protocol != IPPROTO_IPIP && + p.iph.protocol != 0) + goto done; + if (p.iph.version != 4 || p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF))) goto done; if (p.iph.ttl) @@ -1164,7 +1314,7 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ipip6_netdev_ops = { .ndo_uninit = ipip6_tunnel_uninit, - .ndo_start_xmit = ipip6_tunnel_xmit, + .ndo_start_xmit = sit_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, .ndo_change_mtu = ipip6_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, @@ -1176,6 +1326,12 @@ static void ipip6_dev_free(struct net_device *dev) free_netdev(dev); } +#define SIT_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | \ + NETIF_F_GSO_SOFTWARE | \ + NETIF_F_HW_CSUM) + static void ipip6_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip6_netdev_ops; @@ -1188,15 +1344,18 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->iflink = 0; dev->addr_len = 4; - dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; + dev->features |= SIT_FEATURES; + dev->hw_features |= SIT_FEATURES; } static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); + int i; tunnel->dev = dev; + tunnel->net = dev_net(dev); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); @@ -1206,6 +1365,12 @@ static int ipip6_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + for_each_possible_cpu(i) { + struct pcpu_tstats *ipip6_tunnel_stats; + ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i); + u64_stats_init(&ipip6_tunnel_stats->syncp); + } + return 0; } @@ -1215,8 +1380,10 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) struct iphdr *iph = &tunnel->parms.iph; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); + int i; tunnel->dev = dev; + tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); iph->version = 4; @@ -1227,11 +1394,34 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) dev->tstats = alloc_percpu(struct pcpu_tstats); if (!dev->tstats) return -ENOMEM; + + for_each_possible_cpu(i) { + struct pcpu_tstats *ipip6_fb_stats; + ipip6_fb_stats = per_cpu_ptr(dev->tstats, i); + u64_stats_init(&ipip6_fb_stats->syncp); + } + dev_hold(dev); rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); return 0; } +static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + u8 proto; + + if (!data || !data[IFLA_IPTUN_PROTO]) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPV6 && + proto != IPPROTO_IPIP && + proto != 0) + return -EINVAL; + + return 0; +} + static void ipip6_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm *parms) { @@ -1268,6 +1458,10 @@ static void ipip6_netlink_parms(struct nlattr *data[], if (data[IFLA_IPTUN_FLAGS]) parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); + } #ifdef CONFIG_IPV6_SIT_6RD @@ -1339,9 +1533,9 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct ip_tunnel *t; + struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; - struct net *net = dev_net(dev); + struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; @@ -1391,6 +1585,8 @@ static size_t ipip6_get_size(const struct net_device *dev) nla_total_size(1) + /* IFLA_IPTUN_FLAGS */ nla_total_size(2) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + #ifdef CONFIG_IPV6_SIT_6RD /* IFLA_IPTUN_6RD_PREFIX */ nla_total_size(sizeof(struct in6_addr)) + @@ -1416,6 +1612,7 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags)) goto nla_put_failure; @@ -1445,6 +1642,7 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, #ifdef CONFIG_IPV6_SIT_6RD [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, @@ -1453,16 +1651,27 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { #endif }; +static void ipip6_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + + if (dev != sitn->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + static struct rtnl_link_ops sit_link_ops __read_mostly = { .kind = "sit", .maxtype = IFLA_IPTUN_MAX, .policy = ipip6_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipip6_tunnel_setup, + .validate = ipip6_validate, .newlink = ipip6_newlink, .changelink = ipip6_changelink, .get_size = ipip6_get_size, .fill_info = ipip6_fill_info, + .dellink = ipip6_dellink, }; static struct xfrm_tunnel sit_handler __read_mostly = { @@ -1471,10 +1680,23 @@ static struct xfrm_tunnel sit_handler __read_mostly = { .priority = 1, }; -static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = ipip_rcv, + .err_handler = ipip6_err, + .priority = 2, +}; + +static void __net_exit sit_destroy_tunnels(struct net *net, + struct list_head *head) { + struct sit_net *sitn = net_generic(net, sit_net_id); + struct net_device *dev, *aux; int prio; + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &sit_link_ops) + unregister_netdevice_queue(dev, head); + for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { @@ -1482,7 +1704,12 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea t = rtnl_dereference(sitn->tunnels[prio][h]); while (t != NULL) { - unregister_netdevice_queue(t->dev, head); + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, + head); t = rtnl_dereference(t->next); } } @@ -1507,6 +1734,11 @@ static int __net_init sit_init_net(struct net *net) goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); + sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; + /* FB netdevice is special: we have one, and only one per netns. + * Allowing to move it to another netns is clearly unsafe. + */ + sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); if (err) @@ -1532,12 +1764,10 @@ err_alloc_dev: static void __net_exit sit_exit_net(struct net *net) { - struct sit_net *sitn = net_generic(net, sit_net_id); LIST_HEAD(list); rtnl_lock(); - sit_destroy_tunnels(sitn, &list); - unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); + sit_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } @@ -1553,6 +1783,7 @@ static void __exit sit_cleanup(void) { rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); unregister_pernet_device(&sit_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ @@ -1569,9 +1800,14 @@ static int __init sit_init(void) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { - pr_info("%s: can't add protocol\n", __func__); + pr_info("%s: can't register ip6ip4\n", __func__); goto xfrm_tunnel_failed; } + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: can't register ip4ip4\n", __func__); + goto xfrm_tunnel4_failed; + } err = rtnl_link_register(&sit_link_ops); if (err < 0) goto rtnl_link_failed; @@ -1580,6 +1816,8 @@ out: return err; rtnl_link_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel4_failed: xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm_tunnel_failed: unregister_pernet_device(&sit_net_ops); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index d5dda20..535a3ad 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -24,26 +24,23 @@ #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) -/* Table must be sorted. */ +static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS]; + +/* RFC 2460, Section 8.3: + * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..] + * + * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows + * using higher values than ipv4 tcp syncookies. + * The other values are chosen based on ethernet (1500 and 9k MTU), plus + * one that accounts for common encap (PPPoe) overhead. Table must be sorted. + */ static __u16 const msstab[] = { - 64, - 512, - 536, - 1280 - 60, + 1280 - 60, /* IPV6_MIN_MTU - 60 */ 1480 - 60, 1500 - 60, - 4460 - 60, 9000 - 60, }; -/* - * This (misnamed) value is the age of syncookie which is permitted. - * Its ideal value should be dependent on TCP_TIMEOUT_INIT and - * sysctl_tcp_retries1. It's a rather complicated formula (exponential - * backoff) to compute at runtime so it's currently hardcoded here. - */ -#define COUNTER_TRIES 4 - static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) @@ -66,14 +63,18 @@ static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, u32 count, int c) { - __u32 *tmp = __get_cpu_var(ipv6_cookie_scratch); + __u32 *tmp; + + net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret)); + + tmp = __get_cpu_var(ipv6_cookie_scratch); /* * we have 320 bits of information to hash, copy in the remaining - * 192 bits required for sha_transform, from the syncookie_secret + * 192 bits required for sha_transform, from the syncookie6_secret * and overwrite the digest with the secret */ - memcpy(tmp + 10, syncookie_secret[c], 44); + memcpy(tmp + 10, syncookie6_secret[c], 44); memcpy(tmp, saddr, 16); memcpy(tmp + 4, daddr, 16); tmp[8] = ((__force u32)sport << 16) + (__force u32)dport; @@ -86,8 +87,9 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, __u32 sseq, - __u32 count, __u32 data) + __u32 data) { + u32 count = tcp_cookie_time(); return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq + (count << COOKIEBITS) + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) @@ -96,15 +98,14 @@ static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, - __be16 dport, __u32 sseq, __u32 count, - __u32 maxdiff) + __be16 dport, __u32 sseq) { - __u32 diff; + __u32 diff, count = tcp_cookie_time(); cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); - if (diff >= maxdiff) + if (diff >= MAX_SYNCOOKIE_AGE) return (__u32)-1; return (cookie - @@ -112,45 +113,49 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, & COOKIEMASK; } -__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mssp) +u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, + const struct tcphdr *th, __u16 *mssp) { - const struct ipv6hdr *iph = ipv6_hdr(skb); - const struct tcphdr *th = tcp_hdr(skb); int mssind; const __u16 mss = *mssp; - tcp_synq_overflow(sk); - for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--) if (mss >= msstab[mssind]) break; *mssp = msstab[mssind]; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); - return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source, - th->dest, ntohl(th->seq), - jiffies / (HZ * 60), mssind); + th->dest, ntohl(th->seq), mssind); } +EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence); -static inline int cookie_check(const struct sk_buff *skb, __u32 cookie) +__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mssp) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); + + tcp_synq_overflow(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); + + return __cookie_v6_init_sequence(iph, th, mssp); +} + +int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, + __u32 cookie) +{ __u32 seq = ntohl(th->seq) - 1; __u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, - th->source, th->dest, seq, - jiffies / (HZ * 60), COUNTER_TRIES); + th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } +EXPORT_SYMBOL_GPL(__cookie_v6_check); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) { struct tcp_options_received tcp_opt; struct inet_request_sock *ireq; - struct inet6_request_sock *ireq6; struct tcp_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -167,7 +172,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; if (tcp_synq_no_recent_overflow(sk) || - (mss = cookie_check(skb, cookie)) == 0) { + (mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie)) == 0) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED); goto out; } @@ -187,7 +192,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ireq = inet_rsk(req); - ireq6 = inet6_rsk(req); treq = tcp_rsk(req); treq->listener = NULL; @@ -195,22 +199,22 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out_free; req->mss = mss; - ireq->rmt_port = th->source; - ireq->loc_port = th->dest; - ireq6->rmt_addr = ipv6_hdr(skb)->saddr; - ireq6->loc_addr = ipv6_hdr(skb)->daddr; + ireq->ir_rmt_port = th->source; + ireq->ir_num = ntohs(th->dest); + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { atomic_inc(&skb->users); - ireq6->pktopts = skb; + ireq->pktopts = skb; } - ireq6->iif = sk->sk_bound_dev_if; + ireq->ir_iif = sk->sk_bound_dev_if; /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && - ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL) - ireq6->iif = inet6_iif(skb); + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = inet6_iif(skb); req->expires = 0UL; req->num_retrans = 0; @@ -234,12 +238,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = ireq6->rmt_addr; + fl6.daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(&fl6, np->opt, &final); - fl6.saddr = ireq6->loc_addr; + fl6.saddr = ireq->ir_v6_loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_dport = inet_rsk(req)->rmt_port; + fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = inet_sk(sk)->inet_sport; security_req_classify_flow(req, flowi6_to_flowi(&fl6)); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index e85c48b..107b2f1 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,7 +16,7 @@ #include <net/addrconf.h> #include <net/inet_frag.h> -static ctl_table ipv6_table_template[] = { +static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, @@ -27,7 +27,7 @@ static ctl_table ipv6_table_template[] = { { } }; -static ctl_table ipv6_rotable[] = { +static struct ctl_table ipv6_rotable[] = { { .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0a17ed9..0740f93 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -63,6 +63,7 @@ #include <net/inet_common.h> #include <net/secure_seq.h> #include <net/tcp_memcontrol.h> +#include <net/busy_poll.h> #include <asm/uaccess.h> @@ -191,13 +192,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (tp->rx_opt.ts_recent_stamp && - !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) { + !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; tp->write_seq = 0; } - np->daddr = usin->sin6_addr; + sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* @@ -236,17 +237,17 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } else { ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, - &np->rcv_saddr); + &sk->sk_v6_rcv_saddr); } return err; } - if (!ipv6_addr_any(&np->rcv_saddr)) - saddr = &np->rcv_saddr; + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; @@ -265,7 +266,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (saddr == NULL) { saddr = &fl6.saddr; - np->rcv_saddr = *saddr; + sk->sk_v6_rcv_saddr = *saddr; } /* set the source address */ @@ -278,7 +279,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, rt = (struct rt6_info *) dst; if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) + ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr)) tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; @@ -297,7 +298,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, - np->daddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); @@ -464,7 +465,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, u16 queue_mapping) { - struct inet6_request_sock *treq = inet6_rsk(req); + struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff * skb; int err = -ENOMEM; @@ -476,9 +477,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, NULL); if (skb) { - __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); + __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, + &ireq->ir_v6_rmt_addr); - fl6->daddr = treq->rmt_addr; + fl6->daddr = ireq->ir_v6_rmt_addr; skb_set_queue_mapping(skb, queue_mapping); err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); err = net_xmit_eval(err); @@ -501,7 +503,7 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req) static void tcp_v6_reqsk_destructor(struct request_sock *req) { - kfree_skb(inet6_rsk(req)->pktopts); + kfree_skb(inet_rsk(req)->pktopts); } #ifdef CONFIG_TCP_MD5SIG @@ -514,13 +516,13 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, struct sock *addr_sk) { - return tcp_v6_md5_do_lookup(sk, &inet6_sk(addr_sk)->daddr); + return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, struct request_sock *req) { - return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr); + return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr); } static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, @@ -620,10 +622,10 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, if (sk) { saddr = &inet6_sk(sk)->saddr; - daddr = &inet6_sk(sk)->daddr; + daddr = &sk->sk_v6_daddr; } else if (req) { - saddr = &inet6_rsk(req)->loc_addr; - daddr = &inet6_rsk(req)->rmt_addr; + saddr = &inet_rsk(req)->ir_v6_loc_addr; + daddr = &inet_rsk(req)->ir_v6_rmt_addr; } else { const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; @@ -948,7 +950,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_options_received tmp_opt; struct request_sock *req; - struct inet6_request_sock *treq; + struct inet_request_sock *ireq; struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); __u32 isn = TCP_SKB_CB(skb)->when; @@ -962,7 +964,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { + if ((sysctl_tcp_syncookies == 2 || + inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6"); if (!want_cookie) goto drop; @@ -992,25 +995,25 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb); - treq = inet6_rsk(req); - treq->rmt_addr = ipv6_hdr(skb)->saddr; - treq->loc_addr = ipv6_hdr(skb)->daddr; + ireq = inet_rsk(req); + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; if (!want_cookie || tmp_opt.tstamp_ok) TCP_ECN_create_request(req, skb, sock_net(sk)); - treq->iif = sk->sk_bound_dev_if; + ireq->ir_iif = sk->sk_bound_dev_if; /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && - ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) - treq->iif = inet6_iif(skb); + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = inet6_iif(skb); if (!isn) { if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { atomic_inc(&skb->users); - treq->pktopts = skb; + ireq->pktopts = skb; } if (want_cookie) { @@ -1049,7 +1052,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) * to the moment of synflood. */ LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n", - &treq->rmt_addr, ntohs(tcp_hdr(skb)->source)); + &ireq->ir_v6_rmt_addr, ntohs(tcp_hdr(skb)->source)); goto drop_and_release; } @@ -1084,7 +1087,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { - struct inet6_request_sock *treq; + struct inet_request_sock *ireq; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; @@ -1114,11 +1117,11 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - newnp->rcv_saddr = newnp->saddr; + newsk->sk_v6_rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1149,7 +1152,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, return newsk; } - treq = inet6_rsk(req); + ireq = inet_rsk(req); if (sk_acceptq_is_full(sk)) goto out_overflow; @@ -1183,10 +1186,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - newnp->daddr = treq->rmt_addr; - newnp->saddr = treq->loc_addr; - newnp->rcv_saddr = treq->loc_addr; - newsk->sk_bound_dev_if = treq->iif; + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; + newnp->saddr = ireq->ir_v6_loc_addr; + newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; + newsk->sk_bound_dev_if = ireq->ir_iif; /* Now IPv6 options... @@ -1201,11 +1204,11 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; - if (treq->pktopts != NULL) { - newnp->pktoptions = skb_clone(treq->pktopts, + if (ireq->pktopts != NULL) { + newnp->pktoptions = skb_clone(ireq->pktopts, sk_gfp_atomic(sk, GFP_ATOMIC)); - consume_skb(treq->pktopts); - treq->pktopts = NULL; + consume_skb(ireq->pktopts); + ireq->pktopts = NULL; if (newnp->pktoptions) skb_set_owner_r(newnp->pktoptions, newsk); } @@ -1236,21 +1239,19 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->num_retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - if ((key = tcp_v6_md5_do_lookup(sk, &newnp->daddr)) != NULL) { + if ((key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr)) != NULL) { /* We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr, + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, AF_INET6, key->key, key->keylen, sk_gfp_atomic(sk, GFP_ATOMIC)); } @@ -1360,8 +1361,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } } - if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) - goto reset; + tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len); if (opt_skb) goto ipv6_pktoptions; return 0; @@ -1426,7 +1426,7 @@ ipv6_pktoptions: if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; if (np->rxopt.bits.rxtclass) - np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); @@ -1498,6 +1498,7 @@ process: if (sk_filter(sk, skb)) goto discard_and_relse; + sk_mark_napi_id(sk, skb); skb->dev = NULL; bh_lock_sock_nested(sk); @@ -1722,22 +1723,22 @@ static void get_openreq6(struct seq_file *seq, const struct sock *sk, struct request_sock *req, int i, kuid_t uid) { int ttd = req->expires - jiffies; - const struct in6_addr *src = &inet6_rsk(req)->loc_addr; - const struct in6_addr *dest = &inet6_rsk(req)->rmt_addr; + const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; + const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; if (ttd < 0) ttd = 0; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], - ntohs(inet_rsk(req)->loc_port), + inet_rsk(req)->ir_num, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], - ntohs(inet_rsk(req)->rmt_port), + ntohs(inet_rsk(req)->ir_rmt_port), TCP_SYN_RECV, 0,0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ @@ -1758,10 +1759,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); - const struct ipv6_pinfo *np = inet6_sk(sp); - dest = &np->daddr; - src = &np->rcv_saddr; + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; destp = ntohs(inet->inet_dport); srcp = ntohs(inet->inet_sport); @@ -1781,7 +1781,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %lu %lu %u %u %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, @@ -1810,11 +1810,10 @@ static void get_timewait6_sock(struct seq_file *seq, { const struct in6_addr *dest, *src; __u16 destp, srcp; - const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); - long delta = tw->tw_ttd - jiffies; + s32 delta = tw->tw_ttd - inet_tw_time_stamp(); - dest = &tw6->tw_v6_daddr; - src = &tw6->tw_v6_rcv_saddr; + dest = &tw->tw_v6_daddr; + src = &tw->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); @@ -1834,6 +1833,7 @@ static void get_timewait6_sock(struct seq_file *seq, static int tcp6_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; + struct sock *sk = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -1849,14 +1849,14 @@ static int tcp6_seq_show(struct seq_file *seq, void *v) switch (st->state) { case TCP_SEQ_STATE_LISTENING: case TCP_SEQ_STATE_ESTABLISHED: - get_tcp6_sock(seq, v, st->num); + if (sk->sk_state == TCP_TIME_WAIT) + get_timewait6_sock(seq, v, st->num); + else + get_tcp6_sock(seq, v, st->num); break; case TCP_SEQ_STATE_OPENREQ: get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid); break; - case TCP_SEQ_STATE_TIME_WAIT: - get_timewait6_sock(seq, v, st->num); - break; } out: return 0; @@ -1924,10 +1924,12 @@ struct proto tcpv6_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, + .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem = sysctl_tcp_wmem, .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 2ec6bf6..6d18157 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -37,34 +37,32 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, { const struct ipv6hdr *iph = skb_gro_network_header(skb); __wsum wsum; - __sum16 sum; + + /* Don't bother verifying checksum if we're going to flush anyway. */ + if (NAPI_GRO_CB(skb)->flush) + goto skip_csum; + + wsum = skb->csum; switch (skb->ip_summed) { + case CHECKSUM_NONE: + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), + wsum); + + /* fall through */ + case CHECKSUM_COMPLETE: if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, - skb->csum)) { + wsum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } -flush: + NAPI_GRO_CB(skb)->flush = 1; return NULL; - - case CHECKSUM_NONE: - wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), - IPPROTO_TCP, 0)); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; } +skip_csum: return tcp_gro_receive(head, skb); } @@ -83,7 +81,7 @@ static int tcp6_gro_complete(struct sk_buff *skb) static const struct net_offload tcpv6_offload = { .callbacks = { .gso_send_check = tcp_v6_gso_send_check, - .gso_segment = tcp_tso_segment, + .gso_segment = tcp_gso_segment, .gro_receive = tcp6_gro_receive, .gro_complete = tcp6_gro_complete, }, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 42923b1..bcd5699 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -46,28 +46,49 @@ #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/inet6_hashtables.h> +#include <net/busy_poll.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <trace/events/skb.h> #include "udp_impl.h" +static unsigned int udp6_ehashfn(struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) +{ + static u32 udp6_ehash_secret __read_mostly; + static u32 udp_ipv6_hash_secret __read_mostly; + + u32 lhash, fhash; + + net_get_random_once(&udp6_ehash_secret, + sizeof(udp6_ehash_secret)); + net_get_random_once(&udp_ipv6_hash_secret, + sizeof(udp_ipv6_hash_secret)); + + lhash = (__force u32)laddr->s6_addr32[3]; + fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); + + return __inet6_ehashfn(lhash, lport, fhash, fport, + udp_ipv6_hash_secret + net_hash_mix(net)); +} + int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { - const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - __be32 sk1_rcv_saddr = sk_rcv_saddr(sk); - __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); - int addr_type = ipv6_addr_type(sk_rcv_saddr6); + int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; /* if both are mapped, treat as IPv4 */ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) return (!sk2_ipv6only && - (!sk1_rcv_saddr || !sk2_rcv_saddr || - sk1_rcv_saddr == sk2_rcv_saddr)); + (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr || + sk->sk_rcv_saddr == sk2->sk_rcv_saddr)); if (addr_type2 == IPV6_ADDR_ANY && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) @@ -78,7 +99,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 1; if (sk2_rcv_saddr6 && - ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6)) + ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6)) return 1; return 0; @@ -106,7 +127,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) unsigned int hash2_nulladdr = udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum); unsigned int hash2_partial = - udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0); + udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; @@ -116,7 +137,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) static void udp_v6_rehash(struct sock *sk) { u16 new_hash = udp6_portaddr_hash(sock_net(sk), - &inet6_sk(sk)->rcv_saddr, + &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); @@ -132,7 +153,6 @@ static inline int compute_score(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); score = 0; @@ -141,13 +161,13 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score++; } - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; score++; } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) return -1; score++; } @@ -170,10 +190,9 @@ static inline int compute_score2(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; score = 0; if (inet->inet_dport) { @@ -181,8 +200,8 @@ static inline int compute_score2(struct sock *sk, struct net *net, return -1; score++; } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) return -1; score++; } @@ -218,8 +237,8 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - hash = inet6_ehashfn(net, daddr, hnum, - saddr, sport); + hash = udp6_ehashfn(net, daddr, hnum, + saddr, sport); matches = 1; } else if (score == SCORE2_MAX) goto exact_match; @@ -299,8 +318,8 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - hash = inet6_ehashfn(net, daddr, hnum, - saddr, sport); + hash = udp6_ehashfn(net, daddr, hnum, + saddr, sport); matches = 1; } } else if (score == badness && reuseport) { @@ -373,14 +392,11 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, int is_udp4; bool slow; - if (addr_len) - *addr_len = sizeof(struct sockaddr_in6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -461,7 +477,7 @@ try_again: ipv6_iface_scope_id(&sin6->sin6_addr, IP6CB(skb)->iif); } - + *addr_len = sizeof(*sin6); } if (is_udp4) { if (inet->cmsg_flags) @@ -524,8 +540,10 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == ICMPV6_PKT_TOOBIG) ip6_sk_update_pmtu(skb, sk, info); - if (type == NDISC_REDIRECT) + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + goto out; + } np = inet6_sk(sk); @@ -548,8 +566,10 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; - if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { sock_rps_save_rxhash(sk, skb); + sk_mark_napi_id(sk, skb); + } rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { @@ -687,20 +707,19 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, if (udp_sk(s)->udp_port_hash == num && s->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(s); if (inet->inet_dport) { if (inet->inet_dport != rmt_port) continue; } - if (!ipv6_addr_any(&np->daddr) && - !ipv6_addr_equal(&np->daddr, rmt_addr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif) continue; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) continue; } if (!inet6_mc_check(s, loc_addr, rmt_addr)) @@ -841,7 +860,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk != NULL) { - int ret = udpv6_queue_rcv_skb(sk, skb); + int ret; + + ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); /* a return value > 0 means to resubmit the input, but @@ -955,11 +976,16 @@ static int udp_v6_push_pending_frames(struct sock *sk) struct udphdr *uh; struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); - struct flowi6 *fl6 = &inet->cork.fl.u.ip6; + struct flowi6 *fl6; int err = 0; int is_udplite = IS_UDPLITE(sk); __wsum csum = 0; + if (up->pending == AF_INET) + return udp_push_pending_frames(sk); + + fl6 = &inet->cork.fl.u.ip6; + /* Grab the skbuff where UDP header space exists. */ if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) goto out; @@ -1053,7 +1079,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, } else if (!up->pending) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; } else daddr = NULL; @@ -1123,8 +1149,8 @@ do_udp_sendmsg: * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; + ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) + daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && @@ -1135,7 +1161,7 @@ do_udp_sendmsg: return -EDESTADDRREQ; fl6.fl6_dport = inet->inet_dport; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; connected = 1; } @@ -1214,9 +1240,6 @@ do_udp_sendmsg: if (tclass < 0) tclass = np->tclass; - if (dontfrag < 0) - dontfrag = np->dontfrag; - if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: @@ -1235,6 +1258,8 @@ back_from_confirm: up->pending = AF_INET6; do_append_data: + if (dontfrag < 0) + dontfrag = np->dontfrag; up->len += ulen; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, @@ -1251,8 +1276,8 @@ do_append_data: if (dst) { if (connected) { ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &np->daddr) ? - &np->daddr : NULL, + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6.saddr, &np->saddr) ? &np->saddr : @@ -1359,48 +1384,17 @@ static const struct inet6_protocol udpv6_protocol = { /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS - -static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket) -{ - struct inet_sock *inet = inet_sk(sp); - struct ipv6_pinfo *np = inet6_sk(sp); - const struct in6_addr *dest, *src; - __u16 destp, srcp; - - dest = &np->daddr; - src = &np->rcv_saddr; - destp = ntohs(inet->inet_dport); - srcp = ntohs(inet->inet_sport); - seq_printf(seq, - "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", - bucket, - src->s6_addr32[0], src->s6_addr32[1], - src->s6_addr32[2], src->s6_addr32[3], srcp, - dest->s6_addr32[0], dest->s6_addr32[1], - dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - sk_wmem_alloc_get(sp), - sk_rmem_alloc_get(sp), - 0, 0L, 0, - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), - 0, - sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, - atomic_read(&sp->sk_drops)); -} - int udp6_seq_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) - seq_printf(seq, - " sl " - "local_address " - "remote_address " - "st tx_queue rx_queue tr tm->when retrnsmt" - " uid timeout inode ref pointer drops\n"); - else - udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket); + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + int bucket = ((struct udp_iter_state *)seq->private)->bucket; + struct inet_sock *inet = inet_sk(v); + __u16 srcp = ntohs(inet->inet_sport); + __u16 destp = ntohs(inet->inet_dport); + ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + } return 0; } diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 4691ed5..c779c3c 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -7,33 +7,32 @@ #include <net/inet_common.h> #include <net/transp_v6.h> -extern int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int ); -extern void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, - u8 , u8 , int , __be32 , struct udp_table *); +int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int); +void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int, + __be32, struct udp_table *); -extern int udp_v6_get_port(struct sock *sk, unsigned short snum); +int udp_v6_get_port(struct sock *sk, unsigned short snum); -extern int udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen); -extern int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen); +int udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +int udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT -extern int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen); -extern int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen); +int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); +int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); #endif -extern int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len); -extern int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, - int noblock, int flags, int *addr_len); -extern int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb); -extern void udpv6_destroy_sock(struct sock *sk); +int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len); +int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len, int noblock, int flags, int *addr_len); +int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); +void udpv6_destroy_sock(struct sock *sk); -extern void udp_v6_clear_sk(struct sock *sk, int size); +void udp_v6_clear_sk(struct sock *sk, int size); #ifdef CONFIG_PROC_FS -extern int udp6_seq_show(struct seq_file *seq, void *v); +int udp6_seq_show(struct seq_file *seq, void *v); #endif #endif /* _UDP6_IMPL_H */ diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index d3cfaf9..e7359f9 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -21,26 +21,25 @@ static int udp6_ufo_send_check(struct sk_buff *skb) const struct ipv6hdr *ipv6h; struct udphdr *uh; - /* UDP Tunnel offload on ipv6 is not yet supported. */ - if (skb->encapsulation) - return -EINVAL; - if (!pskb_may_pull(skb, sizeof(*uh))) return -EINVAL; - ipv6h = ipv6_hdr(skb); - uh = udp_hdr(skb); + if (likely(!skb->encapsulation)) { + ipv6h = ipv6_hdr(skb); + uh = udp_hdr(skb); + + uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, + IPPROTO_UDP, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + } - uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, - IPPROTO_UDP, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct udphdr, check); - skb->ip_summed = CHECKSUM_PARTIAL; return 0; } static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, - netdev_features_t features) + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; @@ -64,7 +63,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_UDP_TUNNEL | - SKB_GSO_GRE) || + SKB_GSO_GRE | + SKB_GSO_IPIP | + SKB_GSO_SIT | + SKB_GSO_MPLS) || !(type & (SKB_GSO_UDP)))) goto out; @@ -74,47 +76,51 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, goto out; } - /* Do software UFO. Complete and fill in the UDP checksum as HW cannot - * do checksum of UDP packets sent as multiple IP fragments. - */ - offset = skb_checksum_start_offset(skb); - csum = skb_checksum(skb, offset, skb->len - offset, 0); - offset += skb->csum_offset; - *(__sum16 *)(skb->data + offset) = csum_fold(csum); - skb->ip_summed = CHECKSUM_NONE; - - /* Check if there is enough headroom to insert fragment header. */ - tnl_hlen = skb_tnl_header_len(skb); - if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) { - if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) - goto out; + if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) + segs = skb_udp_tunnel_segment(skb, features); + else { + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + offset = skb_checksum_start_offset(skb); + csum = skb_checksum(skb, offset, skb->len - offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + + /* Check if there is enough headroom to insert fragment header. */ + tnl_hlen = skb_tnl_header_len(skb); + if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { + if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) + goto out; + } + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + + unfrag_ip6hlen + tnl_hlen; + packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; + memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); + + SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); } - /* Find the unfragmentable header and shift it left by frag_hdr_sz - * bytes to insert fragment header. - */ - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - nexthdr = *prevhdr; - *prevhdr = NEXTHDR_FRAGMENT; - unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + - unfrag_ip6hlen + tnl_hlen; - packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; - memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); - - SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; - skb->mac_header -= frag_hdr_sz; - skb->network_header -= frag_hdr_sz; - - fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); - fptr->nexthdr = nexthdr; - fptr->reserved = 0; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); - - /* Fragment the skb. ipv6 header and the remaining fields of the - * fragment header are updated in ipv6_gso_segment() - */ - segs = skb_segment(skb, features); - out: return segs; } diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 4770d51..cb04f7a 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -18,6 +18,65 @@ #include <net/ipv6.h> #include <net/xfrm.h> +/* Informational hook. The decap is still done here. */ +static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly; +static DEFINE_MUTEX(xfrm6_mode_tunnel_input_mutex); + +int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler) +{ + struct xfrm_tunnel_notifier __rcu **pprev; + struct xfrm_tunnel_notifier *t; + int ret = -EEXIST; + int priority = handler->priority; + + mutex_lock(&xfrm6_mode_tunnel_input_mutex); + + for (pprev = &rcv_notify_handlers; + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL; + pprev = &t->next) { + if (t->priority > priority) + break; + if (t->priority == priority) + goto err; + + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm6_mode_tunnel_input_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_register); + +int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler) +{ + struct xfrm_tunnel_notifier __rcu **pprev; + struct xfrm_tunnel_notifier *t; + int ret = -ENOENT; + + mutex_lock(&xfrm6_mode_tunnel_input_mutex); + for (pprev = &rcv_notify_handlers; + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + mutex_unlock(&xfrm6_mode_tunnel_input_mutex); + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_deregister); + static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); @@ -63,8 +122,15 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } +#define for_each_input_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) + + static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { + struct xfrm_tunnel_notifier *handler; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) @@ -72,6 +138,9 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; + for_each_input_rcu(rcv_notify_handlers, handler) + handler->handler(skb); + err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8755a30..6cd625e 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -34,8 +34,10 @@ static int xfrm6_local_dontfrag(struct sk_buff *skb) struct sock *sk = skb->sk; if (sk) { - proto = sk->sk_protocol; + if (sk->sk_family != AF_INET6) + return 0; + proto = sk->sk_protocol; if (proto == IPPROTO_UDP || proto == IPPROTO_RAW) return inet6_sk(sk)->dontfrag; } @@ -54,13 +56,15 @@ static void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu) ipv6_local_rxpmtu(sk, &fl6, mtu); } -static void xfrm6_local_error(struct sk_buff *skb, u32 mtu) +void xfrm6_local_error(struct sk_buff *skb, u32 mtu) { struct flowi6 fl6; + const struct ipv6hdr *hdr; struct sock *sk = skb->sk; + hdr = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb); fl6.fl6_dport = inet_sk(sk)->inet_dport; - fl6.daddr = ipv6_hdr(skb)->daddr; + fl6.daddr = hdr->daddr; ipv6_local_error(sk, EMSGSIZE, &fl6, mtu); } @@ -80,7 +84,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if (xfrm6_local_dontfrag(skb)) xfrm6_local_rxpmtu(skb, mtu); else if (skb->sk) - xfrm6_local_error(skb, mtu); + xfrm_local_error(skb, mtu); else icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ret = -EMSGSIZE; @@ -136,13 +140,18 @@ static int __xfrm6_output(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; - int mtu = ip6_skb_dst_mtu(skb); + int mtu; + + if (skb->protocol == htons(ETH_P_IPV6)) + mtu = ip6_skb_dst_mtu(skb); + else + mtu = dst_mtu(skb_dst(skb)); if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); return -EMSGSIZE; } else if (!skb->local_df && skb->len > mtu && skb->sk) { - xfrm6_local_error(skb, mtu); + xfrm_local_error(skb, mtu); return -EMSGSIZE; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 23ed03d..5f8e128 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -135,9 +135,14 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u8 nexthdr = nh[IP6CB(skb)->nhoff]; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; + fl6->flowi6_oif = reverse ? skb->skb_iif : oif; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; @@ -284,7 +289,7 @@ static struct dst_ops xfrm6_dst_ops = { .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, - .gc_thresh = 1024, + .gc_thresh = 32768, }; static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index d8c70b8..3fc9701 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -183,6 +183,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .extract_input = xfrm6_extract_input, .extract_output = xfrm6_extract_output, .transport_finish = xfrm6_transport_finish, + .local_error = xfrm6_local_error, }; int __init xfrm6_state_init(void) |