diff --git a/sys/conf/options b/sys/conf/options index 7431dd8c94c9..ab19720354aa 100644 --- a/sys/conf/options +++ b/sys/conf/options @@ -1,410 +1,411 @@ # $FreeBSD$ # # On the handling of kernel options # # All kernel options should be listed in LINT, with suitable # descriptions. Negative options (options that make some code not # compile) should be commented out; LINT should compile as much code # as possible. Try to structure option-using code so that a single # option only switch code on, or only switch code off, to make it # possible to have a full compile-test. If necessary, you can include # "opt_lint.h" and check for COMPILING_LINT to get maximum code # coverage. # # All new options shall also be listed in either "conf/options" or # "/conf/options.". Options that affect a single # source-file .[c|s] should be directed into "opt_.h", while # options that affect multiple files should either go in # "opt_global.h" if this is a kernel-wide option (used just about # everywhere), or in "opt_.h" if it affect # only some files. Note that the effect of listing only an option # without a header-file-name in conf/options (and cousins) is that the # last convention is followed. # # This handling scheme is not yet fully implemented. # # # Format of this file: # Option name filename # # If filename is missing, the default is # opt_.h # Adaptec aic7xxx SCSI controller options AHC_ALLOW_MEMIO opt_aic7xxx.h # Allow PCI devices to use memory # mapped I/O AHC_TMODE_ENABLE opt_aic7xxx.h # Bitmap of units to enable # targetmode operations. AHC_DUMP_EEPROM opt_aic7xxx.h # Dump the contents of our # configuration prom. ADW_ALLOW_MEMIO opt_adw.h # Allow PCI devices to use memory # mapped I/O # Miscellaneous options. COMPAT_43 opt_compat.h COMPAT_SUNOS opt_compat.h COMPILING_LINT opt_lint.h CY_PCI_FASTINTR DDB DDB_UNATTENDED opt_ddb.h GDB_REMOTE_CHAT opt_ddb.h DEVFS HW_WDOG KTRACE MD5 MFS_ROOT opt_mfs.h MFS_ROOT_SIZE opt_mfs.h NTIMECOUNTER opt_ntp.h NSWAPDEV opt_swap.h PPS_SYNC opt_ntp.h QUOTA SPX_HACK SUIDDIR opt_suiddir.h SYSVMSG opt_sysvipc.h SYSVSEM opt_sysvipc.h SYSVSHM opt_sysvipc.h UCONSOLE ICMP_BANDLIM # POSIX kernel options P1003_1B opt_posix.h _KPOSIX_PRIORITY_SCHEDULING opt_posix.h _KPOSIX_VERSION opt_posix.h # Do we want the config file compiled into the kernel? INCLUDE_CONFIG_FILE opt_config.h # Options for static file systems. These should only be used at config # time, since the corresponding lkms cannot work if there are any static # dependencies. Unusability is enforced by hiding the defines for the # options in a never-included header. EXT2FS opt_dontuse.h FDESC opt_dontuse.h KERNFS opt_dontuse.h MFS opt_dontuse.h MSDOSFS opt_dontuse.h NULLFS opt_dontuse.h PORTAL opt_dontuse.h PROCFS opt_dontuse.h UMAPFS opt_dontuse.h NTFS opt_dontuse.h # These static filesystems has one slightly bogus static dependency in # sys/i386/i386/autoconf.c. If any of these filesystems are # statically compiled into the kernel, code for mounting them as root # filesystems will be enabled - but look below. Boot-code is purposely # unavailable for the LKM-based versions. CODA CD9660 FFS NFS NWFS # If you are following the conditions in the copyright, # you can enable soft-updates which will speed up a lot of thigs # and make the system safer from crashes at the same time. # otherwise a STUB module will be compiled in. SOFTUPDATES opt_ffs.h # The above static dependencies are planned removed, with a # _ROOT option to control if it usable as root. This list # allows these options to be present in config files already (though # they won't make any difference yet). CD9660_ROOT opt_cd9660.h FFS_ROOT opt_ffs.h NFS_ROOT opt_nfsroot.h # Multi-session CD-Rs might require a huge amount of time in order to # "settle". If we are about mounting them as the root f/s, we gotta # wait a little. CD9660_ROOTDELAY opt_cd9660.h # The union static file system has bogus static dependencies, so it isn't # hidden yet. UNION # Options used only in param.c. HZ opt_param.h MAXFILES opt_param.h MAXUSERS opt_param.h MSGMNB opt_param.h MSGMNI opt_param.h MSGSEG opt_param.h MSGSSZ opt_param.h MSGTQL opt_param.h NBUF opt_param.h NMBCLUSTERS opt_param.h NSFBUFS opt_param.h SEMMAP opt_param.h SEMMNI opt_param.h SEMMNS opt_param.h SEMMNU opt_param.h SEMMSL opt_param.h SEMOPM opt_param.h SEMUME opt_param.h SHMALL opt_param.h SHMMAX opt_param.h SHMMAXPGS opt_param.h SHMMIN opt_param.h SHMMNI opt_param.h SHMSEG opt_param.h # Generic SCSI options. CAM_MAX_HIGHPOWER opt_cam.h CAMDEBUG opt_cam.h CAM_DEBUG_DELAY opt_cam.h CAM_DEBUG_BUS opt_cam.h CAM_DEBUG_TARGET opt_cam.h CAM_DEBUG_LUN opt_cam.h CAM_DEBUG_FLAGS opt_cam.h SCSI_DELAY opt_scsi.h SCSI_REPORT_GEOMETRY opt_scsi.h SCSI_NO_SENSE_STRINGS opt_scsi.h SCSI_NO_OP_STRINGS opt_scsi.h # Options used only in cam/scsi/scsi_cd.c CHANGER_MIN_BUSY_SECONDS opt_cd.h CHANGER_MAX_BUSY_SECONDS opt_cd.h # Options used only in cam/scsi/scsi_sa.c. SA_SPACE_TIMEOUT opt_sa.h SA_REWIND_TIMEOUT opt_sa.h SA_ERASE_TIMEOUT opt_sa.h SA_1FM_AT_EOD opt_sa.h # Options used only in cam/scsi/scsi_pt.c SCSI_PT_DEFAULT_TIMEOUT opt_pt.h # Options used only in pci/ncr.c SCSI_NCR_DEBUG opt_ncr.h SCSI_NCR_DFLT_TAGS opt_ncr.h SCSI_NCR_MAX_SYNC opt_ncr.h SCSI_NCR_MAX_WIDE opt_ncr.h SCSI_NCR_MYADDR opt_ncr.h # Options used only in pci/isp_pci.c SCSI_ISP_NO_FWLOAD_MASK opt_isp.h SCSI_ISP_NO_NVRAM_MASK opt_isp.h SCSI_ISP_PREFER_MEM_MAP opt_isp.h SCSI_ISP_FABRIC opt_isp.h SCSI_ISP_SCCLUN opt_isp.h SCSI_ISP_FCDUPLEX opt_isp.h ISP_DISABLE_1020_SUPPORT opt_isp.h ISP_DISABLE_1080_SUPPORT opt_isp.h ISP_DISABLE_2100_SUPPORT opt_isp.h ISP_DISABLE_2200_SUPPORT opt_isp.h # Options used in the 'ata' ATA/ATAPI driver ATA_STATIC_ID opt_ata.h ATA_16BIT_ONLY opt_ata.h # Resource limits. DFLDSIZ opt_rlimit.h MAXDSIZ opt_rlimit.h # Net stuff. BOOTP opt_bootp.h BOOTP_COMPAT opt_bootp.h BOOTP_NFSROOT opt_bootp.h BOOTP_NFSV3 opt_bootp.h BOOTP_WIRED_TO opt_bootp.h BRIDGE opt_bdg.h MROUTING opt_mrouting.h INET opt_inet.h +INET6 opt_inet.h IPDIVERT DUMMYNET opt_ipdn.h IPFILTER_LKM opt_ipfilter.h IPFIREWALL opt_ipfw.h IPFIREWALL_VERBOSE opt_ipfw.h IPFIREWALL_VERBOSE_LIMIT opt_ipfw.h IPFIREWALL_DEFAULT_TO_ACCEPT opt_ipfw.h IPFIREWALL_FORWARD opt_ipfw.h IPSTEALTH IPX opt_ipx.h IPXIP opt_ipx.h IPTUNNEL opt_ipx.h NCP opt_ncp.h NETATALK opt_atalk.h PPP_BSDCOMP opt_ppp.h PPP_DEFLATE opt_ppp.h PPP_FILTER opt_ppp.h SLIP_IFF_OPTS opt_slip.h TCP_COMPAT_42 opt_compat.h TCPDEBUG TCP_DROP_SYNFIN opt_tcp_input.h TCP_RESTRICT_RST opt_tcp_input.h # Netgraph(4). Use option NETGRAPH to enable the base netgraph code. # Each netgraph node type can be either be compiled into the kernel # or loaded dynamically. To get the former, include the corresponding # option below. NETGRAPH NETGRAPH_ASYNC opt_netgraph.h NETGRAPH_CISCO opt_netgraph.h NETGRAPH_ECHO opt_netgraph.h NETGRAPH_FRAME_RELAY opt_netgraph.h NETGRAPH_HOLE opt_netgraph.h NETGRAPH_IFACE opt_netgraph.h NETGRAPH_LMI opt_netgraph.h NETGRAPH_PPP opt_netgraph.h NETGRAPH_PPPOE opt_netgraph.h NETGRAPH_RFC1490 opt_netgraph.h NETGRAPH_SOCKET opt_netgraph.h NETGRAPH_TEE opt_netgraph.h NETGRAPH_TTY opt_netgraph.h NETGRAPH_UI opt_netgraph.h NETGRAPH_VJC opt_netgraph.h # ATM (HARP version) ATM_CORE opt_atm.h ATM_IP opt_atm.h ATM_SIGPVC opt_atm.h ATM_SPANS opt_atm.h ATM_UNI opt_atm.h # XXX Conflict: # of devices vs network protocol (Native ATM). # This makes "atm.h" unusable. NATM opt_natm.h DPT_ALLOW_MEMIO opt_dpt.h # Allow PCI devices to use memory # mapped I/O # DPT driver debug flags DPT_VERIFY_HINTR opt_dpt.h DPT_USE_SINTR opt_dpt.h DPT_RESTRICTED_FREELIST opt_dpt.h DPT_MEASURE_PERFORMANCE opt_dpt.h DPT_FREELIST_IS_STACK opt_dpt.h DPT_HANDLE_TIMEOUTS opt_dpt.h DPT_TIMEOUT_FACTOR opt_dpt.h DPT_INTR_DELAY opt_dpt.h DPT_LOST_IRQ opt_dpt.h DPT_SHUTDOWN_SLEEP opt_dpt.h DPT_RESET_HBA opt_dpt.h # Misc debug flags. Most of these should probably be replaced with # 'DEBUG', and then let people recompile just the interesting modules # with 'make CC="cc -DDEBUG"'. CLUSTERDEBUG opt_debug_cluster.h DEBUG_1284 opt_ppb_1284.h VP0_DEBUG opt_vpo.h LPT_DEBUG opt_lpt.h PLIP_DEBUG opt_plip.h LOCKF_DEBUG opt_debug_lockf.h LOUTB opt_debug_outb.h NPX_DEBUG opt_debug_npx.h NETATALKDEBUG opt_atalk.h SI_DEBUG opt_debug_si.h # ppbus related options PERIPH_1284 opt_ppb_1284.h DONTPROBE_1284 opt_ppb_1284.h # smbus related options ENABLE_ALART opt_intpm.h # These cause changes all over the kernel DEBUG opt_global.h DEBUG_LOCKS opt_global.h DEBUG_VFS_LOCKS opt_global.h DIAGNOSTIC opt_global.h ENABLE_VFS_IOOPT opt_global.h INVARIANT_SUPPORT opt_global.h INVARIANTS opt_global.h SIMPLELOCK_DEBUG opt_global.h VFS_BIO_DEBUG opt_global.h BLKDEV_IOSIZE opt_global.h # These are VM related options VM_KMEM_SIZE opt_vm.h VM_KMEM_SIZE_SCALE opt_vm.h VM_KMEM_SIZE_MAX opt_vm.h NO_SWAPPING opt_vm.h PQ_NOOPT opt_vmpage.h PQ_NORMALCACHE opt_vmpage.h PQ_MEDIUMCACHE opt_vmpage.h PQ_LARGECACHE opt_vmpage.h PQ_HUGECACHE opt_vmpage.h # Standard SMP options SMP opt_global.h NCPU opt_smp.h NBUS opt_smp.h # sys/netkey KEY KEY_DEBUG opt_key.h # Size of the kernel message buffer MSGBUF_SIZE opt_msgbuf.h # PCI related options PCI_QUIET opt_pci.h # NFS options NFS_MINATTRTIMO opt_nfs.h NFS_MAXATTRTIMO opt_nfs.h NFS_MINDIRATTRTIMO opt_nfs.h NFS_MAXDIRATTRTIMO opt_nfs.h NFS_GATHERDELAY opt_nfs.h NFS_UIDHASHSIZ opt_nfs.h NFS_WDELAYHASHSIZ opt_nfs.h NFS_MUIDHASHSIZ opt_nfs.h NFS_NOSERVER opt_nfs.h NFS_DEBUG opt_nfs.h # For the Bt848/Bt848A/Bt849/Bt878/Bt879 driver OVERRIDE_CARD opt_bktr.h OVERRIDE_TUNER opt_bktr.h OVERRIDE_DBX opt_bktr.h OVERRIDE_MSP opt_bktr.h BROOKTREE_SYSTEM_DEFAULT opt_bktr.h BKTR_USE_PLL opt_bktr.h BKTR_GPIO_ACCESS opt_bktr.h BKTR_NO_MSP_RESET opt_bktr.h BKTR_430_FX_MODE opt_bktr.h BKTR_SIS_VIA_MODE opt_bktr.h # meteor opt_meteor.h METEOR_ALLOC_PAGES opt_meteor.h METEOR_TEST_VIDEO opt_meteor.h METEOR_SYSTEM_DEFAULT opt_meteor.h METEOR_DEALLOC_PAGES opt_meteor.h METEOR_DEALLOC_ABOVE opt_meteor.h # Various mi ISA bus flags COM_ESP opt_sio.h COM_MULTIPORT opt_sio.h EXTRA_SIO opt_sio.h # Include tweaks for running under the SimOS machine simulator. SIMOS opt_simos.h # options for bus/device framework BUS_DEBUG opt_bus.h # options for USB support UHCI_DEBUG opt_usb.h OHCI_DEBUG opt_usb.h USB_DEBUG opt_usb.h UGEN_DEBUG opt_usb.h UHID_DEBUG opt_usb.h UHUB_DEBUG opt_usb.h UKBD_DEBUG opt_usb.h ULPT_DEBUG opt_usb.h UMASS_DEBUG opt_usb.h UMS_DEBUG opt_usb.h # Vinum options VINUMDEBUG opt_vinum.h # Embedded system options INIT_PATH opt_init_path.h ROOTDEVNAME opt_rootdevname.h FDC_DEBUG opt_fdc.h FDC_YE opt_fdc.h diff --git a/sys/net/ethernet.h b/sys/net/ethernet.h index c8b62e0c5724..8e982d755f9b 100644 --- a/sys/net/ethernet.h +++ b/sys/net/ethernet.h @@ -1,97 +1,98 @@ /* * Fundamental constants relating to ethernet. * * $FreeBSD$ * */ #ifndef _NET_ETHERNET_H_ #define _NET_ETHERNET_H_ /* * The number of bytes in an ethernet (MAC) address. */ #define ETHER_ADDR_LEN 6 /* * The number of bytes in the type field. */ #define ETHER_TYPE_LEN 2 /* * The number of bytes in the trailing CRC field. */ #define ETHER_CRC_LEN 4 /* * The length of the combined header. */ #define ETHER_HDR_LEN (ETHER_ADDR_LEN*2+ETHER_TYPE_LEN) /* * The minimum packet length. */ #define ETHER_MIN_LEN 64 /* * The maximum packet length. */ #define ETHER_MAX_LEN 1518 /* * A macro to validate a length with */ #define ETHER_IS_VALID_LEN(foo) \ ((foo) >= ETHER_MIN_LEN && (foo) <= ETHER_MAX_LEN) /* * Structure of a 10Mb/s Ethernet header. */ struct ether_header { u_char ether_dhost[ETHER_ADDR_LEN]; u_char ether_shost[ETHER_ADDR_LEN]; u_short ether_type; }; /* * Structure of a 48-bit Ethernet address. */ struct ether_addr { u_char octet[ETHER_ADDR_LEN]; }; #define ETHERTYPE_PUP 0x0200 /* PUP protocol */ #define ETHERTYPE_IP 0x0800 /* IP protocol */ -#define ETHERTYPE_ARP 0x0806 /* Addr. resolution protocol */ -#define ETHERTYPE_REVARP 0x8035 /* reverse Addr. resolution protocol */ -#define ETHERTYPE_VLAN 0x8100 /* IEEE 802.1Q VLAN tagging */ +#define ETHERTYPE_ARP 0x0806 /* Addr. resolution protocol */ +#define ETHERTYPE_REVARP 0x8035 /* reverse Addr. resolution protocol */ +#define ETHERTYPE_VLAN 0x8100 /* IEEE 802.1Q VLAN tagging */ +#define ETHERTYPE_IPV6 0x86dd /* IPv6 */ #define ETHERTYPE_LOOPBACK 0x9000 /* used to test interfaces */ /* XXX - add more useful types here */ /* * The ETHERTYPE_NTRAILER packet types starting at ETHERTYPE_TRAIL have * (type-ETHERTYPE_TRAIL)*512 bytes of data followed * by an ETHER type (as given above) and then the (variable-length) header. */ #define ETHERTYPE_TRAIL 0x1000 /* Trailer packet */ #define ETHERTYPE_NTRAILER 16 #define ETHERMTU (ETHER_MAX_LEN-ETHER_HDR_LEN-ETHER_CRC_LEN) #define ETHERMIN (ETHER_MIN_LEN-ETHER_HDR_LEN-ETHER_CRC_LEN) #ifndef KERNEL #include /* * Ethernet address conversion/parsing routines. */ __BEGIN_DECLS struct ether_addr *ether_aton __P((char *)); int ether_hostton __P((char *, struct ether_addr *)); int ether_line __P((char *, struct ether_addr *, char *)); char *ether_ntoa __P((struct ether_addr *)); int ether_ntohost __P((char *, struct ether_addr *)); __END_DECLS #endif /* !KERNEL */ #endif /* !_NET_ETHERNET_H_ */ diff --git a/sys/net/if.h b/sys/net/if.h index 8ceea66b9fc0..350e6d86ab11 100644 --- a/sys/net/if.h +++ b/sys/net/if.h @@ -1,246 +1,274 @@ /* * Copyright (c) 1982, 1986, 1989, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)if.h 8.1 (Berkeley) 6/10/93 * $FreeBSD$ */ #ifndef _NET_IF_H_ #define _NET_IF_H_ /* * does not depend on on most other systems. This * helps userland compatability. (struct timeval ifi_lastchange) */ #ifndef KERNEL #include #endif /* * Structure describing information about an interface * which may be of interest to management entities. */ struct if_data { /* generic interface information */ u_char ifi_type; /* ethernet, tokenring, etc */ u_char ifi_physical; /* e.g., AUI, Thinnet, 10base-T, etc */ u_char ifi_addrlen; /* media address length */ u_char ifi_hdrlen; /* media header length */ u_char ifi_recvquota; /* polling quota for receive intrs */ u_char ifi_xmitquota; /* polling quota for xmit intrs */ u_long ifi_mtu; /* maximum transmission unit */ u_long ifi_metric; /* routing metric (external only) */ u_long ifi_baudrate; /* linespeed */ /* volatile statistics */ u_long ifi_ipackets; /* packets received on interface */ u_long ifi_ierrors; /* input errors on interface */ u_long ifi_opackets; /* packets sent on interface */ u_long ifi_oerrors; /* output errors on interface */ u_long ifi_collisions; /* collisions on csma interfaces */ u_long ifi_ibytes; /* total number of octets received */ u_long ifi_obytes; /* total number of octets sent */ u_long ifi_imcasts; /* packets received via multicast */ u_long ifi_omcasts; /* packets sent via multicast */ u_long ifi_iqdrops; /* dropped on input, this interface */ u_long ifi_noproto; /* destined for unsupported protocol */ u_long ifi_recvtiming; /* usec spent receiving when timing */ u_long ifi_xmittiming; /* usec spent xmitting when timing */ struct timeval ifi_lastchange; /* time of last administrative change */ }; #define IFF_UP 0x1 /* interface is up */ #define IFF_BROADCAST 0x2 /* broadcast address valid */ #define IFF_DEBUG 0x4 /* turn on debugging */ #define IFF_LOOPBACK 0x8 /* is a loopback net */ #define IFF_POINTOPOINT 0x10 /* interface is point-to-point link */ #define IFF_SMART 0x20 /* interface manages own routes */ #define IFF_RUNNING 0x40 /* resources allocated */ #define IFF_NOARP 0x80 /* no address resolution protocol */ #define IFF_PROMISC 0x100 /* receive all packets */ #define IFF_ALLMULTI 0x200 /* receive all multicast packets */ #define IFF_OACTIVE 0x400 /* transmission in progress */ #define IFF_SIMPLEX 0x800 /* can't hear own transmissions */ #define IFF_LINK0 0x1000 /* per link layer defined bit */ #define IFF_LINK1 0x2000 /* per link layer defined bit */ #define IFF_LINK2 0x4000 /* per link layer defined bit */ #define IFF_ALTPHYS IFF_LINK2 /* use alternate physical connection */ #define IFF_MULTICAST 0x8000 /* supports multicast */ /* flags set internally only: */ #define IFF_CANTCHANGE \ (IFF_BROADCAST|IFF_POINTOPOINT|IFF_RUNNING|IFF_OACTIVE|\ IFF_SIMPLEX|IFF_MULTICAST|IFF_ALLMULTI|IFF_SMART) #define IFQ_MAXLEN 50 #define IFNET_SLOWHZ 1 /* granularity is 1 second */ /* * Message format for use in obtaining information about interfaces * from getkerninfo and the routing socket */ struct if_msghdr { u_short ifm_msglen; /* to skip over non-understood messages */ u_char ifm_version; /* future binary compatability */ u_char ifm_type; /* message type */ int ifm_addrs; /* like rtm_addrs */ int ifm_flags; /* value of if_flags */ u_short ifm_index; /* index for associated ifp */ struct if_data ifm_data;/* statistics and other data about if */ }; /* * Message format for use in obtaining information about interface addresses * from getkerninfo and the routing socket */ struct ifa_msghdr { u_short ifam_msglen; /* to skip over non-understood messages */ u_char ifam_version; /* future binary compatability */ u_char ifam_type; /* message type */ int ifam_addrs; /* like rtm_addrs */ int ifam_flags; /* value of ifa_flags */ u_short ifam_index; /* index for associated ifp */ int ifam_metric; /* value of ifa_metric */ }; /* * Message format for use in obtaining information about multicast addresses * from the routing socket */ struct ifma_msghdr { u_short ifmam_msglen; /* to skip over non-understood messages */ u_char ifmam_version; /* future binary compatability */ u_char ifmam_type; /* message type */ int ifmam_addrs; /* like rtm_addrs */ int ifmam_flags; /* value of ifa_flags */ u_short ifmam_index; /* index for associated ifp */ }; /* * Interface request structure used for socket * ioctl's. All interface ioctl's must have parameter * definitions which begin with ifr_name. The * remainder may be interface specific. */ struct ifreq { #define IFNAMSIZ 16 +#define IF_NAMESIZE IFNAMSIZ char ifr_name[IFNAMSIZ]; /* if name, e.g. "en0" */ union { struct sockaddr ifru_addr; struct sockaddr ifru_dstaddr; struct sockaddr ifru_broadaddr; short ifru_flags[2]; int ifru_metric; int ifru_mtu; int ifru_phys; int ifru_media; caddr_t ifru_data; } ifr_ifru; #define ifr_addr ifr_ifru.ifru_addr /* address */ #define ifr_dstaddr ifr_ifru.ifru_dstaddr /* other end of p-to-p link */ #define ifr_broadaddr ifr_ifru.ifru_broadaddr /* broadcast address */ #define ifr_flags ifr_ifru.ifru_flags[0] /* flags */ #define ifr_prevflags ifr_ifru.ifru_flags[1] /* flags */ #define ifr_metric ifr_ifru.ifru_metric /* metric */ #define ifr_mtu ifr_ifru.ifru_mtu /* mtu */ #define ifr_phys ifr_ifru.ifru_phys /* physical wire */ #define ifr_media ifr_ifru.ifru_media /* physical media */ #define ifr_data ifr_ifru.ifru_data /* for use by interface */ }; #define _SIZEOF_ADDR_IFREQ(ifr) \ ((ifr).ifr_addr.sa_len > sizeof(struct sockaddr) ? \ (sizeof(struct ifreq) - sizeof(struct sockaddr) + \ (ifr).ifr_addr.sa_len) : sizeof(struct ifreq)) struct ifaliasreq { char ifra_name[IFNAMSIZ]; /* if name, e.g. "en0" */ struct sockaddr ifra_addr; struct sockaddr ifra_broadaddr; struct sockaddr ifra_mask; }; struct ifmediareq { char ifm_name[IFNAMSIZ]; /* if name, e.g. "en0" */ int ifm_current; /* current media options */ int ifm_mask; /* don't care mask */ int ifm_status; /* media status */ int ifm_active; /* active options */ int ifm_count; /* # entries in ifm_ulist array */ int *ifm_ulist; /* media words */ }; /* * Structure used to retrieve aux status data from interfaces. * Kernel suppliers to this interface should respect the formatting * needed by ifconfig(8): each line starts with a TAB and ends with * a newline. The canonical example to copy and paste is in if_tun.c. */ #define IFSTATMAX 800 /* 10 lines of text */ struct ifstat { char ifs_name[IFNAMSIZ]; /* if name, e.g. "en0" */ char ascii[IFSTATMAX + 1]; }; /* * Structure used in SIOCGIFCONF request. * Used to retrieve interface configuration * for machine (useful for programs which * must know all networks accessible). */ struct ifconf { int ifc_len; /* size of associated buffer */ union { caddr_t ifcu_buf; struct ifreq *ifcu_req; } ifc_ifcu; #define ifc_buf ifc_ifcu.ifcu_buf /* buffer address */ #define ifc_req ifc_ifcu.ifcu_req /* array of structures returned */ }; + +/* + * Structure for SIOC[AGD]LIFADDR + */ +struct if_laddrreq { + char iflr_name[IFNAMSIZ]; + u_int flags; +#define IFLR_PREFIX 0x8000 /* in: prefix given out: kernel fills id */ + u_int prefixlen; /* in/out */ + struct sockaddr_storage addr; /* in/out */ + struct sockaddr_storage dstaddr; /* out */ +}; + #ifdef KERNEL #ifdef MALLOC_DECLARE MALLOC_DECLARE(M_IFADDR); MALLOC_DECLARE(M_IFMADDR); #endif #endif +#ifndef KERNEL +struct if_nameindex { + u_int if_index; /* 1, 2, ... */ + char *if_name; /* null terminated name: "le0", ... */ +}; + +__BEGIN_DECLS +u_int if_nametoindex __P((const char *)); +char *if_indextoname __P((u_int, char *)); +struct if_nameindex *if_nameindex __P((void)); +void if_freenameindex __P((struct if_nameindex *)); +__END_DECLS +#endif + #ifdef KERNEL struct proc; int prison_if __P((struct proc *p, struct sockaddr *sa)); /* XXX - this should go away soon. */ #include #endif #endif /* !_NET_IF_H_ */ diff --git a/sys/net/if_types.h b/sys/net/if_types.h index ebcbcbfef19f..318b35660096 100644 --- a/sys/net/if_types.h +++ b/sys/net/if_types.h @@ -1,101 +1,103 @@ /* * Copyright (c) 1989, 1993, 1994 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)if_types.h 8.2 (Berkeley) 4/20/94 * $FreeBSD$ */ #ifndef _NET_IF_TYPES_H_ #define _NET_IF_TYPES_H_ /* * Interface types for benefit of parsing media address headers. * This list is derived from the SNMP list of ifTypes, currently * documented in RFC1573. */ #define IFT_OTHER 0x1 /* none of the following */ #define IFT_1822 0x2 /* old-style arpanet imp */ #define IFT_HDH1822 0x3 /* HDH arpanet imp */ #define IFT_X25DDN 0x4 /* x25 to imp */ #define IFT_X25 0x5 /* PDN X25 interface (RFC877) */ #define IFT_ETHER 0x6 /* Ethernet CSMACD */ #define IFT_ISO88023 0x7 /* CMSA CD */ #define IFT_ISO88024 0x8 /* Token Bus */ #define IFT_ISO88025 0x9 /* Token Ring */ #define IFT_ISO88026 0xa /* MAN */ #define IFT_STARLAN 0xb #define IFT_P10 0xc /* Proteon 10MBit ring */ #define IFT_P80 0xd /* Proteon 80MBit ring */ #define IFT_HY 0xe /* Hyperchannel */ #define IFT_FDDI 0xf #define IFT_LAPB 0x10 #define IFT_SDLC 0x11 #define IFT_T1 0x12 #define IFT_CEPT 0x13 /* E1 - european T1 */ #define IFT_ISDNBASIC 0x14 #define IFT_ISDNPRIMARY 0x15 #define IFT_PTPSERIAL 0x16 /* Proprietary PTP serial */ #define IFT_PPP 0x17 /* RFC 1331 */ #define IFT_LOOP 0x18 /* loopback */ #define IFT_EON 0x19 /* ISO over IP */ #define IFT_XETHER 0x1a /* obsolete 3MB experimental ethernet */ #define IFT_NSIP 0x1b /* XNS over IP */ #define IFT_SLIP 0x1c /* IP over generic TTY */ #define IFT_ULTRA 0x1d /* Ultra Technologies */ #define IFT_DS3 0x1e /* Generic T3 */ #define IFT_SIP 0x1f /* SMDS */ #define IFT_FRELAY 0x20 /* Frame Relay DTE only */ #define IFT_RS232 0x21 #define IFT_PARA 0x22 /* parallel-port */ #define IFT_ARCNET 0x23 #define IFT_ARCNETPLUS 0x24 #define IFT_ATM 0x25 /* ATM cells */ #define IFT_MIOX25 0x26 #define IFT_SONET 0x27 /* SONET or SDH */ #define IFT_X25PLE 0x28 #define IFT_ISO88022LLC 0x29 #define IFT_LOCALTALK 0x2a #define IFT_SMDSDXI 0x2b #define IFT_FRELAYDCE 0x2c /* Frame Relay DCE */ #define IFT_V35 0x2d #define IFT_HSSI 0x2e #define IFT_HIPPI 0x2f #define IFT_MODEM 0x30 /* Generic Modem */ #define IFT_AAL5 0x31 /* AAL5 over ATM */ #define IFT_SONETPATH 0x32 #define IFT_SONETVT 0x33 #define IFT_SMDSICIP 0x34 /* SMDS InterCarrier Interface */ #define IFT_PROPVIRTUAL 0x35 /* Proprietary Virtual/internal */ #define IFT_PROPMUX 0x36 /* Proprietary Multiplexing */ +#define IFT_GIF 0x37 +#define IFT_FAITH 0x38 #endif diff --git a/sys/net/if_var.h b/sys/net/if_var.h index a598d193973c..0b6e40d1980b 100644 --- a/sys/net/if_var.h +++ b/sys/net/if_var.h @@ -1,345 +1,363 @@ /* * Copyright (c) 1982, 1986, 1989, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * From: @(#)if.h 8.1 (Berkeley) 6/10/93 * $FreeBSD$ */ #ifndef _NET_IF_VAR_H_ #define _NET_IF_VAR_H_ /* * Structures defining a network interface, providing a packet * transport mechanism (ala level 0 of the PUP protocols). * * Each interface accepts output datagrams of a specified maximum * length, and provides higher level routines with input datagrams * received from its medium. * * Output occurs when the routine if_output is called, with three parameters: * (*ifp->if_output)(ifp, m, dst, rt) * Here m is the mbuf chain to be sent and dst is the destination address. * The output routine encapsulates the supplied datagram if necessary, * and then transmits it on its medium. * * On input, each interface unwraps the data received by it, and either * places it on the input queue of a internetwork datagram routine * and posts the associated software interrupt, or passes the datagram to a raw * packet input routine. * * Routines exist for locating interfaces by their addresses * or for locating a interface on a certain network, as well as more general * routing and gateway routines maintaining information used to locate * interfaces. These routines live in the files if.c and route.c */ #ifdef __STDC__ /* * Forward structure declarations for function prototypes [sic]. */ struct mbuf; struct proc; struct rtentry; struct socket; struct ether_header; #endif #include /* get TAILQ macros */ TAILQ_HEAD(ifnethead, ifnet); /* we use TAILQs so that the order of */ TAILQ_HEAD(ifaddrhead, ifaddr); /* instantiation is preserved in the list */ +TAILQ_HEAD(ifprefixhead, ifprefix); LIST_HEAD(ifmultihead, ifmultiaddr); /* * Structure defining a queue for a network interface. */ struct ifqueue { struct mbuf *ifq_head; struct mbuf *ifq_tail; int ifq_len; int ifq_maxlen; int ifq_drops; }; /* * Structure defining a network interface. * * (Would like to call this struct ``if'', but C isn't PL/1.) */ struct ifnet { void *if_softc; /* pointer to driver state */ char *if_name; /* name, e.g. ``en'' or ``lo'' */ TAILQ_ENTRY(ifnet) if_link; /* all struct ifnets are chained */ struct ifaddrhead if_addrhead; /* linked list of addresses per if */ int if_pcount; /* number of promiscuous listeners */ struct bpf_if *if_bpf; /* packet filter structure */ u_short if_index; /* numeric abbreviation for this if */ short if_unit; /* sub-unit for lower level driver */ short if_timer; /* time 'til if_watchdog called */ short if_flags; /* up/down, broadcast, etc. */ int if_ipending; /* interrupts pending */ void *if_linkmib; /* link-type-specific MIB data */ size_t if_linkmiblen; /* length of above data */ struct if_data if_data; struct ifmultihead if_multiaddrs; /* multicast addresses configured */ int if_amcount; /* number of all-multicast requests */ /* procedure handles */ int (*if_output) /* output routine (enqueue) */ __P((struct ifnet *, struct mbuf *, struct sockaddr *, struct rtentry *)); void (*if_start) /* initiate output routine */ __P((struct ifnet *)); int (*if_done) /* output complete routine */ __P((struct ifnet *)); /* (XXX not used; fake prototype) */ int (*if_ioctl) /* ioctl routine */ __P((struct ifnet *, u_long, caddr_t)); void (*if_watchdog) /* timer routine */ __P((struct ifnet *)); int (*if_poll_recv) /* polled receive routine */ __P((struct ifnet *, int *)); int (*if_poll_xmit) /* polled transmit routine */ __P((struct ifnet *, int *)); void (*if_poll_intren) /* polled interrupt reenable routine */ __P((struct ifnet *)); void (*if_poll_slowinput) /* input routine for slow devices */ __P((struct ifnet *, struct mbuf *)); void (*if_init) /* Init routine */ __P((void *)); int (*if_resolvemulti) /* validate/resolve multicast */ __P((struct ifnet *, struct sockaddr **, struct sockaddr *)); struct ifqueue if_snd; /* output queue */ struct ifqueue *if_poll_slowq; /* input queue for slow devices */ + struct ifprefixhead if_prefixhead; /* list of prefixes per if */ }; typedef void if_init_f_t __P((void *)); #define if_mtu if_data.ifi_mtu #define if_type if_data.ifi_type #define if_physical if_data.ifi_physical #define if_addrlen if_data.ifi_addrlen #define if_hdrlen if_data.ifi_hdrlen #define if_metric if_data.ifi_metric #define if_baudrate if_data.ifi_baudrate #define if_ipackets if_data.ifi_ipackets #define if_ierrors if_data.ifi_ierrors #define if_opackets if_data.ifi_opackets #define if_oerrors if_data.ifi_oerrors #define if_collisions if_data.ifi_collisions #define if_ibytes if_data.ifi_ibytes #define if_obytes if_data.ifi_obytes #define if_imcasts if_data.ifi_imcasts #define if_omcasts if_data.ifi_omcasts #define if_iqdrops if_data.ifi_iqdrops #define if_noproto if_data.ifi_noproto #define if_lastchange if_data.ifi_lastchange #define if_recvquota if_data.ifi_recvquota #define if_xmitquota if_data.ifi_xmitquota #define if_rawoutput(if, m, sa) if_output(if, m, sa, (struct rtentry *)0) /* * Bit values in if_ipending */ #define IFI_RECV 1 /* I want to receive */ #define IFI_XMIT 2 /* I want to transmit */ /* * Output queues (ifp->if_snd) and slow device input queues (*ifp->if_slowq) * are queues of messages stored on ifqueue structures * (defined above). Entries are added to and deleted from these structures * by these macros, which should be called with ipl raised to splimp(). */ #define IF_QFULL(ifq) ((ifq)->ifq_len >= (ifq)->ifq_maxlen) #define IF_DROP(ifq) ((ifq)->ifq_drops++) #define IF_ENQUEUE(ifq, m) { \ (m)->m_nextpkt = 0; \ if ((ifq)->ifq_tail == 0) \ (ifq)->ifq_head = m; \ else \ (ifq)->ifq_tail->m_nextpkt = m; \ (ifq)->ifq_tail = m; \ (ifq)->ifq_len++; \ } #define IF_PREPEND(ifq, m) { \ (m)->m_nextpkt = (ifq)->ifq_head; \ if ((ifq)->ifq_tail == 0) \ (ifq)->ifq_tail = (m); \ (ifq)->ifq_head = (m); \ (ifq)->ifq_len++; \ } #define IF_DEQUEUE(ifq, m) { \ (m) = (ifq)->ifq_head; \ if (m) { \ if (((ifq)->ifq_head = (m)->m_nextpkt) == 0) \ (ifq)->ifq_tail = 0; \ (m)->m_nextpkt = 0; \ (ifq)->ifq_len--; \ } \ } #ifdef KERNEL #define IF_ENQ_DROP(ifq, m) if_enq_drop(ifq, m) #if defined(__GNUC__) && defined(MT_HEADER) static __inline int if_queue_drop(struct ifqueue *ifq, struct mbuf *m) { IF_DROP(ifq); return 0; } static __inline int if_enq_drop(struct ifqueue *ifq, struct mbuf *m) { if (IF_QFULL(ifq) && !if_queue_drop(ifq, m)) return 0; IF_ENQUEUE(ifq, m); return 1; } #else #ifdef MT_HEADER int if_enq_drop __P((struct ifqueue *, struct mbuf *)); #endif #endif /* * 72 was chosen below because it is the size of a TCP/IP * header (40) + the minimum mss (32). */ #define IF_MINMTU 72 #define IF_MAXMTU 65535 #endif /* KERNEL */ /* * The ifaddr structure contains information about one address * of an interface. They are maintained by the different address families, * are allocated and attached when an address is set, and are linked * together so all addresses for an interface can be located. */ struct ifaddr { struct sockaddr *ifa_addr; /* address of interface */ struct sockaddr *ifa_dstaddr; /* other end of p-to-p link */ #define ifa_broadaddr ifa_dstaddr /* broadcast address interface */ struct sockaddr *ifa_netmask; /* used to determine subnet */ struct ifnet *ifa_ifp; /* back-pointer to interface */ TAILQ_ENTRY(ifaddr) ifa_link; /* queue macro glue */ void (*ifa_rtrequest) /* check or clean routes (+ or -)'d */ __P((int, struct rtentry *, struct sockaddr *)); u_short ifa_flags; /* mostly rt_flags for cloning */ u_int ifa_refcnt; /* references to this structure */ int ifa_metric; /* cost of going out this interface */ #ifdef notdef struct rtentry *ifa_rt; /* XXXX for ROUTETOIF ????? */ #endif int (*ifa_claim_addr) /* check if an addr goes to this if */ __P((struct ifaddr *, struct sockaddr *)); }; #define IFA_ROUTE RTF_UP /* route installed */ +/* + * The prefix structure contains information about one prefix + * of an interface. They are maintained by the different address families, + * are allocated and attached when an prefix or an address is set, + * and are linked together so all prfefixes for an interface can be located. + */ +struct ifprefix { + struct sockaddr *ifpr_prefix; /* prefix of interface */ + struct ifnet *ifpr_ifp; /* back-pointer to interface */ + TAILQ_ENTRY(ifprefix) *ifpr_list; /* queue macro glue */ + u_char ifpr_plen; /* prefix length in bits */ + u_char ifpr_type; /* protocol dependent prefix type */ +}; + /* * Multicast address structure. This is analogous to the ifaddr * structure except that it keeps track of multicast addresses. * Also, the reference count here is a count of requests for this * address, not a count of pointers to this structure. */ struct ifmultiaddr { LIST_ENTRY(ifmultiaddr) ifma_link; /* queue macro glue */ struct sockaddr *ifma_addr; /* address this membership is for */ struct sockaddr *ifma_lladdr; /* link-layer translation, if any */ struct ifnet *ifma_ifp; /* back-pointer to interface */ u_int ifma_refcount; /* reference count */ void *ifma_protospec; /* protocol-specific state, if any */ }; #ifdef KERNEL #define IFAFREE(ifa) \ do { \ if ((ifa)->ifa_refcnt <= 0) \ ifafree(ifa); \ else \ (ifa)->ifa_refcnt--; \ } while (0) extern struct ifnethead ifnet; +extern struct ifnet **ifindex2ifnet; extern int ifqmaxlen; extern struct ifnet loif[]; extern int if_index; extern struct ifaddr **ifnet_addrs; void ether_ifattach __P((struct ifnet *)); void ether_input __P((struct ifnet *, struct ether_header *, struct mbuf *)); int ether_output __P((struct ifnet *, struct mbuf *, struct sockaddr *, struct rtentry *)); int ether_ioctl __P((struct ifnet *, int, caddr_t)); int if_addmulti __P((struct ifnet *, struct sockaddr *, struct ifmultiaddr **)); int if_allmulti __P((struct ifnet *, int)); void if_attach __P((struct ifnet *)); int if_delmulti __P((struct ifnet *, struct sockaddr *)); void if_detach __P((struct ifnet *)); void if_down __P((struct ifnet *)); void if_route __P((struct ifnet *, int flag, int fam)); void if_unroute __P((struct ifnet *, int flag, int fam)); void if_up __P((struct ifnet *)); /*void ifinit __P((void));*/ /* declared in systm.h for main() */ int ifioctl __P((struct socket *, u_long, caddr_t, struct proc *)); int ifpromisc __P((struct ifnet *, int)); struct ifnet *ifunit __P((char *)); +struct ifnet *if_withname __P((struct sockaddr *)); int if_poll_recv_slow __P((struct ifnet *ifp, int *quotap)); void if_poll_xmit_slow __P((struct ifnet *ifp, int *quotap)); void if_poll_throttle __P((void)); void if_poll_unthrottle __P((void *)); void if_poll_init __P((void)); void if_poll __P((void)); struct ifaddr *ifa_ifwithaddr __P((struct sockaddr *)); struct ifaddr *ifa_ifwithdstaddr __P((struct sockaddr *)); struct ifaddr *ifa_ifwithnet __P((struct sockaddr *)); struct ifaddr *ifa_ifwithroute __P((int, struct sockaddr *, struct sockaddr *)); struct ifaddr *ifaof_ifpforaddr __P((struct sockaddr *, struct ifnet *)); void ifafree __P((struct ifaddr *)); struct ifmultiaddr *ifmaof_ifpforaddr __P((struct sockaddr *, struct ifnet *)); int if_simloop __P((struct ifnet *ifp, struct mbuf *m, struct sockaddr *dst, int hlen)); #endif /* KERNEL */ #endif /* !_NET_IF_VAR_H_ */ diff --git a/sys/net/netisr.h b/sys/net/netisr.h index d09f31df6c64..432607cf9840 100644 --- a/sys/net/netisr.h +++ b/sys/net/netisr.h @@ -1,94 +1,95 @@ /* * Copyright (c) 1980, 1986, 1989, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)netisr.h 8.1 (Berkeley) 6/10/93 * $FreeBSD$ */ #ifndef _NET_NETISR_H_ #define _NET_NETISR_H_ /* * The networking code runs off software interrupts. * * You can switch into the network by doing splnet() and return by splx(). * The software interrupt level for the network is higher than the software * level for the clock (so you can enter the network in routines called * at timeout time). */ #if defined(vax) || defined(tahoe) #define setsoftnet() mtpr(SIRR, 12) #endif /* * Each ``pup-level-1'' input queue has a bit in a ``netisr'' status * word which is used to de-multiplex a single software * interrupt used for scheduling the network code to calls * on the lowest level routine of each protocol. */ #define NETISR_RAW 0 /* same as AF_UNSPEC */ #define NETISR_IP 2 /* same as AF_INET */ #define NETISR_IMP 3 /* same as AF_IMPLINK */ #define NETISR_NS 6 /* same as AF_NS */ #define NETISR_ISO 7 /* same as AF_ISO */ #define NETISR_CCITT 10 /* same as AF_CCITT */ -#define NETISR_ATALK 16 /* same as AF_APPLETALK */ +#define NETISR_ATALK 16 /* same as AF_APPLETALK */ #define NETISR_ARP 18 /* same as AF_LINK */ -#define NETISR_IPX 23 /* same as AF_IPX */ +#define NETISR_IPX 23 /* same as AF_IPX */ #define NETISR_ISDN 26 /* same as AF_E164 */ #define NETISR_PPP 27 /* PPP soft interrupt */ +#define NETISR_IPV6 28 /* same as AF_INET6 */ #define NETISR_NATM 29 /* same as AF_NATM */ #define NETISR_NETGRAPH 31 /* same as AF_NETGRAPH */ #define schednetisr(anisr) { netisr |= 1<<(anisr); setsoftnet(); } #ifndef LOCORE #ifdef KERNEL extern volatile unsigned int netisr; /* scheduling bits for network */ typedef void netisr_t __P((void)); struct netisrtab { int nit_num; netisr_t *nit_isr; }; int register_netisr __P((int, netisr_t *)); void netisr_sysinit __P((void *)); #define NETISR_SET(num, isr) \ static struct netisrtab nisr_##num = { num, isr }; \ SYSINIT(nisr_##num, SI_SUB_CPU, SI_ORDER_ANY, netisr_sysinit, &nisr_##num) #endif #endif #endif diff --git a/sys/net/route.h b/sys/net/route.h index 48f0d9a517b4..ba1bb9562dfe 100644 --- a/sys/net/route.h +++ b/sys/net/route.h @@ -1,296 +1,298 @@ /* * Copyright (c) 1980, 1986, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)route.h 8.3 (Berkeley) 4/19/94 * $FreeBSD$ */ #ifndef _NET_ROUTE_H_ #define _NET_ROUTE_H_ /* * Kernel resident routing tables. * * The routing tables are initialized when interface addresses * are set by making entries for all directly connected interfaces. */ /* * A route consists of a destination address and a reference * to a routing entry. These are often held by protocols * in their control blocks, e.g. inpcb. */ struct route { struct rtentry *ro_rt; struct sockaddr ro_dst; }; /* * These numbers are used by reliable protocols for determining * retransmission behavior and are included in the routing structure. */ struct rt_metrics { u_long rmx_locks; /* Kernel must leave these values alone */ u_long rmx_mtu; /* MTU for this path */ u_long rmx_hopcount; /* max hops expected */ u_long rmx_expire; /* lifetime for route, e.g. redirect */ u_long rmx_recvpipe; /* inbound delay-bandwidth product */ u_long rmx_sendpipe; /* outbound delay-bandwidth product */ u_long rmx_ssthresh; /* outbound gateway buffer limit */ u_long rmx_rtt; /* estimated round trip time */ u_long rmx_rttvar; /* estimated rtt variance */ u_long rmx_pksent; /* packets sent using this route */ u_long rmx_filler[4]; /* will be used for T/TCP later */ }; /* * rmx_rtt and rmx_rttvar are stored as microseconds; * RTTTOPRHZ(rtt) converts to a value suitable for use * by a protocol slowtimo counter. */ #define RTM_RTTUNIT 1000000 /* units for rtt, rttvar, as units per sec */ #define RTTTOPRHZ(r) ((r) / (RTM_RTTUNIT / PR_SLOWHZ)) /* * XXX kernel function pointer `rt_output' is visible to applications. */ struct mbuf; /* * We distinguish between routes to hosts and routes to networks, * preferring the former if available. For each route we infer * the interface to use from the gateway address supplied when * the route was entered. Routes that forward packets through * gateways are marked so that the output routines know to address the * gateway rather than the ultimate destination. */ #ifndef RNF_NORMAL #include #endif struct rtentry { struct radix_node rt_nodes[2]; /* tree glue, and other values */ #define rt_key(r) ((struct sockaddr *)((r)->rt_nodes->rn_key)) #define rt_mask(r) ((struct sockaddr *)((r)->rt_nodes->rn_mask)) struct sockaddr *rt_gateway; /* value */ long rt_refcnt; /* # held references */ u_long rt_flags; /* up/down?, host/net */ struct ifnet *rt_ifp; /* the answer: interface to use */ struct ifaddr *rt_ifa; /* the answer: interface to use */ struct sockaddr *rt_genmask; /* for generation of cloned routes */ caddr_t rt_llinfo; /* pointer to link level info cache */ struct rt_metrics rt_rmx; /* metrics used by rx'ing protocols */ struct rtentry *rt_gwroute; /* implied entry for gatewayed routes */ int (*rt_output) __P((struct ifnet *, struct mbuf *, struct sockaddr *, struct rtentry *)); /* output routine for this (rt,if) */ struct rtentry *rt_parent; /* cloning parent of this route */ void *rt_filler2; /* more filler */ }; /* * Following structure necessary for 4.3 compatibility; * We should eventually move it to a compat file. */ struct ortentry { u_long rt_hash; /* to speed lookups */ struct sockaddr rt_dst; /* key */ struct sockaddr rt_gateway; /* value */ short rt_flags; /* up/down?, host/net */ short rt_refcnt; /* # held references */ u_long rt_use; /* raw # packets forwarded */ struct ifnet *rt_ifp; /* the answer: interface to use */ }; #define rt_use rt_rmx.rmx_pksent #define RTF_UP 0x1 /* route usable */ #define RTF_GATEWAY 0x2 /* destination is a gateway */ #define RTF_HOST 0x4 /* host entry (net otherwise) */ #define RTF_REJECT 0x8 /* host or net unreachable */ #define RTF_DYNAMIC 0x10 /* created dynamically (by redirect) */ #define RTF_MODIFIED 0x20 /* modified dynamically (by redirect) */ #define RTF_DONE 0x40 /* message confirmed */ /* 0x80 unused */ #define RTF_CLONING 0x100 /* generate new routes on use */ #define RTF_XRESOLVE 0x200 /* external daemon resolves name */ #define RTF_LLINFO 0x400 /* generated by link layer (e.g. ARP) */ #define RTF_STATIC 0x800 /* manually added */ #define RTF_BLACKHOLE 0x1000 /* just discard pkts (during updates) */ #define RTF_PROTO2 0x4000 /* protocol specific routing flag */ #define RTF_PROTO1 0x8000 /* protocol specific routing flag */ #define RTF_PRCLONING 0x10000 /* protocol requires cloning */ #define RTF_WASCLONED 0x20000 /* route generated through cloning */ #define RTF_PROTO3 0x40000 /* protocol specific routing flag */ /* 0x80000 unused */ #define RTF_PINNED 0x100000 /* future use */ #define RTF_LOCAL 0x200000 /* route represents a local address */ #define RTF_BROADCAST 0x400000 /* route represents a bcast address */ #define RTF_MULTICAST 0x800000 /* route represents a mcast address */ /* 0x1000000 and up unassigned */ /* * Routing statistics. */ struct rtstat { short rts_badredirect; /* bogus redirect calls */ short rts_dynamic; /* routes created by redirects */ short rts_newgateway; /* routes modified by redirects */ short rts_unreach; /* lookups which failed */ short rts_wildcard; /* lookups satisfied by a wildcard */ }; /* * Structures for routing messages. */ struct rt_msghdr { u_short rtm_msglen; /* to skip over non-understood messages */ u_char rtm_version; /* future binary compatibility */ u_char rtm_type; /* message type */ u_short rtm_index; /* index for associated ifp */ int rtm_flags; /* flags, incl. kern & message, e.g. DONE */ int rtm_addrs; /* bitmask identifying sockaddrs in msg */ pid_t rtm_pid; /* identify sender */ int rtm_seq; /* for sender to identify action */ int rtm_errno; /* why failed */ int rtm_use; /* from rtentry */ u_long rtm_inits; /* which metrics we are initializing */ struct rt_metrics rtm_rmx; /* metrics themselves */ }; #define RTM_VERSION 5 /* Up the ante and ignore older versions */ /* * Message types. */ #define RTM_ADD 0x1 /* Add Route */ #define RTM_DELETE 0x2 /* Delete Route */ #define RTM_CHANGE 0x3 /* Change Metrics or flags */ #define RTM_GET 0x4 /* Report Metrics */ #define RTM_LOSING 0x5 /* Kernel Suspects Partitioning */ #define RTM_REDIRECT 0x6 /* Told to use different route */ #define RTM_MISS 0x7 /* Lookup failed on this address */ #define RTM_LOCK 0x8 /* fix specified metrics */ #define RTM_OLDADD 0x9 /* caused by SIOCADDRT */ #define RTM_OLDDEL 0xa /* caused by SIOCDELRT */ #define RTM_RESOLVE 0xb /* req to resolve dst to LL addr */ #define RTM_NEWADDR 0xc /* address being added to iface */ #define RTM_DELADDR 0xd /* address being removed from iface */ #define RTM_IFINFO 0xe /* iface going up/down etc. */ #define RTM_NEWMADDR 0xf /* mcast group membership being added to if */ #define RTM_DELMADDR 0x10 /* mcast group membership being deleted */ /* * Bitmask values for rtm_inits and rmx_locks. */ #define RTV_MTU 0x1 /* init or lock _mtu */ #define RTV_HOPCOUNT 0x2 /* init or lock _hopcount */ #define RTV_EXPIRE 0x4 /* init or lock _expire */ #define RTV_RPIPE 0x8 /* init or lock _recvpipe */ #define RTV_SPIPE 0x10 /* init or lock _sendpipe */ #define RTV_SSTHRESH 0x20 /* init or lock _ssthresh */ #define RTV_RTT 0x40 /* init or lock _rtt */ #define RTV_RTTVAR 0x80 /* init or lock _rttvar */ /* * Bitmask values for rtm_addrs. */ #define RTA_DST 0x1 /* destination sockaddr present */ #define RTA_GATEWAY 0x2 /* gateway sockaddr present */ #define RTA_NETMASK 0x4 /* netmask sockaddr present */ #define RTA_GENMASK 0x8 /* cloning mask sockaddr present */ #define RTA_IFP 0x10 /* interface name sockaddr present */ #define RTA_IFA 0x20 /* interface addr sockaddr present */ #define RTA_AUTHOR 0x40 /* sockaddr for author of redirect */ #define RTA_BRD 0x80 /* for NEWADDR, broadcast or p-p dest addr */ /* * Index offsets for sockaddr array for alternate internal encoding. */ #define RTAX_DST 0 /* destination sockaddr present */ #define RTAX_GATEWAY 1 /* gateway sockaddr present */ #define RTAX_NETMASK 2 /* netmask sockaddr present */ #define RTAX_GENMASK 3 /* cloning mask sockaddr present */ #define RTAX_IFP 4 /* interface name sockaddr present */ #define RTAX_IFA 5 /* interface addr sockaddr present */ #define RTAX_AUTHOR 6 /* sockaddr for author of redirect */ #define RTAX_BRD 7 /* for NEWADDR, broadcast or p-p dest addr */ #define RTAX_MAX 8 /* size of array to allocate */ struct rt_addrinfo { int rti_addrs; struct sockaddr *rti_info[RTAX_MAX]; }; struct route_cb { int ip_count; + int ip6_count; int ipx_count; int ns_count; int iso_count; int any_count; }; #ifdef KERNEL #define RTFREE(rt) \ do { \ if ((rt)->rt_refcnt <= 1) \ rtfree(rt); \ else \ (rt)->rt_refcnt--; \ } while (0) extern struct route_cb route_cb; extern struct radix_node_head *rt_tables[AF_MAX+1]; struct ifmultiaddr; struct proc; void route_init __P((void)); void rt_ifmsg __P((struct ifnet *)); void rt_missmsg __P((int, struct rt_addrinfo *, int, int)); void rt_newaddrmsg __P((int, struct ifaddr *, int, struct rtentry *)); void rt_newmaddrmsg __P((int, struct ifmultiaddr *)); int rt_setgate __P((struct rtentry *, struct sockaddr *, struct sockaddr *)); void rtalloc __P((struct route *)); -void rtalloc_ign __P((struct route *, unsigned long)); +void rtalloc_ign __P((struct route *, u_long)); +void rtcalloc __P((struct route *)); /* for INET6 */ struct rtentry * - rtalloc1 __P((struct sockaddr *, int, unsigned long)); + rtalloc1 __P((struct sockaddr *, int, u_long)); void rtfree __P((struct rtentry *)); int rtinit __P((struct ifaddr *, int, int)); int rtioctl __P((int, caddr_t, struct proc *)); void rtredirect __P((struct sockaddr *, struct sockaddr *, struct sockaddr *, int, struct sockaddr *, struct rtentry **)); int rtrequest __P((int, struct sockaddr *, struct sockaddr *, struct sockaddr *, int, struct rtentry **)); #endif #endif diff --git a/sys/netinet/if_ether.h b/sys/netinet/if_ether.h index 79f1252781c7..09caa3128075 100644 --- a/sys/netinet/if_ether.h +++ b/sys/netinet/if_ether.h @@ -1,106 +1,122 @@ /* * Copyright (c) 1982, 1986, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)if_ether.h 8.3 (Berkeley) 5/2/95 * $FreeBSD$ */ #ifndef _NETINET_IF_ETHER_H_ #define _NETINET_IF_ETHER_H_ #include #include /* * Macro to map an IP multicast address to an Ethernet multicast address. * The high-order 25 bits of the Ethernet address are statically assigned, * and the low-order 23 bits are taken from the low end of the IP address. */ #define ETHER_MAP_IP_MULTICAST(ipaddr, enaddr) \ /* struct in_addr *ipaddr; */ \ /* u_char enaddr[ETHER_ADDR_LEN]; */ \ { \ (enaddr)[0] = 0x01; \ (enaddr)[1] = 0x00; \ (enaddr)[2] = 0x5e; \ (enaddr)[3] = ((u_char *)ipaddr)[1] & 0x7f; \ (enaddr)[4] = ((u_char *)ipaddr)[2]; \ (enaddr)[5] = ((u_char *)ipaddr)[3]; \ } +/* + * Macro to map an IP6 multicast address to an Ethernet multicast address. + * The high-order 16 bits of the Ethernet address are statically assigned, + * and the low-order 32 bits are taken from the low end of the IP6 address. + */ +#define ETHER_MAP_IPV6_MULTICAST(ip6addr, enaddr) \ +/* struct in6_addr *ip6addr; */ \ +/* u_char enaddr[ETHER_ADDR_LEN]; */ \ +{ \ + (enaddr)[0] = 0x33; \ + (enaddr)[1] = 0x33; \ + (enaddr)[2] = ((u_char *)ip6addr)[12]; \ + (enaddr)[3] = ((u_char *)ip6addr)[13]; \ + (enaddr)[4] = ((u_char *)ip6addr)[14]; \ + (enaddr)[5] = ((u_char *)ip6addr)[15]; \ +} /* * Ethernet Address Resolution Protocol. * * See RFC 826 for protocol description. Structure below is adapted * to resolving internet addresses. Field names used correspond to * RFC 826. */ struct ether_arp { struct arphdr ea_hdr; /* fixed-size header */ u_char arp_sha[ETHER_ADDR_LEN]; /* sender hardware address */ u_char arp_spa[4]; /* sender protocol address */ u_char arp_tha[ETHER_ADDR_LEN]; /* target hardware address */ u_char arp_tpa[4]; /* target protocol address */ }; #define arp_hrd ea_hdr.ar_hrd #define arp_pro ea_hdr.ar_pro #define arp_hln ea_hdr.ar_hln #define arp_pln ea_hdr.ar_pln #define arp_op ea_hdr.ar_op struct sockaddr_inarp { u_char sin_len; u_char sin_family; u_short sin_port; struct in_addr sin_addr; struct in_addr sin_srcaddr; u_short sin_tos; u_short sin_other; #define SIN_PROXY 1 }; /* * IP and ethernet specific routing flags */ #define RTF_USETRAILERS RTF_PROTO1 /* use trailers */ #define RTF_ANNOUNCE RTF_PROTO2 /* announce new arp entry */ #ifdef KERNEL extern u_char ether_ipmulticast_min[ETHER_ADDR_LEN]; extern u_char ether_ipmulticast_max[ETHER_ADDR_LEN]; extern struct ifqueue arpintrq; int arpresolve __P((struct arpcom *, struct rtentry *, struct mbuf *, struct sockaddr *, u_char *, struct rtentry *)); void arp_ifinit __P((struct arpcom *, struct ifaddr *)); #endif #endif diff --git a/sys/netinet/in.h b/sys/netinet/in.h index ba5d24f91ad4..9e8a65265577 100644 --- a/sys/netinet/in.h +++ b/sys/netinet/in.h @@ -1,444 +1,462 @@ /* * Copyright (c) 1982, 1986, 1990, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)in.h 8.3 (Berkeley) 1/3/94 * $FreeBSD$ */ #ifndef _NETINET_IN_H_ #define _NETINET_IN_H_ /* * Constants and structures defined by the internet system, * Per RFC 790, September 1981, and numerous additions. */ /* * Protocols (RFC 1700) */ #define IPPROTO_IP 0 /* dummy for IP */ +#define IPPROTO_HOPOPTS 0 /* IP6 hop-by-hop options */ #define IPPROTO_ICMP 1 /* control message protocol */ #define IPPROTO_IGMP 2 /* group mgmt protocol */ #define IPPROTO_GGP 3 /* gateway^2 (deprecated) */ -#define IPPROTO_IPIP 4 /* IP encapsulation in IP */ +#define IPPROTO_IPV4 4 /* IPv4 encapsulation */ +#define IPPROTO_IPIP IPPROTO_IPV4 /* for compatibility */ #define IPPROTO_TCP 6 /* tcp */ #define IPPROTO_ST 7 /* Stream protocol II */ #define IPPROTO_EGP 8 /* exterior gateway protocol */ #define IPPROTO_PIGP 9 /* private interior gateway */ #define IPPROTO_RCCMON 10 /* BBN RCC Monitoring */ #define IPPROTO_NVPII 11 /* network voice protocol*/ #define IPPROTO_PUP 12 /* pup */ #define IPPROTO_ARGUS 13 /* Argus */ #define IPPROTO_EMCON 14 /* EMCON */ #define IPPROTO_XNET 15 /* Cross Net Debugger */ #define IPPROTO_CHAOS 16 /* Chaos*/ #define IPPROTO_UDP 17 /* user datagram protocol */ #define IPPROTO_MUX 18 /* Multiplexing */ #define IPPROTO_MEAS 19 /* DCN Measurement Subsystems */ #define IPPROTO_HMP 20 /* Host Monitoring */ #define IPPROTO_PRM 21 /* Packet Radio Measurement */ #define IPPROTO_IDP 22 /* xns idp */ #define IPPROTO_TRUNK1 23 /* Trunk-1 */ #define IPPROTO_TRUNK2 24 /* Trunk-2 */ #define IPPROTO_LEAF1 25 /* Leaf-1 */ #define IPPROTO_LEAF2 26 /* Leaf-2 */ #define IPPROTO_RDP 27 /* Reliable Data */ #define IPPROTO_IRTP 28 /* Reliable Transaction */ #define IPPROTO_TP 29 /* tp-4 w/ class negotiation */ #define IPPROTO_BLT 30 /* Bulk Data Transfer */ #define IPPROTO_NSP 31 /* Network Services */ #define IPPROTO_INP 32 /* Merit Internodal */ #define IPPROTO_SEP 33 /* Sequential Exchange */ #define IPPROTO_3PC 34 /* Third Party Connect */ #define IPPROTO_IDPR 35 /* InterDomain Policy Routing */ #define IPPROTO_XTP 36 /* XTP */ #define IPPROTO_DDP 37 /* Datagram Delivery */ #define IPPROTO_CMTP 38 /* Control Message Transport */ #define IPPROTO_TPXX 39 /* TP++ Transport */ #define IPPROTO_IL 40 /* IL transport protocol */ -#define IPPROTO_SIP 41 /* Simple Internet Protocol */ +#define IPPROTO_IPV6 41 /* IP6 header */ #define IPPROTO_SDRP 42 /* Source Demand Routing */ -#define IPPROTO_SIPSR 43 /* SIP Source Route */ -#define IPPROTO_SIPFRAG 44 /* SIP Fragment */ +#define IPPROTO_ROUTING 43 /* IP6 routing header */ +#define IPPROTO_FRAGMENT 44 /* IP6 fragmentation header */ #define IPPROTO_IDRP 45 /* InterDomain Routing*/ -#define IPPROTO_RSVP 46 /* resource reservation */ +#define IPPROTO_RSVP 46 /* resource reservation */ #define IPPROTO_GRE 47 /* General Routing Encap. */ #define IPPROTO_MHRP 48 /* Mobile Host Routing */ #define IPPROTO_BHA 49 /* BHA */ -#define IPPROTO_ESP 50 /* SIPP Encap Sec. Payload */ -#define IPPROTO_AH 51 /* SIPP Auth Header */ +#define IPPROTO_ESP 50 /* IP6 Encap Sec. Payload */ +#define IPPROTO_AH 51 /* IP6 Auth Header */ #define IPPROTO_INLSP 52 /* Integ. Net Layer Security */ #define IPPROTO_SWIPE 53 /* IP with encryption */ #define IPPROTO_NHRP 54 /* Next Hop Resolution */ -/* 55-60: Unassigned */ +/* 55-57: Unassigned */ +#define IPPROTO_ICMPV6 58 /* ICMP6 */ +#define IPPROTO_NONE 59 /* IP6 no next header */ +#define IPPROTO_DSTOPTS 60 /* IP6 destination option */ #define IPPROTO_AHIP 61 /* any host internal protocol */ #define IPPROTO_CFTP 62 /* CFTP */ #define IPPROTO_HELLO 63 /* "hello" routing protocol */ #define IPPROTO_SATEXPAK 64 /* SATNET/Backroom EXPAK */ #define IPPROTO_KRYPTOLAN 65 /* Kryptolan */ #define IPPROTO_RVD 66 /* Remote Virtual Disk */ #define IPPROTO_IPPC 67 /* Pluribus Packet Core */ #define IPPROTO_ADFS 68 /* Any distributed FS */ #define IPPROTO_SATMON 69 /* Satnet Monitoring */ #define IPPROTO_VISA 70 /* VISA Protocol */ #define IPPROTO_IPCV 71 /* Packet Core Utility */ #define IPPROTO_CPNX 72 /* Comp. Prot. Net. Executive */ #define IPPROTO_CPHB 73 /* Comp. Prot. HeartBeat */ #define IPPROTO_WSN 74 /* Wang Span Network */ #define IPPROTO_PVP 75 /* Packet Video Protocol */ #define IPPROTO_BRSATMON 76 /* BackRoom SATNET Monitoring */ #define IPPROTO_ND 77 /* Sun net disk proto (temp.) */ #define IPPROTO_WBMON 78 /* WIDEBAND Monitoring */ #define IPPROTO_WBEXPAK 79 /* WIDEBAND EXPAK */ #define IPPROTO_EON 80 /* ISO cnlp */ #define IPPROTO_VMTP 81 /* VMTP */ #define IPPROTO_SVMTP 82 /* Secure VMTP */ #define IPPROTO_VINES 83 /* Banyon VINES */ #define IPPROTO_TTP 84 /* TTP */ #define IPPROTO_IGP 85 /* NSFNET-IGP */ #define IPPROTO_DGP 86 /* dissimilar gateway prot. */ #define IPPROTO_TCF 87 /* TCF */ #define IPPROTO_IGRP 88 /* Cisco/GXS IGRP */ #define IPPROTO_OSPFIGP 89 /* OSPFIGP */ #define IPPROTO_SRPC 90 /* Strite RPC protocol */ #define IPPROTO_LARP 91 /* Locus Address Resoloution */ #define IPPROTO_MTP 92 /* Multicast Transport */ #define IPPROTO_AX25 93 /* AX.25 Frames */ #define IPPROTO_IPEIP 94 /* IP encapsulated in IP */ #define IPPROTO_MICP 95 /* Mobile Int.ing control */ #define IPPROTO_SCCSP 96 /* Semaphore Comm. security */ #define IPPROTO_ETHERIP 97 /* Ethernet IP encapsulation */ #define IPPROTO_ENCAP 98 /* encapsulation header */ #define IPPROTO_APES 99 /* any private encr. scheme */ #define IPPROTO_GMTP 100 /* GMTP*/ +#define IPPROTO_IPCOMP 108 /* payload compression (IPComp) */ /* 101-254: Partly Unassigned */ +#define IPPROTO_PIM 103 /* Protocol Independent Mcast */ #define IPPROTO_PGM 113 /* PGM */ /* 255: Reserved */ /* BSD Private, local use, namespace incursion */ #define IPPROTO_DIVERT 254 /* divert pseudo-protocol */ #define IPPROTO_RAW 255 /* raw IP packet */ #define IPPROTO_MAX 256 +/* last return value of *_input(), meaning "all job for this pkt is done". */ +#define IPPROTO_DONE 257 /* * Local port number conventions: * * When a user does a bind(2) or connect(2) with a port number of zero, * a non-conflicting local port address is chosen. * The default range is IPPORT_RESERVED through * IPPORT_USERRESERVED, although that is settable by sysctl. * * A user may set the IPPROTO_IP option IP_PORTRANGE to change this * default assignment range. * * The value IP_PORTRANGE_DEFAULT causes the default behavior. * * The value IP_PORTRANGE_HIGH changes the range of candidate port numbers * into the "high" range. These are reserved for client outbound connections * which do not want to be filtered by any firewalls. * * The value IP_PORTRANGE_LOW changes the range to the "low" are * that is (by convention) restricted to privileged processes. This * convention is based on "vouchsafe" principles only. It is only secure * if you trust the remote host to restrict these ports. * * The default range of ports and the high range can be changed by * sysctl(3). (net.inet.ip.port{hi,low}{first,last}_auto) * * Changing those values has bad security implications if you are * using a a stateless firewall that is allowing packets outside of that * range in order to allow transparent outgoing connections. * * Such a firewall configuration will generally depend on the use of these * default values. If you change them, you may find your Security * Administrator looking for you with a heavy object. * * For a slightly more orthodox text view on this: * * ftp://ftp.isi.edu/in-notes/iana/assignments/port-numbers * * port numbers are divided into three ranges: * * 0 - 1023 Well Known Ports * 1024 - 49151 Registered Ports * 49152 - 65535 Dynamic and/or Private Ports * */ /* * Ports < IPPORT_RESERVED are reserved for * privileged processes (e.g. root). (IP_PORTRANGE_LOW) * Ports > IPPORT_USERRESERVED are reserved * for servers, not necessarily privileged. (IP_PORTRANGE_DEFAULT) */ #define IPPORT_RESERVED 1024 #define IPPORT_USERRESERVED 5000 /* * Default local port range to use by setting IP_PORTRANGE_HIGH */ #define IPPORT_HIFIRSTAUTO 49152 #define IPPORT_HILASTAUTO 65535 /* * Scanning for a free reserved port return a value below IPPORT_RESERVED, * but higher than IPPORT_RESERVEDSTART. Traditionally the start value was * 512, but that conflicts with some well-known-services that firewalls may * have a fit if we use. */ #define IPPORT_RESERVEDSTART 600 /* * Internet address (a structure for historical reasons) */ struct in_addr { u_int32_t s_addr; }; /* * Definitions of bits in internet address integers. * On subnets, the decomposition of addresses to host and net parts * is done according to subnet mask, not the masks here. */ #define IN_CLASSA(i) (((u_int32_t)(i) & 0x80000000) == 0) #define IN_CLASSA_NET 0xff000000 #define IN_CLASSA_NSHIFT 24 #define IN_CLASSA_HOST 0x00ffffff #define IN_CLASSA_MAX 128 #define IN_CLASSB(i) (((u_int32_t)(i) & 0xc0000000) == 0x80000000) #define IN_CLASSB_NET 0xffff0000 #define IN_CLASSB_NSHIFT 16 #define IN_CLASSB_HOST 0x0000ffff #define IN_CLASSB_MAX 65536 #define IN_CLASSC(i) (((u_int32_t)(i) & 0xe0000000) == 0xc0000000) #define IN_CLASSC_NET 0xffffff00 #define IN_CLASSC_NSHIFT 8 #define IN_CLASSC_HOST 0x000000ff #define IN_CLASSD(i) (((u_int32_t)(i) & 0xf0000000) == 0xe0000000) #define IN_CLASSD_NET 0xf0000000 /* These ones aren't really */ #define IN_CLASSD_NSHIFT 28 /* net and host fields, but */ #define IN_CLASSD_HOST 0x0fffffff /* routing needn't know. */ #define IN_MULTICAST(i) IN_CLASSD(i) #define IN_EXPERIMENTAL(i) (((u_int32_t)(i) & 0xf0000000) == 0xf0000000) #define IN_BADCLASS(i) (((u_int32_t)(i) & 0xf0000000) == 0xf0000000) #define INADDR_ANY (u_int32_t)0x00000000 #define INADDR_LOOPBACK (u_int32_t)0x7f000001 #define INADDR_BROADCAST (u_int32_t)0xffffffff /* must be masked */ #ifndef KERNEL #define INADDR_NONE 0xffffffff /* -1 return */ #endif #define INADDR_UNSPEC_GROUP (u_int32_t)0xe0000000 /* 224.0.0.0 */ #define INADDR_ALLHOSTS_GROUP (u_int32_t)0xe0000001 /* 224.0.0.1 */ #define INADDR_ALLRTRS_GROUP (u_int32_t)0xe0000002 /* 224.0.0.2 */ #define INADDR_MAX_LOCAL_GROUP (u_int32_t)0xe00000ff /* 224.0.0.255 */ #define IN_LOOPBACKNET 127 /* official! */ /* * Socket address, internet style. */ struct sockaddr_in { u_char sin_len; u_char sin_family; u_short sin_port; struct in_addr sin_addr; char sin_zero[8]; }; +#define INET_ADDRSTRLEN 16 + /* * Structure used to describe IP options. * Used to store options internally, to pass them to a process, * or to restore options retrieved earlier. * The ip_dst is used for the first-hop gateway when using a source route * (this gets put into the header proper). */ struct ip_opts { struct in_addr ip_dst; /* first hop, 0 w/o src rt */ char ip_opts[40]; /* actually variable in size */ }; /* * Options for use with [gs]etsockopt at the IP level. * First word of comment is data type; bool is stored in int. */ #define IP_OPTIONS 1 /* buf/ip_opts; set/get IP options */ #define IP_HDRINCL 2 /* int; header is included with data */ #define IP_TOS 3 /* int; IP type of service and preced. */ #define IP_TTL 4 /* int; IP time to live */ #define IP_RECVOPTS 5 /* bool; receive all IP opts w/dgram */ #define IP_RECVRETOPTS 6 /* bool; receive IP opts for response */ #define IP_RECVDSTADDR 7 /* bool; receive IP dst addr w/dgram */ #define IP_RETOPTS 8 /* ip_opts; set/get IP options */ #define IP_MULTICAST_IF 9 /* u_char; set/get IP multicast i/f */ #define IP_MULTICAST_TTL 10 /* u_char; set/get IP multicast ttl */ #define IP_MULTICAST_LOOP 11 /* u_char; set/get IP multicast loopback */ #define IP_ADD_MEMBERSHIP 12 /* ip_mreq; add an IP group membership */ #define IP_DROP_MEMBERSHIP 13 /* ip_mreq; drop an IP group membership */ #define IP_MULTICAST_VIF 14 /* set/get IP mcast virt. iface */ #define IP_RSVP_ON 15 /* enable RSVP in kernel */ #define IP_RSVP_OFF 16 /* disable RSVP in kernel */ #define IP_RSVP_VIF_ON 17 /* set RSVP per-vif socket */ #define IP_RSVP_VIF_OFF 18 /* unset RSVP per-vif socket */ #define IP_PORTRANGE 19 /* int; range to choose for unspec port */ #define IP_RECVIF 20 /* bool; receive reception if w/dgram */ +/* for IPSEC */ +#define IP_IPSEC_POLICY 21 /* int; set/get security policy */ +#define IP_FAITH 22 /* bool; accept FAITH'ed connections */ -#define IP_FW_ADD 50 /* add a firewall rule to chain */ -#define IP_FW_DEL 51 /* delete a firewall rule from chain */ -#define IP_FW_FLUSH 52 /* flush firewall rule chain */ -#define IP_FW_ZERO 53 /* clear single/all firewall counter(s) */ -#define IP_FW_GET 54 /* get entire firewall rule chain */ -#define IP_FW_RESETLOG 55 /* reset logging counters */ +#define IP_FW_ADD 50 /* add a firewall rule to chain */ +#define IP_FW_DEL 51 /* delete a firewall rule from chain */ +#define IP_FW_FLUSH 52 /* flush firewall rule chain */ +#define IP_FW_ZERO 53 /* clear single/all firewall counter(s) */ +#define IP_FW_GET 54 /* get entire firewall rule chain */ +#define IP_FW_RESETLOG 55 /* reset logging counters */ #define IP_DUMMYNET_CONFIGURE 60 /* add/configure a dummynet pipe */ #define IP_DUMMYNET_DEL 61 /* delete a dummynet pipe from chain */ #define IP_DUMMYNET_FLUSH 62 /* flush dummynet */ #define IP_DUMMYNET_GET 64 /* get entire dummynet pipes */ /* * Defaults and limits for options */ #define IP_DEFAULT_MULTICAST_TTL 1 /* normally limit m'casts to 1 hop */ #define IP_DEFAULT_MULTICAST_LOOP 1 /* normally hear sends if a member */ #define IP_MAX_MEMBERSHIPS 20 /* per socket */ /* * Argument structure for IP_ADD_MEMBERSHIP and IP_DROP_MEMBERSHIP. */ struct ip_mreq { struct in_addr imr_multiaddr; /* IP multicast address of group */ struct in_addr imr_interface; /* local IP address of interface */ }; /* * Argument for IP_PORTRANGE: * - which range to search when port is unspecified at bind() or connect() */ #define IP_PORTRANGE_DEFAULT 0 /* default range */ #define IP_PORTRANGE_HIGH 1 /* "high" - request firewall bypass */ #define IP_PORTRANGE_LOW 2 /* "low" - vouchsafe security */ /* * Definitions for inet sysctl operations. * * Third level is protocol number. * Fourth level is desired variable within that protocol. */ -#define IPPROTO_MAXID (IPPROTO_IDP + 1) /* don't list to IPPROTO_MAX */ +#define IPPROTO_MAXID (IPPROTO_ESP + 1) /* don't list to IPPROTO_MAX */ #define CTL_IPPROTO_NAMES { \ { "ip", CTLTYPE_NODE }, \ { "icmp", CTLTYPE_NODE }, \ { "igmp", CTLTYPE_NODE }, \ { "ggp", CTLTYPE_NODE }, \ { 0, 0 }, \ { 0, 0 }, \ { "tcp", CTLTYPE_NODE }, \ { 0, 0 }, \ { "egp", CTLTYPE_NODE }, \ { 0, 0 }, \ { 0, 0 }, \ { 0, 0 }, \ { "pup", CTLTYPE_NODE }, \ { 0, 0 }, \ { 0, 0 }, \ { 0, 0 }, \ { 0, 0 }, \ { "udp", CTLTYPE_NODE }, \ { 0, 0 }, \ { 0, 0 }, \ { 0, 0 }, \ { 0, 0 }, \ { "idp", CTLTYPE_NODE }, \ } /* * Names for IP sysctl objects */ #define IPCTL_FORWARDING 1 /* act as router */ #define IPCTL_SENDREDIRECTS 2 /* may send redirects when forwarding */ #define IPCTL_DEFTTL 3 /* default TTL */ #ifdef notyet #define IPCTL_DEFMTU 4 /* default MTU */ #endif #define IPCTL_RTEXPIRE 5 /* cloned route expiration time */ #define IPCTL_RTMINEXPIRE 6 /* min value for expiration time */ #define IPCTL_RTMAXCACHE 7 /* trigger level for dynamic expire */ #define IPCTL_SOURCEROUTE 8 /* may perform source routes */ #define IPCTL_DIRECTEDBROADCAST 9 /* may re-broadcast received packets */ #define IPCTL_INTRQMAXLEN 10 /* max length of netisr queue */ -#define IPCTL_INTRQDROPS 11 /* number of netisr q drops */ +#define IPCTL_INTRQDROPS 11 /* number of netisr q drops */ #define IPCTL_STATS 12 /* ipstat structure */ #define IPCTL_ACCEPTSOURCEROUTE 13 /* may accept source routed packets */ -#define IPCTL_FASTFORWARDING 14 /* use fast IP forwarding code */ -#define IPCTL_MAXID 15 +#define IPCTL_FASTFORWARDING 14 /* use fast IP forwarding code */ +#define IPCTL_KEEPFAITH 15 +#define IPCTL_GIF_TTL 16 /* default TTL for gif encap packet */ +#define IPCTL_MAXID 17 #define IPCTL_NAMES { \ { 0, 0 }, \ { "forwarding", CTLTYPE_INT }, \ { "redirect", CTLTYPE_INT }, \ { "ttl", CTLTYPE_INT }, \ { "mtu", CTLTYPE_INT }, \ { "rtexpire", CTLTYPE_INT }, \ { "rtminexpire", CTLTYPE_INT }, \ { "rtmaxcache", CTLTYPE_INT }, \ { "sourceroute", CTLTYPE_INT }, \ { "directed-broadcast", CTLTYPE_INT }, \ { "intr-queue-maxlen", CTLTYPE_INT }, \ { "intr-queue-drops", CTLTYPE_INT }, \ { "stats", CTLTYPE_STRUCT }, \ { "accept_sourceroute", CTLTYPE_INT }, \ { "fastforwarding", CTLTYPE_INT }, \ } +/* INET6 stuff */ +#include #ifdef KERNEL struct ifnet; struct mbuf; /* forward declarations for Standard C */ struct proc; int in_broadcast __P((struct in_addr, struct ifnet *)); int in_canforward __P((struct in_addr)); int in_cksum __P((struct mbuf *, int)); int in_localaddr __P((struct in_addr)); char *inet_ntoa __P((struct in_addr)); /* in libkern */ int prison_ip __P((struct proc *p, int flag, u_int32_t *ip)); void prison_remote_ip __P((struct proc *p, int flag, u_int32_t *ip)); #endif /* KERNEL */ #endif diff --git a/sys/netinet/in_pcb.c b/sys/netinet/in_pcb.c index 018a040302b8..fdba717509aa 100644 --- a/sys/netinet/in_pcb.c +++ b/sys/netinet/in_pcb.c @@ -1,919 +1,918 @@ /* * Copyright (c) 1982, 1986, 1991, 1993, 1995 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)in_pcb.c 8.4 (Berkeley) 5/24/95 * $FreeBSD$ */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include struct in_addr zeroin_addr; -static void in_pcbremlists __P((struct inpcb *)); static void in_rtchange __P((struct inpcb *, int)); /* * These configure the range of local port addresses assigned to * "unspecified" outgoing connections/packets/whatever. */ static int ipport_lowfirstauto = IPPORT_RESERVED - 1; /* 1023 */ static int ipport_lowlastauto = IPPORT_RESERVEDSTART; /* 600 */ static int ipport_firstauto = IPPORT_RESERVED; /* 1024 */ static int ipport_lastauto = IPPORT_USERRESERVED; /* 5000 */ static int ipport_hifirstauto = IPPORT_HIFIRSTAUTO; /* 49152 */ static int ipport_hilastauto = IPPORT_HILASTAUTO; /* 65535 */ #define RANGECHK(var, min, max) \ if ((var) < (min)) { (var) = (min); } \ else if ((var) > (max)) { (var) = (max); } static int sysctl_net_ipport_check SYSCTL_HANDLER_ARGS { int error = sysctl_handle_int(oidp, oidp->oid_arg1, oidp->oid_arg2, req); if (!error) { RANGECHK(ipport_lowfirstauto, 1, IPPORT_RESERVED - 1); RANGECHK(ipport_lowlastauto, 1, IPPORT_RESERVED - 1); RANGECHK(ipport_firstauto, IPPORT_RESERVED, USHRT_MAX); RANGECHK(ipport_lastauto, IPPORT_RESERVED, USHRT_MAX); RANGECHK(ipport_hifirstauto, IPPORT_RESERVED, USHRT_MAX); RANGECHK(ipport_hilastauto, IPPORT_RESERVED, USHRT_MAX); } return error; } #undef RANGECHK SYSCTL_NODE(_net_inet_ip, IPPROTO_IP, portrange, CTLFLAG_RW, 0, "IP Ports"); SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, lowfirst, CTLTYPE_INT|CTLFLAG_RW, &ipport_lowfirstauto, 0, &sysctl_net_ipport_check, "I", ""); SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, lowlast, CTLTYPE_INT|CTLFLAG_RW, &ipport_lowlastauto, 0, &sysctl_net_ipport_check, "I", ""); SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, first, CTLTYPE_INT|CTLFLAG_RW, &ipport_firstauto, 0, &sysctl_net_ipport_check, "I", ""); SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, last, CTLTYPE_INT|CTLFLAG_RW, &ipport_lastauto, 0, &sysctl_net_ipport_check, "I", ""); SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, hifirst, CTLTYPE_INT|CTLFLAG_RW, &ipport_hifirstauto, 0, &sysctl_net_ipport_check, "I", ""); SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, hilast, CTLTYPE_INT|CTLFLAG_RW, &ipport_hilastauto, 0, &sysctl_net_ipport_check, "I", ""); /* * in_pcb.c: manage the Protocol Control Blocks. * * NOTE: It is assumed that most of these functions will be called at * splnet(). XXX - There are, unfortunately, a few exceptions to this * rule that should be fixed. */ /* * Allocate a PCB and associate it with the socket. */ int in_pcballoc(so, pcbinfo, p) struct socket *so; struct inpcbinfo *pcbinfo; struct proc *p; { register struct inpcb *inp; inp = zalloci(pcbinfo->ipi_zone); if (inp == NULL) return (ENOBUFS); bzero((caddr_t)inp, sizeof(*inp)); inp->inp_gencnt = ++pcbinfo->ipi_gencnt; inp->inp_pcbinfo = pcbinfo; inp->inp_socket = so; LIST_INSERT_HEAD(pcbinfo->listhead, inp, inp_list); pcbinfo->ipi_count++; so->so_pcb = (caddr_t)inp; return (0); } int in_pcbbind(inp, nam, p) register struct inpcb *inp; struct sockaddr *nam; struct proc *p; { register struct socket *so = inp->inp_socket; unsigned short *lastport; struct sockaddr_in *sin; struct inpcbinfo *pcbinfo = inp->inp_pcbinfo; u_short lport = 0; int wild = 0, reuseport = (so->so_options & SO_REUSEPORT); int error, prison = 0; if (TAILQ_EMPTY(&in_ifaddrhead)) /* XXX broken! */ return (EADDRNOTAVAIL); if (inp->inp_lport || inp->inp_laddr.s_addr != INADDR_ANY) return (EINVAL); if ((so->so_options & (SO_REUSEADDR|SO_REUSEPORT)) == 0) wild = 1; if (nam) { sin = (struct sockaddr_in *)nam; if (nam->sa_len != sizeof (*sin)) return (EINVAL); #ifdef notdef /* * We should check the family, but old programs * incorrectly fail to initialize it. */ if (sin->sin_family != AF_INET) return (EAFNOSUPPORT); #endif if (prison_ip(p, 0, &sin->sin_addr.s_addr)) return(EINVAL); lport = sin->sin_port; if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr))) { /* * Treat SO_REUSEADDR as SO_REUSEPORT for multicast; * allow complete duplication of binding if * SO_REUSEPORT is set, or if SO_REUSEADDR is set * and a multicast address is bound on both * new and duplicated sockets. */ if (so->so_options & SO_REUSEADDR) reuseport = SO_REUSEADDR|SO_REUSEPORT; } else if (sin->sin_addr.s_addr != INADDR_ANY) { sin->sin_port = 0; /* yech... */ if (ifa_ifwithaddr((struct sockaddr *)sin) == 0) return (EADDRNOTAVAIL); } if (lport) { struct inpcb *t; /* GROSS */ if (ntohs(lport) < IPPORT_RESERVED && p && suser_xxx(0, p, PRISON_ROOT)) return (EACCES); if (p && p->p_prison) prison = 1; if (so->so_cred->cr_uid != 0 && !IN_MULTICAST(ntohl(sin->sin_addr.s_addr))) { t = in_pcblookup_local(inp->inp_pcbinfo, sin->sin_addr, lport, prison ? 0 : INPLOOKUP_WILDCARD); if (t && (ntohl(sin->sin_addr.s_addr) != INADDR_ANY || ntohl(t->inp_laddr.s_addr) != INADDR_ANY || (t->inp_socket->so_options & SO_REUSEPORT) == 0) && (so->so_cred->cr_uid != t->inp_socket->so_cred->cr_uid)) return (EADDRINUSE); } t = in_pcblookup_local(pcbinfo, sin->sin_addr, lport, prison ? 0 : wild); if (t && (reuseport & t->inp_socket->so_options) == 0) return (EADDRINUSE); } inp->inp_laddr = sin->sin_addr; } if (lport == 0) { ushort first, last; int count; if (prison_ip(p, 0, &inp->inp_laddr.s_addr )) return (EINVAL); inp->inp_flags |= INP_ANONPORT; if (inp->inp_flags & INP_HIGHPORT) { first = ipport_hifirstauto; /* sysctl */ last = ipport_hilastauto; lastport = &pcbinfo->lasthi; } else if (inp->inp_flags & INP_LOWPORT) { if (p && (error = suser_xxx(0, p, PRISON_ROOT))) return error; first = ipport_lowfirstauto; /* 1023 */ last = ipport_lowlastauto; /* 600 */ lastport = &pcbinfo->lastlow; } else { first = ipport_firstauto; /* sysctl */ last = ipport_lastauto; lastport = &pcbinfo->lastport; } /* * Simple check to ensure all ports are not used up causing * a deadlock here. * * We split the two cases (up and down) so that the direction * is not being tested on each round of the loop. */ if (first > last) { /* * counting down */ count = first - last; do { if (count-- < 0) { /* completely used? */ /* * Undo any address bind that may have * occurred above. */ inp->inp_laddr.s_addr = INADDR_ANY; return (EAGAIN); } --*lastport; if (*lastport > first || *lastport < last) *lastport = first; lport = htons(*lastport); } while (in_pcblookup_local(pcbinfo, inp->inp_laddr, lport, wild)); } else { /* * counting up */ count = last - first; do { if (count-- < 0) { /* completely used? */ /* * Undo any address bind that may have * occurred above. */ inp->inp_laddr.s_addr = INADDR_ANY; return (EAGAIN); } ++*lastport; if (*lastport < first || *lastport > last) *lastport = first; lport = htons(*lastport); } while (in_pcblookup_local(pcbinfo, inp->inp_laddr, lport, wild)); } } inp->inp_lport = lport; if (in_pcbinshash(inp) != 0) { inp->inp_laddr.s_addr = INADDR_ANY; inp->inp_lport = 0; return (EAGAIN); } return (0); } /* * Transform old in_pcbconnect() into an inner subroutine for new * in_pcbconnect(): Do some validity-checking on the remote * address (in mbuf 'nam') and then determine local host address * (i.e., which interface) to use to access that remote host. * * This preserves definition of in_pcbconnect(), while supporting a * slightly different version for T/TCP. (This is more than * a bit of a kludge, but cleaning up the internal interfaces would * have forced minor changes in every protocol). */ int in_pcbladdr(inp, nam, plocal_sin) register struct inpcb *inp; struct sockaddr *nam; struct sockaddr_in **plocal_sin; { struct in_ifaddr *ia; register struct sockaddr_in *sin = (struct sockaddr_in *)nam; if (nam->sa_len != sizeof (*sin)) return (EINVAL); if (sin->sin_family != AF_INET) return (EAFNOSUPPORT); if (sin->sin_port == 0) return (EADDRNOTAVAIL); if (!TAILQ_EMPTY(&in_ifaddrhead)) { /* * If the destination address is INADDR_ANY, * use the primary local address. * If the supplied address is INADDR_BROADCAST, * and the primary interface supports broadcast, * choose the broadcast address for that interface. */ #define satosin(sa) ((struct sockaddr_in *)(sa)) #define sintosa(sin) ((struct sockaddr *)(sin)) #define ifatoia(ifa) ((struct in_ifaddr *)(ifa)) if (sin->sin_addr.s_addr == INADDR_ANY) sin->sin_addr = IA_SIN(in_ifaddrhead.tqh_first)->sin_addr; else if (sin->sin_addr.s_addr == (u_long)INADDR_BROADCAST && (in_ifaddrhead.tqh_first->ia_ifp->if_flags & IFF_BROADCAST)) sin->sin_addr = satosin(&in_ifaddrhead.tqh_first->ia_broadaddr)->sin_addr; } if (inp->inp_laddr.s_addr == INADDR_ANY) { register struct route *ro; ia = (struct in_ifaddr *)0; /* * If route is known or can be allocated now, * our src addr is taken from the i/f, else punt. */ ro = &inp->inp_route; if (ro->ro_rt && (satosin(&ro->ro_dst)->sin_addr.s_addr != sin->sin_addr.s_addr || inp->inp_socket->so_options & SO_DONTROUTE)) { RTFREE(ro->ro_rt); ro->ro_rt = (struct rtentry *)0; } if ((inp->inp_socket->so_options & SO_DONTROUTE) == 0 && /*XXX*/ (ro->ro_rt == (struct rtentry *)0 || ro->ro_rt->rt_ifp == (struct ifnet *)0)) { /* No route yet, so try to acquire one */ ro->ro_dst.sa_family = AF_INET; ro->ro_dst.sa_len = sizeof(struct sockaddr_in); ((struct sockaddr_in *) &ro->ro_dst)->sin_addr = sin->sin_addr; rtalloc(ro); } /* * If we found a route, use the address * corresponding to the outgoing interface * unless it is the loopback (in case a route * to our address on another net goes to loopback). */ if (ro->ro_rt && !(ro->ro_rt->rt_ifp->if_flags & IFF_LOOPBACK)) ia = ifatoia(ro->ro_rt->rt_ifa); if (ia == 0) { u_short fport = sin->sin_port; sin->sin_port = 0; ia = ifatoia(ifa_ifwithdstaddr(sintosa(sin))); if (ia == 0) ia = ifatoia(ifa_ifwithnet(sintosa(sin))); sin->sin_port = fport; if (ia == 0) ia = in_ifaddrhead.tqh_first; if (ia == 0) return (EADDRNOTAVAIL); } /* * If the destination address is multicast and an outgoing * interface has been set as a multicast option, use the * address of that interface as our source address. */ if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr)) && inp->inp_moptions != NULL) { struct ip_moptions *imo; struct ifnet *ifp; imo = inp->inp_moptions; if (imo->imo_multicast_ifp != NULL) { ifp = imo->imo_multicast_ifp; for (ia = in_ifaddrhead.tqh_first; ia; ia = ia->ia_link.tqe_next) if (ia->ia_ifp == ifp) break; if (ia == 0) return (EADDRNOTAVAIL); } } /* * Don't do pcblookup call here; return interface in plocal_sin * and exit to caller, that will do the lookup. */ *plocal_sin = &ia->ia_addr; } return(0); } /* * Outer subroutine: * Connect from a socket to a specified address. * Both address and port must be specified in argument sin. * If don't have a local address for this socket yet, * then pick one. */ int in_pcbconnect(inp, nam, p) register struct inpcb *inp; struct sockaddr *nam; struct proc *p; { struct sockaddr_in *ifaddr; register struct sockaddr_in *sin = (struct sockaddr_in *)nam; int error; /* * Call inner routine, to assign local interface address. */ if ((error = in_pcbladdr(inp, nam, &ifaddr)) != 0) return(error); if (in_pcblookup_hash(inp->inp_pcbinfo, sin->sin_addr, sin->sin_port, inp->inp_laddr.s_addr ? inp->inp_laddr : ifaddr->sin_addr, inp->inp_lport, 0) != NULL) { return (EADDRINUSE); } if (inp->inp_laddr.s_addr == INADDR_ANY) { if (inp->inp_lport == 0) { error = in_pcbbind(inp, (struct sockaddr *)0, p); if (error) return (error); } inp->inp_laddr = ifaddr->sin_addr; } inp->inp_faddr = sin->sin_addr; inp->inp_fport = sin->sin_port; in_pcbrehash(inp); return (0); } void in_pcbdisconnect(inp) struct inpcb *inp; { inp->inp_faddr.s_addr = INADDR_ANY; inp->inp_fport = 0; in_pcbrehash(inp); if (inp->inp_socket->so_state & SS_NOFDREF) in_pcbdetach(inp); } void in_pcbdetach(inp) struct inpcb *inp; { struct socket *so = inp->inp_socket; struct inpcbinfo *ipi = inp->inp_pcbinfo; inp->inp_gencnt = ++ipi->ipi_gencnt; in_pcbremlists(inp); so->so_pcb = 0; sofree(so); if (inp->inp_options) (void)m_free(inp->inp_options); if (inp->inp_route.ro_rt) rtfree(inp->inp_route.ro_rt); ip_freemoptions(inp->inp_moptions); zfreei(ipi->ipi_zone, inp); } /* * The calling convention of in_setsockaddr() and in_setpeeraddr() was * modified to match the pru_sockaddr() and pru_peeraddr() entry points * in struct pr_usrreqs, so that protocols can just reference then directly * without the need for a wrapper function. The socket must have a valid * (i.e., non-nil) PCB, but it should be impossible to get an invalid one * except through a kernel programming error, so it is acceptable to panic * (or in this case trap) if the PCB is invalid. (Actually, we don't trap * because there actually /is/ a programming error somewhere... XXX) */ int in_setsockaddr(so, nam) struct socket *so; struct sockaddr **nam; { int s; register struct inpcb *inp; register struct sockaddr_in *sin; /* * Do the malloc first in case it blocks. */ MALLOC(sin, struct sockaddr_in *, sizeof *sin, M_SONAME, M_WAITOK); bzero(sin, sizeof *sin); sin->sin_family = AF_INET; sin->sin_len = sizeof(*sin); s = splnet(); inp = sotoinpcb(so); if (!inp) { splx(s); free(sin, M_SONAME); return EINVAL; } sin->sin_port = inp->inp_lport; sin->sin_addr = inp->inp_laddr; splx(s); *nam = (struct sockaddr *)sin; return 0; } int in_setpeeraddr(so, nam) struct socket *so; struct sockaddr **nam; { int s; struct inpcb *inp; register struct sockaddr_in *sin; /* * Do the malloc first in case it blocks. */ MALLOC(sin, struct sockaddr_in *, sizeof *sin, M_SONAME, M_WAITOK); bzero((caddr_t)sin, sizeof (*sin)); sin->sin_family = AF_INET; sin->sin_len = sizeof(*sin); s = splnet(); inp = sotoinpcb(so); if (!inp) { splx(s); free(sin, M_SONAME); return EINVAL; } sin->sin_port = inp->inp_fport; sin->sin_addr = inp->inp_faddr; splx(s); *nam = (struct sockaddr *)sin; return 0; } /* * Pass some notification to all connections of a protocol * associated with address dst. The local address and/or port numbers * may be specified to limit the search. The "usual action" will be * taken, depending on the ctlinput cmd. The caller must filter any * cmds that are uninteresting (e.g., no error in the map). * Call the protocol specific routine (if any) to report * any errors for each matching socket. */ void in_pcbnotify(head, dst, fport_arg, laddr, lport_arg, cmd, notify) struct inpcbhead *head; struct sockaddr *dst; u_int fport_arg, lport_arg; struct in_addr laddr; int cmd; void (*notify) __P((struct inpcb *, int)); { register struct inpcb *inp, *oinp; struct in_addr faddr; u_short fport = fport_arg, lport = lport_arg; int errno, s; if ((unsigned)cmd > PRC_NCMDS || dst->sa_family != AF_INET) return; faddr = ((struct sockaddr_in *)dst)->sin_addr; if (faddr.s_addr == INADDR_ANY) return; /* * Redirects go to all references to the destination, * and use in_rtchange to invalidate the route cache. * Dead host indications: notify all references to the destination. * Otherwise, if we have knowledge of the local port and address, * deliver only to that socket. */ if (PRC_IS_REDIRECT(cmd) || cmd == PRC_HOSTDEAD) { fport = 0; lport = 0; laddr.s_addr = 0; if (cmd != PRC_HOSTDEAD) notify = in_rtchange; } errno = inetctlerrmap[cmd]; s = splnet(); for (inp = head->lh_first; inp != NULL;) { if (inp->inp_faddr.s_addr != faddr.s_addr || inp->inp_socket == 0 || (lport && inp->inp_lport != lport) || (laddr.s_addr && inp->inp_laddr.s_addr != laddr.s_addr) || (fport && inp->inp_fport != fport)) { inp = inp->inp_list.le_next; continue; } oinp = inp; inp = inp->inp_list.le_next; if (notify) (*notify)(oinp, errno); } splx(s); } /* * Check for alternatives when higher level complains * about service problems. For now, invalidate cached * routing information. If the route was created dynamically * (by a redirect), time to try a default gateway again. */ void in_losing(inp) struct inpcb *inp; { register struct rtentry *rt; struct rt_addrinfo info; if ((rt = inp->inp_route.ro_rt)) { inp->inp_route.ro_rt = 0; bzero((caddr_t)&info, sizeof(info)); info.rti_info[RTAX_DST] = (struct sockaddr *)&inp->inp_route.ro_dst; info.rti_info[RTAX_GATEWAY] = rt->rt_gateway; info.rti_info[RTAX_NETMASK] = rt_mask(rt); rt_missmsg(RTM_LOSING, &info, rt->rt_flags, 0); if (rt->rt_flags & RTF_DYNAMIC) (void) rtrequest(RTM_DELETE, rt_key(rt), rt->rt_gateway, rt_mask(rt), rt->rt_flags, (struct rtentry **)0); else /* * A new route can be allocated * the next time output is attempted. */ rtfree(rt); } } /* * After a routing change, flush old routing * and allocate a (hopefully) better one. */ static void in_rtchange(inp, errno) register struct inpcb *inp; int errno; { if (inp->inp_route.ro_rt) { rtfree(inp->inp_route.ro_rt); inp->inp_route.ro_rt = 0; /* * A new route can be allocated the next time * output is attempted. */ } } /* * Lookup a PCB based on the local address and port. */ struct inpcb * in_pcblookup_local(pcbinfo, laddr, lport_arg, wild_okay) struct inpcbinfo *pcbinfo; struct in_addr laddr; u_int lport_arg; int wild_okay; { register struct inpcb *inp; int matchwild = 3, wildcard; u_short lport = lport_arg; if (!wild_okay) { struct inpcbhead *head; /* * Look for an unconnected (wildcard foreign addr) PCB that * matches the local address and port we're looking for. */ head = &pcbinfo->hashbase[INP_PCBHASH(INADDR_ANY, lport, 0, pcbinfo->hashmask)]; for (inp = head->lh_first; inp != NULL; inp = inp->inp_hash.le_next) { if (inp->inp_faddr.s_addr == INADDR_ANY && inp->inp_laddr.s_addr == laddr.s_addr && inp->inp_lport == lport) { /* * Found. */ return (inp); } } /* * Not found. */ return (NULL); } else { struct inpcbporthead *porthash; struct inpcbport *phd; struct inpcb *match = NULL; /* * Best fit PCB lookup. * * First see if this local port is in use by looking on the * port hash list. */ porthash = &pcbinfo->porthashbase[INP_PCBPORTHASH(lport, pcbinfo->porthashmask)]; for (phd = porthash->lh_first; phd != NULL; phd = phd->phd_hash.le_next) { if (phd->phd_port == lport) break; } if (phd != NULL) { /* * Port is in use by one or more PCBs. Look for best * fit. */ for (inp = phd->phd_pcblist.lh_first; inp != NULL; inp = inp->inp_portlist.le_next) { wildcard = 0; if (inp->inp_faddr.s_addr != INADDR_ANY) wildcard++; if (inp->inp_laddr.s_addr != INADDR_ANY) { if (laddr.s_addr == INADDR_ANY) wildcard++; else if (inp->inp_laddr.s_addr != laddr.s_addr) continue; } else { if (laddr.s_addr != INADDR_ANY) wildcard++; } if (wildcard < matchwild) { match = inp; matchwild = wildcard; if (matchwild == 0) { break; } } } } return (match); } } /* * Lookup PCB in hash list. */ struct inpcb * in_pcblookup_hash(pcbinfo, faddr, fport_arg, laddr, lport_arg, wildcard) struct inpcbinfo *pcbinfo; struct in_addr faddr, laddr; u_int fport_arg, lport_arg; int wildcard; { struct inpcbhead *head; register struct inpcb *inp; u_short fport = fport_arg, lport = lport_arg; /* * First look for an exact match. */ head = &pcbinfo->hashbase[INP_PCBHASH(faddr.s_addr, lport, fport, pcbinfo->hashmask)]; for (inp = head->lh_first; inp != NULL; inp = inp->inp_hash.le_next) { if (inp->inp_faddr.s_addr == faddr.s_addr && inp->inp_laddr.s_addr == laddr.s_addr && inp->inp_fport == fport && inp->inp_lport == lport) { /* * Found. */ return (inp); } } if (wildcard) { struct inpcb *local_wild = NULL; head = &pcbinfo->hashbase[INP_PCBHASH(INADDR_ANY, lport, 0, pcbinfo->hashmask)]; for (inp = head->lh_first; inp != NULL; inp = inp->inp_hash.le_next) { if (inp->inp_faddr.s_addr == INADDR_ANY && inp->inp_lport == lport) { if (inp->inp_laddr.s_addr == laddr.s_addr) return (inp); else if (inp->inp_laddr.s_addr == INADDR_ANY) local_wild = inp; } } return (local_wild); } /* * Not found. */ return (NULL); } /* * Insert PCB onto various hash lists. */ int in_pcbinshash(inp) struct inpcb *inp; { struct inpcbhead *pcbhash; struct inpcbporthead *pcbporthash; struct inpcbinfo *pcbinfo = inp->inp_pcbinfo; struct inpcbport *phd; pcbhash = &pcbinfo->hashbase[INP_PCBHASH(inp->inp_faddr.s_addr, inp->inp_lport, inp->inp_fport, pcbinfo->hashmask)]; pcbporthash = &pcbinfo->porthashbase[INP_PCBPORTHASH(inp->inp_lport, pcbinfo->porthashmask)]; /* * Go through port list and look for a head for this lport. */ for (phd = pcbporthash->lh_first; phd != NULL; phd = phd->phd_hash.le_next) { if (phd->phd_port == inp->inp_lport) break; } /* * If none exists, malloc one and tack it on. */ if (phd == NULL) { MALLOC(phd, struct inpcbport *, sizeof(struct inpcbport), M_PCB, M_NOWAIT); if (phd == NULL) { return (ENOBUFS); /* XXX */ } phd->phd_port = inp->inp_lport; LIST_INIT(&phd->phd_pcblist); LIST_INSERT_HEAD(pcbporthash, phd, phd_hash); } inp->inp_phd = phd; LIST_INSERT_HEAD(&phd->phd_pcblist, inp, inp_portlist); LIST_INSERT_HEAD(pcbhash, inp, inp_hash); return (0); } /* * Move PCB to the proper hash bucket when { faddr, fport } have been * changed. NOTE: This does not handle the case of the lport changing (the * hashed port list would have to be updated as well), so the lport must * not change after in_pcbinshash() has been called. */ void in_pcbrehash(inp) struct inpcb *inp; { struct inpcbhead *head; head = &inp->inp_pcbinfo->hashbase[INP_PCBHASH(inp->inp_faddr.s_addr, inp->inp_lport, inp->inp_fport, inp->inp_pcbinfo->hashmask)]; LIST_REMOVE(inp, inp_hash); LIST_INSERT_HEAD(head, inp, inp_hash); } /* * Remove PCB from various lists. */ -static void +void in_pcbremlists(inp) struct inpcb *inp; { inp->inp_gencnt = ++inp->inp_pcbinfo->ipi_gencnt; if (inp->inp_lport) { struct inpcbport *phd = inp->inp_phd; LIST_REMOVE(inp, inp_hash); LIST_REMOVE(inp, inp_portlist); if (phd->phd_pcblist.lh_first == NULL) { LIST_REMOVE(phd, phd_hash); free(phd, M_PCB); } } LIST_REMOVE(inp, inp_list); inp->inp_pcbinfo->ipi_count--; } int prison_xinpcb(struct proc *p, struct inpcb *inp) { if (!p->p_prison) return (0); if (ntohl(inp->inp_laddr.s_addr) == p->p_prison->pr_ip) return (0); return (1); } diff --git a/sys/netinet/in_pcb.h b/sys/netinet/in_pcb.h index 0912fea898ea..c891207d8bd3 100644 --- a/sys/netinet/in_pcb.h +++ b/sys/netinet/in_pcb.h @@ -1,174 +1,175 @@ /* * Copyright (c) 1982, 1986, 1990, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)in_pcb.h 8.1 (Berkeley) 6/10/93 * $FreeBSD$ */ #ifndef _NETINET_IN_PCB_H_ #define _NETINET_IN_PCB_H_ #include /* * Common structure pcb for internet protocol implementation. * Here are stored pointers to local and foreign host table * entries, local and foreign socket numbers, and pointers * up (to a socket structure) and down (to a protocol-specific) * control block. */ LIST_HEAD(inpcbhead, inpcb); LIST_HEAD(inpcbporthead, inpcbport); typedef u_quad_t inp_gen_t; /* * NB: the zone allocator is type-stable EXCEPT FOR THE FIRST TWO LONGS * of the structure. Therefore, it is important that the members in * that position not contain any information which is required to be * stable. */ struct inpcb { LIST_ENTRY(inpcb) inp_hash; /* hash list */ struct in_addr inp_faddr; /* foreign host table entry */ struct in_addr inp_laddr; /* local host table entry */ u_short inp_fport; /* foreign port */ u_short inp_lport; /* local port */ LIST_ENTRY(inpcb) inp_list; /* list for all PCBs of this proto */ caddr_t inp_ppcb; /* pointer to per-protocol pcb */ struct inpcbinfo *inp_pcbinfo; /* PCB list info */ struct socket *inp_socket; /* back pointer to socket */ struct mbuf *inp_options; /* IP options */ struct route inp_route; /* placeholder for routing entry */ int inp_flags; /* generic IP/datagram flags */ u_char inp_ip_tos; /* type of service proto */ u_char inp_ip_ttl; /* time to live proto */ u_char inp_ip_p; /* protocol proto */ u_char pad[1]; /* alignment */ struct ip_moptions *inp_moptions; /* IP multicast options */ LIST_ENTRY(inpcb) inp_portlist; /* list for this PCB's local port */ struct inpcbport *inp_phd; /* head of this list */ inp_gen_t inp_gencnt; /* generation count of this instance */ }; /* * The range of the generation count, as used in this implementation, * is 9e19. We would have to create 300 billion connections per * second for this number to roll over in a year. This seems sufficiently * unlikely that we simply don't concern ourselves with that possibility. */ /* * Interface exported to userland by various protocols which use * inpcbs. Hack alert -- only define if struct xsocket is in scope. */ #ifdef _SYS_SOCKETVAR_H_ struct xinpcb { size_t xi_len; /* length of this structure */ struct inpcb xi_inp; struct xsocket xi_socket; u_quad_t xi_alignment_hack; }; struct xinpgen { size_t xig_len; /* length of this structure */ u_int xig_count; /* number of PCBs at this time */ inp_gen_t xig_gen; /* generation count at this time */ so_gen_t xig_sogen; /* socket generation count at this time */ }; #endif /* _SYS_SOCKETVAR_H_ */ struct inpcbport { LIST_ENTRY(inpcbport) phd_hash; struct inpcbhead phd_pcblist; u_short phd_port; }; struct inpcbinfo { /* XXX documentation, prefixes */ struct inpcbhead *hashbase; u_long hashmask; struct inpcbporthead *porthashbase; u_long porthashmask; struct inpcbhead *listhead; u_short lastport; u_short lastlow; u_short lasthi; struct vm_zone *ipi_zone; /* zone to allocate pcbs from */ u_int ipi_count; /* number of pcbs in this list */ u_quad_t ipi_gencnt; /* current generation count */ }; #define INP_PCBHASH(faddr, lport, fport, mask) \ (((faddr) ^ ((faddr) >> 16) ^ ntohs((lport) ^ (fport))) & (mask)) #define INP_PCBPORTHASH(lport, mask) \ (ntohs((lport)) & (mask)) /* flags in inp_flags: */ #define INP_RECVOPTS 0x01 /* receive incoming IP options */ #define INP_RECVRETOPTS 0x02 /* receive IP options for reply */ #define INP_RECVDSTADDR 0x04 /* receive IP dst address */ #define INP_HDRINCL 0x08 /* user supplies entire IP header */ #define INP_HIGHPORT 0x10 /* user wants "high" port binding */ #define INP_LOWPORT 0x20 /* user wants "low" port binding */ #define INP_ANONPORT 0x40 /* port chosen for user */ #define INP_RECVIF 0x80 /* receive incoming interface */ #define INP_MTUDISC 0x100 /* user can do MTU discovery */ #define INP_CONTROLOPTS (INP_RECVOPTS|INP_RECVRETOPTS|INP_RECVDSTADDR|\ INP_RECVIF) #define INPLOOKUP_WILDCARD 1 #define sotoinpcb(so) ((struct inpcb *)(so)->so_pcb) #ifdef KERNEL void in_losing __P((struct inpcb *)); int in_pcballoc __P((struct socket *, struct inpcbinfo *, struct proc *)); int in_pcbbind __P((struct inpcb *, struct sockaddr *, struct proc *)); int in_pcbconnect __P((struct inpcb *, struct sockaddr *, struct proc *)); void in_pcbdetach __P((struct inpcb *)); void in_pcbdisconnect __P((struct inpcb *)); int in_pcbinshash __P((struct inpcb *)); int in_pcbladdr __P((struct inpcb *, struct sockaddr *, struct sockaddr_in **)); struct inpcb * in_pcblookup_local __P((struct inpcbinfo *, struct in_addr, u_int, int)); struct inpcb * in_pcblookup_hash __P((struct inpcbinfo *, struct in_addr, u_int, struct in_addr, u_int, int)); void in_pcbnotify __P((struct inpcbhead *, struct sockaddr *, u_int, struct in_addr, u_int, int, void (*)(struct inpcb *, int))); void in_pcbrehash __P((struct inpcb *)); int in_setpeeraddr __P((struct socket *so, struct sockaddr **nam)); int in_setsockaddr __P((struct socket *so, struct sockaddr **nam)); +void in_pcbremlists __P((struct inpcb *inp)); int prison_xinpcb __P((struct proc *p, struct inpcb *inp)); #endif /* KERNEL */ #endif /* !_NETINET_IN_PCB_H_ */ diff --git a/sys/netinet/in_var.h b/sys/netinet/in_var.h index 9569f48f59a1..c04c7781969f 100644 --- a/sys/netinet/in_var.h +++ b/sys/netinet/in_var.h @@ -1,235 +1,238 @@ /* * Copyright (c) 1985, 1986, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)in_var.h 8.2 (Berkeley) 1/9/95 * $FreeBSD$ */ #ifndef _NETINET_IN_VAR_H_ #define _NETINET_IN_VAR_H_ #include /* * Interface address, Internet version. One of these structures * is allocated for each Internet address on an interface. * The ifaddr structure contains the protocol-independent part * of the structure and is assumed to be first. */ struct in_ifaddr { struct ifaddr ia_ifa; /* protocol-independent info */ #define ia_ifp ia_ifa.ifa_ifp #define ia_flags ia_ifa.ifa_flags /* ia_{,sub}net{,mask} in host order */ u_long ia_net; /* network number of interface */ u_long ia_netmask; /* mask of net part */ u_long ia_subnet; /* subnet number, including net */ u_long ia_subnetmask; /* mask of subnet part */ struct in_addr ia_netbroadcast; /* to recognize net broadcasts */ TAILQ_ENTRY(in_ifaddr) ia_link; /* tailq macro glue */ struct sockaddr_in ia_addr; /* reserve space for interface name */ struct sockaddr_in ia_dstaddr; /* reserve space for broadcast addr */ #define ia_broadaddr ia_dstaddr struct sockaddr_in ia_sockmask; /* reserve space for general netmask */ }; struct in_aliasreq { char ifra_name[IFNAMSIZ]; /* if name, e.g. "en0" */ struct sockaddr_in ifra_addr; struct sockaddr_in ifra_broadaddr; #define ifra_dstaddr ifra_broadaddr struct sockaddr_in ifra_mask; }; /* * Given a pointer to an in_ifaddr (ifaddr), * return a pointer to the addr as a sockaddr_in. */ #define IA_SIN(ia) (&(((struct in_ifaddr *)(ia))->ia_addr)) #define IA_DSTSIN(ia) (&(((struct in_ifaddr *)(ia))->ia_dstaddr)) #define IN_LNAOF(in, ifa) \ ((ntohl((in).s_addr) & ~((struct in_ifaddr *)(ifa)->ia_subnetmask)) #ifdef KERNEL extern TAILQ_HEAD(in_ifaddrhead, in_ifaddr) in_ifaddrhead; extern struct ifqueue ipintrq; /* ip packet input queue */ extern struct in_addr zeroin_addr; extern u_char inetctlerrmap[]; /* * Macro for finding the interface (ifnet structure) corresponding to one * of our IP addresses. */ #define INADDR_TO_IFP(addr, ifp) \ /* struct in_addr addr; */ \ /* struct ifnet *ifp; */ \ { \ register struct in_ifaddr *ia; \ \ for (ia = in_ifaddrhead.tqh_first; \ ia != NULL && ((ia->ia_ifp->if_flags & IFF_POINTOPOINT)? \ IA_DSTSIN(ia):IA_SIN(ia))->sin_addr.s_addr != (addr).s_addr; \ ia = ia->ia_link.tqe_next) \ continue; \ if (ia == NULL) \ for (ia = in_ifaddrhead.tqh_first; \ ia != NULL; \ ia = ia->ia_link.tqe_next) \ if (ia->ia_ifp->if_flags & IFF_POINTOPOINT && \ IA_SIN(ia)->sin_addr.s_addr == (addr).s_addr) \ break; \ (ifp) = (ia == NULL) ? NULL : ia->ia_ifp; \ } /* * Macro for finding the internet address structure (in_ifaddr) corresponding * to a given interface (ifnet structure). */ #define IFP_TO_IA(ifp, ia) \ /* struct ifnet *ifp; */ \ /* struct in_ifaddr *ia; */ \ { \ for ((ia) = in_ifaddrhead.tqh_first; \ (ia) != NULL && (ia)->ia_ifp != (ifp); \ (ia) = (ia)->ia_link.tqe_next) \ continue; \ } #endif /* * This information should be part of the ifnet structure but we don't wish * to change that - as it might break a number of things */ struct router_info { struct ifnet *rti_ifp; int rti_type; /* type of router which is querier on this interface */ int rti_time; /* # of slow timeouts since last old query */ struct router_info *rti_next; }; /* * Internet multicast address structure. There is one of these for each IP * multicast group to which this host belongs on a given network interface. * For every entry on the interface's if_multiaddrs list which represents * an IP multicast group, there is one of these structures. They are also * kept on a system-wide list to make it easier to keep our legacy IGMP code * compatible with the rest of the world (see IN_FIRST_MULTI et al, below). */ struct in_multi { LIST_ENTRY(in_multi) inm_link; /* queue macro glue */ struct in_addr inm_addr; /* IP multicast address, convenience */ struct ifnet *inm_ifp; /* back pointer to ifnet */ struct ifmultiaddr *inm_ifma; /* back pointer to ifmultiaddr */ u_int inm_timer; /* IGMP membership report timer */ u_int inm_state; /* state of the membership */ struct router_info *inm_rti; /* router info*/ }; #ifdef KERNEL #ifdef SYSCTL_DECL SYSCTL_DECL(_net_inet_ip); SYSCTL_DECL(_net_inet_raw); #endif extern LIST_HEAD(in_multihead, in_multi) in_multihead; /* * Structure used by macros below to remember position when stepping through * all of the in_multi records. */ struct in_multistep { struct in_multi *i_inm; }; /* * Macro for looking up the in_multi record for a given IP multicast address * on a given interface. If no matching record is found, "inm" is set null. */ #define IN_LOOKUP_MULTI(addr, ifp, inm) \ /* struct in_addr addr; */ \ /* struct ifnet *ifp; */ \ /* struct in_multi *inm; */ \ do { \ register struct ifmultiaddr *ifma; \ \ for (ifma = (ifp)->if_multiaddrs.lh_first; ifma; \ ifma = ifma->ifma_link.le_next) { \ if (ifma->ifma_addr->sa_family == AF_INET \ && ((struct sockaddr_in *)ifma->ifma_addr)->sin_addr.s_addr == \ (addr).s_addr) \ break; \ } \ (inm) = ifma ? ifma->ifma_protospec : 0; \ } while(0) /* * Macro to step through all of the in_multi records, one at a time. * The current position is remembered in "step", which the caller must * provide. IN_FIRST_MULTI(), below, must be called to initialize "step" * and get the first record. Both macros return a NULL "inm" when there * are no remaining records. */ #define IN_NEXT_MULTI(step, inm) \ /* struct in_multistep step; */ \ /* struct in_multi *inm; */ \ do { \ if (((inm) = (step).i_inm) != NULL) \ (step).i_inm = (step).i_inm->inm_link.le_next; \ } while(0) #define IN_FIRST_MULTI(step, inm) \ /* struct in_multistep step; */ \ /* struct in_multi *inm; */ \ do { \ (step).i_inm = in_multihead.lh_first; \ IN_NEXT_MULTI((step), (inm)); \ } while(0) struct route; struct in_multi *in_addmulti __P((struct in_addr *, struct ifnet *)); void in_delmulti __P((struct in_multi *)); int in_control __P((struct socket *, u_long, caddr_t, struct ifnet *, struct proc *)); void in_rtqdrain __P((void)); void ip_input __P((struct mbuf *)); int in_ifadown __P((struct ifaddr *ifa)); void in_ifscrub __P((struct ifnet *, struct in_ifaddr *)); int ipflow_fastforward __P((struct mbuf *)); void ipflow_create __P((const struct route *, struct mbuf *)); void ipflow_slowtimo __P((void)); #endif /* KERNEL */ +/* INET6 stuff */ +#include + #endif /* _NETINET_IN_VAR_H_ */ diff --git a/sys/netinet/ip_var.h b/sys/netinet/ip_var.h index 08b3a06d3304..1b69ec24847b 100644 --- a/sys/netinet/ip_var.h +++ b/sys/netinet/ip_var.h @@ -1,190 +1,191 @@ /* * Copyright (c) 1982, 1986, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)ip_var.h 8.2 (Berkeley) 1/9/95 * $FreeBSD$ */ #ifndef _NETINET_IP_VAR_H_ #define _NETINET_IP_VAR_H_ /* * Overlay for ip header used by other protocols (tcp, udp). */ struct ipovly { u_char ih_x1[9]; /* (unused) */ u_char ih_pr; /* protocol */ u_short ih_len; /* protocol length */ struct in_addr ih_src; /* source internet address */ struct in_addr ih_dst; /* destination internet address */ }; /* * Ip reassembly queue structure. Each fragment * being reassembled is attached to one of these structures. * They are timed out after ipq_ttl drops to 0, and may also * be reclaimed if memory becomes tight. */ struct ipq { struct ipq *next,*prev; /* to other reass headers */ u_char ipq_ttl; /* time for reass q to live */ u_char ipq_p; /* protocol of this fragment */ u_short ipq_id; /* sequence id for reassembly */ struct mbuf *ipq_frags; /* to ip headers of fragments */ struct in_addr ipq_src,ipq_dst; #ifdef IPDIVERT u_short ipq_divert; /* divert protocol port */ u_short ipq_div_cookie; /* divert protocol cookie */ #endif }; /* * Structure stored in mbuf in inpcb.ip_options * and passed to ip_output when ip options are in use. * The actual length of the options (including ipopt_dst) * is in m_len. */ #define MAX_IPOPTLEN 40 struct ipoption { struct in_addr ipopt_dst; /* first-hop dst if source routed */ char ipopt_list[MAX_IPOPTLEN]; /* options proper */ }; /* * Structure attached to inpcb.ip_moptions and * passed to ip_output when IP multicast options are in use. */ struct ip_moptions { struct ifnet *imo_multicast_ifp; /* ifp for outgoing multicasts */ u_char imo_multicast_ttl; /* TTL for outgoing multicasts */ u_char imo_multicast_loop; /* 1 => hear sends if a member */ u_short imo_num_memberships; /* no. memberships this socket */ struct in_multi *imo_membership[IP_MAX_MEMBERSHIPS]; u_long imo_multicast_vif; /* vif num outgoing multicasts */ }; struct ipstat { u_long ips_total; /* total packets received */ u_long ips_badsum; /* checksum bad */ u_long ips_tooshort; /* packet too short */ u_long ips_toosmall; /* not enough data */ u_long ips_badhlen; /* ip header length < data size */ u_long ips_badlen; /* ip length < ip header length */ u_long ips_fragments; /* fragments received */ u_long ips_fragdropped; /* frags dropped (dups, out of space) */ u_long ips_fragtimeout; /* fragments timed out */ u_long ips_forward; /* packets forwarded */ u_long ips_fastforward; /* packets fast forwarded */ u_long ips_cantforward; /* packets rcvd for unreachable dest */ u_long ips_redirectsent; /* packets forwarded on same net */ u_long ips_noproto; /* unknown or unsupported protocol */ u_long ips_delivered; /* datagrams delivered to upper level*/ u_long ips_localout; /* total ip packets generated here */ u_long ips_odropped; /* lost packets due to nobufs, etc. */ u_long ips_reassembled; /* total packets reassembled ok */ u_long ips_fragmented; /* datagrams successfully fragmented */ u_long ips_ofragments; /* output fragments created */ u_long ips_cantfrag; /* don't fragment flag was set, etc. */ u_long ips_badoptions; /* error in option processing */ u_long ips_noroute; /* packets discarded due to no route */ u_long ips_badvers; /* ip version != 4 */ u_long ips_rawout; /* total raw ip packets generated */ u_long ips_toolong; /* ip length > max ip packet size */ u_long ips_notmember; /* multicasts for unregistered grps */ + u_long ips_nogif; /* no match gif found */ }; #ifdef KERNEL /* flags passed to ip_output as last parameter */ #define IP_FORWARDING 0x1 /* most of ip header exists */ #define IP_RAWOUTPUT 0x2 /* raw ip header exists */ #define IP_ROUTETOIF SO_DONTROUTE /* bypass routing tables */ #define IP_ALLOWBROADCAST SO_BROADCAST /* can send broadcast packets */ struct ip; struct inpcb; struct route; struct sockopt; extern struct ipstat ipstat; extern u_short ip_id; /* ip packet ctr, for ids */ extern int ip_defttl; /* default IP ttl */ extern int ipforwarding; /* ip forwarding */ extern u_char ip_protox[]; extern struct socket *ip_rsvpd; /* reservation protocol daemon */ extern struct socket *ip_mrouter; /* multicast routing daemon */ extern int (*legal_vif_num) __P((int)); extern u_long (*ip_mcast_src) __P((int)); extern int rsvp_on; extern struct pr_usrreqs rip_usrreqs; int ip_ctloutput __P((struct socket *, struct sockopt *sopt)); void ip_drain __P((void)); void ip_freemoptions __P((struct ip_moptions *)); void ip_init __P((void)); extern int (*ip_mforward) __P((struct ip *, struct ifnet *, struct mbuf *, struct ip_moptions *)); int ip_output __P((struct mbuf *, struct mbuf *, struct route *, int, struct ip_moptions *)); void ip_savecontrol __P((struct inpcb *, struct mbuf **, struct ip *, struct mbuf *)); void ip_slowtimo __P((void)); struct mbuf * ip_srcroute __P((void)); void ip_stripoptions __P((struct mbuf *, struct mbuf *)); int rip_ctloutput __P((struct socket *, struct sockopt *)); void rip_ctlinput __P((int, struct sockaddr *, void *)); void rip_init __P((void)); void rip_input __P((struct mbuf *, int)); int rip_output __P((struct mbuf *, struct socket *, u_long)); void ipip_input __P((struct mbuf *, int)); void rsvp_input __P((struct mbuf *, int)); int ip_rsvp_init __P((struct socket *)); int ip_rsvp_done __P((void)); int ip_rsvp_vif_init __P((struct socket *, struct sockopt *)); int ip_rsvp_vif_done __P((struct socket *, struct sockopt *)); void ip_rsvp_force_done __P((struct socket *)); #ifdef IPDIVERT void div_init __P((void)); void div_input __P((struct mbuf *, int)); extern struct pr_usrreqs div_usrreqs; extern u_short ip_divert_port; extern u_short ip_divert_cookie; #endif extern struct sockaddr_in *ip_fw_fwd_addr; #endif /* KERNEL */ #endif /* !_NETINET_IP_VAR_H_ */ diff --git a/sys/netinet/tcp.h b/sys/netinet/tcp.h index 268b54e272c1..436f23a86260 100644 --- a/sys/netinet/tcp.h +++ b/sys/netinet/tcp.h @@ -1,122 +1,130 @@ /* * Copyright (c) 1982, 1986, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)tcp.h 8.1 (Berkeley) 6/10/93 * $FreeBSD$ */ #ifndef _NETINET_TCP_H_ #define _NETINET_TCP_H_ typedef u_int32_t tcp_seq; typedef u_int32_t tcp_cc; /* connection count per rfc1644 */ /* * TCP header. * Per RFC 793, September, 1981. */ struct tcphdr { u_short th_sport; /* source port */ u_short th_dport; /* destination port */ tcp_seq th_seq; /* sequence number */ tcp_seq th_ack; /* acknowledgement number */ #if BYTE_ORDER == LITTLE_ENDIAN u_int th_x2:4, /* (unused) */ th_off:4; /* data offset */ #endif #if BYTE_ORDER == BIG_ENDIAN u_int th_off:4, /* data offset */ th_x2:4; /* (unused) */ #endif u_char th_flags; #define TH_FIN 0x01 #define TH_SYN 0x02 #define TH_RST 0x04 #define TH_PUSH 0x08 #define TH_ACK 0x10 #define TH_URG 0x20 #define TH_FLAGS (TH_FIN|TH_SYN|TH_RST|TH_ACK|TH_URG) u_short th_win; /* window */ u_short th_sum; /* checksum */ u_short th_urp; /* urgent pointer */ }; #define TCPOPT_EOL 0 #define TCPOPT_NOP 1 #define TCPOPT_MAXSEG 2 #define TCPOLEN_MAXSEG 4 #define TCPOPT_WINDOW 3 #define TCPOLEN_WINDOW 3 #define TCPOPT_SACK_PERMITTED 4 /* Experimental */ #define TCPOLEN_SACK_PERMITTED 2 #define TCPOPT_SACK 5 /* Experimental */ #define TCPOPT_TIMESTAMP 8 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_TSTAMP_APPA (TCPOLEN_TIMESTAMP+2) /* appendix A */ #define TCPOPT_TSTAMP_HDR \ (TCPOPT_NOP<<24|TCPOPT_NOP<<16|TCPOPT_TIMESTAMP<<8|TCPOLEN_TIMESTAMP) #define TCPOPT_CC 11 /* CC options: RFC-1644 */ #define TCPOPT_CCNEW 12 #define TCPOPT_CCECHO 13 #define TCPOLEN_CC 6 #define TCPOLEN_CC_APPA (TCPOLEN_CC+2) #define TCPOPT_CC_HDR(ccopt) \ (TCPOPT_NOP<<24|TCPOPT_NOP<<16|(ccopt)<<8|TCPOLEN_CC) /* * Default maximum segment size for TCP. * With an IP MSS of 576, this is 536, * but 512 is probably more convenient. * This should be defined as MIN(512, IP_MSS - sizeof (struct tcpiphdr)). */ #define TCP_MSS 512 +/* + * Default maximum segment size for TCP6. + * With an IP6 MSS of 1280, this is 1220, + * but 1024 is probably more convenient. (xxx kazu in doubt) + * This should be defined as MIN(1024, IP6_MSS - sizeof (struct tcpip6hdr)) + */ +#define TCP6_MSS 1024 + #define TCP_MAXWIN 65535 /* largest value for (unscaled) window */ #define TTCP_CLIENT_SND_WND 4096 /* dflt send window for T/TCP client */ #define TCP_MAX_WINSHIFT 14 /* maximum window shift */ #define TCP_MAXHLEN (0xf<<2) /* max length of header in bytes */ #define TCP_MAXOLEN (TCP_MAXHLEN - sizeof(struct tcphdr)) /* max space left for options */ /* * User-settable options (used with setsockopt). */ #define TCP_NODELAY 0x01 /* don't delay send to coalesce packets */ #define TCP_MAXSEG 0x02 /* set maximum segment size */ #define TCP_NOPUSH 0x04 /* don't push last block of write */ #define TCP_NOOPT 0x08 /* don't use TCP options */ #endif diff --git a/sys/netinet/tcp_fsm.h b/sys/netinet/tcp_fsm.h index 2af6e2b6d0e4..eb9a909a2dfb 100644 --- a/sys/netinet/tcp_fsm.h +++ b/sys/netinet/tcp_fsm.h @@ -1,100 +1,114 @@ /* * Copyright (c) 1982, 1986, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)tcp_fsm.h 8.1 (Berkeley) 6/10/93 * $FreeBSD$ */ #ifndef _NETINET_TCP_FSM_H_ #define _NETINET_TCP_FSM_H_ /* * TCP FSM state definitions. * Per RFC793, September, 1981. */ #define TCP_NSTATES 11 #define TCPS_CLOSED 0 /* closed */ #define TCPS_LISTEN 1 /* listening for connection */ #define TCPS_SYN_SENT 2 /* active, have sent syn */ #define TCPS_SYN_RECEIVED 3 /* have send and received syn */ /* states < TCPS_ESTABLISHED are those where connections not established */ #define TCPS_ESTABLISHED 4 /* established */ #define TCPS_CLOSE_WAIT 5 /* rcvd fin, waiting for close */ /* states > TCPS_CLOSE_WAIT are those where user has closed */ #define TCPS_FIN_WAIT_1 6 /* have closed, sent fin */ #define TCPS_CLOSING 7 /* closed xchd FIN; await FIN ACK */ #define TCPS_LAST_ACK 8 /* had fin and close; await FIN ACK */ /* states > TCPS_CLOSE_WAIT && < TCPS_FIN_WAIT_2 await ACK of FIN */ #define TCPS_FIN_WAIT_2 9 /* have closed, fin is acked */ #define TCPS_TIME_WAIT 10 /* in 2*msl quiet wait after close */ +/* for KAME src sync over BSD*'s */ +#define TCP6_NSTATES TCP_NSTATES +#define TCP6S_CLOSED TCPS_CLOSED +#define TCP6S_LISTEN TCPS_LISTEN +#define TCP6S_SYN_SENT TCPS_SYN_SENT +#define TCP6S_SYN_RECEIVED TCPS_SYN_RECEIVED +#define TCP6S_ESTABLISHED TCPS_ESTABLISHED +#define TCP6S_CLOSE_WAIT TCPS_CLOSE_WAIT +#define TCP6S_FIN_WAIT_1 TCPS_FIN_WAIT_1 +#define TCP6S_CLOSING TCPS_CLOSING +#define TCP6S_LAST_ACK TCPS_LAST_ACK +#define TCP6S_FIN_WAIT_2 TCPS_FIN_WAIT_2 +#define TCP6S_TIME_WAIT TCPS_TIME_WAIT + #define TCPS_HAVERCVDSYN(s) ((s) >= TCPS_SYN_RECEIVED) -#define TCPS_HAVEESTABLISHED(s) ((s) >= TCPS_ESTABLISHED) +#define TCPS_HAVEESTABLISHED(s) ((s) >= TCPS_ESTABLISHED) #define TCPS_HAVERCVDFIN(s) ((s) >= TCPS_TIME_WAIT) #ifdef TCPOUTFLAGS /* * Flags used when sending segments in tcp_output. * Basic flags (TH_RST,TH_ACK,TH_SYN,TH_FIN) are totally * determined by state, with the proviso that TH_FIN is sent only * if all data queued for output is included in the segment. */ static u_char tcp_outflags[TCP_NSTATES] = { TH_RST|TH_ACK, /* 0, CLOSED */ 0, /* 1, LISTEN */ TH_SYN, /* 2, SYN_SENT */ TH_SYN|TH_ACK, /* 3, SYN_RECEIVED */ TH_ACK, /* 4, ESTABLISHED */ TH_ACK, /* 5, CLOSE_WAIT */ TH_FIN|TH_ACK, /* 6, FIN_WAIT_1 */ TH_ACK, /* 7, CLOSING */ TH_FIN|TH_ACK, /* 8, LAST_ACK */ TH_ACK, /* 9, FIN_WAIT_2 */ TH_ACK, /* 10, TIME_WAIT */ }; #endif #ifdef KPROF int tcp_acounts[TCP_NSTATES][PRU_NREQ]; #endif #ifdef TCPSTATES char *tcpstates[] = { "CLOSED", "LISTEN", "SYN_SENT", "SYN_RCVD", "ESTABLISHED", "CLOSE_WAIT", "FIN_WAIT_1", "CLOSING", "LAST_ACK", "FIN_WAIT_2", "TIME_WAIT", }; #endif #endif diff --git a/sys/netinet/tcp_subr.c b/sys/netinet/tcp_subr.c index 07da9545535a..68c69b0e1b04 100644 --- a/sys/netinet/tcp_subr.c +++ b/sys/netinet/tcp_subr.c @@ -1,832 +1,838 @@ /* * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1995 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)tcp_subr.c 8.2 (Berkeley) 5/24/95 * $FreeBSD$ */ #include "opt_compat.h" #include "opt_tcpdebug.h" #include #include #include #include #include #include #include #include #include #include #include #include #include #include #define _IP_VHL #include #include #include #include #include #include #include #include #include #include #include #include #ifdef TCPDEBUG #include #endif int tcp_mssdflt = TCP_MSS; SYSCTL_INT(_net_inet_tcp, TCPCTL_MSSDFLT, mssdflt, CTLFLAG_RW, &tcp_mssdflt , 0, "Default TCP Maximum Segment Size"); +#ifdef INET6 +int tcp_v6mssdflt = TCP6_MSS; +SYSCTL_INT(_net_inet_tcp, TCPCTL_V6MSSDFLT, v6mssdflt, + CTLFLAG_RW, &tcp_v6mssdflt , 0, ""); +#endif + #if 0 static int tcp_rttdflt = TCPTV_SRTTDFLT / PR_SLOWHZ; SYSCTL_INT(_net_inet_tcp, TCPCTL_RTTDFLT, rttdflt, CTLFLAG_RW, &tcp_rttdflt , 0, "Default maximum TCP Round Trip Time"); #endif static int tcp_do_rfc1323 = 1; SYSCTL_INT(_net_inet_tcp, TCPCTL_DO_RFC1323, rfc1323, CTLFLAG_RW, &tcp_do_rfc1323 , 0, "Enable rfc1323 (high performance TCP) extensions"); static int tcp_do_rfc1644 = 0; SYSCTL_INT(_net_inet_tcp, TCPCTL_DO_RFC1644, rfc1644, CTLFLAG_RW, &tcp_do_rfc1644 , 0, "Enable rfc1644 (TTCP) extensions"); static int tcp_tcbhashsize = 0; SYSCTL_INT(_net_inet_tcp, OID_AUTO, tcbhashsize, CTLFLAG_RD, &tcp_tcbhashsize, 0, "Size of TCP control-block hashtable"); SYSCTL_INT(_net_inet_tcp, OID_AUTO, pcbcount, CTLFLAG_RD, &tcbinfo.ipi_count, 0, "Number of active PCBs"); static void tcp_cleartaocache __P((void)); static void tcp_notify __P((struct inpcb *, int)); /* * Target size of TCP PCB hash tables. Must be a power of two. * * Note that this can be overridden by the kernel environment * variable net.inet.tcp.tcbhashsize */ #ifndef TCBHASHSIZE #define TCBHASHSIZE 512 #endif /* * This is the actual shape of what we allocate using the zone * allocator. Doing it this way allows us to protect both structures * using the same generation count, and also eliminates the overhead * of allocating tcpcbs separately. By hiding the structure here, * we avoid changing most of the rest of the code (although it needs * to be changed, eventually, for greater efficiency). */ #define ALIGNMENT 32 #define ALIGNM1 (ALIGNMENT - 1) struct inp_tp { union { struct inpcb inp; char align[(sizeof(struct inpcb) + ALIGNM1) & ~ALIGNM1]; } inp_tp_u; struct tcpcb tcb; struct callout inp_tp_rexmt, inp_tp_persist, inp_tp_keep, inp_tp_2msl; struct callout inp_tp_delack; }; #undef ALIGNMENT #undef ALIGNM1 /* * Tcp initialization */ void tcp_init() { int hashsize; tcp_iss = random(); /* wrong, but better than a constant */ tcp_ccgen = 1; tcp_cleartaocache(); tcp_delacktime = TCPTV_DELACK; tcp_keepinit = TCPTV_KEEP_INIT; tcp_keepidle = TCPTV_KEEP_IDLE; tcp_keepintvl = TCPTV_KEEPINTVL; tcp_maxpersistidle = TCPTV_KEEP_IDLE; tcp_msl = TCPTV_MSL; LIST_INIT(&tcb); tcbinfo.listhead = &tcb; TUNABLE_INT_FETCH("net.inet.tcp.tcbhashsize", TCBHASHSIZE, hashsize); if (!powerof2(hashsize)) { printf("WARNING: TCB hash size not a power of 2\n"); hashsize = 512; /* safe default */ } tcp_tcbhashsize = hashsize; tcbinfo.hashbase = hashinit(hashsize, M_PCB, &tcbinfo.hashmask); tcbinfo.porthashbase = hashinit(hashsize, M_PCB, &tcbinfo.porthashmask); tcbinfo.ipi_zone = zinit("tcpcb", sizeof(struct inp_tp), maxsockets, ZONE_INTERRUPT, 0); if (max_protohdr < sizeof(struct tcpiphdr)) max_protohdr = sizeof(struct tcpiphdr); if (max_linkhdr + sizeof(struct tcpiphdr) > MHLEN) panic("tcp_init"); } /* * Create template to be used to send tcp packets on a connection. * Call after host entry created, allocates an mbuf and fills * in a skeletal tcp/ip header, minimizing the amount of work * necessary when the connection is used. */ struct tcpiphdr * tcp_template(tp) struct tcpcb *tp; { register struct inpcb *inp = tp->t_inpcb; register struct mbuf *m; register struct tcpiphdr *n; if ((n = tp->t_template) == 0) { m = m_get(M_DONTWAIT, MT_HEADER); if (m == NULL) return (0); m->m_len = sizeof (struct tcpiphdr); n = mtod(m, struct tcpiphdr *); } bzero(n->ti_x1, sizeof(n->ti_x1)); n->ti_pr = IPPROTO_TCP; n->ti_len = htons(sizeof (struct tcpiphdr) - sizeof (struct ip)); n->ti_src = inp->inp_laddr; n->ti_dst = inp->inp_faddr; n->ti_sport = inp->inp_lport; n->ti_dport = inp->inp_fport; n->ti_seq = 0; n->ti_ack = 0; n->ti_x2 = 0; n->ti_off = 5; n->ti_flags = 0; n->ti_win = 0; n->ti_sum = 0; n->ti_urp = 0; return (n); } /* * Send a single message to the TCP at address specified by * the given TCP/IP header. If m == 0, then we make a copy * of the tcpiphdr at ti and send directly to the addressed host. * This is used to force keep alive messages out using the TCP * template for a connection tp->t_template. If flags are given * then we send a message back to the TCP which originated the * segment ti, and discard the mbuf containing it and any other * attached mbufs. * * In any case the ack and sequence number of the transmitted * segment are as specified by the parameters. * * NOTE: If m != NULL, then ti must point to *inside* the mbuf. */ void tcp_respond(tp, ti, m, ack, seq, flags) struct tcpcb *tp; register struct tcpiphdr *ti; register struct mbuf *m; tcp_seq ack, seq; int flags; { register int tlen; int win = 0; struct route *ro = 0; struct route sro; if (tp) { if (!(flags & TH_RST)) win = sbspace(&tp->t_inpcb->inp_socket->so_rcv); ro = &tp->t_inpcb->inp_route; } else { ro = &sro; bzero(ro, sizeof *ro); } if (m == 0) { m = m_gethdr(M_DONTWAIT, MT_HEADER); if (m == NULL) return; #ifdef TCP_COMPAT_42 tlen = 1; #else tlen = 0; #endif m->m_data += max_linkhdr; *mtod(m, struct tcpiphdr *) = *ti; ti = mtod(m, struct tcpiphdr *); flags = TH_ACK; } else { m_freem(m->m_next); m->m_next = 0; m->m_data = (caddr_t)ti; m->m_len = sizeof (struct tcpiphdr); tlen = 0; #define xchg(a,b,type) { type t; t=a; a=b; b=t; } xchg(ti->ti_dst.s_addr, ti->ti_src.s_addr, n_long); xchg(ti->ti_dport, ti->ti_sport, n_short); #undef xchg } ti->ti_len = htons((u_short)(sizeof (struct tcphdr) + tlen)); tlen += sizeof (struct tcpiphdr); m->m_len = tlen; m->m_pkthdr.len = tlen; m->m_pkthdr.rcvif = (struct ifnet *) 0; bzero(ti->ti_x1, sizeof(ti->ti_x1)); ti->ti_seq = htonl(seq); ti->ti_ack = htonl(ack); ti->ti_x2 = 0; ti->ti_off = sizeof (struct tcphdr) >> 2; ti->ti_flags = flags; if (tp) ti->ti_win = htons((u_short) (win >> tp->rcv_scale)); else ti->ti_win = htons((u_short)win); ti->ti_urp = 0; ti->ti_sum = 0; ti->ti_sum = in_cksum(m, tlen); ((struct ip *)ti)->ip_len = tlen; ((struct ip *)ti)->ip_ttl = ip_defttl; #ifdef TCPDEBUG if (tp == NULL || (tp->t_inpcb->inp_socket->so_options & SO_DEBUG)) tcp_trace(TA_OUTPUT, 0, tp, ti, 0); #endif (void) ip_output(m, NULL, ro, 0, NULL); if (ro == &sro && ro->ro_rt) { RTFREE(ro->ro_rt); } } /* * Create a new TCP control block, making an * empty reassembly queue and hooking it to the argument * protocol control block. The `inp' parameter must have * come from the zone allocator set up in tcp_init(). */ struct tcpcb * tcp_newtcpcb(inp) struct inpcb *inp; { struct inp_tp *it; register struct tcpcb *tp; it = (struct inp_tp *)inp; tp = &it->tcb; bzero((char *) tp, sizeof(struct tcpcb)); tp->t_segq = NULL; tp->t_maxseg = tp->t_maxopd = tcp_mssdflt; /* Set up our timeouts. */ callout_init(tp->tt_rexmt = &it->inp_tp_rexmt); callout_init(tp->tt_persist = &it->inp_tp_persist); callout_init(tp->tt_keep = &it->inp_tp_keep); callout_init(tp->tt_2msl = &it->inp_tp_2msl); callout_init(tp->tt_delack = &it->inp_tp_delack); if (tcp_do_rfc1323) tp->t_flags = (TF_REQ_SCALE|TF_REQ_TSTMP); if (tcp_do_rfc1644) tp->t_flags |= TF_REQ_CC; tp->t_inpcb = inp; /* XXX */ /* * Init srtt to TCPTV_SRTTBASE (0), so we can tell that we have no * rtt estimate. Set rttvar so that srtt + 4 * rttvar gives * reasonable initial retransmit time. */ tp->t_srtt = TCPTV_SRTTBASE; tp->t_rttvar = ((TCPTV_RTOBASE - TCPTV_SRTTBASE) << TCP_RTTVAR_SHIFT) / 4; tp->t_rttmin = TCPTV_MIN; tp->t_rxtcur = TCPTV_RTOBASE; tp->snd_cwnd = TCP_MAXWIN << TCP_MAX_WINSHIFT; tp->snd_ssthresh = TCP_MAXWIN << TCP_MAX_WINSHIFT; tp->t_rcvtime = ticks; inp->inp_ip_ttl = ip_defttl; inp->inp_ppcb = (caddr_t)tp; return (tp); /* XXX */ } /* * Drop a TCP connection, reporting * the specified error. If connection is synchronized, * then send a RST to peer. */ struct tcpcb * tcp_drop(tp, errno) register struct tcpcb *tp; int errno; { struct socket *so = tp->t_inpcb->inp_socket; if (TCPS_HAVERCVDSYN(tp->t_state)) { tp->t_state = TCPS_CLOSED; (void) tcp_output(tp); tcpstat.tcps_drops++; } else tcpstat.tcps_conndrops++; if (errno == ETIMEDOUT && tp->t_softerror) errno = tp->t_softerror; so->so_error = errno; return (tcp_close(tp)); } /* * Close a TCP control block: * discard all space held by the tcp * discard internet protocol block * wake up any sleepers */ struct tcpcb * tcp_close(tp) register struct tcpcb *tp; { register struct mbuf *q; register struct mbuf *nq; struct inpcb *inp = tp->t_inpcb; struct socket *so = inp->inp_socket; register struct rtentry *rt; int dosavessthresh; /* * Make sure that all of our timers are stopped before we * delete the PCB. */ callout_stop(tp->tt_rexmt); callout_stop(tp->tt_persist); callout_stop(tp->tt_keep); callout_stop(tp->tt_2msl); callout_stop(tp->tt_delack); /* * If we got enough samples through the srtt filter, * save the rtt and rttvar in the routing entry. * 'Enough' is arbitrarily defined as the 16 samples. * 16 samples is enough for the srtt filter to converge * to within 5% of the correct value; fewer samples and * we could save a very bogus rtt. * * Don't update the default route's characteristics and don't * update anything that the user "locked". */ if (tp->t_rttupdated >= 16 && (rt = inp->inp_route.ro_rt) && ((struct sockaddr_in *)rt_key(rt))->sin_addr.s_addr != INADDR_ANY) { register u_long i = 0; if ((rt->rt_rmx.rmx_locks & RTV_RTT) == 0) { i = tp->t_srtt * (RTM_RTTUNIT / (hz * TCP_RTT_SCALE)); if (rt->rt_rmx.rmx_rtt && i) /* * filter this update to half the old & half * the new values, converting scale. * See route.h and tcp_var.h for a * description of the scaling constants. */ rt->rt_rmx.rmx_rtt = (rt->rt_rmx.rmx_rtt + i) / 2; else rt->rt_rmx.rmx_rtt = i; tcpstat.tcps_cachedrtt++; } if ((rt->rt_rmx.rmx_locks & RTV_RTTVAR) == 0) { i = tp->t_rttvar * (RTM_RTTUNIT / (hz * TCP_RTTVAR_SCALE)); if (rt->rt_rmx.rmx_rttvar && i) rt->rt_rmx.rmx_rttvar = (rt->rt_rmx.rmx_rttvar + i) / 2; else rt->rt_rmx.rmx_rttvar = i; tcpstat.tcps_cachedrttvar++; } /* * The old comment here said: * update the pipelimit (ssthresh) if it has been updated * already or if a pipesize was specified & the threshhold * got below half the pipesize. I.e., wait for bad news * before we start updating, then update on both good * and bad news. * * But we want to save the ssthresh even if no pipesize is * specified explicitly in the route, because such * connections still have an implicit pipesize specified * by the global tcp_sendspace. In the absence of a reliable * way to calculate the pipesize, it will have to do. */ i = tp->snd_ssthresh; if (rt->rt_rmx.rmx_sendpipe != 0) dosavessthresh = (i < rt->rt_rmx.rmx_sendpipe / 2); else dosavessthresh = (i < so->so_snd.sb_hiwat / 2); if (((rt->rt_rmx.rmx_locks & RTV_SSTHRESH) == 0 && i != 0 && rt->rt_rmx.rmx_ssthresh != 0) || dosavessthresh) { /* * convert the limit from user data bytes to * packets then to packet data bytes. */ i = (i + tp->t_maxseg / 2) / tp->t_maxseg; if (i < 2) i = 2; i *= (u_long)(tp->t_maxseg + sizeof (struct tcpiphdr)); if (rt->rt_rmx.rmx_ssthresh) rt->rt_rmx.rmx_ssthresh = (rt->rt_rmx.rmx_ssthresh + i) / 2; else rt->rt_rmx.rmx_ssthresh = i; tcpstat.tcps_cachedssthresh++; } } /* free the reassembly queue, if any */ for (q = tp->t_segq; q; q = nq) { nq = q->m_nextpkt; tp->t_segq = nq; m_freem(q); } if (tp->t_template) (void) m_free(dtom(tp->t_template)); inp->inp_ppcb = NULL; soisdisconnected(so); in_pcbdetach(inp); tcpstat.tcps_closed++; return ((struct tcpcb *)0); } void tcp_drain() { } /* * Notify a tcp user of an asynchronous error; * store error as soft error, but wake up user * (for now, won't do anything until can select for soft error). */ static void tcp_notify(inp, error) struct inpcb *inp; int error; { register struct tcpcb *tp = (struct tcpcb *)inp->inp_ppcb; register struct socket *so = inp->inp_socket; /* * Ignore some errors if we are hooked up. * If connection hasn't completed, has retransmitted several times, * and receives a second error, give up now. This is better * than waiting a long time to establish a connection that * can never complete. */ if (tp->t_state == TCPS_ESTABLISHED && (error == EHOSTUNREACH || error == ENETUNREACH || error == EHOSTDOWN)) { return; } else if (tp->t_state < TCPS_ESTABLISHED && tp->t_rxtshift > 3 && tp->t_softerror) so->so_error = error; else tp->t_softerror = error; wakeup((caddr_t) &so->so_timeo); sorwakeup(so); sowwakeup(so); } static int tcp_pcblist SYSCTL_HANDLER_ARGS { int error, i, n, s; struct inpcb *inp, **inp_list; inp_gen_t gencnt; struct xinpgen xig; /* * The process of preparing the TCB list is too time-consuming and * resource-intensive to repeat twice on every request. */ if (req->oldptr == 0) { n = tcbinfo.ipi_count; req->oldidx = 2 * (sizeof xig) + (n + n/8) * sizeof(struct xtcpcb); return 0; } if (req->newptr != 0) return EPERM; /* * OK, now we're committed to doing something. */ s = splnet(); gencnt = tcbinfo.ipi_gencnt; n = tcbinfo.ipi_count; splx(s); xig.xig_len = sizeof xig; xig.xig_count = n; xig.xig_gen = gencnt; xig.xig_sogen = so_gencnt; error = SYSCTL_OUT(req, &xig, sizeof xig); if (error) return error; inp_list = malloc(n * sizeof *inp_list, M_TEMP, M_WAITOK); if (inp_list == 0) return ENOMEM; s = splnet(); for (inp = tcbinfo.listhead->lh_first, i = 0; inp && i < n; inp = inp->inp_list.le_next) { if (inp->inp_gencnt <= gencnt && !prison_xinpcb(req->p, inp)) inp_list[i++] = inp; } splx(s); n = i; error = 0; for (i = 0; i < n; i++) { inp = inp_list[i]; if (inp->inp_gencnt <= gencnt) { struct xtcpcb xt; caddr_t inp_ppcb; xt.xt_len = sizeof xt; /* XXX should avoid extra copy */ bcopy(inp, &xt.xt_inp, sizeof *inp); inp_ppcb = inp->inp_ppcb; if (inp_ppcb != NULL) bcopy(inp_ppcb, &xt.xt_tp, sizeof xt.xt_tp); else bzero((char *) &xt.xt_tp, sizeof xt.xt_tp); if (inp->inp_socket) sotoxsocket(inp->inp_socket, &xt.xt_socket); error = SYSCTL_OUT(req, &xt, sizeof xt); } } if (!error) { /* * Give the user an updated idea of our state. * If the generation differs from what we told * her before, she knows that something happened * while we were processing this request, and it * might be necessary to retry. */ s = splnet(); xig.xig_gen = tcbinfo.ipi_gencnt; xig.xig_sogen = so_gencnt; xig.xig_count = tcbinfo.ipi_count; splx(s); error = SYSCTL_OUT(req, &xig, sizeof xig); } free(inp_list, M_TEMP); return error; } SYSCTL_PROC(_net_inet_tcp, TCPCTL_PCBLIST, pcblist, CTLFLAG_RD, 0, 0, tcp_pcblist, "S,xtcpcb", "List of active TCP connections"); static int tcp_getcred SYSCTL_HANDLER_ARGS { struct sockaddr_in addrs[2]; struct inpcb *inp; int error, s; error = suser(req->p); if (error) return (error); error = SYSCTL_IN(req, addrs, sizeof(addrs)); if (error) return (error); s = splnet(); inp = in_pcblookup_hash(&tcbinfo, addrs[1].sin_addr, addrs[1].sin_port, addrs[0].sin_addr, addrs[0].sin_port, 0); if (inp == NULL || inp->inp_socket == NULL) { error = ENOENT; goto out; } error = SYSCTL_OUT(req, inp->inp_socket->so_cred, sizeof(struct ucred)); out: splx(s); return (error); } SYSCTL_PROC(_net_inet_tcp, OID_AUTO, getcred, CTLTYPE_OPAQUE|CTLFLAG_RW, 0, 0, tcp_getcred, "S,ucred", "Get the ucred of a TCP connection"); void tcp_ctlinput(cmd, sa, vip) int cmd; struct sockaddr *sa; void *vip; { register struct ip *ip = vip; register struct tcphdr *th; void (*notify) __P((struct inpcb *, int)) = tcp_notify; if (cmd == PRC_QUENCH) notify = tcp_quench; else if (cmd == PRC_MSGSIZE) notify = tcp_mtudisc; else if (!PRC_IS_REDIRECT(cmd) && ((unsigned)cmd > PRC_NCMDS || inetctlerrmap[cmd] == 0)) return; if (ip) { th = (struct tcphdr *)((caddr_t)ip + (IP_VHL_HL(ip->ip_vhl) << 2)); in_pcbnotify(&tcb, sa, th->th_dport, ip->ip_src, th->th_sport, cmd, notify); } else in_pcbnotify(&tcb, sa, 0, zeroin_addr, 0, cmd, notify); } /* * When a source quench is received, close congestion window * to one segment. We will gradually open it again as we proceed. */ void tcp_quench(inp, errno) struct inpcb *inp; int errno; { struct tcpcb *tp = intotcpcb(inp); if (tp) tp->snd_cwnd = tp->t_maxseg; } /* * When `need fragmentation' ICMP is received, update our idea of the MSS * based on the new value in the route. Also nudge TCP to send something, * since we know the packet we just sent was dropped. * This duplicates some code in the tcp_mss() function in tcp_input.c. */ void tcp_mtudisc(inp, errno) struct inpcb *inp; int errno; { struct tcpcb *tp = intotcpcb(inp); struct rtentry *rt; struct rmxp_tao *taop; struct socket *so = inp->inp_socket; int offered; int mss; if (tp) { rt = tcp_rtlookup(inp); if (!rt || !rt->rt_rmx.rmx_mtu) { tp->t_maxopd = tp->t_maxseg = tcp_mssdflt; return; } taop = rmx_taop(rt->rt_rmx); offered = taop->tao_mssopt; mss = rt->rt_rmx.rmx_mtu - sizeof(struct tcpiphdr); if (offered) mss = min(mss, offered); /* * XXX - The above conditional probably violates the TCP * spec. The problem is that, since we don't know the * other end's MSS, we are supposed to use a conservative * default. But, if we do that, then MTU discovery will * never actually take place, because the conservative * default is much less than the MTUs typically seen * on the Internet today. For the moment, we'll sweep * this under the carpet. * * The conservative default might not actually be a problem * if the only case this occurs is when sending an initial * SYN with options and data to a host we've never talked * to before. Then, they will reply with an MSS value which * will get recorded and the new parameters should get * recomputed. For Further Study. */ if (tp->t_maxopd <= mss) return; tp->t_maxopd = mss; if ((tp->t_flags & (TF_REQ_TSTMP|TF_NOOPT)) == TF_REQ_TSTMP && (tp->t_flags & TF_RCVD_TSTMP) == TF_RCVD_TSTMP) mss -= TCPOLEN_TSTAMP_APPA; if ((tp->t_flags & (TF_REQ_CC|TF_NOOPT)) == TF_REQ_CC && (tp->t_flags & TF_RCVD_CC) == TF_RCVD_CC) mss -= TCPOLEN_CC_APPA; #if (MCLBYTES & (MCLBYTES - 1)) == 0 if (mss > MCLBYTES) mss &= ~(MCLBYTES-1); #else if (mss > MCLBYTES) mss = mss / MCLBYTES * MCLBYTES; #endif if (so->so_snd.sb_hiwat < mss) mss = so->so_snd.sb_hiwat; tp->t_maxseg = mss; tcpstat.tcps_mturesent++; tp->t_rtttime = 0; tp->snd_nxt = tp->snd_una; tcp_output(tp); } } /* * Look-up the routing entry to the peer of this inpcb. If no route * is found and it cannot be allocated the return NULL. This routine * is called by TCP routines that access the rmx structure and by tcp_mss * to get the interface MTU. */ struct rtentry * tcp_rtlookup(inp) struct inpcb *inp; { struct route *ro; struct rtentry *rt; ro = &inp->inp_route; rt = ro->ro_rt; if (rt == NULL || !(rt->rt_flags & RTF_UP)) { /* No route yet, so try to acquire one */ if (inp->inp_faddr.s_addr != INADDR_ANY) { ro->ro_dst.sa_family = AF_INET; ro->ro_dst.sa_len = sizeof(ro->ro_dst); ((struct sockaddr_in *) &ro->ro_dst)->sin_addr = inp->inp_faddr; rtalloc(ro); rt = ro->ro_rt; } } return rt; } /* * Return a pointer to the cached information about the remote host. * The cached information is stored in the protocol specific part of * the route metrics. */ struct rmxp_tao * tcp_gettaocache(inp) struct inpcb *inp; { struct rtentry *rt = tcp_rtlookup(inp); /* Make sure this is a host route and is up. */ if (rt == NULL || (rt->rt_flags & (RTF_UP|RTF_HOST)) != (RTF_UP|RTF_HOST)) return NULL; return rmx_taop(rt->rt_rmx); } /* * Clear all the TAO cache entries, called from tcp_init. * * XXX * This routine is just an empty one, because we assume that the routing * routing tables are initialized at the same time when TCP, so there is * nothing in the cache left over. */ static void tcp_cleartaocache() { } diff --git a/sys/netinet/tcp_timewait.c b/sys/netinet/tcp_timewait.c index 07da9545535a..68c69b0e1b04 100644 --- a/sys/netinet/tcp_timewait.c +++ b/sys/netinet/tcp_timewait.c @@ -1,832 +1,838 @@ /* * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1995 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)tcp_subr.c 8.2 (Berkeley) 5/24/95 * $FreeBSD$ */ #include "opt_compat.h" #include "opt_tcpdebug.h" #include #include #include #include #include #include #include #include #include #include #include #include #include #include #define _IP_VHL #include #include #include #include #include #include #include #include #include #include #include #include #ifdef TCPDEBUG #include #endif int tcp_mssdflt = TCP_MSS; SYSCTL_INT(_net_inet_tcp, TCPCTL_MSSDFLT, mssdflt, CTLFLAG_RW, &tcp_mssdflt , 0, "Default TCP Maximum Segment Size"); +#ifdef INET6 +int tcp_v6mssdflt = TCP6_MSS; +SYSCTL_INT(_net_inet_tcp, TCPCTL_V6MSSDFLT, v6mssdflt, + CTLFLAG_RW, &tcp_v6mssdflt , 0, ""); +#endif + #if 0 static int tcp_rttdflt = TCPTV_SRTTDFLT / PR_SLOWHZ; SYSCTL_INT(_net_inet_tcp, TCPCTL_RTTDFLT, rttdflt, CTLFLAG_RW, &tcp_rttdflt , 0, "Default maximum TCP Round Trip Time"); #endif static int tcp_do_rfc1323 = 1; SYSCTL_INT(_net_inet_tcp, TCPCTL_DO_RFC1323, rfc1323, CTLFLAG_RW, &tcp_do_rfc1323 , 0, "Enable rfc1323 (high performance TCP) extensions"); static int tcp_do_rfc1644 = 0; SYSCTL_INT(_net_inet_tcp, TCPCTL_DO_RFC1644, rfc1644, CTLFLAG_RW, &tcp_do_rfc1644 , 0, "Enable rfc1644 (TTCP) extensions"); static int tcp_tcbhashsize = 0; SYSCTL_INT(_net_inet_tcp, OID_AUTO, tcbhashsize, CTLFLAG_RD, &tcp_tcbhashsize, 0, "Size of TCP control-block hashtable"); SYSCTL_INT(_net_inet_tcp, OID_AUTO, pcbcount, CTLFLAG_RD, &tcbinfo.ipi_count, 0, "Number of active PCBs"); static void tcp_cleartaocache __P((void)); static void tcp_notify __P((struct inpcb *, int)); /* * Target size of TCP PCB hash tables. Must be a power of two. * * Note that this can be overridden by the kernel environment * variable net.inet.tcp.tcbhashsize */ #ifndef TCBHASHSIZE #define TCBHASHSIZE 512 #endif /* * This is the actual shape of what we allocate using the zone * allocator. Doing it this way allows us to protect both structures * using the same generation count, and also eliminates the overhead * of allocating tcpcbs separately. By hiding the structure here, * we avoid changing most of the rest of the code (although it needs * to be changed, eventually, for greater efficiency). */ #define ALIGNMENT 32 #define ALIGNM1 (ALIGNMENT - 1) struct inp_tp { union { struct inpcb inp; char align[(sizeof(struct inpcb) + ALIGNM1) & ~ALIGNM1]; } inp_tp_u; struct tcpcb tcb; struct callout inp_tp_rexmt, inp_tp_persist, inp_tp_keep, inp_tp_2msl; struct callout inp_tp_delack; }; #undef ALIGNMENT #undef ALIGNM1 /* * Tcp initialization */ void tcp_init() { int hashsize; tcp_iss = random(); /* wrong, but better than a constant */ tcp_ccgen = 1; tcp_cleartaocache(); tcp_delacktime = TCPTV_DELACK; tcp_keepinit = TCPTV_KEEP_INIT; tcp_keepidle = TCPTV_KEEP_IDLE; tcp_keepintvl = TCPTV_KEEPINTVL; tcp_maxpersistidle = TCPTV_KEEP_IDLE; tcp_msl = TCPTV_MSL; LIST_INIT(&tcb); tcbinfo.listhead = &tcb; TUNABLE_INT_FETCH("net.inet.tcp.tcbhashsize", TCBHASHSIZE, hashsize); if (!powerof2(hashsize)) { printf("WARNING: TCB hash size not a power of 2\n"); hashsize = 512; /* safe default */ } tcp_tcbhashsize = hashsize; tcbinfo.hashbase = hashinit(hashsize, M_PCB, &tcbinfo.hashmask); tcbinfo.porthashbase = hashinit(hashsize, M_PCB, &tcbinfo.porthashmask); tcbinfo.ipi_zone = zinit("tcpcb", sizeof(struct inp_tp), maxsockets, ZONE_INTERRUPT, 0); if (max_protohdr < sizeof(struct tcpiphdr)) max_protohdr = sizeof(struct tcpiphdr); if (max_linkhdr + sizeof(struct tcpiphdr) > MHLEN) panic("tcp_init"); } /* * Create template to be used to send tcp packets on a connection. * Call after host entry created, allocates an mbuf and fills * in a skeletal tcp/ip header, minimizing the amount of work * necessary when the connection is used. */ struct tcpiphdr * tcp_template(tp) struct tcpcb *tp; { register struct inpcb *inp = tp->t_inpcb; register struct mbuf *m; register struct tcpiphdr *n; if ((n = tp->t_template) == 0) { m = m_get(M_DONTWAIT, MT_HEADER); if (m == NULL) return (0); m->m_len = sizeof (struct tcpiphdr); n = mtod(m, struct tcpiphdr *); } bzero(n->ti_x1, sizeof(n->ti_x1)); n->ti_pr = IPPROTO_TCP; n->ti_len = htons(sizeof (struct tcpiphdr) - sizeof (struct ip)); n->ti_src = inp->inp_laddr; n->ti_dst = inp->inp_faddr; n->ti_sport = inp->inp_lport; n->ti_dport = inp->inp_fport; n->ti_seq = 0; n->ti_ack = 0; n->ti_x2 = 0; n->ti_off = 5; n->ti_flags = 0; n->ti_win = 0; n->ti_sum = 0; n->ti_urp = 0; return (n); } /* * Send a single message to the TCP at address specified by * the given TCP/IP header. If m == 0, then we make a copy * of the tcpiphdr at ti and send directly to the addressed host. * This is used to force keep alive messages out using the TCP * template for a connection tp->t_template. If flags are given * then we send a message back to the TCP which originated the * segment ti, and discard the mbuf containing it and any other * attached mbufs. * * In any case the ack and sequence number of the transmitted * segment are as specified by the parameters. * * NOTE: If m != NULL, then ti must point to *inside* the mbuf. */ void tcp_respond(tp, ti, m, ack, seq, flags) struct tcpcb *tp; register struct tcpiphdr *ti; register struct mbuf *m; tcp_seq ack, seq; int flags; { register int tlen; int win = 0; struct route *ro = 0; struct route sro; if (tp) { if (!(flags & TH_RST)) win = sbspace(&tp->t_inpcb->inp_socket->so_rcv); ro = &tp->t_inpcb->inp_route; } else { ro = &sro; bzero(ro, sizeof *ro); } if (m == 0) { m = m_gethdr(M_DONTWAIT, MT_HEADER); if (m == NULL) return; #ifdef TCP_COMPAT_42 tlen = 1; #else tlen = 0; #endif m->m_data += max_linkhdr; *mtod(m, struct tcpiphdr *) = *ti; ti = mtod(m, struct tcpiphdr *); flags = TH_ACK; } else { m_freem(m->m_next); m->m_next = 0; m->m_data = (caddr_t)ti; m->m_len = sizeof (struct tcpiphdr); tlen = 0; #define xchg(a,b,type) { type t; t=a; a=b; b=t; } xchg(ti->ti_dst.s_addr, ti->ti_src.s_addr, n_long); xchg(ti->ti_dport, ti->ti_sport, n_short); #undef xchg } ti->ti_len = htons((u_short)(sizeof (struct tcphdr) + tlen)); tlen += sizeof (struct tcpiphdr); m->m_len = tlen; m->m_pkthdr.len = tlen; m->m_pkthdr.rcvif = (struct ifnet *) 0; bzero(ti->ti_x1, sizeof(ti->ti_x1)); ti->ti_seq = htonl(seq); ti->ti_ack = htonl(ack); ti->ti_x2 = 0; ti->ti_off = sizeof (struct tcphdr) >> 2; ti->ti_flags = flags; if (tp) ti->ti_win = htons((u_short) (win >> tp->rcv_scale)); else ti->ti_win = htons((u_short)win); ti->ti_urp = 0; ti->ti_sum = 0; ti->ti_sum = in_cksum(m, tlen); ((struct ip *)ti)->ip_len = tlen; ((struct ip *)ti)->ip_ttl = ip_defttl; #ifdef TCPDEBUG if (tp == NULL || (tp->t_inpcb->inp_socket->so_options & SO_DEBUG)) tcp_trace(TA_OUTPUT, 0, tp, ti, 0); #endif (void) ip_output(m, NULL, ro, 0, NULL); if (ro == &sro && ro->ro_rt) { RTFREE(ro->ro_rt); } } /* * Create a new TCP control block, making an * empty reassembly queue and hooking it to the argument * protocol control block. The `inp' parameter must have * come from the zone allocator set up in tcp_init(). */ struct tcpcb * tcp_newtcpcb(inp) struct inpcb *inp; { struct inp_tp *it; register struct tcpcb *tp; it = (struct inp_tp *)inp; tp = &it->tcb; bzero((char *) tp, sizeof(struct tcpcb)); tp->t_segq = NULL; tp->t_maxseg = tp->t_maxopd = tcp_mssdflt; /* Set up our timeouts. */ callout_init(tp->tt_rexmt = &it->inp_tp_rexmt); callout_init(tp->tt_persist = &it->inp_tp_persist); callout_init(tp->tt_keep = &it->inp_tp_keep); callout_init(tp->tt_2msl = &it->inp_tp_2msl); callout_init(tp->tt_delack = &it->inp_tp_delack); if (tcp_do_rfc1323) tp->t_flags = (TF_REQ_SCALE|TF_REQ_TSTMP); if (tcp_do_rfc1644) tp->t_flags |= TF_REQ_CC; tp->t_inpcb = inp; /* XXX */ /* * Init srtt to TCPTV_SRTTBASE (0), so we can tell that we have no * rtt estimate. Set rttvar so that srtt + 4 * rttvar gives * reasonable initial retransmit time. */ tp->t_srtt = TCPTV_SRTTBASE; tp->t_rttvar = ((TCPTV_RTOBASE - TCPTV_SRTTBASE) << TCP_RTTVAR_SHIFT) / 4; tp->t_rttmin = TCPTV_MIN; tp->t_rxtcur = TCPTV_RTOBASE; tp->snd_cwnd = TCP_MAXWIN << TCP_MAX_WINSHIFT; tp->snd_ssthresh = TCP_MAXWIN << TCP_MAX_WINSHIFT; tp->t_rcvtime = ticks; inp->inp_ip_ttl = ip_defttl; inp->inp_ppcb = (caddr_t)tp; return (tp); /* XXX */ } /* * Drop a TCP connection, reporting * the specified error. If connection is synchronized, * then send a RST to peer. */ struct tcpcb * tcp_drop(tp, errno) register struct tcpcb *tp; int errno; { struct socket *so = tp->t_inpcb->inp_socket; if (TCPS_HAVERCVDSYN(tp->t_state)) { tp->t_state = TCPS_CLOSED; (void) tcp_output(tp); tcpstat.tcps_drops++; } else tcpstat.tcps_conndrops++; if (errno == ETIMEDOUT && tp->t_softerror) errno = tp->t_softerror; so->so_error = errno; return (tcp_close(tp)); } /* * Close a TCP control block: * discard all space held by the tcp * discard internet protocol block * wake up any sleepers */ struct tcpcb * tcp_close(tp) register struct tcpcb *tp; { register struct mbuf *q; register struct mbuf *nq; struct inpcb *inp = tp->t_inpcb; struct socket *so = inp->inp_socket; register struct rtentry *rt; int dosavessthresh; /* * Make sure that all of our timers are stopped before we * delete the PCB. */ callout_stop(tp->tt_rexmt); callout_stop(tp->tt_persist); callout_stop(tp->tt_keep); callout_stop(tp->tt_2msl); callout_stop(tp->tt_delack); /* * If we got enough samples through the srtt filter, * save the rtt and rttvar in the routing entry. * 'Enough' is arbitrarily defined as the 16 samples. * 16 samples is enough for the srtt filter to converge * to within 5% of the correct value; fewer samples and * we could save a very bogus rtt. * * Don't update the default route's characteristics and don't * update anything that the user "locked". */ if (tp->t_rttupdated >= 16 && (rt = inp->inp_route.ro_rt) && ((struct sockaddr_in *)rt_key(rt))->sin_addr.s_addr != INADDR_ANY) { register u_long i = 0; if ((rt->rt_rmx.rmx_locks & RTV_RTT) == 0) { i = tp->t_srtt * (RTM_RTTUNIT / (hz * TCP_RTT_SCALE)); if (rt->rt_rmx.rmx_rtt && i) /* * filter this update to half the old & half * the new values, converting scale. * See route.h and tcp_var.h for a * description of the scaling constants. */ rt->rt_rmx.rmx_rtt = (rt->rt_rmx.rmx_rtt + i) / 2; else rt->rt_rmx.rmx_rtt = i; tcpstat.tcps_cachedrtt++; } if ((rt->rt_rmx.rmx_locks & RTV_RTTVAR) == 0) { i = tp->t_rttvar * (RTM_RTTUNIT / (hz * TCP_RTTVAR_SCALE)); if (rt->rt_rmx.rmx_rttvar && i) rt->rt_rmx.rmx_rttvar = (rt->rt_rmx.rmx_rttvar + i) / 2; else rt->rt_rmx.rmx_rttvar = i; tcpstat.tcps_cachedrttvar++; } /* * The old comment here said: * update the pipelimit (ssthresh) if it has been updated * already or if a pipesize was specified & the threshhold * got below half the pipesize. I.e., wait for bad news * before we start updating, then update on both good * and bad news. * * But we want to save the ssthresh even if no pipesize is * specified explicitly in the route, because such * connections still have an implicit pipesize specified * by the global tcp_sendspace. In the absence of a reliable * way to calculate the pipesize, it will have to do. */ i = tp->snd_ssthresh; if (rt->rt_rmx.rmx_sendpipe != 0) dosavessthresh = (i < rt->rt_rmx.rmx_sendpipe / 2); else dosavessthresh = (i < so->so_snd.sb_hiwat / 2); if (((rt->rt_rmx.rmx_locks & RTV_SSTHRESH) == 0 && i != 0 && rt->rt_rmx.rmx_ssthresh != 0) || dosavessthresh) { /* * convert the limit from user data bytes to * packets then to packet data bytes. */ i = (i + tp->t_maxseg / 2) / tp->t_maxseg; if (i < 2) i = 2; i *= (u_long)(tp->t_maxseg + sizeof (struct tcpiphdr)); if (rt->rt_rmx.rmx_ssthresh) rt->rt_rmx.rmx_ssthresh = (rt->rt_rmx.rmx_ssthresh + i) / 2; else rt->rt_rmx.rmx_ssthresh = i; tcpstat.tcps_cachedssthresh++; } } /* free the reassembly queue, if any */ for (q = tp->t_segq; q; q = nq) { nq = q->m_nextpkt; tp->t_segq = nq; m_freem(q); } if (tp->t_template) (void) m_free(dtom(tp->t_template)); inp->inp_ppcb = NULL; soisdisconnected(so); in_pcbdetach(inp); tcpstat.tcps_closed++; return ((struct tcpcb *)0); } void tcp_drain() { } /* * Notify a tcp user of an asynchronous error; * store error as soft error, but wake up user * (for now, won't do anything until can select for soft error). */ static void tcp_notify(inp, error) struct inpcb *inp; int error; { register struct tcpcb *tp = (struct tcpcb *)inp->inp_ppcb; register struct socket *so = inp->inp_socket; /* * Ignore some errors if we are hooked up. * If connection hasn't completed, has retransmitted several times, * and receives a second error, give up now. This is better * than waiting a long time to establish a connection that * can never complete. */ if (tp->t_state == TCPS_ESTABLISHED && (error == EHOSTUNREACH || error == ENETUNREACH || error == EHOSTDOWN)) { return; } else if (tp->t_state < TCPS_ESTABLISHED && tp->t_rxtshift > 3 && tp->t_softerror) so->so_error = error; else tp->t_softerror = error; wakeup((caddr_t) &so->so_timeo); sorwakeup(so); sowwakeup(so); } static int tcp_pcblist SYSCTL_HANDLER_ARGS { int error, i, n, s; struct inpcb *inp, **inp_list; inp_gen_t gencnt; struct xinpgen xig; /* * The process of preparing the TCB list is too time-consuming and * resource-intensive to repeat twice on every request. */ if (req->oldptr == 0) { n = tcbinfo.ipi_count; req->oldidx = 2 * (sizeof xig) + (n + n/8) * sizeof(struct xtcpcb); return 0; } if (req->newptr != 0) return EPERM; /* * OK, now we're committed to doing something. */ s = splnet(); gencnt = tcbinfo.ipi_gencnt; n = tcbinfo.ipi_count; splx(s); xig.xig_len = sizeof xig; xig.xig_count = n; xig.xig_gen = gencnt; xig.xig_sogen = so_gencnt; error = SYSCTL_OUT(req, &xig, sizeof xig); if (error) return error; inp_list = malloc(n * sizeof *inp_list, M_TEMP, M_WAITOK); if (inp_list == 0) return ENOMEM; s = splnet(); for (inp = tcbinfo.listhead->lh_first, i = 0; inp && i < n; inp = inp->inp_list.le_next) { if (inp->inp_gencnt <= gencnt && !prison_xinpcb(req->p, inp)) inp_list[i++] = inp; } splx(s); n = i; error = 0; for (i = 0; i < n; i++) { inp = inp_list[i]; if (inp->inp_gencnt <= gencnt) { struct xtcpcb xt; caddr_t inp_ppcb; xt.xt_len = sizeof xt; /* XXX should avoid extra copy */ bcopy(inp, &xt.xt_inp, sizeof *inp); inp_ppcb = inp->inp_ppcb; if (inp_ppcb != NULL) bcopy(inp_ppcb, &xt.xt_tp, sizeof xt.xt_tp); else bzero((char *) &xt.xt_tp, sizeof xt.xt_tp); if (inp->inp_socket) sotoxsocket(inp->inp_socket, &xt.xt_socket); error = SYSCTL_OUT(req, &xt, sizeof xt); } } if (!error) { /* * Give the user an updated idea of our state. * If the generation differs from what we told * her before, she knows that something happened * while we were processing this request, and it * might be necessary to retry. */ s = splnet(); xig.xig_gen = tcbinfo.ipi_gencnt; xig.xig_sogen = so_gencnt; xig.xig_count = tcbinfo.ipi_count; splx(s); error = SYSCTL_OUT(req, &xig, sizeof xig); } free(inp_list, M_TEMP); return error; } SYSCTL_PROC(_net_inet_tcp, TCPCTL_PCBLIST, pcblist, CTLFLAG_RD, 0, 0, tcp_pcblist, "S,xtcpcb", "List of active TCP connections"); static int tcp_getcred SYSCTL_HANDLER_ARGS { struct sockaddr_in addrs[2]; struct inpcb *inp; int error, s; error = suser(req->p); if (error) return (error); error = SYSCTL_IN(req, addrs, sizeof(addrs)); if (error) return (error); s = splnet(); inp = in_pcblookup_hash(&tcbinfo, addrs[1].sin_addr, addrs[1].sin_port, addrs[0].sin_addr, addrs[0].sin_port, 0); if (inp == NULL || inp->inp_socket == NULL) { error = ENOENT; goto out; } error = SYSCTL_OUT(req, inp->inp_socket->so_cred, sizeof(struct ucred)); out: splx(s); return (error); } SYSCTL_PROC(_net_inet_tcp, OID_AUTO, getcred, CTLTYPE_OPAQUE|CTLFLAG_RW, 0, 0, tcp_getcred, "S,ucred", "Get the ucred of a TCP connection"); void tcp_ctlinput(cmd, sa, vip) int cmd; struct sockaddr *sa; void *vip; { register struct ip *ip = vip; register struct tcphdr *th; void (*notify) __P((struct inpcb *, int)) = tcp_notify; if (cmd == PRC_QUENCH) notify = tcp_quench; else if (cmd == PRC_MSGSIZE) notify = tcp_mtudisc; else if (!PRC_IS_REDIRECT(cmd) && ((unsigned)cmd > PRC_NCMDS || inetctlerrmap[cmd] == 0)) return; if (ip) { th = (struct tcphdr *)((caddr_t)ip + (IP_VHL_HL(ip->ip_vhl) << 2)); in_pcbnotify(&tcb, sa, th->th_dport, ip->ip_src, th->th_sport, cmd, notify); } else in_pcbnotify(&tcb, sa, 0, zeroin_addr, 0, cmd, notify); } /* * When a source quench is received, close congestion window * to one segment. We will gradually open it again as we proceed. */ void tcp_quench(inp, errno) struct inpcb *inp; int errno; { struct tcpcb *tp = intotcpcb(inp); if (tp) tp->snd_cwnd = tp->t_maxseg; } /* * When `need fragmentation' ICMP is received, update our idea of the MSS * based on the new value in the route. Also nudge TCP to send something, * since we know the packet we just sent was dropped. * This duplicates some code in the tcp_mss() function in tcp_input.c. */ void tcp_mtudisc(inp, errno) struct inpcb *inp; int errno; { struct tcpcb *tp = intotcpcb(inp); struct rtentry *rt; struct rmxp_tao *taop; struct socket *so = inp->inp_socket; int offered; int mss; if (tp) { rt = tcp_rtlookup(inp); if (!rt || !rt->rt_rmx.rmx_mtu) { tp->t_maxopd = tp->t_maxseg = tcp_mssdflt; return; } taop = rmx_taop(rt->rt_rmx); offered = taop->tao_mssopt; mss = rt->rt_rmx.rmx_mtu - sizeof(struct tcpiphdr); if (offered) mss = min(mss, offered); /* * XXX - The above conditional probably violates the TCP * spec. The problem is that, since we don't know the * other end's MSS, we are supposed to use a conservative * default. But, if we do that, then MTU discovery will * never actually take place, because the conservative * default is much less than the MTUs typically seen * on the Internet today. For the moment, we'll sweep * this under the carpet. * * The conservative default might not actually be a problem * if the only case this occurs is when sending an initial * SYN with options and data to a host we've never talked * to before. Then, they will reply with an MSS value which * will get recorded and the new parameters should get * recomputed. For Further Study. */ if (tp->t_maxopd <= mss) return; tp->t_maxopd = mss; if ((tp->t_flags & (TF_REQ_TSTMP|TF_NOOPT)) == TF_REQ_TSTMP && (tp->t_flags & TF_RCVD_TSTMP) == TF_RCVD_TSTMP) mss -= TCPOLEN_TSTAMP_APPA; if ((tp->t_flags & (TF_REQ_CC|TF_NOOPT)) == TF_REQ_CC && (tp->t_flags & TF_RCVD_CC) == TF_RCVD_CC) mss -= TCPOLEN_CC_APPA; #if (MCLBYTES & (MCLBYTES - 1)) == 0 if (mss > MCLBYTES) mss &= ~(MCLBYTES-1); #else if (mss > MCLBYTES) mss = mss / MCLBYTES * MCLBYTES; #endif if (so->so_snd.sb_hiwat < mss) mss = so->so_snd.sb_hiwat; tp->t_maxseg = mss; tcpstat.tcps_mturesent++; tp->t_rtttime = 0; tp->snd_nxt = tp->snd_una; tcp_output(tp); } } /* * Look-up the routing entry to the peer of this inpcb. If no route * is found and it cannot be allocated the return NULL. This routine * is called by TCP routines that access the rmx structure and by tcp_mss * to get the interface MTU. */ struct rtentry * tcp_rtlookup(inp) struct inpcb *inp; { struct route *ro; struct rtentry *rt; ro = &inp->inp_route; rt = ro->ro_rt; if (rt == NULL || !(rt->rt_flags & RTF_UP)) { /* No route yet, so try to acquire one */ if (inp->inp_faddr.s_addr != INADDR_ANY) { ro->ro_dst.sa_family = AF_INET; ro->ro_dst.sa_len = sizeof(ro->ro_dst); ((struct sockaddr_in *) &ro->ro_dst)->sin_addr = inp->inp_faddr; rtalloc(ro); rt = ro->ro_rt; } } return rt; } /* * Return a pointer to the cached information about the remote host. * The cached information is stored in the protocol specific part of * the route metrics. */ struct rmxp_tao * tcp_gettaocache(inp) struct inpcb *inp; { struct rtentry *rt = tcp_rtlookup(inp); /* Make sure this is a host route and is up. */ if (rt == NULL || (rt->rt_flags & (RTF_UP|RTF_HOST)) != (RTF_UP|RTF_HOST)) return NULL; return rmx_taop(rt->rt_rmx); } /* * Clear all the TAO cache entries, called from tcp_init. * * XXX * This routine is just an empty one, because we assume that the routing * routing tables are initialized at the same time when TCP, so there is * nothing in the cache left over. */ static void tcp_cleartaocache() { } diff --git a/sys/netinet/tcp_var.h b/sys/netinet/tcp_var.h index 8d7c5979b22e..0258b77bb40e 100644 --- a/sys/netinet/tcp_var.h +++ b/sys/netinet/tcp_var.h @@ -1,387 +1,390 @@ /* * Copyright (c) 1982, 1986, 1993, 1994, 1995 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)tcp_var.h 8.4 (Berkeley) 5/24/95 * $FreeBSD$ */ #ifndef _NETINET_TCP_VAR_H_ #define _NETINET_TCP_VAR_H_ /* * Kernel variables for tcp. */ /* * Tcp control block, one per tcp; fields: * Organized for 16 byte cacheline efficiency. */ struct tcpcb { struct mbuf *t_segq; int t_dupacks; /* consecutive dup acks recd */ struct tcpiphdr *t_template; /* skeletal packet for transmit */ struct callout *tt_rexmt; /* retransmit timer */ struct callout *tt_persist; /* retransmit persistence */ struct callout *tt_keep; /* keepalive */ struct callout *tt_2msl; /* 2*msl TIME_WAIT timer */ struct callout *tt_delack; /* delayed ACK timer */ struct inpcb *t_inpcb; /* back pointer to internet pcb */ int t_state; /* state of this connection */ u_int t_flags; #define TF_ACKNOW 0x00001 /* ack peer immediately */ #define TF_DELACK 0x00002 /* ack, but try to delay it */ #define TF_NODELAY 0x00004 /* don't delay packets to coalesce */ #define TF_NOOPT 0x00008 /* don't use tcp options */ #define TF_SENTFIN 0x00010 /* have sent FIN */ #define TF_REQ_SCALE 0x00020 /* have/will request window scaling */ #define TF_RCVD_SCALE 0x00040 /* other side has requested scaling */ #define TF_REQ_TSTMP 0x00080 /* have/will request timestamps */ #define TF_RCVD_TSTMP 0x00100 /* a timestamp was received in SYN */ #define TF_SACK_PERMIT 0x00200 /* other side said I could SACK */ #define TF_NEEDSYN 0x00400 /* send SYN (implicit state) */ #define TF_NEEDFIN 0x00800 /* send FIN (implicit state) */ #define TF_NOPUSH 0x01000 /* don't push */ #define TF_REQ_CC 0x02000 /* have/will request CC */ #define TF_RCVD_CC 0x04000 /* a CC was received in SYN */ #define TF_SENDCCNEW 0x08000 /* send CCnew instead of CC in SYN */ #define TF_MORETOCOME 0x10000 /* More data to be appended to sock */ int t_force; /* 1 if forcing out a byte */ tcp_seq snd_una; /* send unacknowledged */ tcp_seq snd_max; /* highest sequence number sent; * used to recognize retransmits */ tcp_seq snd_nxt; /* send next */ tcp_seq snd_up; /* send urgent pointer */ tcp_seq snd_wl1; /* window update seg seq number */ tcp_seq snd_wl2; /* window update seg ack number */ tcp_seq iss; /* initial send sequence number */ tcp_seq irs; /* initial receive sequence number */ tcp_seq rcv_nxt; /* receive next */ tcp_seq rcv_adv; /* advertised window */ u_long rcv_wnd; /* receive window */ tcp_seq rcv_up; /* receive urgent pointer */ u_long snd_wnd; /* send window */ u_long snd_cwnd; /* congestion-controlled window */ u_long snd_ssthresh; /* snd_cwnd size threshold for * for slow start exponential to * linear switch */ u_int t_maxopd; /* mss plus options */ u_long t_rcvtime; /* inactivity time */ u_long t_starttime; /* time connection was established */ int t_rtttime; /* round trip time */ tcp_seq t_rtseq; /* sequence number being timed */ int t_rxtcur; /* current retransmit value (ticks) */ u_int t_maxseg; /* maximum segment size */ int t_srtt; /* smoothed round-trip time */ int t_rttvar; /* variance in round-trip time */ int t_rxtshift; /* log(2) of rexmt exp. backoff */ u_int t_rttmin; /* minimum rtt allowed */ u_long t_rttupdated; /* number of times rtt sampled */ u_long max_sndwnd; /* largest window peer has offered */ int t_softerror; /* possible error not yet reported */ /* out-of-band data */ char t_oobflags; /* have some */ char t_iobc; /* input character */ #define TCPOOB_HAVEDATA 0x01 #define TCPOOB_HADDATA 0x02 /* RFC 1323 variables */ u_char snd_scale; /* window scaling for send window */ u_char rcv_scale; /* window scaling for recv window */ u_char request_r_scale; /* pending window scaling */ u_char requested_s_scale; u_long ts_recent; /* timestamp echo data */ u_long ts_recent_age; /* when last updated */ tcp_seq last_ack_sent; /* RFC 1644 variables */ tcp_cc cc_send; /* send connection count */ tcp_cc cc_recv; /* receive connection count */ /* experimental */ u_long snd_cwnd_prev; /* cwnd prior to retransmit */ u_long snd_ssthresh_prev; /* ssthresh prior to retransmit */ u_long t_badrxtwin; /* window for retransmit recovery */ }; /* * Structure to hold TCP options that are only used during segment * processing (in tcp_input), but not held in the tcpcb. * It's basically used to reduce the number of parameters * to tcp_dooptions. */ struct tcpopt { u_long to_flag; /* which options are present */ #define TOF_TS 0x0001 /* timestamp */ #define TOF_CC 0x0002 /* CC and CCnew are exclusive */ #define TOF_CCNEW 0x0004 #define TOF_CCECHO 0x0008 u_long to_tsval; u_long to_tsecr; tcp_cc to_cc; /* holds CC or CCnew */ tcp_cc to_ccecho; }; /* * The TAO cache entry which is stored in the protocol family specific * portion of the route metrics. */ struct rmxp_tao { tcp_cc tao_cc; /* latest CC in valid SYN */ tcp_cc tao_ccsent; /* latest CC sent to peer */ u_short tao_mssopt; /* peer's cached MSS */ #ifdef notyet u_short tao_flags; /* cache status flags */ #define TAOF_DONT 0x0001 /* peer doesn't understand rfc1644 */ #define TAOF_OK 0x0002 /* peer does understand rfc1644 */ #define TAOF_UNDEF 0 /* we don't know yet */ #endif /* notyet */ }; #define rmx_taop(r) ((struct rmxp_tao *)(r).rmx_filler) #define intotcpcb(ip) ((struct tcpcb *)(ip)->inp_ppcb) #define sototcpcb(so) (intotcpcb(sotoinpcb(so))) /* * The smoothed round-trip time and estimated variance * are stored as fixed point numbers scaled by the values below. * For convenience, these scales are also used in smoothing the average * (smoothed = (1/scale)sample + ((scale-1)/scale)smoothed). * With these scales, srtt has 3 bits to the right of the binary point, * and thus an "ALPHA" of 0.875. rttvar has 2 bits to the right of the * binary point, and is smoothed with an ALPHA of 0.75. */ #define TCP_RTT_SCALE 32 /* multiplier for srtt; 3 bits frac. */ #define TCP_RTT_SHIFT 5 /* shift for srtt; 3 bits frac. */ #define TCP_RTTVAR_SCALE 16 /* multiplier for rttvar; 2 bits */ #define TCP_RTTVAR_SHIFT 4 /* shift for rttvar; 2 bits */ #define TCP_DELTA_SHIFT 2 /* see tcp_input.c */ /* * The initial retransmission should happen at rtt + 4 * rttvar. * Because of the way we do the smoothing, srtt and rttvar * will each average +1/2 tick of bias. When we compute * the retransmit timer, we want 1/2 tick of rounding and * 1 extra tick because of +-1/2 tick uncertainty in the * firing of the timer. The bias will give us exactly the * 1.5 tick we need. But, because the bias is * statistical, we have to test that we don't drop below * the minimum feasible timer (which is 2 ticks). * This version of the macro adapted from a paper by Lawrence * Brakmo and Larry Peterson which outlines a problem caused * by insufficient precision in the original implementation, * which results in inappropriately large RTO values for very * fast networks. */ #define TCP_REXMTVAL(tp) \ max((tp)->t_rttmin, (((tp)->t_srtt >> (TCP_RTT_SHIFT - TCP_DELTA_SHIFT)) \ + (tp)->t_rttvar) >> TCP_DELTA_SHIFT) /* * TCP statistics. * Many of these should be kept per connection, * but that's inconvenient at the moment. */ struct tcpstat { u_long tcps_connattempt; /* connections initiated */ u_long tcps_accepts; /* connections accepted */ u_long tcps_connects; /* connections established */ u_long tcps_drops; /* connections dropped */ u_long tcps_conndrops; /* embryonic connections dropped */ u_long tcps_closed; /* conn. closed (includes drops) */ u_long tcps_segstimed; /* segs where we tried to get rtt */ u_long tcps_rttupdated; /* times we succeeded */ u_long tcps_delack; /* delayed acks sent */ u_long tcps_timeoutdrop; /* conn. dropped in rxmt timeout */ u_long tcps_rexmttimeo; /* retransmit timeouts */ u_long tcps_persisttimeo; /* persist timeouts */ u_long tcps_keeptimeo; /* keepalive timeouts */ u_long tcps_keepprobe; /* keepalive probes sent */ u_long tcps_keepdrops; /* connections dropped in keepalive */ u_long tcps_sndtotal; /* total packets sent */ u_long tcps_sndpack; /* data packets sent */ u_long tcps_sndbyte; /* data bytes sent */ u_long tcps_sndrexmitpack; /* data packets retransmitted */ u_long tcps_sndrexmitbyte; /* data bytes retransmitted */ u_long tcps_sndacks; /* ack-only packets sent */ u_long tcps_sndprobe; /* window probes sent */ u_long tcps_sndurg; /* packets sent with URG only */ u_long tcps_sndwinup; /* window update-only packets sent */ u_long tcps_sndctrl; /* control (SYN|FIN|RST) packets sent */ u_long tcps_rcvtotal; /* total packets received */ u_long tcps_rcvpack; /* packets received in sequence */ u_long tcps_rcvbyte; /* bytes received in sequence */ u_long tcps_rcvbadsum; /* packets received with ccksum errs */ u_long tcps_rcvbadoff; /* packets received with bad offset */ + u_long tcps_rcvmemdrop; /* packets dropped for lack of memory */ u_long tcps_rcvshort; /* packets received too short */ u_long tcps_rcvduppack; /* duplicate-only packets received */ u_long tcps_rcvdupbyte; /* duplicate-only bytes received */ u_long tcps_rcvpartduppack; /* packets with some duplicate data */ u_long tcps_rcvpartdupbyte; /* dup. bytes in part-dup. packets */ u_long tcps_rcvoopack; /* out-of-order packets received */ u_long tcps_rcvoobyte; /* out-of-order bytes received */ u_long tcps_rcvpackafterwin; /* packets with data after window */ u_long tcps_rcvbyteafterwin; /* bytes rcvd after window */ u_long tcps_rcvafterclose; /* packets rcvd after "close" */ u_long tcps_rcvwinprobe; /* rcvd window probe packets */ u_long tcps_rcvdupack; /* rcvd duplicate acks */ u_long tcps_rcvacktoomuch; /* rcvd acks for unsent data */ u_long tcps_rcvackpack; /* rcvd ack packets */ u_long tcps_rcvackbyte; /* bytes acked by rcvd acks */ u_long tcps_rcvwinupd; /* rcvd window update packets */ u_long tcps_pawsdrop; /* segments dropped due to PAWS */ u_long tcps_predack; /* times hdr predict ok for acks */ u_long tcps_preddat; /* times hdr predict ok for data pkts */ u_long tcps_pcbcachemiss; u_long tcps_cachedrtt; /* times cached RTT in route updated */ u_long tcps_cachedrttvar; /* times cached rttvar updated */ u_long tcps_cachedssthresh; /* times cached ssthresh updated */ u_long tcps_usedrtt; /* times RTT initialized from route */ u_long tcps_usedrttvar; /* times RTTVAR initialized from rt */ u_long tcps_usedssthresh; /* times ssthresh initialized from rt*/ u_long tcps_persistdrop; /* timeout in persist state */ u_long tcps_badsyn; /* bogus SYN, e.g. premature ACK */ u_long tcps_mturesent; /* resends due to MTU discovery */ u_long tcps_listendrop; /* listen queue overflows */ }; /* * TCB structure exported to user-land via sysctl(3). * Evil hack: declare only if in_pcb.h and sys/socketvar.h have been * included. Not all of our clients do. */ #if defined(_NETINET_IN_PCB_H_) && defined(_SYS_SOCKETVAR_H_) struct xtcpcb { size_t xt_len; struct inpcb xt_inp; struct tcpcb xt_tp; struct xsocket xt_socket; u_quad_t xt_alignment_hack; }; #endif /* * Names for TCP sysctl objects */ #define TCPCTL_DO_RFC1323 1 /* use RFC-1323 extensions */ #define TCPCTL_DO_RFC1644 2 /* use RFC-1644 extensions */ #define TCPCTL_MSSDFLT 3 /* MSS default */ #define TCPCTL_STATS 4 /* statistics (read-only) */ #define TCPCTL_RTTDFLT 5 /* default RTT estimate */ #define TCPCTL_KEEPIDLE 6 /* keepalive idle timer */ #define TCPCTL_KEEPINTVL 7 /* interval to send keepalives */ #define TCPCTL_SENDSPACE 8 /* send buffer space */ #define TCPCTL_RECVSPACE 9 /* receive buffer space */ #define TCPCTL_KEEPINIT 10 /* receive buffer space */ #define TCPCTL_PCBLIST 11 /* list of all outstanding PCBs */ #define TCPCTL_DELACKTIME 12 /* time before sending delayed ACK */ -#define TCPCTL_MAXID 13 +#define TCPCTL_V6MSSDFLT 13 /* MSS default for IPv6 */ +#define TCPCTL_MAXID 14 #define TCPCTL_NAMES { \ { 0, 0 }, \ { "rfc1323", CTLTYPE_INT }, \ { "rfc1644", CTLTYPE_INT }, \ { "mssdflt", CTLTYPE_INT }, \ { "stats", CTLTYPE_STRUCT }, \ { "rttdflt", CTLTYPE_INT }, \ { "keepidle", CTLTYPE_INT }, \ { "keepintvl", CTLTYPE_INT }, \ { "sendspace", CTLTYPE_INT }, \ { "recvspace", CTLTYPE_INT }, \ { "keepinit", CTLTYPE_INT }, \ { "pcblist", CTLTYPE_STRUCT }, \ { "delacktime", CTLTYPE_INT }, \ + { "v6mssdflt", CTLTYPE_INT }, \ } #ifdef KERNEL #ifdef SYSCTL_DECL SYSCTL_DECL(_net_inet_tcp); #endif extern struct inpcbhead tcb; /* head of queue of active tcpcb's */ extern struct inpcbinfo tcbinfo; extern struct tcpstat tcpstat; /* tcp statistics */ extern int tcp_mssdflt; /* XXX */ extern int tcp_delack_enabled; extern int ss_fltsz; extern int ss_fltsz_local; void tcp_canceltimers __P((struct tcpcb *)); struct tcpcb * tcp_close __P((struct tcpcb *)); void tcp_ctlinput __P((int, struct sockaddr *, void *)); int tcp_ctloutput __P((struct socket *, struct sockopt *)); struct tcpcb * tcp_drop __P((struct tcpcb *, int)); void tcp_drain __P((void)); void tcp_fasttimo __P((void)); struct rmxp_tao * tcp_gettaocache __P((struct inpcb *)); void tcp_init __P((void)); void tcp_input __P((struct mbuf *, int)); void tcp_mss __P((struct tcpcb *, int)); int tcp_mssopt __P((struct tcpcb *)); void tcp_mtudisc __P((struct inpcb *, int)); struct tcpcb * tcp_newtcpcb __P((struct inpcb *)); int tcp_output __P((struct tcpcb *)); void tcp_quench __P((struct inpcb *, int)); void tcp_respond __P((struct tcpcb *, struct tcpiphdr *, struct mbuf *, tcp_seq, tcp_seq, int)); struct rtentry * tcp_rtlookup __P((struct inpcb *)); void tcp_setpersist __P((struct tcpcb *)); void tcp_slowtimo __P((void)); struct tcpiphdr * tcp_template __P((struct tcpcb *)); struct tcpcb * tcp_timers __P((struct tcpcb *, int)); void tcp_trace __P((int, int, struct tcpcb *, struct tcpiphdr *, int)); extern struct pr_usrreqs tcp_usrreqs; extern u_long tcp_sendspace; extern u_long tcp_recvspace; #endif /* KERNEL */ #endif /* _NETINET_TCP_VAR_H_ */ diff --git a/sys/netinet/udp_usrreq.c b/sys/netinet/udp_usrreq.c index 44ff6eedec03..b47b0be3a10d 100644 --- a/sys/netinet/udp_usrreq.c +++ b/sys/netinet/udp_usrreq.c @@ -1,740 +1,739 @@ /* * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1995 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)udp_usrreq.c 8.6 (Berkeley) 5/23/95 * $FreeBSD$ */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* * UDP protocol implementation. * Per RFC 768, August, 1980. */ #ifndef COMPAT_42 static int udpcksum = 1; #else static int udpcksum = 0; /* XXX */ #endif SYSCTL_INT(_net_inet_udp, UDPCTL_CHECKSUM, checksum, CTLFLAG_RW, &udpcksum, 0, ""); -static int log_in_vain = 0; +int log_in_vain = 0; SYSCTL_INT(_net_inet_udp, OID_AUTO, log_in_vain, CTLFLAG_RW, &log_in_vain, 0, "Log all incoming UDP packets"); -static int blackhole = 0; +static int blackhole = 0; SYSCTL_INT(_net_inet_udp, OID_AUTO, blackhole, CTLFLAG_RW, &blackhole, 0, "Do not send port unreachables for refused connects"); -static struct inpcbhead udb; /* from udp_var.h */ -struct inpcbinfo udbinfo; +struct inpcbhead udb; /* from udp_var.h */ +struct inpcbinfo udbinfo; #ifndef UDBHASHSIZE #define UDBHASHSIZE 16 #endif -static struct udpstat udpstat; /* from udp_var.h */ +struct udpstat udpstat; /* from udp_var.h */ SYSCTL_STRUCT(_net_inet_udp, UDPCTL_STATS, stats, CTLFLAG_RD, &udpstat, udpstat, "UDP statistics (struct udpstat, netinet/udp_var.h)"); static struct sockaddr_in udp_in = { sizeof(udp_in), AF_INET }; static int udp_output __P((struct inpcb *, struct mbuf *, struct sockaddr *, struct mbuf *, struct proc *)); -static void udp_notify __P((struct inpcb *, int)); void udp_init() { LIST_INIT(&udb); udbinfo.listhead = &udb; udbinfo.hashbase = hashinit(UDBHASHSIZE, M_PCB, &udbinfo.hashmask); udbinfo.porthashbase = hashinit(UDBHASHSIZE, M_PCB, &udbinfo.porthashmask); udbinfo.ipi_zone = zinit("udpcb", sizeof(struct inpcb), maxsockets, ZONE_INTERRUPT, 0); } void udp_input(m, iphlen) register struct mbuf *m; int iphlen; { register struct ip *ip; register struct udphdr *uh; register struct inpcb *inp; struct mbuf *opts = 0; int len; struct ip save_ip; udpstat.udps_ipackets++; /* * Strip IP options, if any; should skip this, * make available to user, and use on returned packets, * but we don't yet have a way to check the checksum * with options still present. */ if (iphlen > sizeof (struct ip)) { ip_stripoptions(m, (struct mbuf *)0); iphlen = sizeof(struct ip); } /* * Get IP and UDP header together in first mbuf. */ ip = mtod(m, struct ip *); if (m->m_len < iphlen + sizeof(struct udphdr)) { if ((m = m_pullup(m, iphlen + sizeof(struct udphdr))) == 0) { udpstat.udps_hdrops++; return; } ip = mtod(m, struct ip *); } uh = (struct udphdr *)((caddr_t)ip + iphlen); /* * Make mbuf data length reflect UDP length. * If not enough data to reflect UDP length, drop. */ len = ntohs((u_short)uh->uh_ulen); if (ip->ip_len != len) { if (len > ip->ip_len || len < sizeof(struct udphdr)) { udpstat.udps_badlen++; goto bad; } m_adj(m, len - ip->ip_len); /* ip->ip_len = len; */ } /* * Save a copy of the IP header in case we want restore it * for sending an ICMP error message in response. */ save_ip = *ip; /* * Checksum extended UDP header and data. */ if (uh->uh_sum) { bzero(((struct ipovly *)ip)->ih_x1, 9); ((struct ipovly *)ip)->ih_len = uh->uh_ulen; uh->uh_sum = in_cksum(m, len + sizeof (struct ip)); if (uh->uh_sum) { udpstat.udps_badsum++; m_freem(m); return; } } if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) || in_broadcast(ip->ip_dst, m->m_pkthdr.rcvif)) { struct inpcb *last; /* * Deliver a multicast or broadcast datagram to *all* sockets * for which the local and remote addresses and ports match * those of the incoming datagram. This allows more than * one process to receive multi/broadcasts on the same port. * (This really ought to be done for unicast datagrams as * well, but that would cause problems with existing * applications that open both address-specific sockets and * a wildcard socket listening to the same port -- they would * end up receiving duplicates of every unicast datagram. * Those applications open the multiple sockets to overcome an * inadequacy of the UDP socket interface, but for backwards * compatibility we avoid the problem here rather than * fixing the interface. Maybe 4.5BSD will remedy this?) */ /* * Construct sockaddr format source address. */ udp_in.sin_port = uh->uh_sport; udp_in.sin_addr = ip->ip_src; m->m_len -= sizeof (struct udpiphdr); m->m_data += sizeof (struct udpiphdr); /* * Locate pcb(s) for datagram. * (Algorithm copied from raw_intr().) */ last = NULL; for (inp = udb.lh_first; inp != NULL; inp = inp->inp_list.le_next) { if (inp->inp_lport != uh->uh_dport) continue; if (inp->inp_laddr.s_addr != INADDR_ANY) { if (inp->inp_laddr.s_addr != ip->ip_dst.s_addr) continue; } if (inp->inp_faddr.s_addr != INADDR_ANY) { if (inp->inp_faddr.s_addr != ip->ip_src.s_addr || inp->inp_fport != uh->uh_sport) continue; } if (last != NULL) { struct mbuf *n; if ((n = m_copy(m, 0, M_COPYALL)) != NULL) { if (last->inp_flags & INP_CONTROLOPTS || last->inp_socket->so_options & SO_TIMESTAMP) ip_savecontrol(last, &opts, ip, n); if (sbappendaddr(&last->inp_socket->so_rcv, (struct sockaddr *)&udp_in, n, opts) == 0) { m_freem(n); if (opts) m_freem(opts); udpstat.udps_fullsock++; } else sorwakeup(last->inp_socket); opts = 0; } } last = inp; /* * Don't look for additional matches if this one does * not have either the SO_REUSEPORT or SO_REUSEADDR * socket options set. This heuristic avoids searching * through all pcbs in the common case of a non-shared * port. It * assumes that an application will never * clear these options after setting them. */ if ((last->inp_socket->so_options&(SO_REUSEPORT|SO_REUSEADDR)) == 0) break; } if (last == NULL) { /* * No matching pcb found; discard datagram. * (No need to send an ICMP Port Unreachable * for a broadcast or multicast datgram.) */ udpstat.udps_noportbcast++; goto bad; } if (last->inp_flags & INP_CONTROLOPTS || last->inp_socket->so_options & SO_TIMESTAMP) ip_savecontrol(last, &opts, ip, m); if (sbappendaddr(&last->inp_socket->so_rcv, (struct sockaddr *)&udp_in, m, opts) == 0) { udpstat.udps_fullsock++; goto bad; } sorwakeup(last->inp_socket); return; } /* * Locate pcb for datagram. */ inp = in_pcblookup_hash(&udbinfo, ip->ip_src, uh->uh_sport, ip->ip_dst, uh->uh_dport, 1); if (inp == NULL) { if (log_in_vain) { char buf[4*sizeof "123"]; strcpy(buf, inet_ntoa(ip->ip_dst)); log(LOG_INFO, "Connection attempt to UDP %s:%d from %s:%d\n", buf, ntohs(uh->uh_dport), inet_ntoa(ip->ip_src), ntohs(uh->uh_sport)); } udpstat.udps_noport++; if (m->m_flags & (M_BCAST | M_MCAST)) { udpstat.udps_noportbcast++; goto bad; } *ip = save_ip; #ifdef ICMP_BANDLIM if (badport_bandlim(0) < 0) goto bad; #endif if (!blackhole) icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_PORT, 0, 0); return; } /* * Construct sockaddr format source address. * Stuff source address and datagram in user buffer. */ udp_in.sin_port = uh->uh_sport; udp_in.sin_addr = ip->ip_src; if (inp->inp_flags & INP_CONTROLOPTS || inp->inp_socket->so_options & SO_TIMESTAMP) ip_savecontrol(inp, &opts, ip, m); iphlen += sizeof(struct udphdr); m->m_len -= iphlen; m->m_pkthdr.len -= iphlen; m->m_data += iphlen; if (sbappendaddr(&inp->inp_socket->so_rcv, (struct sockaddr *)&udp_in, m, opts) == 0) { udpstat.udps_fullsock++; goto bad; } sorwakeup(inp->inp_socket); return; bad: m_freem(m); if (opts) m_freem(opts); } /* * Notify a udp user of an asynchronous error; * just wake up so that he can collect error status. */ -static void +void udp_notify(inp, errno) register struct inpcb *inp; int errno; { inp->inp_socket->so_error = errno; sorwakeup(inp->inp_socket); sowwakeup(inp->inp_socket); } void udp_ctlinput(cmd, sa, vip) int cmd; struct sockaddr *sa; void *vip; { register struct ip *ip = vip; register struct udphdr *uh; if (!PRC_IS_REDIRECT(cmd) && ((unsigned)cmd >= PRC_NCMDS || inetctlerrmap[cmd] == 0)) return; if (ip) { uh = (struct udphdr *)((caddr_t)ip + (ip->ip_hl << 2)); in_pcbnotify(&udb, sa, uh->uh_dport, ip->ip_src, uh->uh_sport, cmd, udp_notify); } else in_pcbnotify(&udb, sa, 0, zeroin_addr, 0, cmd, udp_notify); } static int udp_pcblist SYSCTL_HANDLER_ARGS { int error, i, n, s; struct inpcb *inp, **inp_list; inp_gen_t gencnt; struct xinpgen xig; /* * The process of preparing the TCB list is too time-consuming and * resource-intensive to repeat twice on every request. */ if (req->oldptr == 0) { n = udbinfo.ipi_count; req->oldidx = 2 * (sizeof xig) + (n + n/8) * sizeof(struct xinpcb); return 0; } if (req->newptr != 0) return EPERM; /* * OK, now we're committed to doing something. */ s = splnet(); gencnt = udbinfo.ipi_gencnt; n = udbinfo.ipi_count; splx(s); xig.xig_len = sizeof xig; xig.xig_count = n; xig.xig_gen = gencnt; xig.xig_sogen = so_gencnt; error = SYSCTL_OUT(req, &xig, sizeof xig); if (error) return error; inp_list = malloc(n * sizeof *inp_list, M_TEMP, M_WAITOK); if (inp_list == 0) return ENOMEM; s = splnet(); for (inp = udbinfo.listhead->lh_first, i = 0; inp && i < n; inp = inp->inp_list.le_next) { if (inp->inp_gencnt <= gencnt && !prison_xinpcb(req->p, inp)) inp_list[i++] = inp; } splx(s); n = i; error = 0; for (i = 0; i < n; i++) { inp = inp_list[i]; if (inp->inp_gencnt <= gencnt) { struct xinpcb xi; xi.xi_len = sizeof xi; /* XXX should avoid extra copy */ bcopy(inp, &xi.xi_inp, sizeof *inp); if (inp->inp_socket) sotoxsocket(inp->inp_socket, &xi.xi_socket); error = SYSCTL_OUT(req, &xi, sizeof xi); } } if (!error) { /* * Give the user an updated idea of our state. * If the generation differs from what we told * her before, she knows that something happened * while we were processing this request, and it * might be necessary to retry. */ s = splnet(); xig.xig_gen = udbinfo.ipi_gencnt; xig.xig_sogen = so_gencnt; xig.xig_count = udbinfo.ipi_count; splx(s); error = SYSCTL_OUT(req, &xig, sizeof xig); } free(inp_list, M_TEMP); return error; } SYSCTL_PROC(_net_inet_udp, UDPCTL_PCBLIST, pcblist, CTLFLAG_RD, 0, 0, udp_pcblist, "S,xinpcb", "List of active UDP sockets"); static int udp_getcred SYSCTL_HANDLER_ARGS { struct sockaddr_in addrs[2]; struct inpcb *inp; int error, s; error = suser(req->p); if (error) return (error); error = SYSCTL_IN(req, addrs, sizeof(addrs)); if (error) return (error); s = splnet(); inp = in_pcblookup_hash(&udbinfo, addrs[1].sin_addr, addrs[1].sin_port, addrs[0].sin_addr, addrs[0].sin_port, 1); if (inp == NULL || inp->inp_socket == NULL) { error = ENOENT; goto out; } error = SYSCTL_OUT(req, inp->inp_socket->so_cred, sizeof(struct ucred)); out: splx(s); return (error); } SYSCTL_PROC(_net_inet_udp, OID_AUTO, getcred, CTLTYPE_OPAQUE|CTLFLAG_RW, 0, 0, udp_getcred, "S,ucred", "Get the ucred of a UDP connection"); static int udp_output(inp, m, addr, control, p) register struct inpcb *inp; register struct mbuf *m; struct sockaddr *addr; struct mbuf *control; struct proc *p; { register struct udpiphdr *ui; register int len = m->m_pkthdr.len; struct in_addr laddr; struct sockaddr_in *sin; int s = 0, error = 0; if (control) m_freem(control); /* XXX */ if (len + sizeof(struct udpiphdr) > IP_MAXPACKET) { error = EMSGSIZE; goto release; } if (addr) { sin = (struct sockaddr_in *)addr; prison_remote_ip(p, 0, &sin->sin_addr.s_addr); laddr = inp->inp_laddr; if (inp->inp_faddr.s_addr != INADDR_ANY) { error = EISCONN; goto release; } /* * Must block input while temporarily connected. */ s = splnet(); error = in_pcbconnect(inp, addr, p); if (error) { splx(s); goto release; } } else { if (inp->inp_faddr.s_addr == INADDR_ANY) { error = ENOTCONN; goto release; } } /* * Calculate data length and get a mbuf * for UDP and IP headers. */ M_PREPEND(m, sizeof(struct udpiphdr), M_DONTWAIT); if (m == 0) { error = ENOBUFS; if (addr) splx(s); goto release; } /* * Fill in mbuf with extended UDP header * and addresses and length put into network format. */ ui = mtod(m, struct udpiphdr *); bzero(ui->ui_x1, sizeof(ui->ui_x1)); ui->ui_pr = IPPROTO_UDP; ui->ui_len = htons((u_short)len + sizeof (struct udphdr)); ui->ui_src = inp->inp_laddr; ui->ui_dst = inp->inp_faddr; ui->ui_sport = inp->inp_lport; ui->ui_dport = inp->inp_fport; ui->ui_ulen = ui->ui_len; /* * Stuff checksum and output datagram. */ ui->ui_sum = 0; if (udpcksum) { if ((ui->ui_sum = in_cksum(m, sizeof (struct udpiphdr) + len)) == 0) ui->ui_sum = 0xffff; } ((struct ip *)ui)->ip_len = sizeof (struct udpiphdr) + len; ((struct ip *)ui)->ip_ttl = inp->inp_ip_ttl; /* XXX */ ((struct ip *)ui)->ip_tos = inp->inp_ip_tos; /* XXX */ udpstat.udps_opackets++; error = ip_output(m, inp->inp_options, &inp->inp_route, inp->inp_socket->so_options & (SO_DONTROUTE | SO_BROADCAST), inp->inp_moptions); if (addr) { in_pcbdisconnect(inp); inp->inp_laddr = laddr; /* XXX rehash? */ splx(s); } return (error); release: m_freem(m); return (error); } -static u_long udp_sendspace = 9216; /* really max datagram size */ +u_long udp_sendspace = 9216; /* really max datagram size */ /* 40 1K datagrams */ SYSCTL_INT(_net_inet_udp, UDPCTL_MAXDGRAM, maxdgram, CTLFLAG_RW, &udp_sendspace, 0, "Maximum outgoing UDP datagram size"); -static u_long udp_recvspace = 40 * (1024 + sizeof(struct sockaddr_in)); +u_long udp_recvspace = 40 * (1024 + sizeof(struct sockaddr_in)); SYSCTL_INT(_net_inet_udp, UDPCTL_RECVSPACE, recvspace, CTLFLAG_RW, &udp_recvspace, 0, "Maximum incoming UDP datagram size"); static int udp_abort(struct socket *so) { struct inpcb *inp; int s; inp = sotoinpcb(so); if (inp == 0) return EINVAL; /* ??? possible? panic instead? */ soisdisconnected(so); s = splnet(); in_pcbdetach(inp); splx(s); return 0; } static int udp_attach(struct socket *so, int proto, struct proc *p) { struct inpcb *inp; int s, error; inp = sotoinpcb(so); if (inp != 0) return EINVAL; s = splnet(); error = in_pcballoc(so, &udbinfo, p); splx(s); if (error) return error; error = soreserve(so, udp_sendspace, udp_recvspace); if (error) return error; ((struct inpcb *) so->so_pcb)->inp_ip_ttl = ip_defttl; return 0; } static int udp_bind(struct socket *so, struct sockaddr *nam, struct proc *p) { struct inpcb *inp; int s, error; inp = sotoinpcb(so); if (inp == 0) return EINVAL; s = splnet(); error = in_pcbbind(inp, nam, p); splx(s); return error; } static int udp_connect(struct socket *so, struct sockaddr *nam, struct proc *p) { struct inpcb *inp; int s, error; struct sockaddr_in *sin; inp = sotoinpcb(so); if (inp == 0) return EINVAL; if (inp->inp_faddr.s_addr != INADDR_ANY) return EISCONN; s = splnet(); sin = (struct sockaddr_in *)nam; prison_remote_ip(p, 0, &sin->sin_addr.s_addr); error = in_pcbconnect(inp, nam, p); splx(s); if (error == 0) soisconnected(so); return error; } static int udp_detach(struct socket *so) { struct inpcb *inp; int s; inp = sotoinpcb(so); if (inp == 0) return EINVAL; s = splnet(); in_pcbdetach(inp); splx(s); return 0; } static int udp_disconnect(struct socket *so) { struct inpcb *inp; int s; inp = sotoinpcb(so); if (inp == 0) return EINVAL; if (inp->inp_faddr.s_addr == INADDR_ANY) return ENOTCONN; s = splnet(); in_pcbdisconnect(inp); inp->inp_laddr.s_addr = INADDR_ANY; splx(s); so->so_state &= ~SS_ISCONNECTED; /* XXX */ return 0; } static int udp_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *addr, struct mbuf *control, struct proc *p) { struct inpcb *inp; inp = sotoinpcb(so); if (inp == 0) { m_freem(m); return EINVAL; } return udp_output(inp, m, addr, control, p); } -static int +int udp_shutdown(struct socket *so) { struct inpcb *inp; inp = sotoinpcb(so); if (inp == 0) return EINVAL; socantsendmore(so); return 0; } struct pr_usrreqs udp_usrreqs = { udp_abort, pru_accept_notsupp, udp_attach, udp_bind, udp_connect, pru_connect2_notsupp, in_control, udp_detach, udp_disconnect, pru_listen_notsupp, in_setpeeraddr, pru_rcvd_notsupp, pru_rcvoob_notsupp, udp_send, pru_sense_null, udp_shutdown, in_setsockaddr, sosend, soreceive, sopoll }; diff --git a/sys/netinet/udp_var.h b/sys/netinet/udp_var.h index 5ede8a6a3d43..0ee825863905 100644 --- a/sys/netinet/udp_var.h +++ b/sys/netinet/udp_var.h @@ -1,113 +1,124 @@ /* * Copyright (c) 1982, 1986, 1989, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)udp_var.h 8.1 (Berkeley) 6/10/93 * $FreeBSD$ */ #ifndef _NETINET_UDP_VAR_H_ #define _NETINET_UDP_VAR_H_ /* * UDP kernel structures and variables. */ struct udpiphdr { struct ipovly ui_i; /* overlaid ip structure */ struct udphdr ui_u; /* udp header */ }; #define ui_x1 ui_i.ih_x1 #define ui_pr ui_i.ih_pr #define ui_len ui_i.ih_len #define ui_src ui_i.ih_src #define ui_dst ui_i.ih_dst #define ui_sport ui_u.uh_sport #define ui_dport ui_u.uh_dport #define ui_ulen ui_u.uh_ulen #define ui_sum ui_u.uh_sum struct udpcb { /* XXX - these should be by reference so we can do options quickly */ struct ip udb_ip; struct udphdr udb_uh; struct sockaddr_in udb_conn; struct in_hostcache *udb_hc; struct mbuf *udb_queue; }; #define inptoudpcb(inp) ((struct udpdb *)(inp)->inp_ppcb) struct udpstat { /* input statistics: */ u_long udps_ipackets; /* total input packets */ u_long udps_hdrops; /* packet shorter than header */ u_long udps_badsum; /* checksum error */ + u_long udps_nosum; /* no checksum */ u_long udps_badlen; /* data length larger than packet */ u_long udps_noport; /* no socket on port */ u_long udps_noportbcast; /* of above, arrived as broadcast */ u_long udps_fullsock; /* not delivered, input socket full */ u_long udpps_pcbcachemiss; /* input packets missing pcb cache */ u_long udpps_pcbhashmiss; /* input packets not for hashed pcb */ /* output statistics: */ u_long udps_opackets; /* total output packets */ u_long udps_fastout; /* output packets on fast path */ + /* of no socket on port, arrived as multicast */ + u_long udps_noportmcast; }; /* * Names for UDP sysctl objects */ #define UDPCTL_CHECKSUM 1 /* checksum UDP packets */ #define UDPCTL_STATS 2 /* statistics (read-only) */ #define UDPCTL_MAXDGRAM 3 /* max datagram size */ #define UDPCTL_RECVSPACE 4 /* default receive buffer space */ #define UDPCTL_PCBLIST 5 /* list of PCBs for UDP sockets */ #define UDPCTL_MAXID 6 #define UDPCTL_NAMES { \ { 0, 0 }, \ { "checksum", CTLTYPE_INT }, \ { "stats", CTLTYPE_STRUCT }, \ { "maxdgram", CTLTYPE_INT }, \ { "recvspace", CTLTYPE_INT }, \ { "pcblist", CTLTYPE_STRUCT }, \ } #ifdef KERNEL SYSCTL_DECL(_net_inet_udp); extern struct pr_usrreqs udp_usrreqs; +extern struct inpcbhead udb; extern struct inpcbinfo udbinfo; +extern u_long udp_sendspace; +extern u_long udp_recvspace; +extern struct udpstat udpstat; +extern int log_in_vain; -void udp_ctlinput __P((int, struct sockaddr *, void *)); -void udp_init __P((void)); -void udp_input __P((struct mbuf *, int)); +void udp_ctlinput __P((int, struct sockaddr *, void *)); +void udp_init __P((void)); +void udp_input __P((struct mbuf *, int)); + +void udp_notify __P((struct inpcb *inp, int errno)); +int udp_shutdown __P((struct socket *so)); #endif #endif diff --git a/sys/netinet6/in6.h b/sys/netinet6/in6.h new file mode 100644 index 000000000000..97b0c7e9dd58 --- /dev/null +++ b/sys/netinet6/in6.h @@ -0,0 +1,639 @@ +/* + * Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the project nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE PROJECT AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE PROJECT OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +/* + * Copyright (c) 1982, 1986, 1990, 1993 + * The Regents of the University of California. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)in.h 8.3 (Berkeley) 1/3/94 + * $FreeBSD$ + */ + +#ifndef _NETINET6_IN6_H_ +#define _NETINET6_IN6_H_ + +#if !defined(_XOPEN_SOURCE) +#include +#endif + +/* + * Identification of the network protocol stack + */ +#define __KAME__ + +/* + * Local port number conventions: + * + * Ports < IPPORT_RESERVED are reserved for privileged processes (e.g. root), + * unless a kernel is compiled with IPNOPRIVPORTS defined. + * + * When a user does a bind(2) or connect(2) with a port number of zero, + * a non-conflicting local port address is chosen. + * + * The default range is IPPORT_ANONMIX to IPPORT_ANONMAX, although + * that is settable by sysctl(3); net.inet.ip.anonportmin and + * net.inet.ip.anonportmax respectively. + * + * A user may set the IPPROTO_IP option IP_PORTRANGE to change this + * default assignment range. + * + * The value IP_PORTRANGE_DEFAULT causes the default behavior. + * + * The value IP_PORTRANGE_HIGH is the same as IP_PORTRANGE_DEFAULT, + * and exists only for FreeBSD compatibility purposes. + * + * The value IP_PORTRANGE_LOW changes the range to the "low" are + * that is (by convention) restricted to privileged processes. + * This convention is based on "vouchsafe" principles only. + * It is only secure if you trust the remote host to restrict these ports. + * The range is IPPORT_RESERVEDMIN to IPPORT_RESERVEDMAX. + */ + +#define IPV6PORT_RESERVED 1024 +#define IPV6PORT_ANONMIN 49152 +#define IPV6PORT_ANONMAX 65535 +#define IPV6PORT_RESERVEDMIN 600 +#define IPV6PORT_RESERVEDMAX (IPV6PORT_RESERVED-1) + +/* + * IPv6 address + */ +struct in6_addr { + union { + u_int8_t __u6_addr8[16]; + u_int16_t __u6_addr16[8]; + u_int32_t __u6_addr32[4]; + } __u6_addr; /* 128-bit IP6 address */ +}; + +#define s6_addr __u6_addr.__u6_addr8 +#ifdef _KERNEL /*XXX nonstandard*/ +#define s6_addr8 __u6_addr.__u6_addr8 +#define s6_addr16 __u6_addr.__u6_addr16 +#define s6_addr32 __u6_addr.__u6_addr32 +#endif + +#define INET6_ADDRSTRLEN 46 + +/* + * Socket address for IPv6 + */ +#if !defined(_XOPEN_SOURCE) +#define SIN6_LEN +#endif +struct sockaddr_in6 { + u_char sin6_len; /* length of this struct(sa_family_t)*/ + u_char sin6_family; /* AF_INET6 (sa_family_t) */ + u_int16_t sin6_port; /* Transport layer port # (in_port_t)*/ + u_int32_t sin6_flowinfo; /* IP6 flow information */ + struct in6_addr sin6_addr; /* IP6 address */ + u_int32_t sin6_scope_id; /* intface scope id */ +}; + +/* + * Local definition for masks + */ +#ifdef _KERNEL /*XXX nonstandard*/ +#define IN6MASK0 {{{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }}} +#define IN6MASK32 {{{ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }}} +#define IN6MASK64 {{{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }}} +#define IN6MASK96 {{{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, \ + 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }}} +#define IN6MASK128 {{{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, \ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }}} +#endif + +#ifdef _KERNEL +extern const struct in6_addr in6mask0; +extern const struct in6_addr in6mask32; +extern const struct in6_addr in6mask64; +extern const struct in6_addr in6mask96; +extern const struct in6_addr in6mask128; +#endif /* _KERNEL */ + +/* + * Macros started with IPV6_ADDR is KAME local + */ +#ifdef _KERNEL /*XXX nonstandard*/ +#if BYTE_ORDER == BIG_ENDIAN +#define IPV6_ADDR_INT32_ONE 1 +#define IPV6_ADDR_INT32_TWO 2 +#define IPV6_ADDR_INT32_MNL 0xff010000 +#define IPV6_ADDR_INT32_MLL 0xff020000 +#define IPV6_ADDR_INT32_SMP 0x0000ffff +#define IPV6_ADDR_INT16_ULL 0xfe80 +#define IPV6_ADDR_INT16_USL 0xfec0 +#define IPV6_ADDR_INT16_MLL 0xff02 +#elif BYTE_ORDER == LITTLE_ENDIAN +#define IPV6_ADDR_INT32_ONE 0x01000000 +#define IPV6_ADDR_INT32_TWO 0x02000000 +#define IPV6_ADDR_INT32_MNL 0x000001ff +#define IPV6_ADDR_INT32_MLL 0x000002ff +#define IPV6_ADDR_INT32_SMP 0xffff0000 +#define IPV6_ADDR_INT16_ULL 0x80fe +#define IPV6_ADDR_INT16_USL 0xc0fe +#define IPV6_ADDR_INT16_MLL 0x02ff +#endif +#endif + +/* + * Definition of some useful macros to handle IP6 addresses + */ +#define IN6ADDR_ANY_INIT \ + {{{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }}} +#define IN6ADDR_LOOPBACK_INIT \ + {{{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01 }}} +#define IN6ADDR_NODELOCAL_ALLNODES_INIT \ + {{{ 0xff, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01 }}} +#define IN6ADDR_LINKLOCAL_ALLNODES_INIT \ + {{{ 0xff, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01 }}} +#define IN6ADDR_LINKLOCAL_ALLROUTERS_INIT \ + {{{ 0xff, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02 }}} + +extern const struct in6_addr in6addr_any; +extern const struct in6_addr in6addr_loopback; +extern const struct in6_addr in6addr_nodelocal_allnodes; +extern const struct in6_addr in6addr_linklocal_allnodes; +extern const struct in6_addr in6addr_linklocal_allrouters; + +/* + * Equality + */ +#define IN6_ARE_ADDR_EQUAL(a, b) \ + (memcmp((a), (b), sizeof(struct in6_addr)) == 0) + +/* + * Unspecified + */ +#define IN6_IS_ADDR_UNSPECIFIED(a) \ + ((*(u_int32_t *)(&(a)->s6_addr[0]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[4]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[8]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[12]) == 0)) + +/* + * Loopback + */ +#define IN6_IS_ADDR_LOOPBACK(a) \ + ((*(u_int32_t *)(&(a)->s6_addr[0]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[4]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[8]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[12]) == ntohl(1))) + +/* + * IPv4 compatible + */ +#define IN6_IS_ADDR_V4COMPAT(a) \ + ((*(u_int32_t *)(&(a)->s6_addr[0]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[4]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[8]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[12]) != 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[12]) != ntohl(1))) + +/* + * Mapped + */ +#define IN6_IS_ADDR_V4MAPPED(a) \ + ((*(u_int32_t *)(&(a)->s6_addr[0]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[4]) == 0) && \ + (*(u_int32_t *)(&(a)->s6_addr[8]) == ntohl(0x0000ffff))) + +/* + * KAME Scope Values + */ + +#ifdef _KERNEL /*XXX nonstandard*/ +#define IPV6_ADDR_SCOPE_NODELOCAL 0x01 +#define IPV6_ADDR_SCOPE_LINKLOCAL 0x02 +#define IPV6_ADDR_SCOPE_SITELOCAL 0x05 +#define IPV6_ADDR_SCOPE_ORGLOCAL 0x08 /* just used in this file */ +#define IPV6_ADDR_SCOPE_GLOBAL 0x0e +#else +#define __IPV6_ADDR_SCOPE_NODELOCAL 0x01 +#define __IPV6_ADDR_SCOPE_LINKLOCAL 0x02 +#define __IPV6_ADDR_SCOPE_SITELOCAL 0x05 +#define __IPV6_ADDR_SCOPE_ORGLOCAL 0x08 /* just used in this file */ +#define __IPV6_ADDR_SCOPE_GLOBAL 0x0e +#endif + +/* + * Unicast Scope + * Note that we must check topmost 10 bits only, not 16 bits (see RFC2373). + */ +#define IN6_IS_ADDR_LINKLOCAL(a) \ + (((a)->s6_addr[0] == 0xfe) && (((a)->s6_addr[1] & 0xc0) == 0x80)) +#define IN6_IS_ADDR_SITELOCAL(a) \ + (((a)->s6_addr[0] == 0xfe) && (((a)->s6_addr[1] & 0xc0) == 0xc0)) + +/* + * Multicast + */ +#define IN6_IS_ADDR_MULTICAST(a) ((a)->s6_addr[0] == 0xff) + +#ifdef _KERNEL /*XXX nonstandard*/ +#define IPV6_ADDR_MC_SCOPE(a) ((a)->s6_addr[1] & 0x0f) +#else +#define __IPV6_ADDR_MC_SCOPE(a) ((a)->s6_addr[1] & 0x0f) +#endif + +/* + * Multicast Scope + */ +#ifdef _KERNEL /*refers nonstandard items */ +#define IN6_IS_ADDR_MC_NODELOCAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (IPV6_ADDR_MC_SCOPE(a) == IPV6_ADDR_SCOPE_NODELOCAL)) +#define IN6_IS_ADDR_MC_LINKLOCAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (IPV6_ADDR_MC_SCOPE(a) == IPV6_ADDR_SCOPE_LINKLOCAL)) +#define IN6_IS_ADDR_MC_SITELOCAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (IPV6_ADDR_MC_SCOPE(a) == IPV6_ADDR_SCOPE_SITELOCAL)) +#define IN6_IS_ADDR_MC_ORGLOCAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (IPV6_ADDR_MC_SCOPE(a) == IPV6_ADDR_SCOPE_ORGLOCAL)) +#define IN6_IS_ADDR_MC_GLOBAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (IPV6_ADDR_MC_SCOPE(a) == IPV6_ADDR_SCOPE_GLOBAL)) +#else +#define IN6_IS_ADDR_MC_NODELOCAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (__IPV6_ADDR_MC_SCOPE(a) == __IPV6_ADDR_SCOPE_NODELOCAL)) +#define IN6_IS_ADDR_MC_LINKLOCAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (__IPV6_ADDR_MC_SCOPE(a) == __IPV6_ADDR_SCOPE_LINKLOCAL)) +#define IN6_IS_ADDR_MC_SITELOCAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (__IPV6_ADDR_MC_SCOPE(a) == __IPV6_ADDR_SCOPE_SITELOCAL)) +#define IN6_IS_ADDR_MC_ORGLOCAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (__IPV6_ADDR_MC_SCOPE(a) == __IPV6_ADDR_SCOPE_ORGLOCAL)) +#define IN6_IS_ADDR_MC_GLOBAL(a) \ + (IN6_IS_ADDR_MULTICAST(a) && \ + (__IPV6_ADDR_MC_SCOPE(a) == __IPV6_ADDR_SCOPE_GLOBAL)) +#endif + +/* + * Wildcard Socket + */ +#if 0 /*pre-RFC2553*/ +#define IN6_IS_ADDR_ANY(a) IN6_IS_ADDR_UNSPECIFIED(a) +#endif + +/* + * KAME Scope + */ +#ifdef _KERNEL /*nonstandard*/ +#define IN6_IS_SCOPE_LINKLOCAL(a) \ + ((IN6_IS_ADDR_LINKLOCAL(a)) || \ + (IN6_IS_ADDR_MC_LINKLOCAL(a))) +#endif + +/* + * IP6 route structure + */ +#if !defined(_XOPEN_SOURCE) +struct route_in6 { + struct rtentry *ro_rt; + struct sockaddr_in6 ro_dst; +}; +#endif + +/* + * Options for use with [gs]etsockopt at the IPV6 level. + * First word of comment is data type; bool is stored in int. + */ +#define IPV6_OPTIONS 1 /* buf/ip6_opts; set/get IP6 options */ +/* no hdrincl */ +#define IPV6_SOCKOPT_RESERVED1 3 /* reserved for future use */ +#define IPV6_UNICAST_HOPS 4 /* int; IP6 hops */ +#define IPV6_RECVOPTS 5 /* bool; receive all IP6 opts w/dgram */ +#define IPV6_RECVRETOPTS 6 /* bool; receive IP6 opts for response */ +#define IPV6_RECVDSTADDR 7 /* bool; receive IP6 dst addr w/dgram */ +#define IPV6_RETOPTS 8 /* ip6_opts; set/get IP6 options */ +#define IPV6_MULTICAST_IF 9 /* u_char; set/get IP6 multicast i/f */ +#define IPV6_MULTICAST_HOPS 10 /* u_char; set/get IP6 multicast hops */ +#define IPV6_MULTICAST_LOOP 11 /* u_char; set/get IP6 multicast loopback */ +#define IPV6_JOIN_GROUP 12 /* ip6_mreq; join a group membership */ +#define IPV6_LEAVE_GROUP 13 /* ip6_mreq; leave a group membership */ +#define IPV6_PORTRANGE 14 /* int; range to choose for unspec port */ +#define ICMP6_FILTER 18 /* icmp6_filter; icmp6 filter */ +#define IPV6_PKTINFO 19 /* bool; send/rcv if, src/dst addr */ +#define IPV6_HOPLIMIT 20 /* bool; hop limit */ +#define IPV6_NEXTHOP 21 /* bool; next hop addr */ +#define IPV6_HOPOPTS 22 /* bool; hop-by-hop option */ +#define IPV6_DSTOPTS 23 /* bool; destination option */ +#define IPV6_RTHDR 24 /* bool; routing header */ +#define IPV6_PKTOPTIONS 25 /* buf/cmsghdr; set/get IPv6 options */ +#define IPV6_CHECKSUM 26 /* int; checksum offset for raw socket */ +#define IPV6_BINDV6ONLY 27 /* bool; only bind INET6 at null bind */ + +/* for IPsec */ +#define IPV6_IPSEC_POLICY 28 /* struct; get/set security policy */ +#define IPV6_FAITH 29 /* bool; accept FAITH'ed connections */ + +/* for IPV6FIREWALL */ +#define IPV6_FW_ADD 30 /* add a firewall rule to chain */ +#define IPV6_FW_DEL 31 /* delete a firewall rule from chain */ +#define IPV6_FW_FLUSH 32 /* flush firewall rule chain */ +#define IPV6_FW_ZERO 33 /* clear single/all firewall counter(s) */ +#define IPV6_FW_GET 34 /* get entire firewall rule chain */ + +#define IPV6_RTHDR_LOOSE 0 /* this hop need not be a neighbor. XXX old spec */ +#define IPV6_RTHDR_STRICT 1 /* this hop must be a neighbor. XXX old spec */ +#define IPV6_RTHDR_TYPE_0 0 /* IPv6 routing header type 0 */ + +/* + * Defaults and limits for options + */ +#define IPV6_DEFAULT_MULTICAST_HOPS 1 /* normally limit m'casts to 1 hop */ +#define IPV6_DEFAULT_MULTICAST_LOOP 1 /* normally hear sends if a member */ + +/* + * Argument structure for IPV6_JOIN_GROUP and IPV6_LEAVE_GROUP. + */ +struct ipv6_mreq { + struct in6_addr ipv6mr_multiaddr; + u_int ipv6mr_interface; +}; + +/* + * IPV6_PKTINFO: Packet information(RFC2292 sec 5) + */ +struct in6_pktinfo { + struct in6_addr ipi6_addr; /* src/dst IPv6 address */ + u_int ipi6_ifindex; /* send/recv interface index */ +}; + +/* + * Argument for IPV6_PORTRANGE: + * - which range to search when port is unspecified at bind() or connect() + */ +#define IPV6_PORTRANGE_DEFAULT 0 /* default range */ +#define IPV6_PORTRANGE_HIGH 1 /* "high" - request firewall bypass */ +#define IPV6_PORTRANGE_LOW 2 /* "low" - vouchsafe security */ + +#if !defined(_XOPEN_SOURCE) +/* + * Definitions for inet6 sysctl operations. + * + * Third level is protocol number. + * Fourth level is desired variable within that protocol. + */ +#define IPV6PROTO_MAXID (IPPROTO_PIM + 1) /* don't list to IPV6PROTO_MAX */ + +#define CTL_IPV6PROTO_NAMES { \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, \ + { "tcp6", CTLTYPE_NODE }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { "udp6", CTLTYPE_NODE }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, \ + { "ip6", CTLTYPE_NODE }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, \ + { "ipsec6", CTLTYPE_NODE }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { "icmp6", CTLTYPE_NODE }, \ + { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { "pim6", CTLTYPE_NODE }, \ +} + +/* + * Names for IP sysctl objects + */ +#define IPV6CTL_FORWARDING 1 /* act as router */ +#define IPV6CTL_SENDREDIRECTS 2 /* may send redirects when forwarding*/ +#define IPV6CTL_DEFHLIM 3 /* default Hop-Limit */ +#ifdef notyet +#define IPV6CTL_DEFMTU 4 /* default MTU */ +#endif +#define IPV6CTL_FORWSRCRT 5 /* forward source-routed dgrams */ +#define IPV6CTL_STATS 6 /* stats */ +#define IPV6CTL_MRTSTATS 7 /* multicast forwarding stats */ +#define IPV6CTL_MRTPROTO 8 /* multicast routing protocol */ +#define IPV6CTL_MAXFRAGPACKETS 9 /* max packets reassembly queue */ +#define IPV6CTL_SOURCECHECK 10 /* verify source route and intf */ +#define IPV6CTL_SOURCECHECK_LOGINT 11 /* minimume logging interval */ +#define IPV6CTL_ACCEPT_RTADV 12 +#define IPV6CTL_KEEPFAITH 13 +#define IPV6CTL_LOG_INTERVAL 14 +#define IPV6CTL_HDRNESTLIMIT 15 +#define IPV6CTL_DAD_COUNT 16 +#define IPV6CTL_AUTO_FLOWLABEL 17 +#define IPV6CTL_DEFMCASTHLIM 18 +#define IPV6CTL_GIF_HLIM 19 /* default HLIM for gif encap packet */ +#define IPV6CTL_USE_DEPRECATED 21 /* use deprecated addr (RFC2462 5.5.4) */ +#define IPV6CTL_RR_PRUNE 22 /* walk timer for router renumbering */ +#ifdef MAPPED_ADDR_ENABLED +#define IPV6CTL_MAPPED_ADDR 23 +#endif /* MAPPED_ADDR_ENABLED */ +/* New entries should be added here from current IPV6CTL_MAXID value. */ +#define IPV6CTL_MAXID 24 + +#ifdef MAPPED_ADDR_ENABLED +#define IPV6CTL_NAMES_MAPPED_ADDR "mapped_addr" +#define IPV6CTL_TYPE_MAPPED_ADDR CTLTYPE_INT +#define IPV6CTL_VARS_MAPPED_ADDR &ip6_mapped_addr_on +#else /* MAPPED_ADDR_ENABLED */ +#define IPV6CTL_NAMES_MAPPED_ADDR 0 +#define IPV6CTL_TYPE_MAPPED_ADDR 0 +#define IPV6CTL_VARS_MAPPED_ADDR 0 +#endif /* MAPPED_ADDR_ENABLED */ + +#define IPV6CTL_NAMES { \ + { 0, 0 }, \ + { "forwarding", CTLTYPE_INT }, \ + { "redirect", CTLTYPE_INT }, \ + { "hlim", CTLTYPE_INT }, \ + { "mtu", CTLTYPE_INT }, \ + { "forwsrcrt", CTLTYPE_INT }, \ + { 0, 0 }, \ + { 0, 0 }, \ + { "mrtproto", CTLTYPE_INT }, \ + { "maxfragpackets", CTLTYPE_INT }, \ + { "sourcecheck", CTLTYPE_INT }, \ + { "sourcecheck_logint", CTLTYPE_INT }, \ + { "accept_rtadv", CTLTYPE_INT }, \ + { "keepfaith", CTLTYPE_INT }, \ + { "log_interval", CTLTYPE_INT }, \ + { "hdrnestlimit", CTLTYPE_INT }, \ + { "dad_count", CTLTYPE_INT }, \ + { "auto_flowlabel", CTLTYPE_INT }, \ + { "defmcasthlim", CTLTYPE_INT }, \ + { "gifhlim", CTLTYPE_INT }, \ + { 0, 0 }, \ + { "use_deprecated", CTLTYPE_INT }, \ + { "rr_prune", CTLTYPE_INT }, \ + { IPV6CTL_NAMES_MAPPED_ADDR, IPV6CTL_TYPE_MAPPED_ADDR }, \ +} + +#define IPV6CTL_VARS { \ + 0, \ + &ip6_forwarding, \ + &ip6_sendredirects, \ + &ip6_defhlim, \ + 0, \ + &ip6_forward_srcrt, \ + 0, \ + 0, \ + 0, \ + &ip6_maxfragpackets, \ + &ip6_sourcecheck, \ + &ip6_sourcecheck_interval, \ + &ip6_accept_rtadv, \ + &ip6_keepfaith, \ + &ip6_log_interval, \ + &ip6_hdrnestlimit, \ + &ip6_dad_count, \ + &ip6_auto_flowlabel, \ + &ip6_defmcasthlim, \ + &ip6_gif_hlim, \ + 0, \ + &ip6_use_deprecated, \ + &ip6_rr_prune, \ + IPV6CTL_VARS_MAPPED_ADDR, \ +} +#endif /* !_XOPEN_SOURCE */ + +#ifdef _KERNEL +struct cmsghdr; + +int in6_canforward __P((struct in6_addr *, struct in6_addr *)); +int in6_cksum __P((struct mbuf *, u_int8_t, int, int)); +int in6_localaddr __P((struct in6_addr *)); +int in6_addrscope __P((struct in6_addr *)); +struct in6_ifaddr *in6_ifawithscope __P((struct ifnet *, struct in6_addr *)); +struct in6_ifaddr *in6_ifawithifp __P((struct ifnet *, struct in6_addr *)); +extern void in6_if_up __P((struct ifnet *)); +#ifdef MAPPED_ADDR_ENABLED +struct sockaddr; + +void in6_sin6_2_sin __P((struct sockaddr_in *sin, + struct sockaddr_in6 *sin6)); +void in6_sin_2_v4mapsin6 __P((struct sockaddr_in *sin, + struct sockaddr_in6 *sin6)); +void in6_sin6_2_sin_in_sock __P((struct sockaddr *nam)); +void in6_sin_2_v4mapsin6_in_sock __P((struct sockaddr **nam)); +#endif /* MAPPED_ADDR_ENABLED */ + +#define satosin6(sa) ((struct sockaddr_in6 *)(sa)) +#define sin6tosa(sin6) ((struct sockaddr *)(sin6)) +#define ifatoia6(ifa) ((struct in6_ifaddr *)(ifa)) +#endif /* _KERNEL */ + +__BEGIN_DECLS +struct cmsghdr; + +extern int inet6_option_space(int); +extern int inet6_option_init(void *, struct cmsghdr **, int); +extern int inet6_option_append(struct cmsghdr *, const u_int8_t *, int, int); +extern u_int8_t *inet6_option_alloc(struct cmsghdr *, int, int, int); +extern int inet6_option_next(const struct cmsghdr *, u_int8_t **); +extern int inet6_option_find(const struct cmsghdr *, u_int8_t **, int); + +extern size_t inet6_rthdr_space __P((int, int)); +extern struct cmsghdr *inet6_rthdr_init __P((void *, int)); +extern int inet6_rthdr_add __P((struct cmsghdr *, const struct in6_addr *, + u_int)); +extern int inet6_rthdr_lasthop __P((struct cmsghdr *, u_int)); +#if 0 /* not implemented yet */ +extern int inet6_rthdr_reverse __P((const struct cmsghdr *, struct cmsghdr *)); +#endif +extern int inet6_rthdr_segments __P((const struct cmsghdr *)); +extern struct in6_addr *inet6_rthdr_getaddr __P((struct cmsghdr *, int)); +extern int inet6_rthdr_getflags __P((const struct cmsghdr *, int)); +__END_DECLS + +#endif /* !_NETINET6_IN6_H_ */ diff --git a/sys/netinet6/in6_var.h b/sys/netinet6/in6_var.h new file mode 100644 index 000000000000..a1aa13e698d0 --- /dev/null +++ b/sys/netinet6/in6_var.h @@ -0,0 +1,647 @@ +/* + * Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the project nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE PROJECT AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE PROJECT OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +/* + * Copyright (c) 1985, 1986, 1993 + * The Regents of the University of California. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)in_var.h 8.1 (Berkeley) 6/10/93 + * $FreeBSD$ + */ + +#ifndef _NETINET6_IN6_VAR_H_ +#define _NETINET6_IN6_VAR_H_ + +/* + * Interface address, Internet version. One of these structures + * is allocated for each interface with an Internet address. + * The ifaddr structure contains the protocol-independent part + * of the structure and is assumed to be first. + */ + +/* + * pltime/vltime are just for future reference (required to implements 2 + * hour rule for hosts). they should never be modified by nd6_timeout or + * anywhere else. + * userland -> kernel: accept pltime/vltime + * kernel -> userland: throuw up everything + * in kernel: modify preferred/expire only + */ +struct in6_addrlifetime { + time_t ia6t_expire; /* valid lifetime expiration time */ + time_t ia6t_preferred; /* preferred lifetime expiration time */ + u_int32_t ia6t_vltime; /* valid lifetime */ + u_int32_t ia6t_pltime; /* prefix lifetime */ +}; + +struct in6_ifaddr { + struct ifaddr ia_ifa; /* protocol-independent info */ +#define ia_ifp ia_ifa.ifa_ifp +#define ia_flags ia_ifa.ifa_flags + struct sockaddr_in6 ia_addr; /* interface address */ + struct sockaddr_in6 ia_net; /* network number of interface */ + struct sockaddr_in6 ia_dstaddr; /* space for destination addr */ + struct sockaddr_in6 ia_prefixmask; /* prefix mask */ + u_int32_t ia_plen; /* prefix length */ + struct in6_ifaddr *ia_next; /* next in6 list of IP6 addresses */ +#if !(defined(__FreeBSD__) && __FreeBSD__ >= 3) + LIST_HEAD(in6_multihead, in6_multi) ia6_multiaddrs; + /* list of multicast addresses */ +#endif + int ia6_flags; + + struct in6_addrlifetime ia6_lifetime; /* NULL = infty */ + struct ifprefix *ia6_ifpr; /* back pointer to ifprefix */ +}; + +/* + * IPv6 interface statistics, as defined in RFC2465 Ipv6IfStatsEntry (p12). + */ +struct in6_ifstat { + u_int64_t ifs6_in_receive; /* # of total input datagram */ + u_int64_t ifs6_in_hdrerr; /* # of datagrams with invalid hdr */ + u_int64_t ifs6_in_toobig; /* # of datagrams exceeded MTU */ + u_int64_t ifs6_in_noroute; /* # of datagrams with no route */ + u_int64_t ifs6_in_addrerr; /* # of datagrams with invalid dst */ + u_int64_t ifs6_in_protounknown; /* # of datagrams with unknown proto */ + /* NOTE: increment on final dst if */ + u_int64_t ifs6_in_truncated; /* # of truncated datagrams */ + u_int64_t ifs6_in_discard; /* # of discarded datagrams */ + /* NOTE: fragment timeout is not here */ + u_int64_t ifs6_in_deliver; /* # of datagrams delivered to ULP */ + /* NOTE: increment on final dst if */ + u_int64_t ifs6_out_forward; /* # of datagrams forwarded */ + /* NOTE: increment on outgoing if */ + u_int64_t ifs6_out_request; /* # of outgoing datagrams from ULP */ + /* NOTE: does not include forwrads */ + u_int64_t ifs6_out_discard; /* # of discarded datagrams */ + u_int64_t ifs6_out_fragok; /* # of datagrams fragmented */ + u_int64_t ifs6_out_fragfail; /* # of datagrams failed on fragment */ + u_int64_t ifs6_out_fragcreat; /* # of fragment datagrams */ + /* NOTE: this is # after fragment */ + u_int64_t ifs6_reass_reqd; /* # of incoming fragmented packets */ + /* NOTE: increment on final dst if */ + u_int64_t ifs6_reass_ok; /* # of reassembled packets */ + /* NOTE: this is # after reass */ + /* NOTE: increment on final dst if */ + u_int64_t ifs6_reass_fail; /* # of reass failures */ + /* NOTE: may not be packet count */ + /* NOTE: increment on final dst if */ + u_int64_t ifs6_in_mcast; /* # of inbound multicast datagrams */ + u_int64_t ifs6_out_mcast; /* # of outbound multicast datagrams */ +}; + +/* + * ICMPv6 interface statistics, as defined in RFC2466 Ipv6IfIcmpEntry. + * XXX: I'm not sure if this file is the right place for this structure... + */ +struct icmp6_ifstat { + /* + * Input statistics + */ + /* ipv6IfIcmpInMsgs, total # of input messages */ + u_int64_t ifs6_in_msg; + /* ipv6IfIcmpInErrors, # of input error messages */ + u_int64_t ifs6_in_error; + /* ipv6IfIcmpInDestUnreachs, # of input dest unreach errors */ + u_int64_t ifs6_in_dstunreach; + /* ipv6IfIcmpInAdminProhibs, # of input administratively prohibited errs */ + u_int64_t ifs6_in_adminprohib; + /* ipv6IfIcmpInTimeExcds, # of input time exceeded errors */ + u_int64_t ifs6_in_timeexceed; + /* ipv6IfIcmpInParmProblems, # of input parameter problem errors */ + u_int64_t ifs6_in_paramprob; + /* ipv6IfIcmpInPktTooBigs, # of input packet too big errors */ + u_int64_t ifs6_in_pkttoobig; + /* ipv6IfIcmpInEchos, # of input echo requests */ + u_int64_t ifs6_in_echo; + /* ipv6IfIcmpInEchoReplies, # of input echo replies */ + u_int64_t ifs6_in_echoreply; + /* ipv6IfIcmpInRouterSolicits, # of input router solicitations */ + u_int64_t ifs6_in_routersolicit; + /* ipv6IfIcmpInRouterAdvertisements, # of input router advertisements */ + u_int64_t ifs6_in_routeradvert; + /* ipv6IfIcmpInNeighborSolicits, # of input neighbor solicitations */ + u_int64_t ifs6_in_neighborsolicit; + /* ipv6IfIcmpInNeighborAdvertisements, # of input neighbor advertisements */ + u_int64_t ifs6_in_neighboradvert; + /* ipv6IfIcmpInRedirects, # of input redirects */ + u_int64_t ifs6_in_redirect; + /* ipv6IfIcmpInGroupMembQueries, # of input MLD queries */ + u_int64_t ifs6_in_mldquery; + /* ipv6IfIcmpInGroupMembResponses, # of input MLD reports */ + u_int64_t ifs6_in_mldreport; + /* ipv6IfIcmpInGroupMembReductions, # of input MLD done */ + u_int64_t ifs6_in_mlddone; + + /* + * Output statistics. We should solve unresolved routing problem... + */ + /* ipv6IfIcmpOutMsgs, total # of output messages */ + u_int64_t ifs6_out_msg; + /* ipv6IfIcmpOutErrors, # of output error messages */ + u_int64_t ifs6_out_error; + /* ipv6IfIcmpOutDestUnreachs, # of output dest unreach errors */ + u_int64_t ifs6_out_dstunreach; + /* ipv6IfIcmpOutAdminProhibs, # of output administratively prohibited errs */ + u_int64_t ifs6_out_adminprohib; + /* ipv6IfIcmpOutTimeExcds, # of output time exceeded errors */ + u_int64_t ifs6_out_timeexceed; + /* ipv6IfIcmpOutParmProblems, # of output parameter problem errors */ + u_int64_t ifs6_out_paramprob; + /* ipv6IfIcmpOutPktTooBigs, # of output packet too big errors */ + u_int64_t ifs6_out_pkttoobig; + /* ipv6IfIcmpOutEchos, # of output echo requests */ + u_int64_t ifs6_out_echo; + /* ipv6IfIcmpOutEchoReplies, # of output echo replies */ + u_int64_t ifs6_out_echoreply; + /* ipv6IfIcmpOutRouterSolicits, # of output router solicitations */ + u_int64_t ifs6_out_routersolicit; + /* ipv6IfIcmpOutRouterAdvertisements, # of output router advertisements */ + u_int64_t ifs6_out_routeradvert; + /* ipv6IfIcmpOutNeighborSolicits, # of output neighbor solicitations */ + u_int64_t ifs6_out_neighborsolicit; + /* ipv6IfIcmpOutNeighborAdvertisements, # of output neighbor advertisements */ + u_int64_t ifs6_out_neighboradvert; + /* ipv6IfIcmpOutRedirects, # of output redirects */ + u_int64_t ifs6_out_redirect; + /* ipv6IfIcmpOutGroupMembQueries, # of output MLD queries */ + u_int64_t ifs6_out_mldquery; + /* ipv6IfIcmpOutGroupMembResponses, # of output MLD reports */ + u_int64_t ifs6_out_mldreport; + /* ipv6IfIcmpOutGroupMembReductions, # of output MLD done */ + u_int64_t ifs6_out_mlddone; +}; + +struct in6_ifreq { + char ifr_name[IFNAMSIZ]; + union { + struct sockaddr_in6 ifru_addr; + struct sockaddr_in6 ifru_dstaddr; + short ifru_flags; + int ifru_flags6; + int ifru_metric; + caddr_t ifru_data; + struct in6_addrlifetime ifru_lifetime; + struct in6_ifstat ifru_stat; + struct icmp6_ifstat ifru_icmp6stat; + } ifr_ifru; +}; + +struct in6_aliasreq { + char ifra_name[IFNAMSIZ]; + struct sockaddr_in6 ifra_addr; + struct sockaddr_in6 ifra_dstaddr; + struct sockaddr_in6 ifra_prefixmask; + int ifra_flags; + struct in6_addrlifetime ifra_lifetime; +}; + +/* prefix type macro */ +#define IN6_PREFIX_ND 1 +#define IN6_PREFIX_RR 2 + +/* + * prefix related flags passed between kernel(NDP related part) and + * user land command(ifconfig) and daemon(rtadvd). + */ +struct in6_prflags { + struct prf_ra { + u_char onlink : 1; + u_char autonomous : 1; + u_char reserved : 6; + } prf_ra; + u_char prf_reserved1; + u_short prf_reserved2; + /* want to put this on 4byte offset */ + struct prf_rr { + u_char decrvalid : 1; + u_char decrprefd : 1; + u_char reserved : 6; + } prf_rr; + u_char prf_reserved3; + u_short prf_reserved4; +}; + +struct in6_prefixreq { + char ipr_name[IFNAMSIZ]; + u_char ipr_origin; + u_char ipr_plen; + u_int32_t ipr_vltime; + u_int32_t ipr_pltime; + struct in6_prflags ipr_flags; + struct sockaddr_in6 ipr_prefix; +}; + +#define PR_ORIG_RA 0 +#define PR_ORIG_RR 1 +#define PR_ORIG_STATIC 2 +#define PR_ORIG_KERNEL 3 + +#define ipr_raf_onlink ipr_flags.prf_ra.onlink +#define ipr_raf_auto ipr_flags.prf_ra.autonomous + +#define ipr_statef_onlink ipr_flags.prf_state.onlink + +#define ipr_rrf_decrvalid ipr_flags.prf_rr.decrvalid +#define ipr_rrf_decrprefd ipr_flags.prf_rr.decrprefd + +struct in6_rrenumreq { + char irr_name[IFNAMSIZ]; + u_char irr_origin; + u_char irr_m_len; /* match len for matchprefix */ + u_char irr_m_minlen; /* minlen for matching prefix */ + u_char irr_m_maxlen; /* maxlen for matching prefix */ + u_char irr_u_uselen; /* uselen for adding prefix */ + u_char irr_u_keeplen; /* keeplen from matching prefix */ + struct irr_raflagmask { + u_char onlink : 1; + u_char autonomous : 1; + u_char reserved : 6; + } irr_raflagmask; + u_int32_t irr_vltime; + u_int32_t irr_pltime; + struct in6_prflags irr_flags; + struct sockaddr_in6 irr_matchprefix; + struct sockaddr_in6 irr_useprefix; +}; + +#define irr_raf_mask_onlink irr_raflagmask.onlink +#define irr_raf_mask_auto irr_raflagmask.autonomous +#define irr_raf_mask_reserved irr_raflagmask.reserved + +#define irr_raf_onlink irr_flags.prf_ra.onlink +#define irr_raf_auto irr_flags.prf_ra.autonomous + +#define irr_statef_onlink irr_flags.prf_state.onlink + +#define irr_rrf irr_flags.prf_rr +#define irr_rrf_decrvalid irr_flags.prf_rr.decrvalid +#define irr_rrf_decrprefd irr_flags.prf_rr.decrprefd + +/* + * Given a pointer to an in6_ifaddr (ifaddr), + * return a pointer to the addr as a sockaddr_in6 + */ +#define IA6_IN6(ia) (&((ia)->ia_addr.sin6_addr)) +#define IA6_DSTIN6(ia) (&((ia)->ia_dstaddr.sin6_addr)) +#define IA6_MASKIN6(ia) (&((ia)->ia_prefixmask.sin6_addr)) +#define IA6_SIN6(ia) (&((ia)->ia_addr)) +#define IA6_DSTSIN6(ia) (&((ia)->ia_dstaddr)) +#define IFA_IN6(x) (&((struct sockaddr_in6 *)((x)->ifa_addr))->sin6_addr) +#define IFA_DSTIN6(x) (&((struct sockaddr_in6 *)((x)->ifa_dstaddr))->sin6_addr) + +#define IFPR_IN6(x) (&((struct sockaddr_in6 *)((x)->ifpr_prefix))->sin6_addr) + +#ifdef _KERNEL +#define IN6_ARE_MASKED_ADDR_EQUAL(d, a, m) ( \ + (((d)->s6_addr32[0] ^ (a)->s6_addr32[0]) & (m)->s6_addr32[0]) == 0 && \ + (((d)->s6_addr32[1] ^ (a)->s6_addr32[1]) & (m)->s6_addr32[1]) == 0 && \ + (((d)->s6_addr32[2] ^ (a)->s6_addr32[2]) & (m)->s6_addr32[2]) == 0 && \ + (((d)->s6_addr32[3] ^ (a)->s6_addr32[3]) & (m)->s6_addr32[3]) == 0 ) +#endif + +#define SIOCSIFADDR_IN6 _IOW('i', 12, struct in6_ifreq) +#define SIOCGIFADDR_IN6 _IOWR('i', 33, struct in6_ifreq) +#define SIOCSIFDSTADDR_IN6 _IOW('i', 14, struct in6_ifreq) +#define SIOCGIFDSTADDR_IN6 _IOWR('i', 34, struct in6_ifreq) +#define SIOCSIFNETMASK_IN6 _IOW('i', 22, struct in6_ifreq) +#define SIOCGIFNETMASK_IN6 _IOWR('i', 37, struct in6_ifreq) + +#define SIOCDIFADDR_IN6 _IOW('i', 25, struct in6_ifreq) +#define SIOCAIFADDR_IN6 _IOW('i', 26, struct in6_aliasreq) + +#define SIOCSIFPHYADDR_IN6 _IOW('i', 70, struct in6_aliasreq) +#define SIOCGIFPSRCADDR_IN6 _IOWR('i', 71, struct in6_ifreq) +#define SIOCGIFPDSTADDR_IN6 _IOWR('i', 72, struct in6_ifreq) + +#define SIOCGIFAFLAG_IN6 _IOWR('i', 73, struct in6_ifreq) + +#define SIOCGDRLST_IN6 _IOWR('i', 74, struct in6_drlist) +#define SIOCGPRLST_IN6 _IOWR('i', 75, struct in6_prlist) +#define SIOCGIFINFO_IN6 _IOWR('i', 76, struct in6_ndireq) +#define SIOCSNDFLUSH_IN6 _IOWR('i', 77, struct in6_ifreq) +#define SIOCGNBRINFO_IN6 _IOWR('i', 78, struct in6_nbrinfo) +#define SIOCSPFXFLUSH_IN6 _IOWR('i', 79, struct in6_ifreq) +#define SIOCSRTRFLUSH_IN6 _IOWR('i', 80, struct in6_ifreq) + +#define SIOCGIFALIFETIME_IN6 _IOWR('i', 81, struct in6_ifreq) +#define SIOCSIFALIFETIME_IN6 _IOWR('i', 82, struct in6_ifreq) +#define SIOCGIFSTAT_IN6 _IOWR('i', 83, struct in6_ifreq) +#define SIOCGIFSTAT_ICMP6 _IOWR('i', 84, struct in6_ifreq) + +#define SIOCSIFPREFIX_IN6 _IOW('i', 100, struct in6_prefixreq) /* set */ +#define SIOCGIFPREFIX_IN6 _IOWR('i', 101, struct in6_prefixreq) /* get */ +#define SIOCDIFPREFIX_IN6 _IOW('i', 102, struct in6_prefixreq) /* del */ +#define SIOCAIFPREFIX_IN6 _IOW('i', 103, struct in6_rrenumreq) /* add */ +#define SIOCCIFPREFIX_IN6 _IOW('i', 104, \ + struct in6_rrenumreq) /* change */ +#define SIOCSGIFPREFIX_IN6 _IOW('i', 105, \ + struct in6_rrenumreq) /* set global */ + +#define SIOCGETSGCNT_IN6 _IOWR('u', 106, \ + struct sioc_sg_req6) /* get s,g pkt cnt */ +#define SIOCGETMIFCNT_IN6 _IOWR('u', 107, \ + struct sioc_mif_req6) /* get pkt cnt per if */ + +#define IN6_IFF_ANYCAST 0x01 /* anycast address */ +#define IN6_IFF_TENTATIVE 0x02 /* tentative address */ +#define IN6_IFF_DUPLICATED 0x04 /* DAD detected duplicate */ +#define IN6_IFF_DETACHED 0x08 /* may be detached from the link */ +#define IN6_IFF_DEPRECATED 0x10 /* deprecated address */ + +/* do not input/output */ +#define IN6_IFF_NOTREADY (IN6_IFF_TENTATIVE|IN6_IFF_DUPLICATED) + +#ifdef _KERNEL +extern struct in6_ifaddr *in6_ifaddr; + +extern struct in6_ifstat **in6_ifstat; +extern size_t in6_ifstatmax; +extern struct icmp6stat icmp6stat; +extern struct icmp6_ifstat **icmp6_ifstat; +extern size_t icmp6_ifstatmax; +#define in6_ifstat_inc(ifp, tag) \ +do { \ + if ((ifp) && (ifp)->if_index <= if_index \ + && (ifp)->if_index < in6_ifstatmax \ + && in6_ifstat && in6_ifstat[(ifp)->if_index]) { \ + in6_ifstat[(ifp)->if_index]->tag++; \ + } \ +} while (0) + +extern struct ifqueue ip6intrq; /* IP6 packet input queue */ +extern struct in6_addr zeroin6_addr; +extern u_char inet6ctlerrmap[]; +extern u_long in6_maxmtu; +#if defined(__FreeBSD__) && __FreeBSD__ >= 3 +#ifdef MALLOC_DECLARE +MALLOC_DECLARE(M_IPMADDR); +#endif /* MALLOC_DECLARE */ +#endif + +/* + * Macro for finding the internet address structure (in6_ifaddr) corresponding + * to a given interface (ifnet structure). + */ +#if defined(__bsdi__) || (defined(__FreeBSD__) && __FreeBSD__ < 3) + +#define IFP_TO_IA6(ifp, ia) \ +/* struct ifnet *ifp; */ \ +/* struct in6_ifaddr *ia; */ \ +do { \ + struct ifaddr *ifa; \ + for (ifa = (ifp)->if_addrlist; ifa; ifa = ifa->ifa_next) { \ + if (!ifa->ifa_addr) \ + continue; \ + if (ifa->ifa_addr->sa_family == AF_INET6) \ + break; \ + } \ + (ia) = (struct in6_ifaddr *)ifa; \ +} while (0) + +#else + +#define IFP_TO_IA6(ifp, ia) \ +/* struct ifnet *ifp; */ \ +/* struct in6_ifaddr *ia; */ \ +do { \ + struct ifaddr *ifa; \ + for (ifa = (ifp)->if_addrlist.tqh_first; ifa; ifa = ifa->ifa_list.tqe_next) { \ + if (!ifa->ifa_addr) \ + continue; \ + if (ifa->ifa_addr->sa_family == AF_INET6) \ + break; \ + } \ + (ia) = (struct in6_ifaddr *)ifa; \ +} while (0) +#endif /* _KERNEL */ + +#endif + +/* + * Multi-cast membership entry. One for each group/ifp that a PCB + * belongs to. + */ +struct in6_multi_mship { + struct in6_multi *i6mm_maddr; /* Multicast address pointer */ + LIST_ENTRY(in6_multi_mship) i6mm_chain; /* multicast options chain */ +}; + +struct in6_multi { + LIST_ENTRY(in6_multi) in6m_entry; /* list glue */ + struct in6_addr in6m_addr; /* IP6 multicast address */ + struct ifnet *in6m_ifp; /* back pointer to ifnet */ +#if !(defined(__FreeBSD__) && __FreeBSD__ >= 3) + struct in6_ifaddr *in6m_ia; /* back pointer to in6_ifaddr */ +#else + struct ifmultiaddr *in6m_ifma; /* back pointer to ifmultiaddr */ +#endif + u_int in6m_refcount; /* # membership claims by sockets */ + u_int in6m_state; /* state of the membership */ + u_int in6m_timer; /* MLD6 listener report timer */ +}; + +#ifdef _KERNEL +#if defined(__FreeBSD__) && __FreeBSD__ >= 3 +extern LIST_HEAD(in6_multihead, in6_multi) in6_multihead; +#endif + +/* + * Structure used by macros below to remember position when stepping through + * all of eht in6_multi records. + */ +struct in6_multistep { + struct in6_ifaddr *i_ia; + struct in6_multi *i_in6m; +}; + +/* + * Macros for looking up the in6_multi record for a given IP6 multicast + * address on a given interface. If no matching record is found, "in6m" + * returns NLL. + */ + +#if defined(__FreeBSD__) && __FreeBSD__ >= 3 + +#define IN6_LOOKUP_MULTI(addr, ifp, in6m) \ +/* struct in6_addr addr; */ \ +/* struct ifnet *ifp; */ \ +/* struct in6_multi *in6m; */ \ +do { \ + register struct ifmultiaddr *ifma; \ + for (ifma = (ifp)->if_multiaddrs.lh_first; ifma; \ + ifma = ifma->ifma_link.le_next) { \ + if (ifma->ifma_addr->sa_family == AF_INET6 \ + && IN6_ARE_ADDR_EQUAL(&((struct sockaddr_in6 *)ifma->ifma_addr)->sin6_addr, \ + &(addr))) \ + break; \ + } \ + (in6m) = (struct in6_multi *)(ifma ? ifma->ifma_protospec : 0); \ +} while(0) + +/* + * Macro to step through all of the in6_multi records, one at a time. + * The current position is remembered in "step", which the caller must + * provide. IN6_FIRST_MULTI(), below, must be called to initialize "step" + * and get the first record. Both macros return a NULL "in6m" when there + * are no remaining records. + */ +#define IN6_NEXT_MULTI(step, in6m) \ +/* struct in6_multistep step; */ \ +/* struct in6_multi *in6m; */ \ +do { \ + if (((in6m) = (step).i_in6m) != NULL) \ + (step).i_in6m = (step).i_in6m->in6m_entry.le_next; \ +} while(0) + +#define IN6_FIRST_MULTI(step, in6m) \ +/* struct in6_multistep step; */ \ +/* struct in6_multi *in6m */ \ +do { \ + (step).i_in6m = in6_multihead.lh_first; \ + IN6_NEXT_MULTI((step), (in6m)); \ +} while(0) + +#else /* not FreeBSD3 */ + +#define IN6_LOOKUP_MULTI(addr, ifp, in6m) \ +/* struct in6_addr addr; */ \ +/* struct ifnet *ifp; */ \ +/* struct in6_multi *in6m; */ \ +do { \ + register struct in6_ifaddr *ia; \ + \ + IFP_TO_IA6((ifp), ia); \ + if (ia == NULL) \ + (in6m) = NULL; \ + else \ + for ((in6m) = ia->ia6_multiaddrs.lh_first; \ + (in6m) != NULL && \ + !IN6_ARE_ADDR_EQUAL(&(in6m)->in6m_addr, &(addr)); \ + (in6m) = in6m->in6m_entry.le_next) \ + continue; \ +} while (0) + +/* + * Macro to step through all of the in6_multi records, one at a time. + * The current position is remembered in "step", which the caller must + * provide. IN6_FIRST_MULTI(), below, must be called to initialize "step" + * and get the first record. Both macros return a NULL "in6m" when there + * are no remaining records. + */ +#define IN6_NEXT_MULTI(step, in6m) \ +/* struct in6_multistep step; */ \ +/* struct in6_multi *in6m; */ \ +do { \ + if (((in6m) = (step).i_in6m) != NULL) \ + (step).i_in6m = (in6m)->in6m_entry.le_next; \ + else \ + while ((step).i_ia != NULL) { \ + (in6m) = (step).i_ia->ia6_multiaddrs.lh_first; \ + (step).i_ia = (step).i_ia->ia_next; \ + if ((in6m) != NULL) { \ + (step).i_in6m = (in6m)->in6m_entry.le_next; \ + break; \ + } \ + } \ +} while (0) + +#define IN6_FIRST_MULTI(step, in6m) \ +/* struct in6_multistep step; */ \ +/* struct in6_multi *in6m */ \ +do { \ + (step).i_ia = in6_ifaddr; \ + (step).i_in6m = NULL; \ + IN6_NEXT_MULTI((step), (in6m)); \ +} while (0) + +#endif /* not FreeBSD3 */ + +int in6_ifinit __P((struct ifnet *, + struct in6_ifaddr *, struct sockaddr_in6 *, int)); +struct in6_multi *in6_addmulti __P((struct in6_addr *, struct ifnet *, + int *)); +void in6_delmulti __P((struct in6_multi *)); +void in6_ifscrub __P((struct ifnet *, struct in6_ifaddr *)); +extern int in6_ifindex2scopeid __P((int)); +extern int in6_mask2len __P((struct in6_addr *)); +extern void in6_len2mask __P((struct in6_addr *, int)); +#if !defined(__bsdi__) && !(defined(__FreeBSD__) && __FreeBSD__ < 3) +int in6_control __P((struct socket *, + u_long, caddr_t, struct ifnet *, struct proc *)); +#else +int in6_control __P((struct socket *, u_long, caddr_t, struct ifnet *)); +#endif +void in6_savemkludge __P((struct in6_ifaddr *)); +void in6_setmaxmtu __P((void)); +void in6_restoremkludge __P((struct in6_ifaddr *, struct ifnet *)); +struct in6_ifaddr *in6ifa_ifpforlinklocal __P((struct ifnet *)); +struct in6_ifaddr *in6ifa_ifpwithaddr __P((struct ifnet *, + struct in6_addr *)); +char *ip6_sprintf __P((struct in6_addr *)); +int in6_matchlen __P((struct in6_addr *, struct in6_addr *)); +int in6_are_prefix_equal __P((struct in6_addr *p1, struct in6_addr *p2, + int len)); +void in6_prefixlen2mask __P((struct in6_addr *maskp, int len)); +int in6_prefix_ioctl __P((struct socket *so, u_long cmd, caddr_t data, + struct ifnet *ifp)); +int in6_prefix_add_ifid __P((int iilen, struct in6_ifaddr *ia)); +void in6_prefix_remove_ifid __P((int iilen, struct in6_ifaddr *ia)); +#endif /* _KERNEL */ + +#endif /* _NETINET6_IN6_VAR_H_ */ diff --git a/sys/sys/malloc.h b/sys/sys/malloc.h index 99eb85cbfe1d..f0e62ec15969 100644 --- a/sys/sys/malloc.h +++ b/sys/sys/malloc.h @@ -1,216 +1,219 @@ /* * Copyright (c) 1987, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)malloc.h 8.5 (Berkeley) 5/3/95 * $FreeBSD$ */ #ifndef _SYS_MALLOC_H_ #define _SYS_MALLOC_H_ #define splmem splhigh #define KMEMSTATS /* * flags to malloc. */ #define M_WAITOK 0x0000 #define M_NOWAIT 0x0001 /* do not block */ #define M_USE_RESERVE 0x0002 /* can alloc out of reserve memory */ #define M_ASLEEP 0x0004 /* async sleep on failure */ #define M_MAGIC 877983977 /* time when first defined :-) */ struct malloc_type { struct malloc_type *ks_next; /* next in list */ long ks_memuse; /* total memory held in bytes */ long ks_limit; /* most that are allowed to exist */ long ks_size; /* sizes of this thing that are allocated */ long ks_inuse; /* # of packets of this type currently in use */ int64_t ks_calls; /* total packets of this type ever allocated */ long ks_maxused; /* maximum number ever used */ u_long ks_magic; /* if it's not magic, don't touch it */ const char *ks_shortdesc; /* short description */ u_short ks_limblocks; /* number of times blocked for hitting limit */ u_short ks_mapblocks; /* number of times blocked for kernel map */ }; #ifdef KERNEL #define MALLOC_DEFINE(type, shortdesc, longdesc) \ struct malloc_type type[1] = { \ { NULL, 0, 0, 0, 0, 0, 0, M_MAGIC, shortdesc, 0, 0 } \ }; \ SYSINIT(type##_init, SI_SUB_KMEM, SI_ORDER_ANY, malloc_init, type); \ SYSUNINIT(type##_uninit, SI_SUB_KMEM, SI_ORDER_ANY, malloc_uninit, type) #define MALLOC_DECLARE(type) \ extern struct malloc_type type[1] MALLOC_DECLARE(M_CACHE); MALLOC_DECLARE(M_DEVBUF); MALLOC_DECLARE(M_TEMP); + +MALLOC_DECLARE(M_IP6OPT); /* for INET6 */ +MALLOC_DECLARE(M_IP6NDP); /* for INET6 */ #endif /* KERNEL */ /* * Array of descriptors that describe the contents of each page */ struct kmemusage { short ku_indx; /* bucket index */ union { u_short freecnt;/* for small allocations, free pieces in page */ u_short pagecnt;/* for large allocations, pages alloced */ } ku_un; }; #define ku_freecnt ku_un.freecnt #define ku_pagecnt ku_un.pagecnt /* * Set of buckets for each size of memory block that is retained */ struct kmembuckets { caddr_t kb_next; /* list of free blocks */ caddr_t kb_last; /* last free block */ int64_t kb_calls; /* total calls to allocate this size */ long kb_total; /* total number of blocks allocated */ long kb_elmpercl; /* # of elements in this sized allocation */ long kb_totalfree; /* # of free elements in this bucket */ long kb_highwat; /* high water mark */ long kb_couldfree; /* over high water mark and could free */ }; #ifdef KERNEL #define MINALLOCSIZE (1 << MINBUCKET) #define BUCKETINDX(size) \ ((size) <= (MINALLOCSIZE * 128) \ ? (size) <= (MINALLOCSIZE * 8) \ ? (size) <= (MINALLOCSIZE * 2) \ ? (size) <= (MINALLOCSIZE * 1) \ ? (MINBUCKET + 0) \ : (MINBUCKET + 1) \ : (size) <= (MINALLOCSIZE * 4) \ ? (MINBUCKET + 2) \ : (MINBUCKET + 3) \ : (size) <= (MINALLOCSIZE* 32) \ ? (size) <= (MINALLOCSIZE * 16) \ ? (MINBUCKET + 4) \ : (MINBUCKET + 5) \ : (size) <= (MINALLOCSIZE * 64) \ ? (MINBUCKET + 6) \ : (MINBUCKET + 7) \ : (size) <= (MINALLOCSIZE * 2048) \ ? (size) <= (MINALLOCSIZE * 512) \ ? (size) <= (MINALLOCSIZE * 256) \ ? (MINBUCKET + 8) \ : (MINBUCKET + 9) \ : (size) <= (MINALLOCSIZE * 1024) \ ? (MINBUCKET + 10) \ : (MINBUCKET + 11) \ : (size) <= (MINALLOCSIZE * 8192) \ ? (size) <= (MINALLOCSIZE * 4096) \ ? (MINBUCKET + 12) \ : (MINBUCKET + 13) \ : (size) <= (MINALLOCSIZE * 16384) \ ? (MINBUCKET + 14) \ : (MINBUCKET + 15)) /* * Turn virtual addresses into kmem map indices */ #define kmemxtob(alloc) (kmembase + (alloc) * PAGE_SIZE) #define btokmemx(addr) (((caddr_t)(addr) - kmembase) / PAGE_SIZE) #define btokup(addr) (&kmemusage[((caddr_t)(addr) - kmembase) >> PAGE_SHIFT]) /* * Macro versions for the usual cases of malloc/free */ #if defined(KMEMSTATS) || defined(DIAGNOSTIC) #define MALLOC(space, cast, size, type, flags) \ (space) = (cast)malloc((u_long)(size), type, flags) #define FREE(addr, type) free((addr), type) #else /* do not collect statistics */ #define MALLOC(space, cast, size, type, flags) do { \ register struct kmembuckets *kbp = &bucket[BUCKETINDX(size)]; \ long s = splmem(); \ if (kbp->kb_next == NULL) { \ (space) = (cast)malloc((u_long)(size), type, flags); \ } else { \ (space) = (cast)kbp->kb_next; \ kbp->kb_next = *(caddr_t *)(space); \ } \ splx(s); \ } while (0) #define FREE(addr, type) do { \ register struct kmembuckets *kbp; \ register struct kmemusage *kup = btokup(addr); \ long s = splmem(); \ if (1 << kup->ku_indx > MAXALLOCSAVE) { \ free((addr), type); \ } else { \ kbp = &bucket[kup->ku_indx]; \ if (kbp->kb_next == NULL) \ kbp->kb_next = (caddr_t)(addr); \ else \ *(caddr_t *)(kbp->kb_last) = (caddr_t)(addr); \ *(caddr_t *)(addr) = NULL; \ kbp->kb_last = (caddr_t)(addr); \ } \ splx(s); \ } while (0) extern struct kmemusage *kmemusage; extern char *kmembase; extern struct kmembuckets bucket[]; #endif /* do not collect statistics */ /* * XXX this should be declared in , but that tends to fail * because is included in a header before the source file * has a chance to include to get MALLOC_DECLARE() defined. */ MALLOC_DECLARE(M_IOV); /* XXX struct malloc_type is unused for contig*(). */ void contigfree __P((void *addr, unsigned long size, struct malloc_type *type)); void *contigmalloc __P((unsigned long size, struct malloc_type *type, int flags, unsigned long low, unsigned long high, unsigned long alignment, unsigned long boundary)); void free __P((void *addr, struct malloc_type *type)); void *malloc __P((unsigned long size, struct malloc_type *type, int flags)); void malloc_init __P((void *)); void malloc_uninit __P((void *)); #endif /* KERNEL */ #endif /* !_SYS_MALLOC_H_ */ diff --git a/sys/sys/mbuf.h b/sys/sys/mbuf.h index cce10ad3dd6e..5c6a58d71d41 100644 --- a/sys/sys/mbuf.h +++ b/sys/sys/mbuf.h @@ -1,435 +1,439 @@ /* * Copyright (c) 1982, 1986, 1988, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)mbuf.h 8.5 (Berkeley) 2/19/95 * $FreeBSD$ */ #ifndef _SYS_MBUF_H_ #define _SYS_MBUF_H_ /* * Mbufs are of a single size, MSIZE (machine/machparam.h), which * includes overhead. An mbuf may add a single "mbuf cluster" of size * MCLBYTES (also in machine/machparam.h), which has no additional overhead * and is used instead of the internal data area; this is done when * at least MINCLSIZE of data must be stored. */ #define MLEN (MSIZE - sizeof(struct m_hdr)) /* normal data len */ #define MHLEN (MLEN - sizeof(struct pkthdr)) /* data len w/pkthdr */ -#define MINCLSIZE (MHLEN + MLEN) /* smallest amount to put in cluster */ +#define MINCLSIZE (MHLEN + 1) /* smallest amount to put in cluster */ #define M_MAXCOMPRESS (MHLEN / 2) /* max amount to copy for compression */ /* * Macros for type conversion * mtod(m,t) - convert mbuf pointer to data pointer of correct type * dtom(x) - convert data pointer within mbuf to mbuf pointer (XXX) * mtocl(x) - convert pointer within cluster to cluster index # * cltom(x) - convert cluster # to ptr to beginning of cluster */ #define mtod(m,t) ((t)((m)->m_data)) #define dtom(x) ((struct mbuf *)((intptr_t)(x) & ~(MSIZE-1))) #define mtocl(x) (((uintptr_t)(x) - (uintptr_t)mbutl) >> MCLSHIFT) #define cltom(x) ((caddr_t)((uintptr_t)mbutl + \ ((uintptr_t)(x) << MCLSHIFT))) /* header at beginning of each mbuf: */ struct m_hdr { struct mbuf *mh_next; /* next buffer in chain */ struct mbuf *mh_nextpkt; /* next chain in queue/record */ caddr_t mh_data; /* location of data */ int mh_len; /* amount of data in this mbuf */ short mh_type; /* type of data in this mbuf */ short mh_flags; /* flags; see below */ }; /* record/packet header in first mbuf of chain; valid if M_PKTHDR set */ struct pkthdr { struct ifnet *rcvif; /* rcv interface */ int len; /* total packet length */ /* variables for ip and tcp reassembly */ void *header; /* pointer to packet header */ }; /* description of external storage mapped into mbuf, valid if M_EXT set */ struct m_ext { caddr_t ext_buf; /* start of buffer */ void (*ext_free) /* free routine if not the usual */ __P((caddr_t, u_int)); u_int ext_size; /* size of buffer, for ext_free */ void (*ext_ref) /* add a reference to the ext object */ __P((caddr_t, u_int)); }; struct mbuf { struct m_hdr m_hdr; union { struct { struct pkthdr MH_pkthdr; /* M_PKTHDR set */ union { struct m_ext MH_ext; /* M_EXT set */ char MH_databuf[MHLEN]; } MH_dat; } MH; char M_databuf[MLEN]; /* !M_PKTHDR, !M_EXT */ } M_dat; }; #define m_next m_hdr.mh_next #define m_len m_hdr.mh_len #define m_data m_hdr.mh_data #define m_type m_hdr.mh_type #define m_flags m_hdr.mh_flags #define m_nextpkt m_hdr.mh_nextpkt #define m_act m_nextpkt #define m_pkthdr M_dat.MH.MH_pkthdr #define m_ext M_dat.MH.MH_dat.MH_ext #define m_pktdat M_dat.MH.MH_dat.MH_databuf #define m_dat M_dat.M_databuf /* mbuf flags */ #define M_EXT 0x0001 /* has associated external storage */ #define M_PKTHDR 0x0002 /* start of record */ #define M_EOR 0x0004 /* end of record */ #define M_PROTO1 0x0008 /* protocol-specific */ +#define M_PROTO2 0x0010 /* protocol-specific */ +#define M_PROTO3 0x0020 /* protocol-specific */ +#define M_PROTO4 0x0040 /* protocol-specific */ +#define M_PROTO5 0x0080 /* protocol-specific */ /* mbuf pkthdr flags, also in m_flags */ #define M_BCAST 0x0100 /* send/received as link-level broadcast */ #define M_MCAST 0x0200 /* send/received as link-level multicast */ -#define M_FRAG 0x0400 /* packet is a fragment of a larger packet */ +#define M_FRAG 0x0400 /* packet is a fragment of a larger packet */ /* flags copied when copying m_pkthdr */ -#define M_COPYFLAGS (M_PKTHDR|M_EOR|M_PROTO1|M_BCAST|M_MCAST) +#define M_COPYFLAGS (M_PKTHDR|M_EOR|M_PROTO1|M_PROTO1|M_PROTO2|M_PROTO3|M_PROTO4|M_PROTO5|M_BCAST|M_MCAST|M_FRAG) /* mbuf types */ #define MT_FREE 0 /* should be on free list */ #define MT_DATA 1 /* dynamic (data) allocation */ #define MT_HEADER 2 /* packet header */ /*efine MT_SOCKET 3*/ /* socket structure */ /*efine MT_PCB 4*/ /* protocol control block */ /*efine MT_RTABLE 5*/ /* routing tables */ /*efine MT_HTABLE 6*/ /* IMP host tables */ /*efine MT_ATABLE 7*/ /* address resolution tables */ #define MT_SONAME 8 /* socket name */ /*efine MT_SOOPTS 10*/ /* socket options */ #define MT_FTABLE 11 /* fragment reassembly header */ /*efine MT_RIGHTS 12*/ /* access rights */ /*efine MT_IFADDR 13*/ /* interface address */ #define MT_CONTROL 14 /* extra-data protocol message */ #define MT_OOBDATA 15 /* expedited data */ /* flags to m_get/MGET */ #define M_DONTWAIT 1 #define M_WAIT 0 /* Freelists: * * Normal mbuf clusters are normally treated as character arrays * after allocation, but use the first word of the buffer as a free list * pointer while on the free list. */ union mcluster { union mcluster *mcl_next; char mcl_buf[MCLBYTES]; }; /* * mbuf utility macros: * * MBUFLOCK(code) * prevents a section of code from from being interrupted by network * drivers. */ #define MBUFLOCK(code) \ do { int ms = splimp(); \ { code } \ splx(ms); \ } while(0) /* * mbuf allocation/deallocation macros: * * MGET(struct mbuf *m, int how, int type) * allocates an mbuf and initializes it to contain internal data. * * MGETHDR(struct mbuf *m, int how, int type) * allocates an mbuf and initializes it to contain a packet header * and internal data. */ #define MGET(m, how, type) { \ int _ms = splimp(); \ if (mmbfree == 0) \ (void)m_mballoc(1, (how)); \ if (((m) = mmbfree) != 0) { \ mmbfree = (m)->m_next; \ mbstat.m_mtypes[MT_FREE]--; \ (m)->m_type = (type); \ mbstat.m_mtypes[type]++; \ (m)->m_next = (struct mbuf *)NULL; \ (m)->m_nextpkt = (struct mbuf *)NULL; \ (m)->m_data = (m)->m_dat; \ (m)->m_flags = 0; \ splx(_ms); \ } else { \ splx(_ms); \ (m) = m_retry((how), (type)); \ } \ } #define MGETHDR(m, how, type) { \ int _ms = splimp(); \ if (mmbfree == 0) \ (void)m_mballoc(1, (how)); \ if (((m) = mmbfree) != 0) { \ mmbfree = (m)->m_next; \ mbstat.m_mtypes[MT_FREE]--; \ (m)->m_type = (type); \ mbstat.m_mtypes[type]++; \ (m)->m_next = (struct mbuf *)NULL; \ (m)->m_nextpkt = (struct mbuf *)NULL; \ (m)->m_data = (m)->m_pktdat; \ (m)->m_flags = M_PKTHDR; \ splx(_ms); \ } else { \ splx(_ms); \ (m) = m_retryhdr((how), (type)); \ } \ } /* * Mbuf cluster macros. * MCLALLOC(caddr_t p, int how) allocates an mbuf cluster. * MCLGET adds such clusters to a normal mbuf; * the flag M_EXT is set upon success. * MCLFREE releases a reference to a cluster allocated by MCLALLOC, * freeing the cluster if the reference count has reached 0. */ #define MCLALLOC(p, how) \ MBUFLOCK( \ if (mclfree == 0) \ (void)m_clalloc(1, (how)); \ if (((p) = (caddr_t)mclfree) != 0) { \ ++mclrefcnt[mtocl(p)]; \ mbstat.m_clfree--; \ mclfree = ((union mcluster *)(p))->mcl_next; \ } \ ) #define MCLGET(m, how) \ { MCLALLOC((m)->m_ext.ext_buf, (how)); \ if ((m)->m_ext.ext_buf != NULL) { \ (m)->m_data = (m)->m_ext.ext_buf; \ (m)->m_flags |= M_EXT; \ (m)->m_ext.ext_free = NULL; \ (m)->m_ext.ext_ref = NULL; \ (m)->m_ext.ext_size = MCLBYTES; \ } \ } #define MCLFREE1(p) \ do { \ if (--mclrefcnt[mtocl(p)] == 0) { \ ((union mcluster *)(p))->mcl_next = mclfree; \ mclfree = (union mcluster *)(p); \ mbstat.m_clfree++; \ } \ } while (0) #define MCLFREE(p) \ MBUFLOCK( \ MCLFREE1(p); \ ) #define MEXTFREE1(m) \ do { \ if ((m)->m_ext.ext_free) \ (*((m)->m_ext.ext_free))((m)->m_ext.ext_buf, \ (m)->m_ext.ext_size); \ else { \ char *p = (m)->m_ext.ext_buf; \ MCLFREE1(p); \ } \ } while (0) #define MEXTFREE(m) \ MBUFLOCK( \ MCLEXTFREE1(m); \ ) /* * MFREE(struct mbuf *m, struct mbuf *n) * Free a single mbuf and associated external storage. * Place the successor, if any, in n. */ #define MFREE(m, n) \ MBUFLOCK( \ mbstat.m_mtypes[(m)->m_type]--; \ if ((m)->m_flags & M_EXT) { \ MEXTFREE1(m); \ } \ (n) = (m)->m_next; \ (m)->m_type = MT_FREE; \ mbstat.m_mtypes[MT_FREE]++; \ (m)->m_next = mmbfree; \ mmbfree = (m); \ ) /* * Copy mbuf pkthdr from from to to. * from must have M_PKTHDR set, and to must be empty. */ #define M_COPY_PKTHDR(to, from) { \ (to)->m_pkthdr = (from)->m_pkthdr; \ (to)->m_flags = (from)->m_flags & M_COPYFLAGS; \ (to)->m_data = (to)->m_pktdat; \ } /* * Set the m_data pointer of a newly-allocated mbuf (m_get/MGET) to place * an object of the specified size at the end of the mbuf, longword aligned. */ #define M_ALIGN(m, len) \ { (m)->m_data += (MLEN - (len)) &~ (sizeof(long) - 1); } /* * As above, for mbufs allocated with m_gethdr/MGETHDR * or initialized by M_COPY_PKTHDR. */ #define MH_ALIGN(m, len) \ { (m)->m_data += (MHLEN - (len)) &~ (sizeof(long) - 1); } /* * Compute the amount of space available * before the current start of data in an mbuf. */ #define M_LEADINGSPACE(m) \ ((m)->m_flags & M_EXT ? /* (m)->m_data - (m)->m_ext.ext_buf */ 0 : \ (m)->m_flags & M_PKTHDR ? (m)->m_data - (m)->m_pktdat : \ (m)->m_data - (m)->m_dat) /* * Compute the amount of space available * after the end of data in an mbuf. */ #define M_TRAILINGSPACE(m) \ ((m)->m_flags & M_EXT ? (m)->m_ext.ext_buf + (m)->m_ext.ext_size - \ ((m)->m_data + (m)->m_len) : \ &(m)->m_dat[MLEN] - ((m)->m_data + (m)->m_len)) /* * Arrange to prepend space of size plen to mbuf m. * If a new mbuf must be allocated, how specifies whether to wait. * If how is M_DONTWAIT and allocation fails, the original mbuf chain * is freed and m is set to NULL. */ #define M_PREPEND(m, plen, how) { \ if (M_LEADINGSPACE(m) >= (plen)) { \ (m)->m_data -= (plen); \ (m)->m_len += (plen); \ } else \ (m) = m_prepend((m), (plen), (how)); \ if ((m) && (m)->m_flags & M_PKTHDR) \ (m)->m_pkthdr.len += (plen); \ } /* change mbuf to new type */ #define MCHTYPE(m, t) do { \ MBUFLOCK(mbstat.m_mtypes[(m)->m_type]--; mbstat.m_mtypes[t]++;); \ (m)->m_type = t;\ } while(0) /* length to m_copy to copy all */ #define M_COPYALL 1000000000 /* compatibility with 4.3 */ #define m_copy(m, o, l) m_copym((m), (o), (l), M_DONTWAIT) /* * Mbuf statistics. */ struct mbstat { u_long m_mbufs; /* mbufs obtained from page pool */ u_long m_clusters; /* clusters obtained from page pool */ u_long m_spare; /* spare field */ u_long m_clfree; /* free clusters */ u_long m_drops; /* times failed to find space */ u_long m_wait; /* times waited for space */ u_long m_drain; /* times drained protocols for space */ u_short m_mtypes[256]; /* type specific mbuf allocations */ u_long m_mcfail; /* times m_copym failed */ u_long m_mpfail; /* times m_pullup failed */ u_long m_msize; /* length of an mbuf */ u_long m_mclbytes; /* length of an mbuf cluster */ u_long m_minclsize; /* min length of data to allocate a cluster */ u_long m_mlen; /* length of data in an mbuf */ u_long m_mhlen; /* length of data in a header mbuf */ }; #ifdef KERNEL extern struct mbuf *mbutl; /* virtual address of mclusters */ extern char *mclrefcnt; /* cluster reference counts */ extern struct mbstat mbstat; extern int nmbclusters; extern int nmbufs; extern int nsfbufs; extern struct mbuf *mmbfree; extern union mcluster *mclfree; extern int max_linkhdr; /* largest link-level header */ extern int max_protohdr; /* largest protocol header */ extern int max_hdr; /* largest link+protocol header */ extern int max_datalen; /* MHLEN - max_hdr */ struct mbuf *m_copym __P((struct mbuf *, int, int, int)); struct mbuf *m_copypacket __P((struct mbuf *, int)); struct mbuf *m_devget __P((char *, int, int, struct ifnet *, void (*copy)(char *, caddr_t, u_int))); struct mbuf *m_free __P((struct mbuf *)); struct mbuf *m_get __P((int, int)); struct mbuf *m_getclr __P((int, int)); struct mbuf *m_gethdr __P((int, int)); struct mbuf *m_prepend __P((struct mbuf *,int,int)); void m_print __P((const struct mbuf *m)); struct mbuf *m_pullup __P((struct mbuf *, int)); struct mbuf *m_retry __P((int, int)); struct mbuf *m_retryhdr __P((int, int)); struct mbuf *m_split __P((struct mbuf *,int,int)); void m_adj __P((struct mbuf *, int)); void m_cat __P((struct mbuf *,struct mbuf *)); int m_mballoc __P((int, int)); int m_clalloc __P((int, int)); void m_copyback __P((struct mbuf *, int, int, caddr_t)); void m_copydata __P((struct mbuf *,int,int,caddr_t)); void m_freem __P((struct mbuf *)); #endif /* KERNEL */ #endif /* !_SYS_MBUF_H_ */ diff --git a/sys/sys/socket.h b/sys/sys/socket.h index b83466758f0a..febf2f8a0e9b 100644 --- a/sys/sys/socket.h +++ b/sys/sys/socket.h @@ -1,412 +1,442 @@ /* * Copyright (c) 1982, 1985, 1986, 1988, 1993, 1994 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)socket.h 8.4 (Berkeley) 2/21/94 * $FreeBSD$ */ #ifndef _SYS_SOCKET_H_ #define _SYS_SOCKET_H_ /* * Definitions related to sockets: types, address families, options. */ /* * Types */ #define SOCK_STREAM 1 /* stream socket */ #define SOCK_DGRAM 2 /* datagram socket */ #define SOCK_RAW 3 /* raw-protocol interface */ #define SOCK_RDM 4 /* reliably-delivered message */ #define SOCK_SEQPACKET 5 /* sequenced packet stream */ /* * Option flags per-socket. */ #define SO_DEBUG 0x0001 /* turn on debugging info recording */ #define SO_ACCEPTCONN 0x0002 /* socket has had listen() */ #define SO_REUSEADDR 0x0004 /* allow local address reuse */ #define SO_KEEPALIVE 0x0008 /* keep connections alive */ #define SO_DONTROUTE 0x0010 /* just use interface addresses */ #define SO_BROADCAST 0x0020 /* permit sending of broadcast msgs */ #define SO_USELOOPBACK 0x0040 /* bypass hardware when possible */ #define SO_LINGER 0x0080 /* linger on close if data present */ #define SO_OOBINLINE 0x0100 /* leave received OOB data in line */ #define SO_REUSEPORT 0x0200 /* allow local address & port reuse */ #define SO_TIMESTAMP 0x0400 /* timestamp received dgram traffic */ /* * Additional options, not kept in so_options. */ #define SO_SNDBUF 0x1001 /* send buffer size */ #define SO_RCVBUF 0x1002 /* receive buffer size */ #define SO_SNDLOWAT 0x1003 /* send low-water mark */ #define SO_RCVLOWAT 0x1004 /* receive low-water mark */ #define SO_SNDTIMEO 0x1005 /* send timeout */ #define SO_RCVTIMEO 0x1006 /* receive timeout */ #define SO_ERROR 0x1007 /* get error status and clear */ #define SO_TYPE 0x1008 /* get socket type */ /*efine SO_PRIVSTATE 0x1009 get/deny privileged state */ /* * Structure used for manipulating linger option. */ struct linger { int l_onoff; /* option on/off */ int l_linger; /* linger time */ }; /* * Level number for (get/set)sockopt() to apply to socket itself. */ #define SOL_SOCKET 0xffff /* options for socket level */ /* * Address families. */ #define AF_UNSPEC 0 /* unspecified */ #define AF_LOCAL 1 /* local to host (pipes, portals) */ #define AF_UNIX AF_LOCAL /* backward compatibility */ #define AF_INET 2 /* internetwork: UDP, TCP, etc. */ #define AF_IMPLINK 3 /* arpanet imp addresses */ #define AF_PUP 4 /* pup protocols: e.g. BSP */ #define AF_CHAOS 5 /* mit CHAOS protocols */ #define AF_NS 6 /* XEROX NS protocols */ #define AF_ISO 7 /* ISO protocols */ #define AF_OSI AF_ISO #define AF_ECMA 8 /* European computer manufacturers */ #define AF_DATAKIT 9 /* datakit protocols */ #define AF_CCITT 10 /* CCITT protocols, X.25 etc */ #define AF_SNA 11 /* IBM SNA */ #define AF_DECnet 12 /* DECnet */ #define AF_DLI 13 /* DEC Direct data link interface */ #define AF_LAT 14 /* LAT */ #define AF_HYLINK 15 /* NSC Hyperchannel */ #define AF_APPLETALK 16 /* Apple Talk */ #define AF_ROUTE 17 /* Internal Routing Protocol */ #define AF_LINK 18 /* Link layer interface */ #define pseudo_AF_XTP 19 /* eXpress Transfer Protocol (no AF) */ #define AF_COIP 20 /* connection-oriented IP, aka ST II */ #define AF_CNT 21 /* Computer Network Technology */ #define pseudo_AF_RTIP 22 /* Help Identify RTIP packets */ #define AF_IPX 23 /* Novell Internet Protocol */ #define AF_SIP 24 /* Simple Internet Protocol */ #define pseudo_AF_PIP 25 /* Help Identify PIP packets */ #define AF_ISDN 26 /* Integrated Services Digital Network*/ #define AF_E164 AF_ISDN /* CCITT E.164 recommendation */ #define pseudo_AF_KEY 27 /* Internal key-management function */ #define AF_INET6 28 /* IPv6 */ #define AF_NATM 29 /* native ATM access */ #define AF_ATM 30 /* ATM */ #define pseudo_AF_HDRCMPLT 31 /* Used by BPF to not rewrite headers * in interface output routine */ #define AF_NETGRAPH 32 /* Netgraph sockets */ #define AF_MAX 33 /* * Structure used by kernel to store most * addresses. */ struct sockaddr { u_char sa_len; /* total length */ u_char sa_family; /* address family */ char sa_data[14]; /* actually longer; address value */ }; #define SOCK_MAXADDRLEN 255 /* longest possible addresses */ /* * Structure used by kernel to pass protocol * information in raw sockets. */ struct sockproto { u_short sp_family; /* address family */ u_short sp_protocol; /* protocol */ }; +/* + * bsd-api-new-02a: protocol-independent placeholder for socket addresses + */ +#define _SS_MAXSIZE 128 +#define _SS_ALIGNSIZE (sizeof(int64_t)) +#define _SS_PAD1SIZE (_SS_ALIGNSIZE - sizeof(u_char) * 2) +#define _SS_PAD2SIZE (_SS_MAXSIZE - sizeof(u_char) * 2 - \ + _SS_PAD1SIZE - _SS_ALIGNSIZE) + +struct sockaddr_storage { + u_char __ss_len; /* address length */ + u_char __ss_family; /* address family */ + char __ss_pad1[_SS_PAD1SIZE]; + int64_t __ss_align; /* force desired structure storage alignment */ + char __ss_pad2[_SS_PAD2SIZE]; +}; + /* * Protocol families, same as address families for now. */ #define PF_UNSPEC AF_UNSPEC #define PF_LOCAL AF_LOCAL #define PF_UNIX PF_LOCAL /* backward compatibility */ #define PF_INET AF_INET +#define PF_INET6 AF_INET6 #define PF_IMPLINK AF_IMPLINK #define PF_PUP AF_PUP #define PF_CHAOS AF_CHAOS #define PF_NS AF_NS #define PF_ISO AF_ISO #define PF_OSI AF_ISO #define PF_ECMA AF_ECMA #define PF_DATAKIT AF_DATAKIT #define PF_CCITT AF_CCITT #define PF_SNA AF_SNA #define PF_DECnet AF_DECnet #define PF_DLI AF_DLI #define PF_LAT AF_LAT #define PF_HYLINK AF_HYLINK #define PF_APPLETALK AF_APPLETALK #define PF_ROUTE AF_ROUTE #define PF_LINK AF_LINK #define PF_XTP pseudo_AF_XTP /* really just proto family, no AF */ #define PF_COIP AF_COIP #define PF_CNT AF_CNT #define PF_SIP AF_SIP #define PF_IPX AF_IPX /* same format as AF_NS */ #define PF_RTIP pseudo_AF_RTIP /* same format as AF_INET */ #define PF_PIP pseudo_AF_PIP #define PF_ISDN AF_ISDN #define PF_KEY pseudo_AF_KEY #define PF_INET6 AF_INET6 #define PF_NATM AF_NATM #define PF_ATM AF_ATM #define PF_NETGRAPH AF_NETGRAPH #define PF_MAX AF_MAX /* * Definitions for network related sysctl, CTL_NET. * * Second level is protocol family. * Third level is protocol number. * * Further levels are defined by the individual families below. */ #define NET_MAXID AF_MAX #define CTL_NET_NAMES { \ { 0, 0 }, \ { "unix", CTLTYPE_NODE }, \ { "inet", CTLTYPE_NODE }, \ { "implink", CTLTYPE_NODE }, \ { "pup", CTLTYPE_NODE }, \ { "chaos", CTLTYPE_NODE }, \ { "xerox_ns", CTLTYPE_NODE }, \ { "iso", CTLTYPE_NODE }, \ { "emca", CTLTYPE_NODE }, \ { "datakit", CTLTYPE_NODE }, \ { "ccitt", CTLTYPE_NODE }, \ { "ibm_sna", CTLTYPE_NODE }, \ { "decnet", CTLTYPE_NODE }, \ { "dec_dli", CTLTYPE_NODE }, \ { "lat", CTLTYPE_NODE }, \ { "hylink", CTLTYPE_NODE }, \ { "appletalk", CTLTYPE_NODE }, \ { "route", CTLTYPE_NODE }, \ { "link_layer", CTLTYPE_NODE }, \ { "xtp", CTLTYPE_NODE }, \ { "coip", CTLTYPE_NODE }, \ { "cnt", CTLTYPE_NODE }, \ { "rtip", CTLTYPE_NODE }, \ { "ipx", CTLTYPE_NODE }, \ { "sip", CTLTYPE_NODE }, \ { "pip", CTLTYPE_NODE }, \ { "isdn", CTLTYPE_NODE }, \ { "key", CTLTYPE_NODE }, \ { "inet6", CTLTYPE_NODE }, \ { "natm", CTLTYPE_NODE }, \ { "atm", CTLTYPE_NODE }, \ { "hdrcomplete", CTLTYPE_NODE }, \ { "netgraph", CTLTYPE_NODE }, \ } /* * PF_ROUTE - Routing table * * Three additional levels are defined: * Fourth: address family, 0 is wildcard * Fifth: type of info, defined below * Sixth: flag(s) to mask with for NET_RT_FLAGS */ #define NET_RT_DUMP 1 /* dump; may limit to a.f. */ #define NET_RT_FLAGS 2 /* by flags, e.g. RESOLVING */ #define NET_RT_IFLIST 3 /* survey interface list */ #define NET_RT_MAXID 4 #define CTL_NET_RT_NAMES { \ { 0, 0 }, \ { "dump", CTLTYPE_STRUCT }, \ { "flags", CTLTYPE_STRUCT }, \ { "iflist", CTLTYPE_STRUCT }, \ } /* * Maximum queue length specifiable by listen. */ #define SOMAXCONN 128 /* * Message header for recvmsg and sendmsg calls. * Used value-result for recvmsg, value only for sendmsg. */ struct msghdr { caddr_t msg_name; /* optional address */ u_int msg_namelen; /* size of address */ struct iovec *msg_iov; /* scatter/gather array */ u_int msg_iovlen; /* # elements in msg_iov */ caddr_t msg_control; /* ancillary data, see below */ u_int msg_controllen; /* ancillary data buffer len */ int msg_flags; /* flags on received message */ }; #define MSG_OOB 0x1 /* process out-of-band data */ #define MSG_PEEK 0x2 /* peek at incoming message */ #define MSG_DONTROUTE 0x4 /* send without using routing tables */ #define MSG_EOR 0x8 /* data completes record */ #define MSG_TRUNC 0x10 /* data discarded before delivery */ #define MSG_CTRUNC 0x20 /* control data lost before delivery */ #define MSG_WAITALL 0x40 /* wait for full request or error */ #define MSG_DONTWAIT 0x80 /* this message should be nonblocking */ #define MSG_EOF 0x100 /* data completes connection */ #define MSG_COMPAT 0x8000 /* used in sendit() */ /* * Header for ancillary data objects in msg_control buffer. * Used for additional information with/about a datagram * not expressible by flags. The format is a sequence * of message elements headed by cmsghdr structures. */ struct cmsghdr { u_int cmsg_len; /* data byte count, including hdr */ int cmsg_level; /* originating protocol */ int cmsg_type; /* protocol-specific type */ /* followed by u_char cmsg_data[]; */ }; /* * While we may have more groups than this, the cmsgcred struct must * be able to fit in an mbuf, and NGROUPS_MAX is too large to allow * this. */ #define CMGROUP_MAX 16 /* * Credentials structure, used to verify the identity of a peer * process that has sent us a message. This is allocated by the * peer process but filled in by the kernel. This prevents the * peer from lying about its identity. (Note that cmcred_groups[0] * is the effective GID.) */ struct cmsgcred { pid_t cmcred_pid; /* PID of sending process */ uid_t cmcred_uid; /* real UID of sending process */ uid_t cmcred_euid; /* effective UID of sending process */ gid_t cmcred_gid; /* real GID of sending process */ short cmcred_ngroups; /* number or groups */ gid_t cmcred_groups[CMGROUP_MAX]; /* groups */ }; /* given pointer to struct cmsghdr, return pointer to data */ #define CMSG_DATA(cmsg) ((u_char *)((cmsg) + 1)) +/* + * Alignment requirement for CMSG struct manipulation. + * This is different from ALIGN() defined in ARCH/include/param.h. + * XXX think again carefully about architecture dependencies. + */ +#define CMSG_ALIGN(n) (((n) + 3) & ~3) + /* given pointer to struct cmsghdr, return pointer to next cmsghdr */ #define CMSG_NXTHDR(mhdr, cmsg) \ (((caddr_t)(cmsg) + (cmsg)->cmsg_len + sizeof(struct cmsghdr) > \ (mhdr)->msg_control + (mhdr)->msg_controllen) ? \ (struct cmsghdr *)NULL : \ - (struct cmsghdr *)((caddr_t)(cmsg) + ALIGN((cmsg)->cmsg_len))) + (struct cmsghdr *)((caddr_t)(cmsg) + CMSG_ALIGN((cmsg)->cmsg_len))) #define CMSG_FIRSTHDR(mhdr) ((struct cmsghdr *)(mhdr)->msg_control) +#define CMSG_SPACE(l) (CMSG_ALIGN(sizeof(struct cmsghdr)) + CMSG_ALIGN(l)) +#define CMSG_LEN(l) (CMSG_ALIGN(sizeof(struct cmsghdr)) + (l)) + /* "Socket"-level control message types: */ #define SCM_RIGHTS 0x01 /* access rights (array of int) */ #define SCM_TIMESTAMP 0x02 /* timestamp (struct timeval) */ #define SCM_CREDS 0x03 /* process creds (struct cmsgcred) */ /* * 4.3 compat sockaddr, move to compat file later */ struct osockaddr { u_short sa_family; /* address family */ char sa_data[14]; /* up to 14 bytes of direct address */ }; /* * 4.3-compat message header (move to compat file later). */ struct omsghdr { caddr_t msg_name; /* optional address */ int msg_namelen; /* size of address */ struct iovec *msg_iov; /* scatter/gather array */ int msg_iovlen; /* # elements in msg_iov */ caddr_t msg_accrights; /* access rights sent/received */ int msg_accrightslen; }; /* * howto arguments for shutdown(2), specified by Posix.1g. */ #define SHUT_RD 0 /* shut down the reading side */ #define SHUT_WR 1 /* shut down the writing side */ #define SHUT_RDWR 2 /* shut down both sides */ /* * sendfile(2) header/trailer struct */ struct sf_hdtr { struct iovec *headers; /* pointer to an array of header struct iovec's */ int hdr_cnt; /* number of header iovec's */ struct iovec *trailers; /* pointer to an array of trailer struct iovec's */ int trl_cnt; /* number of trailer iovec's */ }; #ifndef KERNEL #include __BEGIN_DECLS int accept __P((int, struct sockaddr *, int *)); int bind __P((int, const struct sockaddr *, int)); int connect __P((int, const struct sockaddr *, int)); int getpeername __P((int, struct sockaddr *, int *)); int getsockname __P((int, struct sockaddr *, int *)); int getsockopt __P((int, int, int, void *, int *)); int listen __P((int, int)); ssize_t recv __P((int, void *, size_t, int)); ssize_t recvfrom __P((int, void *, size_t, int, struct sockaddr *, int *)); ssize_t recvmsg __P((int, struct msghdr *, int)); ssize_t send __P((int, const void *, size_t, int)); ssize_t sendto __P((int, const void *, size_t, int, const struct sockaddr *, int)); ssize_t sendmsg __P((int, const struct msghdr *, int)); int sendfile __P((int, int, off_t, size_t, struct sf_hdtr *, off_t *, int)); int setsockopt __P((int, int, int, const void *, int)); int shutdown __P((int, int)); int socket __P((int, int, int)); int socketpair __P((int, int, int, int *)); + +void pfctlinput __P((int, struct sockaddr *)); __END_DECLS #endif /* !KERNEL */ #endif /* !_SYS_SOCKET_H_ */ diff --git a/sys/sys/sockio.h b/sys/sys/sockio.h index afefc83d7f20..1e649a18074f 100644 --- a/sys/sys/sockio.h +++ b/sys/sys/sockio.h @@ -1,90 +1,98 @@ /*- * Copyright (c) 1982, 1986, 1990, 1993, 1994 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * @(#)sockio.h 8.1 (Berkeley) 3/28/94 * $FreeBSD$ */ #ifndef _SYS_SOCKIO_H_ #define _SYS_SOCKIO_H_ #include /* Socket ioctl's. */ #define SIOCSHIWAT _IOW('s', 0, int) /* set high watermark */ #define SIOCGHIWAT _IOR('s', 1, int) /* get high watermark */ #define SIOCSLOWAT _IOW('s', 2, int) /* set low watermark */ #define SIOCGLOWAT _IOR('s', 3, int) /* get low watermark */ #define SIOCATMARK _IOR('s', 7, int) /* at oob mark? */ #define SIOCSPGRP _IOW('s', 8, int) /* set process group */ #define SIOCGPGRP _IOR('s', 9, int) /* get process group */ #define SIOCADDRT _IOW('r', 10, struct ortentry) /* add route */ #define SIOCDELRT _IOW('r', 11, struct ortentry) /* delete route */ #define SIOCGETVIFCNT _IOWR('r', 15, struct sioc_vif_req)/* get vif pkt cnt */ #define SIOCGETSGCNT _IOWR('r', 16, struct sioc_sg_req) /* get s,g pkt cnt */ #define SIOCSIFADDR _IOW('i', 12, struct ifreq) /* set ifnet address */ #define OSIOCGIFADDR _IOWR('i', 13, struct ifreq) /* get ifnet address */ #define SIOCGIFADDR _IOWR('i', 33, struct ifreq) /* get ifnet address */ #define SIOCSIFDSTADDR _IOW('i', 14, struct ifreq) /* set p-p address */ #define OSIOCGIFDSTADDR _IOWR('i', 15, struct ifreq) /* get p-p address */ #define SIOCGIFDSTADDR _IOWR('i', 34, struct ifreq) /* get p-p address */ #define SIOCSIFFLAGS _IOW('i', 16, struct ifreq) /* set ifnet flags */ #define SIOCGIFFLAGS _IOWR('i', 17, struct ifreq) /* get ifnet flags */ #define OSIOCGIFBRDADDR _IOWR('i', 18, struct ifreq) /* get broadcast addr */ #define SIOCGIFBRDADDR _IOWR('i', 35, struct ifreq) /* get broadcast addr */ #define SIOCSIFBRDADDR _IOW('i', 19, struct ifreq) /* set broadcast addr */ #define OSIOCGIFCONF _IOWR('i', 20, struct ifconf) /* get ifnet list */ #define SIOCGIFCONF _IOWR('i', 36, struct ifconf) /* get ifnet list */ #define OSIOCGIFNETMASK _IOWR('i', 21, struct ifreq) /* get net addr mask */ #define SIOCGIFNETMASK _IOWR('i', 37, struct ifreq) /* get net addr mask */ #define SIOCSIFNETMASK _IOW('i', 22, struct ifreq) /* set net addr mask */ #define SIOCGIFMETRIC _IOWR('i', 23, struct ifreq) /* get IF metric */ #define SIOCSIFMETRIC _IOW('i', 24, struct ifreq) /* set IF metric */ #define SIOCDIFADDR _IOW('i', 25, struct ifreq) /* delete IF addr */ #define SIOCAIFADDR _IOW('i', 26, struct ifaliasreq)/* add/chg IF alias */ +#define SIOCALIFADDR _IOW('i', 27, struct if_laddrreq) /* add IF addr */ +#define SIOCGLIFADDR _IOWR('i', 28, struct if_laddrreq) /* get IF addr */ +#define SIOCDLIFADDR _IOW('i', 29, struct if_laddrreq) /* delete IF addr */ + #define SIOCADDMULTI _IOW('i', 49, struct ifreq) /* add m'cast addr */ #define SIOCDELMULTI _IOW('i', 50, struct ifreq) /* del m'cast addr */ #define SIOCGIFMTU _IOWR('i', 51, struct ifreq) /* get IF mtu */ #define SIOCSIFMTU _IOW('i', 52, struct ifreq) /* set IF mtu */ #define SIOCGIFPHYS _IOWR('i', 53, struct ifreq) /* get IF wire */ #define SIOCSIFPHYS _IOW('i', 54, struct ifreq) /* set IF wire */ #define SIOCSIFMEDIA _IOWR('i', 55, struct ifreq) /* set net media */ #define SIOCGIFMEDIA _IOWR('i', 56, struct ifmediareq) /* get net media */ + +#define SIOCSIFPHYADDR _IOW('i', 70, struct ifaliasreq) /* set gif addres */ +#define SIOCGIFPSRCADDR _IOWR('i', 71, struct ifreq) /* get gif psrc addr */ +#define SIOCGIFPDSTADDR _IOWR('i', 72, struct ifreq) /* get gif pdst addr */ #define SIOCSIFGENERIC _IOW('i', 57, struct ifreq) /* generic IF set op */ #define SIOCGIFGENERIC _IOWR('i', 58, struct ifreq) /* generic IF get op */ #define SIOCGIFSTATUS _IOWR('i', 59, struct ifstat) /* get IF status */ #endif /* !_SYS_SOCKIO_H_ */