freebsd-skq/sys/netinet/raw_ip.c

1055 lines
25 KiB
C
Raw Normal View History

/*-
1994-05-24 10:09:53 +00:00
* Copyright (c) 1982, 1986, 1988, 1993
* The Regents of the University of California.
* All rights reserved.
1994-05-24 10:09:53 +00:00
*
* 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.
* 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.
*
* @(#)raw_ip.c 8.7 (Berkeley) 5/15/95
1994-05-24 10:09:53 +00:00
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_inet6.h"
#include "opt_ipsec.h"
#include "opt_route.h"
#include "opt_mac.h"
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/lock.h>
1994-05-24 10:09:53 +00:00
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/priv.h>
#include <sys/proc.h>
1994-05-24 10:09:53 +00:00
#include <sys/protosw.h>
Conditionally compile out V_ globals while instantiating the appropriate container structures, depending on VIMAGE_GLOBALS compile time option. Make VIMAGE_GLOBALS a new compile-time option, which by default will not be defined, resulting in instatiations of global variables selected for V_irtualization (enclosed in #ifdef VIMAGE_GLOBALS blocks) to be effectively compiled out. Instantiate new global container structures to hold V_irtualized variables: vnet_net_0, vnet_inet_0, vnet_inet6_0, vnet_ipsec_0, vnet_netgraph_0, and vnet_gif_0. Update the VSYM() macro so that depending on VIMAGE_GLOBALS the V_ macros resolve either to the original globals, or to fields inside container structures, i.e. effectively #ifdef VIMAGE_GLOBALS #define V_rt_tables rt_tables #else #define V_rt_tables vnet_net_0._rt_tables #endif Update SYSCTL_V_*() macros to operate either on globals or on fields inside container structs. Extend the internal kldsym() lookups with the ability to resolve selected fields inside the virtualization container structs. This applies only to the fields which are explicitly registered for kldsym() visibility via VNET_MOD_DECLARE() and vnet_mod_register(), currently this is done only in sys/net/if.c. Fix a few broken instances of MODULE_GLOBAL() macro use in SCTP code, and modify the MODULE_GLOBAL() macro to resolve to V_ macros, which in turn result in proper code being generated depending on VIMAGE_GLOBALS. De-virtualize local static variables in sys/contrib/pf/net/pf_subr.c which were prematurely V_irtualized by automated V_ prepending scripts during earlier merging steps. PF virtualization will be done separately, most probably after next PF import. Convert a few variable initializations at instantiation to initialization in init functions, most notably in ipfw. Also convert TUNABLE_INT() initializers for V_ variables to TUNABLE_FETCH_INT() in initializer functions. Discussed at: devsummit Strassburg Reviewed by: bz, julian Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-12-10 23:12:39 +00:00
#include <sys/rwlock.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
1994-05-24 10:09:53 +00:00
#include <sys/socketvar.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/systm.h>
#include <sys/vimage.h>
#include <vm/uma.h>
1994-05-24 10:09:53 +00:00
#include <net/if.h>
#include <net/route.h>
#include <net/vnet.h>
1994-05-24 10:09:53 +00:00
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
1994-05-24 10:09:53 +00:00
#include <netinet/ip_var.h>
#include <netinet/ip_mroute.h>
#include <netinet/ip_fw.h>
#include <netinet/ip_dummynet.h>
#include <netinet/vinet.h>
#ifdef IPSEC
#include <netipsec/ipsec.h>
#endif /*IPSEC*/
#include <security/mac/mac_framework.h>
#ifdef VIMAGE_GLOBALS
struct inpcbhead ripcb;
struct inpcbinfo ripcbinfo;
#endif
1994-05-24 10:09:53 +00:00
/* control hooks for ipfw and dummynet */
Convert ipfw to use PFIL_HOOKS. This is change is transparent to userland and preserves the ipfw ABI. The ipfw core packet inspection and filtering functions have not been changed, only how ipfw is invoked is different. However there are many changes how ipfw is and its add-on's are handled: In general ipfw is now called through the PFIL_HOOKS and most associated magic, that was in ip_input() or ip_output() previously, is now done in ipfw_check_[in|out]() in the ipfw PFIL handler. IPDIVERT is entirely handled within the ipfw PFIL handlers. A packet to be diverted is checked if it is fragmented, if yes, ip_reass() gets in for reassembly. If not, or all fragments arrived and the packet is complete, divert_packet is called directly. For 'tee' no reassembly attempt is made and a copy of the packet is sent to the divert socket unmodified. The original packet continues its way through ip_input/output(). ipfw 'forward' is done via m_tag's. The ipfw PFIL handlers tag the packet with the new destination sockaddr_in. A check if the new destination is a local IP address is made and the m_flags are set appropriately. ip_input() and ip_output() have some more work to do here. For ip_input() the m_flags are checked and a packet for us is directly sent to the 'ours' section for further processing. Destination changes on the input path are only tagged and the 'srcrt' flag to ip_forward() is set to disable destination checks and ICMP replies at this stage. The tag is going to be handled on output. ip_output() again checks for m_flags and the 'ours' tag. If found, the packet will be dropped back to the IP netisr where it is going to be picked up by ip_input() again and the directly sent to the 'ours' section. When only the destination changes, the route's 'dst' is overwritten with the new destination from the forward m_tag. Then it jumps back at the route lookup again and skips the firewall check because it has been marked with M_SKIP_FIREWALL. ipfw 'forward' has to be compiled into the kernel with 'option IPFIREWALL_FORWARD' to enable it. DUMMYNET is entirely handled within the ipfw PFIL handlers. A packet for a dummynet pipe or queue is directly sent to dummynet_io(). Dummynet will then inject it back into ip_input/ip_output() after it has served its time. Dummynet packets are tagged and will continue from the next rule when they hit the ipfw PFIL handlers again after re-injection. BRIDGING and IPFW_ETHER are not changed yet and use ipfw_chk() directly as they did before. Later this will be changed to dedicated ETHER PFIL_HOOKS. More detailed changes to the code: conf/files Add netinet/ip_fw_pfil.c. conf/options Add IPFIREWALL_FORWARD option. modules/ipfw/Makefile Add ip_fw_pfil.c. net/bridge.c Disable PFIL_HOOKS if ipfw for bridging is active. Bridging ipfw is still directly invoked to handle layer2 headers and packets would get a double ipfw when run through PFIL_HOOKS as well. netinet/ip_divert.c Removed divert_clone() function. It is no longer used. netinet/ip_dummynet.[ch] Neither the route 'ro' nor the destination 'dst' need to be stored while in dummynet transit. Structure members and associated macros are removed. netinet/ip_fastfwd.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_fw.h Removed 'ro' and 'dst' from struct ip_fw_args. netinet/ip_fw2.c (Re)moved some global variables and the module handling. netinet/ip_fw_pfil.c New file containing the ipfw PFIL handlers and module initialization. netinet/ip_input.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. ip_forward() does not longer require the 'next_hop' struct sockaddr_in argument. Disable early checks if 'srcrt' is set. netinet/ip_output.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_var.h Add ip_reass() as general function. (Used from ipfw PFIL handlers for IPDIVERT.) netinet/raw_ip.c Directly check if ipfw and dummynet control pointers are active. netinet/tcp_input.c Rework the 'ipfw forward' to local code to work with the new way of forward tags. netinet/tcp_sack.c Remove include 'opt_ipfw.h' which is not needed here. sys/mbuf.h Remove m_claim_next() macro which was exclusively for ipfw 'forward' and is no longer needed. Approved by: re (scottl)
2004-08-17 22:05:54 +00:00
ip_fw_ctl_t *ip_fw_ctl_ptr = NULL;
ip_dn_ctl_t *ip_dn_ctl_ptr = NULL;
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
/*
* Hooks for multicast routing. They all default to NULL, so leave them not
* initialized and rely on BSS being set to 0.
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
*/
/*
* The socket used to communicate with the multicast routing daemon.
*/
#ifdef VIMAGE_GLOBALS
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
struct socket *ip_mrouter;
#endif
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
/*
* The various mrouter and rsvp functions.
*/
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
int (*ip_mrouter_set)(struct socket *, struct sockopt *);
int (*ip_mrouter_get)(struct socket *, struct sockopt *);
int (*ip_mrouter_done)(void);
int (*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
struct ip_moptions *);
Add code to allow the system to handle multiple routing tables. This particular implementation is designed to be fully backwards compatible and to be MFC-able to 7.x (and 6.x) Currently the only protocol that can make use of the multiple tables is IPv4 Similar functionality exists in OpenBSD and Linux. From my notes: ----- One thing where FreeBSD has been falling behind, and which by chance I have some time to work on is "policy based routing", which allows different packet streams to be routed by more than just the destination address. Constraints: ------------ I want to make some form of this available in the 6.x tree (and by extension 7.x) , but FreeBSD in general needs it so I might as well do it in -current and back port the portions I need. One of the ways that this can be done is to have the ability to instantiate multiple kernel routing tables (which I will now refer to as "Forwarding Information Bases" or "FIBs" for political correctness reasons). Which FIB a particular packet uses to make the next hop decision can be decided by a number of mechanisms. The policies these mechanisms implement are the "Policies" referred to in "Policy based routing". One of the constraints I have if I try to back port this work to 6.x is that it must be implemented as a EXTENSION to the existing ABIs in 6.x so that third party applications do not need to be recompiled in timespan of the branch. This first version will not have some of the bells and whistles that will come with later versions. It will, for example, be limited to 16 tables in the first commit. Implementation method, Compatible version. (part 1) ------------------------------- For this reason I have implemented a "sufficient subset" of a multiple routing table solution in Perforce, and back-ported it to 6.x. (also in Perforce though not always caught up with what I have done in -current/P4). The subset allows a number of FIBs to be defined at compile time (8 is sufficient for my purposes in 6.x) and implements the changes needed to allow IPV4 to use them. I have not done the changes for ipv6 simply because I do not need it, and I do not have enough knowledge of ipv6 (e.g. neighbor discovery) needed to do it. Other protocol families are left untouched and should there be users with proprietary protocol families, they should continue to work and be oblivious to the existence of the extra FIBs. To understand how this is done, one must know that the current FIB code starts everything off with a single dimensional array of pointers to FIB head structures (One per protocol family), each of which in turn points to the trie of routes available to that family. The basic change in the ABI compatible version of the change is to extent that array to be a 2 dimensional array, so that instead of protocol family X looking at rt_tables[X] for the table it needs, it looks at rt_tables[Y][X] when for all protocol families except ipv4 Y is always 0. Code that is unaware of the change always just sees the first row of the table, which of course looks just like the one dimensional array that existed before. The entry points rtrequest(), rtalloc(), rtalloc1(), rtalloc_ign() are all maintained, but refer only to the first row of the array, so that existing callers in proprietary protocols can continue to do the "right thing". Some new entry points are added, for the exclusive use of ipv4 code called in_rtrequest(), in_rtalloc(), in_rtalloc1() and in_rtalloc_ign(), which have an extra argument which refers the code to the correct row. In addition, there are some new entry points (currently called rtalloc_fib() and friends) that check the Address family being looked up and call either rtalloc() (and friends) if the protocol is not IPv4 forcing the action to row 0 or to the appropriate row if it IS IPv4 (and that info is available). These are for calling from code that is not specific to any particular protocol. The way these are implemented would change in the non ABI preserving code to be added later. One feature of the first version of the code is that for ipv4, the interface routes show up automatically on all the FIBs, so that no matter what FIB you select you always have the basic direct attached hosts available to you. (rtinit() does this automatically). You CAN delete an interface route from one FIB should you want to but by default it's there. ARP information is also available in each FIB. It's assumed that the same machine would have the same MAC address, regardless of which FIB you are using to get to it. This brings us as to how the correct FIB is selected for an outgoing IPV4 packet. Firstly, all packets have a FIB associated with them. if nothing has been done to change it, it will be FIB 0. The FIB is changed in the following ways. Packets fall into one of a number of classes. 1/ locally generated packets, coming from a socket/PCB. Such packets select a FIB from a number associated with the socket/PCB. This in turn is inherited from the process, but can be changed by a socket option. The process in turn inherits it on fork. I have written a utility call setfib that acts a bit like nice.. setfib -3 ping target.example.com # will use fib 3 for ping. It is an obvious extension to make it a property of a jail but I have not done so. It can be achieved by combining the setfib and jail commands. 2/ packets received on an interface for forwarding. By default these packets would use table 0, (or possibly a number settable in a sysctl(not yet)). but prior to routing the firewall can inspect them (see below). (possibly in the future you may be able to associate a FIB with packets received on an interface.. An ifconfig arg, but not yet.) 3/ packets inspected by a packet classifier, which can arbitrarily associate a fib with it on a packet by packet basis. A fib assigned to a packet by a packet classifier (such as ipfw) would over-ride a fib associated by a more default source. (such as cases 1 or 2). 4/ a tcp listen socket associated with a fib will generate accept sockets that are associated with that same fib. 5/ Packets generated in response to some other packet (e.g. reset or icmp packets). These should use the FIB associated with the packet being reponded to. 6/ Packets generated during encapsulation. gif, tun and other tunnel interfaces will encapsulate using the FIB that was in effect withthe proces that set up the tunnel. thus setfib 1 ifconfig gif0 [tunnel instructions] will set the fib for the tunnel to use to be fib 1. Routing messages would be associated with their process, and thus select one FIB or another. messages from the kernel would be associated with the fib they refer to and would only be received by a routing socket associated with that fib. (not yet implemented) In addition Netstat has been edited to be able to cope with the fact that the array is now 2 dimensional. (It looks in system memory using libkvm (!)). Old versions of netstat see only the first FIB. In addition two sysctls are added to give: a) the number of FIBs compiled in (active) b) the default FIB of the calling process. Early testing experience: ------------------------- Basically our (IronPort's) appliance does this functionality already using ipfw fwd but that method has some drawbacks. For example, It can't fully simulate a routing table because it can't influence the socket's choice of local address when a connect() is done. Testing during the generating of these changes has been remarkably smooth so far. Multiple tables have co-existed with no notable side effects, and packets have been routes accordingly. ipfw has grown 2 new keywords: setfib N ip from anay to any count ip from any to any fib N In pf there seems to be a requirement to be able to give symbolic names to the fibs but I do not have that capacity. I am not sure if it is required. SCTP has interestingly enough built in support for this, called VRFs in Cisco parlance. it will be interesting to see how that handles it when it suddenly actually does something. Where to next: -------------------- After committing the ABI compatible version and MFCing it, I'd like to proceed in a forward direction in -current. this will result in some roto-tilling in the routing code. Firstly: the current code's idea of having a separate tree per protocol family, all of the same format, and pointed to by the 1 dimensional array is a bit silly. Especially when one considers that there is code that makes assumptions about every protocol having the same internal structures there. Some protocols don't WANT that sort of structure. (for example the whole idea of a netmask is foreign to appletalk). This needs to be made opaque to the external code. My suggested first change is to add routing method pointers to the 'domain' structure, along with information pointing the data. instead of having an array of pointers to uniform structures, there would be an array pointing to the 'domain' structures for each protocol address domain (protocol family), and the methods this reached would be called. The methods would have an argument that gives FIB number, but the protocol would be free to ignore it. When the ABI can be changed it raises the possibilty of the addition of a fib entry into the "struct route". Currently, the structure contains the sockaddr of the desination, and the resulting fib entry. To make this work fully, one could add a fib number so that given an address and a fib, one can find the third element, the fib entry. Interaction with the ARP layer/ LL layer would need to be revisited as well. Qing Li has been working on this already. This work was sponsored by Ironport Systems/Cisco Reviewed by: several including rwatson, bz and mlair (parts each) Obtained from: Ironport systems/Cisco
2008-05-09 23:03:00 +00:00
int (*mrt_ioctl)(int, caddr_t, int);
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
int (*legal_vif_num)(int);
u_long (*ip_mcast_src)(int);
void (*rsvp_input_p)(struct mbuf *m, int off);
int (*ip_rsvp_vif)(struct socket *, struct sockopt *);
void (*ip_rsvp_force_done)(struct socket *);
/*
* Hash functions
*/
#define INP_PCBHASH_RAW_SIZE 256
#define INP_PCBHASH_RAW(proto, laddr, faddr, mask) \
(((proto) + (laddr) + (faddr)) % (mask) + 1)
static void
rip_inshash(struct inpcb *inp)
{
struct inpcbinfo *pcbinfo = inp->inp_pcbinfo;
struct inpcbhead *pcbhash;
int hash;
INP_INFO_WLOCK_ASSERT(pcbinfo);
INP_WLOCK_ASSERT(inp);
if (inp->inp_ip_p != 0 &&
inp->inp_laddr.s_addr != INADDR_ANY &&
inp->inp_faddr.s_addr != INADDR_ANY) {
hash = INP_PCBHASH_RAW(inp->inp_ip_p, inp->inp_laddr.s_addr,
inp->inp_faddr.s_addr, pcbinfo->ipi_hashmask);
} else
hash = 0;
pcbhash = &pcbinfo->ipi_hashbase[hash];
LIST_INSERT_HEAD(pcbhash, inp, inp_hash);
}
static void
rip_delhash(struct inpcb *inp)
{
INP_INFO_WLOCK_ASSERT(inp->inp_pcbinfo);
INP_WLOCK_ASSERT(inp);
LIST_REMOVE(inp, inp_hash);
}
1994-05-24 10:09:53 +00:00
/*
* Raw interface to IP protocol.
*/
/*
* Initialize raw connection block q.
1994-05-24 10:09:53 +00:00
*/
static void
rip_zone_change(void *tag)
{
INIT_VNET_INET(curvnet);
uma_zone_set_max(V_ripcbinfo.ipi_zone, maxsockets);
}
static int
rip_inpcb_init(void *mem, int size, int flags)
{
struct inpcb *inp = mem;
INP_LOCK_INIT(inp, "inp", "rawinp");
return (0);
}
1994-05-24 10:09:53 +00:00
void
rip_init(void)
1994-05-24 10:09:53 +00:00
{
INIT_VNET_INET(curvnet);
INP_INFO_LOCK_INIT(&V_ripcbinfo, "rip");
LIST_INIT(&V_ripcb);
V_ripcbinfo.ipi_listhead = &V_ripcb;
V_ripcbinfo.ipi_hashbase =
hashinit(INP_PCBHASH_RAW_SIZE, M_PCB, &V_ripcbinfo.ipi_hashmask);
V_ripcbinfo.ipi_porthashbase =
hashinit(1, M_PCB, &V_ripcbinfo.ipi_porthashmask);
V_ripcbinfo.ipi_zone = uma_zcreate("ripcb", sizeof(struct inpcb),
NULL, NULL, rip_inpcb_init, NULL, UMA_ALIGN_PTR, UMA_ZONE_NOFREE);
uma_zone_set_max(V_ripcbinfo.ipi_zone, maxsockets);
EVENTHANDLER_REGISTER(maxsockets_change, rip_zone_change, NULL,
EVENTHANDLER_PRI_ANY);
1994-05-24 10:09:53 +00:00
}
static int
rip_append(struct inpcb *last, struct ip *ip, struct mbuf *n,
struct sockaddr_in *ripsrc)
{
int policyfail = 0;
INP_RLOCK_ASSERT(last);
#ifdef IPSEC
/* check AH/ESP integrity. */
if (ipsec4_in_reject(n, last)) {
policyfail = 1;
}
#endif /* IPSEC */
#ifdef MAC
if (!policyfail && mac_inpcb_check_deliver(last, n) != 0)
policyfail = 1;
#endif
/* Check the minimum TTL for socket. */
if (last->inp_ip_minttl && last->inp_ip_minttl > ip->ip_ttl)
policyfail = 1;
if (!policyfail) {
struct mbuf *opts = NULL;
struct socket *so;
so = last->inp_socket;
if ((last->inp_flags & INP_CONTROLOPTS) ||
(so->so_options & (SO_TIMESTAMP | SO_BINTIME)))
ip_savecontrol(last, &opts, ip, n);
SOCKBUF_LOCK(&so->so_rcv);
if (sbappendaddr_locked(&so->so_rcv,
(struct sockaddr *)ripsrc, n, opts) == 0) {
/* should notify about lost packet */
m_freem(n);
if (opts)
m_freem(opts);
SOCKBUF_UNLOCK(&so->so_rcv);
} else
sorwakeup_locked(so);
} else
m_freem(n);
return (policyfail);
}
1994-05-24 10:09:53 +00:00
/*
* Setup generic address and protocol structures for raw_input routine, then
* pass them along with mbuf chain.
1994-05-24 10:09:53 +00:00
*/
void
rip_input(struct mbuf *m, int off)
1994-05-24 10:09:53 +00:00
{
INIT_VNET_INET(curvnet);
struct ifnet *ifp;
struct ip *ip = mtod(m, struct ip *);
int proto = ip->ip_p;
struct inpcb *inp, *last;
struct sockaddr_in ripsrc;
int hash;
1994-05-24 10:09:53 +00:00
bzero(&ripsrc, sizeof(ripsrc));
ripsrc.sin_len = sizeof(ripsrc);
ripsrc.sin_family = AF_INET;
1994-05-24 10:09:53 +00:00
ripsrc.sin_addr = ip->ip_src;
last = NULL;
ifp = m->m_pkthdr.rcvif;
hash = INP_PCBHASH_RAW(proto, ip->ip_src.s_addr,
ip->ip_dst.s_addr, V_ripcbinfo.ipi_hashmask);
INP_INFO_RLOCK(&V_ripcbinfo);
LIST_FOREACH(inp, &V_ripcbinfo.ipi_hashbase[hash], inp_hash) {
if (inp->inp_ip_p != proto)
continue;
#ifdef INET6
/* XXX inp locking */
if ((inp->inp_vflag & INP_IPV4) == 0)
continue;
#endif
if (inp->inp_laddr.s_addr != ip->ip_dst.s_addr)
continue;
if (inp->inp_faddr.s_addr != ip->ip_src.s_addr)
continue;
if (jailed(inp->inp_cred)) {
/*
* XXX: If faddr was bound to multicast group,
* jailed raw socket will drop datagram.
*/
if (prison_check_ip4(inp->inp_cred, &ip->ip_dst) != 0)
continue;
}
if (last != NULL) {
struct mbuf *n;
n = m_copy(m, 0, (int)M_COPYALL);
if (n != NULL)
(void) rip_append(last, ip, n, &ripsrc);
/* XXX count dropped packet */
INP_RUNLOCK(last);
}
INP_RLOCK(inp);
last = inp;
}
LIST_FOREACH(inp, &V_ripcbinfo.ipi_hashbase[0], inp_hash) {
if (inp->inp_ip_p && inp->inp_ip_p != proto)
continue;
#ifdef INET6
/* XXX inp locking */
if ((inp->inp_vflag & INP_IPV4) == 0)
continue;
#endif
if (!in_nullhost(inp->inp_laddr) &&
!in_hosteq(inp->inp_laddr, ip->ip_dst))
continue;
if (!in_nullhost(inp->inp_faddr) &&
!in_hosteq(inp->inp_faddr, ip->ip_src))
continue;
if (jailed(inp->inp_cred)) {
/*
* Allow raw socket in jail to receive multicast;
* assume process had PRIV_NETINET_RAW at attach,
* and fall through into normal filter path if so.
*/
if (!IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) &&
prison_check_ip4(inp->inp_cred, &ip->ip_dst) != 0)
continue;
}
/*
* If this raw socket has multicast state, and we
* have received a multicast, check if this socket
* should receive it, as multicast filtering is now
* the responsibility of the transport layer.
*/
if (inp->inp_moptions != NULL &&
IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
struct sockaddr_in group;
int blocked;
bzero(&group, sizeof(struct sockaddr_in));
group.sin_len = sizeof(struct sockaddr_in);
group.sin_family = AF_INET;
group.sin_addr = ip->ip_dst;
blocked = imo_multi_filter(inp->inp_moptions, ifp,
(struct sockaddr *)&group,
(struct sockaddr *)&ripsrc);
if (blocked != MCAST_PASS) {
IPSTAT_INC(ips_notmember);
continue;
}
}
if (last != NULL) {
struct mbuf *n;
n = m_copy(m, 0, (int)M_COPYALL);
if (n != NULL)
(void) rip_append(last, ip, n, &ripsrc);
/* XXX count dropped packet */
INP_RUNLOCK(last);
1994-05-24 10:09:53 +00:00
}
INP_RLOCK(inp);
last = inp;
1994-05-24 10:09:53 +00:00
}
INP_INFO_RUNLOCK(&V_ripcbinfo);
if (last != NULL) {
if (rip_append(last, ip, m, &ripsrc) != 0)
IPSTAT_INC(ips_delivered);
INP_RUNLOCK(last);
1994-05-24 10:09:53 +00:00
} else {
m_freem(m);
IPSTAT_INC(ips_noproto);
IPSTAT_DEC(ips_delivered);
}
}
1994-05-24 10:09:53 +00:00
/*
* Generate IP header and pass packet to ip_output. Tack on options user may
* have setup with control call.
1994-05-24 10:09:53 +00:00
*/
int
rip_output(struct mbuf *m, struct socket *so, u_long dst)
1994-05-24 10:09:53 +00:00
{
INIT_VNET_INET(so->so_vnet);
struct ip *ip;
int error;
struct inpcb *inp = sotoinpcb(so);
int flags = ((so->so_options & SO_DONTROUTE) ? IP_ROUTETOIF : 0) |
IP_ALLOWBROADCAST;
1994-05-24 10:09:53 +00:00
/*
* If the user handed us a complete IP packet, use it. Otherwise,
* allocate an mbuf for a header and fill it in.
1994-05-24 10:09:53 +00:00
*/
if ((inp->inp_flags & INP_HDRINCL) == 0) {
if (m->m_pkthdr.len + sizeof(struct ip) > IP_MAXPACKET) {
m_freem(m);
return(EMSGSIZE);
}
M_PREPEND(m, sizeof(struct ip), M_DONTWAIT);
if (m == NULL)
return(ENOBUFS);
INP_RLOCK(inp);
1994-05-24 10:09:53 +00:00
ip = mtod(m, struct ip *);
ip->ip_tos = inp->inp_ip_tos;
if (inp->inp_flags & INP_DONTFRAG)
ip->ip_off = IP_DF;
else
ip->ip_off = 0;
ip->ip_p = inp->inp_ip_p;
1994-05-24 10:09:53 +00:00
ip->ip_len = m->m_pkthdr.len;
ip->ip_src = inp->inp_laddr;
error = prison_get_ip4(inp->inp_cred, &ip->ip_src);
if (error != 0) {
INP_RUNLOCK(inp);
m_freem(m);
return (error);
MFp4: Bring in updated jail support from bz_jail branch. This enhances the current jail implementation to permit multiple addresses per jail. In addtion to IPv4, IPv6 is supported as well. Due to updated checks it is even possible to have jails without an IP address at all, which basically gives one a chroot with restricted process view, no networking,.. SCTP support was updated and supports IPv6 in jails as well. Cpuset support permits jails to be bound to specific processor sets after creation. Jails can have an unrestricted (no duplicate protection, etc.) name in addition to the hostname. The jail name cannot be changed from within a jail and is considered to be used for management purposes or as audit-token in the future. DDB 'show jails' command was added to aid debugging. Proper compat support permits 32bit jail binaries to be used on 64bit systems to manage jails. Also backward compatibility was preserved where possible: for jail v1 syscalls, as well as with user space management utilities. Both jail as well as prison version were updated for the new features. A gap was intentionally left as the intermediate versions had been used by various patches floating around the last years. Bump __FreeBSD_version for the afore mentioned and in kernel changes. Special thanks to: - Pawel Jakub Dawidek (pjd) for his multi-IPv4 patches and Olivier Houchard (cognet) for initial single-IPv6 patches. - Jeff Roberson (jeff) and Randall Stewart (rrs) for their help, ideas and review on cpuset and SCTP support. - Robert Watson (rwatson) for lots and lots of help, discussions, suggestions and review of most of the patch at various stages. - John Baldwin (jhb) for his help. - Simon L. Nielsen (simon) as early adopter testing changes on cluster machines as well as all the testers and people who provided feedback the last months on freebsd-jail and other channels. - My employer, CK Software GmbH, for the support so I could work on this. Reviewed by: (see above) MFC after: 3 months (this is just so that I get the mail) X-MFC Before: 7.2-RELEASE if possible
2008-11-29 14:32:14 +00:00
}
1994-05-24 10:09:53 +00:00
ip->ip_dst.s_addr = dst;
ip->ip_ttl = inp->inp_ip_ttl;
1994-05-24 10:09:53 +00:00
} else {
if (m->m_pkthdr.len > IP_MAXPACKET) {
m_freem(m);
return(EMSGSIZE);
}
INP_RLOCK(inp);
1994-05-24 10:09:53 +00:00
ip = mtod(m, struct ip *);
error = prison_check_ip4(inp->inp_cred, &ip->ip_src);
if (error != 0) {
MFp4: Bring in updated jail support from bz_jail branch. This enhances the current jail implementation to permit multiple addresses per jail. In addtion to IPv4, IPv6 is supported as well. Due to updated checks it is even possible to have jails without an IP address at all, which basically gives one a chroot with restricted process view, no networking,.. SCTP support was updated and supports IPv6 in jails as well. Cpuset support permits jails to be bound to specific processor sets after creation. Jails can have an unrestricted (no duplicate protection, etc.) name in addition to the hostname. The jail name cannot be changed from within a jail and is considered to be used for management purposes or as audit-token in the future. DDB 'show jails' command was added to aid debugging. Proper compat support permits 32bit jail binaries to be used on 64bit systems to manage jails. Also backward compatibility was preserved where possible: for jail v1 syscalls, as well as with user space management utilities. Both jail as well as prison version were updated for the new features. A gap was intentionally left as the intermediate versions had been used by various patches floating around the last years. Bump __FreeBSD_version for the afore mentioned and in kernel changes. Special thanks to: - Pawel Jakub Dawidek (pjd) for his multi-IPv4 patches and Olivier Houchard (cognet) for initial single-IPv6 patches. - Jeff Roberson (jeff) and Randall Stewart (rrs) for their help, ideas and review on cpuset and SCTP support. - Robert Watson (rwatson) for lots and lots of help, discussions, suggestions and review of most of the patch at various stages. - John Baldwin (jhb) for his help. - Simon L. Nielsen (simon) as early adopter testing changes on cluster machines as well as all the testers and people who provided feedback the last months on freebsd-jail and other channels. - My employer, CK Software GmbH, for the support so I could work on this. Reviewed by: (see above) MFC after: 3 months (this is just so that I get the mail) X-MFC Before: 7.2-RELEASE if possible
2008-11-29 14:32:14 +00:00
INP_RUNLOCK(inp);
m_freem(m);
return (error);
}
/*
* Don't allow both user specified and setsockopt options,
* and don't allow packet length sizes that will crash.
*/
if (((ip->ip_hl != (sizeof (*ip) >> 2)) && inp->inp_options)
|| (ip->ip_len > m->m_pkthdr.len)
|| (ip->ip_len < (ip->ip_hl << 2))) {
INP_RUNLOCK(inp);
m_freem(m);
return (EINVAL);
}
1994-05-24 10:09:53 +00:00
if (ip->ip_id == 0)
ip->ip_id = ip_newid();
/*
* XXX prevent ip_output from overwriting header fields.
*/
1994-05-24 10:09:53 +00:00
flags |= IP_RAWOUTPUT;
IPSTAT_INC(ips_rawout);
1994-05-24 10:09:53 +00:00
}
if (inp->inp_flags & INP_ONESBCAST)
flags |= IP_SENDONES;
#ifdef MAC
mac_inpcb_create_mbuf(inp, m);
#endif
error = ip_output(m, inp->inp_options, NULL, flags,
inp->inp_moptions, inp);
INP_RUNLOCK(inp);
return (error);
1994-05-24 10:09:53 +00:00
}
/*
* Raw IP socket option processing.
*
* IMPORTANT NOTE regarding access control: Traditionally, raw sockets could
* only be created by a privileged process, and as such, socket option
* operations to manage system properties on any raw socket were allowed to
* take place without explicit additional access control checks. However,
* raw sockets can now also be created in jail(), and therefore explicit
* checks are now required. Likewise, raw sockets can be used by a process
* after it gives up privilege, so some caution is required. For options
* passed down to the IP layer via ip_ctloutput(), checks are assumed to be
* performed in ip_ctloutput() and therefore no check occurs here.
* Unilaterally checking priv_check() here breaks normal IP socket option
* operations on raw sockets.
*
* When adding new socket options here, make sure to add access control
* checks here as necessary.
1994-05-24 10:09:53 +00:00
*/
int
rip_ctloutput(struct socket *so, struct sockopt *sopt)
1994-05-24 10:09:53 +00:00
{
struct inpcb *inp = sotoinpcb(so);
int error, optval;
1994-05-24 10:09:53 +00:00
if (sopt->sopt_level != IPPROTO_IP) {
if ((sopt->sopt_level == SOL_SOCKET) &&
(sopt->sopt_name == SO_SETFIB)) {
inp->inp_inc.inc_fibnum = so->so_fibnum;
return (0);
}
1994-05-24 10:09:53 +00:00
return (EINVAL);
}
1994-05-24 10:09:53 +00:00
error = 0;
switch (sopt->sopt_dir) {
case SOPT_GET:
switch (sopt->sopt_name) {
case IP_HDRINCL:
optval = inp->inp_flags & INP_HDRINCL;
error = sooptcopyout(sopt, &optval, sizeof optval);
break;
case IP_FW_ADD: /* ADD actually returns the body... */
case IP_FW_GET:
case IP_FW_TABLE_GETSIZE:
case IP_FW_TABLE_LIST:
case IP_FW_NAT_GET_CONFIG:
case IP_FW_NAT_GET_LOG:
Convert ipfw to use PFIL_HOOKS. This is change is transparent to userland and preserves the ipfw ABI. The ipfw core packet inspection and filtering functions have not been changed, only how ipfw is invoked is different. However there are many changes how ipfw is and its add-on's are handled: In general ipfw is now called through the PFIL_HOOKS and most associated magic, that was in ip_input() or ip_output() previously, is now done in ipfw_check_[in|out]() in the ipfw PFIL handler. IPDIVERT is entirely handled within the ipfw PFIL handlers. A packet to be diverted is checked if it is fragmented, if yes, ip_reass() gets in for reassembly. If not, or all fragments arrived and the packet is complete, divert_packet is called directly. For 'tee' no reassembly attempt is made and a copy of the packet is sent to the divert socket unmodified. The original packet continues its way through ip_input/output(). ipfw 'forward' is done via m_tag's. The ipfw PFIL handlers tag the packet with the new destination sockaddr_in. A check if the new destination is a local IP address is made and the m_flags are set appropriately. ip_input() and ip_output() have some more work to do here. For ip_input() the m_flags are checked and a packet for us is directly sent to the 'ours' section for further processing. Destination changes on the input path are only tagged and the 'srcrt' flag to ip_forward() is set to disable destination checks and ICMP replies at this stage. The tag is going to be handled on output. ip_output() again checks for m_flags and the 'ours' tag. If found, the packet will be dropped back to the IP netisr where it is going to be picked up by ip_input() again and the directly sent to the 'ours' section. When only the destination changes, the route's 'dst' is overwritten with the new destination from the forward m_tag. Then it jumps back at the route lookup again and skips the firewall check because it has been marked with M_SKIP_FIREWALL. ipfw 'forward' has to be compiled into the kernel with 'option IPFIREWALL_FORWARD' to enable it. DUMMYNET is entirely handled within the ipfw PFIL handlers. A packet for a dummynet pipe or queue is directly sent to dummynet_io(). Dummynet will then inject it back into ip_input/ip_output() after it has served its time. Dummynet packets are tagged and will continue from the next rule when they hit the ipfw PFIL handlers again after re-injection. BRIDGING and IPFW_ETHER are not changed yet and use ipfw_chk() directly as they did before. Later this will be changed to dedicated ETHER PFIL_HOOKS. More detailed changes to the code: conf/files Add netinet/ip_fw_pfil.c. conf/options Add IPFIREWALL_FORWARD option. modules/ipfw/Makefile Add ip_fw_pfil.c. net/bridge.c Disable PFIL_HOOKS if ipfw for bridging is active. Bridging ipfw is still directly invoked to handle layer2 headers and packets would get a double ipfw when run through PFIL_HOOKS as well. netinet/ip_divert.c Removed divert_clone() function. It is no longer used. netinet/ip_dummynet.[ch] Neither the route 'ro' nor the destination 'dst' need to be stored while in dummynet transit. Structure members and associated macros are removed. netinet/ip_fastfwd.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_fw.h Removed 'ro' and 'dst' from struct ip_fw_args. netinet/ip_fw2.c (Re)moved some global variables and the module handling. netinet/ip_fw_pfil.c New file containing the ipfw PFIL handlers and module initialization. netinet/ip_input.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. ip_forward() does not longer require the 'next_hop' struct sockaddr_in argument. Disable early checks if 'srcrt' is set. netinet/ip_output.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_var.h Add ip_reass() as general function. (Used from ipfw PFIL handlers for IPDIVERT.) netinet/raw_ip.c Directly check if ipfw and dummynet control pointers are active. netinet/tcp_input.c Rework the 'ipfw forward' to local code to work with the new way of forward tags. netinet/tcp_sack.c Remove include 'opt_ipfw.h' which is not needed here. sys/mbuf.h Remove m_claim_next() macro which was exclusively for ipfw 'forward' and is no longer needed. Approved by: re (scottl)
2004-08-17 22:05:54 +00:00
if (ip_fw_ctl_ptr != NULL)
error = ip_fw_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break;
case IP_DUMMYNET_GET:
Convert ipfw to use PFIL_HOOKS. This is change is transparent to userland and preserves the ipfw ABI. The ipfw core packet inspection and filtering functions have not been changed, only how ipfw is invoked is different. However there are many changes how ipfw is and its add-on's are handled: In general ipfw is now called through the PFIL_HOOKS and most associated magic, that was in ip_input() or ip_output() previously, is now done in ipfw_check_[in|out]() in the ipfw PFIL handler. IPDIVERT is entirely handled within the ipfw PFIL handlers. A packet to be diverted is checked if it is fragmented, if yes, ip_reass() gets in for reassembly. If not, or all fragments arrived and the packet is complete, divert_packet is called directly. For 'tee' no reassembly attempt is made and a copy of the packet is sent to the divert socket unmodified. The original packet continues its way through ip_input/output(). ipfw 'forward' is done via m_tag's. The ipfw PFIL handlers tag the packet with the new destination sockaddr_in. A check if the new destination is a local IP address is made and the m_flags are set appropriately. ip_input() and ip_output() have some more work to do here. For ip_input() the m_flags are checked and a packet for us is directly sent to the 'ours' section for further processing. Destination changes on the input path are only tagged and the 'srcrt' flag to ip_forward() is set to disable destination checks and ICMP replies at this stage. The tag is going to be handled on output. ip_output() again checks for m_flags and the 'ours' tag. If found, the packet will be dropped back to the IP netisr where it is going to be picked up by ip_input() again and the directly sent to the 'ours' section. When only the destination changes, the route's 'dst' is overwritten with the new destination from the forward m_tag. Then it jumps back at the route lookup again and skips the firewall check because it has been marked with M_SKIP_FIREWALL. ipfw 'forward' has to be compiled into the kernel with 'option IPFIREWALL_FORWARD' to enable it. DUMMYNET is entirely handled within the ipfw PFIL handlers. A packet for a dummynet pipe or queue is directly sent to dummynet_io(). Dummynet will then inject it back into ip_input/ip_output() after it has served its time. Dummynet packets are tagged and will continue from the next rule when they hit the ipfw PFIL handlers again after re-injection. BRIDGING and IPFW_ETHER are not changed yet and use ipfw_chk() directly as they did before. Later this will be changed to dedicated ETHER PFIL_HOOKS. More detailed changes to the code: conf/files Add netinet/ip_fw_pfil.c. conf/options Add IPFIREWALL_FORWARD option. modules/ipfw/Makefile Add ip_fw_pfil.c. net/bridge.c Disable PFIL_HOOKS if ipfw for bridging is active. Bridging ipfw is still directly invoked to handle layer2 headers and packets would get a double ipfw when run through PFIL_HOOKS as well. netinet/ip_divert.c Removed divert_clone() function. It is no longer used. netinet/ip_dummynet.[ch] Neither the route 'ro' nor the destination 'dst' need to be stored while in dummynet transit. Structure members and associated macros are removed. netinet/ip_fastfwd.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_fw.h Removed 'ro' and 'dst' from struct ip_fw_args. netinet/ip_fw2.c (Re)moved some global variables and the module handling. netinet/ip_fw_pfil.c New file containing the ipfw PFIL handlers and module initialization. netinet/ip_input.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. ip_forward() does not longer require the 'next_hop' struct sockaddr_in argument. Disable early checks if 'srcrt' is set. netinet/ip_output.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_var.h Add ip_reass() as general function. (Used from ipfw PFIL handlers for IPDIVERT.) netinet/raw_ip.c Directly check if ipfw and dummynet control pointers are active. netinet/tcp_input.c Rework the 'ipfw forward' to local code to work with the new way of forward tags. netinet/tcp_sack.c Remove include 'opt_ipfw.h' which is not needed here. sys/mbuf.h Remove m_claim_next() macro which was exclusively for ipfw 'forward' and is no longer needed. Approved by: re (scottl)
2004-08-17 22:05:54 +00:00
if (ip_dn_ctl_ptr != NULL)
error = ip_dn_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break ;
case MRT_INIT:
case MRT_DONE:
case MRT_ADD_VIF:
case MRT_DEL_VIF:
case MRT_ADD_MFC:
case MRT_DEL_MFC:
case MRT_VERSION:
case MRT_ASSERT:
case MRT_API_SUPPORT:
case MRT_API_CONFIG:
case MRT_ADD_BW_UPCALL:
case MRT_DEL_BW_UPCALL:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
error = ip_mrouter_get ? ip_mrouter_get(so, sopt) :
EOPNOTSUPP;
break;
1994-05-24 10:09:53 +00:00
default:
error = ip_ctloutput(so, sopt);
break;
}
break;
case SOPT_SET:
switch (sopt->sopt_name) {
case IP_HDRINCL:
error = sooptcopyin(sopt, &optval, sizeof optval,
sizeof optval);
if (error)
break;
if (optval)
inp->inp_flags |= INP_HDRINCL;
else
inp->inp_flags &= ~INP_HDRINCL;
break;
1994-05-24 10:09:53 +00:00
case IP_FW_ADD:
case IP_FW_DEL:
case IP_FW_FLUSH:
case IP_FW_ZERO:
case IP_FW_RESETLOG:
case IP_FW_TABLE_ADD:
case IP_FW_TABLE_DEL:
case IP_FW_TABLE_FLUSH:
case IP_FW_NAT_CFG:
case IP_FW_NAT_DEL:
Convert ipfw to use PFIL_HOOKS. This is change is transparent to userland and preserves the ipfw ABI. The ipfw core packet inspection and filtering functions have not been changed, only how ipfw is invoked is different. However there are many changes how ipfw is and its add-on's are handled: In general ipfw is now called through the PFIL_HOOKS and most associated magic, that was in ip_input() or ip_output() previously, is now done in ipfw_check_[in|out]() in the ipfw PFIL handler. IPDIVERT is entirely handled within the ipfw PFIL handlers. A packet to be diverted is checked if it is fragmented, if yes, ip_reass() gets in for reassembly. If not, or all fragments arrived and the packet is complete, divert_packet is called directly. For 'tee' no reassembly attempt is made and a copy of the packet is sent to the divert socket unmodified. The original packet continues its way through ip_input/output(). ipfw 'forward' is done via m_tag's. The ipfw PFIL handlers tag the packet with the new destination sockaddr_in. A check if the new destination is a local IP address is made and the m_flags are set appropriately. ip_input() and ip_output() have some more work to do here. For ip_input() the m_flags are checked and a packet for us is directly sent to the 'ours' section for further processing. Destination changes on the input path are only tagged and the 'srcrt' flag to ip_forward() is set to disable destination checks and ICMP replies at this stage. The tag is going to be handled on output. ip_output() again checks for m_flags and the 'ours' tag. If found, the packet will be dropped back to the IP netisr where it is going to be picked up by ip_input() again and the directly sent to the 'ours' section. When only the destination changes, the route's 'dst' is overwritten with the new destination from the forward m_tag. Then it jumps back at the route lookup again and skips the firewall check because it has been marked with M_SKIP_FIREWALL. ipfw 'forward' has to be compiled into the kernel with 'option IPFIREWALL_FORWARD' to enable it. DUMMYNET is entirely handled within the ipfw PFIL handlers. A packet for a dummynet pipe or queue is directly sent to dummynet_io(). Dummynet will then inject it back into ip_input/ip_output() after it has served its time. Dummynet packets are tagged and will continue from the next rule when they hit the ipfw PFIL handlers again after re-injection. BRIDGING and IPFW_ETHER are not changed yet and use ipfw_chk() directly as they did before. Later this will be changed to dedicated ETHER PFIL_HOOKS. More detailed changes to the code: conf/files Add netinet/ip_fw_pfil.c. conf/options Add IPFIREWALL_FORWARD option. modules/ipfw/Makefile Add ip_fw_pfil.c. net/bridge.c Disable PFIL_HOOKS if ipfw for bridging is active. Bridging ipfw is still directly invoked to handle layer2 headers and packets would get a double ipfw when run through PFIL_HOOKS as well. netinet/ip_divert.c Removed divert_clone() function. It is no longer used. netinet/ip_dummynet.[ch] Neither the route 'ro' nor the destination 'dst' need to be stored while in dummynet transit. Structure members and associated macros are removed. netinet/ip_fastfwd.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_fw.h Removed 'ro' and 'dst' from struct ip_fw_args. netinet/ip_fw2.c (Re)moved some global variables and the module handling. netinet/ip_fw_pfil.c New file containing the ipfw PFIL handlers and module initialization. netinet/ip_input.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. ip_forward() does not longer require the 'next_hop' struct sockaddr_in argument. Disable early checks if 'srcrt' is set. netinet/ip_output.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_var.h Add ip_reass() as general function. (Used from ipfw PFIL handlers for IPDIVERT.) netinet/raw_ip.c Directly check if ipfw and dummynet control pointers are active. netinet/tcp_input.c Rework the 'ipfw forward' to local code to work with the new way of forward tags. netinet/tcp_sack.c Remove include 'opt_ipfw.h' which is not needed here. sys/mbuf.h Remove m_claim_next() macro which was exclusively for ipfw 'forward' and is no longer needed. Approved by: re (scottl)
2004-08-17 22:05:54 +00:00
if (ip_fw_ctl_ptr != NULL)
error = ip_fw_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break;
case IP_DUMMYNET_CONFIGURE:
case IP_DUMMYNET_DEL:
case IP_DUMMYNET_FLUSH:
Convert ipfw to use PFIL_HOOKS. This is change is transparent to userland and preserves the ipfw ABI. The ipfw core packet inspection and filtering functions have not been changed, only how ipfw is invoked is different. However there are many changes how ipfw is and its add-on's are handled: In general ipfw is now called through the PFIL_HOOKS and most associated magic, that was in ip_input() or ip_output() previously, is now done in ipfw_check_[in|out]() in the ipfw PFIL handler. IPDIVERT is entirely handled within the ipfw PFIL handlers. A packet to be diverted is checked if it is fragmented, if yes, ip_reass() gets in for reassembly. If not, or all fragments arrived and the packet is complete, divert_packet is called directly. For 'tee' no reassembly attempt is made and a copy of the packet is sent to the divert socket unmodified. The original packet continues its way through ip_input/output(). ipfw 'forward' is done via m_tag's. The ipfw PFIL handlers tag the packet with the new destination sockaddr_in. A check if the new destination is a local IP address is made and the m_flags are set appropriately. ip_input() and ip_output() have some more work to do here. For ip_input() the m_flags are checked and a packet for us is directly sent to the 'ours' section for further processing. Destination changes on the input path are only tagged and the 'srcrt' flag to ip_forward() is set to disable destination checks and ICMP replies at this stage. The tag is going to be handled on output. ip_output() again checks for m_flags and the 'ours' tag. If found, the packet will be dropped back to the IP netisr where it is going to be picked up by ip_input() again and the directly sent to the 'ours' section. When only the destination changes, the route's 'dst' is overwritten with the new destination from the forward m_tag. Then it jumps back at the route lookup again and skips the firewall check because it has been marked with M_SKIP_FIREWALL. ipfw 'forward' has to be compiled into the kernel with 'option IPFIREWALL_FORWARD' to enable it. DUMMYNET is entirely handled within the ipfw PFIL handlers. A packet for a dummynet pipe or queue is directly sent to dummynet_io(). Dummynet will then inject it back into ip_input/ip_output() after it has served its time. Dummynet packets are tagged and will continue from the next rule when they hit the ipfw PFIL handlers again after re-injection. BRIDGING and IPFW_ETHER are not changed yet and use ipfw_chk() directly as they did before. Later this will be changed to dedicated ETHER PFIL_HOOKS. More detailed changes to the code: conf/files Add netinet/ip_fw_pfil.c. conf/options Add IPFIREWALL_FORWARD option. modules/ipfw/Makefile Add ip_fw_pfil.c. net/bridge.c Disable PFIL_HOOKS if ipfw for bridging is active. Bridging ipfw is still directly invoked to handle layer2 headers and packets would get a double ipfw when run through PFIL_HOOKS as well. netinet/ip_divert.c Removed divert_clone() function. It is no longer used. netinet/ip_dummynet.[ch] Neither the route 'ro' nor the destination 'dst' need to be stored while in dummynet transit. Structure members and associated macros are removed. netinet/ip_fastfwd.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_fw.h Removed 'ro' and 'dst' from struct ip_fw_args. netinet/ip_fw2.c (Re)moved some global variables and the module handling. netinet/ip_fw_pfil.c New file containing the ipfw PFIL handlers and module initialization. netinet/ip_input.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. ip_forward() does not longer require the 'next_hop' struct sockaddr_in argument. Disable early checks if 'srcrt' is set. netinet/ip_output.c Removed all direct ipfw handling code and replace it with the new 'ipfw forward' handling code. netinet/ip_var.h Add ip_reass() as general function. (Used from ipfw PFIL handlers for IPDIVERT.) netinet/raw_ip.c Directly check if ipfw and dummynet control pointers are active. netinet/tcp_input.c Rework the 'ipfw forward' to local code to work with the new way of forward tags. netinet/tcp_sack.c Remove include 'opt_ipfw.h' which is not needed here. sys/mbuf.h Remove m_claim_next() macro which was exclusively for ipfw 'forward' and is no longer needed. Approved by: re (scottl)
2004-08-17 22:05:54 +00:00
if (ip_dn_ctl_ptr != NULL)
error = ip_dn_ctl_ptr(sopt);
else
error = ENOPROTOOPT ;
break ;
case IP_RSVP_ON:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_init(so);
break;
Initial get-the-easy-case-working upgrade of the multicast code to something more recent than the ancient 1.2 release contained in 4.4. This code has the following advantages as compared to previous versions (culled from the README file for the SunOS release): - True multicast delivery - Configurable rate-limiting of forwarded multicast traffic on each physical interface or tunnel, using a token-bucket limiter. - Simplistic classification of packets for prioritized dropping. - Administrative scoping of multicast address ranges. - Faster detection of hosts leaving groups. - Support for multicast traceroute (code not yet available). - Support for RSVP, the Resource Reservation Protocol. What still needs to be done: - The multicast forwarder needs testing. - The multicast routing daemon needs to be ported. - Network interface drivers need to have the `#ifdef MULTICAST' goop ripped out of them. - The IGMP code should probably be bogon-tested. Some notes about the porting process: In some cases, the Berkeley people decided to incorporate functionality from later releases of the multicast code, but then had to do things differently. As a result, if you look at Deering's patches, and then look at our code, it is not always obvious whether the patch even applies. Let the reader beware. I ran ip_mroute.c through several passes of `unifdef' to get rid of useless grot, and to permanently enable the RSVP support, which we will include as standard. Ported by: Garrett Wollman Submitted by: Steve Deering and Ajit Thyagarajan (among others)
1994-09-06 22:42:31 +00:00
case IP_RSVP_OFF:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_done();
break;
Initial get-the-easy-case-working upgrade of the multicast code to something more recent than the ancient 1.2 release contained in 4.4. This code has the following advantages as compared to previous versions (culled from the README file for the SunOS release): - True multicast delivery - Configurable rate-limiting of forwarded multicast traffic on each physical interface or tunnel, using a token-bucket limiter. - Simplistic classification of packets for prioritized dropping. - Administrative scoping of multicast address ranges. - Faster detection of hosts leaving groups. - Support for multicast traceroute (code not yet available). - Support for RSVP, the Resource Reservation Protocol. What still needs to be done: - The multicast forwarder needs testing. - The multicast routing daemon needs to be ported. - Network interface drivers need to have the `#ifdef MULTICAST' goop ripped out of them. - The IGMP code should probably be bogon-tested. Some notes about the porting process: In some cases, the Berkeley people decided to incorporate functionality from later releases of the multicast code, but then had to do things differently. As a result, if you look at Deering's patches, and then look at our code, it is not always obvious whether the patch even applies. Let the reader beware. I ran ip_mroute.c through several passes of `unifdef' to get rid of useless grot, and to permanently enable the RSVP support, which we will include as standard. Ported by: Garrett Wollman Submitted by: Steve Deering and Ajit Thyagarajan (among others)
1994-09-06 22:42:31 +00:00
case IP_RSVP_VIF_ON:
case IP_RSVP_VIF_OFF:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
error = ip_rsvp_vif ?
ip_rsvp_vif(so, sopt) : EINVAL;
break;
case MRT_INIT:
case MRT_DONE:
case MRT_ADD_VIF:
case MRT_DEL_VIF:
case MRT_ADD_MFC:
case MRT_DEL_MFC:
case MRT_VERSION:
case MRT_ASSERT:
case MRT_API_SUPPORT:
case MRT_API_CONFIG:
case MRT_ADD_BW_UPCALL:
case MRT_DEL_BW_UPCALL:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
Massive cleanup of the ip_mroute code. No functional changes, but: + the mrouting module now should behave the same as the compiled-in version (it did not before, some of the rsvp code was not loaded properly); + netinet/ip_mroute.c is now truly optional; + removed some redundant/unused code; + changed many instances of '0' to NULL and INADDR_ANY as appropriate; + removed several static variables to make the code more SMP-friendly; + fixed some minor bugs in the mrouting code (mostly, incorrect return values from functions). This commit is also a prerequisite to the addition of support for PIM, which i would like to put in before DP2 (it does not change any of the existing APIs, anyways). Note, in the process we found out that some device drivers fail to properly handle changes in IFF_ALLMULTI, leading to interesting behaviour when a multicast router is started. This bug is not corrected by this commit, and will be fixed with a separate commit. Detailed changes: -------------------- netinet/ip_mroute.c all the above. conf/files make ip_mroute.c optional net/route.c fix mrt_ioctl hook netinet/ip_input.c fix ip_mforward hook, move rsvp_input() here together with other rsvp code, and a couple of indentation fixes. netinet/ip_output.c fix ip_mforward and ip_mcast_src hooks netinet/ip_var.h rsvp function hooks netinet/raw_ip.c hooks for mrouting and rsvp functions, plus interface cleanup. netinet/ip_mroute.h remove an unused and optional field from a struct Most of the code is from Pavlin Radoslavov and the XORP project Reviewed by: sam MFC after: 1 week
2002-11-15 22:53:53 +00:00
error = ip_mrouter_set ? ip_mrouter_set(so, sopt) :
EOPNOTSUPP;
break;
default:
error = ip_ctloutput(so, sopt);
break;
}
break;
1994-05-24 10:09:53 +00:00
}
return (error);
1994-05-24 10:09:53 +00:00
}
/*
* This function exists solely to receive the PRC_IFDOWN messages which are
* sent by if_down(). It looks for an ifaddr whose ifa_addr is sa, and calls
* in_ifadown() to remove all routes corresponding to that address. It also
* receives the PRC_IFUP messages from if_up() and reinstalls the interface
* routes.
*/
void
rip_ctlinput(int cmd, struct sockaddr *sa, void *vip)
{
INIT_VNET_INET(curvnet);
struct in_ifaddr *ia;
struct ifnet *ifp;
int err;
int flags;
switch (cmd) {
case PRC_IFDOWN:
TAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if (ia->ia_ifa.ifa_addr == sa
&& (ia->ia_flags & IFA_ROUTE)) {
/*
* in_ifscrub kills the interface route.
*/
in_ifscrub(ia->ia_ifp, ia);
/*
* in_ifadown gets rid of all the rest of the
* routes. This is not quite the right thing
* to do, but at least if we are running a
* routing process they will come back.
*/
in_ifadown(&ia->ia_ifa, 0);
break;
}
}
break;
case PRC_IFUP:
TAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if (ia->ia_ifa.ifa_addr == sa)
break;
}
if (ia == 0 || (ia->ia_flags & IFA_ROUTE))
return;
flags = RTF_UP;
ifp = ia->ia_ifa.ifa_ifp;
if ((ifp->if_flags & IFF_LOOPBACK)
|| (ifp->if_flags & IFF_POINTOPOINT))
flags |= RTF_HOST;
err = rtinit(&ia->ia_ifa, RTM_ADD, flags);
if (err == 0)
ia->ia_flags |= IFA_ROUTE;
break;
}
}
u_long rip_sendspace = 9216;
u_long rip_recvspace = 9216;
SYSCTL_ULONG(_net_inet_raw, OID_AUTO, maxdgram, CTLFLAG_RW,
&rip_sendspace, 0, "Maximum outgoing raw IP datagram size");
SYSCTL_ULONG(_net_inet_raw, OID_AUTO, recvspace, CTLFLAG_RW,
&rip_recvspace, 0, "Maximum space for incoming raw IP datagrams");
static int
rip_attach(struct socket *so, int proto, struct thread *td)
{
INIT_VNET_INET(so->so_vnet);
struct inpcb *inp;
int error;
inp = sotoinpcb(so);
KASSERT(inp == NULL, ("rip_attach: inp != NULL"));
error = priv_check(td, PRIV_NETINET_RAW);
if (error)
return (error);
if (proto >= IPPROTO_MAX || proto < 0)
return EPROTONOSUPPORT;
error = soreserve(so, rip_sendspace, rip_recvspace);
if (error)
return (error);
INP_INFO_WLOCK(&V_ripcbinfo);
error = in_pcballoc(so, &V_ripcbinfo);
if (error) {
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (error);
}
inp = (struct inpcb *)so->so_pcb;
inp->inp_vflag |= INP_IPV4;
inp->inp_ip_p = proto;
inp->inp_ip_ttl = V_ip_defttl;
rip_inshash(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
INP_WUNLOCK(inp);
return (0);
}
1994-05-24 10:09:53 +00:00
static void
rip_detach(struct socket *so)
{
INIT_VNET_INET(so->so_vnet);
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_detach: inp == NULL"));
KASSERT(inp->inp_faddr.s_addr == INADDR_ANY,
("rip_detach: not closed"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
if (so == V_ip_mrouter && ip_mrouter_done)
ip_mrouter_done();
if (ip_rsvp_force_done)
ip_rsvp_force_done(so);
if (so == V_ip_rsvpd)
ip_rsvp_done();
in_pcbdetach(inp);
in_pcbfree(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
}
static void
rip_dodisconnect(struct socket *so, struct inpcb *inp)
{
INP_INFO_WLOCK_ASSERT(inp->inp_pcbinfo);
INP_WLOCK_ASSERT(inp);
rip_delhash(inp);
inp->inp_faddr.s_addr = INADDR_ANY;
rip_inshash(inp);
SOCK_LOCK(so);
so->so_state &= ~SS_ISCONNECTED;
SOCK_UNLOCK(so);
}
static void
rip_abort(struct socket *so)
{
INIT_VNET_INET(so->so_vnet);
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_abort: inp == NULL"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_dodisconnect(so, inp);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
}
1994-05-24 10:09:53 +00:00
static void
rip_close(struct socket *so)
{
INIT_VNET_INET(so->so_vnet);
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_close: inp == NULL"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_dodisconnect(so, inp);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
}
1994-05-24 10:09:53 +00:00
static int
rip_disconnect(struct socket *so)
{
INIT_VNET_INET(so->so_vnet);
struct inpcb *inp;
if ((so->so_state & SS_ISCONNECTED) == 0)
return (ENOTCONN);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_disconnect: inp == NULL"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_dodisconnect(so, inp);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (0);
}
1994-05-24 10:09:53 +00:00
static int
rip_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
{
INIT_VNET_NET(so->so_vnet);
INIT_VNET_INET(so->so_vnet);
struct sockaddr_in *addr = (struct sockaddr_in *)nam;
struct inpcb *inp;
int error;
if (nam->sa_len != sizeof(*addr))
return (EINVAL);
error = prison_check_ip4(td->td_ucred, &addr->sin_addr);
if (error != 0)
return (error);
if (TAILQ_EMPTY(&V_ifnet) ||
(addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK) ||
(addr->sin_addr.s_addr &&
ifa_ifwithaddr((struct sockaddr *)addr) == 0))
return (EADDRNOTAVAIL);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_bind: inp == NULL"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
inp->inp_laddr = addr->sin_addr;
rip_inshash(inp);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (0);
}
1994-05-24 10:09:53 +00:00
static int
rip_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
{
INIT_VNET_NET(so->so_vnet);
INIT_VNET_INET(so->so_vnet);
struct sockaddr_in *addr = (struct sockaddr_in *)nam;
struct inpcb *inp;
if (nam->sa_len != sizeof(*addr))
return (EINVAL);
if (TAILQ_EMPTY(&V_ifnet))
return (EADDRNOTAVAIL);
if (addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK)
return (EAFNOSUPPORT);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_connect: inp == NULL"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
inp->inp_faddr = addr->sin_addr;
rip_inshash(inp);
soisconnected(so);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (0);
}
1994-05-24 10:09:53 +00:00
static int
rip_shutdown(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_shutdown: inp == NULL"));
INP_WLOCK(inp);
socantsendmore(so);
INP_WUNLOCK(inp);
return (0);
}
1994-05-24 10:09:53 +00:00
static int
rip_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam,
struct mbuf *control, struct thread *td)
{
struct inpcb *inp;
u_long dst;
1994-05-24 10:09:53 +00:00
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_send: inp == NULL"));
/*
* Note: 'dst' reads below are unlocked.
*/
if (so->so_state & SS_ISCONNECTED) {
if (nam) {
m_freem(m);
return (EISCONN);
1994-05-24 10:09:53 +00:00
}
dst = inp->inp_faddr.s_addr; /* Unlocked read. */
} else {
if (nam == NULL) {
m_freem(m);
return (ENOTCONN);
}
dst = ((struct sockaddr_in *)nam)->sin_addr.s_addr;
1994-05-24 10:09:53 +00:00
}
return (rip_output(m, so, dst));
1994-05-24 10:09:53 +00:00
}
static int
rip_pcblist(SYSCTL_HANDLER_ARGS)
{
INIT_VNET_INET(curvnet);
int error, i, n;
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 = V_ripcbinfo.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.
*/
INP_INFO_RLOCK(&V_ripcbinfo);
gencnt = V_ripcbinfo.ipi_gencnt;
n = V_ripcbinfo.ipi_count;
INP_INFO_RUNLOCK(&V_ripcbinfo);
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);
INP_INFO_RLOCK(&V_ripcbinfo);
for (inp = LIST_FIRST(V_ripcbinfo.ipi_listhead), i = 0; inp && i < n;
inp = LIST_NEXT(inp, inp_list)) {
INP_RLOCK(inp);
if (inp->inp_gencnt <= gencnt &&
cr_canseeinpcb(req->td->td_ucred, inp) == 0) {
/* XXX held references? */
inp_list[i++] = inp;
}
INP_RUNLOCK(inp);
}
INP_INFO_RUNLOCK(&V_ripcbinfo);
n = i;
error = 0;
for (i = 0; i < n; i++) {
inp = inp_list[i];
INP_RLOCK(inp);
if (inp->inp_gencnt <= gencnt) {
struct xinpcb xi;
bzero(&xi, sizeof(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);
INP_RUNLOCK(inp);
error = SYSCTL_OUT(req, &xi, sizeof xi);
} else
INP_RUNLOCK(inp);
}
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.
*/
INP_INFO_RLOCK(&V_ripcbinfo);
xig.xig_gen = V_ripcbinfo.ipi_gencnt;
xig.xig_sogen = so_gencnt;
xig.xig_count = V_ripcbinfo.ipi_count;
INP_INFO_RUNLOCK(&V_ripcbinfo);
error = SYSCTL_OUT(req, &xig, sizeof xig);
}
free(inp_list, M_TEMP);
return (error);
}
SYSCTL_PROC(_net_inet_raw, OID_AUTO/*XXX*/, pcblist, CTLFLAG_RD, 0, 0,
rip_pcblist, "S,xinpcb", "List of active raw IP sockets");
struct pr_usrreqs rip_usrreqs = {
.pru_abort = rip_abort,
.pru_attach = rip_attach,
.pru_bind = rip_bind,
.pru_connect = rip_connect,
.pru_control = in_control,
.pru_detach = rip_detach,
.pru_disconnect = rip_disconnect,
.pru_peeraddr = in_getpeeraddr,
.pru_send = rip_send,
.pru_shutdown = rip_shutdown,
.pru_sockaddr = in_getsockaddr,
.pru_sosetlabel = in_pcbsosetlabel,
.pru_close = rip_close,
};