d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
530c006014
freebsd-nq/sys/netinet/ip_icmp.c

989 lines
26 KiB
C
Raw Normal View History

/* -> /*- for license, minor formatting changes
2005-01-07 01:45:51 +00:00
/*-
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
* 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.
* 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_icmp.c 8.2 (Berkeley) 1/4/94
*/
Add FBSDID to all files in netinet so that people can more easily include file version information in bug reports. Approved by: re (kensmith)
2007-10-07 20:44:24 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
IPSEC support in the kernel. pr_input() routines prototype is also changed to support IPSEC and IPV6 chained protocol headers. Reviewed by: freebsd-arch, cvs-committers Obtained from: KAME project
1999-12-22 19:13:38 +00:00
#include "opt_ipsec.h"
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/time.h>
#include <sys/kernel.h>
Add and move declarations to fix all of the warnings from `gcc -Wimplicit' (except in netccitt, netiso and netns) and most of the warnings from `gcc -Wnested-externs'. Fix all the bugs found. There were no serious ones.
1995-03-16 18:17:34 +00:00
#include <sys/sysctl.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <net/if.h>
Make faith loadable, unloadable, and clonable.
2001-09-25 18:40:52 +00:00
#include <net/if_types.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <net/route.h>
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
#include <net/vnet.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <netinet/in.h>
Introduce tcp_hostcache and remove the tcp specific metrics from the routing table. Move all usage and references in the tcp stack from the routing table metrics to the tcp hostcache. It caches measured parameters of past tcp sessions to provide better initial start values for following connections from or to the same source or destination. Depending on the network parameters to/from the remote host this can lead to significant speedups for new tcp connections after the first one because they inherit and shortcut the learning curve. tcp_hostcache is designed for multiple concurrent access in SMP environments with high contention and is hash indexed by remote ip address. It removes significant locking requirements from the tcp stack with regard to the routing table. Reviewed by: sam (mentor), bms Reviewed by: -net, -current, core@kame.net (IPv6 parts) Approved by: re (scottl)
2003-11-20 20:07:39 +00:00
#include <netinet/in_pcb.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>
Add and move declarations to fix all of the warnings from `gcc -Wimplicit' (except in netccitt, netiso and netns) and most of the warnings from `gcc -Wnested-externs'. Fix all the bugs found. There were no serious ones.
1995-03-16 18:17:34 +00:00
#include <netinet/ip_var.h>
Consolidate all IP Options handling functions into ip_options.[ch] and include ip_options.h into all files making use of IP Options functions. From ip_input.c rev 1.306: ip_dooptions(struct mbuf *m, int pass) save_rte(m, option, dst) ip_srcroute(m0) ip_stripoptions(m, mopt) From ip_output.c rev 1.249: ip_insertoptions(m, opt, phlen) ip_optcopy(ip, jp) ip_pcbopts(struct inpcb *inp, int optname, struct mbuf *m) No functional changes in this commit. Discussed with: rwatson Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 20:12:40 +00:00
#include <netinet/ip_options.h>
Introduce tcp_hostcache and remove the tcp specific metrics from the routing table. Move all usage and references in the tcp stack from the routing table metrics to the tcp hostcache. It caches measured parameters of past tcp sessions to provide better initial start values for following connections from or to the same source or destination. Depending on the network parameters to/from the remote host this can lead to significant speedups for new tcp connections after the first one because they inherit and shortcut the learning curve. tcp_hostcache is designed for multiple concurrent access in SMP environments with high contention and is hash indexed by remote ip address. It removes significant locking requirements from the tcp stack with regard to the routing table. Reviewed by: sam (mentor), bms Reviewed by: -net, -current, core@kame.net (IPv6 parts) Approved by: re (scottl)
2003-11-20 20:07:39 +00:00
#include <netinet/tcp.h>
#include <netinet/tcp_var.h>
#include <netinet/tcpip.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#include <netinet/icmp_var.h>
Commit the change from FAST_IPSEC to IPSEC. The FAST_IPSEC option is now deprecated, as well as the KAME IPsec code. What was FAST_IPSEC is now IPSEC. Approved by: re Sponsored by: Secure Computing
2007-07-03 12:13:45 +00:00
#ifdef IPSEC
Tie new "Fast IPsec" code into the build. This involves the usual configuration stuff as well as conditional code in the IPv4 and IPv6 areas. Everything is conditional on FAST_IPSEC which is mutually exclusive with IPSEC (KAME IPsec implmentation). As noted previously, don't use FAST_IPSEC with INET6 at the moment. Reviewed by: KAME, rwatson Approved by: silence Supported by: Vernier Networks
2002-10-16 02:25:05 +00:00
#include <netipsec/ipsec.h>
#include <netipsec/key.h>
#endif
Add #include <machine/in_cksum.h>, in order to pick up the checksum inline functions and prototypes.
2000-05-06 18:19:58 +00:00
#include <machine/in_cksum.h>
Complete break-out of sys/sys/mac.h into sys/security/mac/mac_framework.h begun with a repo-copy of mac.h to mac_framework.h. sys/mac.h now contains the userspace and user<->kernel API and definitions, with all in-kernel interfaces moved to mac_framework.h, which is now included across most of the kernel instead. This change is the first step in a larger cleanup and sweep of MAC Framework interfaces in the kernel, and will not be MFC'd. Obtained from: TrustedBSD Project Sponsored by: SPARTA
2006-10-22 11:52:19 +00:00
#include <security/mac/mac_framework.h>
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
/*
* ICMP routines: error generation, receive packet processing, and
* routines to turnaround packets back to the originator, and
* host table maintenance routines.
*/
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
VNET_DEFINE(struct icmpstat, icmpstat);
static VNET_DEFINE(int, icmpmaskrepl);
static VNET_DEFINE(u_int, icmpmaskfake);
static VNET_DEFINE(int, drop_redirect);
static VNET_DEFINE(int, log_redirect);
static VNET_DEFINE(int, icmplim);
static VNET_DEFINE(int, icmplim_output);
static VNET_DEFINE(char, reply_src[IFNAMSIZ]);
static VNET_DEFINE(int, icmp_rfi);
static VNET_DEFINE(int, icmp_quotelen);
static VNET_DEFINE(int, icmpbmcastecho);
Remove unused VNET_SET() and related macros; only VNET_GET() is ever actually used. Rename VNET_GET() to VNET() to shorten variable references. Discussed with: bz, julian Reviewed by: bz Approved by: re (kensmith, kib)
2009-07-16 21:13:04 +00:00
#define V_icmpmaskrepl VNET(icmpmaskrepl)
#define V_icmpmaskfake VNET(icmpmaskfake)
#define V_drop_redirect VNET(drop_redirect)
#define V_log_redirect VNET(log_redirect)
#define V_icmplim VNET(icmplim)
#define V_icmplim_output VNET(icmplim_output)
#define V_reply_src VNET(reply_src)
#define V_icmp_rfi VNET(icmp_rfi)
#define V_icmp_quotelen VNET(icmp_quotelen)
#define V_icmpbmcastecho VNET(icmpbmcastecho)
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_STRUCT(_net_inet_icmp, ICMPCTL_STATS, stats, CTLFLAG_RW,
&VNET_NAME(icmpstat), icmpstat, "");
SYSCTL_VNET_INT(_net_inet_icmp, ICMPCTL_MASKREPL, maskrepl, CTLFLAG_RW,
&VNET_NAME(icmpmaskrepl), 0,
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
"Reply to ICMP Address Mask Request packets.");
Add a sysctl node allowing the specification of an address mask to use when replying to ICMP Address Mask Request packets.
2003-03-21 15:43:06 +00:00
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_UINT(_net_inet_icmp, OID_AUTO, maskfake, CTLFLAG_RW,
&VNET_NAME(icmpmaskfake), 0,
"Fake reply to ICMP Address Mask Request packets.");
New style sysctl & staticize alot of stuff.
1995-11-14 20:34:56 +00:00
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_INT(_net_inet_icmp, OID_AUTO, drop_redirect, CTLFLAG_RW,
&VNET_NAME(drop_redirect), 0,
"Ignore ICMP redirects");
Add net.inet.icmp.log_redirect and net.inet.icmp.drop_redirect, for respectively logging and dropping ICMP REDIRECT packets. Note that there is no rate limiting on the log messages, so log_redirect should be used with caution (preferrably only for debugging purposes).
1999-08-10 09:45:33 +00:00
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_INT(_net_inet_icmp, OID_AUTO, log_redirect, CTLFLAG_RW,
&VNET_NAME(log_redirect), 0,
"Log ICMP redirects to the console");
Reorder.
1999-09-14 16:40:28 +00:00
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_INT(_net_inet_icmp, ICMPCTL_ICMPLIM, icmplim, CTLFLAG_RW,
&VNET_NAME(icmplim), 0,
"Maximum number of ICMP responses per second");
Cleanup icmp_var.h, make icmp bandlim sysctl permanent but if ICMP_BANDLIM option not defined the sysctl int value is set to -1 and read-only. #ifdef KERNEL's added appropriately to wall off visibility of kernel routines from user code.
1998-12-04 04:21:25 +00:00
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_INT(_net_inet_icmp, OID_AUTO, icmplim_output, CTLFLAG_RW,
&VNET_NAME(icmplim_output), 0,
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
"Enable rate limiting of ICMP responses");
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_STRING(_net_inet_icmp, OID_AUTO, reply_src, CTLFLAG_RW,
&VNET_NAME(reply_src), IFNAMSIZ,
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
"icmp reply source for non-local packets.");
Add sysctl net.inet.icmp.reply_src to specify the interface name used for the ICMP reply source in reponse to packets which are not directly addressed to us. By default continue with with normal source selection. Reviewed by: bms
2004-02-02 22:53:16 +00:00
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_INT(_net_inet_icmp, OID_AUTO, reply_from_interface, CTLFLAG_RW,
&VNET_NAME(icmp_rfi), 0,
"ICMP reply from incoming interface for non-local packets");
Add an option to have ICMP replies to non-local packets generated with the IP address the packet came through in. This is useful for routers to show in traceroutes the actual path a packet has taken instead of the possibly different return path. The new sysctl is named net.inet.icmp.reply_from_interface and defaults to off. MFC after: 2 weeks
2005-08-21 12:29:39 +00:00
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_INT(_net_inet_icmp, OID_AUTO, quotelen, CTLFLAG_RW,
&VNET_NAME(icmp_quotelen), 0,
"Number of bytes from original packet to quote in ICMP reply");
Add a sysctl to change to length of the quotation of the original packet in an ICMP reply. The minimum of 8 bytes is internally enforced. The maximum quotation is the remaining space in the reply mbuf. This option is added in response to the issues raised in I-D draft-gont-icmp-payload-00.txt. MFC after: 2 weeks Spnsored by: TCP/IP Optimizations Fundraise 2005
2005-08-21 15:09:07 +00:00
Cleanup icmp_var.h, make icmp bandlim sysctl permanent but if ICMP_BANDLIM option not defined the sysctl int value is set to -1 and read-only. #ifdef KERNEL's added appropriately to wall off visibility of kernel routines from user code.
1998-12-04 04:21:25 +00:00
/*
* ICMP broadcast echo sysctl
*/
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
SYSCTL_VNET_INT(_net_inet_icmp, OID_AUTO, bmcastecho, CTLFLAG_RW,
&VNET_NAME(icmpbmcastecho), 0,
"");
Configurably don't reply to broadcast or multicast echos. There are still potential problems with other automatic-reply ICMPs, but some of them may depend on broadcast/multicast to operate. (This code can simply be moved to the `reflect' label to generalize it.)
1997-08-25 01:25:31 +00:00
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#ifdef ICMPPRINTFS
int icmpprintfs = 0;
#endif
Remove __P.
2002-03-19 21:25:46 +00:00
static void icmp_reflect(struct mbuf *);
Remove the global one-level rtcache variable and associated complex locking and rework ip_rtaddr() to do its own rtlookup. Adopt all its callers to this and make ip_output() callable with NULL rt pointer. Reviewed by: sam (mentor)
2003-11-14 21:48:57 +00:00
static void icmp_send(struct mbuf *, struct mbuf *);
New style sysctl & staticize alot of stuff.
1995-11-14 20:34:56 +00:00
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
extern struct protosw inetsw[];
Change the initialization methodology for global variables scheduled for virtualization. Instead of initializing the affected global variables at instatiation, assign initial values to them in initializer functions. As a rule, initialization at instatiation for such variables should never be introduced again from now on. Furthermore, enclose all instantiations of such global variables in #ifdef VIMAGE_GLOBALS blocks. Essentialy, this change should have zero functional impact. In the next phase of merging network stack virtualization infrastructure from p4/vimage branch, the new initialization methology will allow us to switch between using global variables and their counterparts residing in virtualization containers with minimum code churn, and in the long run allow us to intialize multiple instances of such container structures. 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
2008-11-19 09:39:34 +00:00
void
icmp_init(void)
{
V_icmpmaskrepl = 0;
V_icmpmaskfake = 0;
V_drop_redirect = 0;
V_log_redirect = 0;
V_icmplim = 200;
V_icmplim_output = 1;
V_icmp_rfi = 0;
V_icmp_quotelen = 8;
V_icmpbmcastecho = 0;
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
/*
* Generate an error packet of type error
* in response to bad packet ip.
*/
void
Use uint32_t instead of n_long and n_time, and uint16_t instead of n_short. Add a note next to fields in network format. The n_* types are not enough for compiler checks on endianness, and their use often requires an otherwise unnecessary #include <netinet/in_systm.h> The typedef in in_systm.h are still there.
2009-02-13 15:14:43 +00:00
icmp_error(struct mbuf *n, int type, int code, uint32_t dest, int mtu)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
register struct ip *oip = mtod(n, struct ip *), *nip;
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
register unsigned oiphlen = oip->ip_hl << 2;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
register struct icmp *icp;
register struct mbuf *m;
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
unsigned icmplen, icmpelen, nlen;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
KASSERT((u_int)type <= ICMP_MAXTYPE, ("%s: illegal ICMP type", __func__));
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#ifdef ICMPPRINTFS
if (icmpprintfs)
GCC cleanup. Reviewed by: Submitted by: Obtained from:
1994-10-02 17:48:58 +00:00
printf("icmp_error(%p, %x, %d)\n", oip, type, code);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#endif
if (type != ICMP_REDIRECT)
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_error);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
/*
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
* Don't send error:
* if the original packet was encrypted.
* if not the first fragment of message.
* in response to a multicast or broadcast packet.
* if the old packet protocol was an ICMP error message.
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
*/
do not send icmp response if the original packet is encrypted. Obtained from: KAME MFC after: 1 week
2004-06-07 09:56:59 +00:00
if (n->m_flags & M_DECRYPTED)
goto freeit;
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
if (oip->ip_off & ~(IP_MF|IP_DF))
goto freeit;
if (n->m_flags & (M_BCAST|M_MCAST))
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
goto freeit;
if (oip->ip_p == IPPROTO_ICMP && type != ICMP_REDIRECT &&
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
n->m_len >= oiphlen + ICMP_MINLEN &&
!ICMP_INFOTYPE(((struct icmp *)((caddr_t)oip + oiphlen))->icmp_type)) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_oldicmp);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
goto freeit;
}
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
/* Drop if IP header plus 8 bytes is not contignous in first mbuf. */
if (oiphlen + 8 > n->m_len)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
goto freeit;
Add a sysctl to change to length of the quotation of the original packet in an ICMP reply. The minimum of 8 bytes is internally enforced. The maximum quotation is the remaining space in the reply mbuf. This option is added in response to the issues raised in I-D draft-gont-icmp-payload-00.txt. MFC after: 2 weeks Spnsored by: TCP/IP Optimizations Fundraise 2005
2005-08-21 15:09:07 +00:00
/*
* Calculate length to quote from original packet and
* prevent the ICMP mbuf from overflowing.
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
* Unfortunatly this is non-trivial since ip_forward()
* sends us truncated packets.
Add a sysctl to change to length of the quotation of the original packet in an ICMP reply. The minimum of 8 bytes is internally enforced. The maximum quotation is the remaining space in the reply mbuf. This option is added in response to the issues raised in I-D draft-gont-icmp-payload-00.txt. MFC after: 2 weeks Spnsored by: TCP/IP Optimizations Fundraise 2005
2005-08-21 15:09:07 +00:00
*/
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
nlen = m_length(n, NULL);
Always quote the entire TCP header when responding and allocate an mbuf cluster if needed. Fixes the TCP issues raised in I-D draft-gont-icmp-payload-00.txt. This aids in-the-wild debugging a lot and allows the receiver to do more elaborate checks on the validity of the response. MFC after: 2 weeks Sponsored by: TCP/IP Optimization Fundraise 2005
2005-08-22 14:12:18 +00:00
if (oip->ip_p == IPPROTO_TCP) {
struct tcphdr *th;
int tcphlen;
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
if (oiphlen + sizeof(struct tcphdr) > n->m_len &&
n->m_next == NULL)
goto stdreply;
if (n->m_len < oiphlen + sizeof(struct tcphdr) &&
((n = m_pullup(n, oiphlen + sizeof(struct tcphdr))) == NULL))
Always quote the entire TCP header when responding and allocate an mbuf cluster if needed. Fixes the TCP issues raised in I-D draft-gont-icmp-payload-00.txt. This aids in-the-wild debugging a lot and allows the receiver to do more elaborate checks on the validity of the response. MFC after: 2 weeks Sponsored by: TCP/IP Optimization Fundraise 2005
2005-08-22 14:12:18 +00:00
goto freeit;
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
th = (struct tcphdr *)((caddr_t)oip + oiphlen);
Always quote the entire TCP header when responding and allocate an mbuf cluster if needed. Fixes the TCP issues raised in I-D draft-gont-icmp-payload-00.txt. This aids in-the-wild debugging a lot and allows the receiver to do more elaborate checks on the validity of the response. MFC after: 2 weeks Sponsored by: TCP/IP Optimization Fundraise 2005
2005-08-22 14:12:18 +00:00
tcphlen = th->th_off << 2;
if (tcphlen < sizeof(struct tcphdr))
goto freeit;
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
if (oip->ip_len < oiphlen + tcphlen)
Always quote the entire TCP header when responding and allocate an mbuf cluster if needed. Fixes the TCP issues raised in I-D draft-gont-icmp-payload-00.txt. This aids in-the-wild debugging a lot and allows the receiver to do more elaborate checks on the validity of the response. MFC after: 2 weeks Sponsored by: TCP/IP Optimization Fundraise 2005
2005-08-22 14:12:18 +00:00
goto freeit;
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
if (oiphlen + tcphlen > n->m_len && n->m_next == NULL)
goto stdreply;
if (n->m_len < oiphlen + tcphlen &&
((n = m_pullup(n, oiphlen + tcphlen)) == NULL))
Always quote the entire TCP header when responding and allocate an mbuf cluster if needed. Fixes the TCP issues raised in I-D draft-gont-icmp-payload-00.txt. This aids in-the-wild debugging a lot and allows the receiver to do more elaborate checks on the validity of the response. MFC after: 2 weeks Sponsored by: TCP/IP Optimization Fundraise 2005
2005-08-22 14:12:18 +00:00
goto freeit;
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
icmpelen = max(tcphlen, min(V_icmp_quotelen, oip->ip_len - oiphlen));
Always quote the entire TCP header when responding and allocate an mbuf cluster if needed. Fixes the TCP issues raised in I-D draft-gont-icmp-payload-00.txt. This aids in-the-wild debugging a lot and allows the receiver to do more elaborate checks on the validity of the response. MFC after: 2 weeks Sponsored by: TCP/IP Optimization Fundraise 2005
2005-08-22 14:12:18 +00:00
} else
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
stdreply: icmpelen = max(8, min(V_icmp_quotelen, oip->ip_len - oiphlen));
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
icmplen = min(oiphlen + icmpelen, nlen);
It was possible for ip_forward() to supply to icmp_error() an IP header with ip_len in network byte order. For certain values of ip_len, this could cause icmp_error() to write beyond the end of an mbuf, causing mbuf free-list corruption. This problem was observed during generation of ICMP redirects. We now make quite sure that the copy of the IP header kept for icmp_error() is stored in a non-shared mbuf header so that it will not be modified by ip_output(). Also: - Calculate the correct number of bytes that need to be retained for icmp_error(), instead of assuming that 64 is enough (it's not). - In icmp_error(), use m_copydata instead of bcopy() to copy from the supplied mbuf chain, in case the first 8 bytes of IP payload are not stored directly after the IP header. - Sanity-check ip_len in icmp_error(), and panic if it is less than sizeof(struct ip). Incoming packets with bad ip_len values are discarded in ip_input(), so this should only be triggered by bugs in the code, not by bad packets. This patch results from code and suggestions from Ruslan, Bosko, Jonathan Lemon and Matt Dillon, with important testing by Mike Tancsa, who could reproduce this problem at will. Reported by: Mike Tancsa <mike@sentex.net> Reviewed by: ru, bmilekic, jlemon, dillon
2001-03-08 19:03:26 +00:00
if (icmplen < sizeof(struct ip))
Always quote the entire TCP header when responding and allocate an mbuf cluster if needed. Fixes the TCP issues raised in I-D draft-gont-icmp-payload-00.txt. This aids in-the-wild debugging a lot and allows the receiver to do more elaborate checks on the validity of the response. MFC after: 2 weeks Sponsored by: TCP/IP Optimization Fundraise 2005
2005-08-22 14:12:18 +00:00
goto freeit;
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
if (MHLEN > sizeof(struct ip) + ICMP_MINLEN + icmplen)
m = m_gethdr(M_DONTWAIT, MT_DATA);
else
m = m_getcl(M_DONTWAIT, MT_DATA, M_PKTHDR);
if (m == NULL)
goto freeit;
#ifdef MAC
Continue to move from generic network entry points in the TrustedBSD MAC Framework by moving from mac_mbuf_create_netlayer() to more specific entry points for specific network services: - mac_netinet_firewall_reply() to be used when replying to in-bound TCP segments in pf and ipfw (etc). - Rename mac_netinet_icmp_reply() to mac_netinet_icmp_replyinplace() and add mac_netinet_icmp_reply(), reflecting that in some cases we overwrite a label in place, but in others we apply the label to a new mbuf. Obtained from: TrustedBSD Project
2007-10-28 17:12:48 +00:00
mac_netinet_icmp_reply(n, m);
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
#endif
icmplen = min(icmplen, M_TRAILINGSPACE(m) - sizeof(struct ip) - ICMP_MINLEN);
m_align(m, ICMP_MINLEN + icmplen);
m->m_len = ICMP_MINLEN + icmplen;
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
/* XXX MRT make the outgoing packet use the same FIB
* that was associated with the incoming packet
*/
M_SETFIB(m, M_GETFIB(n));
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
icp = mtod(m, struct icmp *);
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_outhist[type]);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
icp->icmp_type = type;
if (type == ICMP_REDIRECT)
icp->icmp_gwaddr.s_addr = dest;
else {
icp->icmp_void = 0;
Remove trailing whitespace.
1995-05-30 08:16:23 +00:00
/*
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
* The following assignments assume an overlay with the
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
* just zeroed icmp_void field.
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
*/
if (type == ICMP_PARAMPROB) {
icp->icmp_pptr = code;
code = 0;
} else if (type == ICMP_UNREACH &&
Pass icmp_error() the MTU argument directly instead of an interface pointer. This simplifies a couple of uses and removes some XXX workarounds.
2005-05-04 13:09:19 +00:00
code == ICMP_UNREACH_NEEDFRAG && mtu) {
icp->icmp_nextmtu = htons(mtu);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
}
icp->icmp_code = code;
Fixed broken ICMP error generation, unified conversion of IP header fields between host and network byte order. The details: o icmp_error() now does not add IP header length. This fixes the problem when icmp_error() is called from ip_forward(). In this case the ip_len of the original IP datagram returned with ICMP error was wrong. o icmp_error() expects all three fields, ip_len, ip_id and ip_off in host byte order, so DTRT and convert these fields back to network byte order before sending a message. This fixes the problem described in PR 16240 and PR 20877 (ip_id field was returned in host byte order). o ip_ttl decrement operation in ip_forward() was moved down to make sure that it does not corrupt the copy of original IP datagram passed later to icmp_error(). o A copy of original IP datagram in ip_forward() was made a read-write, independent copy. This fixes the problem I first reported to Garrett Wollman and Bill Fenner and later put in audit trail of PR 16240: ip_output() (not always) converts fields of original datagram to network byte order, but because copy (mcopy) and its original (m) most likely share the same mbuf cluster, ip_output()'s manipulations on original also corrupted the copy. o ip_output() now expects all three fields, ip_len, ip_off and (what is significant) ip_id in host byte order. It was a headache for years that ip_id was handled differently. The only compatibility issue here is the raw IP socket interface with IP_HDRINCL socket option set and a non-zero ip_id field, but ip.4 manual page was unclear on whether in this case ip_id field should be in host or network byte order.
2000-09-01 12:33:03 +00:00
/*
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
* Copy the quotation into ICMP message and
* convert quoted IP header back to network representation.
Fixed broken ICMP error generation, unified conversion of IP header fields between host and network byte order. The details: o icmp_error() now does not add IP header length. This fixes the problem when icmp_error() is called from ip_forward(). In this case the ip_len of the original IP datagram returned with ICMP error was wrong. o icmp_error() expects all three fields, ip_len, ip_id and ip_off in host byte order, so DTRT and convert these fields back to network byte order before sending a message. This fixes the problem described in PR 16240 and PR 20877 (ip_id field was returned in host byte order). o ip_ttl decrement operation in ip_forward() was moved down to make sure that it does not corrupt the copy of original IP datagram passed later to icmp_error(). o A copy of original IP datagram in ip_forward() was made a read-write, independent copy. This fixes the problem I first reported to Garrett Wollman and Bill Fenner and later put in audit trail of PR 16240: ip_output() (not always) converts fields of original datagram to network byte order, but because copy (mcopy) and its original (m) most likely share the same mbuf cluster, ip_output()'s manipulations on original also corrupted the copy. o ip_output() now expects all three fields, ip_len, ip_off and (what is significant) ip_id in host byte order. It was a headache for years that ip_id was handled differently. The only compatibility issue here is the raw IP socket interface with IP_HDRINCL socket option set and a non-zero ip_id field, but ip.4 manual page was unclear on whether in this case ip_id field should be in host or network byte order.
2000-09-01 12:33:03 +00:00
*/
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
m_copydata(n, 0, icmplen, (caddr_t)&icp->icmp_ip);
nip = &icp->icmp_ip;
o Move NTOHL() and associated macros into <sys/param.h>. These are deprecated in favor of the POSIX-defined lowercase variants. o Change all occurrences of NTOHL() and associated marcros in the source tree to use the lowercase function variants. o Add missing license bits to sparc64's <machine/endian.h>. Approved by: jake o Clean up <machine/endian.h> files. o Remove unused __uint16_swap_uint32() from i386's <machine/endian.h>. o Remove prototypes for non-existent bswapXX() functions. o Include <machine/endian.h> in <arpa/inet.h> to define the POSIX-required ntohl() family of functions. o Do similar things to expose the ntohl() family in libstand, <netinet/in.h>, and <sys/param.h>. o Prepend underscores to the ntohl() family to help deal with complexities associated with having MD (asm and inline) versions, and having to prevent exposure of these functions in other headers that happen to make use of endian-specific defines. o Create weak aliases to the canonical function name to help deal with third-party software forgetting to include an appropriate header. o Remove some now unneeded pollution from <sys/types.h>. o Add missing <arpa/inet.h> includes in userland. Tested on: alpha, i386 Reviewed by: bde, jake, tmm
2002-02-18 20:35:27 +00:00
nip->ip_len = htons(nip->ip_len);
nip->ip_off = htons(nip->ip_off);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
/*
Rework icmp_error() to deal with truncated IP packets from ip_forward() when doing extended quoting in error messages. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-18 14:48:42 +00:00
* Set up ICMP message mbuf and copy old IP header (without options
* in front of ICMP message.
Define semantic of M_SKIP_FIREWALL more precisely, i.e. also pass associated icmp_error() packets. While here retire PACKET_TAG_PF_GENERATED (which served the same purpose) and use M_SKIP_FIREWALL in pf as well. This should speed up things a bit as we get rid of the tag allocations. Discussed with: juli
2004-07-17 05:10:06 +00:00
* If the original mbuf was meant to bypass the firewall, the error
* reply should bypass as well.
*/
m->m_flags |= n->m_flags & M_SKIP_FIREWALL;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
m->m_data -= sizeof(struct ip);
m->m_len += sizeof(struct ip);
m->m_pkthdr.len = m->m_len;
m->m_pkthdr.rcvif = n->m_pkthdr.rcvif;
nip = mtod(m, struct ip *);
bcopy((caddr_t)oip, (caddr_t)nip, sizeof(struct ip));
nip->ip_len = m->m_len;
Fix two instances of variant struct definitions in sys/netinet: Remove the never completed _IP_VHL version, it has not caught on anywhere and it would make us incompatible with other BSD netstacks to retain this version. Add a CTASSERT protecting sizeof(struct ip) == 20. Don't let the size of struct ipq depend on the IPDIVERT option. This is a functional no-op commit. Approved by: re
2002-10-20 22:52:07 +00:00
nip->ip_v = IPVERSION;
nip->ip_hl = 5;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
nip->ip_p = IPPROTO_ICMP;
nip->ip_tos = 0;
icmp_reflect(m);
freeit:
m_freem(n);
}
/*
* Process a received ICMP message.
*/
void
Move universally to ANSI C function declarations, with relatively consistent style(9)-ish layout.
2007-05-10 15:58:48 +00:00
icmp_input(struct mbuf *m, int off)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
Move global variables for icmp_input() to its stack. With SMP or preemption two CPUs can be in the same function at the same time and clobber each others variables. Remove register declaration from local variables. Reviewed by: sam (mentor)
2003-11-13 00:32:13 +00:00
struct icmp *icp;
struct in_ifaddr *ia;
struct ip *ip = mtod(m, struct ip *);
struct sockaddr_in icmpsrc, icmpdst, icmpgw;
IPSEC support in the kernel. pr_input() routines prototype is also changed to support IPSEC and IPV6 chained protocol headers. Reviewed by: freebsd-arch, cvs-committers Obtained from: KAME project
1999-12-22 19:13:38 +00:00
int hlen = off;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
int icmplen = ip->ip_len;
Move global variables for icmp_input() to its stack. With SMP or preemption two CPUs can be in the same function at the same time and clobber each others variables. Remove register declaration from local variables. Reviewed by: sam (mentor)
2003-11-13 00:32:13 +00:00
int i, code;
Remove __P.
2002-03-19 21:25:46 +00:00
void (*ctlfunc)(int, struct sockaddr *, void *);
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 fibnum;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
/*
* Locate icmp structure in mbuf, and check
* that not corrupted and of at least minimum length.
*/
#ifdef ICMPPRINTFS
Fix long-standing bug in ICMPPRINTFS code where NTOHL was used instead of ntohl for printing IP addresses, by instead substituting inet_ntoa() to produce human-readable output. Obtained from: 4.4-Lite-2
1995-08-29 17:49:04 +00:00
if (icmpprintfs) {
char buf[4 * sizeof "123"];
strcpy(buf, inet_ntoa(ip->ip_src));
printf("icmp_input from %s to %s, len %d\n",
buf, inet_ntoa(ip->ip_dst), icmplen);
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#endif
if (icmplen < ICMP_MINLEN) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_tooshort);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
goto freeit;
}
i = hlen + min(icmplen, ICMP_ADVLENMIN);
if (m->m_len < i && (m = m_pullup(m, i)) == 0) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_tooshort);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
return;
}
ip = mtod(m, struct ip *);
m->m_len -= hlen;
m->m_data += hlen;
icp = mtod(m, struct icmp *);
if (in_cksum(m, icmplen)) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_checksum);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
goto freeit;
}
m->m_len += hlen;
m->m_data -= hlen;
IPSEC support in the kernel. pr_input() routines prototype is also changed to support IPSEC and IPV6 chained protocol headers. Reviewed by: freebsd-arch, cvs-committers Obtained from: KAME project
1999-12-22 19:13:38 +00:00
if (m->m_pkthdr.rcvif && m->m_pkthdr.rcvif->if_type == IFT_FAITH) {
/*
* Deliver very specific ICMP type only.
*/
switch (icp->icmp_type) {
case ICMP_UNREACH:
case ICMP_TIMXCEED:
break;
default:
goto freeit;
}
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("icmp_input, type %d code %d\n", icp->icmp_type,
icp->icmp_code);
#endif
ICMP messages received from broken hosts which reply to multicast packets were mistakenly delivered, rather than getting thrown out, which caused substantial lossage. Submitted by: Bill Fenner <fenner@parc.xerox.com>
1995-07-10 16:16:00 +00:00
/*
* Message type specific processing.
*/
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
if (icp->icmp_type > ICMP_MAXTYPE)
goto raw;
Move global variables for icmp_input() to its stack. With SMP or preemption two CPUs can be in the same function at the same time and clobber each others variables. Remove register declaration from local variables. Reviewed by: sam (mentor)
2003-11-13 00:32:13 +00:00
/* Initialize */
bzero(&icmpsrc, sizeof(icmpsrc));
icmpsrc.sin_len = sizeof(struct sockaddr_in);
icmpsrc.sin_family = AF_INET;
bzero(&icmpdst, sizeof(icmpdst));
icmpdst.sin_len = sizeof(struct sockaddr_in);
icmpdst.sin_family = AF_INET;
bzero(&icmpgw, sizeof(icmpgw));
icmpgw.sin_len = sizeof(struct sockaddr_in);
icmpgw.sin_family = AF_INET;
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_inhist[icp->icmp_type]);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
code = icp->icmp_code;
switch (icp->icmp_type) {
case ICMP_UNREACH:
switch (code) {
case ICMP_UNREACH_NET:
case ICMP_UNREACH_HOST:
case ICMP_UNREACH_SRCFAIL:
Allow ICMP unreachables which map into PRC_UNREACH_ADMIN_PROHIB to reset TCP connections which are in the SYN_SENT state, if the sequence number in the echoed ICMP reply is correct. This behavior can be controlled by the sysctl net.inet.tcp.icmp_may_rst. Currently, only subtypes 2,3,10,11,12 are treated as such (port, protocol and administrative unreachables). Assocaiate an error code with these resets which is reported to the user application: ENETRESET. Disallow resetting TCP sessions which are not in a SYN_SENT state. Reviewed by: jesper, -net
2001-02-23 20:51:46 +00:00
case ICMP_UNREACH_NET_UNKNOWN:
case ICMP_UNREACH_HOST_UNKNOWN:
case ICMP_UNREACH_ISOLATED:
case ICMP_UNREACH_TOSNET:
case ICMP_UNREACH_TOSHOST:
case ICMP_UNREACH_HOST_PRECEDENCE:
case ICMP_UNREACH_PRECEDENCE_CUTOFF:
code = PRC_UNREACH_NET;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
case ICMP_UNREACH_NEEDFRAG:
code = PRC_MSGSIZE;
break;
Remove trailing whitespace.
1995-05-30 08:16:23 +00:00
Allow ICMP unreachables which map into PRC_UNREACH_ADMIN_PROHIB to reset TCP connections which are in the SYN_SENT state, if the sequence number in the echoed ICMP reply is correct. This behavior can be controlled by the sysctl net.inet.tcp.icmp_may_rst. Currently, only subtypes 2,3,10,11,12 are treated as such (port, protocol and administrative unreachables). Assocaiate an error code with these resets which is reported to the user application: ENETRESET. Disallow resetting TCP sessions which are not in a SYN_SENT state. Reviewed by: jesper, -net
2001-02-23 20:51:46 +00:00
/*
* RFC 1122, Sections 3.2.2.1 and 4.2.3.9.
* Treat subcodes 2,3 as immediate RST
*/
case ICMP_UNREACH_PROTOCOL:
case ICMP_UNREACH_PORT:
MFC candidate. Change code from PRC_UNREACH_ADMIN_PROHIB to PRC_UNREACH_PORT for ICMP_UNREACH_PROTOCOL and ICMP_UNREACH_PORT And let TCP treat PRC_UNREACH_PORT like PRC_UNREACH_ADMIN_PROHIB This should fix the case where port unreachables for udp returned ENETRESET instead of ECONNREFUSED Problem found by: Bill Fenner <fenner@research.att.com> Reviewed by: jlemon
2001-03-28 14:13:19 +00:00
code = PRC_UNREACH_PORT;
Remove unneeded loop increment in src/sys/netinet/in_pcb.c:in_pcbnotify Add new PRC_UNREACH_ADMIN_PROHIB in sys/sys/protosw.h Remove condition on TCP in src/sys/netinet/ip_icmp.c:icmp_input In src/sys/netinet/ip_icmp.c:icmp_input set code = PRC_UNREACH_ADMIN_PROHIB or PRC_UNREACH_HOST for all unreachables except ICMP_UNREACH_NEEDFRAG Rename sysctl icmp_admin_prohib_like_rst to icmp_unreach_like_rst to reflect the fact that we also react on ICMP unreachables that are not administrative prohibited. Also update the comments to reflect this. In sys/netinet/tcp_subr.c:tcp_ctlinput add code to treat PRC_UNREACH_ADMIN_PROHIB and PRC_UNREACH_HOST different. PR: 23986 Submitted by: Jesper Skriver <jesper@skriver.dk>
2001-02-18 09:34:55 +00:00
break;
We currently does not react to ICMP administratively prohibited messages send by routers when they deny our traffic, this causes a timeout when trying to connect to TCP ports/services on a remote host, which is blocked by routers or firewalls. rfc1122 (Requirements for Internet Hosts) section 3.2.2.1 actually requi re that we treat such a message for a TCP session, that we treat it like if we had recieved a RST. quote begin. A Destination Unreachable message that is received MUST be reported to the transport layer. The transport layer SHOULD use the information appropriately; for example, see Sections 4.1.3.3, 4.2.3.9, and 4.2.4 below. A transport protocol that has its own mechanism for notifying the sender that a port is unreachable (e.g., TCP, which sends RST segments) MUST nevertheless accept an ICMP Port Unreachable for the same purpose. quote end. I've written a small extension that implement this, it also create a sysctl "net.inet.tcp.icmp_admin_prohib_like_rst" to control if this new behaviour is activated. When it's activated (set to 1) we'll treat a ICMP administratively prohibited message (icmp type 3 code 9, 10 and 13) for a TCP sessions, as if we recived a TCP RST, but only if the TCP session is in SYN_SENT state. The reason for only reacting when in SYN_SENT state, is that this will solve the problem, and at the same time minimize the risk of this being abused. I suggest that we enable this new behaviour by default, but it would be a change of current behaviour, so if people prefer to leave it disabled by default, at least for now, this would be ok for me, the attached diff actually have the sysctl set to 0 by default. PR: 23086 Submitted by: Jesper Skriver <jesper@skriver.dk>
2000-12-16 19:42:06 +00:00
Allow ICMP unreachables which map into PRC_UNREACH_ADMIN_PROHIB to reset TCP connections which are in the SYN_SENT state, if the sequence number in the echoed ICMP reply is correct. This behavior can be controlled by the sysctl net.inet.tcp.icmp_may_rst. Currently, only subtypes 2,3,10,11,12 are treated as such (port, protocol and administrative unreachables). Assocaiate an error code with these resets which is reported to the user application: ENETRESET. Disallow resetting TCP sessions which are not in a SYN_SENT state. Reviewed by: jesper, -net
2001-02-23 20:51:46 +00:00
case ICMP_UNREACH_NET_PROHIB:
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
case ICMP_UNREACH_HOST_PROHIB:
Handle ICMP codes defined in RFC1812 more appropriately
1996-09-20 08:23:54 +00:00
case ICMP_UNREACH_FILTER_PROHIB:
Remove unneeded loop increment in src/sys/netinet/in_pcb.c:in_pcbnotify Add new PRC_UNREACH_ADMIN_PROHIB in sys/sys/protosw.h Remove condition on TCP in src/sys/netinet/ip_icmp.c:icmp_input In src/sys/netinet/ip_icmp.c:icmp_input set code = PRC_UNREACH_ADMIN_PROHIB or PRC_UNREACH_HOST for all unreachables except ICMP_UNREACH_NEEDFRAG Rename sysctl icmp_admin_prohib_like_rst to icmp_unreach_like_rst to reflect the fact that we also react on ICMP unreachables that are not administrative prohibited. Also update the comments to reflect this. In sys/netinet/tcp_subr.c:tcp_ctlinput add code to treat PRC_UNREACH_ADMIN_PROHIB and PRC_UNREACH_HOST different. PR: 23986 Submitted by: Jesper Skriver <jesper@skriver.dk>
2001-02-18 09:34:55 +00:00
code = PRC_UNREACH_ADMIN_PROHIB;
break;
We currently does not react to ICMP administratively prohibited messages send by routers when they deny our traffic, this causes a timeout when trying to connect to TCP ports/services on a remote host, which is blocked by routers or firewalls. rfc1122 (Requirements for Internet Hosts) section 3.2.2.1 actually requi re that we treat such a message for a TCP session, that we treat it like if we had recieved a RST. quote begin. A Destination Unreachable message that is received MUST be reported to the transport layer. The transport layer SHOULD use the information appropriately; for example, see Sections 4.1.3.3, 4.2.3.9, and 4.2.4 below. A transport protocol that has its own mechanism for notifying the sender that a port is unreachable (e.g., TCP, which sends RST segments) MUST nevertheless accept an ICMP Port Unreachable for the same purpose. quote end. I've written a small extension that implement this, it also create a sysctl "net.inet.tcp.icmp_admin_prohib_like_rst" to control if this new behaviour is activated. When it's activated (set to 1) we'll treat a ICMP administratively prohibited message (icmp type 3 code 9, 10 and 13) for a TCP sessions, as if we recived a TCP RST, but only if the TCP session is in SYN_SENT state. The reason for only reacting when in SYN_SENT state, is that this will solve the problem, and at the same time minimize the risk of this being abused. I suggest that we enable this new behaviour by default, but it would be a change of current behaviour, so if people prefer to leave it disabled by default, at least for now, this would be ok for me, the attached diff actually have the sysctl set to 0 by default. PR: 23086 Submitted by: Jesper Skriver <jesper@skriver.dk>
2000-12-16 19:42:06 +00:00
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
default:
goto badcode;
}
goto deliver;
case ICMP_TIMXCEED:
if (code > 1)
goto badcode;
code += PRC_TIMXCEED_INTRANS;
goto deliver;
case ICMP_PARAMPROB:
if (code > 1)
goto badcode;
code = PRC_PARAMPROB;
goto deliver;
case ICMP_SOURCEQUENCH:
if (code)
goto badcode;
code = PRC_QUENCH;
deliver:
/*
* Problem with datagram; advise higher level routines.
*/
if (icmplen < ICMP_ADVLENMIN || icmplen < ICMP_ADVLEN(icp) ||
Fix two instances of variant struct definitions in sys/netinet: Remove the never completed _IP_VHL version, it has not caught on anywhere and it would make us incompatible with other BSD netstacks to retain this version. Add a CTASSERT protecting sizeof(struct ip) == 20. Don't let the size of struct ipq depend on the IPDIVERT option. This is a functional no-op commit. Approved by: re
2002-10-20 22:52:07 +00:00
icp->icmp_ip.ip_hl < (sizeof(struct ip) >> 2)) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_badlen);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
goto freeit;
}
o Move NTOHL() and associated macros into <sys/param.h>. These are deprecated in favor of the POSIX-defined lowercase variants. o Change all occurrences of NTOHL() and associated marcros in the source tree to use the lowercase function variants. o Add missing license bits to sparc64's <machine/endian.h>. Approved by: jake o Clean up <machine/endian.h> files. o Remove unused __uint16_swap_uint32() from i386's <machine/endian.h>. o Remove prototypes for non-existent bswapXX() functions. o Include <machine/endian.h> in <arpa/inet.h> to define the POSIX-required ntohl() family of functions. o Do similar things to expose the ntohl() family in libstand, <netinet/in.h>, and <sys/param.h>. o Prepend underscores to the ntohl() family to help deal with complexities associated with having MD (asm and inline) versions, and having to prevent exposure of these functions in other headers that happen to make use of endian-specific defines. o Create weak aliases to the canonical function name to help deal with third-party software forgetting to include an appropriate header. o Remove some now unneeded pollution from <sys/types.h>. o Add missing <arpa/inet.h> includes in userland. Tested on: alpha, i386 Reviewed by: bde, jake, tmm
2002-02-18 20:35:27 +00:00
icp->icmp_ip.ip_len = ntohs(icp->icmp_ip.ip_len);
ICMP messages received from broken hosts which reply to multicast packets were mistakenly delivered, rather than getting thrown out, which caused substantial lossage. Submitted by: Bill Fenner <fenner@parc.xerox.com>
1995-07-10 16:16:00 +00:00
/* Discard ICMP's in response to multicast packets */
if (IN_MULTICAST(ntohl(icp->icmp_ip.ip_dst.s_addr)))
goto badcode;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("deliver to protocol %d\n", icp->icmp_ip.ip_p);
#endif
icmpsrc.sin_addr = icp->icmp_ip.ip_dst;
IPSEC support in the kernel. pr_input() routines prototype is also changed to support IPSEC and IPV6 chained protocol headers. Reviewed by: freebsd-arch, cvs-committers Obtained from: KAME project
1999-12-22 19:13:38 +00:00
/*
* XXX if the packet contains [IPv4 AH TCP], we can't make a
* notification to TCP layer.
*/
GCC cleanup. Reviewed by: Submitted by: Obtained from:
1994-10-02 17:48:58 +00:00
ctlfunc = inetsw[ip_protox[icp->icmp_ip.ip_p]].pr_ctlinput;
if (ctlfunc)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
(*ctlfunc)(code, (struct sockaddr *)&icmpsrc,
Uniformized pr_ctlinput protosw functions. The third arg is now `void *' instead of caddr_t and it isn't optional (it never was). Most of the netipx (and netns) pr_ctlinput functions abuse the second arg instead of using the third arg but fixing this is beyond the scope of this round of changes.
1995-12-16 02:14:44 +00:00
(void *)&icp->icmp_ip);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
badcode:
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_badcode);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
case ICMP_ECHO:
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (!V_icmpbmcastecho
Fixed logic in the test to drop ICMP echo and timestamp packets when net.inet.ip.icmp.bmcastecho = 0 by removing the extra check for the address being a multicast address. The test now relies on the link layer flags that indicate it was received via multicast. The previous logic was broken and replied to ICMP echo/timestamp broadcasts even when the sysctl option disallowed them. Reviewed by: wollman
1998-05-26 11:34:30 +00:00
&& (m->m_flags & (M_MCAST | M_BCAST)) != 0) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_bmcastecho);
Configurably don't reply to broadcast or multicast echos. There are still potential problems with other automatic-reply ICMPs, but some of them may depend on broadcast/multicast to operate. (This code can simply be moved to the `reflect' label to generalize it.)
1997-08-25 01:25:31 +00:00
break;
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
icp->icmp_type = ICMP_ECHOREPLY;
Clean up RST ratelimiting. Previously, ratelimiting occured before tests were performed to determine if the received packet should be reset. This created erroneous ratelimiting and false alarms in some cases. The code has now been reorganized so that the checks for validity come before the call to badport_bandlim. Additionally, a few changes in the symbolic names of the bandlim types have been made, as well as a clarification of exactly which type each RST case falls under. Submitted by: Mike Silbersack <silby@silby.com>
2001-02-11 07:39:51 +00:00
if (badport_bandlim(BANDLIM_ICMP_ECHO) < 0)
Change the following: 1. ICMP ECHO and TSTAMP replies are now rate limited. 2. RSTs generated due to packets sent to open and unopen ports are now limited by seperate counters. 3. Each rate limiting queue now has its own description, as follows: Limiting icmp unreach response from 439 to 200 packets per second Limiting closed port RST response from 283 to 200 packets per second Limiting open port RST response from 18724 to 200 packets per second Limiting icmp ping response from 211 to 200 packets per second Limiting icmp tstamp response from 394 to 200 packets per second Submitted by: Mike Silbersack <silby@silby.com>
2000-12-15 21:45:49 +00:00
goto freeit;
else
goto reflect;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
case ICMP_TSTAMP:
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (!V_icmpbmcastecho
Fixed logic in the test to drop ICMP echo and timestamp packets when net.inet.ip.icmp.bmcastecho = 0 by removing the extra check for the address being a multicast address. The test now relies on the link layer flags that indicate it was received via multicast. The previous logic was broken and replied to ICMP echo/timestamp broadcasts even when the sysctl option disallowed them. Reviewed by: wollman
1998-05-26 11:34:30 +00:00
&& (m->m_flags & (M_MCAST | M_BCAST)) != 0) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_bmcasttstamp);
ICMP Timestamp Request messages could have harbored the same sort of problem as Echo Requests when broad/multicast. When multicast echo responses are disabled, also do the same for timestamp responses.
1997-08-25 16:29:27 +00:00
break;
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
if (icmplen < ICMP_TSLEN) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_badlen);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
}
icp->icmp_type = ICMP_TSTAMPREPLY;
icp->icmp_rtime = iptime();
icp->icmp_ttime = icp->icmp_rtime; /* bogus, do later! */
Clean up RST ratelimiting. Previously, ratelimiting occured before tests were performed to determine if the received packet should be reset. This created erroneous ratelimiting and false alarms in some cases. The code has now been reorganized so that the checks for validity come before the call to badport_bandlim. Additionally, a few changes in the symbolic names of the bandlim types have been made, as well as a clarification of exactly which type each RST case falls under. Submitted by: Mike Silbersack <silby@silby.com>
2001-02-11 07:39:51 +00:00
if (badport_bandlim(BANDLIM_ICMP_TSTAMP) < 0)
Change the following: 1. ICMP ECHO and TSTAMP replies are now rate limited. 2. RSTs generated due to packets sent to open and unopen ports are now limited by seperate counters. 3. Each rate limiting queue now has its own description, as follows: Limiting icmp unreach response from 439 to 200 packets per second Limiting closed port RST response from 283 to 200 packets per second Limiting open port RST response from 18724 to 200 packets per second Limiting icmp ping response from 211 to 200 packets per second Limiting icmp tstamp response from 394 to 200 packets per second Submitted by: Mike Silbersack <silby@silby.com>
2000-12-15 21:45:49 +00:00
goto freeit;
else
goto reflect;
Remove trailing whitespace.
1995-05-30 08:16:23 +00:00
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
case ICMP_MASKREQ:
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (V_icmpmaskrepl == 0)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
/*
* We are not able to respond with all ones broadcast
* unless we receive it over a point-to-point interface.
*/
if (icmplen < ICMP_MASKLEN)
break;
switch (ip->ip_dst.s_addr) {
case INADDR_BROADCAST:
case INADDR_ANY:
icmpdst.sin_addr = ip->ip_src;
break;
default:
icmpdst.sin_addr = ip->ip_dst;
}
ia = (struct in_ifaddr *)ifaof_ifpforaddr(
(struct sockaddr *)&icmpdst, m->m_pkthdr.rcvif);
Modify most routines returning 'struct ifaddr *' to return references rather than pointers, requiring callers to properly dispose of those references. The following routines now return references: ifaddr_byindex ifa_ifwithaddr ifa_ifwithbroadaddr ifa_ifwithdstaddr ifa_ifwithnet ifaof_ifpforaddr ifa_ifwithroute ifa_ifwithroute_fib rt_getifa rt_getifa_fib IFP_TO_IA ip_rtaddr in6_ifawithifp in6ifa_ifpforlinklocal in6ifa_ifpwithaddr in6_ifadd carp_iamatch6 ip6_getdstifaddr Remove unused macro which didn't have required referencing: IFP_TO_IA6 This closes many small races in which changes to interface or address lists while an ifaddr was in use could lead to use of freed memory (etc). In a few cases, add missing if_addr_list locking required to safely acquire references. Because of a lack of deep copying support, we accept a race in which an in6_ifaddr pointed to by mbuf tags and extracted with ip6_getdstifaddr() doesn't hold a reference while in transmit. Once we have mbuf tag deep copy support, this can be fixed. Reviewed by: bz Obtained from: Apple, Inc. (portions) MFC after: 6 weeks (portions)
2009-06-23 20:19:09 +00:00
if (ia == NULL)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
Modify most routines returning 'struct ifaddr *' to return references rather than pointers, requiring callers to properly dispose of those references. The following routines now return references: ifaddr_byindex ifa_ifwithaddr ifa_ifwithbroadaddr ifa_ifwithdstaddr ifa_ifwithnet ifaof_ifpforaddr ifa_ifwithroute ifa_ifwithroute_fib rt_getifa rt_getifa_fib IFP_TO_IA ip_rtaddr in6_ifawithifp in6ifa_ifpforlinklocal in6ifa_ifpwithaddr in6_ifadd carp_iamatch6 ip6_getdstifaddr Remove unused macro which didn't have required referencing: IFP_TO_IA6 This closes many small races in which changes to interface or address lists while an ifaddr was in use could lead to use of freed memory (etc). In a few cases, add missing if_addr_list locking required to safely acquire references. Because of a lack of deep copying support, we accept a race in which an in6_ifaddr pointed to by mbuf tags and extracted with ip6_getdstifaddr() doesn't hold a reference while in transmit. Once we have mbuf tag deep copy support, this can be fixed. Reviewed by: bz Obtained from: Apple, Inc. (portions) MFC after: 6 weeks (portions)
2009-06-23 20:19:09 +00:00
if (ia->ia_ifp == NULL) {
ifa_free(&ia->ia_ifa);
Fix two cases where ia->ia_ifp could be NULL.
1996-04-02 12:26:10 +00:00
break;
Modify most routines returning 'struct ifaddr *' to return references rather than pointers, requiring callers to properly dispose of those references. The following routines now return references: ifaddr_byindex ifa_ifwithaddr ifa_ifwithbroadaddr ifa_ifwithdstaddr ifa_ifwithnet ifaof_ifpforaddr ifa_ifwithroute ifa_ifwithroute_fib rt_getifa rt_getifa_fib IFP_TO_IA ip_rtaddr in6_ifawithifp in6ifa_ifpforlinklocal in6ifa_ifpwithaddr in6_ifadd carp_iamatch6 ip6_getdstifaddr Remove unused macro which didn't have required referencing: IFP_TO_IA6 This closes many small races in which changes to interface or address lists while an ifaddr was in use could lead to use of freed memory (etc). In a few cases, add missing if_addr_list locking required to safely acquire references. Because of a lack of deep copying support, we accept a race in which an in6_ifaddr pointed to by mbuf tags and extracted with ip6_getdstifaddr() doesn't hold a reference while in transmit. Once we have mbuf tag deep copy support, this can be fixed. Reviewed by: bz Obtained from: Apple, Inc. (portions) MFC after: 6 weeks (portions)
2009-06-23 20:19:09 +00:00
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
icp->icmp_type = ICMP_MASKREPLY;
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (V_icmpmaskfake == 0)
Add a sysctl node allowing the specification of an address mask to use when replying to ICMP Address Mask Request packets.
2003-03-21 15:43:06 +00:00
icp->icmp_mask = ia->ia_sockmask.sin_addr.s_addr;
else
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
icp->icmp_mask = V_icmpmaskfake;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
if (ip->ip_src.s_addr == 0) {
if (ia->ia_ifp->if_flags & IFF_BROADCAST)
ip->ip_src = satosin(&ia->ia_broadaddr)->sin_addr;
else if (ia->ia_ifp->if_flags & IFF_POINTOPOINT)
ip->ip_src = satosin(&ia->ia_dstaddr)->sin_addr;
}
Modify most routines returning 'struct ifaddr *' to return references rather than pointers, requiring callers to properly dispose of those references. The following routines now return references: ifaddr_byindex ifa_ifwithaddr ifa_ifwithbroadaddr ifa_ifwithdstaddr ifa_ifwithnet ifaof_ifpforaddr ifa_ifwithroute ifa_ifwithroute_fib rt_getifa rt_getifa_fib IFP_TO_IA ip_rtaddr in6_ifawithifp in6ifa_ifpforlinklocal in6ifa_ifpwithaddr in6_ifadd carp_iamatch6 ip6_getdstifaddr Remove unused macro which didn't have required referencing: IFP_TO_IA6 This closes many small races in which changes to interface or address lists while an ifaddr was in use could lead to use of freed memory (etc). In a few cases, add missing if_addr_list locking required to safely acquire references. Because of a lack of deep copying support, we accept a race in which an in6_ifaddr pointed to by mbuf tags and extracted with ip6_getdstifaddr() doesn't hold a reference while in transmit. Once we have mbuf tag deep copy support, this can be fixed. Reviewed by: bz Obtained from: Apple, Inc. (portions) MFC after: 6 weeks (portions)
2009-06-23 20:19:09 +00:00
ifa_free(&ia->ia_ifa);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
reflect:
ip->ip_len += hlen; /* since ip_input deducts this */
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_reflect);
ICMPSTAT_INC(icps_outhist[icp->icmp_type]);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
icmp_reflect(m);
return;
case ICMP_REDIRECT:
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (V_log_redirect) {
Add net.inet.icmp.log_redirect and net.inet.icmp.drop_redirect, for respectively logging and dropping ICMP REDIRECT packets. Note that there is no rate limiting on the log messages, so log_redirect should be used with caution (preferrably only for debugging purposes).
1999-08-10 09:45:33 +00:00
u_long src, dst, gw;
src = ntohl(ip->ip_src.s_addr);
dst = ntohl(icp->icmp_ip.ip_dst.s_addr);
gw = ntohl(icp->icmp_gwaddr.s_addr);
printf("icmp redirect from %d.%d.%d.%d: "
"%d.%d.%d.%d => %d.%d.%d.%d\n",
(int)(src >> 24), (int)((src >> 16) & 0xff),
(int)((src >> 8) & 0xff), (int)(src & 0xff),
(int)(dst >> 24), (int)((dst >> 16) & 0xff),
(int)((dst >> 8) & 0xff), (int)(dst & 0xff),
(int)(gw >> 24), (int)((gw >> 16) & 0xff),
(int)((gw >> 8) & 0xff), (int)(gw & 0xff));
}
According to RFC1812 we have to ignore ICMP redirects when we are acting as router (ipforwarding enabled). This doesn't fix the problem that host routes from ICMP redirects are never removed from the kernel routing table but removes the problem for machines doing packet forwarding. Reviewed by: sam (mentor)
2004-01-06 23:20:07 +00:00
/*
* RFC1812 says we must ignore ICMP redirects if we
* are acting as router.
*/
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (V_drop_redirect || V_ipforwarding)
Add net.inet.icmp.log_redirect and net.inet.icmp.drop_redirect, for respectively logging and dropping ICMP REDIRECT packets. Note that there is no rate limiting on the log messages, so log_redirect should be used with caution (preferrably only for debugging purposes).
1999-08-10 09:45:33 +00:00
break;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
if (code > 3)
goto badcode;
if (icmplen < ICMP_ADVLENMIN || icmplen < ICMP_ADVLEN(icp) ||
Fix two instances of variant struct definitions in sys/netinet: Remove the never completed _IP_VHL version, it has not caught on anywhere and it would make us incompatible with other BSD netstacks to retain this version. Add a CTASSERT protecting sizeof(struct ip) == 20. Don't let the size of struct ipq depend on the IPDIVERT option. This is a functional no-op commit. Approved by: re
2002-10-20 22:52:07 +00:00
icp->icmp_ip.ip_hl < (sizeof(struct ip) >> 2)) {
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_badlen);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
}
/*
* Short circuit routing redirects to force
* immediate change in the kernel's routing
* tables. The message is also handed to anyone
* listening on a raw socket (e.g. the routing
* daemon for use in updating its tables).
*/
icmpgw.sin_addr = ip->ip_src;
icmpdst.sin_addr = icp->icmp_gwaddr;
#ifdef ICMPPRINTFS
Fix long-standing bug in ICMPPRINTFS code where NTOHL was used instead of ntohl for printing IP addresses, by instead substituting inet_ntoa() to produce human-readable output. Obtained from: 4.4-Lite-2
1995-08-29 17:49:04 +00:00
if (icmpprintfs) {
char buf[4 * sizeof "123"];
strcpy(buf, inet_ntoa(icp->icmp_ip.ip_dst));
printf("redirect dst %s to %s\n",
buf, inet_ntoa(icp->icmp_gwaddr));
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#endif
icmpsrc.sin_addr = icp->icmp_ip.ip_dst;
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
for ( fibnum = 0; fibnum < rt_numfibs; fibnum++) {
in_rtredirect((struct sockaddr *)&icmpsrc,
(struct sockaddr *)&icmpdst,
(struct sockaddr *)0, RTF_GATEWAY | RTF_HOST,
(struct sockaddr *)&icmpgw, fibnum);
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
pfctlinput(PRC_REDIRECT_HOST, (struct sockaddr *)&icmpsrc);
Commit the change from FAST_IPSEC to IPSEC. The FAST_IPSEC option is now deprecated, as well as the KAME IPsec code. What was FAST_IPSEC is now IPSEC. Approved by: re Sponsored by: Secure Computing
2007-07-03 12:13:45 +00:00
#ifdef IPSEC
IPSEC support in the kernel. pr_input() routines prototype is also changed to support IPSEC and IPV6 chained protocol headers. Reviewed by: freebsd-arch, cvs-committers Obtained from: KAME project
1999-12-22 19:13:38 +00:00
key_sa_routechange((struct sockaddr *)&icmpsrc);
#endif
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
/*
* No kernel processing for the following;
* just fall through to send to raw listener.
*/
case ICMP_ECHOREPLY:
case ICMP_ROUTERADVERT:
case ICMP_ROUTERSOLICIT:
case ICMP_TSTAMPREPLY:
case ICMP_IREQREPLY:
case ICMP_MASKREPLY:
default:
break;
}
raw:
Patches from Keiichi SHIMA <keiichi@iij.ad.jp> to make ip use the standard protosw structure again. Obtained from: Well, KAME I guess.
2001-09-03 20:03:55 +00:00
rip_input(m, off);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
return;
freeit:
m_freem(m);
}
/*
* Reflect the ip packet back to the source
*/
New style sysctl & staticize alot of stuff.
1995-11-14 20:34:56 +00:00
static void
Move universally to ANSI C function declarations, with relatively consistent style(9)-ish layout.
2007-05-10 15:58:48 +00:00
icmp_reflect(struct mbuf *m)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
Add a hash table that contains the list of internet addresses, and use this in place of the in_ifaddr list when appropriate. This improves performance on hosts which have a large number of IP aliases.
2001-09-29 04:34:11 +00:00
struct ip *ip = mtod(m, struct ip *);
struct ifaddr *ifa;
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
struct ifnet *ifp;
Add a hash table that contains the list of internet addresses, and use this in place of the in_ifaddr list when appropriate. This improves performance on hosts which have a large number of IP aliases.
2001-09-29 04:34:11 +00:00
struct in_ifaddr *ia;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
struct in_addr t;
Add and move declarations to fix all of the warnings from `gcc -Wimplicit' (except in netccitt, netiso and netns) and most of the warnings from `gcc -Wnested-externs'. Fix all the bugs found. There were no serious ones.
1995-03-16 18:17:34 +00:00
struct mbuf *opts = 0;
Fix two instances of variant struct definitions in sys/netinet: Remove the never completed _IP_VHL version, it has not caught on anywhere and it would make us incompatible with other BSD netstacks to retain this version. Add a CTASSERT protecting sizeof(struct ip) == 20. Don't let the size of struct ipq depend on the IPDIVERT option. This is a functional no-op commit. Approved by: re
2002-10-20 22:52:07 +00:00
int optlen = (ip->ip_hl << 2) - sizeof(struct ip);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
Clean up the code that checks the types of address so that it is done by understandable macros. Fix the bug that prevented the system from responding on interfaces with link local addresses assigned. PR: 120958 Submitted by: James Snow <snow at teardrop.org> MFC after: 2 weeks
2008-04-17 12:50:42 +00:00
if (IN_MULTICAST(ntohl(ip->ip_src.s_addr)) ||
IN_EXPERIMENTAL(ntohl(ip->ip_src.s_addr)) ||
IN_ZERONET(ntohl(ip->ip_src.s_addr)) ) {
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
m_freem(m); /* Bad return address */
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_badaddr);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
goto done; /* Ip_output() will check for broadcast */
}
Clean up the code that checks the types of address so that it is done by understandable macros. Fix the bug that prevented the system from responding on interfaces with link local addresses assigned. PR: 120958 Submitted by: James Snow <snow at teardrop.org> MFC after: 2 weeks
2008-04-17 12:50:42 +00:00
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
t = ip->ip_dst;
ip->ip_dst = ip->ip_src;
More verbose description of the source ip address selection for ICMP replies. Reviewed by: bms
2004-02-02 22:17:09 +00:00
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
/*
More verbose description of the source ip address selection for ICMP replies. Reviewed by: bms
2004-02-02 22:17:09 +00:00
* Source selection for ICMP replies:
*
* If the incoming packet was addressed directly to one of our
* own addresses, use dst as the src for the reply.
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
*/
Add a new global rwlock, in_ifaddr_lock, which will synchronize use of the in_ifaddrhead and INADDR_HASH address lists. Previously, these lists were used unsynchronized as they were effectively never changed in steady state, but we've seen increasing reports of writer-writer races on very busy VPN servers as core count has gone up (and similar configurations where address lists change frequently and concurrently). For the time being, use rwlocks rather than rmlocks in order to take advantage of their better lock debugging support. As a result, we don't enable ip_input()'s read-locking of INADDR_HASH until an rmlock conversion is complete and a performance analysis has been done. This means that one class of reader-writer races still exists. MFC after: 6 weeks Reviewed by: bz
2009-06-25 11:52:33 +00:00
IN_IFADDR_RLOCK();
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
LIST_FOREACH(ia, INADDR_HASH(t.s_addr), ia_hash) {
if (t.s_addr == IA_SIN(ia)->sin_addr.s_addr) {
t = IA_SIN(ia)->sin_addr;
Add a new global rwlock, in_ifaddr_lock, which will synchronize use of the in_ifaddrhead and INADDR_HASH address lists. Previously, these lists were used unsynchronized as they were effectively never changed in steady state, but we've seen increasing reports of writer-writer races on very busy VPN servers as core count has gone up (and similar configurations where address lists change frequently and concurrently). For the time being, use rwlocks rather than rmlocks in order to take advantage of their better lock debugging support. As a result, we don't enable ip_input()'s read-locking of INADDR_HASH until an rmlock conversion is complete and a performance analysis has been done. This means that one class of reader-writer races still exists. MFC after: 6 weeks Reviewed by: bz
2009-06-25 11:52:33 +00:00
IN_IFADDR_RUNLOCK();
Add a hash table that contains the list of internet addresses, and use this in place of the in_ifaddr list when appropriate. This improves performance on hosts which have a large number of IP aliases.
2001-09-29 04:34:11 +00:00
goto match;
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
}
}
Add a new global rwlock, in_ifaddr_lock, which will synchronize use of the in_ifaddrhead and INADDR_HASH address lists. Previously, these lists were used unsynchronized as they were effectively never changed in steady state, but we've seen increasing reports of writer-writer races on very busy VPN servers as core count has gone up (and similar configurations where address lists change frequently and concurrently). For the time being, use rwlocks rather than rmlocks in order to take advantage of their better lock debugging support. As a result, we don't enable ip_input()'s read-locking of INADDR_HASH until an rmlock conversion is complete and a performance analysis has been done. This means that one class of reader-writer races still exists. MFC after: 6 weeks Reviewed by: bz
2009-06-25 11:52:33 +00:00
IN_IFADDR_RUNLOCK();
More verbose description of the source ip address selection for ICMP replies. Reviewed by: bms
2004-02-02 22:17:09 +00:00
/*
* If the incoming packet was addressed to one of our broadcast
* addresses, use the first non-broadcast address which corresponds
* to the incoming interface.
*/
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
ifp = m->m_pkthdr.rcvif;
if (ifp != NULL && ifp->if_flags & IFF_BROADCAST) {
IF_ADDR_LOCK(ifp);
TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
Add a hash table that contains the list of internet addresses, and use this in place of the in_ifaddr list when appropriate. This improves performance on hosts which have a large number of IP aliases.
2001-09-29 04:34:11 +00:00
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
whitespace fixes.
2001-12-14 19:32:47 +00:00
ia = ifatoia(ifa);
if (satosin(&ia->ia_broadaddr)->sin_addr.s_addr ==
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
t.s_addr) {
t = IA_SIN(ia)->sin_addr;
IF_ADDR_UNLOCK(ifp);
whitespace fixes.
2001-12-14 19:32:47 +00:00
goto match;
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
}
whitespace fixes.
2001-12-14 19:32:47 +00:00
}
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
IF_ADDR_UNLOCK(ifp);
whitespace fixes.
2001-12-14 19:32:47 +00:00
}
Add an option to have ICMP replies to non-local packets generated with the IP address the packet came through in. This is useful for routers to show in traceroutes the actual path a packet has taken instead of the possibly different return path. The new sysctl is named net.inet.icmp.reply_from_interface and defaults to off. MFC after: 2 weeks
2005-08-21 12:29:39 +00:00
/*
* If the packet was transiting through us, use the address of
* the interface the packet came through in. If that interface
* doesn't have a suitable IP address, the normal selection
* criteria apply.
*/
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
if (V_icmp_rfi && ifp != NULL) {
IF_ADDR_LOCK(ifp);
TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
Add an option to have ICMP replies to non-local packets generated with the IP address the packet came through in. This is useful for routers to show in traceroutes the actual path a packet has taken instead of the possibly different return path. The new sysctl is named net.inet.icmp.reply_from_interface and defaults to off. MFC after: 2 weeks
2005-08-21 12:29:39 +00:00
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
ia = ifatoia(ifa);
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
t = IA_SIN(ia)->sin_addr;
IF_ADDR_UNLOCK(ifp);
Add an option to have ICMP replies to non-local packets generated with the IP address the packet came through in. This is useful for routers to show in traceroutes the actual path a packet has taken instead of the possibly different return path. The new sysctl is named net.inet.icmp.reply_from_interface and defaults to off. MFC after: 2 weeks
2005-08-21 12:29:39 +00:00
goto match;
}
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
IF_ADDR_UNLOCK(ifp);
Add an option to have ICMP replies to non-local packets generated with the IP address the packet came through in. This is useful for routers to show in traceroutes the actual path a packet has taken instead of the possibly different return path. The new sysctl is named net.inet.icmp.reply_from_interface and defaults to off. MFC after: 2 weeks
2005-08-21 12:29:39 +00:00
}
Add sysctl net.inet.icmp.reply_src to specify the interface name used for the ICMP reply source in reponse to packets which are not directly addressed to us. By default continue with with normal source selection. Reviewed by: bms
2004-02-02 22:53:16 +00:00
/*
* If the incoming packet was not addressed directly to us, use
* designated interface for icmp replies specified by sysctl
* net.inet.icmp.reply_src (default not set). Otherwise continue
* with normal source selection.
*/
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
if (V_reply_src[0] != '\0' && (ifp = ifunit(V_reply_src))) {
IF_ADDR_LOCK(ifp);
TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
Add sysctl net.inet.icmp.reply_src to specify the interface name used for the ICMP reply source in reponse to packets which are not directly addressed to us. By default continue with with normal source selection. Reviewed by: bms
2004-02-02 22:53:16 +00:00
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
ia = ifatoia(ifa);
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
t = IA_SIN(ia)->sin_addr;
IF_ADDR_UNLOCK(ifp);
Add sysctl net.inet.icmp.reply_src to specify the interface name used for the ICMP reply source in reponse to packets which are not directly addressed to us. By default continue with with normal source selection. Reviewed by: bms
2004-02-02 22:53:16 +00:00
goto match;
}
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
IF_ADDR_UNLOCK(ifp);
Add sysctl net.inet.icmp.reply_src to specify the interface name used for the ICMP reply source in reponse to packets which are not directly addressed to us. By default continue with with normal source selection. Reviewed by: bms
2004-02-02 22:53:16 +00:00
}
White space cleanup for netinet before branch: - Trailing tab/space cleanup - Remove spurious spaces between or before tabs This change avoids touching files that Andre likely has in his working set for PFIL hooks changes for IPFW/DUMMYNET. Approved by: re (scottl) Submitted by: Xin LI <delphij@frontfree.net>
2004-08-16 18:32:07 +00:00
/*
More verbose description of the source ip address selection for ICMP replies. Reviewed by: bms
2004-02-02 22:17:09 +00:00
* If the packet was transiting through us, use the address of
* the interface that is the closest to the packet source.
* When we don't have a route back to the packet source, stop here
* and drop the packet.
*/
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
ia = ip_rtaddr(ip->ip_dst, M_GETFIB(m));
In icmp_reflect(): If the packet was not addressed to us and was received on an interface without an IP address, try to find a non-loopback AF_INET address to use. If that fails, drop it. Previously, we used the address at the top of the in_ifaddrhead list, which didn't make much sense, and would cause a panic if there were no AF_INET addresses configured on the system. PR: 29337, 30524 Reviewed by: ru, jlemon Obtained from: NetBSD
2001-11-27 19:58:09 +00:00
if (ia == NULL) {
m_freem(m);
Update stats in struct icmpstat and icmp6stat using four new macros: ICMPSTAT_ADD(), ICMPSTAT_INC(), ICMP6STAT_ADD(), and ICMP6STAT_INC(), rather than directly manipulating the fields of these structures across the kernel. This will make it easier to change the implementation of these statistics, such as using per-CPU versions of the data structures. In on case, icmp6stat members are manipulated indirectly, by icmp6_errcount(), and this will require further work to fix for per-CPU stats. MFC after: 3 days
2009-04-12 13:22:33 +00:00
ICMPSTAT_INC(icps_noroute);
In icmp_reflect(): If the packet was not addressed to us and was received on an interface without an IP address, try to find a non-loopback AF_INET address to use. If that fails, drop it. Previously, we used the address at the top of the in_ifaddrhead list, which didn't make much sense, and would cause a panic if there were no AF_INET addresses configured on the system. PR: 29337, 30524 Reviewed by: ru, jlemon Obtained from: NetBSD
2001-11-27 19:58:09 +00:00
goto done;
}
In icmp_reflect(), acquire the inteface address list lock when searching for a source address to use. MFC after: 2 weeks Reviewed by: bz
2009-04-20 13:45:39 +00:00
t = IA_SIN(ia)->sin_addr;
Modify most routines returning 'struct ifaddr *' to return references rather than pointers, requiring callers to properly dispose of those references. The following routines now return references: ifaddr_byindex ifa_ifwithaddr ifa_ifwithbroadaddr ifa_ifwithdstaddr ifa_ifwithnet ifaof_ifpforaddr ifa_ifwithroute ifa_ifwithroute_fib rt_getifa rt_getifa_fib IFP_TO_IA ip_rtaddr in6_ifawithifp in6ifa_ifpforlinklocal in6ifa_ifpwithaddr in6_ifadd carp_iamatch6 ip6_getdstifaddr Remove unused macro which didn't have required referencing: IFP_TO_IA6 This closes many small races in which changes to interface or address lists while an ifaddr was in use could lead to use of freed memory (etc). In a few cases, add missing if_addr_list locking required to safely acquire references. Because of a lack of deep copying support, we accept a race in which an in6_ifaddr pointed to by mbuf tags and extracted with ip6_getdstifaddr() doesn't hold a reference while in transmit. Once we have mbuf tag deep copy support, this can be fixed. Reviewed by: bz Obtained from: Apple, Inc. (portions) MFC after: 6 weeks (portions)
2009-06-23 20:19:09 +00:00
ifa_free(&ia->ia_ifa);
Add a hash table that contains the list of internet addresses, and use this in place of the in_ifaddr list when appropriate. This improves performance on hosts which have a large number of IP aliases.
2001-09-29 04:34:11 +00:00
match:
Introduce two new MAC Framework and MAC policy entry points: mac_reflect_mbuf_icmp() mac_reflect_mbuf_tcp() These entry points permit MAC policies to do "update in place" changes to the labels on ICMP and TCP mbuf headers when an ICMP or TCP response is generated to a packet outside of the context of an existing socket. For example, in respond to a ping or a RST packet to a SYN on a closed port. Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2003-08-21 18:39:16 +00:00
#ifdef MAC
Continue to move from generic network entry points in the TrustedBSD MAC Framework by moving from mac_mbuf_create_netlayer() to more specific entry points for specific network services: - mac_netinet_firewall_reply() to be used when replying to in-bound TCP segments in pf and ipfw (etc). - Rename mac_netinet_icmp_reply() to mac_netinet_icmp_replyinplace() and add mac_netinet_icmp_reply(), reflecting that in some cases we overwrite a label in place, but in others we apply the label to a new mbuf. Obtained from: TrustedBSD Project
2007-10-28 17:12:48 +00:00
mac_netinet_icmp_replyinplace(m);
Introduce two new MAC Framework and MAC policy entry points: mac_reflect_mbuf_icmp() mac_reflect_mbuf_tcp() These entry points permit MAC policies to do "update in place" changes to the labels on ICMP and TCP mbuf headers when an ICMP or TCP response is generated to a packet outside of the context of an existing socket. For example, in respond to a ping or a RST packet to a SYN on a closed port. Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2003-08-21 18:39:16 +00:00
#endif
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
ip->ip_src = t;
Commit step 1 of the vimage project, (network stack) virtualization work done by Marko Zec (zec@). This is the first in a series of commits over the course of the next few weeks. Mark all uses of global variables to be virtualized with a V_ prefix. Use macros to map them back to their global names for now, so this is a NOP change only. We hope to have caught at least 85-90% of what is needed so we do not invalidate a lot of outstanding patches again. Obtained from: //depot/projects/vimage-commit2/... Reviewed by: brooks, des, ed, mav, julian, jamie, kris, rwatson, zec, ... (various people I forgot, different versions) md5 (with a bit of help) Sponsored by: NLnet Foundation, The FreeBSD Foundation X-MFC after: never V_Commit_Message_Reviewed_By: more people than the patch
2008-08-17 23:27:27 +00:00
ip->ip_ttl = V_ip_defttl;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
if (optlen > 0) {
register u_char *cp;
int opt, cnt;
u_int len;
/*
* Retrieve any source routing from the incoming packet;
* add on any record-route or timestamp options.
*/
cp = (u_char *) (ip + 1);
Remove the last two global variables that are used to store packet state while it travels through the IP stack. This wasn't much of a problem because IP source routing is disabled by default but when enabled together with SMP and preemption it would have very likely cross-corrupted the IP options in transit. The IP source route options of a packet are now stored in a mtag instead of the global variable.
2004-09-15 20:13:26 +00:00
if ((opts = ip_srcroute(m)) == 0 &&
Retire MT_HEADER mbuf type and change its users to use MT_DATA. Having an additional MT_HEADER mbuf type is superfluous and redundant as nothing depends on it. It only adds a layer of confusion. The distinction between header mbuf's and data mbuf's is solely done through the m->m_flags M_PKTHDR flag. Non-native code is not changed in this commit. For compatibility MT_HEADER is mapped to MT_DATA. Sponsored by: TCP/IP Optimization Fundraise 2005
2005-11-02 13:46:32 +00:00
(opts = m_gethdr(M_DONTWAIT, MT_DATA))) {
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
opts->m_len = sizeof(struct in_addr);
mtod(opts, struct in_addr *)->s_addr = 0;
}
if (opts) {
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("icmp_reflect optlen %d rt %d => ",
optlen, opts->m_len);
#endif
for (cnt = optlen; cnt > 0; cnt -= len, cp += len) {
opt = cp[IPOPT_OPTVAL];
if (opt == IPOPT_EOL)
break;
if (opt == IPOPT_NOP)
len = 1;
else {
Add boundary checks against IP options. Obtained from: OpenBSD
2000-06-02 20:18:38 +00:00
if (cnt < IPOPT_OLEN + sizeof(*cp))
break;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
len = cp[IPOPT_OLEN];
Add boundary checks against IP options. Obtained from: OpenBSD
2000-06-02 20:18:38 +00:00
if (len < IPOPT_OLEN + sizeof(*cp) ||
len > cnt)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
break;
}
/*
* Should check for overflow, but it "can't happen"
*/
Remove trailing whitespace.
1995-05-30 08:16:23 +00:00
if (opt == IPOPT_RR || opt == IPOPT_TS ||
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
opt == IPOPT_SECURITY) {
bcopy((caddr_t)cp,
mtod(opts, caddr_t) + opts->m_len, len);
opts->m_len += len;
}
}
/* Terminate & pad, if necessary */
GCC cleanup. Reviewed by: Submitted by: Obtained from:
1994-10-02 17:48:58 +00:00
cnt = opts->m_len % 4;
if (cnt) {
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
for (; cnt < 4; cnt++) {
*(mtod(opts, caddr_t) + opts->m_len) =
IPOPT_EOL;
opts->m_len++;
}
}
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("%d\n", opts->m_len);
#endif
}
/*
* Now strip out original options by copying rest of first
* mbuf's data back, and adjust the IP length.
*/
ip->ip_len -= optlen;
Fix two instances of variant struct definitions in sys/netinet: Remove the never completed _IP_VHL version, it has not caught on anywhere and it would make us incompatible with other BSD netstacks to retain this version. Add a CTASSERT protecting sizeof(struct ip) == 20. Don't let the size of struct ipq depend on the IPDIVERT option. This is a functional no-op commit. Approved by: re
2002-10-20 22:52:07 +00:00
ip->ip_v = IPVERSION;
ip->ip_hl = 5;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
m->m_len -= optlen;
if (m->m_flags & M_PKTHDR)
m->m_pkthdr.len -= optlen;
optlen += sizeof(struct ip);
bcopy((caddr_t)ip + optlen, (caddr_t)(ip + 1),
(unsigned)(m->m_len - sizeof(struct ip)));
}
Introduce the notion of "persistent mbuf tags"; these are tags that stay with an mbuf until it is reclaimed. This is in contrast to tags that vanish when an mbuf chain passes through an interface. Persistent tags are used, for example, by MAC labels. Add an m_tag_delete_nonpersistent function to strip non-persistent tags from mbufs and use it to strip such tags from packets as they pass through the loopback interface and when turned around by icmp. This fixes problems with "tag leakage". Pointed out by: Jonathan Stone Reviewed by: Robert Watson
2003-10-29 05:40:07 +00:00
m_tag_delete_nonpersistent(m);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
m->m_flags &= ~(M_BCAST|M_MCAST);
Remove the global one-level rtcache variable and associated complex locking and rework ip_rtaddr() to do its own rtlookup. Adopt all its callers to this and make ip_output() callable with NULL rt pointer. Reviewed by: sam (mentor)
2003-11-14 21:48:57 +00:00
icmp_send(m, opts);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
done:
if (opts)
(void)m_free(opts);
}
/*
* Send an icmp packet back to the ip level,
* after supplying a checksum.
*/
New style sysctl & staticize alot of stuff.
1995-11-14 20:34:56 +00:00
static void
Move universally to ANSI C function declarations, with relatively consistent style(9)-ish layout.
2007-05-10 15:58:48 +00:00
icmp_send(struct mbuf *m, struct mbuf *opts)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
register struct ip *ip = mtod(m, struct ip *);
register int hlen;
register struct icmp *icp;
Fix two instances of variant struct definitions in sys/netinet: Remove the never completed _IP_VHL version, it has not caught on anywhere and it would make us incompatible with other BSD netstacks to retain this version. Add a CTASSERT protecting sizeof(struct ip) == 20. Don't let the size of struct ipq depend on the IPDIVERT option. This is a functional no-op commit. Approved by: re
2002-10-20 22:52:07 +00:00
hlen = ip->ip_hl << 2;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
m->m_data += hlen;
m->m_len -= hlen;
icp = mtod(m, struct icmp *);
icp->icmp_cksum = 0;
icp->icmp_cksum = in_cksum(m, ip->ip_len - hlen);
m->m_data -= hlen;
m->m_len += hlen;
When an incoming packet is reflected back as an ICMP reply, make sure we zero "m->m_pkthdr.rcvif", otherwise ipfw may wrongly match the outgoing packet. PR: kern/9723 Submitted by: David Malone <dwmalone@maths.tcd.ie>
1999-03-06 23:10:42 +00:00
m->m_pkthdr.rcvif = (struct ifnet *)0;
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#ifdef ICMPPRINTFS
Fix long-standing bug in ICMPPRINTFS code where NTOHL was used instead of ntohl for printing IP addresses, by instead substituting inet_ntoa() to produce human-readable output. Obtained from: 4.4-Lite-2
1995-08-29 17:49:04 +00:00
if (icmpprintfs) {
char buf[4 * sizeof "123"];
strcpy(buf, inet_ntoa(ip->ip_dst));
printf("icmp_send dst %s src %s\n",
buf, inet_ntoa(ip->ip_src));
}
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
#endif
Remove the global one-level rtcache variable and associated complex locking and rework ip_rtaddr() to do its own rtlookup. Adopt all its callers to this and make ip_output() callable with NULL rt pointer. Reviewed by: sam (mentor)
2003-11-14 21:48:57 +00:00
(void) ip_output(m, opts, NULL, 0, NULL, NULL);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
}
Use uint32_t instead of n_long and n_time, and uint16_t instead of n_short. Add a note next to fields in network format. The n_* types are not enough for compiler checks on endianness, and their use often requires an otherwise unnecessary #include <netinet/in_systm.h> The typedef in in_systm.h are still there.
2009-02-13 15:14:43 +00:00
/*
* Return milliseconds since 00:00 GMT in network format.
*/
uint32_t
Move universally to ANSI C function declarations, with relatively consistent style(9)-ish layout.
2007-05-10 15:58:48 +00:00
iptime(void)
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
{
struct timeval atv;
u_long t;
Use getmicrotime() instead of microtime() when timestamping ICMP packets, the former is quicker and accurate enough for use here. Submitted by: Jason Slagle <raistlin@toledolink.com> (on IRC) Reviewed by: phk
2000-12-16 21:39:48 +00:00
getmicrotime(&atv);
BSD 4.4 Lite Kernel Sources
1994-05-24 10:09:53 +00:00
t = (atv.tv_sec % (24*60*60)) * 1000 + atv.tv_usec / 1000;
return (htonl(t));
}
Initial back-end support for IP MTU discovery, gated on MTUDISC. The support for TCP has yet to be written.
1995-09-18 15:51:40 +00:00
/*
* Return the next larger or smaller MTU plateau (table from RFC 1191)
* given current value MTU. If DIR is less than zero, a larger plateau
* is returned; otherwise, a smaller value is returned.
*/
Move Path MTU discovery ICMP processing from icmp_input() to tcp_ctlinput() and subject it to active tcpcb and sequence number checking. Previously any ICMP unreachable/needfrag message would cause an update to the TCP hostcache. Now only ICMP PMTU messages belonging to an active TCP session with the correct src/dst/port and sequence number will update the hostcache and complete the path MTU discovery process. Note that we don't entirely implement the recommended counter measures of Section 7.2 of the paper. However we close down the possible degradation vector from trivially easy to really complex and resource intensive. In addition we have limited the smallest acceptable MTU with net.inet.tcp.minmss sysctl for some time already, further reducing the effect of any degradation due to an attack. Security: draft-gont-tcpm-icmp-attacks-03.txt Section 7.2 MFC after: 3 days
2005-04-21 14:29:34 +00:00
int
Move universally to ANSI C function declarations, with relatively consistent style(9)-ish layout.
2007-05-10 15:58:48 +00:00
ip_next_mtu(int mtu, int dir)
Initial back-end support for IP MTU discovery, gated on MTUDISC. The support for TCP has yet to be written.
1995-09-18 15:51:40 +00:00
{
static int mtutab[] = {
Add another step of 1280 (gif(4) tunnels) to ip_next_mtu().
2005-05-04 13:23:54 +00:00
65535, 32000, 17914, 8166, 4352, 2002, 1492, 1280, 1006, 508,
296, 68, 0
Initial back-end support for IP MTU discovery, gated on MTUDISC. The support for TCP has yet to be written.
1995-09-18 15:51:40 +00:00
};
Simplify ip_next_mtu() and make its logic more easy to see while silencing code analysis tools. Found by: Coverity Prevent(tm) Coverity ID: CID341 Sponsored by: TCP/IP Optimization Fundraise 2005
2006-01-23 17:06:32 +00:00
int i, size;
Initial back-end support for IP MTU discovery, gated on MTUDISC. The support for TCP has yet to be written.
1995-09-18 15:51:40 +00:00
Simplify ip_next_mtu() and make its logic more easy to see while silencing code analysis tools. Found by: Coverity Prevent(tm) Coverity ID: CID341 Sponsored by: TCP/IP Optimization Fundraise 2005
2006-01-23 17:06:32 +00:00
size = (sizeof mtutab) / (sizeof mtutab[0]);
if (dir >= 0) {
Fix build.
2006-01-23 20:10:49 +00:00
for (i = 0; i < size; i++)
Simplify ip_next_mtu() and make its logic more easy to see while silencing code analysis tools. Found by: Coverity Prevent(tm) Coverity ID: CID341 Sponsored by: TCP/IP Optimization Fundraise 2005
2006-01-23 17:06:32 +00:00
if (mtu > mtutab[i])
return mtutab[i];
Initial back-end support for IP MTU discovery, gated on MTUDISC. The support for TCP has yet to be written.
1995-09-18 15:51:40 +00:00
} else {
Simplify ip_next_mtu() and make its logic more easy to see while silencing code analysis tools. Found by: Coverity Prevent(tm) Coverity ID: CID341 Sponsored by: TCP/IP Optimization Fundraise 2005
2006-01-23 17:06:32 +00:00
for (i = size - 1; i >= 0; i--)
if (mtu < mtutab[i])
return mtutab[i];
if (mtu == mtutab[0])
return mtutab[0];
Initial back-end support for IP MTU discovery, gated on MTUDISC. The support for TCP has yet to be written.
1995-09-18 15:51:40 +00:00
}
Simplify ip_next_mtu() and make its logic more easy to see while silencing code analysis tools. Found by: Coverity Prevent(tm) Coverity ID: CID341 Sponsored by: TCP/IP Optimization Fundraise 2005
2006-01-23 17:06:32 +00:00
return 0;
Initial back-end support for IP MTU discovery, gated on MTUDISC. The support for TCP has yet to be written.
1995-09-18 15:51:40 +00:00
}
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
/*
* badport_bandlim() - check for ICMP bandwidth limit
*
* Return 0 if it is ok to send an ICMP error response, -1 if we have
White space cleanup for netinet before branch: - Trailing tab/space cleanup - Remove spurious spaces between or before tabs This change avoids touching files that Andre likely has in his working set for PFIL hooks changes for IPFW/DUMMYNET. Approved by: re (scottl) Submitted by: Xin LI <delphij@frontfree.net>
2004-08-16 18:32:07 +00:00
* hit our bandwidth limit and it is not ok.
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
*
* If icmplim is <= 0, the feature is disabled and 0 is returned.
*
* For now we separate the TCP and UDP subsystems w/ different 'which'
* values. We may eventually remove this separation (and simplify the
* code further).
*
* Note that the printing of the error message is delayed so we can
* properly print the icmp error rate that the system was trying to do
* (i.e. 22000/100 pps, etc...). This can cause long delays in printing
White space cleanup for netinet before branch: - Trailing tab/space cleanup - Remove spurious spaces between or before tabs This change avoids touching files that Andre likely has in his working set for PFIL hooks changes for IPFW/DUMMYNET. Approved by: re (scottl) Submitted by: Xin LI <delphij@frontfree.net>
2004-08-16 18:32:07 +00:00
* the 'final' error, but it doesn't make sense to solve the printing
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
* delay with more complex code.
*/
int
badport_bandlim(int which)
{
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
replace the special-purpose rate-limiting code with the general facility just added; this tries to maintain the same behaviour vis a vis printing the rate-limiting messages but need tweaking
2002-12-21 00:08:20 +00:00
#define N(a) (sizeof (a) / sizeof (a[0]))
static struct rate {
const char *type;
struct timeval lasttime;
Remove erroneous semicolons.
2004-07-13 16:06:19 +00:00
int curpps;
replace the special-purpose rate-limiting code with the general facility just added; this tries to maintain the same behaviour vis a vis printing the rate-limiting messages but need tweaking
2002-12-21 00:08:20 +00:00
} rates[BANDLIM_MAX+1] = {
{ "icmp unreach response" },
{ "icmp ping response" },
{ "icmp tstamp response" },
{ "closed port RST response" },
Attempt to improve feature parity between UDPv4 and UDPv6 by merging UDPv4 features to UDPv6: - Add MAC checks on delivery and MAC labeling on transmit. - Check for (and reject) datagrams with destination port 0. - For multicast delivery, check the source port only if the socket being considered as a destination has been connected. - Implement UDP blackholing based on net.inet.udp.blackhole. - Add a new ICMPv6 unreachable reply rate limiting category for failed delivery attempts and implement rate limiting for UDPv6 (submitted by bz). Approved by: re (kensmith) Reviewed by: bz
2007-07-19 22:34:25 +00:00
{ "open port RST response" },
{ "icmp6 unreach response" }
replace the special-purpose rate-limiting code with the general facility just added; this tries to maintain the same behaviour vis a vis printing the rate-limiting messages but need tweaking
2002-12-21 00:08:20 +00:00
};
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
/*
replace the special-purpose rate-limiting code with the general facility just added; this tries to maintain the same behaviour vis a vis printing the rate-limiting messages but need tweaking
2002-12-21 00:08:20 +00:00
* Return ok status if feature disabled or argument out of range.
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
*/
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (V_icmplim > 0 && (u_int) which < N(rates)) {
replace the special-purpose rate-limiting code with the general facility just added; this tries to maintain the same behaviour vis a vis printing the rate-limiting messages but need tweaking
2002-12-21 00:08:20 +00:00
struct rate *r = &rates[which];
int opps = r->curpps;
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (!ppsratecheck(&r->lasttime, &r->curpps, V_icmplim))
replace the special-purpose rate-limiting code with the general facility just added; this tries to maintain the same behaviour vis a vis printing the rate-limiting messages but need tweaking
2002-12-21 00:08:20 +00:00
return -1; /* discard packet */
/*
* If we've dropped below the threshold after having
* rate-limited traffic print the message. This preserves
* the previous behaviour at the expense of added complexity.
*/
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
if (V_icmplim_output && opps > V_icmplim)
replace the special-purpose rate-limiting code with the general facility just added; this tries to maintain the same behaviour vis a vis printing the rate-limiting messages but need tweaking
2002-12-21 00:08:20 +00:00
printf("Limiting %s from %d to %d packets/sec\n",
Step 1.5 of importing the network stack virtualization infrastructure from the vimage project, as per plan established at devsummit 08/08: http://wiki.freebsd.org/Image/Notes200808DevSummit Introduce INIT_VNET_*() initializer macros, VNET_FOREACH() iterator macros, and CURVNET_SET() context setting macros, all currently resolving to NOPs. Prepare for virtualization of selected SYSCTL objects by introducing a family of SYSCTL_V_*() macros, currently resolving to their global counterparts, i.e. SYSCTL_V_INT() == SYSCTL_INT(). Move selected #defines from sys/sys/vimage.h to newly introduced header files specific to virtualized subsystems (sys/net/vnet.h, sys/netinet/vinet.h etc.). All the changes are verified to have zero functional impact at this point in time by doing MD5 comparision between pre- and post-change object files(*). (*) netipsec/keysock.c did not validate depending on compile time options. Implemented by: julian, bz, brooks, zec Reviewed by: julian, bz, brooks, kris, rwatson, ... Approved by: julian (mentor) Obtained from: //depot/projects/vimage-commit2/... X-MFC after: never Sponsored by: NLnet Foundation, The FreeBSD Foundation
2008-10-02 15:37:58 +00:00
r->type, opps, V_icmplim);
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
}
replace the special-purpose rate-limiting code with the general facility just added; this tries to maintain the same behaviour vis a vis printing the rate-limiting messages but need tweaking
2002-12-21 00:08:20 +00:00
return 0; /* okay to send packet */
#undef N
Reviewed by: freebsd-current Add ICMP_BANDLIM option and 'net.inet.icmp.icmplim' sysctl. If option is specified in kernel config, icmplim defaults to 100 pps. Setting it to 0 will disable the feature. This feature limits ICMP error responses for packets sent to bad tcp or udp ports, which does a lot to help the machine handle network D.O.S. attacks. The kernel will report packet rates that exceed the limit at a rate of one kernel printf per second. There is one issue in regards to the 'tail end' of an attack... the kernel will not output the last report until some unrelated and valid icmp error packet is return at some point after the attack is over. This is a minor reporting issue only.
1998-12-03 20:23:21 +00:00
}
Reference in New Issue Copy Permalink