whether decapsulated IPsec packets will be passed to pfil again depending
on the setting of the net.ip6.ipsec6.filtertunnel sysctl.
PR: kern/157670
Submitted by: Manuel Kasper (mk neon1.net)
MFC after: 2 weeks
struct inpcbgroup. pcbgroups, or "connection groups", supplement the
existing inpcbinfo connection hash table, which when pcbgroups are
enabled, might now be thought of more usefully as a per-protocol
4-tuple reservation table.
Connections are assigned to connection groups base on a hash of their
4-tuple; wildcard sockets require special handling, and are members
of all connection groups. During a connection lookup, a
per-connection group lock is employed rather than the global pcbinfo
lock. By aligning connection groups with input path processing,
connection groups take on an effective CPU affinity, especially when
aligned with RSS work placement (see a forthcoming commit for
details). This eliminates cache line migration associated with
global, protocol-layer data structures in steady state TCP and UDP
processing (with the exception of protocol-layer statistics; further
commit to follow).
Elements of this approach were inspired by Willman, Rixner, and Cox's
2006 USENIX paper, "An Evaluation of Network Stack Parallelization
Strategies in Modern Operating Systems". However, there are also
significant differences: we maintain the inpcb lock, rather than using
the connection group lock for per-connection state.
Likewise, the focus of this implementation is alignment with NIC
packet distribution strategies such as RSS, rather than pure software
strategies. Despite that focus, software distribution is supported
through the parallel netisr implementation, and works well in
configurations where the number of hardware threads is greater than
the number of NIC input queues, such as in the RMI XLR threaded MIPS
architecture.
Another important difference is the continued maintenance of existing
hash tables as "reservation tables" -- these are useful both to
distinguish the resource allocation aspect of protocol name management
and the more common-case lookup aspect. In configurations where
connection tables are aligned with hardware hashes, it is desirable to
use the traditional lookup tables for loopback or encapsulated traffic
rather than take the expense of hardware hashes that are hard to
implement efficiently in software (such as RSS Toeplitz).
Connection group support is enabled by compiling "options PCBGROUP"
into your kernel configuration; for the time being, this is an
experimental feature, and hence is not enabled by default.
Subject to the limited MFCability of change dependencies in inpcb,
and its change to the inpcbinfo init function signature, this change
in principle could be merged to FreeBSD 8.x.
Reviewed by: bz
Sponsored by: Juniper Networks, Inc.
an explicit action for INET6 configuration happens. The changes are:
1. When an ND6 flag is changed via SIOCSIFINFO_FLAGS ioctl,
setting ND6_IFF_ACCEPT_RTADV and/or ND6_IFF_AUTO_LINKLOCAL now triggers
an attempt to clear the ND6_IFF_IFDISABLED flag.
2. When an AF_INET6 address is added successfully to an interface and
it is marked as ND6_IFF_IFDISABLED, an attempt to clear the
ND6_IFF_IFDISABLED happens.
This simplifies ND6_IFF_IFDISABLED flag manipulation by users via ifconfig(8);
in most cases manual configuration is no longer needed.
- When ND6_IFF_AUTO_LINKLOCAL is set and no link-local address is assigned to
an interface, SIOCSIFINFO_FLAGS ioctl now calls in6_ifattach() to configure
a link-local address.
This change ensures link-local address configuration when "ifconfig IF inet6"
command is invoked. For example, "ifconfig IF inet6 auto_linklocal" now
always try to configure an LL addr even if ND6_IFF_AUTO_LINKLOCAL is already
set to 1 (i.e. down/up cycle is no longer needed).
Reviewed by: bz
- A new per-interface knob IFF_ND6_NO_RADR and sysctl IPV6CTL_NO_RADR.
This controls if accepting a route in an RA message as the default route.
The default value for each interface can be set by net.inet6.ip6.no_radr.
The system wide default value is 0.
- A new sysctl: net.inet6.ip6.norbit_raif. This controls if setting R-bit in
NA on RA accepting interfaces. The default is 0 (R-bit is set based on
net.inet6.ip6.forwarding).
Background:
IPv6 host/router model suggests a router sends an RA and a host accepts it for
router discovery. Because of that, KAME implementation does not allow
accepting RAs when net.inet6.ip6.forwarding=1. Accepting RAs on a router can
make the routing table confused since it can change the default router
unintentionally.
However, in practice there are cases where we cannot distinguish a host from
a router clearly. For example, a customer edge router often works as a host
against the ISP, and as a router against the LAN at the same time. Another
example is a complex network configurations like an L2TP tunnel for IPv6
connection to Internet over an Ethernet link with another native IPv6 subnet.
In this case, the physical interface for the native IPv6 subnet works as a
host, and the pseudo-interface for L2TP works as the default IP forwarding
route.
Problem:
Disabling processing RA messages when net.inet6.ip6.forwarding=1 and
accepting them when net.inet6.ip6.forward=0 cause the following practical
issues:
- A router cannot perform SLAAC. It becomes a problem if a box has
multiple interfaces and you want to use SLAAC on some of them, for
example. A customer edge router for IPv6 Internet access service
using an IPv6-over-IPv6 tunnel sometimes needs SLAAC on the
physical interface for administration purpose; updating firmware
and so on (link-local addresses can be used there, but GUAs by
SLAAC are often used for scalability).
- When a host has multiple IPv6 interfaces and it receives multiple RAs on
them, controlling the default route is difficult. Router preferences
defined in RFC 4191 works only when the routers on the links are
under your control.
Details of Implementation Changes:
Router Advertisement messages will be accepted even when
net.inet6.ip6.forwarding=1. More precisely, the conditions are as
follow:
(ACCEPT_RTADV && !NO_RADR && !ip6.forwarding)
=> Normal RA processing on that interface. (as IPv6 host)
(ACCEPT_RTADV && (NO_RADR || ip6.forwarding))
=> Accept RA but add the router to the defroute list with
rtlifetime=0 unconditionally. This effectively prevents
from setting the received router address as the box's
default route.
(!ACCEPT_RTADV)
=> No RA processing on that interface.
ACCEPT_RTADV and NO_RADR are per-interface knob. In short, all interface
are classified as "RA-accepting" or not. An RA-accepting interface always
processes RA messages regardless of ip6.forwarding. The difference caused by
NO_RADR or ip6.forwarding is whether the RA source address is considered as
the default router or not.
R-bit in NA on the RA accepting interfaces is set based on
net.inet6.ip6.forwarding. While RFC 6204 W-1 rule (for CPE case) suggests
a router should disable the R-bit completely even when the box has
net.inet6.ip6.forwarding=1, I believe there is no technical reason with
doing so. This behavior can be set by a new sysctl net.inet6.ip6.norbit_raif
(the default is 0).
Usage:
# ifconfig fxp0 inet6 accept_rtadv
=> accept RA on fxp0
# ifconfig fxp0 inet6 accept_rtadv no_radr
=> accept RA on fxp0 but ignore default route information in it.
# sysctl net.inet6.ip6.norbit_no_radr=1
=> R-bit in NAs on RA accepting interfaces will always be set to 0.
hash install, etc. For now, these are arguments are unused, but as we add
RSS support, we will want to use hashes extracted from mbufs, rather than
manually calculated hashes of header fields, due to the expensive of the
software version of Toeplitz (and similar hashes).
Add notes that it would be nice to be able to pass mbufs into lookup
routines in pf(4), optimising firewall lookup in the same way, but the
code structure there doesn't facilitate that currently.
(In principle there is no reason this couldn't be MFCed -- the change
extends rather than modifies the KBI. However, it won't be useful without
other previous possibly less MFCable changes.)
Reviewed by: bz
Sponsored by: Juniper Networks, Inc.
- The existing ipi_lock continues to protect the global inpcb list and
inpcb counter. This lock is now relegated to a small number of
allocation and free operations, and occasional operations that walk
all connections (including, awkwardly, certain UDP multicast receive
operations -- something to revisit).
- A new ipi_hash_lock protects the two inpcbinfo hash tables for
looking up connections and bound sockets, manipulated using new
INP_HASH_*() macros. This lock, combined with inpcb locks, protects
the 4-tuple address space.
Unlike the current ipi_lock, ipi_hash_lock follows the individual inpcb
connection locks, so may be acquired while manipulating a connection on
which a lock is already held, avoiding the need to acquire the inpcbinfo
lock preemptively when a binding change might later be required. As a
result, however, lookup operations necessarily go through a reference
acquire while holding the lookup lock, later acquiring an inpcb lock --
if required.
A new function in_pcblookup() looks up connections, and accepts flags
indicating how to return the inpcb. Due to lock order changes, callers
no longer need acquire locks before performing a lookup: the lookup
routine will acquire the ipi_hash_lock as needed. In the future, it will
also be able to use alternative lookup and locking strategies
transparently to callers, such as pcbgroup lookup. New lookup flags are,
supplementing the existing INPLOOKUP_WILDCARD flag:
INPLOOKUP_RLOCKPCB - Acquire a read lock on the returned inpcb
INPLOOKUP_WLOCKPCB - Acquire a write lock on the returned inpcb
Callers must pass exactly one of these flags (for the time being).
Some notes:
- All protocols are updated to work within the new regime; especially,
TCP, UDPv4, and UDPv6. pcbinfo ipi_lock acquisitions are largely
eliminated, and global hash lock hold times are dramatically reduced
compared to previous locking.
- The TCP syncache still relies on the pcbinfo lock, something that we
may want to revisit.
- Support for reverting to the FreeBSD 7.x locking strategy in TCP input
is no longer available -- hash lookup locks are now held only very
briefly during inpcb lookup, rather than for potentially extended
periods. However, the pcbinfo ipi_lock will still be acquired if a
connection state might change such that a connection is added or
removed.
- Raw IP sockets continue to use the pcbinfo ipi_lock for protection,
due to maintaining their own hash tables.
- The interface in6_pcblookup_hash_locked() is maintained, which allows
callers to acquire hash locks and perform one or more lookups atomically
with 4-tuple allocation: this is required only for TCPv6, as there is no
in6_pcbconnect_setup(), which there should be.
- UDPv6 locking remains significantly more conservative than UDPv4
locking, which relates to source address selection. This needs
attention, as it likely significantly reduces parallelism in this code
for multithreaded socket use (such as in BIND).
- In the UDPv4 and UDPv6 multicast cases, we need to revisit locking
somewhat, as they relied on ipi_lock to stablise 4-tuple matches, which
is no longer sufficient. A second check once the inpcb lock is held
should do the trick, keeping the general case from requiring the inpcb
lock for every inpcb visited.
- This work reminds us that we need to revisit locking of the v4/v6 flags,
which may be accessed lock-free both before and after this change.
- Right now, a single lock name is used for the pcbhash lock -- this is
undesirable, and probably another argument is required to take care of
this (or a char array name field in the pcbinfo?).
This is not an MFC candidate for 8.x due to its impact on lookup and
locking semantics. It's possible some of these issues could be worked
around with compatibility wrappers, if necessary.
Reviewed by: bz
Sponsored by: Juniper Networks, Inc.
feature_present(3) to dynamically decide whether to use one or the
other family.
Reviewed by: gnn
Sponsored by: The FreeBSD Foundation
Sponsored by: iXsystems
MFC after: 10 days
in_pcb_lport(), in_pcblookup_local(), and in_pcblookup_hash(), and similarly
for IPv6 functions. In the future, we would like to support other flags
relating to locking strategy.
This change doesn't appear to modify the KBI in practice, as callers already
passed in INPLOOKUP_WILDCARD rather than a simple boolean.
MFC after: 3 weeks
Reviewed by: bz
Sponsored by: Juniper Networks, Inc.
interface is brought down, even though the interface address is still
valid. This patch maintains the permanent ARP entries as long as the
interface address (having the same prefix as that of the ARP entries)
is valid.
Reviewed by: delphij
MFC after: 5 days
Some bugs where fixed while doing this:
* ASCONF-ACK messages might use wrong port number when using
IPv6.
* Checking for additional addresses takes the correct address
into account and also does not do more comparisons than
necessary.
This patch is based on one received from bz@ who was
sponsored by The FreeBSD Foundation and iXsystems.
MFC after: 1 week
as well compiling out most functions adding or extending #ifdef INET
coverage.
Reviewed by: gnn
Sponsored by: The FreeBSD Foundation
Sponsored by: iXsystems
MFC after: 4 days
Unfold the IPSEC_COMMON_INPUT_CB() macro in xform_{ah,esp,ipcomp}.c
to not need three different versions depending on INET, INET6 or both.
Mark two places preparing for not yet supported functionality with IPv6.
Reviewed by: gnn
Sponsored by: The FreeBSD Foundation
Sponsored by: iXsystems
MFC after: 4 days
Not compiling in and not initializing from inetsw from in_proto.c for
IPv6 only, we need to initialize upper layer protocols from inet6sw.
Make sure to not initialize them twice in a Dual-Stack
environment but only conditionally on no INET as we have done for
TCP for a long time. Otherwise we would leak resources.
Reviewed by: gnn
Sponsored by: The FreeBSD Foundation
Sponsored by: iXsystems
MFC after: 3 days
passing the cached proxydl reference (sockaddr_dl initialized or not) to
nd6_na_output(). nd6_na_output() will thus assume a proxy NA. Revert to
conditionally passing either &proxydl or NULL if no proxy case desired.
Tested by: ipv6gw and ref9-i386
Reported by: Pete French (petefrench ingresso.co.uk on stable)
Reported by: bz, simon on Y! cluster
Reported by: kib
PR: kern/151908
MFC after: 3 days
working. We store v4 and v6 addresses as a union but for v4-mapped
addresses only store the 32bits w/o the ::ffff: word. That failed the
check as for example 127.0.0.1 would be ::7f00:1 rather than ::ffff:7f00:1
and the IN6_IS_ADDR_V4MAPPED() never worked here. Given we can hardly get
here with an unbound local address or invalid inp_vflags remove the check.
Reported by: tuexen
Reviewed by: tuexen
MFC after: 3 days
some more. Similar to what we do for TCP check for v4-mapped
addresses and then handle them or the normal v6 address case.
For either set inp_vflags before calling into the pcb connect
function so that we have an unambiguous view in case we need to
set the local address or port.
Looked at: tuexen (as part of more)
MFC after: 3 days
callers. This also fixes a problem when the prison call could set
the inp->in6p_laddr (laddr) and a following priv_check_cred() call
would return an error and will allow us to merge the IPv4 and IPv6
implementation.
MFC after: 2 weeks
even after dropping the reference and unlocking. Previously we
have dereferenced a NULL pointer (after r121765).
Simply unlocking after the block does not work either because of
lock ordering (see r121765) and in addition we would still hold
a pointer to something that might be gone by the time we access it.
Thus take a copy of the value rather than just caching the pointer.
PR: kern/151908
Submitted by: chenyl (netstar2008 126.com) (initial version)
MFC after: 2 weeks
* Store the flowid when receiving an SCTP/IPv6 packet.
* Store the flowid when receiving an SCTP packet with wrong CRC.
* Initilize flowid correctly.
* Put test code under INVARIANTS.
MFC after: 3 months.
Call the handler function with the lock held, return unlocked as we
might free the entry. Rework functions later in the call graph to be
either called with the lock held or, only if needed, unlocked.
Place asserts to document and tighten assumptions on various lle locking,
which were not always true before.
We call nd6_ns_output() unlocked and the assignment of ip6->ip6_src was
decentralized to minimize possible complexity introduced with the formerly
missing locking there. This also resulted in a push down of local
variable scopes into smaller blocks.
Reported by: many
PR: kern/148857
Submitted by: Dmitrij Tejblum (tejblum yandex-team.ru) (original version)
MFC After: 4 days
DPCPU_DEFINE and VNET_DEFINE macros, as these cause problems for various
people working on the affected files. A better long-term solution is
still being considered. This reversal may give some modules empty
set_pcpu or set_vnet sections, but these are harmless.
Changes reverted:
------------------------------------------------------------------------
r215318 | dim | 2010-11-14 21:40:55 +0100 (Sun, 14 Nov 2010) | 4 lines
Instead of unconditionally emitting .globl's for the __start_set_xxx and
__stop_set_xxx symbols, only emit them when the set_vnet or set_pcpu
sections are actually defined.
------------------------------------------------------------------------
r215317 | dim | 2010-11-14 21:38:11 +0100 (Sun, 14 Nov 2010) | 3 lines
Apply the STATIC_VNET_DEFINE and STATIC_DPCPU_DEFINE macros throughout
the tree.
------------------------------------------------------------------------
r215316 | dim | 2010-11-14 21:23:02 +0100 (Sun, 14 Nov 2010) | 2 lines
Add macros to define static instances of VNET_DEFINE and DPCPU_DEFINE.
Consistently use the LLE_ prefix for lla_lookup() and the ND6_ prefix
for nd6_lookup() even though both are defined the same. Use the right
flag variable when checking each.
No real functional change.
MFC after: 4 days
legacy and IPv6 route destination address.
Previously in case of IPv6, there was a memory overwrite due to not enough
space for the IPv6 address.
PR: kern/122565
MFC After: 2 weeks
un-expiring.
The previous version of code have no locking when testing rt_refcnt.
The result of the lack of locking may result in a condition where
a routing entry have a reference count but at the same time have
RTPRF_OURS bit set and an expiration timer. These would eventually
lead to a panic:
panic: rtqkill route really not free
When the system have ICMP redirects accepted from local gateway
in a moderate frequency, for instance.
Commit this workaround for now until we have some better solution.
PR: kern/149804
Reviewed by: bz
Tested by: Zhao Xin, Pete French
MFC after: 2 weeks
In protosw we define pr_protocol as short, while on the wire
it is an uint8_t. That way we can have "internal" protocols
like DIVERT, SEND or gaps for modules (PROTO_SPACER).
Switch ipproto_{un,}register to accept a short protocol number(*)
and do an upfront check for valid boundries. With this we
also consistently report EPROTONOSUPPORT for out of bounds
protocols, as we did for proto == 0. This allows a caller
to not error for this case, which is especially important
if we want to automatically call these from domain handling.
(*) the functions have been without any in-tree consumer
since the initial introducation, so this is considered save.
Implement ip6proto_{un,}register() similarly to their legacy IP
counter parts to allow modules to hook up dynamically.
Reviewed by: philip, will
MFC after: 1 week
Fix the switching on/off of PF and NR-SACKs using sysctl.
Add minor improvement in handling malloc failures.
Improve the address checks when sending.
MFC after: 4 weeks
Add kernel side support for Secure Neighbor Discovery (SeND), RFC 3971.
The implementation consists of a kernel module that gets packets from
the nd6 code, sends them to user space on a dedicated socket and reinjects
them back for further processing.
Hooks are used from nd6 code paths to divert relevant packets to the
send implementation for processing in user space. The hooks are only
triggered if the send module is loaded. In case no user space
application is connected to the send socket, processing continues
normaly as if the module would not be loaded. Unloading the module
is not possible at this time due to missing nd6 locking.
The native SeND socket is similar to a raw IPv6 socket but with its own,
internal pseudo-protocol.
Approved by: bz (mentor)
