| Age | Commit message (Collapse) | Author |
|---|
|
purged. Remove it and move the prototype to if.c since ifconf() is
not used outside of this file.
ok mpi
|
|
NOTE: code still runs with single softnet task. change definition of
SOFTNET_TASKS in net/if.c, if you want to have more than one softnet task
OK mpi@, OK phessler@
|
|
rectification.
|
|
an ifq to transmit a packet is picked by the current traffic
conditioner (ie, priq or hfsc) by providing an index into an array
of ifqs. by default interfaces get a single ifq but can ask for
more using if_attach_queues().
the vast majority of our drivers still think there's a 1:1 mapping
between interfaces and transmit queues, so their if_start routines
take an ifnet pointer instead of a pointer to the ifqueue struct.
instead of changing all the drivers in the tree, drivers can opt
into using an if_qstart routine and setting the IFXF_MPSAFE flag.
the stack provides a compatability wrapper from the new if_qstart
handler to the previous if_start handlers if IFXF_MPSAFE isnt set.
enabling hfsc on an interface configures it to transmit everything
through the first ifq. any other ifqs are left configured as priq,
but unused, when hfsc is enabled.
getting this in now so everyone can kick the tyres.
ok mpi@ visa@ (who provided some tweaks for cnmac).
|
|
only once per packet.
Fix a regression introduced when if_input() started to be called by
every pseudo-driver.
ok claudio@, dlg@
|
|
this lets pflogd run again.
rename if_data() to if_getdata() while here to make grepping for
things less noisy.
reported by jsg@
worked through with deraadt@
|
|
a new if_data() function takes a pointer to ifnet and merges its
if_data and ifq statistics. it takes the ifq mutex around the reads
of the ifq stats so they get a consistent copy.
the ifnet and ifq stats are merged because some parts of the stack
still update the ifnet counters.
ok visa@ (on an earlier diff) mpi@ claudio@
|
|
inputs and ok bluhm@
|
|
a certain vendor likes to make chips that specify the rx buffer
sizes in kilobyte increments. unfortunately it places the ethernet
header on the start of the rx buffer, which means if you give it a
mcl2k cluster, the ethernet header will not be ETHER_ALIGNed cos
mcl2k clusters are always allocated on 2k boundarys (cos they pack
into pages well). that in turn means the ip header wont be aligned
correctly.
the current workaround on these chips has been to let non-strict
alignment archs just use the normal 2k cluster, but use whatever
cluster can fit 2k + 2 on strict archs. that turns out to be the
4k cluster, meaning we waste nearly 2k of space on every packet.
properly aligning the ethernet header and ip headers gives a
performance boost, even on non-strict archs.
|
|
to a new function if_setrdomain().
OK mpi@ henning@
|
|
mode, vxlan(4) must be configured to accept any virtual network
identifier with "vnetid any" and added to a bridge(4) or switch(4).
This way the driver will dynamically learn the tunnel endpoints and
their vnetids for the responses and can be used to dynamically bridge
between VXLANs. It is also being used in combination with switch(4)
and the OpenFlow tunnel classifiers.
With input from yasuoka@ goda@
OK deraadt@ dlg@
|
|
to ifconfig.
"llprio" allows one to set the priority of packets that do not go through
pf(4), as the case is for arp(4) or bpf(4).
ok sthen@ mikeb@
|
|
in the future this will subsume the individual vlandev, carpdev,
pppoedev, foodev options for things like vlan, carp, pppoe, etc.
inspired by vnetid
ok mpi@ jmatthew@
|
|
|
|
existing start routines will still be called under the kernel lock
and at IPL_NET.
mpsafe start routines will be serialised so only one instance of
each interfaces function will be running in the kernel at any point
in time. this guarantees packets will be dequeued in order, and the
start routines dont have to lock against themselves because if_start
does it for them.
the code to do that is based on the scsi runqueue code.
this also provides an if_start_barrier() function that should wait
until any currently running instances of if_start have finished.
a driver can opt in to the mpsafe if_start call by doing the following:
1. setting ifp->if_xflags = IFXF_MPSAFE
2. only calling if_start() instead of its own start routine
3. clearing IFF_RUNNING before calling if_start_barrier() on its way down
4. only using IFQ_DEQUEUE (not ifq_deq_begin/commit/rollback)
to simplify the implementation the tx mitigation code has been removed.
tested by several
ok mpi@ jmatthew@
|
|
The thread detaching an interface will sleep until all references to this
interface have been released. So we decided to only keep references for
a short period of time.
Keeping if_ref() private will hopefully help preserve this goal as long
as it makes sense.
Calling if_get()/if_put() in the same function also allows us to make
use of static analysis tools (thanks jsg@!) to catch our errors.
ok dlg@
|
|
rdomains and bridges on the local system. This can be used to route
through local rdomains, to create L2 devices (like trunks) between
them, and many other things.
Discussed with many, with input from mpi@
OK sthen@ phessler@ yasuoka@ mikeb@
|
|
mappings. This will be used by if_nameindex(3), if_nametoindex(3) and
if_indextoname(3) soon to fix the issues in pledge because of inet6 link
local addressing.
OK mpi@ benno@ deraadt@
The libc version will follow soon so better start updating your kernels
|
|
the abstract vnetid is promoted to a uin32_t, and adds a SIOCDVNETID
ioctl so it can be cleared.
this is all because i set an assignment on implementing a virtual
network interface and the students got confused when vnetid 0 didnt
show up in ifconfig output.
the vnetid in the vxlan(4) protocol is optional, but the current
code confuses 0 with no vnetid being set. this makes it clear.
ok reyk@ who also simplified my diff
|
|
Necessary bumps in Ports will be handled by sthen@.
OK mpi@ dlg@
|
|
With suggestions from tedu@ and guenther@
ok kettenis@
|
|
This changes numbers of the SIOCSIFMEDIA and SIOCGIFMEDIA ioctls and
grows struct ifmediareq.
Old ifconfig and dhclient binaries can still assign addresses, however
the 'media' subcommand stops working. Recompiling ifconfig and dhclient
with new headers before a reboot should not be necessary unless in very
special circumstances where non-default media settings must be used to
get link and console access is not available.
There may be some MD fallout but that will be cleared up later.
ok deraadt miod
with help and suggestions from several sharks attending l2k15
|
|
if_get can get a reference to an ifp, but it never releases that
reference. this provides an if_put function that can be used to
decrement the refcount.
we cannot come up with a scheme for letting the network stack run on
one (or many) cpus while ioctls are pulling interfaces down on another
cpu without refcounts for the interfaces.
if_put is going in now so we can go through the stack and put the
necessary calls to it in, and then we'll backfill this implementation
to actually check the refcounts when the interface detaches.
ok mpi@ mikeb@ claudio@
|
|
As a side effect there's no need to run if_attachdomain() after the
list of domains has been built.
ok claudio@, reyk@
|
|
something based on an address family and later assumes one of the paths
was taken. This was initially just calls to panic until guenther
suggested a function to reduce the amount of strings needed.
This reduces the amount of noise with static analysers and acts
as a sanity check.
ok guenther@ bluhm@
|
|
will be exported to userland with the existing sysctl, getifaddrs()
and routing socket (if_msghdr.ifm_data) interfaces that expose
if_data. All programs and daemons - Apps - that call the
SIOCGIFRDOMAIN ioctl in a getifaddrs() loop or after receiving an
interface message on the routing socket can now remove the pointless
additional ioctl. In base, that could be: dhclient, isakmpd, dhcpd,
dhcrelay, ntpd, ospfd, ripd, ifconfig.
No ABI breakage because it uses a previously unused pad field in if_data.
OK mpi@ deraadt@
|
|
an interface is destroyed/removed. This way we can ensure pseudo-driver
changes done after attaching an interface are undone before detaching it.
Note: it is safe to call if_deactivate() multiple times as the interface
should not have any attached pseudo-interface after the first call.
ok deraadt@, dlg@
|
|
its only used for the ip and ip6 network stack input queues, so it
seems unfair that every instance of ifqueue has to carry a pointer
around for this specific use case.
this moves the congestion marker to a kernel global. if we detect
that we're congested, we assume the whole system is busy and punish
all input queues.
marking a system as congested is done by setting the global to the
current value of ticks. as the system moves away from that value,
it moves away from being congested until the comparison fails.
written at s2k15
ok henning@ beck@ bluhm@ claudio@
|
|
recieving ring to the stack.
if_input() is at the moment a drop-in replacement for ether_input_mbuf()
but will let us stack pseudo-driver in a nice way in order to no longer
call ether_input() recursively.
ok pelikan@, reyk@, blambert@, henning@
|
|
was enabled by default. Add AFATTACH/AFDETACH ioctls which enable/disable
an address family for an interface (currently used for IPv6 only).
New kernel needs new ifconfig for IPv6 configuration (address assignment
still works with old ifconfig making this easy to cross over).
Committing on behalf of henning@ who is currently lebensmittelvergiftet.
ok stsp, benno, mpi
|
|
ok mikeb@, krw@, bluhm@, tedu@
|
|
we can pull the space the mbuf layer used to do per interface accounting
out of struct if_data.
saves a hundredish bytes on every interface.
ok deraadt@ claudio@
|
|
accept rtadvs on that interface. the global net.inet6.ip6.accept_rtadv
sysctl just doesn't cut it, even tho the spec wants that - but in their
little absurd world, a host just has one interface by definition anyway...
the sysctlgoes away.
lots of head scratching, brain cell elemination etc from bluhm benno stsp
florian, excitement from simon and todd, ok bluhm stsp benno florian
|
|
out of the mbuf layer, and break the assumption that an interface will
only have a single ring per mbuf cluster size.
mpi@ is ok with moving this forward
|
|
interfaces when the kernel is livelocked, only do it for the current
pool and defer the other updates.
This allow us to get rid of an interface list iteration in a critical
path.
Ridding the libc crank since this change introduce an ABI break.
ok claudio@
|
|
which allows us to modify ifnet structure in a relatively safe way;
discussed with deraadt, ok mpi
|
|
the rx ring was last allowed to grow and then assigned to it. it
is erroneous to do this because mcl_grown is a u_int and ticks is an
int.
this makes mcl_grown an int, and follows the idiom in kern_timeout.c
of going "thing - ticks < diff", which better copes with ticks
wrapping around and being used to calculate relative intervals.
ok pirofti@ guenther@
|
|
tested by naddy, ok deraadt
|
|
"do it" deraadt@
|
|
ok mpi@ henning@ benno@
|
|
interface. VXLAN is a UDP-based tunnelling protocol for overlaying
virtualized layer 2 networks over layer 3 networks. The implementation
is based on draft-mahalingam-dutt-dcops-vxlan-04 and has been tested
with other implementations in the wild.
put it in deraadt@
|
|
uses hfsc behind the scenes; altq stays in parallel for a migration phase.
if.h even more messy for the transition, but eventuelly it should become
readable...
looked over & tested by many, ok phessler sthen
|
|
on the parent interface. This is similar to what bridge(4), trunk(4)
or carp(4) are doing and allows us to get rid of the detachhook.
ok reyk@, mikeb@
|
|
ok krw@, mikeb@
|
|
Reported by naddy@
|
|
structure rather than doing various M_WAITOK allocations during
the *attach() functions, we always rely on them anyway.
ok mikeb@, uebayasi@
|
|
array indexed by interface numbers, add a new field to the interface
descriptor pointing to it.
claudio@ and todd@ like it, ok mikeb@
|
|
ok beck@, mikeb@
|
|
an interface index and replace all the redondant checks and accesses
to a global array by a call to this function.
With imputs from and ok bluhm@, mikeb@
|
|
ok mikeb@, miod@
|
