| Age | Commit message (Collapse) | Author |
|---|
|
|
|
ok millert@ mpi@
|
|
Reviewed by Martin Natano.
|
|
problem noted by yasuoka@
ok yasuoka@ millert@
|
|
without pipex.enable=1. Also fix tun(4) not to pass the packets to pipex
when pipex.enable=0.
"go for it" dlg
|
|
destroyed during our sleep.
No objection from the slackers.
|
|
only a driver sets or clears OACTIVE. clearing it without setting it is
a waste of time.
|
|
found by and ok jsg@
|
|
the code is refactored so the IFQ macros call newly implemented ifq
functions. the ifq code is split so each discipline (priq and hfsc
in our case) is an opaque set of operations that the common ifq
code can call. the common code does the locking, accounting (ifq_len
manipulation), and freeing of the mbuf if the disciplines enqueue
function rejects it. theyre kind of like bufqs in the block layer
with their fifo and nscan disciplines.
the new api also supports atomic switching of disciplines at runtime.
the hfsc setup in pf_ioctl.c has been tweaked to build a complete
hfsc_if structure which it attaches to the send queue in a single
operation, rather than attaching to the interface up front and
building up a list of queues.
the send queue is now mutexed, which raises the expectation that
packets can be enqueued or purged on one cpu while another cpu is
dequeueing them in a driver for transmission. a lot of drivers use
IFQ_POLL to peek at an mbuf and attempt to fit it on the ring before
committing to it with a later IFQ_DEQUEUE operation. if the mbuf
gets freed in between the POLL and DEQUEUE operations, fireworks
will ensue.
to avoid this, the ifq api introduces ifq_deq_begin, ifq_deq_rollback,
and ifq_deq_commit. ifq_deq_begin allows a driver to take the ifq
mutex and get a reference to the mbuf they wish to try and tx. if
there's space, they can ifq_deq_commit it to remove the mbuf and
release the mutex. if there's no space, ifq_deq_rollback simply
releases the mutex. this api was developed to make updating the
drivers using IFQ_POLL easy, instead of having to do significant
semantic changes to avoid POLL that we cannot test on all the
hardware.
the common code has been tested pretty hard, and all the driver
modifications are straightforward except for de(4). if that breaks
it can be dealt with later.
ok mpi@ jmatthew@
|
|
|
|
L2 resolution depends on the protocol (encoded in the route entry) and
an ``ifp''. Not having to care about an ``ifa'' makes our life easier
in our MP effort. Fewer dependencies between data structures implies
fewer headaches.
Discussed with bluhm@, ok claudio@
|
|
libevent likes this more.
|
|
between modes. The two drivers still share most of the code but the mode
switcher is gone.
OK dlg@ mpi@
|
|
found by jsg@
|
|
this is a bit funky cos we give up the ref while sleeping in tunread,
and have to get a new ref on wakeup.
ok claudio@
|
|
From David Hill; OK mpi@; tested kspillner@; tweaks bluhm@
|
|
OK mikeb@
|
|
if_input() has been designed to be able to safely handle a batch of
packets from physical drivers to the network stack. Most of these
drivers have an interrupt routine executed at IPL_NET and the check
made sense during the conversion. However we also want to re-enqueue
packets with if_input() from the network stack currently running at
IPL_SOFTNET.
ok claudio@
|
|
ok stsp mpi
|
|
ok bluhm@, claudio@, dlg@
|
|
talking about (*ifp->if_output)().
ok claudio@, dlg@
|
|
Note that pseudo-drivers not using if_input() are not affected by this
conversion.
ok mikeb@, kettenis@, claudio@, dlg@
|
|
receiving interface in the packet header of every mbuf.
The interface pointer should now be retrieved when necessary with
if_get(). If a NULL pointer is returned by if_get(), the interface
has probably been destroy/removed and the mbuf should be freed.
Such mechanism will simplify garbage collection of mbufs and limit
problems with dangling ifp pointers.
Tested by jmatthew@ and krw@, discussed with many.
ok mikeb@, bluhm@, dlg@
|
|
Tested by Norman Golisz and <mxb AT alumni DOT chalmers DOT se>, thanks!
ok bluhm@
|
|
change it from feeding the ethertype of the packet (which is almost
certainly an ip packet or vlan packet, so not that variable) to the
number of packets about to be processed.
ok deraadt@ mpi@
|
|
that later but all drivers should be adapated.
Should fix a double output packet accounting, reported by Hrvoje Popovski.
|
|
introduced during the if_output() conversion.
Found by jsg@
|
|
|
|
a packet on the sending queue of an interface.
Tested by many, thanks a lot!
ok dlg@, claudio@
|
|
descriptor during SIOCSIFFLAGS.
This prevent a use after free, triggered by the pool/malloc damage
finder being currently cooked by dlg@ and deraadt@.
ok deraadt@
|
|
has destroyed or damaged the interface clone.
with mpi
|
|
Should fix a panic reported by many on bugs@ and misc@.
ok dlg@
|
|
with niqueues.
this change is so big because there's a lot of code that takes
pointers to different input queues (eg, ether_input picks between
ipv4, ipv6, pppoe, arp, and mpls input queues) and falls through
to code to enqueue packets against the pointer. if i changed only
one of the input queues id have to add sepearate code paths, one
for ifqueues and one for niqueues in each of these places
by flipping all these input queues at once i can keep the currently
common code common.
testing by mpi@ sthen@ and rafael zalamena
ok mpi@ sthen@ claudio@ henning@
|
|
|
|
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@
|
|
have any direct symbols used. Tested for indirect use by compiling
amd64/i386/sparc64 kernels.
ok tedu@ deraadt@
|
|
- rename uiomove() to uiomovei() and update all its users.
- introduce uiomove(), which is similar to uiomovei() but with a size_t.
- rewrite uiomovei() as an uiomove() wrapper.
ok kettenis@
|
|
for a couple decades. Keep the OSIOCGIFCONF ioctl to support COMPAT_LINUX
but move the rest of the Linux-specific ioctl() handling into linux_socket.c
This lets struct osockaddr finally move from sys/socket.h to protocols/talkd.h
ok krw@ deraadt@ mpi@
|
|
long live the one true internet.
ok henning mikeb
|
|
wasn't freeed when the interface is destroyed. Free it properly.
ok dlg
|
|
ok miod@ mpi@
|
|
|
|
after discussions with beck deraadt kettenis.
|
|
instead of relying on hacks in nd6_rtrequest() to add a route to
loopback for each address configured on such interfaces.
While here document that abusing lo0 for local traffic is not safe
for interfaces in a non-default rdomain.
Tested by claudio@, jca@ and sthen@, ok sthen@
|
|
ok pelikan@, henning@
|
|
|
|
Avoid the confusion by using an appropriate name for the variable.
Note that since routing domain IDs are a subset of the set of routing
table IDs, the following idiom is correct:
rtableid = rdomain
But to get the routing domain ID corresponding to a given routing table
ID, you must call rtable_l2(9).
claudio@ likes it, ok mikeb@
|
|
struct ucred; struct process then directly links to the ucred
Based on a discussion at c2k10 or so before noting that FreeBSD and
NetBSD did this too.
ok matthew@
|
|
global variables to in6.h.
ok deraadt@
|
|
global variables to in.h.
ok mikeb@, deraadt@
|
