udp: Don't propagate connect error, as long as the inpcb has local port.

This fixes the UDP socket disconnect->[read/write] support; before this
fix, the immediate read/write after disconnect will g

udp: Don't propagate connect error, as long as the inpcb has local port.

This fixes the UDP socket disconnect->[read/write] support; before this
fix, the immediate read/write after disconnect will get EAFNOTSUPPORT.

show more ...

inpcb: Split portinfo token into tokens for porthash head

And use pooled token for porthash head. This avoids another 10K/s
~20K/s contention during local port selection.

udp: Wakeup callers sleeping on failed to connect socket.

udp: Fix bind races due to async close and random socket inital msgport

Bind for UDP sockets is now serialized by local port based netisr. And
on detach path, the UDP inpcb is removed from local po

udp: Fix bind races due to async close and random socket inital msgport

Bind for UDP sockets is now serialized by local port based netisr. And
on detach path, the UDP inpcb is removed from local port hash before
other netisrs are synchronized, so that the local port for the detaching
UDP inpcb could be recycled timely.

show more ...

udp: Implement asynchronized pru_connect.

This is mainly used to improve UDP connect(2) performance. Most
of the DNS resolvers (getaddrinfo(3) and curl's DNS resolver, etc)
and RTP application will

udp: Implement asynchronized pru_connect.

This is mainly used to improve UDP connect(2) performance. Most
of the DNS resolvers (getaddrinfo(3) and curl's DNS resolver, etc)
and RTP application will see improvement.

Before this commit the user space thread uses connect(2) will have
to wait for the netisr to complete all preceeding messages. This
could be performance hit for connect(2): the user space thread is
suspended, even if the UDP connect(2) should always be nonblocking.

The only drawback is that bunch of datagrams sent immediately after
connect(2) may not appear on the network in the sending order, but
UDP applications should always be able to handle out-of-order data-
grams.

UDP's asynchronous pru_connect implementation will set ISCONNECTED
before dispatching connect message to netisr. The errors like
EADDRNOTAVAIL, i.e. out of local port space, will be notified
through later send(2)/recv(2), or getsockopt(2) SOL_SOCKET/SO_ERROR.

The measured effect of this change on 2-ways E5-2600v2 with Intel
82599 (10Gbe) using tools/kq_connect_client -u, i.e. UDP socket/
connect/send /close before initiating a TCP connection:
- Connect rate increases by ~45Kconns/s; we are now doing
300Kconns/s.
- IPIs rate to the CPUs not running netisrs reduces (23Kipis/s ->
16Kipis/s).

show more ...

udp: Save original protocol processing port for later synchronizing.

Unlike TCP, user could send data w/ address to a UDP socket that
connect(2) is being called (those data messages will be on the
o

udp: Save original protocol processing port for later synchronizing.

Unlike TCP, user could send data w/ address to a UDP socket that
connect(2) is being called (those data messages will be on the
original protocol processing port and forwarded to the new protocol
processing port later), and then close the UDP socket (the detach
message could be sent to the new protocol processing port before
the inflight data messages). The inflight data messages will cause
later panic, since the socket/inp has been destroyed by the detach
message. I will have to say this probably will never happen for any
real world applications.

We fix this by recording the original message port, and synchronize
inflight data messages on it upon detaching. If the connect(2) moves
between protocol processing ports more than once, we will go though
all UDP processing netisrs to synchronize all possible inflight data
messages.

show more ...

udp/usrreq: Add brackets properly

The brackets were left out pretty accidentally, but the code
also worked pretty accidentally:

int error = 0;

if (ai != NULL)
error = udp_preattach(...);

if (

udp/usrreq: Add brackets properly

The brackets were left out pretty accidentally, but the code
also worked pretty accidentally:

int error = 0;

if (ai != NULL)
error = udp_preattach(...);

if (error)
goto out
else {
/* mismatched comment */
}

Reported-by: s4 on DragonFlyDigest

show more ...

udp/usrreq: Implement asynchronized pru_attach for UDP

The idea is same as c892825ffb53edaa4e5d7270b9254de80099dc53

The measured effect of this change on 2-ways E5-2600v2 with Intel 82599
(10Gbe) u

udp/usrreq: Implement asynchronized pru_attach for UDP

The idea is same as c892825ffb53edaa4e5d7270b9254de80099dc53

The measured effect of this change on 2-ways E5-2600v2 with Intel 82599
(10Gbe) using tools/kq_connect_client -u, i.e. UDP socket/connect/send
/close before initiating a TCP connection:
- Connect rate increases by ~15Kconns/s; we are now doing 260Kconns/s.
- IPIs rate to the CPUs not running netisrs reduces (36Kipis/s ->
23Kipis/s).

show more ...

udp/usrreq: Add missing return

udp/usrreq: Fix up cleanup so_pcb checks

- pru_attach must not be called twice, so so_pcb must be NULL.
- Check so_pcb in udp_ctloutput; this prepares asynchronized udp
pru_attach.

net: Factor out ASSERT_IN_NETISR and ASSERT_IS_NETISR

udp: Disable direct detach only if multicast options are to be set.

udp: Disable direct detach, if multicast options are set.

Add additional comment about disabling direct detach when setting
multicast options.

Submitted-by: Romick
DragonFly-bug: http://bugs.dragon

udp: Disable direct detach, if multicast options are set.

Add additional comment about disabling direct detach when setting
multicast options.

Submitted-by: Romick
DragonFly-bug: http://bugs.dragonflybsd.org/issues/2792

show more ...

kernel: Move us to using M_NOWAIT and M_WAITOK for mbuf functions.

The main reason is that our having to use the MB_WAIT and MB_DONTWAIT
flags was a recurring issue when porting drivers from FreeBSD

kernel: Move us to using M_NOWAIT and M_WAITOK for mbuf functions.

The main reason is that our having to use the MB_WAIT and MB_DONTWAIT
flags was a recurring issue when porting drivers from FreeBSD because
it tended to get forgotten and the code would compile anyway with the
wrong constants. And since MB_WAIT and MB_DONTWAIT ended up as ocflags
for an objcache_get() or objcache_reclaimlist call (which use M_WAITOK
and M_NOWAIT), it was just one big converting back and forth with some
sanitization in between.

This commit allows M_* again for the mbuf functions and keeps the
sanitizing as it was before: when M_WAITOK is among the passed flags,
objcache functions will be called with M_WAITOK and when it is absent,
they will be called with M_NOWAIT. All other flags are scrubbed by the
MB_OCFLAG() macro which does the same as the former MBTOM().

Approved-by: dillon

show more ...

inet/inet6: Remove the v4-mapped address support

This greatly simplies the code (even the IPv4 code) and avoids all kinds
of possible port theft.

INPCB:
- Nuke IN6P_IPV6_V6ONLY, which is always on

inet/inet6: Remove the v4-mapped address support

This greatly simplies the code (even the IPv4 code) and avoids all kinds
of possible port theft.

INPCB:
- Nuke IN6P_IPV6_V6ONLY, which is always on after this commit.
- Change inp_vflag into inp_af (AF_INET or AF_INET6), since the socket
is either IPv6 or IPv4, but never both. Set inpcb.inp_af in
in_pcballoc() instead of in every pru_attach methods. Add INP_ISIPV4()
and INP_ISIPV6() macros to check inpcb family (socket family and
inpcb.inp_af are same).
- Nuke the convoluted code in in_pcbbind() and in6_pcbbind() which is used
to allow wildcard binding to accepting IPv4 connections on IPv6 wildcard
bound sockets.
- Nuke the code in in_pcblookup_pkthash() to match IPv4 faddr with IPv6
wildcard bound socket.
- Nuke in6_mapped_{peeraddr,sockaddr,savefaddr}(); use in6_{setpeeraddr,
setsockaddr,savefaddr}() directly.
- Nuke v4-mapped address convertion functions.
- Don't allow binding to v4-mapped address in in6_pcbind().
- Don't allow connecting to v4-mapped address in in6_pcbconnect().

TCP:
- Nuke the code in tcp_output() which takes care of the IP header TTL
setting for v4-mapped IPv6 socket.
- Don't allow binding to v4-mapped address (through in6_pcbbind()).
- Don't allow connecting to v4-mapped address and nuke the related code
(PRUC_NAMALLOC etc.).
- Nuke the code (PRUC_FALLBACK etc.) to fallback to IPv4 connection if
IPv6 connection fails, which is wrong.
- Nuke the code for v4-mapped IPv6 socket in tcp6_soport().

UDP:
- Nuke the code for v4-mapped IPv6 socket in udp_input() and udp_append().
- Don't allow binding to v4-mapped address (through in6_pcbbind()).
- Don't allow connecting to v4-mapped address.
- Don't allow sending datagrams to v4-mapped address and nuke the related
code in udp6_output().
- Nuke the code for v4-mapped IPv6 socket in udp6_disconnect()

RIP:
- Don't allow sending packets to v4-mapped address.
- Don't allow binding to v4-mapped address.
- Don't allow connecting to v4-mapped address.

Misc fixup:
- Don't force rip pru_attach method to return 0. If in_pcballoc() fails,
just return the error code.

show more ...

icmp: Asynchonize ctlinput/mtudisc/redirect processing

Supportive facilities added:
- Embed netmsg_ctlinput into mbuf (used by input ICMP datagram) so that
we don't need to do additional memory al

icmp: Asynchonize ctlinput/mtudisc/redirect processing

Supportive facilities added:
- Embed netmsg_ctlinput into mbuf (used by input ICMP datagram) so that
we don't need to do additional memory allocation to forward the
pr_ctlinput to all netisrs for certain types of ICMP datagrams.
- Add/Expose so_pr_ctlport().
- Return target netisr's cpuid from pr_ctlport. If the returned cpuid
equals to ncpus, it means that pr_ctlinput needs to be run in all
netisrs.
- Support 'direct' mode for TCP/UDP's pr_ctlinput. The caller of the
'direct' mode pr_ctlinput will do the message forwarding.

ICMP pr_ctlinput/mtudisc/redirect processing changes:
- For mtudisc and redirect we unconditionally forward the message
embedded in input ICMP datagram to all netisrs, and call pr_ctlinput
in 'direct' mode.
- For pr_ctlinput, we first call so_pr_ctlport() to see whether we need
to forward the message embedded in input ICMP datagram to all netisrs,
and act accordingly.
- Once pr_ctlinput/mtudisc/redirect processing is done, the message
embedded in the input ICMP datagram is forwarded back to the netisr0
to run rip_input().

After this commit, netisr0 will not be blocked for ICMP pr_ctlinput/
mtudisc/redirect processing. This also fixes the mtudisc (originally
only cpu0's routes get mtu updates).

show more ...

udp: Fix parameter order of udp_addrcpu()

udp: Unify ctlinput and ctlport cmd/faddr/icmp_ip processing

inpcb: Define inp_notify_t

udp: Minor udp_ctlinput cleanup

netinet: Remove check for jailed process

This check caused jailed processes to not be able to do name lookups
via libc anymore, since a connect() on a udp socket failed.

Reviewed-by: Sepherosa Zieh

netinet: Remove check for jailed process

This check caused jailed processes to not be able to do name lookups
via libc anymore, since a connect() on a udp socket failed.

Reviewed-by: Sepherosa Ziehau <sepherosa@gmail.com>

show more ...

udp: Add assertion for preconditions for direct detach

udp: Add NOTINHASH assertion to udp_inswildcardhash()

So that we could catch programming bugs earlier.

udp: Use ncpus2 instead of ncpus, since udp uses ncpus2 netisrs

There is actually no functional change.

inpcb: Factor out in_pcbresetroute()