rev. 1.149 rework.
It allows to save several percents of CPU time on SMP by using UMA's
internal per-CPU allocation limits instead of own global variable
each time updated with atomics.
Tested with: Netperf cluster
- reorder structures fields (XX_refs) a bit to group fields modified
same time together. According to my tests it gives up to 10%
SMP performance benefit on real workload due to reduced inter-CPU
cache trashing.
- change q_flags from long to int as long is not really needed there and
it's usage with atomics is argued by some people.
- move NGF_WORKQ flag into the separate field q_flags2 as it protected by
queue mutex instead of node writer protection used by the rest of flags.
- move nd_work queue entry to ng_queue structure to which it is more
related and make it STAILQ instead of TAILQ as now it is a classic FIFO.
- remove q_node pointer from ng_queue structure as it is not really needed.
- reimplement item queue using STAILQ instead of own equal implementation.
As soon as BT subsystem has own item queues using ng_item.el_next update
it also.
- change depth field in ng_item from uintptr_t to u_int. It was made
uintptr_t to keep ABI compatibility.
Reviewed by: julian, emax
Tested with: Netperf cluster
- Do not check destination hook presence, it will be done by netgraph.
- Use u_int instead of int in some places to simplify type conversions.
- Use NG_SEND_DATA_ONLY() macro instead of selfmade equivalent.
will never exit ngintr(), while there is some ready requests on the queue.
It was made years ago with hope of parallel queue processing by several
net threads. But even if we have several threads sometimes, we have no
rights to process queue in parallel as it will break original requests
serialization that is critically important for some setups.
of pptpgre and ksocket nodes for all calls between two peers. This patch
modifies node's API by adding new "session_%04x" hook names support, while
keeping backward compatibility.
Together with appropriate user-level support (by latest mpd5) it gives
huge performance benefits for case of multiple active calls between
two peers because of avoiding data duplication and extra socket processing.
On my benchmarks I have got more then 10 times speedup for the 200
simultaneous PPTP calls between two peers.
In conclusion, it allows now to build effective "clients <=> PAC <=> PNS"
setups.
Before this patch callback returned result of the last finished call chain.
Now it returns last nonzero result from all call chain results in this request.
As soon as this improvement gives reliable error reporting, it is now possible
to remove dirty workaround in ng_socket, made to return ENOBUFS error statuses
of request-response operations. That workaround was responsible for returning
ENOBUFS errors to completely unrelated requests working at the same time
on socket.
if netgraph reported error while delivering to destination.
Reset 'next send' counter to the last requested by peer on ack timeout
to resend all subsequest packets after lost one again without additional hints.
trashing and improve performance.
Remove waitflag argument from ng_ksocket_incoming2(), it means nothing
as function call was queued by netgraph.
Remove node validity check, as node validity guarantied by netgraph.
Update comments.
to avoid terrible unpredicted effects for netgraph operation of their
exhaustion while allocating control messages.
Add separate configurable 512 items limit for data items allocation
for DoS/overload protection.
Discussed with: julian
- Introduce a finit() which is used to initailize the fields of struct file
in such a way that the ops vector is only valid after the data, type,
and flags are valid.
- Protect f_flag and f_count with atomic operations.
- Remove the global list of all files and associated accounting.
- Rewrite the unp garbage collection such that it no longer requires
the global list of all files and instead uses a list of all unp sockets.
- Mark sockets in the accept queue so we don't incorrectly gc them.
Tested by: kris, pho
argument. It allows ppp, mpd or any other node consumer to request
connection to specified access concentrator.
Proposed by: Alexander A. Burylov <burylov@mail.ru>
for that argument. This will allow DDB to detect the broad category of
reason why the debugger has been entered, which it can use for the
purposes of deciding which DDB script to run.
Assign approximate why values to all current consumers of the
kdb_enter() interface.
Previous value 16 was too small for real LAC as temporal activity
spike cound easily overflow queue demanding tunnel disconnection due
to possible state inconsistency.
removing some copy&pasted code.
- Reduce copy and paste in ng_apply_item().
- Resurrect ng_send_fn() as a valid symbol, not a define.
Reviewed by: mav, julian
zero (0). Actual RFCOMM channel will be assigned after listen(2)
call is done on a RFCOMM socket bound to a ''wildcard'' RFCOMM
channel zero (0).
Address locking issues in ng_btsocket_rfcomm_bind()
Submitted by: Heiko Wundram (Beenic) < wundram at beenic dot net >
MFC after: 1 week
When item forwarded refence counter is incremented, when item
processed, counter decremented. When counter reaches zero,
apply handler is getting called.
Now it allows to report right connect() call status from user-level
at the right time.
simplifies code and should speedup pppoe_findsession() function which is
called for every incoming packet.
Approved by: re (kensmith), glebius (mentor)
Without it some errors may left unnoticed and unhandeled
that will lead to hooks left in half-connected state.
Reviewed by: julian@
Approved by: re (kensmith), glebius (mentor)
previously conditionally acquired Giant based on debug.mpsafenet. As that
has now been removed, they are no longer required. Removing them
significantly simplifies error-handling in the socket layer, eliminated
quite a bit of unwinding of locking in error cases.
While here clean up the now unneeded opt_net.h, which previously was used
for the NET_WITH_GIANT kernel option. Clean up some related gotos for
consistency.
Reviewed by: bz, csjp
Tested by: kris
Approved by: re (kensmith)
64bit counters are needed to simplify traffic accounting and
reduce system load at the big PPP concentrators.
Approved by: re (rwatson), glebius (mentor)
Till now node's transmit path was completely unprotected
and so wasn't thread safe in multilink mode. It's receive path was
declared as WRITER as the simpliest protection method but it
reduces performance when compression or encryption enabled.
Approved by: re (rwatson), glebius (mentor)
stack overflow in complicated traffic filtering setups.
There can be minor performance degradation for the MHLEN < len <= 256 case
due to additional buffer allocation, but it is a rare case.
Approved by: re (rwatson), glebius (mentor)
MFC after: 1 week
sysctl_handle_int is not sizeof the int type you want to export.
The type must always be an int or an unsigned int.
Remove the instances where a sizeof(variable) is passed to stop
people accidently cut and pasting these examples.
In a few places this was sysctl_handle_int was being used on 64 bit
types, which would truncate the value to be exported. In these
cases use sysctl_handle_quad to export them and change the format
to Q so that sysctl(1) can still print them.
While ng_fec called the ioctl to let interfaces in the bundle know
the list of multicast addresses had changed, it never actually
updated that list on the interfaces in the bundle. Consequently,
the multicast filters could be programmed incorrectly.
if_lagg does this correctly, by maintaining a list of addresses
that it has added to interfaces in the bundle. This commit basically
takes the if_lagg code and adds it to ng_fec.
A version of this patch for RELENG_6 has fixed some problems with
IPv6 ND over ng_fec. This is probably the problem in PR 107523.
PR: 107523
Tested by: Rob Gallagher <robert.gallagher@heanet.ie>
Obtained from: if_lagg
MFC after: 3 weeks
protocol entry points using functions named proto_getsockaddr and
proto_getpeeraddr rather than proto_setsockaddr and proto_setpeeraddr.
While it's true that sockaddrs are allocated and set, the net effect is
to retrieve (get) the socket address or peer address from a socket, not
set it, so align names to that intent.
when one of links is inactive and have stale sequence number. To avoid
this sequence numbers of all links are getting updated on every
successful packet reassembling.
- ng_ppp_bump_mseq function created to simplify code.
- ng_ppp_frag_drop function separated from ng_ppp_frag_process to
simplify code.
Reviewed by: archie
Approved by: glebius (mentor)
which lead to ineffective multilink packet distribution plans.
- Changed bytesInQueue calculation math to have more precise information
about links utilization.
- Taken rough account of the link overhead. Better way to do it could be to
get exact overhead from user-level, but I have not done it to keep
binary compatibility.
Reviewed by: archie
Approved by: glebius (mentor)
for doing this job. This change will make it easy to migrate from using
spinning locks to adaptive ones.
Reviewed by: glebius, julian
Approved by: cognet (mentor)
This will increase the memory consumption for more than 1 Mb, but this
is required for operation on multiinterface access concentrators running
mpd.
Requested by: Alexander Motin
structures. Detect when ifnet instances are detached from the network
stack and perform appropriate cleanup to prevent memory leaks.
This has been implemented in such a way as to be backwards ABI compatible.
Kernel consumers are changed to use if_delmulti_ifma(); in_delmulti()
is unable to detect interface removal by design, as it performs searches
on structures which are removed with the interface.
With this architectural change, the panics FreeBSD users have experienced
with carp and pfsync should be resolved.
Obtained from: p4 branch bms_netdev
Reviewed by: andre
Sponsored by: Garance A Drosehn
Idea from: NetBSD
MFC after: 1 month
from whoever has dequeued the item from the queue. Generally they have
no interest in the result, and even if it is called by the queuer, it
should still pretend that it was queued. The queuer should be assuming
that the call was queued and giving them the false confidence that they
are getting status leads to hard to find bugs.
Make it a void and remove all the code that tried to return status through it.
to embed up to four counters in outgoing packets. The message specifies
the offset at which the counter should be inserted as well as the
parameters of the counter.
Example usage:
ngctl msg src0: setcounter \
'{ index=0 offset=0x40 flags=1 width=4 increment=1 max_val=12345 }'
Sponsored by: Sandvine Incorporated
to embed a timestamp (struct timeval) in outgoing packets. The message
specifies the offset at which the timestamp should be inserted.
NG_SOURCE(4) gives an example usage that queues an ICMP packet. Using that
example, the following command will insert a timestamp in the ICMP's data
payload:
ngctl msg src0: settimestamp '{ offset=0x2a flags=1 }'
Sponsored by: Sandvine Incorporated
addressing if a packet is later re-encapsulated and sent to a
non-broadcast, non-multicast destination after being received on the
ng_ksocket input hook.
PR: 106999
Submitted by: Kevin Lahey
MFC after: 4 weeks
Formulas described in RFC require high precision of floating point.
Formulas of integer math implemented in ng_pptpgre give mistake in range
of +0-7ms on RTT and +0-3ms on deviation. This leads to significant
underestimation of real packet RTT.
I have made a very simple patch to reduce mistake to +4-3ms on RTT and
+2-1ms on deviation. Mistake in RTT is not good, but gets covered by
deviation. To cover worst possible negative mistake in deviation I have
added 2ms to it. Also this 2 ms cover the case when measured deviation
is so small (about zero) that it can interfere with process scheduling
delays or weather on Mars.
My tests show decreasing of packet losses on 20ms RTT link from 2.5% to
0.3% while speed increased un 1/3.
Reviewed by: archie
with bypass header, to send it out to userland.
- Use ng_ppp_bypass() in ng_ppp_proto_recv().
- Use ng_ppp_bypass() in ng_ppp_comp_recv() and in
ng_ppp_crypt_recv() if compression or encryption is
disabled, respectively.
- Any LCP packet goes directly to ng_ppp_bypass(), instead
of passing through PPP stack.
- Any non-LCP packet on disabled link is discarded. This
is behavior defined in RFC.
Submitted by: Alexander Motin <mav alkar.net>
hooks get their per hook rcvdata methods, and all functions are organized
corresponding to protocol stack model.
Submitted by: Alexander Motin <mav alkar.net>
Reviewed by: archie, julian
semantics.
- Stop testing bpf pointers for NULL. In some cases use
bpf_peers_present() and then call the function directly inside the
conditional block instead of the macro.
- For places where the entire conditional block is the macro, remove the
test and make the macro unconditional.
- Use BPF_MTAP() in if_pfsync on FreeBSD instead of an expanded version of
the old semantics.
Reviewed by: csjp (older version)
node would send every outgoing frame to the "compress" hook.
Packets received on the "compress" hook were expected to be
compressed and PROT_COMPD tag was put on them unconditionally.
After this commit an alternative compression mode can be set.
In this mode the node doesn't put the PROT_COMPD, the compressor
should put it itself. This is important for such kind of
compressors, that can submit uncompressed frames.
Before this commit, if the decompression is enabled, the ng_ppp(4)
node would send and incoming frame to the "decompress" hook
only if it has the PROT_COMPD proto tag on it.
After this commit an alternative decompression mode can be set.
In this mode the node sends all the incoming packets to the
decompression hook. This is important for such kind of compressors
that need uncompressed packets too, to keep their library in sync.
These new features will be used in new version of mpd4, and in new
compressor nodes.
Submitted by: Alexander Motin <mav alkar.net>