Rather than calling mircotime() in catchpacket(), make catchpacket()
take a timeval indicating when the packet was captured. Move
microtime() to the calling functions and grab the timestamp as soon
as we know that we're going to call catchpacket at least once.
This means that we call microtime() once per matched packet, as
opposed to once per matched packet per bpf listener. It also means
that we return the same timestamp to all bpf listeners, rather than
slightly different ones.
It would be more accurate to call microtime() even earlier for all
packets, as you have to grab (1+#listener) locks before you can
determine if the packet will be logged. You could always grab a
timestamp before the locks, but microtime() can be costly, so this
didn't seem like a good idea.
(I guess most ethernet interfaces will have a bpf listener these
days because of dhclient. That means that we could be doing two bpf
locks on most packets going through the interface.)
and net.bpf.peers sysctls respectively.
A new structure was added to describe the external (user viewable)
representation of a BPF file; a new entry was added to the bpf_d
structure to store the PID of the calling process; a simple_lock was added
to protect the insert/removal from the net.bpf.peers sysctl handler.
This idea came from FreeBSD (Christian S.J. Peron) but while it is
implemented with sysctl's it differs a bit.
Reviewed by: christos@ and atatat@ (who gave me the tip for the net.bpf.peers
sysctl helper function).
The __UNCONST macro is now used only where necessary and the RW macros
are gone. Most of the changes here are consumers of the
sysctl_createv(9) interface that now takes a pair of const pointers
which used not to be.
Add bpf_deliver prototype.
Rename bpf_measure to m_length and move it to sys/sys/mbuf.h. I
make m_length an inline function in the header file to preserve
its performance characteristics, for better or for worse.
Optimize m_length: use the length in m_pkthdr.len, if M_PKTHDR.
In bpf_deliver, zero the on-stack mbuf before we do anything else
with it.
particule device. In doing this, make a new the bpf_stat structure with
members that are u_long rather than u_int, matching the counters in the bpf_d.
the original bpf_stat is now bpf_stat_old and so to the original ioctl
is preserved as BIOCGSTATSOLD.
not a read operation should be allowed to sleep. This allows the use of
bd_rtout with a value of "-1" to be eliminated (signed comparison and
assignment to an unsigned long.)
* in 1.91, a change was introduced that had bpfpoll() returning POLLRDNORM
set when the timeout expired. This impacted poorly on performance as well
as causing select to return an fd available for reading when it wasn't.
Change the behaviour here to only allow the possibility of POLLIN being
returned as active in the event of a timeout.
Fix the behaviour of BIOCIMMEDIATE (fix from LBL BPF code via FreeBSD.)
In bpf_mtap(), optimise the calling of bpf_filter() and catchpacket()
based on whether or not the entire packet is in one mbuf (based on
similar change FreeBSD but fixes BIOC*SEESENT issue with that.)
Copy the implementation of BIOCSSEESENT, BIOCGSEESENT by FreeBSD.
Review Assistance: Guy Harris
PRs: kern/8674, kern/12170
Increase the default bpf buffer size used by naive apps that don't do
BIOCSBLEN, from 8k to 32k. The former value of 8192 is too small to
hold a normal jumbo Ethernet frame (circa 9k), 16k is a little small
for Large-jumbo (~16k) frames supported by newer gigabit
Ethernet/10Gbe, so (somewhat arbitrarily) increase the default to 32k.
Increase the upper limit to which BIOSBLEN can raise bpf buffer-size
drastically, to 1 Mbyte. State-of-the-art for packet capture circa
1999 was around 256k; savvy NetBSD developers now use 1 Mbyte.
Note that libpcap has been updated to do binary-search on BIOCSBLEN
values up to 1 Mbyte.
Work is in progress to make both values sysctl'able. Source comments
note that consensus on tech-net is that we should find some heuristic
to set the boot-time default values dynamically, based on system memory.
* introduce fsetown(), fgetown(), fownsignal() - this sets/retrieves/signals
the owner of descriptor, according to appropriate sematics
of TIOCSPGRP/FIOSETOWN/SIOCSPGRP/TIOCGPGRP/FIOGETOWN/SIOCGPGRP ioctl; use
these routines instead of custom code where appropriate
* make every place handling TIOCSPGRP/TIOCGPGRP handle also FIOSETOWN/FIOGETOWN
properly, and remove the translation of FIO[SG]OWN to TIOC[SG]PGRP
in sys_ioctl() & sys_fcntl()
* also remove the socket-specific hack in sys_ioctl()/sys_fcntl() and
pass the ioctls down to soo_ioctl() as any other ioctl
change discussed on tech-kern@
When using bpf(4) in immediate mode, and using kevent(2) to receive
notification of packet arrival, the usermode application isn't notified
until a second packet arrives.
This is because KNOTE() calls filt_bpfread() before bd_slen has been
updated with the newly arrived packet length, so it looks like there
is no data there.
Moving the bpf_wakeup() call for immediate mode to after bd_slen is set
fixes it.
From: wayne@epipe.com.au in pr 3175
be inserted into ktrace records. The general change has been to replace
"struct proc *" with "struct lwp *" in various function prototypes, pass
the lwp through and use l_proc to get the process pointer when needed.
Bump the kernel rev up to 1.6V
Do a little mbuf rework while here. Change all uses of MGET*(*, M_WAIT, *)
to m_get*(M_WAIT, *). These are not performance critical and making them
call m_get saves considerable space. Add m_clget analogue of MCLGET and
make corresponding change for M_WAIT uses.
Modify netinet, gem, fxp, tulip, nfs to support MBUFTRACE.
Begin to change netstat to use sysctl.
kqueue provides a stateful and efficient event notification framework
currently supported events include socket, file, directory, fifo,
pipe, tty and device changes, and monitoring of processes and signals
kqueue is supported by all writable filesystems in NetBSD tree
(with exception of Coda) and all device drivers supporting poll(2)
based on work done by Jonathan Lemon for FreeBSD
initial NetBSD port done by Luke Mewburn and Jason Thorpe