trasz [Thu, 3 Dec 2009 19:16:40 +0000 (19:16 +0000)]
Description of steps required to setup NFSv4 server is in nfsv4(4);
add reference to exports(5), since that's the obvious starting point
for searching for this.
Instead of digging through the utmp database by hand, use proper API
calls to do so. Instead of parsing entries with a non-empty ut_user, we
now look at LOGIN_PROCESS entries.
avg [Thu, 3 Dec 2009 16:10:21 +0000 (16:10 +0000)]
mca: small enhancements related to cpu quirks
- use utility macros for CPU family/model checking
- limit Intel P6 quirk to pre-Nehalem models (taken from OpenSolaris)
- add AMD GartTblWkEn quirk for families 0Fh and 10h; I haven't experienced
any problems without the quirk but both Linux and OpenSolaris do this
- slightly re-arrange quirk code to provide for the future generalization
and separation of vendor-specific quirk functions
syrinx [Thu, 3 Dec 2009 16:08:00 +0000 (16:08 +0000)]
Fix a problem with high CPU consumption (up to 30%) by bsnmpd on a loaded system.
Instead of constantly calling the mibII_idle function when the server is not busy
call the function only once every 10 seconds to avoid bsnmpd constantly doing
gettimeofday syscalls. Make the idle polling interval confugurable via
begemotIfDataPoll.
Reported and tested by: misho (at) aitbg (dot) com
Oked by: harti
MFC after: 1 week
One of the things I really want to do, is to get rid of the limitations
of our current utmp(5) mechanism:
- It only allows 8 byte TTY device names.
- The hostname only allows 16 bytes of storage.
I'm not a big fan of <utmpx.h>, but I think we should at least try to
add parts of it. Unfortunately we cannot implement <utmpx.h>, because we
miss various fields, such as ut_id, ut_pid, etc. The API provided by
libulog shares some similarities with <utmpx.h>, so it shouldn't be too
hard to port these applications eventually. In most simple cases, it
should just be a matter of removing the ulog_ prefix everywhere.
As a bonus, it also implements a function called ulog_login_pseudo(),
which allows unprivileged applications to write log entries, provided
they have a valid file descriptor to a pseudo-terminal master device.
libulog will allow a smoother transition to a new file format by adding
a library interface to deal with utmp/wtmp/lastlog files. I initially
thought about adding the functionality to libutil, but because I'm not
planning on keeping this library around forever, we'd better keep it
separated.
Next items on the todo list:
1. Port applications in the base system (and ports) to libulog, instead
of letting them use <utmp.h>.
2. Remove <utmp.h>, implement <utmpx.h> and reimplement this library on
top.
3. Port as many applications as possible back to <utmpx.h>.
jhb [Thu, 3 Dec 2009 15:14:30 +0000 (15:14 +0000)]
The fd_mask type is an unsigned long, not an int, so treat the mask as a
long instead of an int when examining the results of select() to look for
RPC requests. Previously this routine would ignore RPC requests to sockets
whose file descriptor mod 64 was greater than 31 on a 64-bit platform.
PR: amd64/141130
Submitted by: liujb of array networks
MFC after: 3 days
luigi [Thu, 3 Dec 2009 14:22:15 +0000 (14:22 +0000)]
preparation work to replace the monster switch in ipfw_chk() with
table of functions.
This commit (which is heavily based on work done by Marta Carbone
in this year's GSOC project), removes the goto's and explicit
return from the inner switch(), so we will have a easier time when
putting the blocks into individual functions.
trasz [Thu, 3 Dec 2009 13:29:24 +0000 (13:29 +0000)]
Add change that was somehow missed in r192586. It could manifest by
incorrectly returning EINVAL from acl_valid(3) for applications linked
against pre-8.0 libc.
avg [Thu, 3 Dec 2009 08:11:20 +0000 (08:11 +0000)]
ichsmb: try attaching only to intel hardware in the default case
Ideally we should attempt attaching only to known supported devices.
But I am not sure that we have all supported PCI IDs already listed,
and I am too young to die, err, I don't want to take the heat from
causing a trouble to someone.
marcel [Thu, 3 Dec 2009 04:06:48 +0000 (04:06 +0000)]
Make sure bus space accesses use unorder memory loads and stores.
Memory accesses are posted in program order by virtue of the
uncacheable memory attribute.
Since GCC, by default, adds acquire and release semantics to
volatile memory loads and stores, we need to use inline assembly
to guarantee it. With inline assembly, we don't need volatile
pointers anymore.
Itanium does not support semaphore instructions to uncacheable
memory.
luigi [Wed, 2 Dec 2009 17:50:52 +0000 (17:50 +0000)]
- initialize src_ip in the main loop to prevent a compiler warning
(gcc 4.x under linux, not sure how real is the complaint).
- rename a macro argument to prevent name clashes.
- add the macro name on a couple of #endif
- add a blank line for readability.
kib [Wed, 2 Dec 2009 16:34:20 +0000 (16:34 +0000)]
Properly support -fPIE by linking PIE binaries with specially-built
Scrt1.o instead of crt1.o, since the later is built as non-PIC.
Separate i386-elf crt1.c into the pure assembler part and C code,
supplying all data extracted by assembler stub as explicit parameters [1].
Hide and localize _start1 symbol used as an interface between asm and
C code.
In collaboration with: kan
Inspired by: PR i386/127387 [1]
Prodded and tested by: rdivacky [1]
MFC after: 3 weeks
jhb [Wed, 2 Dec 2009 16:26:18 +0000 (16:26 +0000)]
ndis_scan_results() can sleep if the scan results are not ready when
ndis_scan() is called. However, ndis_scan() is invoked from softclock()
and cannot sleep. Move ndis_scan_results() to the ndis' driver's scan_end
hook instead.
Submitted by: Paul B Mahol onemda of gmail
MFC after: 1 week
luigi [Wed, 2 Dec 2009 15:50:43 +0000 (15:50 +0000)]
Dispatch sockopt calls to ipfw and dummynet
using the new option numbers, IP_FW3 and IP_DUMMYNET3.
Right now the modules return an error if called with those arguments
so there is no danger of unwanted behaviour.
avg [Wed, 2 Dec 2009 15:45:55 +0000 (15:45 +0000)]
mca: improve status checking, recording and reporting
- directly print mca information in case we fail to allocate memory
for a record
- include bank number into mca record
- print raw mca status value for extended information
luigi [Wed, 2 Dec 2009 15:20:31 +0000 (15:20 +0000)]
small changes for portability and diff reduction wrt/ FreeBSD 7.
No functional differences.
- use the div64() macro to wrap 64 bit divisions
(which almost always are 64 / 32 bits) so they are easier
to handle with compilers or OS that do not have native
support for 64bit divisions;
- use a local variable for p_numbytes even if not strictly
necessary on HEAD, as it reduces diffs with FreeBSD7
- in dummynet_send() check that a tag is present before
dereferencing the pointer.
- add a couple of blank lines for readability near the end of a function
glebius [Wed, 2 Dec 2009 13:24:21 +0000 (13:24 +0000)]
Until this moment carp(4) used a strange logging priority. It used debug
priority for such important information as MASTER/BACKUP state change,
and used a normal logging priority for such innocent messages as receiving
short packet (which is a normal VRRP packet between some other routers) or
receving a CARP packet on non-carp interface (someone else running CARP).
This commit shifts message logging priorities to a more sane default.
luigi [Wed, 2 Dec 2009 08:52:06 +0000 (08:52 +0000)]
change the type of the opcode from enum *:8 to u_int8_t
so the size and alignment of the ipfw_insn is not compiler dependent.
No changes in the code generated by gcc.
There was only one instance of this kind in our entire source tree,
so i suspect the old definition was a poor choice (which i made).
Don't allocate an input buffer for a TTY when the receiver is turned off.
When the termios CREAD flag is not set, it makes little sense to
allocate an input buffer. Just set the size to 0 in this case to reduce
memory footprint.
Disallow CREAD to be disabled for pseudo-devices to prevent
foot-shooting.
gibbs [Tue, 1 Dec 2009 17:29:25 +0000 (17:29 +0000)]
Add media ioctl support and link notifications so that devd will attempt
to run dhclient on a netfront (xn) device that is setup for DHCP in
/etc/rc.conf.
PR: kern/136251 (fixed differently than the submitted patch)
keramida [Tue, 1 Dec 2009 06:12:31 +0000 (06:12 +0000)]
Describe what setpgid(2) does when pgid=0. The text has been
copied from NetBSD's manpage, and it also matches the behavior
described by the Open Group's online copy of setpgid.2 at
http://www.opengroup.org/onlinepubs/009695399/functions/setpgid.html
green [Tue, 1 Dec 2009 05:04:31 +0000 (05:04 +0000)]
Do not gratuitously fail *env(3) operations due to corrupt ('='-less)
**environ entries. This puts non-getenv(3) operations in line with
getenv(3) in that bad environ entries do not cause all operations to
fail. There is still some inconsistency in that getenv(3) in the
absence of any environment-modifying operation does not emit corrupt
environ entry warnings.
I also fixed another inconsistency in getenv(3) where updating the
global environ pointer would not be reflected in the return values.
It would have taken an intermediary setenv(3)/putenv(3)/unsetenv(3)
in order to see the change.
jhb [Mon, 30 Nov 2009 21:03:44 +0000 (21:03 +0000)]
Remove extra parantheses from usb_ethernet.c and usb_serial.c lines.
config(8) doesn't parse parantheses and instead treated them as being
part of the device driver name (e.g. '(u3g' vs 'u3g'). While here, fix the
style of these long lines to match the wrapping used for other long lines
in this file.
avg [Mon, 30 Nov 2009 11:44:03 +0000 (11:44 +0000)]
amdsbwd: new driver for AMD SB600/SB7xx watchdog timer
The hardware is compliant with WDRT specification, so I originally
considered including generic WDRT watchdog support, but decided
against it, because I couldn't find anyone to the code for me.
WDRT seems to be not very popular.
Besides, generic WDRT porbably requires a slightly different driver
approach.
dougb [Mon, 30 Nov 2009 03:38:34 +0000 (03:38 +0000)]
Update to BIND 9.6.1-P2. The vulnerability this is designed to fix is
related to DNSSEC validation on a resolving name server that allows
access to untrusted users. If your system does not fall into all 3 of
these categories you do not need to update immediately.
jilles [Sun, 29 Nov 2009 22:33:59 +0000 (22:33 +0000)]
Fix some cases where file descriptors from redirections leak to programs.
- Redirecting fds that were not open before kept two copies of the
redirected file.
sh -c '{ :; } 7>/dev/null; fstat -p $$; true'
(both fd 7 and 10 remained open)
- File descriptors used to restore things after redirection were not
set close-on-exec, instead they were explicitly closed before executing
a program normally and before executing a shell procedure. The latter
must remain but the former is replaced by close-on-exec.
sh -c 'exec 7</; { exec fstat -p $$; } 7>/dev/null; true'
(fd 10 remained open)
The examples above are simpler than the testsuite because I do not want to
use fstat or procstat in the testsuite.
nwhitehorn [Sun, 29 Nov 2009 20:48:19 +0000 (20:48 +0000)]
Early-generation touchpads do not send periodic calibration frames for
baseline subtraction, and are very temperature sensitive, so would slowly
drift out of a calibrated state when under load. Escape this by taking
the last frame before we decide that the pad is idle as a finger-free
baseline.
marcel [Sun, 29 Nov 2009 20:17:50 +0000 (20:17 +0000)]
Move the sysctl related fields to the end of the structure and
make them conditional upon _KERNEL. libkvm includes <sys/pcpu.h>
and <sys/sysctl.h> does not expose the structure definitions to
userland.
bz [Sun, 29 Nov 2009 17:53:57 +0000 (17:53 +0000)]
In case the compression result is the same size as the orignal version,
the compression was useless as well. Make sure to not update the data
and return, else we would waste resources when decompressing.
This also avoids the copyback() changing data other consumers like
xform_ipcomp.c would have ignored because of no win and sent out without
noting that compression was used, resulting in invalid packets at the
receiver.
bz [Sun, 29 Nov 2009 10:53:34 +0000 (10:53 +0000)]
Only add the IPcomp header if crypto reported success and we have a lower
payload size. Before we had always added the header, no matter if we
actually send out compressed data or not.
With this, after the opencrypto/deflate changes, IPcomp starts to work
apart from edge cases. Leave it disabled by default until those are
fixed as well.
ed [Sat, 28 Nov 2009 23:50:48 +0000 (23:50 +0000)]
Decompose <sys/termios.h>.
The <sys/termios.h> header file is hardlinked to <termios.h>. It
contains both the structures and the flag definitions, but also the C
library interface that's implemented by the C library.
This header file has the typical problem of including too many random
things and being badly ordered. Instead of trying to fix this, decompose
it into two header files:
- <sys/_termios.h>, which contains struct termios and the flags.
- <termios.h>, which includes <sys/_termios.h> and contains the C
library interface.
This means userspace has to include <termios.h> for struct termios,
while kernelspace code has to include <sys/tty.h>. Also add a
<sys/termios.h>, which prints a warning message before including
<termios.h>. I am aware that there are some applications that use this
header file as well.
bz [Sat, 28 Nov 2009 21:08:19 +0000 (21:08 +0000)]
Change memory managment from a fixed size array to a list.
This is needed to avoid running into out of buffer situations
where we cannot alloc a new buffer because we hit the array size
limit (ZBUF).
Use a combined allocation for the struct and the actual data buffer
to not increase the number of malloc calls. [1]
Defer initialization of zbuf until we actually need it.
Make sure the output buffer will be large enough in all cases.
marcel [Sat, 28 Nov 2009 21:01:15 +0000 (21:01 +0000)]
Eliminate teh use of MAXCPU in static arrays of interrupt counters by
adding statistics counters to the PCPU structure. Export the counters
through sysctl by giving each PCPU structure its own sysctl context.
While here, fix cnt.v_intr by not just having it count clock interrupts,
but every interrupt and add more counters for each interrupt source.
bz [Sat, 28 Nov 2009 17:44:57 +0000 (17:44 +0000)]
Z_PARTIAL_FLUSH is marked deprecated. Z_SYNC_FLUSH is the suggested
replacement but only use it for inflate. For deflate use Z_FINISH
as Z_SYNC_FLUSH adds a trailing marker in some cases that inflate(),
despite the comment in zlib, does npt seem to cope well with, resulting
in errors when uncompressing exactly fills the outbut buffer without
a Z_STREAM_END and a successive call returns an error.
nwhitehorn [Sat, 28 Nov 2009 17:33:19 +0000 (17:33 +0000)]
Add a CPU features framework on PowerPC and simplify CPU setup a little
more. This provides three new sysctls to user space:
hw.cpu_features - A bitmask of available CPU features
hw.floatingpoint - Whether or not there is hardware FP support
hw.altivec - Whether or not Altivec is available
ed [Sat, 28 Nov 2009 16:30:06 +0000 (16:30 +0000)]
Include <sys/tty.h> instead of <sys/termios.h>.
Right now <sys/termios.h> includes <sys/ttycom.h>, which provides the
TTY ioctls to the svr4 code. We need both struct termios and the ioctls,
so include <sys/tty.h> for now.
kib [Sat, 28 Nov 2009 14:29:32 +0000 (14:29 +0000)]
Allow to load not-openable dso when tracing. This fixes ldd on such dso or
dso linked to non-openable object.
Remove '\n' at the end of error message.
End comments with dot.
trasz [Sat, 28 Nov 2009 11:57:43 +0000 (11:57 +0000)]
Provide a set of sysctls and tunables to disable device node creation
for specific "kinds" of disk labels - for example, GPT UUIDs. Reason
for this is that sometimes, other GEOM classes attach to these device
nodes instead of the proper ones - e.g. they attach to /dev/gptid/XXX
instead of /dev/ada0p2, which is annoying.