Commit Graph

151004 Commits

Author SHA1 Message Date
Jilles Tjoelker
e1ef314121 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.
2009-11-29 22:33:59 +00:00
Bjoern A. Zeeb
fbd69dff68 Correct typo.
Reported by:	gabor
MFC after:	5 days
2009-11-29 21:03:54 +00:00
Nathan Whitehorn
2c494821d4 Add atp(4) to powerpc GENERIC. Most late-generation Apple PowerPC laptops
have trackpads that do not work at all without this driver.
2009-11-29 20:51:23 +00:00
Nathan Whitehorn
d7e7c660b4 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.

Tested on:	iBook G4
2009-11-29 20:48:19 +00:00
Bjoern A. Zeeb
a77cb332ee Enable IPcomp by default.
PR:		kern/123587
MFC after:	5 days
2009-11-29 20:47:43 +00:00
Bjoern A. Zeeb
90b4c081d0 Add more statistics variables for IPcomp.
Try to version the struct in a backward compatible way.
People asked for the versioning of the stats structs in general before.

MFC after:	5 days
2009-11-29 20:37:30 +00:00
Marcel Moolenaar
6852bd671f 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.
2009-11-29 20:17:50 +00:00
Bjoern A. Zeeb
df4dece102 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.

MFC after:	5 days
2009-11-29 17:53:57 +00:00
Bjoern A. Zeeb
10229cd109 Assimilate very similar input and output code paths
(no real functional change).

MFC after:	5 days
2009-11-29 17:47:49 +00:00
Bjoern A. Zeeb
d8ce467304 Add SDT iter probes forgotten in r199885.
MFC after:	5 days
2009-11-29 17:46:40 +00:00
Bjoern A. Zeeb
afa47e51aa 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.

PR:		kern/123587
MFC after:	5 days
2009-11-29 10:53:34 +00:00
Ed Schouten
f14ad5fa40 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.
2009-11-28 23:50:48 +00:00
Bjoern A. Zeeb
3d34d241be Remove whitespace.
MFC after:	6 days
2009-11-28 21:42:39 +00:00
Bjoern A. Zeeb
4ff9852103 Directly send data uncompressed if the packet payload size is lower than
the compression algorithm threshold.

MFC after:	6 days
2009-11-28 21:40:57 +00:00
Bjoern A. Zeeb
6f443bec58 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.

Details discussed with:	kib [1]
Reviewed by:		kib [1]
MFC after:		6 days
2009-11-28 21:08:19 +00:00
Bjoern A. Zeeb
023795f033 Correct a typo.
MFC after:	6 days
2009-11-28 21:01:26 +00:00
Marcel Moolenaar
1011cc260e 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.
2009-11-28 21:01:15 +00:00
Nathan Whitehorn
f697a802bb Add support for interpreting taps on ADB touchpads as a button click.
Submitted by:	Andreas Tobler <andreast-list at fgznet dot ch>
MFC after:	2 weeks
2009-11-28 17:48:25 +00:00
Bjoern A. Zeeb
9699afb61b 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.

MFC after:	6 days
2009-11-28 17:44:57 +00:00
Nathan Whitehorn
227f66048e 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

PR:		powerpc/139154
MFC after:	10 days
2009-11-28 17:33:19 +00:00
Bjoern A. Zeeb
d9c18e5627 Add SDT probes for opencrypto:deflate:deflate_gobal:*.
They are not nice but they were helpful.

MFC after:	6 days
2009-11-28 17:20:41 +00:00
Bjoern A. Zeeb
df21ad6e41 Define an SDT provider for "opencrypto".
MFC after:	6 days
2009-11-28 16:54:18 +00:00
Bjoern A. Zeeb
e7ad2d3410 Add SDT_PROBE[1-5] in the same way we have SDT_PROBE_DEFINE[1-5] to
avoid having to add all the unused trailing arguments as zeros.

MFC after:	6 days
2009-11-28 16:47:42 +00:00
Ed Schouten
0ab939d261 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.
2009-11-28 16:30:06 +00:00
Ed Schouten
5b19140604 Include <sys/ttydefaults.h>, instead of doing it through <sys/termios.h>.
I want to prevent the header polution of <sys/termios.h> eventually.
2009-11-28 16:25:55 +00:00
Konstantin Belousov
6d772c3b9e Revert r199830 for now. Too many ports dlopen() libraries linked with
libthr, but forgot to link main binary with it.
2009-11-28 14:34:28 +00:00
Konstantin Belousov
abf48e8311 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.

MFC after:	3 weeks (together with r199829)
2009-11-28 14:29:32 +00:00
Ed Schouten
d343f5397d Remove unneeded inclusion of <sys/termios.h>. 2009-11-28 13:20:29 +00:00
Edward Tomasz Napierala
3ce9ca8947 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.

Reviewed by:	pjd (earlier version)
MFC after:	1 month
2009-11-28 11:57:43 +00:00
Ed Schouten
ea74c11fae Use <termios.h> instead of <sys/termios.h>.
<sys/termios.h> only works on FreeBSD by accident.
2009-11-28 11:57:25 +00:00
Daniel Gerzo
1743ff6a01 - correct xref sections
PR:		docs/140940
Submitted by:	Bruce Cran <bruce@cran.org.uk>
MFC after:	1 week
2009-11-28 11:27:37 +00:00
Ed Schouten
f02d50a3c8 Remove unneeded includes of <sys/termios.h>. 2009-11-28 11:13:50 +00:00
Daniel Gerzo
a2ec746f79 - correctly render the provided example
PR:		docs/140962
Submitted by:	mharo
2009-11-28 11:05:22 +00:00
Alan Cox
79f6ebe233 Properly synchronize the previous change. 2009-11-28 00:50:09 +00:00
Alan Cox
d8778512cf Support the new VM_PROT_COPY option on wired pages. The effect of which
is that a debugger can now set a breakpoint in a program that uses mlock(2)
on its text segment or mlockall(2) on its entire address space.
2009-11-27 22:08:29 +00:00
Alan Cox
e2997fea72 Simplify the invocation of vm_fault(). Specifically, eliminate the flag
VM_FAULT_DIRTY.  The information provided by this flag can be trivially
inferred by vm_fault().

Discussed with:	kib
2009-11-27 20:24:11 +00:00
Tony Finch
137f2acad4 unifdef: fix invalid array access when nesting limit exceeded
If the number of nested #if blocks exceeds 64, nest() increments
the nesting depth and then reports an error.  The message includes
the line number for the start of the current #if block, which is
read from past the end of the relevant array.

Avoid the out-of-bounds read by reporting the error and exiting
before the nesting depth has a chance to increase.

Submitted by: Jonathan Nieder <jrnieder@gmail.com>
2009-11-27 17:53:49 +00:00
Michael Tuexen
dec7fa27c6 Use the default stack size for the iterator thread.
This fixes a crash reported by Irene Ruengeler.

Approved by: rrs (mentor)
MFC after: 1 month
2009-11-27 17:25:19 +00:00
Maxim Sobolev
5d695da1d7 Remove spinconsole from pc98, some parts seem to be missed and it's
too late (early?) to figure out what exactly.

Reported by:	TAKAHASHI Yoshihiro
2009-11-27 13:19:06 +00:00
Peter Pentchev
2cacf8cffb Fix the cross-reference to sctp_opt_info in the text - section 3, not 2.
PR:		140938
Submitted by:	Bruce Cran <bruce@cran.org.uk>
MFC after:	2 weeks
2009-11-27 13:08:25 +00:00
Ed Schouten
f67d07f0e1 Properly use the envp argument in execvPe().
execvPe() is called by _execvpe(), which we added to implement
posix_spawnp(). We just took execvP() and added the envp argument.
Unfortunately we forgot to change the implementation to use envp over
environ.

This fixes the following piece of code:

| char * const arg[2] = { "env", NULL };
| char * const env[2] = { "FOO=BAR", NULL };
| posix_spawnp(NULL, "/usr/bin/env", NULL, NULL, arg, env);

MFC after:	2 weeks
2009-11-27 13:05:14 +00:00
Maxim Konovalov
1439785421 o HEAD is FreeBSD 9-current now.
Submitted by:	Alex Kozlov
2009-11-27 07:55:39 +00:00
Maxim Konovalov
90d49b091a o FreeBSD 8.0 added. 2009-11-27 06:23:47 +00:00
Maxim Sobolev
12ff431c6c Whitespace-only: another instance of identation with spaces. 2009-11-27 04:00:52 +00:00
Maxim Sobolev
8e67cba0d8 Whitespace on: use tabs for identation consistently. 2009-11-27 03:58:21 +00:00
Maxim Sobolev
c4c3b35172 Add new loader console type: "spinconsole". This console selects the
video console which doesn't take any input from keyboard and hides
all output replacing it with ``spinning'' character (useful for
embedded products and custom installations).

Sponsored by:	Sippy Software, Inc.
2009-11-27 03:55:42 +00:00
Attilio Rao
385e11118c i386 has not (yet) any DEV_ATPIC conditional than axe it out from Xen
version.

No objections by:	kmacy
2009-11-27 01:02:17 +00:00
Alexander Motin
eb3d6abdf9 Add two Cirrus Logic codec IDs.
Add GPIO setting quirk for Apple MacBookPro5,5.

Submitted by:	ed
2009-11-26 20:25:57 +00:00
Jaakko Heinonen
909e260153 Reset path name back to original correctly in fts_build() when
FTS_NOCHDIR option is used. fts_build() could strip a trailing slash
from path name in post-order visit if a path pointing to an empty
directory was given for fts_open().

PR:		bin/133907, kern/134513
Reviewed by:	das
Approved by:	trasz (mentor)
MFC after:	1 month
2009-11-26 19:11:44 +00:00
Jaakko Heinonen
8d6956fb6b Clarify that the value of the fts_info field is different in post-order.
Discussed with:	das
Approved by:	trasz (mentor)
MFC after:	1 week
2009-11-26 19:09:10 +00:00