Commit Graph

164790 Commits

Author SHA1 Message Date
Gleb Smirnoff
062393fe00 Don't leak kld_sx lock in kldunloadf().
Approved by:	re (kib)
2011-07-31 13:49:15 +00:00
Adrian Chadd
4b326fda72 Remove two debugging printf()s which snuck in during the testing of the
last commit.

Approved by:	re (kib)
Pointy-hat-to:	adrian@
2011-07-31 08:13:25 +00:00
Adrian Chadd
45abcd6c9c Implement the 4KB split transaction workaround for Merlin (AR9280).
The AR9280 apparently has an issue with descriptors which straddle a page
boundary (4k). I'm not yet sure whether I should use PAGE_SIZE in the
calculations or whether I should use 4096; the reference code uses 4096.

This patch fiddles with descriptor allocation so a descriptor entry
doesn't straddle a 4kb address boundary. The descriptor memory allocation
is made larger to contain extra descriptors and then the descriptor
address is advanced to the next 4kb boundary where needed.

I've tested this both on Merlin (AR9280) and non-Merlin (in this case,
AR9160.)

Obtained from:	Linux, Atheros
Approved by:	re (kib)
2011-07-31 08:01:41 +00:00
Adrian Chadd
ab7aca78ca Fix typo!
Approved by:	re (kib)
2011-07-31 05:59:33 +00:00
Adrian Chadd
44ade163ce Add extra flags for the radar event API.
(They're not used by any public code at the current time.)

Approved by:	re (kib)
2011-07-31 05:01:42 +00:00
Adrian Chadd
6eec7effeb Add some more phyerr bits.
Obtained from:	Atheros
Approved by:	re (kib)
2011-07-31 03:33:02 +00:00
Craig Rodrigues
46d20cbcf1 Pull in some wording to the tftpd.8 man page
from NetBSD, with some slight changes:

=========================================================================================
http://cvsweb.netbsd.org/bsdweb.cgi/src/libexec/tftpd/tftpd.8?only_with_tag=MAIN#rev1.22

Revision 1.22 or diffs], Fri Jan 8 21:05:14 2010 UTC (18 months, 2 weeks ago) by christos

Patrick Welche <prlw1@cam.ac.uk>
    - add -p pathsep option
    - make wrap to zero work, but produce a warning
While here:
    - fix gcc warnings, in particular variable clobbered warnings
      (compiling with fewer warnings does not really fix the problem)
=========================================================================================

These wording changes clarify the default rollover behavior
as a "kludge".  Also, the block numbers and octet counts for 65535 blocks
and 32767 blocks are more accurate than the existing documented numbers.

Requested by:   Pawan Gupta <pawang at juniper dot net>
Obtained from:  Juniper Networks
Approved by:    re (kib)
2011-07-31 03:18:36 +00:00
Craig Rodrigues
38bd7db313 In the old TFTP server, there was an undocumented behavior where
the block counter would rollover to 0 if a file larger
than 65535 blocks was transferred.  With the default block size
of 512 octets per block, this is a file size of approximately 32 megabytes.

The new TFTP server code would report an error and stop transferring
the file if a file was larger than 65535 blocks.

This patch restores the old TFTP server's behavior to the new
TFTP server code.  If a TFTP client transfers a file larger
than 65535 blocks, and does *not* specify the "rollover" option,
then automatically rollover the block counter to 0 every time
we reach 65535 blocks.

This restores interoperability with the FreeBSD 6 TFTP client.
Without this change, if a FreeBSD 6 TFTP client tried to
retrieve a file larger than 65535 blocks from a FreeBSD 9 TFTP server
, the transfer would fail.
The same file could be retrieved successfully if the same FreeBSD 6
TFTP client was used against a FreeBSD 6 TFTP server.

Approved by:  re (kib)
Tested by: Pawan Gupta <pawang at juniper dot net>,
Obtained from:  Juniper Networks
2011-07-31 03:12:20 +00:00
Xin LI
cfc3f46787 Backout r223115 which potentially caused a POLA violation, by restoring
historic behavior (create the default base directory in pw.conf) before
I came up with a better fix for this.

Requested by:	nwhitehorn
Approved by:	re (kib)
2011-07-31 03:00:00 +00:00
Joel Dahl
89e250512d Add a better description, a few examples and a couple of minor fixes.
Reviewed by:	brueffer
Approved by:	re (kib)
2011-07-30 23:09:52 +00:00
Rick Macklem
d1907de2ba The new NFS client failed to vput() the new vnode if a setattr
failed after the file was created in nfs_create(). This would
probably only happen during a forced dismount. The old NFS client
does have a vput() for this case. Detected by pho during recent
testing, where an open syscall returned with a vnode still locked.

Tested by:	pho
Approved by:	re (kib)
MFC after:	2 weeks
2011-07-30 22:57:38 +00:00
Alexander Motin
10a6c3584a Higher-priority initialization request can eat request scheduling done from
adaclose(). Add immediate_priority check into adaschedule() to restore it.

Approved by:	re (kib)
MFC after:	1 week
2011-07-30 21:42:53 +00:00
Andriy Gapon
88e14bfb6a fix a typo/tautology in the release documentation
Approved by:	re (kib)
MFC after:	1 week
2011-07-30 21:09:45 +00:00
Andriy Gapon
235cc4c620 update smp related documentation after recent changes
Remove references to machdep.hlt_logical_cpus and
machdep.hlt_cpus sysctls and tunables.
Document machdep.hyperthreading_allowed and
hint.lapic.X.disabled tunables.

Prompted by:	ru
Proofreading:	bf
Reviewed by:	jhb
Approved by:	re (kib)
2011-07-30 20:42:14 +00:00
Andriy Gapon
35edc49853 smp_rendezvous: master cpu should wait until all slaves are fully done
This is a followup to r222032 and a reimplementation of it.
While that revision fixed the race for the smp_rv_waiters[2] exit
sentinel, it still left a possibility for a target CPU to access
stale or wrong smp_rv_func_arg in smp_rv_teardown_func.
To fix this race the slave CPUs signal when they are really fully
done with the rendezvous and the master CPU waits until all slaves
are done.

Diagnosed by:	kib
Reviewed by:	jhb, mlaier, neel
Approved by:	re (kib)
MFC after:	2 weeks
2011-07-30 20:29:39 +00:00
Martin Matuska
4e1407c428 Fix serious bug in ZIL that can lead to pool corruption
in the case of a held dataset during remount.

Detailed description is available at:
https://www.illumos.org/issues/883

illumos-gate revision:	13380:161b964a0e10

Reviewed by:	pjd
Approved by:	re (kib)
Obtained from:	Illumos (Bug #883)
MFC after:	3 days
2011-07-30 19:00:31 +00:00
Martin Matuska
3036062f0c Fix wrong initialization of "cmd" for calling the jail/unjail ioctl.
Reviewed by:	pjd@, delphij@
Approved by:	re (kib)
MFC after:	3 days
2011-07-30 17:44:06 +00:00
Martin Matuska
b8596ed3ac Fix accidential dos-style endings to unix-style line endings
from last commit (r224523) to match the version approved by re@

Approved by:	re (implicit)
2011-07-30 17:40:11 +00:00
Martin Matuska
6cf3367c6d Fix invalid assertion of C++ external static data member declarations
as anonymous namespaces are local to the current translation.

GCC PR:		c++/33094

Reviewed by:	uqs
Approved by:	re (kib)
Obtained from:	gcc (branches/redhat/gcc-4_1-branch, rev. 129554, GPLv2)
MFC after:	1 week
2011-07-30 17:27:29 +00:00
Konstantin Belousov
339772b003 Fix a race in the device pager allocation. If another thread won and
allocated the device pager for the given handle, then the object
fictitious pages list and the object membership in the global object
list still need to be initialized. Otherwise, dev_pager_dealloc() will
traverse uninitialized pointers.

Reported and tested by: pho
Reviewed by:    jhb
Approved by:	re (kensmith)
MFC after:      1 week
2011-07-30 14:13:57 +00:00
Konstantin Belousov
889dffba25 Fix the devmtx lock leak from make_dev(9) when the old device cloning
failed due to invalid or duplicated path being generated.

Reviewed by:	jh
Approved by:	re (kensmith)
MFC after:	1 week
2011-07-30 14:12:37 +00:00
Adrian Chadd
99271119d3 Fix incorrect error reporting during the dfs ioctl function.
Approved by:	re (kib)
2011-07-30 13:46:41 +00:00
Adrian Chadd
7239f9f75b Introduce the FRAC_5G EEPROM parameter.
This seems to indicate whether to program the NIC for fractional 5ghz
mode (ie, 5mhz spaced channels, rather than 10 or 20mhz spacing) or not.
The default (0) seems to mean "only program fractional mode if needed".
A different value (eg 1) seems to always enable fractional 5ghz mode
regardless of the frequency.

Obtained from:	Atheros
Approved by:	re (kib)
2011-07-30 13:45:12 +00:00
Adrian Chadd
b649b13f03 Prepare for embedded use of the AR9285/AR9287.
Calibration/PCI data that's written to flash (rather than EEPROM attached
to the NIC) is typically already in host-endian. The existing checks
end up swapping 16 bit words incorrectly - the correct solution would be
to read the magic value and determine the EEPROM endianness from that.
(This is what Linux does.)

This doesn't completely enable embedded use of the AR9285/AR9287 -
notably, the EEPROM read methods need to be made generic and available
to all EEPROM drivers. I'll worry about that later.

Approved by:	re (kib)
2011-07-30 13:37:38 +00:00
Adrian Chadd
bb40c7e83f Fix AR5416 radar parameter initialisation.
* I messed up the order of parameter true/false; oops!
* AR_PHY_RADAR_1 was being written at the wrong place, and was writing
  potential garbage to the hardware.

Approved by:	re (kib)
2011-07-30 13:34:57 +00:00
Bjoern A. Zeeb
0a5f264d60 Introduce a tunable to disable the time consuming parts of bootup
memtesting, which can easily save seconds to minutes of boot time.
The tunable name is kept general to allow reusing the code in
alternate frameworks.

Requested by:	many
Discussed on:	arch (a while a go)
Obtained from:	Sandvine Incorporated
Reviewed by:	sbruno
Approved by:	re (kib)
MFC after:	2 weeks
2011-07-30 13:33:05 +00:00
Adrian Chadd
78b72aff33 Fix the initial calibration sample count when doing ADC calibrations.
Obtained from:	Atheros
Approved by:	re (kib)
2011-07-30 13:31:27 +00:00
Adrian Chadd
e875139a4f Fix ANI handling to work correctly when (trying) to receive radar errors.
* Teach the AR5212/AR5416 ANI code to use the RX filter methods, rather
  than calling the RX filter routines directly.

* Make HAL_ANI_PRESENT and HAL_ANI_MODE unconditionally available,
  regardless of whether ah_ani_function is masking it.

* (Mostly) fully disable ANI if interference mitigation is disabled.
  When disabled, the ANI code doesn't touch any ANI/PHY registers,
  leaving them the default value. This is in line with what the
  Atheros reference driver does.

* Correctly set the ANI parameters during ANI reset, rather than
  when ANI is enabled. In this way, if ANI is disabled or enabled
  whilst the NIC is not active (and there's no current channel),
  bogus parameters or a NULL pointer deference doesn't occur.

There's still some lingering issues - notably, the MIB events/interrupts
aren't fully disabled, so MIB interrupts still occur. I'll worry about
that later.

Approved by:	re (kib)
2011-07-30 13:30:24 +00:00
Adrian Chadd
f1ef788d6f Bring over AR5416 specific RX filter get/set routines.
This in particular fixes radar PHY handling - on the AR5212
NIC, one enables the AR_PHY_ERR_RADAR bit in AR_PHY_ERR;
the AR5416 and later also needs a bit set in AR_RX_FILTER.

A follow-up commit is needed to convert the AR5416 ANI code
to use this particular method, as it's currently using the
AR5212 methods directly.

Obtained from:	Atheros
Approved by:	re (kib)
2011-07-30 13:25:11 +00:00
Alexander Motin
1bee2ec756 MFprojects/hid:
- Fix usbhidctl and usbhidaction to handle HID devices with multiple
report ids, such as multimedia keyboards.
 - Add collection type and report id to the `usbhidctl -r` output. They
are important for proper device understanding and debugging.
 - Fix usbhidaction tool to properly handle items having report_count
more then 1.

Approved by:	re (kib)
MFC after:	2 weeks
2011-07-30 13:22:44 +00:00
Adrian Chadd
c86c3aa3d9 I noticed that the Merlin NICs I had (AR9220, AR9280) never completed
the ADC calibrations if the NIC is in 5ghz 11a or 5ghz HT/20 modes.
I've been told that the dual-ADC is only engaged in turbo/40mhz modes.

Since Sowl (AR9160) seems to return valid-looking calibration data
in 5ghz 20MHz modes, I'm only disabling it for Merlin for now.
It may turn out I can disable it for all chipsets and only enable
it for 40MHz modes.

Approved by:	re (kib)
2011-07-30 13:21:33 +00:00
Adrian Chadd
827660cf9a Fix the AR9280 initial AGC calibration code.
It looks like this was mixed up with the AR9285 calibration code.
This code is now more in line with what Linux ath9k and Atheros
reference drivers do.

Obtained from:	Atheros
Approved by:	re (kib)
2011-07-30 13:18:48 +00:00
Pyun YongHyeon
caa19d50d1 Add new device id of D-Link DGE-530T Rev. C controller. DGE-503T
Rev A1 and B1 is supported by sk(4) but the DGE-530T Rev. C
controller is re-branded RealTek 8169 controller.

PR:	kern/159116
Approved by:	re (kib)
2011-07-30 01:06:12 +00:00
Nathan Whitehorn
02d9c7407f Fix an error that could cause sysctl -a to enter an infinite loop in the
event of a broken or busy fan due to returning incorrect error codes from
the FCU sysctl handler.

Reported by:	Path Mather <paul at gromit dot dlib dot vt dot edu>1
Approved by:	re (kib)
2011-07-30 00:52:13 +00:00
Nathan Whitehorn
86354c8d38 Mount memsticks read-only by default to prevent them being filled by
user modifications and subsequently preventing a functioning installation.

Approved by:	re (kib)
2011-07-30 00:51:36 +00:00
Kirk McKusick
fddf7baebe Update to -r224294 to ensure that only one of MNT_SUJ or MNT_SOFTDEP
is set so that mount can revert back to using MNT_NOWAIT when doing
getmntinfo.

Approved by: re (kib)
2011-07-30 00:43:18 +00:00
Adrian Chadd
f9da901e77 Reset the NIC if ANI is enabled or disabled.
Although this may not be what the original sysctl was designed to do,
it feels a bit more "expected".

Before, if ANI is disabled, the initial ANI parameters are still written
to the hardware, even if they're not enabled. "ANI enabled" would then
adjust the noise immunity parameters dynamically. Disabling ANI would
simply leave the existing noise immunity parameters where they are,
and disable the dynamic part.

The problem is that disabling ANI doesn't leave the hardware in
a consistent, predictable state - so asking a user to disable ANI
wouldn't actually reset the NIC to a consistent set of PHY signal
detection parameters, resulting in an unpredictable/unreliable outcome.
This makes it difficult to get reliable debugging information from
the user.

Approved by:	re (kib)
2011-07-29 23:55:17 +00:00
Alexander Motin
7ea00a6866 Make ums(4) driver more picky, not attaching to "mouses" with absolute
coordinates, such as digitizers and touch-screens, leaving these devices
to uhid(4) and user-level. Specially patched xf86-input-mouse driver can
handle them, that isn't done and can't be done properly with ums(4)
because of mouse(4) protocol limitations.

Approved by:	re (kib)
2011-07-29 20:38:06 +00:00
Alexander Motin
2d33cc7688 In some cases, at least on Marvell 88SE912x controllers, Current Command
Slot field of the PxCMD register may point to an empty command slot.
That breaks command timeout detection logic, making impossible to find
what command actually caused timeout, and leading to infinite wait.
Workaround that by checking whether pointed command slot is really used
and can timeout in its time. And if not, fallback to the dumb algorithm
used with FBS -- let all commands to time out and then fail all of them.

Approved by:	re (kib)
MFC after:	1 week
2011-07-29 20:35:23 +00:00
Alexander Motin
1ed6aaf99e Add control for ATA disk read-ahead, alike to the previously added write
cache control. Some controller BIOS'es tend to disable read-ahead, that
dramatically reduces read performance. Previously ata(4) always enabled
read-ahead unconditionally.

Approved by:	re (kib)
2011-07-29 20:32:27 +00:00
Alexander Motin
a07e846be0 In some cases failed SATA disks may report their presence, but don't
respond to any commands. I've found that because of multiple command
retries, each of which cause 30s timeout, bus reset and another retry or
requeue for many commands, it may take ages to eventually drop the
failed device. The odd thing is that those retries continue even after
XPT considered device as dead and invalidated it.

This patch makes cam_periph_error() to block any command retries after
periph was marked as invalid. With that patch all activity completes in
1-2 minutes, just after several timeouts, required to consider device
death. This should make ZFS, gmirror, graid, etc. operation more robust.

Reviewed by:	mjacob@ on scsi@

Approved by:	re (kib)
2011-07-29 20:30:28 +00:00
John Baldwin
c0ca022a34 Properly initialize an error variable to avoid returning uninitialized
data when 'show drives' succeeds, often resulting in a failing exit code
even though the command worked fine.

Reviewed by:	bz
Approved by:	re (kib)
MFC after:	3 days
2011-07-29 20:24:04 +00:00
Marius Strobl
ec3e6e77a1 - Send the RELSIM_ADJUST_OPENINGS in response to a MPI_EVENT_QUEUE_FULL using
the right SIM in case the HBA is RAID-capable but the target in question is
  not a hot spare or member of a RAID volume.
- Report the loss and addition of SAS and SATA targets detected via PHY link
  status changes and signalled by MPI_EVENT_SAS_DEVICE_STATUS_CHANGE to cam(4)
  as lost devices and trigger rescans as appropriate. Without this it can take
  quite some time until a lost device actually is no longer tried to be used,
  if it ever stops. [1]
- Handle MPI_EVENT_IR2, MPI_EVENT_LOG_ENTRY_ADDED, MPI_EVENT_SAS_DISCOVERY
  and MPI_EVENT_SAS_PHY_LINK_STATUS silently as these serve no additional
  purpose beyond adding cryptic entries to logs.

Thanks to Hans-Joerg Sirtl for providing one of the HBAs these changes were
developed with and RIP to the mainboard that didn't survive testing them.

PR:		157534 [1]
Approved by:	re (kib)
MFC after:	2 weeks
2011-07-29 18:38:31 +00:00
Marius Strobl
87e255ac52 - Staticize functions as appropriate and comment out unused ones.
- Sprinkle some const where appropriate.
- Consistently use target_id_t for the target parameter of mpt_map_physdisk()
  and mpt_is_raid_volume().
- Fix some whitespace bugs.

Approved by:	re (kib)
2011-07-29 18:35:10 +00:00
Benedict Reuschling
76e54f993c Revert my last change to this file, as BETA1 is not announced yet.
Pointed out by: kib
Pointy hat to:  me
Approved by:	re (kib, implicit)
2011-07-28 12:23:32 +00:00
Benedict Reuschling
f49a230f9c Add a section to the jail chapter that explains why it is not
recommended to allow root users in the jail to access the host system.

PR:		docs/156853
Submitted by:	crees
Patch by:	crees
Approved by:	re (kib) for BETA1
2011-07-28 11:41:55 +00:00
Bjoern A. Zeeb
b5cb9d4fa6 To inet or not two inet. Unbreak static IPv4 configuration. If you tried
you were stuck in an endless loop.

Reported by:	kensmith
Approved by:	re (kib) for BETA1
Pointy hat to:	bz - wonder why I had not tested legacy IP thoroughly..
2011-07-28 03:01:22 +00:00
Ken Smith
d8048725e0 Looks like we're ready for 9.0-BETA1 builds.
Approved by:	re (implicit)
2011-07-26 04:00:00 +00:00
Craig Rodrigues
ded85b3037 Document the tftp.blksize variable added in src/lib/libstand/tftp.c.
Approved by: re	(kib)
Requested by: maxim
2011-07-25 21:52:17 +00:00
Andreas Tobler
42f2270475 This a follow up commit from r224216 for powerpc 32-bit. Increase
the storage size for sintrcnt/sintrnames to .long.

Reviewed by: nwhitehorn
Approved by: re (kib)
2011-07-25 20:10:01 +00:00