Patch to eliminate struct files_struct.file_lock spinlock on the reader side
and use rcu refcounting rcuref_xxx api for the f_count refcounter. The
updates to the fdtable are done by allocating a new fdtable structure and
setting files->fdt to point to the new structure. The fdtable structure is
protected by RCU thereby allowing lock-free lookup. For fd arrays/sets that
are vmalloced, we use keventd to free them since RCU callbacks can't sleep. A
global list of fdtable to be freed is not scalable, so we use a per-cpu list.
If keventd is already handling the current cpu's work, we use a timer to defer
queueing of that work.
Since the last publication, this patch has been re-written to avoid using
explicit memory barriers and use rcu_assign_pointer(), rcu_dereference()
premitives instead. This required that the fd information is kept in a
separate structure (fdtable) and updated atomically.
Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
In order for the RCU to work, the file table array, sets and their sizes must
be updated atomically. Instead of ensuring this through too many memory
barriers, we put the arrays and their sizes in a separate structure. This
patch takes the first step of putting the file table elements in a separate
structure fdtable that is embedded withing files_struct. It also changes all
the users to refer to the file table using files_fdtable() macro. Subsequent
applciation of RCU becomes easier after this.
Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com>
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Adds a set of primitives to do reference counting for objects that are looked
up without locks using RCU.
Signed-off-by: Ravikiran Thirumalai <kiran_th@gmail.com>
Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
First of a number of files_lock scaability patches.
Here are the x86 numbers -
tiobench on a 4(8)-way (HT) P4 system on ramdisk :
(lockfree)
Test 2.6.10-vanilla Stdev 2.6.10-fd Stdev
-------------------------------------------------------------
Seqread 1400.8 11.52 1465.4 34.27
Randread 1594 8.86 2397.2 29.21
Seqwrite 242.72 3.47 238.46 6.53
Randwrite 445.74 9.15 446.4 9.75
The performance improvement is very significant.
We are getting killed by the cacheline bouncing of the files_struct
lock here. Writes on ramdisk (ext2) seems to vary just too
much to get any meaningful number.
Also, With Tridge's thread_perf test on a 4(8)-way (HT) P4 xeon system :
2.6.12-rc5-vanilla :
Running test 'readwrite' with 8 tasks
Threads 0.34 +/- 0.01 seconds
Processes 0.16 +/- 0.00 seconds
2.6.12-rc5-fd :
Running test 'readwrite' with 8 tasks
Threads 0.17 +/- 0.02 seconds
Processes 0.17 +/- 0.02 seconds
I repeated the measurements on ramfs (as opposed to ext2 on ramdisk in
the earlier measurement) and I got more consistent results from tiobench :
4(8) way xeon P4
-----------------
(lock-free)
Test 2.6.12-rc5 Stdev 2.6.12-rc5-fd Stdev
-------------------------------------------------------------
Seqread 1282 18.59 1343.6 26.37
Randread 1517 7 2415 34.27
Seqwrite 702.2 5.27 709.46 5.9
Randwrite 846.86 15.15 919.68 21.4
4-way ppc64
------------
(lock-free)
Test 2.6.12-rc5 Stdev 2.6.12-rc5-fd Stdev
-------------------------------------------------------------
Seqread 1549 91.16 1569.6 47.2
Randread 1473.6 25.11 1585.4 69.99
Seqwrite 1096.8 20.03 1136 29.61
Randwrite 1189.6 4.04 1275.2 32.96
Also running Tridge's thread_perf test on ppc64 :
2.6.12-rc5-vanilla
--------------------
Running test 'readwrite' with 4 tasks
Threads 0.20 +/- 0.02 seconds
Processes 0.16 +/- 0.01 seconds
2.6.12-rc5-fd
--------------------
Running test 'readwrite' with 4 tasks
Threads 0.18 +/- 0.04 seconds
Processes 0.16 +/- 0.01 seconds
The benefits are huge (upto ~60%) in some cases on x86 primarily
due to the atomic operations during acquisition of ->file_lock
and cache line bouncing in fast path. ppc64 benefits are modest
due to LL/SC based locking, but still statistically significant.
This patch:
RCU head initilizer no longer needs the head varible name since we don't use
list.h lists anymore.
Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
- Remove $Id CVS logs for V4L files
- Included newer cards.
- Added a new NEC protocol for ir based on pulse distance.
- Enable ATSC support for DViCO FusionHDTV5 Gold.
- Added tuner LG NTSC (TALN mini series).
- Fixed tea5767 autodetection.
- Resolve more tuner types.
- Commented debug function removed from mainstream.
- Remove comments from mainstream. Still on development tree.
- linux/version dependencies removed.
- BTSC Lang1 now is set to auto_stereo mode.
- New tuner standby API.
- i2c-core.c uses hexadecimal for the i2c address, so it should stay consistent.
Signed-off-by: Uli Luckas <luckas@musoft.de>
Signed-off-by: Mac Michaels <wmichaels1@earthlink.net>
Signed-off-by: Michael Krufky <mkrufky@m1k.net>
Signed-off-by: Hermann Pitton <hermann.pitton@onlinehome.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab@brturbo.com.br>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Share code between setup-bus.c and yenta_socket.c: use the write-out code of
resources to the bridge also in yenta_socket.c, as it provides useful debug
output. In addition, it fixes the bug that the CPU-centric resource view
might need to be transferred to the PCI-centric view: setup-bus.c does that,
while yenta-socket.c did not.
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
For architecture like ia64, the switch stack structure is fairly large
(currently 528 bytes). For context switch intensive application, we found
that significant amount of cache misses occurs in switch_to() function.
The following patch adds a hook in the schedule() function to prefetch
switch stack structure as soon as 'next' task is determined. This allows
maximum overlap in prefetch cache lines for that structure.
Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch removes the inode_post_link and inode_post_rename LSM hooks as
they are unused (and likely useless).
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch removes the inode_post_create/mkdir/mknod/symlink LSM hooks as
they are obsoleted by the new inode_init_security hook that enables atomic
inode security labeling.
If anyone sees any reason to retain these hooks, please speak now. Also,
is anyone using the post_rename/link hooks; if not, those could also be
removed.
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The following patch set enables atomic security labeling of newly created
inodes by altering the fs code to invoke a new LSM hook to obtain the security
attribute to apply to a newly created inode and to set up the incore inode
security state during the inode creation transaction. This parallels the
existing processing for setting ACLs on newly created inodes. Otherwise, it
is possible for new inodes to be accessed by another thread via the dcache
prior to complete security setup (presently handled by the
post_create/mkdir/... LSM hooks in the VFS) and a newly created inode may be
left unlabeled on the disk in the event of a crash. SELinux presently works
around the issue by ensuring that the incore inode security label is
initialized to a special SID that is inaccessible to unprivileged processes
(in accordance with policy), thereby preventing inappropriate access but
potentially causing false denials on legitimate accesses. A simple test
program demonstrates such false denials on SELinux, and the patch solves the
problem. Similar such false denials have been encountered in real
applications.
This patch defines a new inode_init_security LSM hook to obtain the security
attribute to apply to a newly created inode and to set up the incore inode
security state for it, and adds a corresponding hook function implementation
to SELinux.
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
29 July 2005, Cambridge, MA:
This afternoon Alan Stern submitted a patch to remove the URB_ASYNC_UNLINK
flag from the Linux kernel. Mr. Stern explained, "This flag is a relic
from an earlier, less-well-designed system. For over a year it hasn't
been used for anything other than printing warning messages."
An anonymous spokesman for the Linux kernel development community
commented, "This is exactly the sort of thing we see happening all the
time. As the kernel evolves, support for old techniques and old code can
be jettisoned and replaced by newer, better approaches. Proprietary
operating systems do not have the freedom or flexibility to change so
quickly."
Mr. Stern, a staff member at Harvard University's Rowland Institute who
works on Linux only as a hobby, noted that the patch (labelled as548) did
not update two files, keyspan.c and option.c, in the USB drivers' "serial"
subdirectory. "Those files need more extensive changes," he remarked.
"They examine the status field of several URBs at times when they're not
supposed to. That will need to be fixed before the URB_ASYNC_UNLINK flag
is removed."
Greg Kroah-Hartman, the kernel maintainer responsible for overseeing all
of Linux's USB drivers, did not respond to our inquiries or return our
calls. His only comment was "Applied, thanks."
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch removes support for user-provided platform-specific hardware reset
and clock starting/stopping functions. Hardware reset was needed earlier as
getting the software reset working was tricky due to the lack of documentation.
Recently, a number of people using isp116x have said the software reset is
working for them.
I haven't heard of anybody using the clock starting/stopping.
Signed-off-by: Olav Kongas <ok@artecdesign.ee>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch sets the isp116x to report overcurrent always per-port.
Signed-off-by: Olav Kongas <ok@artecdesign.ee>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
The isp116x chip will now always be in per-port power switching mode. Remove
conf options to set any other mode.
Signed-off-by: Olav Kongas <ok@artecdesign.ee>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch removes the power-on-to-power-good-time configuration option for
isp116x-hcd.
Signed-off-by: Olav Kongas <ok@artecdesign.ee>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch introduces a /sys/class/usb_device/ class
where every connected usb-device will show up:
tree /sys/class/usb_device/
/sys/class/usb_device/
|-- usb1.1
| |-- dev
| `-- device -> ../../../devices/pci0000:00/0000:00:1d.0/usb1
|-- usb2.1
| |-- dev
| `-- device -> ../../../devices/pci0000:00/0000:00:1d.1/usb2
...
The presence of the "dev" file lets udev create real device nodes.
kay@pim:~/src/linux-2.6> tree /dev/bus/usb/
/dev/bus/usb/
|-- 1
| `-- 1
|-- 2
| `-- 1
...
udev rule:
SUBSYSTEM="usb_device", PROGRAM="/sbin/usb_device %k", NAME="%c"
(echo $1 | /bin/sed 's/usb\([0-9]*\)\.\([0-9]*\)/bus\/usb\/\1\/\2/')
This makes libusb pick up the real nodes instead of the mounted usbfs:
export USB_DEVFS_PATH=/dev/bus/usb
Background:
All this makes it possible to manage usb devices with udev instead of
the devfs solution. We are currently working on a pam_console/resmgr
replacement driven by udev and a pam-helper. It applies ACL's to device
nodes, which is required for modern desktop functionalty like
"Fast User Switching" or multiple local login support.
New patch with its own major. I've succesfully disabled usbfs and use real
nodes only on my box. With: "export USB_DEVFS_PATH=/dev/bus/usb" libusb picks
up the udev managed nodes instead of reading usbfs files.
This makes udev to provide symlinks for libusb to pick up:
SUBSYSTEM="usb_device", PROGRAM="/sbin/usbdevice %k", SYMLINK="%c"
/sbin/usbdevice:
#!/bin/sh
echo $1 | /bin/sed 's/usbdev\([0-9]*\)\.\([0-9]*\)/bus\/usb\/\1\/\2/'
Signed-off-by: Kay Sievers <kay.sievers@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Simple cleanup to eliminate X copies of the pci_enable_intx() function
in libata. Moved ahci.c's pci_intx() to pci.c and use it throughout
libata and msi.c.
Signed-off-by: Brett Russ <russb@emc.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
- support PCI PM CAP version 3 (as defined in PCI PM Interface Spec v1.2)
- pci/probe.c sets the PM state initially to 4 which is D3cold. add a
PCI_UNKNOWN
- minor cleanups
Signed-off-by: Daniel Ritz <daniel.ritz@gmx.ch>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
The PCI error recovery infrastructure needs to be able to contact all
the drivers affected by a PCI error event, which may mean traversing
all the devices under a given PCI-PCI bridge. This patch adds a
function to the PCI core that traverses all the PCI devices on a PCI
bus and under any PCI-PCI bridges on that bus (and so on), calling a
given function for each device. This provides a way for the error
recovery code to iterate through all devices that are affected by an
error event.
This version is not implemented as a recursive function. Instead,
when we reach a PCI-PCI bridge, we set the pointers to start doing the
devices on the bus under the bridge, and when we reach the end of a
bus's devices, we use the bus->self pointer to go back up to the next
higher bus and continue doing its devices.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Some PCI devices (e.g. 3c905B, 3c556B) lose all configuration
(including BARs) when transitioning from D3hot->D0. This leaves such
a device in an inaccessible state. The patch below causes the BARs
to be restored when enabling such a device, so that its driver will
be able to access it.
The patch also adds pci_restore_bars as a new global symbol, and adds a
correpsonding EXPORT_SYMBOL_GPL for that.
Some firmware (e.g. Thinkpad T21) leaves devices in D3hot after a
(re)boot. Most drivers call pci_enable_device very early, so devices
left in D3hot that lose configuration during the D3hot->D0 transition
will be inaccessible to their drivers.
Drivers could be modified to account for this, but it would
be difficult to know which drivers need modification. This is
especially true since often many devices are covered by the same
driver. It likely would be necessary to replicate code across dozens
of drivers.
The patch below should trigger only when transitioning from D3hot->D0
(or at boot), and only for devices that have the "no soft reset" bit
cleared in the PM control register. I believe it is safe to include
this patch as part of the PCI infrastructure.
The cleanest implementation of pci_restore_bars was to call
pci_update_resource. Unfortunately, that does not currently exist
for the sparc64 architecture. The patch below includes a null
implemenation of pci_update_resource for sparc64.
Some have expressed interest in making general use of the the
pci_restore_bars function, so that has been exported to GPL licensed
modules.
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This cleans up some of the #ifdef CONFIG_PCI stuff up, and moves the pci register
info out to a separate file, where it belongs. Eventually we can stop including
this file from within pci.h, but lots of code needs to be audited first.
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Make PCI fixup data const, so it'll end up in a r/o section.
This also fixes the conversion into ECOFF which gets broken by too many
changes between r/w and r/o sections. Call it a hack but it's a change
that's correct by itself.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Run PCI driver initialization on local node
Instead of adding messy kmalloc_node()s everywhere run the
PCI driver probe on the node local to the device.
This would not have helped for IDE, but should for
other more clean drivers that do more initialization in probe().
It won't help for drivers that do most of the work
on first open (like many network drivers)
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Proud member of Uglyhacks'R'US.
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Russell King <rmk+lkml@arm.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
mmc_priv() has some nasty effects if the wrong pointer type is
passed to it. Introduce type checking, which also means we get
the right type. Also add an additional member to mmc_host which
is used to align host-private data appropriately.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Add the crc16 routines, as used by w1 devices.
Signed-off-by: Ben Gardner <bgardner@wabtec.com>
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Since packets almost never contain extra garbage at the end, it is
worthwhile to optimize for that case.
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change mmc_detect_change() to take a delay argument such that
the detection of card insertions and removals can be delayed
according to the requirements of the host driver or platform.
Signed-off-by: Richard Purdie <rpurdie@rpsys.net>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Rather than hard-coding the platform device IDs, enumerate them.
We don't particularly care about the actual ID we get, just as
long as they're unique.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The problem is that klists claim to provide semantics for safe traversal of
lists which are being modified. The failure case is when traversal of a
list causes element removal (a fairly common case). The issue is that
although the list node is refcounted, if it is embedded in an object (which
is universally the case), then the object will be freed regardless of the
klist refcount leading to slab corruption because the klist iterator refers
to the prior element to get the next.
The solution is to make the klist take and release references to the
embedding object meaning that the embedding object won't be released until
the list relinquishes the reference to it.
(akpm: fast-track this because it's needed for the 2.6.13 scsi merge)
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Based on patch from David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Support several new socket options / ancillary data:
IPV6_RECVPKTINFO, IPV6_PKTINFO,
IPV6_RECVHOPOPTS, IPV6_HOPOPTS,
IPV6_RECVDSTOPTS, IPV6_DSTOPTS, IPV6_RTHDRDSTOPTS,
IPV6_RECVRTHDR, IPV6_RTHDR,
IPV6_RECVHOPOPTS, IPV6_HOPOPTS
Old semantics are preserved as IPV6_2292xxxx so that
we can maintain backward compatibility.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
There are possible race conditions if probes are placed on routines within the
kprobes files and routines used by the kprobes. For example if you put probe
on get_kprobe() routines, the system can hang while inserting probes on any
routine such as do_fork(). Because while inserting probes on do_fork(),
register_kprobes() routine grabs the kprobes spin lock and executes
get_kprobe() routine and to handle probe of get_kprobe(), kprobes_handler()
gets executed and tries to grab kprobes spin lock, and spins forever. This
patch avoids such possible race conditions by preventing probes on routines
within the kprobes file and routines used by kprobes.
I have modified the patches as per Andi Kleen's suggestion to move kprobes
routines and other routines used by kprobes to a seperate section
.kprobes.text.
Also moved page fault and exception handlers, general protection fault to
.kprobes.text section.
These patches have been tested on i386, x86_64 and ppc64 architectures, also
compiled on ia64 and sparc64 architectures.
Signed-off-by: Prasanna S Panchamukhi <prasanna@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Introduce new ll_rw_block() operation SWRITE meaning that block layer should
wait for the buffer lock and write-out afterwards. Hence data in buffers at
the time of call are guaranteed to be submitted to the disk.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
