Looks like locking can be optimised quite a lot. Increase lock widths
slightly so lo_lock is taken fewer times per request. Also it was quite
trivial to cover lo_pending with that lock, and remove the atomic
requirement. This also makes memory ordering explicitly correct, which is
nice (not that I particularly saw any mem ordering bugs).
Test was reading 4 250MB files in parallel on ext2-on-tmpfs filesystem (1K
block size, 4K page size). System is 2 socket Xeon with HT (4 thread).
intel:/home/npiggin# umount /dev/loop0 ; mount /dev/loop0 /mnt/loop ; /usr/bin/time ./mtloop.sh
Before:
0.24user 5.51system 0:02.84elapsed 202%CPU (0avgtext+0avgdata 0maxresident)k
0.19user 5.52system 0:02.88elapsed 198%CPU (0avgtext+0avgdata 0maxresident)k
0.19user 5.57system 0:02.89elapsed 198%CPU (0avgtext+0avgdata 0maxresident)k
0.22user 5.51system 0:02.90elapsed 197%CPU (0avgtext+0avgdata 0maxresident)k
0.19user 5.44system 0:02.91elapsed 193%CPU (0avgtext+0avgdata 0maxresident)k
After:
0.07user 2.34system 0:01.68elapsed 143%CPU (0avgtext+0avgdata 0maxresident)k
0.06user 2.37system 0:01.68elapsed 144%CPU (0avgtext+0avgdata 0maxresident)k
0.06user 2.39system 0:01.68elapsed 145%CPU (0avgtext+0avgdata 0maxresident)k
0.06user 2.36system 0:01.68elapsed 144%CPU (0avgtext+0avgdata 0maxresident)k
0.06user 2.42system 0:01.68elapsed 147%CPU (0avgtext+0avgdata 0maxresident)k
Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch creates a new kstrdup library function and changes the "local"
implementations in several places to use this function.
Most of the changes come from the sound and net subsystems. The sound part
had already been acknowledged by Takashi Iwai and the net part by David S.
Miller.
I left UML alone for now because I would need more time to read the code
carefully before making changes there.
Signed-off-by: Paulo Marques <pmarques@grupopie.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Sprinkle around a few branch hints in the block layer.
Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Jens Axboe <axboe@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This memory barrier is not needed because the waitqueue will only get waiters
on it in the following situations:
rq->count has exceeded the threshold - however all manipulations of ->count
are performed under the runqueue lock, and so we will correctly pick up any
waiter.
Memory allocation for the request fails. In this case, there is no additional
help provided by the memory barrier. We are guaranteed to eventually wake up
waiters because the request allocation mempool guarantees that if the mem
allocation for a request fails, there must be some requests in flight. They
will wake up waiters when they are retired.
Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Jens Axboe <axboe@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add KERN_ERR and __FUNCTION__ to generic tag error messages, and add a comment
in blk_queue_end_tag() which explains the silent failure path.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Acked-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
blk_queue_tag->real_max_depth was used to optimize out unnecessary
allocations/frees on tag resize. However, the whole thing was very broken -
tag_map was never allocated to real_max_depth resulting in access beyond the
end of the map, bits in [max_depth..real_max_depth] were set when initializing
a map and copied when resizing resulting in pre-occupied tags.
As the gain of the optimization is very small, well, almost nill, remove the
whole thing.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Acked-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
blk_queue_start_tag() hand-coded searching for the first zero bit in the tag
map. Replace it with find_first_zero_bit(). With this patch,
blk_queue_star_tag() doesn't need to fill remains of tag map with 1, thus
allowing it to work properly with the next remove_real_max_depth patch.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Acked-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Patch to allocate the control structures for for ide devices on the node of
the device itself (for NUMA systems). The patch depends on the Slab API
change patch by Manfred and me (in mm) and the pcidev_to_node patch that I
posted today.
Does some realignment too.
Signed-off-by: Justin M. Forbes <jmforbes@linuxtx.org>
Signed-off-by: Christoph Lameter <christoph@lameter.com>
Signed-off-by: Pravin Shelar <pravin@calsoftinc.com>
Signed-off-by: Shobhit Dayal <shobhit@calsoftinc.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch fixes an obvious and nasty bug where we could exit the transmit
routine while holding tx_lock.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Don't error out if something "bad" happens when trying to bind a driver to a
device. We want the sysfs attributes to be present for later when we try to
tear down the device.
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Drivers need to return -ENODEV when they can't bind to a device.
Anything else stops the "bind a device to a driver" search.
From: Stelian Pop <stelian@popies.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Use ssleep() / msleep() [as appropriate]
instead of schedule_timeout() to guarantee the task delays as expected.
Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
Acked-by: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
Signed-off-by: Maximilian Attems <janitor@sternwelten.at>
Signed-off-by: Domen Puncer <domen@coderock.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes the support for the W83697HF and W83627THF chips from
the w83781d driver. These chips have no I2C/SMBus interface and are
better supported by the Super-I/O-based w83627hf driver. Documentation
was updated to reflect the support drop.
Signed-off-by: Grant Coady <gcoady@gmail.com>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Add support for Maxim/Dallas DS1374 Real-Time Clock Chip
This change adds support for the Maxim/Dallas DS1374 RTC chip. This chip
is an I2C-based RTC that maintains a simple 32-bit binary seconds count
with battery backup support.
Signed-off-by: Randy Vinson <rvinson@mvista.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This is an i2c driver for the Philips PCA9539 (16 bit I/O port).
It uses the new i2c-sysfs interfaces.
The patch includes documentation.
It depends on the patch that renames "i2c-sysfs.h" to "hwmon-sysfs.h"
Signed-off-by: Ben Gardner <bgardner@wabtec.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch renames the new linux/i2c-sysfs.h header file to
linux/hwmon-sysfs.h. This names seems to be more appropriate since this
file defines macros and structures not related to i2c but to hardware
monitoring drivers. The patch also updates the five hardware monitoring
driver which include that header file already.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch adds support for the MAX6875/MAX6874 chips.
Signed-off-by: Ben Gardner <bgardner@wabtec.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch modifies the it87 hardware monitoring driver to take benefit
of the new sysfs callback features introduced by Yani Ioannou, making
the code much clearer and the resulting driver significantly smaller.
From: Yani Ioannou <yani.ioannou@gmail.com>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
I updated the lm63 hardware monitoring driver to take benefit of Yani
Ioannou's new sysfs callback capabilities.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
I updated the lm83 hardware monitoring driver to take benefit of Yani
Ioannou's new sysfs callback capabilities.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
I updated the lm90 hardware monitoring driver to take benefit of Yani
Ioannou's new sysfs callback capabilities.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
I found a possible cleanup in the pcf8574 driver. We don't need to store
the read value in our private data structure, as we then never use it
again. I asked Aurelien and he is fine with the change. Please apply,
thanks.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Following patch removes EXPERIMENTAL flag from some of I2C bus and chip
drivers. It is removed when the driver is in kernel at least from
2.6.3 and I generally think there is no problem with it.
Also this patch adds SiS 745 to help option of sis96x and it
also fixes nForce2 driver entry to reflect current state.
Signed-off-by: Rudolf Marek <r.marek@sh.cvut.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This adds an I2C driver for the TPS6501x series of power management chips.
It's used on many OMAP based boards, and this driver has been widely used
in the Linux-OMAP trees over the last year or so.
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
i2c: Race fix for i2c-mpc.c
The problem was that the clock speed and driver data is
initialized after the i2c adapter was added. This caused
the i2c bus to start working at a wrong speed. (Mostly
noticable on the second bus on mpc5200)
With this patch we've tried to keep the i2c adapter
working perfectly all the time it is included in the system.
Initialize before added, Remove garbage after deleleted.
Submitted-by: Asier Llano Palacios
Signed-off-by: Sylvain Munaut <tnt@246tNt.com>
Signed-off-by: Kumar Gala <kumar.gala@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch fixes a misspelling in a comment section.
Signed-off-by: Tobias Klauser <tklauser@nuerscht.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch fixes a misspelling in a comment section.
Signed-off-by: Tobias Klauser <tklauser@nuerscht.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch fixes a double "the" in a comment section.
Signed-off-by: Tobias Klauser <tklauser@nuerscht.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch fixes the some misspellings and a trailing whitespace in
the comments.
Signed-off-by: Tobias Klauser <tklauser@nuerscht.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch kills another macro abuse in the via686a hardware monitoring
driver. Using a macro just to alias an array is quite useless, isn't it?
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Here are some corrections for drivers/i2c/chips/Kconfig.
Signed-off-by: Alexey Fisher <fishor@gmx.net>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch removes die_code from adm1021 as nothing within the
driver uses it.
Signed-off-by: Grant Coady <gcoady@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
The via686a hardware monitoring driver has infamous coding style at the
moment. I'd like to clean up the mess before I start working on other
changes to this driver. Is the following patch acceptable? No code
change, only coding style (indentation, alignments, trailing white
space, a few parentheses and a typo).
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch kills a common macro abuse in i2c chip drivers: defining
ALARMS_FROM_REG returning its argument unchanged. Dropping the macro
makes the code somewhat more readable IMHO.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch includes jiffies.h in two i2c drivers.
(jiffies.h is needed for the time_after function.)
Signed-off-by: Dominik Hackl <dominik@hackl.dhs.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch adds an info print of detected VRM stolen from Sebastian
Witt's atxp1 sriver. ADM9240 already has vrm accessor removed.
Write no-op and whitespace fixes removed :)
Couple of comments changed, tested on 2.6.11.9.
Signed-off-by: Grant Coady <gcoady@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This small patch changes two drivers, adm1025 and adm1026, to
report vid as cpu0_vid sysfs name as used by the other drivers.
Added duplicated names and six month warning for old names to
be removed as requested. Compile tested.
Signed-off-by: Grant Coady <gcoady@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Jarkko Lavinen provided patch to fix: "couldn't set the divisor 128
through fan1_div sysfs entry even though the chip supports it and
setting divisors 1..64 worked. This was due to POWER_TO_REG() only
checking 2's powers 0 till 5 but not 6."
This patch applies that fix to w83627hf and w83781d drivers.
Signed-off-by: Grant Coady <gcoady@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
In my cross-reference checking of sysfs names, the via686a needs
special case treatment as it the only driver expands S_IWUSR to
00200 with gcc -E. (00200 is the correct value for S_IWUSR).
This is caused by the driver including <linux/delay.h>, it compiles
fine without that header but I am unable to test drive the change.
Signed-off-by: Grant Coady <gcoady@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Call i2c_transfer() from i2c_master_send() and i2c_master_recv() to
avoid the redundant code that was in all three functions. It also
removes unnecessary debug statements as suggested by Jean Delvare.
This is important for the non-blocking interfaces because they will
have to handle a non-blocking interface in this area. Having it in
one place greatly simplifies the changes.
Signed-off-by: Corey Minyard <minyard@acm.org>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
I2C-MPC: Allow for sharing of the interrupt line
On the MPC8548 devices we have multiple I2C-MPC buses however they are on the
same interrupt line. Made request_irq pass SA_SHIRQ now so the second bus can
register for the same IRQ.
Signed-off-by: Kumar Gala <kumar.gala@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
