Tomas Winkler [Mon, 29 Sep 2014 13:31:42 +0000 (16:31 +0300)]
mei: get rid of most of the pci dependencies in mei
For purpose of adding testing HW we would like
to get rid of pci dependency in generic mei code
This patch provides only straight forward changes
FW status and prob quirks need to be handled separately
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Drivers: hv: vmbus: Enable interrupt driven flow control
In win8 we have a feature that allows for interrupt driven flow management
for host/guest communication. For instance, if the host were blocked because
there was no space available in the ringbuffer, the host could request that the
guest send an interrupt when space becomes available in the ringbuffer (when
the guest drains the ringbuffer).
While this feature was implemented in the guest a while ago, we had not
advertised that the guest supported this feature. This patch advertises
the support to the host.
For pre-win8 hosts, this has no effect since the size of the ringbuffer
control structure has not changed and all changes have been backward
compatible - unused/reserved space has been used to implement this
feature.
In this version of the patch I have cleaned up the commit log based on
feedback from Greg KH.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Drivers: hv: util: Properly pack the data for file copy functionality
Properly pack the data for file copy functionality. Patch based on
investigation done by Matej Muzila <mmuzila@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reported-by: <qge@redhat.com> Cc: <stable@vger.kernel.org> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
K. Y. Srinivasan [Fri, 29 Aug 2014 01:29:52 +0000 (18:29 -0700)]
Drivers: hv: vmbus: Cleanup hv_post_message()
Minimize failures in this function by pre-allocating the buffer
for posting messages. The hypercall for posting the message can fail
for a number of reasons:
1. Transient resource related issues
2. Buffer alignment
3. Buffer cannot span a page boundry
We address issues 2 and 3 by preallocating a per-cpu page for the buffer.
Transient resource related failures are handled by retrying by the callers
of this function.
This patch is based on the investigation
done by Dexuan Cui <decui@microsoft.com>.
I would like to thank Sitsofe Wheeler <sitsofe@yahoo.com>
for reporting the issue and helping in debuggging.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reported-by: Sitsofe Wheeler <sitsofe@yahoo.com> Cc: <stable@vger.kernel.org> Tested-by: Sitsofe Wheeler <sitsofe@yahoo.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Eliminate the call to BUG_ON() by waiting for the host to respond. We are
trying to reclaim the ownership of memory that was given to the host and so
we will have to wait until the host responds.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Cc: <stable@vger.kernel.org> Tested-by: Sitsofe Wheeler <sitsofe@yahoo.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Eliminate calls to BUG_ON() by properly handling errors. In cases where
rollback is possible, we will return the appropriate error to have the
calling code decide how to rollback state. In the case where we are
transferring ownership of the guest physical pages to the host,
we will wait for the host to respond.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Cc: <stable@vger.kernel.org> Tested-by: Sitsofe Wheeler <sitsofe@yahoo.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
K. Y. Srinivasan [Wed, 27 Aug 2014 23:25:31 +0000 (16:25 -0700)]
Drivers: hv: vmbus: Cleanup vmbus_post_msg()
Posting messages to the host can fail because of transient resource
related failures. Correctly deal with these failures and increase the
number of attempts to post the message before giving up.
In this version of the patch, I have normalized the error code to
Linux error code.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Cc: <stable@vger.kernel.org> Tested-by: Sitsofe Wheeler <sitsofe@yahoo.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Federico Vaga [Mon, 1 Sep 2014 11:49:56 +0000 (13:49 +0200)]
ipoctal: clear break interrupt as soon as it occurs
In some condition we receive the break interrupt but nothing is putted
in the Rx FIFO and the correspondend bit in the status register is not
set. Thus, no-one clear the interrupt and the handler will be called
forever.
This patch clear the break interrupt as soon as it occurs. Then, if the
break character '\0' is putted in the fifo we will manage it.
We can also unmask the Break interrupt but its bit in ISR is still set
on break. So I think is better to keep the registers clean.
Signed-off-by: Federico Vaga <federico.vaga@cern.ch> Acked-by: Samuel Iglesias Gonsalvez <siglesias@igalia.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Frank Haverkamp [Wed, 10 Sep 2014 14:37:53 +0000 (16:37 +0200)]
GenWQE: Support blocking when DDCB queue is busy
When the GenWQE hardware queue was busy, the driver returned simply
-EBUSY. This caused polling by applications which increased the load
on the already busy system. This change implements the possiblity to
sleep on a waitqueue instead when the DDCB queue is busy. The
requestor is woken up when there is free space on the queue again.
The old way to get -EBUSY is still available if the device is openend
with O_NONBLOCKING. The default is now blocking behavior.
Signed-off-by: Frank Haverkamp <haver@linux.vnet.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Frank Haverkamp [Wed, 10 Sep 2014 14:37:49 +0000 (16:37 +0200)]
GenWQE: Do not modify return code of genwqe_set_interrupt_capability
Follow up patch to the one from Sebastian Ott. There is no need to
change the return code once it fails. And Sebastians version is tested
now and works nicely on our test-system.
Signed-off-by: Frank Haverkamp <haver@linux.vnet.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Frank Haverkamp [Wed, 10 Sep 2014 14:37:47 +0000 (16:37 +0200)]
GenWQE: Remove sysfs entry for driver version
A special sysfs entry to display the driver version is not
needed. We left the driver version and adjusted it to the
naming a lot of other drivers use. The information can be
retrieved by using modinfo genwqe_card.
modinfo genwqe_card will provide the same information.
Signed-off-by: Frank Haverkamp <haver@linux.vnet.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Frank Haverkamp [Wed, 10 Sep 2014 14:37:46 +0000 (16:37 +0200)]
GenWQE: Check pci_get_totalvfs return code
Currently the driver is using the pci_get_totalvfs() return code
directly in a loop. To avoid problems with potentially negative
returns in case of errors, we are adding some more sanity checking
code.
Signed-off-by: Frank Haverkamp <haver@linux.vnet.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Lee Jones [Thu, 28 Aug 2014 13:14:09 +0000 (14:14 +0100)]
misc: st_kim: Increase size of dev_name buffer to incorporate termination
Calling strncpy with a maximum size argument of 32 bytes on destination
array kim_gdata->dev_name of size 32 bytes might leave the destination
string unterminated.
Signed-off-by: Lee Jones <lee.jones@linaro.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
parport: parport_pc: Implement architecture and device check to cut off false-positives
We definitely know that only x86 (32-bit) architecture is affected by the issue, so implement a stub instead of the actual check for other architectures.
We also know that motherboard LPT chipset is affected, so the port is either come from
parport_pc_init (when `io' module param is used) or
parport_pc_find_isa_ports (when default LPT ports are probbed: 0x378, 0x278, 0x3bc).
In both cases the port considered as 'legacy' and `dev' member of struct parport is NULL. See also comments for `struct parport' in parport.h
Signed-off-by: Matwey V. Kornilov <matwey@sai.msu.ru> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Put the code to check present of the Intel bug from parport_EPP_supported
into new intel_bug_present function. The later also return ECR register
to the state it has before function call.
Signed-off-by: Matwey V. Kornilov <matwey@sai.msu.ru> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Michal Simek [Wed, 13 Aug 2014 12:02:05 +0000 (14:02 +0200)]
char: xilinx_hwicap: Remove .owner field for driver
There is no need to init .owner field.
Based on the patch from Peter Griffin <peter.griffin@linaro.org>
"mmc: remove .owner field for drivers using module_platform_driver"
This patch removes the superflous .owner field for drivers which
use the module_platform_driver API, as this is overriden in
platform_driver_register anyway."
Signed-off-by: Michal Simek <michal.simek@xilinx.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Himangi Saraogi [Thu, 7 Aug 2014 12:13:28 +0000 (17:43 +0530)]
pcie-gadget-spear: use devm_ functions
The various devm_ functions allocate memory that is released when a
driver detaches. This patch uses these functions for data that is
allocated in the probe function of a platform device and is only freed
in the remove function. Also, the unnecessary labels are removed and
linux/device.h is added to make sure the devm_*() routine declarations
are unambiguously available.
The initial call to platform_get_resource is moved down to the
introduced call to devm_ioremap_resource that uses its result.
Himangi Saraogi [Fri, 1 Aug 2014 19:04:23 +0000 (00:34 +0530)]
EEPROM: Introduce the use of devm_kzalloc
This patch introduces the use of devm_kzalloc and does away with the
kfrees in the probe and remove functions. Also, a label and the err
variable are removed. The header device.h is included to make the devm_
function explicitly available and slab.h is done away with as it is no
longer needed.
Signed-off-by: Himangi Saraogi <himangi774@gmail.com> Acked-by: Julia Lawall <julia.lawall@lip6.fr> Reviewed-by: Jean Delvare <jdelvare@suse.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
function 'strncpy' will fill whole buffer 'id.name' of fixed size (32)
with string value and will not leave place for NULL-terminator.
Possible buffer boundaries violation in following string operations.
Replace strncpy with strlcpy.
Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tomas Winkler [Thu, 21 Aug 2014 11:29:18 +0000 (14:29 +0300)]
mei: revamp connect and disconnect response handling
Both responses have same flow only the client status
update is different. We introduce handler mei_hbm_cl_res()
that handles both responses
Also we use per client wait queue (cl->wait) rather then
global dev->wait_recvd_msg
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tomas Winkler [Thu, 21 Aug 2014 11:29:15 +0000 (14:29 +0300)]
mei: add mei_me_cl_by_uuid_id function
When handling dynamic clients there might be a race
scenario in which two me clients with the same me
address would be linked in the me clients list,
therefore we need to search by both uuid and me address.
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tomas Winkler [Sun, 24 Aug 2014 09:08:55 +0000 (12:08 +0300)]
mei: me_client lookup function to return me_client object
For support of dynamic addition and removal of me clients
it is more convenient to use a list instead of static array
as is use now.
As the first step of the transition to the new data structure
we change the lookup function so it returns me client address
instead of an index.
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
We cannot handle user interrupt in context of hw initialization
so we only wait for time out which is reasonably short
Also we don't need to check error from wait, only flag value.
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Merge tag 'extcon-next-for-3.18' of git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/extcon into char-misc-next
Chanwoo writes:
Update extcon for v3.18
This patchset add new extcon provider driver and fix minor issue of extcon driver.
Detailed description for patchset:
1. Add new Richtek RT8973A extcon driver
This driver support for Richtek RT8973A which is Micro USB Switch OVP and
i2c interface. The RT8973A is a USB port accessory detector and switch that is
optimized to protect low voltage system from abnormal high input voltage
(up to 28V) and supports high speed USB operation. Also, RT8973A support
'auto-configuration' mode. If auto-configuration mode is enabled, RT8973A
would control internal h/w patch for USB D-/D+ switching.
2. Fix code cleanup for other extcon driver
- extcon-sm5502 driver
: Fix bug to check cable type and build break.
: Move header file from include/linux/extcon to drivers/extcon because this
header file is only user for extcon-sm5502.c.
: Clean up codes by using checkpatch script
- extcon-max77693 driver
: Use resource managed interrupt function
: Fix bug to set ADC debounce time
- extcon-gpio driver
: Fix minor code cleanup
George Cherian [Tue, 9 Sep 2014 04:14:34 +0000 (09:44 +0530)]
extcon: gpio: Fix code cleanup
This patch fixes following minor cleanup:
- Order the include files in alphabetical order.
- Fix description of state_off in extcon_gpio.h
- Add a descrition for check_on_resume in extcon_gpio.h
Signed-off-by: George Cherian <george.cherian@ti.com>
[Modify the name/description of patch to keep standary codiyg style by Chanwoo Choi] Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Jonghwa Lee [Wed, 17 Sep 2014 03:58:43 +0000 (12:58 +0900)]
extcon: max77693: Fix a bug occured at changing ADC debounce time.
When it writes some value other than 0 to BTLDset and JIGset, muic device
will be reset automatically. And it happens during updating ADC debounce time,
because it shares same register. To update ADC debounce time without reset,
set value only to ADCDbset and 0 to BTLDset and JIGset.
Signed-off-by: Jonghwa Lee <jonghwa3.lee@samsung.com>
[Remove un-needed masking operation by Chanwoo Choi] Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
extcon: max77693: Use resource managed interrupt line
Use resource managed interrupt line devm_request_threaded_irq() to
simplify a little cleanup paths:
- no goto to cleanup label,
- simpler remove function.
Overall the driver size is decreased by 11 line of code.
Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com> Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Chanwoo Choi [Mon, 4 Aug 2014 06:54:14 +0000 (15:54 +0900)]
dt-bindings: extcon: Add support for Richtek RT8973A MUIC device
This patch add documentation for binding of Richtek RT8973A (Micro USB Switch)
device which is using EXTCON subsystem. The RT8973A device can detect various
external accessories when external accessories is attached or detached.
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com> Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
This patch add support for Richtek RT8973A which is Micro USB Switch OVP
and i2c interface. The RT8973A is a USB port accessory detector and switch
that is optimized to protect low voltage system from abnormal high input
voltage (up to 28V) and supports high speed USB operation. Also, RT8973A
support 'auto-configuration' mode. If auto-configuration mode is enabled,
RT8973A would control internal h/w patch for USB D-/D+ switching.
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com> Signed-off-by: Seung-Woo Kim <sw0312.kim@samsung.com> Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
extcon: sm5502: Move sm5502.h header file to extcon directory
This patch move sm5502.h header file from 'include/linux/extcon' to
'driver/extcon' because sm5502.h is used for driver/extcon/extcon-sm5502.c.
and remove duplicate license description.
Chanwoo Choi [Tue, 12 Aug 2014 04:28:11 +0000 (13:28 +0900)]
extcon: sm5502: Add I2C dependency to fix build break
This patch add I2C configuration dependency to fix following build break.
If specific kernel build I2C as module, extcon-sm5502 have to depend on
I2C configuration.
drivers/built-in.o: In function `regmap_smbus_byte_reg_read':
regmap-i2c.c:(.text+0x5030a): undefined reference to `i2c_smbus_read_byte_data'
drivers/built-in.o: In function `regmap_smbus_byte_reg_write':
regmap-i2c.c:(.text+0x50338): undefined reference to `i2c_smbus_write_byte_data'
drivers/built-in.o: In function `regmap_smbus_word_reg_read':
regmap-i2c.c:(.text+0x50356): undefined reference to `i2c_smbus_read_word_data'
drivers/built-in.o: In function `regmap_smbus_word_reg_write':
regmap-i2c.c:(.text+0x50384): undefined reference to `i2c_smbus_write_word_data'
drivers/built-in.o: In function `regmap_i2c_read':
regmap-i2c.c:(.text+0x503cf): undefined reference to `i2c_transfer'
drivers/built-in.o: In function `regmap_i2c_gather_write':
regmap-i2c.c:(.text+0x50442): undefined reference to `i2c_transfer'
drivers/built-in.o: In function `regmap_i2c_write':
regmap-i2c.c:(.text+0x50474): undefined reference to `i2c_master_send'
drivers/built-in.o: In function `sm5502_muic_i2c_init':
extcon-sm5502.c:(.init.text+0x6630): undefined reference to `i2c_register_driver'
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs fixes from Al Viro:
"double iput() on failure exit in lustre, racy removal of spliced
dentries from ->s_anon in __d_materialise_dentry() plus a bunch of
assorted RCU pathwalk fixes"
The RCU pathwalk fixes end up fixing a couple of cases where we
incorrectly dropped out of RCU walking, due to incorrect initialization
and testing of the sequence locks in some corner cases. Since dropping
out of RCU walk mode forces the slow locked accesses, those corner cases
slowed down quite dramatically.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
be careful with nd->inode in path_init() and follow_dotdot_rcu()
don't bugger nd->seq on set_root_rcu() from follow_dotdot_rcu()
fix bogus read_seqretry() checks introduced in b37199e
move the call of __d_drop(anon) into __d_materialise_unique(dentry, anon)
[fix] lustre: d_make_root() does iput() on dentry allocation failure
vfs: avoid non-forwarding large load after small store in path lookup
The performance regression that Josef Bacik reported in the pathname
lookup (see commit 99d263d4c5b2 "vfs: fix bad hashing of dentries") made
me look at performance stability of the dcache code, just to verify that
the problem was actually fixed. That turned up a few other problems in
this area.
There are a few cases where we exit RCU lookup mode and go to the slow
serializing case when we shouldn't, Al has fixed those and they'll come
in with the next VFS pull.
But my performance verification also shows that link_path_walk() turns
out to have a very unfortunate 32-bit store of the length and hash of
the name we look up, followed by a 64-bit read of the combined hash_len
field. That screws up the processor store to load forwarding, causing
an unnecessary hickup in this critical routine.
It's caused by the ugly calling convention for the "hash_name()"
function, and easily fixed by just making hash_name() fill in the whole
'struct qstr' rather than passing it a pointer to just the hash value.
With that, the profile for this function looks much smoother.
Merge branch 'parisc-3.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux
Pull parisc updates from Helge Deller:
"The most important patch is a new Light Weigth Syscall (LWS) for 8,
16, 32 and 64 bit atomic CAS operations which is required in order to
be able to implement the atomic gcc builtins on our platform.
Other than that, we wire up the seccomp, getrandom and memfd_create
syscalls, fixes a minor off-by-one bug and a wrong printk string"
* 'parisc-3.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Implement new LWS CAS supporting 64 bit operations.
parisc: Wire up seccomp, getrandom and memfd_create syscalls
parisc: dino: fix %d confusingly prefixed with 0x in format string
parisc: sys_hpux: NUL terminator is one past the end
Al Viro [Sun, 14 Sep 2014 01:59:43 +0000 (21:59 -0400)]
be careful with nd->inode in path_init() and follow_dotdot_rcu()
in the former we simply check if dentry is still valid after picking
its ->d_inode; in the latter we fetch ->d_inode in the same places
where we fetch dentry and its ->d_seq, under the same checks.
Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Al Viro [Sun, 14 Sep 2014 01:55:46 +0000 (21:55 -0400)]
don't bugger nd->seq on set_root_rcu() from follow_dotdot_rcu()
return the value instead, and have path_init() do the assignment. Broken by
"vfs: Fix absolute RCU path walk failures due to uninitialized seq number",
which was Cc-stable with 2.6.38+ as destination. This one should go where
it went.
To avoid dummy value returned in case when root is already set (it would do
no harm, actually, since the only caller that doesn't ignore the return value
is guaranteed to have nd->root *not* set, but it's more obvious that way),
lift the check into callers. And do the same to set_root(), to keep them
in sync.
Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Merge tag 'ntb-3.17' of git://github.com/jonmason/ntb
Pull ntb driver bugfixes from Jon Mason:
"NTB driver fixes for queue spread and buffer alignment. Also, update
to MAINTAINERS to reflect new e-mail address"
* tag 'ntb-3.17' of git://github.com/jonmason/ntb:
ntb: Add alignment check to meet hardware requirement
MAINTAINERS: update NTB info
NTB: correct the spread of queues over mw's
Merge branch 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull ARM irq chip fixes from Thomas Gleixner:
"Another pile of ARM specific irq chip fixlets:
- off by one bugs in the crossbar driver
- missing annotations
- a bunch of "make it compile" updates
I pulled the lot today from Jason, but it has been in -next for at
least a week"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip: gic-v3: Declare rdist as __percpu pointer to __iomem pointer
irqchip: gic: Make gic_default_routable_irq_domain_ops static
irqchip: exynos-combiner: Fix compilation error on ARM64
irqchip: crossbar: Off by one bugs in init
irqchip: gic-v3: Tag all low level accessors __maybe_unused
irqchip: gic-v3: Only define gic_peek_irq() when building SMP
Dave Jiang [Thu, 28 Aug 2014 20:53:02 +0000 (13:53 -0700)]
ntb: Add alignment check to meet hardware requirement
The NTB translate register must have the value to be BAR size aligned.
This alignment check make sure that the DMA memory allocated has the
proper alignment. Another requirement for NTB to function properly with
memory window BAR size greater or equal to 4M is to use the CMA feature
in 3.16 kernel with the appropriate CONFIG_CMA_ALIGNMENT and
CONFIG_CMA_SIZE_MBYTES set.
Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Jon Mason <jdmason@kudzu.us>
Jon Mason [Thu, 19 Jun 2014 17:11:13 +0000 (10:11 -0700)]
NTB: correct the spread of queues over mw's
The detection of an uneven number of queues on the given memory windows
was not correct. The mw_num is zero based and the mod should be
division to spread them evenly over the mw's.
Merge branches 'locking-urgent-for-linus' and 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull futex and timer fixes from Thomas Gleixner:
"A oneliner bugfix for the jinxed futex code:
- Drop hash bucket lock in the error exit path. I really could slap
myself for intruducing that bug while fixing all the other horror
in that code three month ago ...
and the timer department is not too proud about the following fixes:
- Deal with a long standing rounding bug in the timeval to jiffies
conversion. It's a real issue and this fix fell through the cracks
for quite some time.
- Another round of alarmtimer fixes. Finally this code gets used
more widely and the subtle issues hidden for quite some time are
noticed and fixed. Nothing really exciting, just the itty bitty
details which bite the serious users here and there"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
futex: Unlock hb->lock in futex_wait_requeue_pi() error path
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
alarmtimer: Lock k_itimer during timer callback
alarmtimer: Do not signal SIGEV_NONE timers
alarmtimer: Return relative times in timer_gettime
jiffies: Fix timeval conversion to jiffies
Josef Bacik found a performance regression between 3.2 and 3.10 and
narrowed it down to commit bfcfaa77bdf0 ("vfs: use 'unsigned long'
accesses for dcache name comparison and hashing"). He reports:
On xfs on a fio card this goes at about 20k dir/sec with 3.2, and 12k
dir/sec with 3.10. This is because we spend waaaaay more time in
__d_lookup on 3.10 than in 3.2.
The new hashing function for strings is suboptimal for <
sizeof(unsigned long) string names (and hell even > sizeof(unsigned
long) string names that I've tested). I broke out the old hashing
function and the new one into a userspace helper to get real numbers
and this is what I'm getting:
Old hash table had 1000000 entries, 0 dupes, 0 max dupes
New hash table had 12628 entries, 987372 dupes, 900 max dupes
We had 11400 buckets with a p50 of 30 dupes, p90 of 240 dupes, p99 of 567 dupes for the new hash
My test does the hash, and then does the d_hash into a integer pointer
array the same size as the dentry hash table on my system, and then
just increments the value at the address we got to see how many
entries we overlap with.
As you can see the old hash function ended up with all 1 million
entries in their own bucket, whereas the new one they are only
distributed among ~12.5k buckets, which is why we're using so much
more CPU in __d_lookup".
The reason for this hash regression is two-fold:
- On 64-bit architectures the down-mixing of the original 64-bit
word-at-a-time hash into the final 32-bit hash value is very
simplistic and suboptimal, and just adds the two 32-bit parts
together.
In particular, because there is no bit shuffling and the mixing
boundary is also a byte boundary, similar character patterns in the
low and high word easily end up just canceling each other out.
- the old byte-at-a-time hash mixed each byte into the final hash as it
hashed the path component name, resulting in the low bits of the hash
generally being a good source of hash data. That is not true for the
word-at-a-time case, and the hash data is distributed among all the
bits.
The fix is the same in both cases: do a better job of mixing the bits up
and using as much of the hash data as possible. We already have the
"hash_32|64()" functions to do that.
Reported-by: Josef Bacik <jbacik@fb.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make hash_64() use a 64-bit multiply when appropriate
The hash_64() function historically does the multiply by the
GOLDEN_RATIO_PRIME_64 number with explicit shifts and adds, because
unlike the 32-bit case, gcc seems unable to turn the constant multiply
into the more appropriate shift and adds when required.
However, that means that we generate those shifts and adds even when the
architecture has a fast multiplier, and could just do it better in
hardware.
Use the now-cleaned-up CONFIG_ARCH_HAS_FAST_MULTIPLIER (together with
"is it a 64-bit architecture") to decide whether to use an integer
multiply or the explicit sequence of shift/add instructions.
Make ARCH_HAS_FAST_MULTIPLIER a real config variable
It used to be an ad-hoc hack defined by the x86 version of
<asm/bitops.h> that enabled a couple of library routines to know whether
an integer multiply is faster than repeated shifts and additions.
This just makes it use the real Kconfig system instead, and makes x86
(which was the only architecture that did this) select the option.
NOTE! Even for x86, this really is kind of wrong. If we cared, we would
probably not enable this for builds optimized for netburst (P4), where
shifts-and-adds are generally faster than multiplies. This patch does
*not* change that kind of logic, though, it is purely a syntactic change
with no code changes.
This was triggered by the fact that we have other places that really
want to know "do I want to expand multiples by constants by hand or
not", particularly the hash generation code.
Merge tag 'dm-3.17-fix2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fix from Mike Snitzer:
"Fix a race in the DM cache target that caused dirty blocks to be
marked as clean. This could cause no writeback to occur or spurious
dirty block counts"
* tag 'dm-3.17-fix2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm cache: fix race causing dirty blocks to be marked as clean
projects / linux-beck.git / log