Defers the release of the socket reference using call_rcu() to
allow using an RCU read-side protected call to rhashtable_lookup()
This restores behaviour and performance gains as previously
introduced by e341694 ("netlink: Convert netlink_lookup() to use
RCU protected hash table") without the side effect of severely
delayed socket destruction.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to allow for wider usage of rhashtable, use a special nulls
marker to terminate each chain. The reason for not using the existing
nulls_list is that the prev pointer usage would not be valid as entries
can be linked in two different buckets at the same time.
The 4 nulls base bits can be set through the rhashtable_params structure
like this:
struct rhashtable_params params = {
[...]
.nulls_base = (1U << RHT_BASE_SHIFT),
};
This reduces the hash length from 32 bits to 27 bits.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduces an array of spinlocks to protect bucket mutations. The number
of spinlocks per CPU is configurable and selected based on the hash of
the bucket. This allows for parallel insertions and removals of entries
which do not share a lock.
The patch also defers expansion and shrinking to a worker queue which
allows insertion and removal from atomic context. Insertions and
deletions may occur in parallel to it and are only held up briefly
while the particular bucket is linked or unzipped.
Mutations of the bucket table pointer is protected by a new mutex, read
access is RCU protected.
In the event of an expansion or shrinking, the new bucket table allocated
is exposed as a so called future table as soon as the resize process
starts. Lookups, deletions, and insertions will briefly use both tables.
The future table becomes the main table after an RCU grace period and
initial linking of the old to the new table was performed. Optimization
of the chains to make use of the new number of buckets follows only the
new table is in use.
The side effect of this is that during that RCU grace period, a bucket
traversal using any rht_for_each() variant on the main table will not see
any insertions performed during the RCU grace period which would at that
point land in the future table. The lookup will see them as it searches
both tables if needed.
Having multiple insertions and removals occur in parallel requires nelems
to become an atomic counter.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
The removal function of nft_hash currently stores a reference to the
previous element during lookup which is used to optimize removal later
on. This was possible because a lock is held throughout calling
rhashtable_lookup() and rhashtable_remove().
With the introdution of deferred table resizing in parallel to lookups
and insertions, the nftables lock will no longer synchronize all
table mutations and the stored pprev may become invalid.
Removing this optimization makes removal slightly more expensive on
average but allows taking the resize cost out of the insert and
remove path.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Subsequent patches will require access to the bucket tail. Access
to the tail is relatively cheap as the automatic resizing of the
table should keep the number of entries per bucket to no more
than 0.75 on average.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is in preparation to introduce per bucket spinlocks. It
extends all iterator macros to take the bucket table and bucket
index. It also introduces a new rht_dereference_bucket() to
handle protected accesses to buckets.
It introduces a barrier() to the RCU iterators to the prevent
the compiler from caching the first element.
The lockdep verifier is introduced as stub which always succeeds
and properly implement in the next patch when the locks are
introduced.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hash the key inside of rhashtable_lookup_compare() like
rhashtable_lookup() does. This allows to simplify the hashing
functions and keep them private.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixs the following kbuild test robot warning:
coccinelle warnings: (new ones prefixed by >>)
>> net/mac802154/cfg.c:53:1-3: WARNING: PTR_ERR_OR_ZERO can be used
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
This patch handles the IEEE802154 Kconfig entry as menuconfig.
Furthermore we move this entry out of "Network Options" and put it into
"Networking" where the other networking subsystems are. This requires a
menuconfig entry like all other networking subsystems.
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
This patch renames the "af_ieee802154.c" to "socket.c". This is just a
cleanup to have a short name for it which describes the implementationm
stuff more human understandable.
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
This patch solves the following checkpatch issue:
CHECK: Comparison to NULL could be written "skb"
+ if (skb != NULL) {
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
This patch puts all related socket handling into one file. This is just
a cleanup to do all socket handling stuff inside of one implementation
file.
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
This patch changes the module name of af_802154 to ieee802154_socket.
Just for keeping the name convention according to the 6LoWPAN module
ieee802154_6lowpan.
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
This patch makes the ieee802154 socket handling as module. Currently
this is part of ieee802154 module. It pointed out that ieee802154 module
has also two module_init/module_exit functions. One inside of core.c and
the other in af_ieee802154.c. This patch will also solve this issue by
handle the af_802154 as separate module.
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Looks like we pull it in through other ways on x86, but we fail
on sparc:
In file included from drivers/block/cryptoloop.c:30:0:
drivers/block/loop.h:63:24: error: field 'tag_set' has incomplete type
struct blk_mq_tag_set tag_set;
Add the include to loop.h, kill it from loop.c.
Signed-off-by: Jens Axboe <axboe@fb.com>
block core handles REQ_FUA by its flush state machine, so
won't do it in loop explicitly.
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
No behaviour change, just move the handling for REQ_DISCARD
and REQ_FLUSH in these two functions.
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The conversion is a bit straightforward, and use work queue to
dispatch requests of loop block, and one big change is that requests
is submitted to backend file/device concurrently with work queue,
so throughput may get improved much. Given write requests over same
file are often run exclusively, so don't handle them concurrently for
avoiding extra context switch cost, possible lock contention and work
schedule cost. Also with blk-mq, there is opportunity to get loop I/O
merged before submitting to backend file/device.
In the following test:
- base: v3.19-rc2-2041231
- loop over file in ext4 file system on SSD disk
- bs: 4k, libaio, io depth: 64, O_DIRECT, num of jobs: 1
- throughput: IOPS
------------------------------------------------------
| | base | base with loop-mq | delta |
------------------------------------------------------
| randread | 1740 | 25318 | +1355%|
------------------------------------------------------
| read | 42196 | 51771 | +22.6%|
-----------------------------------------------------
| randwrite | 35709 | 34624 | -3% |
-----------------------------------------------------
| write | 39137 | 40326 | +3% |
-----------------------------------------------------
So loop-mq can improve throughput for both read and randread, meantime,
performance of write and randwrite isn't hurted basically.
Another benefit is that loop driver code gets simplified
much after blk-mq conversion, and the patch can be thought as
cleanup too.
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Commit b4c6a02877 exported the start and unfreeze, but we need
the regular blk_mq_freeze_queue() for the loop conversion.
Signed-off-by: Jens Axboe <axboe@fb.com>
Richard Cochran says:
====================
Fixing the "Time Counter fixes and improvements"
For this series I had only tested the build with ARCH=x86 and arm, but
others like sparc64, microblaze, powerpc, and s390 will fail because
they somehow don't indirectly include clocksource.h for the drivers in
question.
This series fixes the build issues reported by:
kbuild test robot <fengguang.wu@intel.com>
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The timecounter/cyclecounter code has moved, so users need the new include.
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This driver uses the function, clocksource_khz2mult, and so it really must
include clocksource.h.
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no need for users of the timecounter/cyclecounter code to include
clocksource.h just for a single macro.
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
OVS development is moved to netdev mailing list. Update tree and
list in MAINTAINERS file.
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When allocation of all RQs fail, we do not free previously allocated buffers,
before returning error. This causes memory leak.
This patch fixes this by calling vnic_rq_clean(), which frees all the rq
buffers.
Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some buggy firmwares export an incorrect MAC address (00:a0:c6:00:00:00). This
makes for example checking devices for random MAC addresses tricky, and you
might end up with multiple network interfaces with the same address.
This patch tries to fix, or at least improve, the situation by setting the MAC
address of devices with this firmware bug to a random address. I tested the
patch with two devices that has this firmware bug (Huawei E398 and E392), and
network traffic worked fine after changing the address.
Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Changes:
* ath9k: enable Transmit Power Control (TPC) for ar9003 chips
* rtlwifi: cleanup and updates from the vendor driver
* rsi: fix memory leak related to firmware image
* ath: parameter fix for FCC DFS pattern
Signed-off-by: David S. Miller <davem@davemloft.net>
Removes some functions that are not used anywhere:
enic_dev_enable2_done() enic_dev_enable2() enic_dev_deinit_done()
enic_dev_init_prov2() enic_vnic_dev_deinit()
This was partially found by using a static code analysis program called cppcheck.
Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
Removes some functions that are not used anywhere:
Read_hfc32() Write_hfc32() Write_hfc16()
This was partially found by using a static code analysis program called cppcheck.
Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove the function smt_ifconfig() that is not used anywhere.
This was partially found by using a static code analysis program called cppcheck.
Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
Removes some functions that are not used anywhere:
dbgi_rd_rsp3() dbgi_wr_addr3()
This was partially found by using a static code analysis program called cppcheck.
Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull SCSI fixes from James Bottomley:
"This is a set of three fixes: one to correct an abort path thinko
causing failures (and a panic) in USB on device misbehaviour, One to
fix an out of order issue in the fnic driver and one to match discard
expectations to qemu which otherwise cause Linux to behave badly as a
guest"
* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
SCSI: fix regression in scsi_send_eh_cmnd()
fnic: IOMMU Fault occurs when IO and abort IO is out of order
sd: tweak discard heuristics to work around QEMU SCSI issue
The Roper Class 1 Bluetooth Dongle is another device that claims to
support Bluetooth 1.2 specification, but does not support the HCI
command for reading the local supported commands.
< HCI Command: Read Local Version Information (0x04|0x0001) plen 0
> HCI Event: Command Complete (0x0e) plen 12
Read Local Version Information (0x04|0x0001) ncmd 1
status 0x00
HCI Version: 1.2 (0x2) HCI Revision: 0x0
LMP Version: 1.2 (0x2) LMP Subversion: 0x757
Manufacturer: Silicon Wave (11)
It clearly claims Bluetooth 1.2 support and in that regard has the
same issue as the AVM BlueFritz! USB devices (Silicon Wave based),
but the HCI Read Local Supported Commands command fails.
< HCI Command: Read Local Supported Commands (0x04|0x0002) plen 0
> HCI Event: Command Status (0x0f) plen 4
Read Local Supported Commands (0x04|0x0002) status 0x01 ncmd 1
Error: Unknown HCI Command
Use the HCI_QUIRK_BROKEN_LOCAL_COMMANDS quirk for these devices and
the failing command will be skipped.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
When the Bluetooth controllers requires an unconfigured state (for
example when the BD_ADDR is missing), then it is important to try
to register the SMP channels when the controller transitions to the
configured state.
This also fixes an issue with the debugfs entires that are not present
for controllers that start out as unconfigured.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
One of the LE Secure Connections security credentials was still using
the BT_DBG instead of SMP_DBG.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
The sc_only_mode debugfs entry is used to read the current state of the
Secure Connections Only mode. Before Bluetooth 4.2 this mode was only
for BR/EDR controllers and with that tight to the support Secure Simple
Pairing. Since Secure Connections is now available for BR/EDR and LE
this debugfs entry is no longer correctly place.
Move it to the common section and enable it when either BR/EDR Secure
Connections feature is supported or when the controller has LE support.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
The force_sc_support debugfs option was introduced to easily work with
pre-production Bluetooth 4.1 silicon. This option is no longer needed
since controllers supporting BR/EDR Secure Connections feature are now
available.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
The force_lesc_support debugfs option never really worked. It has a race
condition between creating the debugfs entry and registering the L2CAP
fixed channel for BR/EDR SMP support.
Also this has been replaced with a working force_bredr_smp debugfs
switch that developers can use now.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Testing cross-transport pairing that starts on BR/EDR is only valid when
using a controller with BR/EDR Secure Connections. Devices will indicate
this by providing BR/EDR SMP fixed channel over L2CAP. To allow testing
of this feature on Bluetooth 4.0 controller or controllers without the
BR/EDR Secure Connections features, introduce a force_bredr_smp debugfs
option that allows faking the required AES connection.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Until now, when VLAN acceleration was in use, the bytes of the VLAN header
were not included in port or flow byte counters. They were however
included when VLAN acceleration was not used. This commit corrects the
inconsistency, by always including the VLAN header in byte counters.
Previous discussion at
http://openvswitch.org/pipermail/dev/2014-December/049521.html
Reported-by: Motonori Shindo <mshindo@vmware.com>
Signed-off-by: Ben Pfaff <blp@nicira.com>
Reviewed-by: Flavio Leitner <fbl@sysclose.org>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
