The x_tables are organized with a table structure and a per-cpu copies
of the counters and rules. On older kernels there was a reader/writer
lock per table which was a performance bottleneck. In 2.6.30-rc, this
was converted to use RCU and the counters/rules which solved the performance
problems for do_table but made replacing rules much slower because of
the necessary RCU grace period.
This version uses a per-cpu set of spinlocks and counters to allow to
table processing to proceed without the cache thrashing of a global
reader lock and keeps the same performance for table updates.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Bluetooth stack uses a reference counting for all established ACL
links and if no user (L2CAP connection) is present, the link will be
terminated to save power. The problem part is the dedicated pairing
when using Legacy Pairing (Bluetooth 2.0 and before). At that point
no user is present and pairing attempts will be disconnected within
10 seconds or less. In previous kernel version this was not a problem
since the disconnect timeout wasn't triggered on incoming connections
for the first time. However this caused issues with broken host stacks
that kept the connections around after dedicated pairing. When the
support for Simple Pairing got added, the link establishment procedure
needed to be changed and now causes issues when using Legacy Pairing
When using Simple Pairing it is possible to do a proper reference
counting of ACL link users. With Legacy Pairing this is not possible
since the specification is unclear in some areas and too many broken
Bluetooth devices have already been deployed. So instead of trying to
deal with all the broken devices, a special pairing timeout will be
introduced that increases the timeout to 60 seconds when pairing is
triggered.
If a broken devices now puts the stack into an unforeseen state, the
worst that happens is the disconnect timeout triggers after 120 seconds
instead of 4 seconds. This allows successful pairings with legacy and
broken devices now.
Based on a report by Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
In 2.6.25 we added UDP mem accounting.
This unfortunatly added a penalty when a frame is transmitted, since
we have at TX completion time to call sock_wfree() to perform necessary
memory accounting. This calls sock_def_write_space() and utimately
scheduler if any thread is waiting on the socket.
Thread(s) waiting for an incoming frame was scheduled, then had to sleep
again as event was meaningless.
(All threads waiting on a socket are using same sk_sleep anchor)
This adds lot of extra wakeups and increases latencies, as noted
by Christoph Lameter, and slows down softirq handler.
Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2
Fortunatly, Davide Libenzi recently added concept of keyed wakeups
into kernel, and particularly for sockets (see commit
37e5540b3c
epoll keyed wakeups: make sockets use keyed wakeups)
Davide goal was to optimize epoll, but this new wakeup infrastructure
can help non epoll users as well, if they care to setup an appropriate
handler.
This patch introduces new DEFINE_WAIT_FUNC() helper and uses it
in wait_for_packet(), so that only relevant event can wakeup a thread
blocked in this function.
Trace of function calls from bnx2 TX completion bnx2_poll_work() is :
__kfree_skb()
skb_release_head_state()
sock_wfree()
sock_def_write_space()
__wake_up_sync_key()
__wake_up_common()
receiver_wake_function() : Stops here since thread is waiting for an INPUT
Reported-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds missing role attribute to the DCCP type, otherwise
the creation of entries is not of any use.
The attribute added is CTA_PROTOINFO_DCCP_ROLE which contains the
role of the conntrack original tuple.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
The removal of the SAME target accidentally removed one feature that is
not available from the normal NAT targets so far, having multi-range
mappings that use the same mapping for each connection from a single
client. The current behaviour is to choose the address from the range
based on source and destination IP, which breaks when communicating
with sites having multiple addresses that require all connections to
originate from the same IP address.
Introduce a IP_NAT_RANGE_PERSISTENT option that controls whether the
destination address is taken into account for selecting addresses.
http://bugzilla.kernel.org/show_bug.cgi?id=12954
Signed-off-by: Patrick McHardy <kaber@trash.net>
Marvell 88E1121R Dual PHY device can be hardware-configured
to use shared interrupt pin for both PHY ports. For such
PHY configurations using shared PHY interrupt phy_interrupt()
handler will also schedule a work for PHY port which didn't
cause an interrupt.
This patch adds a possibility for PHY drivers to provide
did_interrupt() function which reports if the PHY (or a PHY
port in a multi-PHY device) generated an interrupt. This
function is called in phy_change() as phy_change() shouldn't
proceed if it is invoked for a PHY which didn't cause an
interrupt. So check for interrupt originator in phy_change()
to allow early-out.
Signed-off-by: Anatolij Gustschin <agust@denx.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a race between resume from hibernation and the asynchronous
scanning of SCSI devices and to prevent it from happening we need to
call scsi_complete_async_scans() during resume from hibernation.
In addition, if the resume from hibernation is userland-driven, it's
better to wait for all device probes in the kernel to complete before
attempting to open the resume device.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
tracing/filters: return proper error code when writing filter file
tracing/filters: allow user input integer to be oct or hex
tracing/filters: fix NULL pointer dereference
tracing/filters: NIL-terminate user input filter
ftrace: Output REC->var instead of __entry->var for trace format
Make __stringify support variable argument macros too
tracing: fix document references
tracing: fix splice return too large
tracing: update file->f_pos when splice(2) it
tracing: allocate page when needed
tracing: disable seeking for trace_pipe_raw
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
lockdep: continue lock debugging despite some taints
lockdep: warn about lockdep disabling after kernel taint
* 'i2c-for-linus' of git://jdelvare.pck.nerim.net/jdelvare-2.6:
i2c: Let new-style drivers implement attach_adapter
i2c: Fix sparse warnings for I2C_BOARD_INFO()
i2c-voodoo3: Deprecate in favor of tdfxfb
i2c-algo-pca: Fix use of uninitialized variable in debug message
When POSIX capabilities were introduced during the 2.1 Linux
cycle, the fs mask, which represents the capabilities which having
fsuid==0 is supposed to grant, did not include CAP_MKNOD and
CAP_LINUX_IMMUTABLE. However, before capabilities the privilege
to call these did in fact depend upon fsuid==0.
This patch introduces those capabilities into the fsmask,
restoring the old behavior.
See the thread starting at http://lkml.org/lkml/2009/3/11/157 for
reference.
Note that if this fix is deemed valid, then earlier kernel versions (2.4
and 2.2) ought to be fixed too.
Changelog:
[Mar 23] Actually delete old CAP_FS_SET definition...
[Mar 20] Updated against J. Bruce Fields's patch
Reported-by: Igor Zhbanov <izh1979@gmail.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: stable@kernel.org
Cc: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
percpu: unbreak alpha percpu
mutex: have non-spinning mutexes on s390 by default
Since the first argument to I2C_BOARD_INFO() must be a string constant,
there is no need to parenthesise it, and adding parentheses results in
an invalid initialiser for char[]. gcc obviously accepts this syntax as
an extension, but sparse complains, e.g.:
drivers/net/sfc/boards.c:173:2: warning: array initialized from parenthesized string constant
Therefore, remove the parentheses.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Impact: provide useful missing info for developers
Kernel taint can occur in several situations such as warnings,
load of prorietary or staging modules, bad page, etc...
But when such taint happens, a developer might still be working on
the kernel, expecting that lockdep is still enabled. But a taint
disables lockdep without ever warning about it.
Such a kernel behaviour doesn't really help for kernel development.
This patch adds this missing warning.
Since the taint is done most of the time after the main message that
explain the real source issue, it seems safe to warn about it inside
add_taint() so that it appears at last, without hurting the main
information.
v2: Use a generic helper to disable lockdep instead of an
open coded xchg().
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1239412638-6739-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For the time being, move the generic percpu_*() accessors to
linux/percpu.h.
asm-generic/percpu.h is meant to carry generic stuff for low level
stuff - declarations, definitions and pointer offset calculation
and so on but not for generic interface.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-2.6-mn10300:
Separate out the proc- and unit-specific header directories from the general
Move arch headers from include/asm-mn10300/ to arch/mn10300/include/asm/.
For example:
__stringify(__entry->irq, __entry->ret)
will now convert it to:
"REC->irq, REC->ret"
It also still supports single arguments as the old macro did.
Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <49DC6751.30308@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6: (27 commits)
xsysace: Fix dereferencing of cf_id after hd_driveid removal
at91_ide: turn on PIO 6 support
at91_ide: remove unused ide_mm_{outb,inb}
ide-cd: reverse NOT_READY sense key logic
ide: refactor tf_read() method
ide: refactor tf_load() method
ide: call write_devctl() method from tf_read() method
ide: move common code out of tf_load() method
ide: simplify 'struct ide_taskfile'
ide: replace IDE_TFLAG_* flags by IDE_VALID_*
ide-cd: fix intendation in cdrom_decode_status()
ide-cd: unify handling of fs and pc requests in cdrom_decode_status()
ide-cd: convert cdrom_decode_status() to use switch statements
ide-cd: update debugging support
ide-cd: respect REQ_QUIET for fs requests in cdrom_decode_status()
ide: remove unused #include <linux/version.h>
tx4939ide: Fix tx4939ide_{in,out}put_data_swap argument
tx493[89]ide: Remove big endian version of tx493[89]ide_tf_{load,read}
ide-cd: carve out an ide_cd_breathe()-helper for fs write requests
ide-cd: move status checking into the IRQ handler
...
asm-frv/pgtable.h could just #include <asm-generic/pgtable.h> in NOMMU mode
rather than #defining macros for lazy MMU and CPU stuff.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
tracing: consolidate documents
blktrace: pass the right pointer to kfree()
tracing/syscalls: use a dedicated file header
tracing: append a comma to INIT_FTRACE_GRAPH
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched: do not count frozen tasks toward load
sched: refresh MAINTAINERS entry
sched: Print sched_group::__cpu_power in sched_domain_debug
cpuacct: add per-cgroup utime/stime statistics
posixtimers, sched: Fix posix clock monotonicity
sched_rt: don't allocate cpumask in fastpath
cpuacct: make cpuacct hierarchy walk in cpuacct_charge() safe when rcupreempt is used -v2
Since the whole point of try_then_request_module is to retry
the operation after a module has been loaded, we must wait for
the module to fully load.
Otherwise all sort of things start breaking, e.g., you won't
be able to read your encrypted disks on the first attempt.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Maciej Rutecki <maciej.rutecki@gmail.com>
Tested-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Freezing tasks via the cgroup freezer causes the load average to climb
because the freezer's current implementation puts frozen tasks in
uninterruptible sleep (D state).
Some applications which perform job-scheduling functions consult the
load average when making decisions. If a cgroup is frozen, the load
average does not provide a useful measure of the system's utilization
to such applications. This is especially inconvenient if the job
scheduler employs the cgroup freezer as a mechanism for preempting low
priority jobs. Contrast this with using SIGSTOP for the same purpose:
the stopped tasks do not count toward system load.
Change task_contributes_to_load() to return false if the task is
frozen. This results in /proc/loadavg behavior that better meets
users' expectations.
Signed-off-by: Nathan Lynch <ntl@pobox.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Nigel Cunningham <nigel@tuxonice.net>
Tested-by: Nigel Cunningham <nigel@tuxonice.net>
Cc: <stable@kernel.org>
Cc: containers@lists.linux-foundation.org
Cc: linux-pm@lists.linux-foundation.org
Cc: Matt Helsley <matthltc@us.ibm.com>
LKML-Reference: <20090408194512.47a99b95@manatee.lan>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: fix build warnings and possibe compat misbehavior on IA64
Building a kernel on ia64 might trigger these ugly build warnings:
CC arch/ia64/ia32/sys_ia32.o
In file included from arch/ia64/ia32/sys_ia32.c:55:
arch/ia64/ia32/ia32priv.h:290:1: warning: "elf_check_arch" redefined
In file included from include/linux/elf.h:7,
from include/linux/module.h:14,
from include/linux/ftrace.h:8,
from include/linux/syscalls.h:68,
from arch/ia64/ia32/sys_ia32.c:18:
arch/ia64/include/asm/elf.h:19:1: warning: this is the location of the previous definition
[...]
sys_ia32.c includes linux/syscalls.h which in turn includes linux/ftrace.h
to import the syscalls tracing prototypes.
But including ftrace.h can pull too much things for a low level file,
especially on ia64 where the ia32 private headers conflict with higher
level headers.
Now we isolate the syscall tracing headers in their own lightweight file.
Reported-by: Tony Luck <tony.luck@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Jason Baron <jbaron@redhat.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Jiaying Zhang <jiayingz@google.com>
Cc: Michael Rubin <mrubin@google.com>
Cc: Martin Bligh <mbligh@google.com>
Cc: Michael Davidson <md@google.com>
LKML-Reference: <20090408184058.GB6017@nowhere>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
igb: remove sysfs entry that was used to set the number of vfs
igbvf: add new driver to support 82576 virtual functions
drivers/net/eql.c: Fix a dev leakage.
niu: Fix unused variable warning.
r6040: set MODULE_VERSION
bnx2: Don't use reserved names
FEC driver: add missing #endif
niu: Fix error handling
mv643xx_eth: don't reset the rx coal timer on interface up
smsc911x: correct debugging message on mii read timeout
ethoc: fix library build errors
netfilter: ctnetlink: fix regression in expectation handling
netfilter: fix selection of "LED" target in netfilter
netfilter: ip6tables regression fix
Prepare for full barrier implementation: first remove the restricted support.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6:
x86 ACPI: Add support for Always Running APIC timer
ACPI x86: Make aperf/mperf MSR access in acpi_cpufreq read_only
ACPI x86: Cleanup acpi_cpufreq structures related to aperf/mperf
ACPICA: delete check for AML access to port 0x81-83
ACPI: WMI: use .notify method instead of installing handler directly
sony-laptop: use .notify method instead of installing handler directly
panasonic-laptop: use .notify method instead of installing handler directly
fujitsu-laptop: use .notify method instead of installing hotkey handler directly
fujitsu-laptop: use .notify method instead of installing handler directly
ACPI: video: use .notify method instead of installing handler directly
ACPI: thermal: use .notify method instead of installing handler directly
ACPI battery: fix async boot oops
ACPI: delete acpi_device.g_list
NULL noise: drivers/platform/x86/panasonic-laptop.c
ACPI: cpufreq: remove dupilcated #include
ACPI: Adjust Kelvin offset to match local implementation
ACPI: convert acpi_device_lock spinlock to mutex
Thou shalt remember to use 'git add' or errors shall be visited on your
downloads and there shall be wrath from on list and much gnashing of teeth.
Thou shalt remember to use git status or there shall be catcalls and much
embarrasment shall come to pass.
Signed-off-by: Alan "I'm hiding" Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Simplify tf_read() method, making it deal only with 'struct ide_taskfile' and
the validity flags that the upper layer passes, and factoring out the code that
deals with the high order bytes into ide_tf_readback() to be called from the
only two functions interested, ide_complete_cmd() and ide_dump_sector().
This should stop the needless code duplication in this method and so make
it about twice smaller than it was; along with simplifying the setup for
the method call, this should save both time and space...
Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Simplify tf_load() method, making it deal only with 'struct ide_taskfile' and
the validity flags that the upper layer passes, and moving the code that deals
with the high order bytes into the only function interested, do_rw_taskfile().
This should stop the needless code duplication in this method and so make
it about twice smaller than it was; along with simplifying the setup for the
method call, this should save both time and space...
Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Make 'struct ide_taskfile' cover only 8 register values and thus put two such
fields ('tf' and 'hob') into 'struct ide_cmd', dropping unnecessary 'tf_array'
field from it.
This required changing the prototype of ide_get_lba_addr() and ide_tf_dump().
Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
[bart: fix setting of ATA_LBA bit for LBA48 commands in __ide_do_rw_disk()]
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Replace IDE_TFLAG_{IN|OUT}_* flags meaning to the taskfile register validity on
input/output by the IDE_VALID_* flags and introduce 4 symmetric 8-bit register
validity indicator subfields, 'valid.{input/output}.{tf|hob}', into the 'struct
ide_cmd' instead of using the 'tf_flags' field for that purpose (this field can
then be turned from 32-bit into 8-bit one).
Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
