linux-toradex.git/kernel/softirq.c, branch v2.6.18

[PATCH] Reducing local_bh_enable/disable overhead in irqtrace

2006-07-31T20:28:42+00:00

The recent changes from irqtrace feature has added overheads to
local_bh_disable and local_bh_enable that reduces UDP performance across
x86_64 and IA64, even though IA64 does not support the irqtrace feature.
Patch in question is

[PATCH]lockdep: irqtrace subsystem, core
http://www.kernel.org/git/?p=linux/kernel/git/torvalds/linux-2.6.git;a=c
ommit;h=de30a2b355ea85350ca2f58f3b9bf4e5bc007986

Prior to this patch, local_bh_disable was a short macro.  Now it is a
function which calls __local_bh_disable with added irq flags save and
restore.  The irq flags save and restore were also added to
local_bh_enable, probably for injecting the trace irqs code.

This overhead is on the generic code path across all architectures.  On a
IA_64 test machine (Itanium-2 1.6 GHz) running a benchmark like netperf's
UDP streaming test, the added overhead results in a drop of 3% in
throughput, as udp_sendmsg calls the local_bh_enable/disable several times.

Other workloads that have heavy usages of local_bh_enable/disable could
also be affected.  The patch ideally should not have affected IA-64
performance as it does not have IRQ tracing support.  A significant portion
of the overhead is in the added irq flags save and restore, which I think
is not needed if IRQ tracing is unused.  A suggested patch is attached
below that recovers the lost performance.  However, the "ifdef"s in the
patch are a bit ugly.

Signed-off-by: Tim Chen 
Acked-by: Ingo Molnar 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] cpu hotplug: replace devinit* with cpuinit* for cpu notifications

2006-07-31T20:28:39+00:00

Few of the callback functions and notifier blocks that are associated with cpu
notifications incorrectly have __devinit and __devinitdata.  They should be
__cpuinit and __cpuinitdata instead.

It makes no functional difference but wastes text area when CONFIG_HOTPLUG is
enabled and CONFIG_HOTPLUG_CPU is not.

This patch fixes all those instances.

Signed-off-by: Chandra Seetharaman 
Cc: Ashok Raj 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] unexport open_softirq

2006-07-15T04:53:53+00:00

Christoph Hellwig:
open_softirq just enables a softirq.  The softirq array is statically
allocated so to add a new one you would have to patch the kernel.  So
there's no point to keep this export at all as any user would have to
patch the enum in include/linux/interrupt.h anyway.

Signed-off-by: Adrian Bunk 
Acked-by: Ingo Molnar 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] kernel/softirq.c: EXPORT_UNUSED_SYMBOL

2006-07-10T20:24:18+00:00

This patch marks an unused export as EXPORT_UNUSED_SYMBOL.

Signed-off-by: Adrian Bunk 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] lockdep: irqtrace subsystem, move account_system_vtime() calls into kernel/softirq.c

2006-07-03T22:27:10+00:00

At the moment, powerpc and s390 have their own versions of do_softirq which
include local_bh_disable() and __local_bh_enable() calls.  They end up
calling __do_softirq (in kernel/softirq.c) which also does
local_bh_disable/enable.

Apparently the two levels of disable/enable trigger a warning from some
validation code that Ingo is working on, and he would like to see the outer
level removed.  But to do that, we have to move the account_system_vtime
calls that are currently in the arch do_softirq() implementations for
powerpc and s390 into the generic __do_softirq() (this is a no-op for other
archs because account_system_vtime is defined to be an empty inline
function on all other archs).  This patch does that.

Signed-off-by: Paul Mackerras 
Signed-off-by: Ingo Molnar 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] lockdep: irqtrace subsystem, core

2006-07-03T22:27:03+00:00

Accurate hard-IRQ-flags and softirq-flags state tracing.

This allows us to attach extra functionality to IRQ flags on/off
events (such as trace-on/off).

Signed-off-by: Ingo Molnar 
Signed-off-by: Arjan van de Ven 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] cpu hotplug: revert initdata patch submitted for 2.6.17

2006-06-28T00:32:41+00:00

This patch reverts notifier_block changes made in 2.6.17

Signed-off-by: Chandra Seetharaman 
Cc: Ashok Raj 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] cpu hotplug: revert init patch submitted for 2.6.17

2006-06-28T00:32:40+00:00

In 2.6.17, there was a problem with cpu_notifiers and XFS.  I provided a
band-aid solution to solve that problem.  In the process, i undid all the
changes you both were making to ensure that these notifiers were available
only at init time (unless CONFIG_HOTPLUG_CPU is defined).

We deferred the real fix to 2.6.18.  Here is a set of patches that fixes the
XFS problem cleanly and makes the cpu notifiers available only at init time
(unless CONFIG_HOTPLUG_CPU is defined).

If CONFIG_HOTPLUG_CPU is defined then cpu notifiers are available at run
time.

This patch reverts the notifier_call changes made in 2.6.17

Signed-off-by: Chandra Seetharaman 
Cc: Ashok Raj 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] cpu hotplug: fix CPU_UP_CANCEL handling

2006-06-25T17:01:22+00:00

If a cpu hotplug callback fails on CPU_UP_PREPARE, all callbacks will be
called with CPU_UP_CANCELED.  A few of these callbacks assume that on
CPU_UP_PREPARE a pointer to task has been stored in a percpu array.  This
assumption is not true if CPU_UP_PREPARE fails and the following calls to
kthread_bind() in CPU_UP_CANCELED will cause an addressing exception
because of passing a NULL pointer.

Signed-off-by: Heiko Carstens 
Cc: Ashok Raj 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] Remove devinit and cpuinit from notifier_call definitions

2006-04-26T15:30:03+00:00

Few of the notifier_chain_register() callers use __init in the definition
of notifier_call.  It is incorrect as the function definition should be
available after the initializations (they do not unregister them during
initializations).

This patch fixes all such usages to _not_ have the notifier_call __init
section.

Signed-off-by: Chandra Seetharaman 
Signed-off-by: Linus Torvalds