irq_choose_cpu() should compare the affinity mask against cpu_online_map
rather than CPU_MASK_ALL, since irq_select_affinity() sets the interrupt's
affinity mask to cpu_online_map "and" CPU_MASK_ALL (which ends up being
just cpu_online_map).  The mask comparison in irq_choose_cpu() will always
fail since the two masks are not the same.  So the CPU chosen is the first CPU
in the intersection of cpu_online_map and CPU_MASK_ALL, which is always CPU0.
That means all interrupts are reassigned to CPU0...

Distributing interrupts to CPUs in a linearly increasing round robin fashion
is not optimal for the UltraSPARC T1/T2.  Also, the irq_rover in
irq_choose_cpu() causes an interrupt to be assigned to a different
processor each time the interrupt is allocated and released.  This may lead
to an unbalanced distribution over time.

A static mapping of interrupts to processors is done to optimize and balance
interrupt distribution.  For the T1/T2, interrupts are spread to different
cores first, and then to strands within a core.

The following is some benchmarks showing the effects of interrupt
distribution on a T2.  The test was done with iperf using a pair of T5220
boxes, each with a 10GBe NIU (XAUI) connected back to back.

  TCP     | Stock       Linear RR IRQ  Optimized IRQ
  Streams | 2.6.30-rc5  Distribution   Distribution
          | GBits/sec   GBits/sec      GBits/sec
  --------+-----------------------------------------
    1       0.839       0.862          0.868
    8       1.16        4.96           5.88
   16       1.15        6.40           8.04
  100       1.09        7.28           8.68
Signed-off-by: NHong H. Pham <hong.pham@windriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This gets us real close to the generic implementation of
setup_per_cpu_areas() except:

1) We store the per-cpu offset into the trap_block[], whereas
   the generic code has it's own static array.

2) We have to initialize the %g5 register to hold the boot cpu's
   per-cpu area offset.

3) The OBP/MDESC cpu info scan is performed at the end.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that we defer the cpu_data() initializations to the end of per-cpu
setup, we can get rid of this local hack we had to setup the per-cpu
areas eary.

This is a necessary step in order to support HAVE_DYNAMIC_PER_CPU_AREA
since the per-cpu setup must run when page structs are available.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We need to split up the cpu present mask setup from the cpu_data
initialization, and this is a first step towards that.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With feedback from Sam Ravnborg.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Surprisingly this actually makes LOAD_PER_CPU_BASE() a little
more efficient.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Later we're going to want to get at these definitions from
asm/percpu.h and that's not possible via cpudata.h because
of the set of dependencies the non-trap_block[] stuff has.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This really isn't necessary at all, a local variable suits the
job just fine.

This frees up 8 bytes in the trap_block[] that we can use later
to store the per-cpu base addresses.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ad6561df ("module: trim exception table on init
free.") put a bogus trim_init_extable() function into ia64 which didn't compile.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Without this, the default implementation is a no op which is completely
wrong with a VIVT cache, and usage of sg_copy_buffer() produces
unpredictable results.
Tested-by: NSebastian Andrzej Siewior <bigeasy@breakpoint.cc>

CC: stable@kernel.org
Signed-off-by: NNicolas Pitre <nico@marvell.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

fix the following 'make headers_check' warnings:

  usr/include/asm-mn10300/setup.h:14: extern's make no sense in userspace
  usr/include/asm-mn10300/setup.h:15: extern's make no sense in userspace
Signed-off-by: NJaswinder Singh Rajput <jaswinderrajput@gmail.com>

fix the following 'make headers_check' warning:

  usr/include/asm-mn10300/ptrace.h:80: extern's make no sense in userspace
Signed-off-by: NJaswinder Singh Rajput <jaswinderrajput@gmail.com>

Fix interaction with new generic header stuff as added by:

	commit 6103ec56
	Author: Arnd Bergmann <arnd@arndb.de>
	Date:   Wed May 13 22:56:27 2009 +0000

	    asm-generic: add generic ABI headers

The problem is that asm/signal.h has been made to include asm-generic/signal.h,
but the redundant stuff from asm/signal.h has not been discarded, leading to
multiple redefinitions.

Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The unaligned address exception handler (and others) does not scan the
fixup tables before oopsing. This is bad because it means passing a
badly aligned pointer from user space might crash the kernel.

Fix this by scanning the fixup tables in _exception(). This should
resolve the issue for unaligned addresses as well as other less common
exceptions that might be happening during a userspace access. The page
fault handler already does fixup processing.
Signed-off-by: NHaavard Skinnemoen <haavard.skinnemoen@atmel.com>

This patch (as1241) renames a bunch of functions in the PM core.
Rather than go through a boring list of name changes, suffice it to
say that in the end we have a bunch of pairs of functions:

	device_resume_noirq	dpm_resume_noirq
	device_resume		dpm_resume
	device_complete		dpm_complete
	device_suspend_noirq	dpm_suspend_noirq
	device_suspend		dpm_suspend
	device_prepare		dpm_prepare

in which device_X does the X operation on a single device and dpm_X
invokes device_X for all devices in the dpm_list.

In addition, the old dpm_power_up and device_resume_noirq have been
combined into a single function (dpm_resume_noirq).

Lastly, dpm_suspend_start and dpm_resume_end are the renamed versions
of the former top-level device_suspend and device_resume routines.
Signed-off-by: NAlan Stern <stern@rowland.harvard.edu>
Acked-by: NMagnus Damm <damm@igel.co.jp>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Rename the functions performing "_noirq" dev_pm_ops
operations from device_power_down() and device_power_up()
to device_suspend_noirq() and device_resume_noirq().

The new function names are chosen to show that the functions
are responsible for calling the _noirq() versions to finalize
the suspend/resume operation. The current function names do
not perform power down/up anymore so the names may be misleading.

Global function renames:
- device_power_down() -> device_suspend_noirq()
- device_power_up() -> device_resume_noirq()

Static function renames:
- suspend_device_noirq() -> __device_suspend_noirq()
- resume_device_noirq() -> __device_resume_noirq()
Signed-off-by: NMagnus Damm <damm@igel.co.jp>
Acked-by: NGreg Kroah-Hartman <gregkh@suse.de>
Acked-by: NLen Brown <lenb@kernel.org>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

This patch removes unused asm/suspend.h files for
the following architectures:

 alpha, arm, ia64, m68k, mips, s390, um
Signed-off-by: NMagnus Damm <damm@igel.co.jp>
Acked-by: NPavel Machek <pavel@ucw.cz>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

This is the last unification step. Here we do remove one of the files
and rename the left one as cpu.c, as both are now the same.
Also update power/Makefile, telling it to build cpu.o, instead of
cpu_(32|64).o
Signed-off-by: NSergio Luis <sergio@larces.uece.br>
Signed-off-by: NLauro Salmito <laurosalmito@gmail.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

In this step, we do unify the copyright notes for both files
cpu_32.c and cpu_64.c, making such files exactly the same.
It's the last step before the actual unification, that will
rename one of them to cpu.c and remove the other one.
Signed-off-by: NSergio Luis <sergio@larces.uece.br>
Signed-off-by: NLauro Salmito <laurosalmito@gmail.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

In this step we do unify cpu_32.c and cpu_64.c functions that
work on restoring the saved processor state. Also, we do
eliminate the forward declaration of fix_processor_context()
for X86_64, as it's not needed anymore.
Signed-off-by: NSergio Luis <sergio@larces.uece.br>
Signed-off-by: NLauro Salmito <laurosalmito@gmail.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

In this step we do unify cpu_32.c and cpu_64.c functions that
work on saving the processor state.
Signed-off-by: NSergio Luis <sergio@larces.uece.br>
Signed-off-by: NLauro Salmito <laurosalmito@gmail.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Aiming total unification of cpu_32.c and cpu_64.c, in this step
we do unify the global variables and existing forward declarations
for such files.
Signed-off-by: NSergio Luis <sergio@larces.uece.br>
Signed-off-by: NLauro Salmito <laurosalmito@gmail.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

First step towards the unification of cpu_32.c and cpu_64.c.
This commit unifies the headers of such files, making both
of them use the same header files. It also remove the uneeded
<module.h>.
Signed-off-by: NSergio Luis <sergio@larces.uece.br>
Signed-off-by: NLauro Salmito <laurosalmito@gmail.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

One of the numbers in arch/x86/kernel/acpi/sleep.c is long, but it is
not annotated appropriately, so sparese warns about it.  Fix that.

[rjw: added the changelog.]
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

fix ETIMEOUT -> ETIMEDOUT typos
Signed-off-by: NJean Delvare <khali@linux-fr.org>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

.ko is normally not included in Kconfig help, make it consistent.
Signed-off-by: NPavel Machek <pavel@ucw.cz>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

Fixes a trivial spelling error in powerpc code comments.
Signed-off-by: NSankar P <sankar.curiosity@gmail.com>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

trivial: fix typos s/paramter/parameter/ and s/excute/execute/ in documentation and source comments.
Signed-off-by: NMartin Olsson <martin@minimum.se>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

This version requires that host and guest have the same PAE status.
NX cap is not offered to the guest, yet.
Signed-off-by: NMatias Zabaljauregui <zabaljauregui@gmail.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Add support for kvm_hypercall4(); PAE wants it.

Signed-off-by: Matias Zabaljauregui <zabaljauregui at gmail.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

replace LHCALL_SET_PMD with LHCALL_SET_PGD hypercall name
(That's really what it is, and the confusion gets worse with PAE support)
Signed-off-by: NMatias Zabaljauregui <zabaljauregui@gmail.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Reported-by: NJeremy Fitzhardinge <jeremy@goop.org>

Some cleanups and replace direct assignment with native_set_* macros which properly handle 64-bit entries when PAE is activated
Signed-off-by: NMatias Zabaljauregui <zabaljauregui@gmail.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

The downside of the last patch which made restore_flags and irq_enable
check interrupts is that they are now too big to be patched directly
into the callsites, so the C versions are always used.

But the C versions go via PV_CALLEE_SAVE_REGS_THUNK which saves all
the registers.  In fact, we don't need any registers in the fast path,
so we can do better than this if we actually code them in assembler.

The results are in the noise, but since it's about the same amount of
code, it's worth applying.

1GB Guest->Host: input(suppressed),output(suppressed)
Before:
	Seconds: 0:16.53
	Packets: 377268,753673
	Interrupts: 22461,24297
	Notifications: 1(5245),21303(732370)
	Net IRQs triggered: 377023(245),42578(711095)

After:
	Seconds: 0:16.48
	Packets: 377289,753673
	Interrupts: 22281,24465
	Notifications: 1(5245),21296(732377)
	Net IRQs triggered: 377060(229),42564(711109)
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

lguest never checked for pending interrupts when enabling interrupts, and
things still worked.  However, it makes a significant difference to TCP
performance, so it's time we fixed it by introducing a pending_irq flag
and checking it on irq_restore and irq_enable.

These two routines are now too big to patch into the 8/10 bytes
patch space, so we drop that code.

Note: The high latency on interrupt delivery had a very curious
effect: once everything else was optimized, networking without GSO was
faster than networking with GSO, since more interrupts were sent and
hence a greater chance of one getting through to the Guest!

Note2: (Almost) Closing the same loophole for iret doesn't have any
measurable effect, so I'm leaving that patch for the moment.

Before:
	1GB tcpblast Guest->Host:		30.7 seconds
	1GB tcpblast Guest->Host (no GSO):	76.0 seconds

After:
	1GB tcpblast Guest->Host:		6.8 seconds
	1GB tcpblast Guest->Host (no GSO):	27.8 seconds
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Copy from arch/x86/kernel/irqinit_32.c: we don't use the vectors beyond
LGUEST_IRQS (if any), but we might as well set them all.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>