And add the __acquires() and __releases() annotations, while at it.
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

If an online-attempt on a CPU which has been offlined using H_CEDE
with an appropriate cede latency hint fails, don't panic.

Instead print the error message and let the __cpu_up() code notify the
CPU Hotplug framework of the failure, which in turn can notify the
other subsystem through CPU_UP_CANCELED.
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

It's possible to set CONFIG_XICS without CONFIG_PCI_MSI. When that happens,
the kernel fails to build with

arch/powerpc/platforms/built-in.o: In function `.xics_startup':
xics.c:(.text+0x12f60): undefined reference to `.unmask_msi_irq' make: ***
[.tmp_vmlinux1] Error 1

Furthermore, as noted by Benjamin Herrenschmidt, "CONFIG_XICS should be
made invisible and selected by PSERIES."

This patch fixes PSERIES to select both options

Signed-off-by: Mel Gorman <mel[at]csn.ul.ie>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The Collaborative Memory Manager (CMM) module allocates individual pages
over time that are not migratable.  On a long running system this can
severely impact the ability to find enough pages to support a hotplug
memory remove operation.

This patch adds a memory isolation notifier and a memory hotplug notifier.
The memory isolation notifier will return the number of pages found in
the range specified.  This is used to determine if all of the used pages
in a pageblock are owned by the balloon (or other entities in the notifier
chain).  The hotplug notifier will free pages in the range which is to be
removed.  The priority of this hotplug notifier is low so that it will be
called near last, this helps avoids removing loaned pages in operations
that fail due to other handlers.

CMM activity will be halted when hotplug remove operations are active and
resume activity after a delay period to allow the hypervisor time to
adjust.
Signed-off-by: NRobert Jennings <rcj@linux.vnet.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Brian King <brking@linux.vnet.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Gerald Schaefer <geralds@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Convert locks which cannot be sleeping locks in preempt-rt to
raw_spinlocks.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NPeter Zijlstra <peterz@infradead.org>
Acked-by: NIngo Molnar <mingo@elte.hu>

At the moment when we EOI an interrupt we set the CPPR back to 0xFF
regardless of its previous value. This could lead to problems if we
take an interrupt with a priority of 5, but before EOIing it we get
an IPI which has a priority of 4. The problem is that at the moment
when we EOI the IPI we will set the CPPR to 0xFF, but it should
really be set back to 5 (the previous priority).

To keep track of the previous CPPR values we create the xics_cppr
structure that has an array for CPPR values and an index pointing
to the current priority. This can easily grow if new priorities get
added in the future.

This will also be useful because the partition adjunct option of
upcoming machines will update the H_XIRR hcall to accept the CPPR
as a parameter.
Signed-off-by: NMark Nelson <markn@au1.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The recent patch to add cpu offline/online as part of the DLPAR
process for pseries causes a build break if CONFIG_SMP is not
defined.  Original patch here;
http://lists.ozlabs.org/pipermail/linuxppc-dev/2009-November/078299.html

This corrects the build break by moving the online_node_cpus
and offline_node_cpus under the #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
portions of dlpar.c.

This patch also slightly modifies the online_node_cpus and offline_node_cpus
routines to prepend dlpar_ to the them and make them static.  These two
routine are only used in the dlpar add/remove of cpus and these changes
should help clarify that.
Signed-off-by: NNathan Fontenot <nfont@austin.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Writing a driver using SCLPC on the MPC5200B I detected, that the
intspec arrays to map irqs to Linux virq cannot be const, because the
mapping and xlate functions only take non const pointers. All those
functions do not modify the intspec, so a const pointer could be used.
Signed-off-by: NRoman Fietze <roman.fietze@telemotive.de>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Currently the cpu-allocation/deallocation process comprises of two steps:
- Set the indicators and to update the device tree with DLPAR node
  information.

- Online/offline the allocated/deallocated CPU.

This is achieved by writing to the sysfs tunables "probe" during allocation
and "release" during deallocation.

At the sametime, the userspace can independently online/offline the CPUs of
the system using the sysfs tunable "online".

It is quite possible that when a userspace tool offlines a CPU
for the purpose of deallocation and is in the process of updating the device
tree, some other userspace tool could bring the CPU back online by writing to
the "online" sysfs tunable thereby causing the deallocate process to fail.

The solution to this is to serialize writes to the "probe/release" sysfs
tunable with the writes to the "online" sysfs tunable.

This patch employs a mutex to provide this serialization, which is a no-op on
all architectures except PPC_PSERIES
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Acked-by: NVaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Currently the cpu-allocation/deallocation on pSeries is a
two step process from the Userspace.

- Set the indicators and update the device tree by writing to the sysfs
  tunable "probe" during allocation and "release" during deallocation.
- Online / Offline the CPUs of the allocated/would_be_deallocated node by
  writing to the sysfs tunable "online".

This patch adds kernel code to online/offline the CPUs soon_after/just_before
they have been allocated/would_be_deallocated. This way, the userspace tool
that performs DLPAR operations would only have to deal with one set of sysfs
tunables namely "probe" and release".
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: NNathan Fontenot <nfont@austin.ibm.com>
Acked-by: NVaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This patch adds the specific routines to probe and release (add and remove)
cpu resource for the powerpc pseries platform and registers these handlers
with the ppc_md callout structure.
Signed-off-by: NNathan Fontenot <nfont@austin.ibm.com>
Acked-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The Dynamic Logical Partitioning capabilities of the powerpc pseries platform
allows for the addition and removal of resources (i.e. CPU's, memory, and PCI
devices) from a partition. The removal of a resource involves
removing the resource's node from the device tree and then returning the
resource to firmware via the rtas set-indicator call.  To add a resource, it
is first obtained from firmware via the rtas set-indicator call and then a
new device tree node is created using the ibm,configure-coinnector rtas call
and added to the device tree.

This patch provides the kernel DLPAR infrastructure in a new filed named
dlpar.c.  The functionality provided is for acquiring and releasing a resource
from firmware and the parsing of information returned from the
ibm,configure-connector rtas call.  Additionally this exports the pSeries
reconfiguration notifier chain so that it can be invoked when device tree
updates are made.
Signed-off-by: NNathan Fontenot <nfont@austin.ibm.com>
Acked-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

When a CPU is offlined on POWER currently, we call rtas_stop_self() and hand
the CPU back to the resource pool. This path is used for DLPAR which will
cause a change in the LPAR configuration which will be visible outside.

This patch changes the default state a CPU is put into when it is offlined.
On platforms which support ceding the processor to the hypervisor with
latency hint specifier value, during a cpu offline operation,
instead of calling rtas_stop_self(), we cede the vCPU to the hypervisor
while passing a latency hint specifier value. The Hypervisor can use this hint
to provide better energy savings. Also, during the offline
operation, the control of the vCPU remains with the LPAR as oppposed to
returning it to the resource pool.

The patch achieves this by creating an infrastructure to set the
preferred_offline_state() which can be either
- CPU_STATE_OFFLINE: which is the current behaviour of calling
  rtas_stop_self()

- CPU_STATE_INACTIVE: which cedes the vCPU to the hypervisor with the latency
  hint specifier.

The codepath which wants to perform a DLPAR operation can set the
preferred_offline_state() of a CPU to CPU_STATE_OFFLINE before invoking
cpu_down().

The patch also provides a boot-time command line argument to disable/enable
CPU_STATE_INACTIVE.
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: NNathan Fontenot <nfont@austin.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This patch provides an extended_cede_processor() helper function
which takes the cede latency hint as an argument. This hint is to be passed
on to the hypervisor to cede to the corresponding state on platforms
which support it.
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: NArun R Bharadwaj <arun@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The typename member of struct irq_chip was kept for migration purposes
and is obsolete since more than 2 years. Fix up the leftovers.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Acked-by: NGeoff Levand <geoffrey.levand@am.sony.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Patch f598282f exposed a problem in
powerpc MSI-X functionality, making network interfaces such as ixgbe
and cxgb3 stop to work when MSI-X is enabled. RX interrupts were not
being generated.

The problem was caused because MSI irq was not being effectively
unmasked after device initialization.
Signed-off-by: NAndre Detsch <adetsch@br.ibm.com>
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

When running Active Memory Sharing, the Collaborative Memory Manager (CMM)
may mark some pages as "loaned" with the hypervisor. Periodically, the
CMM will query the hypervisor for a loan request, which is a single signed
value. When kexec'ing into a kdump kernel, the CMM driver in the kdump
kernel is not aware of the pages the previous kernel had marked as "loaned",
so the hypervisor and the CMM driver are out of sync. Fix the CMM driver
to handle this scenario by ignoring requests to decrease the number of loaned
pages if we don't think we have any pages loaned. Pages that are marked as
"loaned" which are not in the balloon will automatically get switched to "active"
the next time we touch the page. This also fixes the case where totalram_pages
is smaller than min_mem_mb, which can occur during kdump.
Signed-off-by: NBrian King <brking@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

get_irq_desc() is a powerpc-specific version of irq_to_desc(). That
is reason enough to remove it, but it also doesn't know about sparse
irq_desc support which irq_to_desc() does (when we enable it).
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Acked-by: NGrant Likely <grant.likely@secretlab.ca>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Rather than open-coding our own check, use irq_has_action()
to check if an irq has an action - ie. is "in use".

irq_has_action() doesn't take the descriptor lock, but it
shouldn't matter - we're just using it as an indicator
that the irq is in use. disable_irq_nosync() will take
the descriptor lock before doing anything also.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Acked-by: NGrant Likely <grant.likely@secretlab.ca>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The CHRP code has some fishy timer based code to scan the RTAS event
log, which uses a 1KB stack buffer and doesn't even use the results.

The pSeries code as a nicer daemon that allows userspace to read the
event log and basically uses the same RTAS interface

This patch moves rtasd.c out of platform/pseries and makes it usable
by CHRP, after removing the old crufty event log mechanism in there.

The nvram logging part of the daemon is still only available on 64-bit
since the underlying nvram management routines aren't currently shared.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Some of the stuff in /proc/ppc64 such as the RTAS bits are actually
useful to some 32-bit platforms. Rename the file, and create a
symlink on 64-bit for backward compatibility
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This patch updates percpu related symbols in powerpc such that percpu
symbols are unique and don't clash with local symbols.  This serves
two purposes of decreasing the possibility of global percpu symbol
collision and allowing dropping per_cpu__ prefix from percpu symbols.

* arch/powerpc/kernel/perf_callchain.c: s/callchain/cpu_perf_callchain/

* arch/powerpc/kernel/setup-common.c: s/pvr/cpu_pvr/

* arch/powerpc/platforms/pseries/dtl.c: s/dtl/cpu_dtl/

* arch/powerpc/platforms/cell/interrupt.c: s/iic/cpu_iic/

Partly based on Rusty Russell's "alloc_percpu: rename percpu vars
which cause name clashes" patch.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@ozlabs.org

While most users of the hcall tracepoints will only want the opcode
and return code, some will want all the arguments.  To avoid the
complexity of using varargs we pass a pointer to the register save
area, which contains all the arguments.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Add hcall_entry and hcall_exit tracepoints.  This replaces the inline
assembly HCALL_STATS code and converts it to use the new tracepoints.

To keep the disabled case as quick as possible, we embed a status word
in the TOC so we can get at it with a single load.  By doing so we
keep the overhead at a minimum.  Time taken for a null hcall:

No tracepoint code:	135.79 cycles
Disabled tracepoints:	137.95 cycles

For reference, before this patch enabling HCALL_STATS resulted in a null
hcall of 201.44 cycles!
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Profiling of a page fault scalability microbenchmark shows flush_hash_range
is not calling the batch hpte invalidate hcall (H_BULK_REMOVE).

It turns out we have a duplicate firmware feature for hcall-bulk and the
current setup code stops after finding the first match. This meant we never
batch and always do individual invalidates.

The patch below removes the duplicate and shifts FW_FEATURE_CMO to close
the gap. With the patch applied the single threaded page fault rate improves
from 217169 to 238755 per second on a POWER5 test box, a 10% improvement.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

[akpm@linux-foundation.org: fix KVM]
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Acked-by: NMike Frysinger <vapier@gentoo.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Sometimes this is used to hold a simple offset, and sometimes
it is used to hold a pointer.  This patch changes it to a union containing
void * and dma_addr_t.  get/set accessors are also provided, because it was
getting a bit ugly to get to the actual data.
Signed-off-by: NBecky Bruce <beckyb@kernel.crashing.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Use the accessors rather than frobbing bits directly (the new versions
are const).
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NMike Travis <travis@sgi.com>

Make all seq_operations structs const, to help mitigate against
revectoring user-triggerable function pointers.

This is derived from the grsecurity patch, although generated from scratch
because it's simpler than extracting the changes from there.
Signed-off-by: NJames Morris <jmorris@namei.org>
Acked-by: NSerge Hallyn <serue@us.ibm.com>
Acked-by: NCasey Schaufler <casey@schaufler-ca.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Currently there is a bug where if you use oprofile on a pSeries
machine, then use perf_counters, then use oprofile again, oprofile
will not work correctly; it will lose the PMU configuration the next
time the hypervisor does a partition context switch, and thereafter
won't count anything.

Maynard Johnson identified the sequence causing the problem:
- oprofile setup calls ppc_enable_pmcs(), which calls
  pseries_lpar_enable_pmcs, which tells the hypervisor that we want
  to use the PMU, and sets the "PMU in use" flag in the lppaca.
  This flag tells the hypervisor whether it needs to save and restore
  the PMU config.
- The perf_counter code sets and clears the "PMU in use" flag directly
  as it context-switches the PMU between tasks, and leaves it clear
  when it finishes.
- oprofile setup, called for a new oprofile run, calls ppc_enable_pmcs,
  which does nothing because it has already been called.  In particular
  it doesn't set the "PMU in use" flag.

This fixes the problem by arranging for ppc_enable_pmcs to always set
the "PMU in use" flag.  It makes the perf_counter code call
ppc_enable_pmcs also rather than calling the lower-level function
directly, and removes the setting of the "PMU in use" flag from
pseries_lpar_enable_pmcs, since that is now done in its caller.

This also removes the declaration of pasemi_enable_pmcs because it
isn't defined anywhere.
Reported-by: NMaynard Johnson <mpjohn@us.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>
Cc: <stable@kernel.org)
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

By default, the EEH framework on powerpc does what's known as a "hot
reset" during recovery of a PCI Express device.  We've found a case
where the device needs a "fundamental reset" to recover properly.  The
current PCI error recovery and EEH frameworks do not support this
distinction.

The attached patch makes changes to EEH to utilize the new bit field.
Signed-off-by: NMike Mason <mmlnx@us.ibm.com>
Signed-off-by: NRichard Lary <rlary@us.ibm.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

The SLB can change sizes across a live migration, which was not
being handled, resulting in possible machine crashes during
migration if migrating to a machine which has a smaller max SLB
size than the source machine. Fix this by first reducing the
SLB size to the minimum possible value, which is 32, prior to
migration. Then during the device tree update which occurs after
migration, we make the call to ensure the SLB gets updated. Also
add the slb_size to the lparcfg output so that the migration
tools can check to make sure the kernel has this capability
before allowing migration in scenarios where the SLB size will change.

BenH: Fixed #include <asm/mmu-hash64.h> -> <asm/mmu.h> to avoid
      breaking ppc32 build
Signed-off-by: NBrian King <brking@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The two versions are doing almost exactly the same thing.  No need to
maintain them as separate files.  This patch also has the side effect
of making the PCI device tree scanning code available to 32 bit powerpc
machines, but no board ports actually make use of this feature at this
point.
Signed-off-by: NGrant Likely <grant.likely@secretlab.ca>
Acked-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Those definitions are currently declared extern in the .c file where
they are used, move them to a header file instead.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

pr_debug() can now result in code being generated even when DEBUG
is not defined. That's not really desirable in some places.

With CONFIG_DYNAMIC_DEBUG=y:

size before:
   text    data     bss     dec     hex filename
   7720    5488     296   13504    34c0 platforms/pseries/xics.o

size after:
   text    data     bss     dec     hex filename
   7535	   5456	    296	  13287	   33e7	platforms/pseries/xics.o
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

pr_debug() can now result in code being generated even when DEBUG
is not defined. That's not really desirable in some places.

In particular, pSeries_lpar_hpte_insert() goes from 185 instructions
to 77 instructions as a result of this patch. Luckily that code
isn't called very often ...

With CONFIG_DYNAMIC_DEBUG=y:

size before:
   text    data     bss     dec     hex filename
   7284    1552     296    9132    23ac platforms/pseries/lpar.o

size after:
   text    data     bss     dec     hex filename
   5806    1096     296    7198    1c1e platforms/pseries/lpar.o
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Several platforms use their own copy of what is essentially the same code,
using RTAS to synchronize the timebases when bringing up new CPUs. This
moves it all into a single common implementation and additionally
turns the spinlock into a raw spinlock since the former can rely on
the timebase not being frozen when spinlock debugging is enabled, and finally
masks interrupts while the timebase is disabled.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Based on PCI Express AER specs, a root port might receive multiple
TLP errors while it could only save a correctable error source id
and an uncorrectable error source id at the same time. In addition,
some root port hardware might be unable to provide a correct source
id, i.e., the source id, or the bus id part of the source id provided
by root port might be equal to 0.

The patchset implements the support in kernel by searching the device
tree under the root port.

Patch 1 changes parameter cb of function pci_walk_bus to return a value.
When cb return non-zero, pci_walk_bus stops more searching on the
device tree.
Reviewed-by: NAndrew Patterson <andrew.patterson@hp.com>
Signed-off-by: NZhang Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

resource_size_t is 64 bits on pseries

Gets rid of these warnings:

arch/powerpc/platforms/pseries/iommu.c: In function 'pci_dma_bus_setup_pSeries':
arch/powerpc/platforms/pseries/iommu.c:391: warning: format '%lx' expects type 'long unsigned int', but argument 2 has type 'resource_size_t'
arch/powerpc/platforms/pseries/iommu.c:417: warning: format '%lx' expects type 'long unsigned int', but argument 2 has type 'resource_size_t'
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

RTAS event scan has to run across all cpus. Right now we use a kernel
thread and set_cpus_allowed but in doing so we wake up the previous cpu
unnecessarily.

Some ftrace output shows this:

previous cpu (2):
[002]  7.022331: sched_switch: task swapper:0 [140] ==> rtasd:194 [120]
[002]  7.022338: sched_switch: task rtasd:194 [120] ==> migration/2:9 [0]
[002]  7.022344: sched_switch: task migration/2:9 [0] ==> swapper:0 [140]

next cpu (3):
[003]  7.022345: sched_switch: task swapper:0 [140] ==> rtasd:194 [120]
[003]  7.022371: sched_switch: task rtasd:194 [120] ==> swapper:0 [140]

We can use schedule_delayed_work_on and avoid the unnecessary wakeup.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>