Before f7b861b7 ("arm: Use generic idle loop") ARM would kill the
CPU within the rcu idle section.  Now that the rcu_idle_enter()/exit()
pair have been pushed lower down in the idle loop this is no longer true
and so using RCU_NONIDLE here is no longer necessary and also harmful
because RCU is not actually idle at this point.

Cc: Russell King <linux@arm.linux.org.uk>
Acked-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: NStephen Boyd <sboyd@codeaurora.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Flush the L1 cache for the CPU which is going down in cpu_die() so
that we don't end up with all platforms doing this.  This ensures
that any cache lines we own are pushed out before the cache becomes
inaccessible.

We may end up subsequently creating some dirty cache lines - for
example, with the complete() call, but this update must become
visible to other CPUs before __cpu_die() can proceed.  Subsequent
accesses from the platforms cpu_die() function should _not_ matter.

Also place a mb() after the complete() call to ensure that this is
visible to other CPUs.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Use the generic idle loop and replace enable/disable_hlt with the
respective core functions.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: NCc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Magnus Damm <magnus.damm@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Tested-by: Kevin Hilman <khilman@linaro.org> # OMAP
Link: http://lkml.kernel.org/r/20130321215233.826238797@linutronix.de

Commit 70264367 ("ARM: 7653/2: do not scale loops_per_jiffy when
using a constant delay clock") fixed a problem with our timer-based
delay loop, where loops_per_jiffy is scaled by cpufreq yet used directly
by the timer delay ops.

This patch fixes the problem in a more elegant way by keeping a private
ticks_per_jiffy field in the delay ops, independent of loops_per_jiffy
and therefore not subject to scaling. The loop-based delay continues to
use loops_per_jiffy directly, as it should.
Acked-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

With recent arm broadcast time clean-up from Mark Rutland, the dummy
broadcast device is always registered with timer subsystem. And since
the rating of the dummy clock event is very high, it may be preferred
over a real clock event.

This is a change in behavior from past and not an intended one. So
reduce the rating of the dummy clock-event so that real clock-event
device is selected when available.
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NMark Rutland <mark.rutland@arm.com>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The ARM ARM requires branch predictor maintenance if, for a given ASID,
the instructions at a specific virtual address appear to change.

From the kernel's point of view, that means:

	- Changing the kernel's view of memory (e.g. switching to the
	  identity map)
	- ASID rollover (since ASIDs will be re-allocated to new tasks)

This patch adds explicit branch predictor maintenance when either of the
two conditions above are met.
Reviewed-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When udelay() is implemented using an architected timer, it is wrong
to scale loops_per_jiffy when changing the CPU clock frequency since
the timer clock remains constant.

The lpj should probably become an implementation detail relevant to
the CPU loop based delay routine only and more confined to it. In the
mean time this is the minimal fix needed to have expected delays with
the timer based implementation when cpufreq is also in use.
Reported-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NNicolas Pitre <nico@linaro.org>
Tested-by: NViresh Kumar <viresh.kumar@linaro.org>
Acked-by: NLiviu Dudau <Liviu.Dudau@arm.com>
Cc: stable@vger.kernel.org
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The assignment of clock_event_device::broadcast can be done by timer
core as of 12ad1000: "clockevents: Add generic timer broadcast
function", and the arm code moved over to this as of 3d06770e: "arm:
Add generic timer broadcast support", but left a dangling #define when
!CONFIG_GENERIC_TIMER_BROADCAST.

This patch removes the now unused #define.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Implement timer_broadcast for the arm architecture, allowing for the use
of clock_event_device_drivers decoupled from the timer tick broadcast
mechanism.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Tested-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Reviewed-by: NStephen Boyd <sboyd@codeaurora.org>

Currently, the ARM backend must maintain a redundant list of timers for
the purpose of centralising timer broadcast functionality. This prevents
sharing timer drivers across architectures.

This patch moves the pain of dealing with timer broadcasts to the core
clockevents tick broadcast code, which already maintains its own list
of timers.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Tested-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Reviewed-by: NStephen Boyd <sboyd@codeaurora.org>

Remove some silly wrapper functions which aren't really required:
	platform_smp_prepare_cpus
	platform_secondary_init
	platform_cpu_die

This simplifies the code.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

In preparation of moving gic code to drivers/irqchip, remove the direct
platform dependencies on gic_raise_softirq. Move the setup of
smp_cross_call into the gic code and use arch_send_wakeup_ipi_mask
function to trigger wake-up IPIs.
Signed-off-by: NRob Herring <rob.herring@calxeda.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Kukjin Kim <kgene.kim@samsung.com>
Cc: Sascha Hauer <kernel@pengutronix.de>
Cc: David Brown <davidb@codeaurora.org>
Cc: Daniel Walker <dwalker@fifo99.com>
Cc: Bryan Huntsman <bryanh@codeaurora.org>
Acked-by: NTony Lindgren <tony@atomide.com>
Acked-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Magnus Damm <magnus.damm@gmail.com>
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Cc: Shiraz Hashim <shiraz.hashim@st.com>
Acked-by: NStephen Warren <swarren@nvidia.com>
Cc: Srinidhi Kasagar <srinidhi.kasagar@stericsson.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Acked-by: NOlof Johansson <olof@lixom.net>

This is what is done for the regular interrupts in kernel/irqs/proc.c
already, before calling arch_show_interrupts().  Not doing so for the
IPIs causes the column headers not to match with the content whenever
some CPUs are offline.
Signed-off-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Use the previously unused TPIDRPRW register to store percpu offsets.
TPIDRPRW is only accessible in PL1, so it can only be used in the kernel.

This replaces 2 loads with a mrc instruction for each percpu variable
access. With hackbench, the performance improvement is 1.4% on Cortex-A9
(highbank). Taking an average of 30 runs of "hackbench -l 1000" yields:

Before: 6.2191
After: 6.1348

Will Deacon reported similar delta on v6 with 11MPCore.

The asm "memory clobber" are needed here to ensure the percpu offset
gets reloaded. Testing by Will found that this would not happen in
__schedule() which is a bit of a special case as preemption is disabled
but the execution can move cores.
Signed-off-by: NRob Herring <rob.herring@calxeda.com>
Acked-by: NWill Deacon <will.deacon@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The advent of big.LITTLE ARM platforms requires the kernel to be able
to identify the MIDRs of all online CPUs upon request. MIDRs are stashed
at boot time so that kernel subsystems can detect the MIDR of online CPUs
by simply retrieving per-CPU data updated by all booted CPUs.
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>

Add function arch_send_wakeup_ipi_mask(), so that platform code can
use it as an easy way to wake up cores that are in WFI.
Signed-off-by: NShawn Guo <shawn.guo@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When booting a secondary CPU, the primary CPU hands two sets of page
tables via the secondary_data struct:

	(1) swapper_pg_dir: a normal, cacheable, shared (if SMP) mapping
	    of the kernel image (i.e. the tables used by init_mm).

	(2) idmap_pgd: an uncached mapping of the .idmap.text ELF
	    section.

The idmap is generally used when enabling and disabling the MMU, which
includes early CPU boot. In this case, the secondary CPU switches to
swapper as soon as it enters C code:

	struct mm_struct *mm = &init_mm;
	unsigned int cpu = smp_processor_id();

	/*
	 * All kernel threads share the same mm context; grab a
	 * reference and switch to it.
	 */
	atomic_inc(&mm->mm_count);
	current->active_mm = mm;
	cpumask_set_cpu(cpu, mm_cpumask(mm));
	cpu_switch_mm(mm->pgd, mm);

This causes a problem on ARMv7, where the identity mapping is treated as
strongly-ordered leading to architecturally UNPREDICTABLE behaviour of
exclusive accesses, such as those used by atomic_inc.

This patch re-orders the secondary_start_kernel function so that we
switch to swapper before performing any exclusive accesses.

Cc: <stable@vger.kernel.org>
Cc: David McKay <david.mckay@st.com>
Reported-by: NGilles Chanteperdrix <gilles.chanteperdrix@xenomai.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When a CPU is hotplugged out caches that reside in its power domain
lose their contents and so must be cleaned to the next memory level.

Currently, __cpu_disable calls flush_cache_all() that for new generation
processor like A15/A7 ends up cleaning and invalidating all cache levels
up to Level of Coherency, which includes the unified L2.

This ends up being a waste of cycles since the L2 cache contents are not
lost on power down.

This patch updates __cpu_disable to use the new LoUIS API cache operations.
Acked-by: NNicolas Pitre <nico@linaro.org>
Reviewed-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Tested-by: NShawn Guo <shawn.guo@linaro.org>

Remove the offset from ipi_msg_type and assume that SGI0 is the
wakeup interrupt now that all WFI hotplug users call
gic_raise_softirq() with 0 instead of 1. This allows us to
track how many wakeup interrupts are sent and also removes the
unknown IPI printk message for WFI hotplug based systems.
Reviewed-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NStephen Boyd <sboyd@codeaurora.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

In order to easily detect pathological cases, print some diagnostics
when the kernel boots.

This also provides helpers to detect that HYP mode is actually available,
which can be used by other subsystems to enable HYP specific features.
Signed-off-by: NDave Martin <dave.martin@linaro.org>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

Almost each SMP platform defines pen_release to manage booting secondary
CPUs. This of course clashes with the single zImage effort.

Add the pen_release definition to the ARM SMP code, and remove all others.
This should only be used by platforms which lack any kind of CPU power
management...
Reported-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>

Now that all SMP platforms have been converted to use struct
smp_operations, remove the "weak" attribute from the hooks
in smp.c, and make the functions static wherever possible.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>

This adds a 'struct smp_operations' to abstract the CPU initialization
and hot plugging functions on SMP systems, which otherwise conflict
in a multiplatform kernel. This also helps shmobile and potentially
others that have more than one method to do these.

To allow the kernel to continue building, the platform hooks are
defined as weak symbols which are overrided by the platform code.
Once all platforms are converted, the "weak" attribute will be
removed and the function made static.

Unlike the original version from Marc, this new version from Arnd
does not use a generalized abstraction for per-soc data structures
but only tries to solve the problem for the SMP operations. This
way, we can collapse the previous four data structures into a
single struct, which is less systematic but also easier to follow
as a causal reader.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Acked-by: NNicolas Pitre <nico@fluxnic.net>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>

If CONFIG_SMP, cpufreq skips loops_per_jiffy update, because different
arch has different per-cpu loops_per_jiffy definition.
Signed-off-by: NRichard Zhao <richard.zhao@linaro.org>
Acked-by: NRussell King <rmk+kernel@arm.linux.org.uk>
Acked-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: NShawn Guo <shawn.guo@linaro.org>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

On reboot or poweroff (machine_shutdown()) a call to smp_send_stop() is
made (to stop the others CPU's) when CONFIG_SMP=y.

arch/arm/kernel/process.c:

void machine_shutdown(void)
{
 #ifdef CONFIG_SMP
       smp_send_stop();
 #endif
}

smp_send_stop() calls the function pointer smp_cross_call(), which is set
on the smp_init_cpus() function for OMAP processors.

arch/arm/mach-omap2/omap-smp.c:

void __init smp_init_cpus(void)
{
...
	set_smp_cross_call(gic_raise_softirq);
...
}

But the ARM setup_arch() function only calls smp_init_cpus()
if CONFIG_SMP=y && is_smp().

arm/kernel/setup.c:

void __init setup_arch(char **cmdline_p)
{
...
 #ifdef CONFIG_SMP
	if (is_smp())
		smp_init_cpus();
 #endif
...
}

Newer OMAP CPU's are SMP machines so omap2plus_defconfig sets
CONFIG_SMP=y. Unfortunately on an OMAP UP machine is_smp()
returns false and smp_init_cpus() is never called and the
smp_cross_call() function remains NULL.

If the machine is rebooted or powered off, smp_send_stop() will
be called (since CONFIG_SMP=y) leading to the following error:

[   42.815551] Restarting system.
[   42.819030] Unable to handle kernel NULL pointer dereference at virtual address 00000000
[   42.827667] pgd = d7a74000
[   42.830566] [00000000] *pgd=96ce7831, *pte=00000000, *ppte=00000000
[   42.837249] Internal error: Oops: 80000007 [#1] SMP ARM
[   42.842773] Modules linked in:
[   42.846008] CPU: 0    Not tainted  (3.5.0-rc3-next-20120622-00002-g62e87ba-dirty #44)
[   42.854278] PC is at 0x0
[   42.856994] LR is at smp_send_stop+0x4c/0xe4
[   42.861511] pc : [<00000000>]    lr : [<c00183a4>]    psr: 60000013
[   42.861511] sp : d6c85e70  ip : 00000000  fp : 00000000
[   42.873626] r10: 00000000  r9 : d6c84000  r8 : 00000002
[   42.879150] r7 : c07235a0  r6 : c06dd2d0  r5 : 000f4241  r4 : d6c85e74
[   42.886047] r3 : 00000000  r2 : 00000000  r1 : 00000006  r0 : d6c85e74
[   42.892944] Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
[   42.900482] Control: 10c5387d  Table: 97a74019  DAC: 00000015
[   42.906555] Process reboot (pid: 1166, stack limit = 0xd6c842f8)
[   42.912902] Stack: (0xd6c85e70 to 0xd6c86000)
[   42.917510] 5e60:                                     c07235a0 00000000 00000000 d6c84000
[   42.926177] 5e80: 01234567 c00143d0 4321fedc c00511bc d6c85ebc 00000168 00000460 00000000
[   42.934814] 5ea0: c1017950 a0000013 c1017900 d8014390 d7ec3858 c0498e48 c1017950 00000000
[   42.943481] 5ec0: d6ddde10 d6c85f78 00000003 00000000 d6ddde10 d6c84000 00000000 00000000
[   42.952117] 5ee0: 00000002 00000000 00000000 c0088c88 00000002 00000000 00000000 c00f4b90
[   42.960784] 5f00: 00000000 d6c85ebc d8014390 d7e311c8 60000013 00000103 00000002 d6c84000
[   42.969421] 5f20: c00f3274 d6e00a00 00000001 60000013 d6c84000 00000000 00000000 c00895d4
[   42.978057] 5f40: 00000002 d8007c80 d781f000 c00f6150 d8010cc0 c00f3274 d781f000 d6c84000
[   42.986694] 5f60: c0013020 d6e00a00 00000001 20000010 0001257c ef000000 00000000 c00895d4
[   42.995361] 5f80: 00000002 00000001 00000003 00000000 00000001 00000003 00000000 00000058
[   43.003997] 5fa0: c00130c8 c0012f00 00000001 00000003 fee1dead 28121969 01234567 00000002
[   43.012634] 5fc0: 00000001 00000003 00000000 00000058 00012584 0001257c 00000001 00000000
[   43.021270] 5fe0: 000124bc bec5cc6c 00008f9c 4a2f7c40 20000010 fee1dead 00000000 00000000
[   43.029968] [<c00183a4>] (smp_send_stop+0x4c/0xe4) from [<c00143d0>] (machine_restart+0xc/0x4c)
[   43.039154] [<c00143d0>] (machine_restart+0xc/0x4c) from [<c00511bc>] (sys_reboot+0x144/0x1f0)
[   43.048278] [<c00511bc>] (sys_reboot+0x144/0x1f0) from [<c0012f00>] (ret_fast_syscall+0x0/0x3c)
[   43.057464] Code: bad PC value
[   43.060760] ---[ end trace c3988d1dd0b8f0fb ]---

Add a check so smp_cross_call() is only called when there is more than one CPU on-line.

Cc: <stable@vger.kernel.org>
Signed-off-by: Javier Martinez Canillas <javier at dowhile0.org>
Acked-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

While running hotplug tests I ran into this RCU splat

===============================
[ INFO: suspicious RCU usage. ]
3.4.0 #3275 Tainted: G        W
-------------------------------
include/linux/rcupdate.h:729 rcu_read_lock() used illegally while idle!

other info that might help us debug this:

RCU used illegally from idle CPU!
rcu_scheduler_active = 1, debug_locks = 0
RCU used illegally from extended quiescent state!
4 locks held by swapper/2/0:
 #0:  ((cpu_died).wait.lock){......}, at: [<c00ab128>] complete+0x1c/0x5c
 #1:  (&p->pi_lock){-.-.-.}, at: [<c00b275c>] try_to_wake_up+0x2c/0x388
 #2:  (&rq->lock){-.-.-.}, at: [<c00b2860>] try_to_wake_up+0x130/0x388
 #3:  (rcu_read_lock){.+.+..}, at: [<c00abe5c>] cpuacct_charge+0x28/0x1f4

stack backtrace:
[<c001521c>] (unwind_backtrace+0x0/0x12c) from [<c00abec8>] (cpuacct_charge+0x94/0x1f4)
[<c00abec8>] (cpuacct_charge+0x94/0x1f4) from [<c00b395c>] (update_curr+0x24c/0x2c8)
[<c00b395c>] (update_curr+0x24c/0x2c8) from [<c00b59c4>] (enqueue_task_fair+0x50/0x194)
[<c00b59c4>] (enqueue_task_fair+0x50/0x194) from [<c00afea4>] (enqueue_task+0x30/0x34)
[<c00afea4>] (enqueue_task+0x30/0x34) from [<c00b0908>] (ttwu_activate+0x14/0x38)
[<c00b0908>] (ttwu_activate+0x14/0x38) from [<c00b28a8>] (try_to_wake_up+0x178/0x388)
[<c00b28a8>] (try_to_wake_up+0x178/0x388) from [<c00a82a0>] (__wake_up_common+0x34/0x78)
[<c00a82a0>] (__wake_up_common+0x34/0x78) from [<c00ab154>] (complete+0x48/0x5c)
[<c00ab154>] (complete+0x48/0x5c) from [<c07db7cc>] (cpu_die+0x2c/0x58)
[<c07db7cc>] (cpu_die+0x2c/0x58) from [<c000f954>] (cpu_idle+0x64/0xfc)
[<c000f954>] (cpu_idle+0x64/0xfc) from [<80208160>] (0x80208160)

When a cpu is marked offline during its idle thread it calls
cpu_die() during an RCU idle period. cpu_die() calls complete()
to notify the killing process that the cpu has died. complete()
calls into the scheduler code and eventually grabs an RCU read
lock in cpuacct_charge().

Mark complete() as RCU_NONIDLE so that RCU pays attention to this
CPU for the duration of the complete() function even though it's
in idle.
Suggested-by: N"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: NStephen Boyd <sboyd@codeaurora.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Checking for process->mm is not enough because process' main thread may
exit or detach its mm via use_mm(), but other threads may still have a
valid mm.

To fix this we would need to use find_lock_task_mm(), which would walk up
all threads and returns an appropriate task (with task lock held).

clear_tasks_mm_cpumask() has this issue fixed, so let's use it.
Suggested-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NAnton Vorontsov <anton.vorontsov@linaro.org>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Commit 4e8ee7de (ARM: SMP: use
idmap_pgd for mapping MMU enable during secondary booting)
switched secondary boot to use idmap_pgd, which is initialized
during early_initcall, instead of a page table initialized during
__cpu_up.  This causes idmap_pgd to contain the static mappings
but be missing all dynamic mappings.

If a console is registered that creates a dynamic mapping, the
printk in secondary_start_kernel will trigger a data abort on
the missing mapping before the exception handlers have been
initialized, leading to a hang.  Initial boot is not affected
because no consoles have been registered, and resume is usually
not affected because the offending console is suspended.
Onlining a cpu with hotplug triggers the problem.

A workaround is to the printk in secondary_start_kernel until
after the page tables have been switched back to init_mm.

Cc: <stable@vger.kernel.org>
Signed-off-by: NColin Cross <ccross@android.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When performing a kexec on an SMP system, the secondary cores are stopped
by calling machine_shutdown(), which in turn issues IPIs to offline the
other CPUs. Unfortunately, this isn't enough to reboot the cores into
a new kernel (since they are just executing a cpu_relax loop somewhere
in memory) so we make use of platform_cpu_kill, part of the CPU hotplug
implementation, to place the cores somewhere safe. This function expects
to be called on the killing CPU for each core that it takes out.

This patch moves the platform_cpu_kill callback out of the IPI handler
and into smp_send_stop, therefore ensuring that it executes on the
killing CPU rather than on the victim, matching what the hotplug code
requires.

Cc: stable@vger.kernel.org
Reported-by: NRussell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When running an SMP_ON_UP enabled kernel on UP, or with nosmp
passed to the kernel, we want to be able to detect that a local
timer is not going to be used (local timers are only used on
SMP platforms), so we could register it as a global timer instead.

Return -ENXIO when the above case is detected.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Russell King <linux@arm.linux.org.uk>
Tested-by: NFrank Rowand <frank.rowand@am.sony.com>
Link: http://lkml.kernel.org/r/20120420124557.448826362@linutronix.de

Preparatory patch to make the idle thread allocation for secondary
cpus generic.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Richard Kuo <rkuo@codeaurora.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Howells <dhowells@redhat.com>
Cc: James E.J. Bottomley <jejb@parisc-linux.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: x86@kernel.org
Link: http://lkml.kernel.org/r/20120420124556.964170564@linutronix.de

This has been obsolescent for a while; time for the final push.

In adjacent context, replaced old cpus_* with cpumask_*.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Acked-by: David S. Miller <davem@davemloft.net> (arch/sparc)
Acked-by: Chris Metcalf <cmetcalf@tilera.com> (arch/tile)
Cc: user-mode-linux-devel@lists.sourceforge.net
Cc: Russell King <linux@arm.linux.org.uk>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Richard Kuo <rkuo@codeaurora.org>
Cc: linux-hexagon@vger.kernel.org
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Helge Deller <deller@gmx.de>
Cc: sparclinux@vger.kernel.org

Rather than open-coding the jiffy-based wait, and polling for the
secondary CPU to come online, use a completion instead.  This
removes the need to poll, instead we will be notified when the
secondary CPU has initialized.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Remove all traces of the compile-time local timer interface,
and make the runtime selection mandatory.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

In order to switch to a runtime selectable local timer,
add a registration interface that timer drivers can use to
register to the core.

local_timer_setup() and local_timer_stop() are made weak symbols
in order not to break existing setups.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

Stepan found:

CPU0		CPUn

_cpu_up()
  __cpu_up()

		boostrap()
		  notify_cpu_starting()
		  set_cpu_online()
		  while (!cpu_active())
		    cpu_relax()

<PREEMPT-out>

smp_call_function(.wait=1)
  /* we find cpu_online() is true */
  arch_send_call_function_ipi_mask()

  /* wait-forever-more */

<PREEMPT-in>
		  local_irq_enable()

  cpu_notify(CPU_ONLINE)
    sched_cpu_active()
      set_cpu_active()

Now the purpose of cpu_active is mostly with bringing down a cpu, where
we mark it !active to avoid the load-balancer from moving tasks to it
while we tear down the cpu. This is required because we only update the
sched_domain tree after we brought the cpu-down. And this is needed so
that some tasks can still run while we bring it down, we just don't want
new tasks to appear.

On cpu-up however the sched_domain tree doesn't yet include the new cpu,
so its invisible to the load-balancer, regardless of the active state.
So instead of setting the active state after we boot the new cpu (and
consequently having to wait for it before enabling interrupts) set the
cpu active before we set it online and avoid the whole mess.
Reported-by: NStepan Moskovchenko <stepanm@codeaurora.org>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1323965362.18942.71.camel@twinsSigned-off-by: NIngo Molnar <mingo@elte.hu>

It turns out that the logical CPU mapping is useful even when !CONFIG_SMP
for manipulation of devices like interrupt and power controllers when
running a UP kernel on a CPU other than 0. This can happen when kexecing
a UP image from an SMP kernel.

In the future, multi-cluster systems running AMP configurations will
require something similar for mapping cluster IDs, so it makes sense to
decouple this logic in preparation for this support.
Acked-by: NYang Bai <hamo.by@gmail.com>
Acked-by: NMarc Zyngier <marc.zyngier@arm.com>
Reported-by: NJoerg Roedel <joerg.roedel@amd.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

We can stall RCU processing on SMP platforms if a CPU sits in its idle
loop for a long time.  This happens because we don't call irq_enter()
and irq_exit() around generic_smp_call_function_interrupt() and
friends.  Add the necessary calls, and remove the one from within
ipi_timer(), so that they're all in a common place.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Sending IPI_CPU_STOP to a CPU causes it to execute a busy cpu_relax
loop forever. This makes it impossible to kexec successfully on an SMP
system since the secondary CPUs do not reset.

This patch adds a callback to platform_cpu_kill, defined when
CONFIG_HOTPLUG_CPU=y, from the ipi_cpu_stop handling code. This function
currently just returns 1 on all platforms that define it but allows them
to do something more sophisticated in the future.
Signed-off-by: NWill Deacon <will.deacon@arm.com>