get_user may fail to load from the provided __user address due to an
unhandled fault generated by the access.

In the case of the undefined instruction trap, this results in failure
to load the faulting instruction, in which case we should send SIGILL to
the task rather than continue with potentially uninitialised data.
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Cc: stable@vger.kernel.org
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Breakpoint validation currently fails for single-byte watchpoints on
addresses ending in 11b. There is no reason to forbid such a watchpoint,
so extend the validation code to allow it.

Cc: Ulrich Weigand <Ulrich.Weigand@de.ibm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

From ARM debug architecture v7.1 onwards, a watchpoint exception causes
the DFAR to be updated with the faulting data address. However, DFSR.WnR
takes an UNKNOWN value and therefore cannot be used in general to
determine the access type that triggered the watchpoint.

This patch forbids watchpoints without an overflow handler from
specifying a specific access type (load/store). Those with overflow
handlers must be able to handle false positives potentially triggered by
a watchpoint of a different access type on the same address. For
SIGTRAP-based handlers (i.e. ptrace), this should have no impact.

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

This patch moves the CPU-specific IRQ registration and parsing code into
the CPU PMU backend. This is required because a PMU may have more than
one interrupt, which in turn can be either PPI (per-cpu) or SPI
(requiring strict affinity setting at the interrupt distributor).
Signed-off-by: NSudeep KarkadaNagesha <Sudeep.KarkadaNagesha@arm.com>
[will: cosmetic edits and reworked interrupt dispatching]
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This patch moves the CPU-specific PMU handling code out of perf_event.c
and into perf_event_cpu.c.
Signed-off-by: NWill Deacon <will.deacon@arm.com>

The CPU PMU code is tightly coupled with generic ARM PMU handling code.
This makes it cumbersome when trying to add support for other ARM PMUs
(e.g. interconnect, L2 cache controller, bus) as the generic parts of
the code are not readily reusable.

This patch cleans up perf_event.c so that reusable code is exposed via
header files to other potential PMU drivers. The CPU code is
consistently named to identify it as such and also to prepare for moving
it into a separate file.
Signed-off-by: NWill Deacon <will.deacon@arm.com>

The CPU PMU is probed using the current cpuid information as part of the
early_initcall initialising the architecture perf backend. For
architectures without NMI (such as ARM), this does not need to be
performed early and can be deferred to the driver probe callback. This
also allows us to probe the devicetree in preference to parsing the
current cpuid, which may be invalid on a big.LITTLE multi-cluster
system.

This patch defers the PMU probing and uses the devicetree information
when available.
Signed-off-by: NWill Deacon <will.deacon@arm.com>

There's a rather strange compiler barrier in the PMU disabling code
which was presumably placed there by aliens. There's no valid reason for
the barrier and one can only suspect that it's up to no good.

This patch removes it before it has a chance to spread.
Signed-off-by: NWill Deacon <will.deacon@arm.com>

The PMU reservation mechanism was originally intended to allow OProfile
and perf-events to co-ordinate over access to the CPU PMU. Since then,
OProfile for ARM has moved to using perf as its backend, so the
reservation code is no longer used.

This patch removes the reservation code for the CPU PMU on ARM.
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This patch adds separate devicetree bindings for 11MPcore and
Cortex-{A5,A7,A15} PMUs in preparation for improved devicetree parsing
in the ARM perf-event CPU PMU driver.

Cc: Grant Likely <grant.likely@secretlab.ca>
Acked-by: NRob Herring <rob.herring@calxeda.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Add runtime PM support to the ARM PMU driver so that devices such as OMAP
supporting dynamic PM can use the platform->runtime_* hooks to initialise
hardware at runtime. Without having these runtime PM hooks in place any
configuration of the PMU hardware would be lost when low power states are
entered and hence would prevent PMU from working.

This change also replaces the PMU platform functions enable_irq and disable_irq
added by Ming Lei with runtime_resume and runtime_suspend funtions. Ming had
added the enable_irq and disable_irq functions as a method to configure the
cross trigger interface on OMAP4 for routing the PMU interrupts. By adding
runtime PM support, we can move the code called by enable_irq and disable_irq
into the runtime PM callbacks runtime_resume and runtime_suspend.

Cc: Ming Lei <ming.lei@canonical.com>
Cc: Benoit Cousson <b-cousson@ti.com>
Cc: Paul Walmsley <paul@pwsan.com>
Cc: Kevin Hilman <khilman@ti.com>
Signed-off-by: NJon Hunter <jon-hunter@ti.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Many clocks that are used to provide sched_clock will reset during
suspend.  If read_sched_clock returns 0 after suspend, sched_clock will
appear to jump forward.  This patch resets cd.epoch_cyc to the current
value of read_sched_clock during resume, which causes sched_clock() just
after suspend to return the same value as sched_clock() just before
suspend.

In addition, during the window where epoch_ns has been updated before
suspend, but epoch_cyc has not been updated after suspend, it is unknown
whether the clock has reset or not, and sched_clock() could return a
bogus value.  Add a suspended flag, and return the pre-suspend epoch_ns
value during this period.

The new behavior is triggered by calling setup_sched_clock_needs_suspend
instead of setup_sched_clock.
Signed-off-by: NColin Cross <ccross@android.com>
Reviewed-by: NLinus Walleij <linus.walleij@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Get rid of this warning..
arch/arm/kernel/built-in.o(.text+0xac78): Section mismatch in reference
from the function init_cpu_topology() to the function
 .init.text:parse_dt_topology()
The function init_cpu_topology() references
the function __init parse_dt_topology().
This is often because init_cpu_topology lacks a __init
annotation or the annotation of parse_dt_topology is wrong.
Signed-off-by: NVenkatraman S <svenkatr@ti.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

While trying to get a v3.5 kernel booted on the cubox, I noticed that
VFP does not work correctly with VFP bounce handling.  This is because
of the confusion over 16-bit vs 32-bit instructions, and where PC is
supposed to point to.

The rule is that FP handlers are entered with regs->ARM_pc pointing at
the _next_ instruction to be executed.  However, if the exception is
not handled, regs->ARM_pc points at the faulting instruction.

This is easy for ARM mode, because we know that the next instruction and
previous instructions are separated by four bytes.  This is not true of
Thumb2 though.

Since all FP instructions are 32-bit in Thumb2, it makes things easy.
We just need to select the appropriate adjustment.  Do this by moving
the adjustment out of do_undefinstr() into the assembly code, as only
the assembly code knows whether it's dealing with a 32-bit or 16-bit
instruction.

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

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>

Commit 722b3c74 modified x86 ftrace to
avoid tracing all functions called from irqs when function graph was
used with a filter.  Port the same fix to ARM.
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NColin Cross <ccross@android.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The CPU will endlessly spin at the end of machine_halt and
machine_restart calls.  However, this will lead to a soft lockup
warning after about 20 seconds, if CONFIG_LOCKUP_DETECTOR is enabled,
as system timer is still alive.

Disable interrupt before going to spin endlessly, so that the lockup
warning will never be seen.

Cc: <stable@vger.kernel.org>
Reported-by: NMarek Vasut <marex@denx.de>
Signed-off-by: NShawn Guo <shawn.guo@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The memory regions which are passed to arm_add_memory() from
device tree blobs via early_init_dt_add_memory_arch() can
have sizes which are larger than will fit in a 32 bit integer,
so switch to using a phys_addr_t to hold them, to avoid
silently dropping the top 32 bits of the size. Similarly, use
phys_addr_t in early_mem() so that mem=size@start command line
options specifying more than 4GB behave sensibly.
Acked-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Prior to syscall invocation, __sys_trace only reloads r0-r3 from the
kernel stack, preventing the debugger from updating arguments 5-7 when
signalled via ptrace.

This patch updates the code to reload r0-r6, updating arguments 5 and 6
on the stack (argument 7 is only used by OABI indirect syscalls and
can remain in a register).
Reported-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

just let do_work_pending() return 1 on normal local restarts and
-1 on those that had been caused by ERESTART_RESTARTBLOCK (and 0
is still "all done, sod off to userland now").  And let the asm
glue flip scno to restart_syscall(2) one if it got negative from
us...

[will: resolved conflicts with audit fixes]
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This reverts commit 3b0c0622.

We no longer require the restart trampoline for syscall restarting.
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This reverts commit 433e2f30.

Conflicts:

	arch/arm/kernel/ptrace.c

Reintroduce the new syscall restart handling in preparation for further
patches from Al Viro.
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

With consolidation of the PCI i/o mappings, the i/o space is being
set to start at a PCI bus addr of 0x0 and fixed to 64K per bus. In
this case the core ARM PCI setup code can setup the i/o resource.

Currently, the resource is only setup if the platform did not setup
an i/o resource.
Signed-off-by: NRob Herring <rob.herring@calxeda.com>
Reviewed-by: NArnd Bergmann <arnd@arndb.de>

This adds a fixed virtual mapping for PCI i/o addresses. The mapping is
located at the last 2MB of vmalloc region (0xfee00000-0xff000000). 2MB
is used to align with PMD size, but IO_SPACE_LIMIT is 1MB. The space
is reserved after .map_io and can be mapped at any time later with
pci_ioremap_io. Platforms which need early i/o mapping (e.g. for vga
console) can call pci_map_io_early in their .map_io function.

This has changed completely from the 1st implementation which only
supported creating the static mapping at .map_io.
Signed-off-by: NRob Herring <rob.herring@calxeda.com>
Cc: Russell King <linux@arm.linux.org.uk>
Acked-by: NNicolas Pitre <nico@linaro.org>

Use cpu compatibility field and clock-frequency field of DT to
estimate the capacity of each core of the system and to update
the cpu_power field accordingly.
This patch enables to put more running tasks on big cores than
on LITTLE ones. But this patch doesn't ensure that long running
tasks will run on big cores and short ones on LITTLE cores.
Signed-off-by: NVincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: NNamhyung Kim <namhyung@kernel.org>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This factorization has also been proposed in another patch that has not been
merged yet:
http://lists.infradead.org/pipermail/linux-arm-kernel/2012-January/080873.html
So, this patch could be dropped depending of the state of the other one.
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: NVincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: NNamhyung Kim <namhyung@kernel.org>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Add infrastructure to be able to modify the cpu_power of each core
Signed-off-by: NVincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: NNamhyung Kim <namhyung@kernel.org>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The syscall_trace on ARM takes a `why' parameter to indicate whether or
not we are entering or exiting a system call. This can be confusing for
people looking at the code since (a) it conflicts with the why register
alias in the entry assembly code and (b) it is not immediately clear
what it represents.

This patch splits up the syscall_trace function into separate wrappers
for syscall entry and exit, allowing the low-level syscall handling
code to branch to the appropriate function.
Reported-by: NAl Viro <viro@zeniv.linux.org.uk>
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 auditing system calls on ARM, the audit code is called before
notifying the parent process in the case that the current task is being
ptraced. At this point, the parent (debugger) may choose to change the
system call being issued via the SET_SYSCALL ptrace request, causing
the wrong system call to be reported to the audit tools.

This patch moves the audit calls after the ptrace SIGTRAP handling code
in the syscall tracing implementation.
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>

ret_from_fork is setup for a freshly spawned child task via copy_thread,
called from copy_process. The latter function clears TIF_SYSCALL_TRACE
and also resets the child task's audit_context to NULL, meaning that
there is little point invoking the system call tracing routines.
Furthermore, getting hold of the syscall number is a complete pain and
it looks like the current code doesn't even bother.

This patch removes the syscall tracing checks from ret_from_fork.
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>

This patch allows a timer-based delay implementation to be selected by
switching the delay routines over to use get_cycles, which is
implemented in terms of read_current_timer. This further allows us to
skip the loop calibration and have a consistent delay function in the
face of core frequency scaling.

To avoid the pain of dealing with memory-mapped counters, this
implementation uses the co-processor interface to the architected timers
when they are available. The previous loop-based implementation is
kept around for CPUs without the architected timers and we retain both
the maximum delay (2ms) and the corresponding conversion factors for
determining the number of loops required for a given interval. Since the
indirection of the timer routines will only work when called from C,
the sa1100 sleep routines are modified to branch to the loop-based delay
functions directly.
Tested-by: NShinya Kuribayashi <shinya.kuribayashi.px@renesas.com>
Reviewed-by: NStephen Boyd <sboyd@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This patch implements read_current_timer using the architected timers
when they are selected via CONFIG_ARM_ARCH_TIMER. If they are detected
not to be usable at runtime, we return -ENXIO to the caller.

Furthermore, if read_current_timer is exported then we can implement
get_cycles in terms of it for use as both an entropy source and for
implementing __udelay and friends.
Tested-by: NShinya Kuribayashi <shinya.kuribayashi.px@renesas.com>
Reviewed-by: NStephen Boyd <sboyd@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This patch implements the word-at-a-time interface for ARM using the
same algorithm as x86. We use the fls macro from ARMv5 onwards, where
we have a clz instruction available which saves us a mov instruction
when targetting Thumb-2. For older CPUs, we use the magic 0x0ff0001
constant. Big-endian configurations make use of the implementation from
asm-generic.

With this implemented, we can replace our byte-at-a-time strnlen_user
and strncpy_from_user functions with the optimised generic versions.
Reviewed-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>

In order to provide PMU name strings compatible with the OProfile
user ABI, an enumeration of all PMUs is currently used by perf to
identify each PMU uniquely. Unfortunately, this does not scale well
in the presence of multiple PMUs and creates a single, global namespace
across all PMUs in the system.

This patch removes the enumeration and instead uses the name string
for the PMU to map onto the OProfile variant. perf_pmu_name is
implemented for CPU PMUs, which is all that OProfile cares about anyway.
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When a CPU is shutdown its architected timer comparators registers are
lost. Within CPU idle, before processors enter shutdown they enter
clock events broadcast mode through the

clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, cpuid);

function where the local timers are emulated by a global always-on timer.
On CPU resume, the per-CPU tick device normal mode is restored by exiting
broadcast mode through

clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, cpuid);

In order for this mechanism to function, architected timers should add to
their feature C3STOP, which means that they are not able to function when the
CPU is in off-mode.
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Let's map the initial RAM up to the end of the kernel .bss instead of
the strict kernel image area.  This simplifies the code as the kernel
image only needs to be handled specially in the XIP case.  That covers
the legacy ATAG location as well.
Signed-off-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Robustify ARM's die() handling with improvements from x86:

 - Fix for a deadlock (before panic in the case of panic_on_oops) if we
   oops under a spinlock which is also used from interrupt handler,
   since the old code was unconditionally enabling interrupts.

 - Usage of arch spinlock so lockdep etc doesn't get involved while
   we're trying to dump out oopses.

 - Deadlock prevention in the unlikely event that die() recurses.

The changes all touch the same few lines of code, so they're done
together in one patch.
Signed-off-by: NRabin Vincent <rabin.vincent@stericsson.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>