Starting up the C compiler can be a slow operation on some systems.
Though these calls don't individually take a lot of time, they add up.
Rearrange the ARM Makefile a bit to avoid extra calls to the compiler
when they can be easily avoided.

When running with the Chrome OS ARM cross compiler
"armv7a-cros-linux-gnueabi-", this shaved .55 seconds (from 5.31
seconds to 4.76 seconds) off an incremental build of the kernel:
  time make -j32 ARCH=arm CROSS_COMPILE=armv7a-cros-linux-gnueabi-

Thanks to Mike Frysinger for the clean trick to make this work.
Signed-off-by: NDoug Anderson <dianders@chromium.org>
Acked-by: NMike Frysinger <vapier@gentoo.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The %.dtb dependency is specified to depend on the PHONY "scripts".
That means that it'll build every time even if the underlying dtb file
hasn't been touched.  Use an order-only prerequisites to fix this.
Also mark "dtbs" as PHONY for correctness.

This was broken in (70b0476a ARM: 7513/1: Make sure dtc is built before
running it).
Reported-by: NMike Frysinger <vapier@gentoo.org>
Signed-off-by: NDoug Anderson <dianders@chromium.org>
Acked-by: NOlof Johansson <olof@lixom.net>
Reviewed-by: NDavid Brown <davidb@codeaurora.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

arm26 support in Linux is long gone, yet it left an interresting,
fossilized trace in the decompressor.

Remove it so people won't get confused about what teqp is actually
doing here...
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Looking into the active_asids array is not enough, as we also need
to look into the reserved_asids array (they both represent processes
that are currently running).

Also, not holding the ASID allocator lock is racy, as another CPU
could schedule that process and trigger a rollover, making the erratum
workaround miss an IPI.

Exposing this outside of context.c is a little ugly on the side, so
let's define a new entry point that the erratum workaround can call
to obtain the cpumask.

Cc: <stable@vger.kernel.org> # 3.9
Acked-by: NWill Deacon <will.deacon@arm.com>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

On a CPU that never ran anything, both the active and reserved ASID
fields are set to zero. In this case the ASID_TO_IDX() macro will
return -1, which is not a very useful value to index a bitmap.

Instead of trying to offset the ASID so that ASID #1 is actually
bit 0 in the asid_map bitmap, just always ignore bit 0 and start
the search from bit 1. This makes the code a bit more readable,
and without risk of OoB access.

Cc: <stable@vger.kernel.org> # 3.9
Acked-by: NWill Deacon <will.deacon@arm.com>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Reported-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When a CPU is running a process, the ASID for that process is
held in a per-CPU variable (the "active ASIDs" array). When
the ASID allocator handles a rollover, it copies the active
ASIDs into a "reserved ASIDs" array to ensure that a process
currently running on another CPU will continue to run unaffected.
The active array is zero-ed to indicate that a rollover occurred.

Because of this mechanism, a reserved ASID is only remembered for
a single rollover. A subsequent rollover will completely refill
the reserved ASIDs array.

In a severely oversubscribed environment where a CPU can be
prevented from running for extended periods of time (think virtual
machines), the above has a horrible side effect:

[P{a} denotes process P running with ASID a]

	CPU-0		CPU-1

	A{x}				[active = <x 0>]

	[suspended]	runs B{y}	[active = <x y>]

					[rollover:
					 active = <0 0>
					 reserved = <x y>]

			runs B{y}	[active = <0 y>
					 reserved = <x y>]

					[rollover:
					 active = <0 0>
					 reserved = <0 y>]

			runs C{x}	[active = <0 x>]

	[resumes]

	runs A{x}

At that stage, both A and C have the same ASID, with deadly
consequences.

The fix is to preserve reserved ASIDs across rollovers if
the CPU doesn't have an active ASID when the rollover occurs.

Cc: <stable@vger.kernel.org> # 3.9
Acked-by: NWill Deacon <will.deacon@arm.com>
Acked-by: NCatalin Carinas <catalin.marinas@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When booting fewer cores than are physically present on a versatile
platform (e.g. when passing maxcpus=N on the command line), some
secondary cores may remain in the holding pen, which is marked __INIT,
as each CPU's gic cpumask is initialised to 0xff, and thus an IPI to any
CPU will wake up *all* secondaries. This behaviour is crucial to the GIC
cpumask self-discovery. Late in the boot process, the memory comprising
the holding pen will be released to the kernel for more general use, and
may be overwritten with arbitrary data, which can cause the held
secondaries to start behaving unpredictably. This can lead to all manner
of odd behaviour from the kernel.

As preventing cpus from entering the pen would require invasive changes
to the GIC driver and to existing dts used in the wild, we instead
remove the __INIT marker from the pen, keeping it around and leaving the
unused secondary CPUs dormant.

Link: http://lists.infradead.org/pipermail/linux-arm-kernel/2013-June/175039.htmlSigned-off-by: NMark Rutland <mark.rutland@arm.com>
Acked-by: NPawel Moll <pawel.moll@arm.com>
Acked-by: NNicolas Pitre <nicolas.pitre@linaro.org>
Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

With this change, we no longer lose the innermost entry in the user-mode
part of the call chain.  See also the x86 port, which includes the ip.

It's possible to partially work around this problem by post-processing
the data to use the PERF_SAMPLE_IP value, but this works only if the CPU
wasn't in the kernel when the sample was taken.

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

Since commit 6a1c5312 the user writeable TLS register was zeroed to
prevent it from being used as a covert channel between two tasks.

There are more and more applications coming to Windows RT,
Wine could support them, but mostly they expect to have
the thread environment block (TEB) in TPIDRURW.

This patch preserves that register per thread instead of clearing it.
Unlike the TPIDRURO, which is already switched, the TPIDRURW
can be updated from userspace so needs careful treatment in the case that we
modify TPIDRURW and call fork(). To avoid this we must always read
TPIDRURW in copy_thread.
Signed-off-by: NAndré Hentschel <nerv@dawncrow.de>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NJonathan Austin <jonathan.austin@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This commit fixes the regression on Armada 370 (the kernal hang during
boot) introduced by the commit: "ARM: 7691/1: mm: kill unused
TLB_CAN_READ_FROM_L1_CACHE and use ALT_SMP instead".

When coming out of either a Wait for Interrupt (WFI) or a Wait for
Event (WFE) IDLE states, a specific timing sensitivity exists between
the retiring WFI/WFE instructions and the newly issued subsequent
instructions. This sensitivity can result in a CPU hang scenario.  The
workaround is to insert either a Data Synchronization Barrier (DSB) or
Data Memory Barrier (DMB) command immediately after the WFI/WFE
instruction.

This commit was based on the work of Lior Amsalem, but heavily
modified to apply the errata fix dynamically according to the
processor type thanks to the suggestions of Russell King and Nicolas
Pitre.
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>
Tested-by: NWilly Tarreau <w@1wt.eu>
Cc: <stable@vger.kernel.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Commit 1bc39742 (ARM: 7755/1: handle user space mapped pages in
flush_kernel_dcache_page) moved the implementation of
flush_kernel_dcache_page() into mm/flush.c but did not implement it
on noMMU ARM.
Signed-off-by: NSimon Baatz <gmbnomis@gmail.com>
Acked-by: NKevin Hilman <khilman@linaro.org>
Cc: <stable@vger.kernel.org> # 3.2+: 1bc39742: ARM: 7755/1
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The __cpu_logical_map array is statically initialized to 0, which is a valid
MPIDR value. To prevent issues with the current implementation, this patch
defines an MPIDR_INVALID value, and statically initializes the
__cpu_logical_map[] array to it. Entries in the arm_dt_init_cpu_maps()
tmp_map array used to stash DT reg properties while parsing DT are initialized
with the MPIDR_INVALID value as well for consistency.
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The introduction of the cpu-map topology node in the cpus node implies
that cpus node might have children that are not cpu nodes. The DT
parsing code needs updating otherwise it would check for cpu nodes
properties in nodes that are not required to contain them, resulting
in warnings that have no bearing on bindings defined in the dts source file.

Cc: <stable@vger.kernel.org> [3.8+]
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

As it was already suggested by Russell King and Arnd Bergmann:

https://lkml.org/lkml/2013/5/16/133

moxart and gemini seem to be the only platforms using CPU_FA526,
and instead of pointing arm_pm_idle to an empty function from
platform code, it makes sense to remove WFI code from the processor
specific idle function.

Applies to arm-soc/for-next (and 3.10-rc1).

Changes since v1:

1. remove WFI but make sure cpu_fa526_do_idle do not fall through
   to cpu_fa526_dcache_clean_area

Note: moxart boots and prints to UART without this patch, but input is broken.
Signed-off-by: NJonas Jensen <jonas.jensen@gmail.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Add comments to machine_shutdown()/halt()/power_off()/restart() that
describe their purpose and/or requirements re: CPUs being active/not.

In machine_shutdown(), replace the call to smp_send_stop() with a call to
disable_nonboot_cpus(). This completely disables all but one CPU, thus
satisfying the requirement that only a single CPU be active for kexec.
Adjust Kconfig dependencies for this change.

In machine_halt()/power_off()/restart(), call smp_send_stop() directly,
rather than via machine_shutdown(); these functions don't need to
completely de-activate all CPUs using hotplug, but rather just quiesce
them.

Remove smp_kill_cpus(), and its call from smp_send_stop().
smp_kill_cpus() was indirectly calling smp_ops.cpu_kill() without calling
smp_ops.cpu_die() on the target CPUs first. At least some implementations
of smp_ops had issues with this; it caused cpu_kill() to hang on Tegra,
for example. Since smp_send_stop() is only used for shutdown, halt, and
power-off, there is no need to attempt any kind of CPU hotplug here.

Adjust Kconfig to reflect that machine_shutdown() (and hence kexec)
relies upon disable_nonboot_cpus(). However, this alone doesn't guarantee
that hotplug will work, or even that hotplug is implemented for a
particular piece of HW that a multi-platform zImage runs on. Hence, add
error-checking to machine_kexec() to determine whether it did work.
Suggested-by: NRussell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: NStephen Warren <swarren@nvidia.com>
Acked-by: NWill Deacon <will.deacon@arm.com>
Tested-by: NZhangfei Gao <zhangfei.gao@gmail.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This patch corrects the base address of pinctrl_3 on Exynos5250
platform.
Signed-off-by: NPadmavathi Venna <padma.v@samsung.com>
Acked-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NOlof Johansson <olof@lixom.net>

Make sure hyp-stub.S gets removed during make distclean,
this left over file was introduced in commit:

424e5994 ARM: zImage/virt: hyp mode entry support for the zImage loader
Signed-off-by: NMagnus Damm <damm@opensource.se>
Acked-by: NDave Martin <dave.martin@linaro.org>
Reviewed-by: NSimon Horman <horms+renesas@verge.net.au>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Commit f8b63c18 made flush_kernel_dcache_page a no-op assuming that
the pages it needs to handle are kernel mapped only.  However, for
example when doing direct I/O, pages with user space mappings may
occur.

Thus, continue to do lazy flushing if there are no user space
mappings.  Otherwise, flush the kernel cache lines directly.
Signed-off-by: NSimon Baatz <gmbnomis@gmail.com>
Reviewed-by: NCatalin Marinas <catalin.marinas@arm.com>
Cc: <stable@vger.kernel.org> # 3.2+
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This commit fixes the ID and mask for the PJ4B which was too
restrictive and didn't match the CPU of the Armada 370 SoC.
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This bug was introduced in commit e651eab0.
Some v4/v5 platforms failed to boot due to this.
Signed-off-by: NPo-Yu Chuang <ratbert.chuang@gmail.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

On Cortex-A9 before version r1p0, the LoUIS bit field of the CLIDR
register returns zero when it should return one. This leads to cache
maintenance operations which rely on this value to not function as
intended, causing data corruption.

The workaround for this errata is to detect affected CPUs and correct
the LoUIS value read.
Acked-by: NWill Deacon <will.deacon@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>
Cc: stable@vger.kernel.org
Signed-off-by: NJon Medhurst <tixy@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Bandgap is a device used to measure temperature on electronic
equipments.  It is widely used in digital integrated circuits.  It is
based on the dependency between silicon voltage and temperature.

This patch introduce HAS_BANDGAP config entry.  This config is a boolean
value so that arch code can flag if they feature a bandgap device.

This config entry follows the same idea behind ARCH_HAS_CPUFREQ.

Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-omap@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: NFabio Stevam <festevam@gmail.com>
Acked-by: NTony Lindgren <tony@atomide.com>
Acked-by: NAmit Daniel Kachhap <amit.daniel@samsung.com>
Signed-off-by: NEduardo Valentin <eduardo.valentin@ti.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When scheduling an mm on a CPU where it hasn't previously been used, we
flush the icache on that CPU so that any code loaded previously on
a different core can be safely executed.

For cores with hardware broadcasting of cache maintenance operations,
this is clearly unnecessary, since the inner-shareable invalidation in
__sync_icache_dcache will affect all CPUs.

This patch conditionalises the icache flush in switch_mm based on
cache_ops_need_broadcast().
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Reported-by: NAlbin Tonnerre <albin.tonnerre@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When zImage is loaded into RAM at a low address but TEXT_OFFSET
is set higher, we risk overwriting ourself with the page table
needed to turn on the cache as it is located relative to the relocation
address.  Let's defer the cache setup after relocation in that case.
Signed-off-by: NNicolas Pitre <nico@linaro.org>
Reported-by: NStephen Boyd <sboyd@codeurora.org>
Tested-by: NStephen Boyd <sboyd@codeurora.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

An exclusive store instruction may fail for reasons other than lock
contention (e.g. a cache eviction during the critical section) so, in
line with other architectures using similar exclusive instructions
(alpha, mips, powerpc), retry the trylock operation if the lock appears
to be free but the strex reported failure.
Reported-by: NTony Thompson <anthony.thompson@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Running an OABI_COMPAT kernel on an SMP platform can lead to fun and
games with page aging.

If one CPU issues a swi instruction immediately before another CPU
decides to mkold the page containing the swi instruction, then we will
fault attempting to load the instruction during the vector_swi handler
in order to retrieve its immediate field. Since this fault is not
currently dealt with by our exception tables, this results in a panic:

  Unable to handle kernel paging request at virtual address 4020841c
  pgd = c490c000
  [4020841c] *pgd=84451831, *pte=bf05859d, *ppte=00000000
  Internal error: Oops: 17 [#1] PREEMPT SMP ARM
  Modules linked in: hid_sony(O)
  CPU: 1    Tainted: G        W  O  (3.4.0-perf-gf496dca-01162-gcbcc62b #1)
  PC is at vector_swi+0x28/0x88
  LR is at 0x40208420

This patch wraps all of the swi instruction loads with the USER macro
and provides a shared exception table entry which simply rewinds the
saved user PC and returns from the system call (without setting tbl, so
there's no worries with tracing or syscall restarting). Returning to
userspace will re-enter the page fault handler, from where we will
probably send SIGSEGV to the current task.
Reported-by: NWang, Yalin <yalin.wang@sonymobile.com>
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>

This patch makes legacy code on suspend/resume path being executed
conditionally, on non-DT platforms only, to fix suspend/resume of
DT-enabled systems, for which the code is inappropriate.
Signed-off-by: NTomasz Figa <t.figa@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
[olof: add #include <linux/of.h>]
Signed-off-by: NOlof Johansson <olof@lixom.net>

In prima2, some functions of checking DT is registered in initcall
level. If it doesn't match the compatible name of sirf, kernel
will panic. It blocks the usage of multiplatform on other verndor.

The error message is in below.

Knic - not syncing: unable to find compatible pwrc node in dtb
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.10.0-rc3-00006-gd7f26ea-dirty #86
[<c0013adc>] (unwind_backtrace+0x0/0xf8) from [<c0011430>] (show_stack+0x10/0x1)
[<c0011430>] (show_stack+0x10/0x14) from [<c026f724>] (panic+0x90/0x1e8)
[<c026f724>] (panic+0x90/0x1e8) from [<c03267fc>] (sirfsoc_of_pwrc_init+0x24/0x)
[<c03267fc>] (sirfsoc_of_pwrc_init+0x24/0x58) from [<c0320864>] (do_one_initcal)
[<c0320864>] (do_one_initcall+0x90/0x150) from [<c0320a20>] (kernel_init_freeab)
[<c0320a20>] (kernel_init_freeable+0xfc/0x1c4) from [<c026b9e8>] (kernel_init+0)
[<c026b9e8>] (kernel_init+0x8/0xe4) from [<c000e158>] (ret_from_fork+0x14/0x3c)
Signen-off-by: NHaojian Zhuang <haojian.zhuang@linaro.org>
Signed-off-by: NOlof Johansson <olof@lixom.net>

If the early MMU mapping of the UART happens to get booted out of the
TLB between the start of paging_init() and when we finally re-add the
UART at the very end of s3c_init_cpu(), we'll get a hang at bootup if
we've got early_printk enabled.  Avoid this hang by calling
debug_ll_io_init() early.

Without this patch, you can reliably reproduce a hang when early
printk is enabled by adding flush_tlb_all() at the start of
exynos_init_io().  After this patch the hang goes away.
Signed-off-by: NDoug Anderson <dianders@chromium.org>
Acked-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NOlof Johansson <olof@lixom.net>

Printing low-level debug messages make an assumption that the specified
UART port has been preconfigured by the bootloader. Incorrectly
specified UART port results in system getting stalled while printing the
message "Uncompressing Linux... done, booting the kernel"
This UART port number is specified through S3C_LOWLEVEL_UART_PORT. Since
the UART port might different for different board, it is not possible to
specify it correctly for every board that use a common defconfig file.

Calling this print subroutine only when DEBUG_LL fixes the problem. By
disabling DEBUG_LL in default config file, we would be able to boot
multiple boards with different default UART ports.

With this current approach, we miss the print "Uncompressing Linux...
done, booting the kernel." when DEBUG_LL is not defined.
Signed-off-by: NTushar Behera <tushar.behera@linaro.org>
Signed-off-by: NOlof Johansson <olof@lixom.net>

The ranges DT entry needed by the PCIe controller is defined at the
SoC .dtsi level. However, some boards have a NOR flash, and to support
it, they need to override the SoC-level ranges property to add an
additional range. Since PCIe and NOR support came separately, some
boards were not properly changed to include the PCIe range in their
ranges property at the .dts level.

This commit fixes those platforms.
Signed-off-by: NThomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: NJason Cooper <jason@lakedaemon.net>

MPP_F6281_MASK would be previously be returned when on mv88f6282,
which would disallow some valid MPP configurations.

Commit 830f8b91 (arm: plat-orion: fix printing of "MPP config
unavailable on this hardware") made this problem visible as an invalid
MPP configuration is now correctly detected and not applied.
Signed-off-by: NNicolas Schichan <nschichan@freebox.fr>
Cc: <stable@vger.kernel.org> # v3.9.x
Signed-off-by: NJason Cooper <jason@lakedaemon.net>

omap36xx_pwrdn_clk_enable_with_hsdiv_restore expects the parent hw of
the clock to be a clk_hw_omap. However, looking at cclock3xxx_data.c,
all concerned clock have parent defined as clk_divider.  Fix the
function to use clk_divider.  Tested with 3.9 on dm3730.
Signed-off-by: NJean-Philippe François <jp.francois@cynove.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Mike Turquette <mturquette@linaro.org>
Signed-off-by: NPaul Walmsley <paul@pwsan.com>

Since the introduction of preemptible mmu_gather TLB fast mode has been
broken. TLB fast mode relies on there being absolutely no concurrency;
it frees pages first and invalidates TLBs later.

However now we can get concurrency and stuff goes *bang*.

This patch removes all tlb_fast_mode() code; it was found the better
option vs trying to patch the hole by entangling tlb invalidation with
the scheduler.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Tony Luck <tony.luck@intel.com>
Reported-by: NMax Filippov <jcmvbkbc@gmail.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The smp_init_cpus method in the smp_operations structure is optional
and can be omitted entirely.
Signed-off-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The CPU and cluster numbers (MPIDR affinity levels 0 and 1) may have
at most 8 bits each.
Signed-off-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Currently flush_dcache_page() thinks pages as non-mapped if
mapping_mapped(mapping) return false. This approach is very
coase:
	- mmap on part of file may cause all pages backed on
	the file being thought as mmaped

	- file-backed pages aren't mapped into user space actually
	if the memory mmaped on the file isn't accessed

This patch uses page_mapped() to decide if the page has been
mapped.

From the attached test code, I find there is much performance
improvement(>25%) when accessing page caches via read under this
situations, so memcpy benefits a lot from not flushing cache
under this situation.

No.   read time without the patch	No. read time with the patch
================================================================
No. 0, time  22615636 us		No. 0, time  22014717 us
No. 1, time  4387851 us 		No. 1, time  3113184 us
No. 2, time  4276535 us 		No. 2, time  3005244 us
No. 3, time  4259821 us 		No. 3, time  3001565 us
No. 4, time  4263811 us 		No. 4, time  3002748 us
No. 5, time  4258486 us 		No. 5, time  3004104 us
No. 6, time  4253009 us 		No. 6, time  3002188 us
No. 7, time  4262809 us 		No. 7, time  2998196 us
No. 8, time  4264525 us 		No. 8, time  3007255 us
No. 9, time  4267795 us 		No. 9, time  3005094 us

1), No.0. is to read the file from storage device, and others are
to read the file from page caches basically.
2), file size is 512M, and is on ext4 over usb mass storage.
3), the test is done on Pandaboard.

unsigned int  sum = 0;
unsigned long sum_val = 0;

static unsigned long tv_diff(struct timeval *tv1, struct timeval *tv2)
{
	return (tv2->tv_sec - tv1->tv_sec) * 1000000 +
		(tv2->tv_usec - tv1->tv_usec);
}

int main(int argc, char *argv[])
{
	char *mbuf, fbuf;
	int fd;
	int i;
	unsigned long page_size, size;
	struct stat stat;
	struct timeval t1, t2;
	unsigned char *rbuf = malloc(32 * page_size);

	if (!rbuf) {
		printf("	%sn", "malloc failed");
		exit(-1);
	}

	page_size = getpagesize();
	fd = open(argv[1], O_RDWR);
	assert(fd >= 0);

	fstat(fd, &stat);
	size = stat.st_size;
	printf("%s: file %s, size %lu, page size %lun",
		argv[0],
		argv[1], size, page_size);

	gettimeofday(&t1, NULL);
	mbuf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
	if (!mbuf) {
		printf("	%sn", "mmap failed");
		exit(-1);
	}

	for (i = 0 ; i < size ; i += (page_size * 32)) {
		int rcnt;
		lseek(fd, i, SEEK_SET);
		rcnt = read(fd, rbuf, page_size * 32);
		if (rcnt != page_size * 32) {
			printf("%s: read faildn", __func__);
			exit(-1);
		}
	}
	free(rbuf);
	munmap(mbuf, size);
	gettimeofday(&t2, NULL);
	printf("tread mmaped time: %luusn", tv_diff(&t1, &t2));

	close(fd);
}

Cc: Michel Lespinasse <walken@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

__my_cpu_offset is non-volatile, since we want its value to be cached
when we access several per-cpu variables in a row with preemption
disabled. This means that we rely on preempt_{en,dis}able to hazard
with the operation via the barrier() macro, so that we can't end up
migrating CPUs without reloading the per-cpu offset.

Unfortunately, GCC doesn't treat a "memory" clobber on a non-volatile
asm block as a side-effect, and will happily re-order it before other
memory clobbers (including those in prempt_disable()) and cache the
value. This has been observed to break the cmpxchg logic in the slub
allocator, leading to livelock in kmem_cache_alloc in mainline kernels.

This patch adds a dummy memory input operand to __my_cpu_offset,
forcing it to be ordered with respect to the barrier() macro.

Cc: <stable@vger.kernel.org>
Cc: Rob Herring <rob.herring@calxeda.com>
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>

The previous mask values for the legacy ARM CPU IDs were conflicting
with the CPU ID assignments for late-generation CPUs (like the
Qualcomm MSM/QSD or Broadcom Brahma-15 processors). This change
corrects the legacy ARM CPU ID value so that the jump table can
fall-through to the appropriate cache maintenance / MMU functions.
Signed-off-by: NMarc C <marc.ceeeee@gmail.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

In August 2012, Matthew Gretton-Dann checked a change into binutils
labelled "Error on obsolete & warn on deprecated registers", apparently as
part of ARMv8 support. Apparently, this was supposed to emit the message
"Warning: This coprocessor register access is deprecated in ARMv8" when
using certain mcr/mrc instructions and building for ARMv8. Unfortunately,
the message that is actually emitted appears to be '(null)', which is
less helpful in comparison.

Even more unfortunately, this is biting us on every single kernel
build with a new gas, because arch/arm/boot/compressed/head.S and some
other files in that directory are built with -march=all since kernel
commit 80cec14a "[ARM] Add -march=all to assembly file build in
arch/arm/boot/compressed" back in v2.6.28.

This patch reverts Russell's nice solution and instead marks the head.S
file to be built for armv7-a, which fortunately lets us build all
instructions in that file without warnings even on the broken binutils.

Without this patch, building anything results in:

arch/arm/boot/compressed/head.S: Assembler messages:
arch/arm/boot/compressed/head.S:565: Warning: (null)
arch/arm/boot/compressed/head.S:676: Warning: (null)
arch/arm/boot/compressed/head.S:698: Warning: (null)
arch/arm/boot/compressed/head.S:722: Warning: (null)
arch/arm/boot/compressed/head.S:726: Warning: (null)
arch/arm/boot/compressed/head.S:957: Warning: (null)
arch/arm/boot/compressed/head.S:996: Warning: (null)
arch/arm/boot/compressed/head.S:997: Warning: (null)
arch/arm/boot/compressed/head.S:1027: Warning: (null)
arch/arm/boot/compressed/head.S:1035: Warning: (null)
arch/arm/boot/compressed/head.S:1046: Warning: (null)
arch/arm/boot/compressed/head.S:1060: Warning: (null)
arch/arm/boot/compressed/head.S:1092: Warning: (null)
arch/arm/boot/compressed/head.S:1094: Warning: (null)
arch/arm/boot/compressed/head.S:1095: Warning: (null)
arch/arm/boot/compressed/head.S:1102: Warning: (null)
arch/arm/boot/compressed/head.S:1134: Warning: (null)
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Cc: stable@vger.kernel.org
Cc: Matthew Gretton-Dann <matthew.gretton-dann@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>