Kirkwood, which uses the Feroceon L2 cache controller will soon be
moving into mach-mvebu. Allow the cache controller to be built in this
situation.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Tested-by: NJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: NJason Cooper <jason@lakedaemon.net>

Instantiate the L2 cache from DT. Indicate in DT where the cache
control register is so that it is possible to enable/disable write
through on the CPU.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Tested-by: NJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: NJason Cooper <jason@lakedaemon.net>

With the gradual move to DT, kirkwood has become a lot less dependent
on plat-orion. cache-feroceon-l2.h is the last dependency. Move it out
so we can drop plat-orion when building DT only kirkwood boards.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Tested-by: NJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: NJason Cooper <jason@lakedaemon.net>

Commit 65939301 (arm: set initrd_start/initrd_end for fdt scan)
caused the FDT initrd_start and initrd_end to override the
phys_initrd_start and phys_initrd_size set by the initrd= kernel
parameter.  With this patch initrd_start and initrd_end will be
overridden if phys_initrd_start and phys_initrd_size are set by the
kernel initrd= parameter.

Fixes: 65939301 (arm: set initrd_start/initrd_end for fdt scan)
Signed-off-by: NBen Peddell <klightspeed@killerwolves.net>
Acked-by: NJason Cooper <jason@lakedaemon.net>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Switch to memblock interfaces for early memory allocator instead of
bootmem allocator.  No functional change in beahvior than what it is in
current code from bootmem users points of view.

Archs already converted to NO_BOOTMEM now directly use memblock
interfaces instead of bootmem wrappers build on top of memblock.  And
the archs which still uses bootmem, these new apis just fallback to
exiting bootmem APIs.
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Paul Walmsley <paul@pwsan.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Commit 4b59e6c4 ("mm, show_mem: suppress page counts in
non-blockable contexts") introduced SHOW_MEM_FILTER_PAGE_COUNT to
suppress PFN walks on large memory machines.  Commit c78e9363 ("mm:
do not walk all of system memory during show_mem") avoided a PFN walk in
the generic show_mem helper which removes the requirement for
SHOW_MEM_FILTER_PAGE_COUNT in that case.

This patch removes PFN walkers from the arch-specific implementations
that report on a per-node or per-zone granularity.  ARM and unicore32
still do a PFN walk as they report memory usage on each bank which is a
much finer granularity where the debugging information may still be of
use.  As the remaining arches doing PFN walks have relatively small
amounts of memory, this patch simply removes SHOW_MEM_FILTER_PAGE_COUNT.

[akpm@linux-foundation.org: fix parisc]
Signed-off-by: NMel Gorman <mgorman@suse.de>
Acked-by: NDavid Rientjes <rientjes@google.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: James Bottomley <jejb@parisc-linux.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This reverts commit 787b0d5c since
it is no longer required after 7909/1 was applied, and it causes
build regressions when ARM_PATCH_PHYS_VIRT is disabled and DMA_ZONE
is enabled.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The ASID allocator has to deal with some pretty horrible behaviours by
the CPU, so expand on some of the comments in there so I remember why
we can never allocate ASID zero to a userspace task.
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>

Since we only clear entries in the ASID bitmap on a rollover event, the
bitmap tends to consist of a block of consecutive set bits followed by
a block of consecutive clear bits. The exception to this rule is for
ASIDs which have been carried over from a previous generation, but
these are bound by the number of CPUs.

This patch optimises our bitmap searching strategy, so that we search
from the last successful allocation, rather than search from index 1
each time we allocate a new ASID.
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>

With the new ASID allocation algorithm, active ASIDs at the time of a
rollover event will be marked as reserved, so active mm_structs can
continue to operate with the same ASID as before. This in turn means
that we don't need to worry about allocating a new ASID to an mm that
is currently active (installed in TTBR0).

Since updating the pgd and ASID is atomic on LPAE systems (by virtue of
the two being fields in the same hardware register), we can dispose of
the reserved TTBR0 and rely on whatever tables we currently have live.
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 given a compound high page, __flush_dcache_page will only flush
the first page of the compound page repeatedly rather than the entire
set of constituent pages.

This error was introduced by:
   0b19f933 ARM: mm: Add support for flushing HugeTLB pages.

This patch corrects the logic such that all constituent pages are now
flushed.

Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: NSteve Capper <steve.capper@linaro.org>
Acked-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Make pgd allocation retry on failure; we really need this to succeed
otherwise fork() can trigger OOMs.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This adds support for the Marvell Tauros3 cache controller which
is compatible with pl310 cache controller but broadcasts L1 cache
operations to L2 cache. While updating the binding documentation,
clean up the list of possible compatibles. Also reorder driver
compatibles to allow non-ARM derivated to be compatible to ARM
cache controller compatibles.
Signed-off-by: NSebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Reviewed-by: NMark Rutland <mark.rutland@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Set-associative caches on all v7 implementations map the index bits
to physical addresses LSBs and tag bits to MSBs. As the last level
of cache on current and upcoming ARM systems grows in size,
this means that under normal DRAM controller configurations, the
current v7 cache flush routine using set/way operations triggers a
DRAM memory controller precharge/activate for every cache line
writeback since the cache routine cleans lines by first fixing the
index and then looping through ways (index bits are mapped to lower
physical addresses on all v7 cache implementations; this means that,
with last level cache sizes in the order of MBytes, lines belonging
to the same set but different ways map to different DRAM pages).

Given the random content of cache tags, swapping the order between
indexes and ways loops do not prevent DRAM pages precharge and
activate cycles but at least, on average, improves the chances that
either multiple lines hit the same page or multiple lines belong to
different DRAM banks, improving throughput significantly.

This patch swaps the inner loops in the v7 cache flushing routine
to carry out the clean operations first on all sets belonging to
a given way (looping through sets) and then decrementing the way.

Benchmarks showed that by swapping the ordering in which sets and
ways are decremented in the v7 cache flushing routine, that uses
set/way operations, time required to flush caches is reduced
significantly, owing to improved writebacks throughput to the DRAM
controller.

Benchmarks results vary and depend heavily on the last level of
cache tag RAM content when cache is cleaned and invalidated, ranging
from 2x throughput when all tag RAM entries contain dirty lines
mapping to sequential pages of RAM to 1x (ie no improvement) when
all tag RAM accesses trigger a DRAM precharge/activate cycle, as the
current code implies on most DRAM controller configurations.
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Acked-by: NNicolas Pitre <nico@linaro.org>
Acked-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Reviewed-by: NDave Martin <Dave.Martin@arm.com>
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The CMA region was being marked executable:

0xdc04e000-0xdc050000           8K     RW x      MEM/CACHED/WBRA
0xdc060000-0xdc100000         640K     RW x      MEM/CACHED/WBRA
0xdc4f5000-0xdc500000          44K     RW x      MEM/CACHED/WBRA
0xdcce9000-0xe0000000       52316K     RW x      MEM/CACHED/WBRA

This is mainly due to the badly worded MT_MEMORY_DMA_READY symbol, but
there are also a few other places in dma-mapping which should be
corrected to use the right constant.  Fix all these places:

0xdc04e000-0xdc050000           8K     RW NX     MEM/CACHED/WBRA
0xdc060000-0xdc100000         640K     RW NX     MEM/CACHED/WBRA
0xdc280000-0xdc300000         512K     RW NX     MEM/CACHED/WBRA
0xdc6fc000-0xe0000000       58384K     RW NX     MEM/CACHED/WBRA
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Other architectures define various set_memory functions to allow
attributes to be changed (e.g. set_memory_x, set_memory_rw, etc.)
Currently, these functions are missing on ARM. Define these in an
appropriate manner for ARM.
Signed-off-by: NLaura Abbott <lauraa@codeaurora.org>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Add basic NX support for kernel lowmem mappings.  We mark any section
which does not overlap kernel text as non-executable, preventing it
from being used to write code and then execute directly from there.

This does not change the alignment of the sections, so the kernel
image doesn't grow significantly via this change, so we can do this
without needing a config option.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Document the permissions which the various MT_MEMORY* mapping types
will provide.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This patch allows the kernel page tables to be dumped via a debugfs file,
allowing kernel developers to check the layout of the kernel page tables
and the verify the various permissions and type settings.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Current code is using PHYS_OFFSET to calculate the arm_dma_limit which
will lead to wrong calculations in cases where PHYS_OFFSET is updated
runtime.

So fix the code by using __pv_phys_offset instead of PHYS_OFFSET.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Peter reports that OMAP audio broke with the recent fix for these
checks, caused by OMAP audio using a 64-bit DMA mask.  We should
allow 64-bit DMA masks even with 32-bit dma_addr_t if we can be sure
the amount of RAM we have won't allow the 32-bit dma_addr_t to
overflow.  Unfortunately, the checks to detect overflow were not
correct.
Tested-by: NPeter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Commit f6f91b0d (ARM: allow kuser helpers to be removed from the
vector page) required two pages for the vectors code.  Although the
code setting up the initial page tables was updated, the code which
allocates page tables for new processes wasn't, neither was the code
which tears down the mappings.  Fix this.

Fixes: f6f91b0d ("ARM: allow kuser helpers to be removed from the vector page")
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>
Cc: <stable@vger.kernel.org>

Some buses have negative offsets, which causes the DMA mask checks to
falsely fail.  Fix this by using the actual amount of memory fitted in
the system.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Now with dma_mask series merged and max*pfn has consistent meaning on ARM
as rest of the arch's thanks to RMK's mega series, lets switch ARM code
to NO_BOOTMEM. With NO_BOOTMEM change, now we use memblock allocator to
reserve space for crash kernel to have one less dependency with nobootmem
allocator wrapper.

Tested with both flat memory and sparse (faked) memory models with highmem
enabled.

Cc: Russell King <linux@arm.linux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>

If allowed by call to memblock_allow_resize() - The Memblock core will
try to allocate additional memory and rearrange its internal data in
case, if there are more then INIT_MEMBLOCK_REGIONS(128) memory regions
of any type have been allocated. If this happens before Low memory is
mapped (which is done now by map_lowmem()) the system will hang, because
the Memblock core will try to operate with virtual addresses which
aren't mapped yet.

In ARM code, the memblock resizing is allowed (memblock_allow_resize())
from arm_memblock_init() which is called before map_lowmem(), so
this may lead to an error as described above.

Hence, allow Memblock resizing later during init, from bootmem_init()
when all appropriate mappings are ready.

Cc: Russell King <linux@arm.linux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: NGrygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>

With commit  26ba47b1 {ARM: 7805/1: mm: change max*pfn to include
the physical offset of memory}, the max_pfn already contain
PHYS_PFN_OFFSET, so it shouldn't be taken into account again.

While at it, use use set_max_mapnr() helper.

Cc: Russell King <linux@arm.linux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: NGrygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>

We're going to introduce split page table lock for PMD level.  Let's
rename existing split ptlock for PTE level to avoid confusion.
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: NAlex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

LPAE enabled kernels use the 64-bit version of TTBR0 and TTBR1
registers. If we're running an LPAE kernel, fill the upper half
of TTBR0 with 0 because we're setting it to the idmap here (the
idmap is guaranteed to be < 4Gb) and fully restore TTBR1 instead
of just restoring the lower 32 bits. Failure to do so can cause
failures on resume from suspend when these registers are only
half restored.
Signed-off-by: NMahesh Sivasubramanian <msivasub@codeaurora.org>
Signed-off-by: NStephen Boyd <sboyd@codeaurora.org>
Acked-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

ECC policy can be applied to the whole system
when this bit is implemented by SoC vendor
(IMP - bit 9 - in L1 page table entry format).
When this bit is not implemented by SoC vendor
it doesn't mean that system has no other way
how to do ECC.
This patch ensures to show this message only when ECC
is requested via cmd line ecc=on and runs on
appropriate ARM core.
Signed-off-by: NMichal Simek <michal.simek@xilinx.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The 0-day kernel build robot found this new warning:

arch/arm/mm/nommu.c:303:17: warning: 'struct proc_info_list' declared inside parameter list [enabled by default]
arch/arm/mm/nommu.c:303:17: warning: its scope is only this definition or declaration, which is probably not what you want [enabled by default]

Fix it by including the appropriate header.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

No-MMU configurations currenty fail to build because they are missing
the early_paging_init() symbol.
Acked-by: NOlof Johansson <olof@lixom.net>
Signed-off-by: NThierry Reding <treding@nvidia.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The exception handling code fails to clear the IT state, potentially
leading to incorrect execution of the fixup if the size of the IT
block is more than one.

Let fixup_exception do the IT sanitizing if a fixup has been found,
and restore CPSR from the stack when returning from a data abort.

Cc: Will Deacon <will.deacon@arm.com>
Cc: stable@vger.kernel.org
Reviewed-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>

Most of the kernel code assumes that max*pfn is maximum pfns because
the physical start of memory is expected to be PFN0. Since this
assumption is not true on ARM architectures, the meaning of max*pfn
is number of memory pages. This is done to keep drivers happy which
are making use of of these variable to calculate the dma bounce limit
using dma_mask.

Now since we have a architecture override possibility for DMAable
maximum pfns, lets make meaning of max*pfns as maximum pnfs on ARM
as well.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

We need to start treating DMA masks as something which is specific to
the bus that the device resides on, otherwise we're going to hit all
sorts of nasty issues with LPAE and 32-bit DMA controllers in >32-bit
systems, where memory is offset from PFN 0.

In order to start doing this, we convert the DMA mask to a PFN using
the device specific dma_to_pfn() macro.  This is the reverse of the
pfn_to_dma() macro which is used to get the DMA address for the device.

This gives us a PFN mask, which we can then check against the PFN
limit of the DMA zone.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

With LPAE enabled, physical address space is larger than 4GB. Allow mapping any
part of it via /dev/mem by using PHYS_MASK to determine valid range.

PHYS_MASK covers 40 bits with LPAE enabled and 32 bits otherwise.
Reported-by: NVassili Karpov <av1474@comtv.ru>
Signed-off-by: NSergey Dyasly <dserrg@gmail.com>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

DMA mapping permissions were being derived from pgprot_kernel directly
without using PAGE_KERNEL.  This causes them to be marked with executable
permission, which is not what we want.  Fix this.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

If we are in BE8 mode, we must deal with the instruction stream being
in LE order when data is being loaded in BE order. Ensure the data is
swapped before processing to avoid thre following:

Change to using <asm/opcodes.h> to provide the necessary conversion
functions to change the byte ordering.

This stops the following warning messages from the kernel on a fault:

Unhandled fault: alignment exception (0x001) at 0xbfa09567
Alignment trap: not handling instruction 030091e8 at [<80333e8c>]
Signed-off-by: NBen Dooks <ben.dooks@codethink.co.uk>
Reviewed-by: NDave Martin <Dave.Martin@arm.com>
Tested-by: NThomas Petazzoni <thomas.petazzoni@free-electrons.com>

Add ARM_BE8() helper to wrap any code conditional on being
compile when CONFIG_ARM_ENDIAN_BE8 is selected and convert
existing places where this is to use it.
Acked-by: NNicolas Pitre <nico@linaro.org>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NBen Dooks <ben.dooks@codethink.co.uk>

The Kconfig for arch/arm/mach-ixp4xx has a local definition
of ARCH_SUPPORTS_BIG_ENDIAN which could be used elsewhere.
This means that if IXP4xx is selected and this symbol is
selected eleswhere then an warning is produced.

Clean the following error up by making the symbol be
selected by the main ARCH_IXP4XX definition and have a
common definition in arch/arm/mm/Kconfig

warning: (ARCH_xxx) selects ARCH_SUPPORTS_BIG_ENDIAN which has unmet direct dependencies (ARCH_IXP4XX)
warning: (ARCH_xxx) selects ARCH_SUPPORTS_BIG_ENDIAN which has unmet direct dependencies (ARCH_IXP4XX)
Signed-off-by: NBen Dooks <ben.dooks@codethink.co.uk>

This reverts commit 10bcdfb8. There is
no consensus on the bindings for the reserved memory, so the code for
handing it will be reverted.
Signed-off-by: NMarek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: NGrant Likely <grant.likely@linaro.org>