This changes vmemmap to use a different region (region 0xf) of the
address space, and to configure the page size of that region
dynamically at boot.

The problem with the current approach of always using 16M pages is that
it's not well suited to machines that have small amounts of memory such
as small partitions on pseries, or PS3's.

In fact, on the PS3, failure to allocate the 16M page backing vmmemmap
tends to prevent hotplugging the HV's "additional" memory, thus limiting
the available memory even more, from my experience down to something
like 80M total, which makes it really not very useable.

The logic used by my match to choose the vmemmap page size is:

 - If 16M pages are available and there's 1G or more RAM at boot,
   use that size.
 - Else if 64K pages are available, use that
 - Else use 4K pages

I've tested on a POWER6 (16M pages) and on an iSeries POWER3 (4K pages)
and it seems to work fine.

Note that I intend to change the way we organize the kernel regions &
SLBs so the actual region will change from 0xf back to something else at
one point, as I simplify the SLB miss handler, but that will be for a
later patch.
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This fixes a regression reported by Kamalesh Bulabel where a POWER4
machine would crash because of an SLB miss at a point where the SLB
miss exception was unrecoverable.  This regression is tracked at:

http://bugzilla.kernel.org/show_bug.cgi?id=10082

SLB misses at such points shouldn't happen because the kernel stack is
the only memory accessed other than things in the first segment of the
linear mapping (which is mapped at all times by entry 0 of the SLB).
The context switch code ensures that SLB entry 2 covers the kernel
stack, if it is not already covered by entry 0.  None of entries 0
to 2 are ever replaced by the SLB miss handler.

Where this went wrong is that the context switch code assumes it
doesn't have to write to SLB entry 2 if the new kernel stack is in the
same segment as the old kernel stack, since entry 2 should already be
correct.  However, when we start up a secondary cpu, it calls
slb_initialize, which doesn't set up entry 2.  This is correct for
the boot cpu, where we will be using a stack in the kernel BSS at this
point (i.e. init_thread_union), but not necessarily for secondary
cpus, whose initial stack can be allocated anywhere.  This doesn't
cause any immediate problem since the SLB miss handler will just
create an SLB entry somewhere else to cover the initial stack.

In fact it's possible for the cpu to go quite a long time without SLB
entry 2 being valid.  Eventually, though, the entry created by the SLB
miss handler will get overwritten by some other entry, and if the next
access to the stack is at an unrecoverable point, we get the crash.

This fixes the problem by making slb_initialize create a suitable
entry for the kernel stack, if we are on a secondary cpu and the stack
isn't covered by SLB entry 0.  This requires initializing the
get_paca()->kstack field earlier, so I do that in smp_create_idle
where the current field is initialized.  This also abstracts a bit of
the computation that mk_esid_data in slb.c does so that it can be used
in slb_initialize.
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Arrange for a syntax check to always be done on the powerpc/mm/slb.c
DBG() macro by defining it to pr_debug() for non-debug builds.

Also, fix these related compile warnings:

  slb.c:273: warning: format '%04x' expects type 'unsigned int', but argument 2 has type 'long unsigned int
  slb.c:274: warning: format '%04x' expects type 'unsigned int', but argument 2 has type 'long unsigned int'
Signed-off-by: NGeoff Levand <geoffrey.levand@am.sony.com>
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Provide walk_memory_resource() for 64-bit powerpc.  PowerPC maintains
logical memory region mapping in the lmb.memory structure.  Walk
through these structures and do the callbacks for the contiguous
chunks.
Signed-off-by: NBadari Pulavarty <pbadari@us.ibm.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

All architectures use an effectively identical definition of online_page(), so
just make it common code.  x86-64, ia64, powerpc and sh are actually
identical; x86-32 is slightly different.

x86-32's differences arise because it puts its hotplug pages in the highmem
zone.  We can handle this in the generic code by inspecting the page to see if
its in highmem, and update the totalhigh_pages count appropriately.  This
leaves init_32.c:free_new_highpage with a single caller, so I folded it into
add_one_highpage_init.

I also removed an incorrect comment referring to the NUMA case; any NUMA
details have already been dealt with by the time online_page() is called.

[akpm@linux-foundation.org: fix indenting]
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: NDave Hansen <dave@linux.vnet.ibm.com>
Reviewed-by: NKAMEZAWA Hiroyuki <kamez.hiroyu@jp.fujitsu.com>
Tested-by: NKAMEZAWA Hiroyuki <kamez.hiroyu@jp.fujitsu.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: NIngo Molnar <mingo@elte.hu>
Acked-by: NYasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Use (31-THREAD_SHIFT) to get to thread_info from stack pointer.  This makes
the code a bit easier to read and more robust if we ever change THREAD_SHIFT.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The fixmap code from x86 allows us to have compile time virtual addresses
that we change the physical addresses of at run time.

This is useful for applications like kmap_atomic, PCI config that is done
via direct memory map, kexec/kdump.

We got ride of CONFIG_HIGHMEM_START as we can now determine a more optimal
location for PKMAP_BASE based on where the fixmap addresses start and
working back from there.

Additionally, the kmap code in asm-powerpc/highmem.h always had debug
enabled.  Moved to using CONFIG_DEBUG_HIGHMEM to determine if we should
have the extra debug checking.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Added support to allow an 85xx kernel to be run from a non-zero physical
address (useful for cooperative asymmetric multiprocessing situations and
kdump).  The support can be configured at compile time by setting
CONFIG_PAGE_OFFSET, CONFIG_KERNEL_START, and CONFIG_PHYSICAL_START as
desired.

Alternatively, the kernel build can set CONFIG_RELOCATABLE.  Setting this
config option causes the kernel to determine at runtime the physical
addresses of CONFIG_PAGE_OFFSET and CONFIG_KERNEL_START.  If
CONFIG_RELOCATABLE is set, then CONFIG_PHYSICAL_START has no meaning.
However, CONFIG_PHYSICAL_START will always be used to set the LOAD program
header physical address field in the resulting ELF image.

Currently we are limited to running at a physical address that is a
multiple of 256M.  This is due to how we map TLBs to cover
lowmem.  This should be fixed to allow 64M or maybe even 16M alignment
in the future.  It is considered an error to try and run a kernel at a
non-aligned physical address.

All the magic for this support is accomplished by proper initialization
of the kernel memory subsystem and use of ARCH_PFN_OFFSET.

The use of ARCH_PFN_OFFSET only affects normal memory and not IO mappings.
ioremap uses map_page and isn't affected by ARCH_PFN_OFFSET.

/dev/mem continues to allow access to any physical address in the system
regardless of how CONFIG_PHYSICAL_START is set.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

numa.c requires routines declared in linux/of.h, so should include it.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Remove the __max_memory variable, as it is not referenced anywhere
in the tree besides some code in arch/ppc.
Signed-off-by: NOlof Johansson <olof@lixom.net>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

When we moved to arch/powerpc we actively tried to avoid using the
ppc_md.setup_io_mappings().  Currently no board ports use it so let's
remove it to avoid any new boards using it.

Also, remove early_serial_map() since we don't even have a call out for
it in arch/powerpc.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

We always use __initial_memory_limit as an address so rename it
to be clear.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

* Determine the RPN we are running the kernel at runtime rather
  than using compile time constant for initial TLB

* Cleanup adjust_total_lowmem() to respect memstart_addr and
  be a bit more clear on variables that are sizes vs addresses.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

total_lowmem represents the amount of low memory, not the physical
address that low memory ends at.  If the start of memory is at 0 it
happens that total_lowmem can be used as both the size and the address
that lowmem ends at (or more specifically one byte beyond the end).

To make the code a bit more clear and deal with the case when the start of
memory isn't at physical 0, we introduce lowmem_end_addr that represents
one byte beyond the last physical address in the lowmem region.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

A number of users of PPC_MEMSTART (40x, ppc_mmu_32) can just always
use 0 as we don't support booting these kernels at non-zero physical
addresses since their exception vectors must be at 0 (or 0xfffx_xxxx).

For the sub-arches that support relocatable interrupt vectors
(book-e), it's reasonable to have memory start at a non-zero physical
address.  For those cases use the variable memstart_addr instead of
the #define PPC_MEMSTART since the only uses of PPC_MEMSTART are for
initialization and in the future we can set memstart_addr at runtime
to have a relocatable kernel.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This eliminates a warning in builds that don't define
CONFIG_MEMORY_HOTPLUG.
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

hash_page_sync() takes and releases the low level mmu hash
lock in order to sync with other processors disposing of page
tables.  Because that lock can be needed to service hash misses
triggered by interrupt handlers, taking it must be done with
interrupts off.  However, hash_page_sync() appears to be called
with interrupts enabled, thus causing occasional deadlocks.

We fix it by making sure hash_page_sync() masks interrupts while
holding the lock.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

show_mem() has no need to print the amount of free swap space manually
because show_free_areas() does this already and is called by the
former.

The two outputs only differ in text formatting:

  printk("Free swap  = %lukB\n", ...);
  printk("Free swap:       %6ldkB\n", ...);
Signed-off-by: NJohannes Weiner <hannes@saeurebad.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

__FUNCTION__ is gcc-specific, use __func__
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

WARNING: vmlinux.o(.text+0xb41b0): Section mismatch in reference from the
function .add_memory() to the function .devinit.text:.arch_add_memory()
The function .add_memory() references
the function __devinit .arch_add_memory().
This is often because .add_memory lacks a __devinit
annotation or the annotation of .arch_add_memory is wrong.

arch_add_memory() is also not __devinit on other architectures
Signed-off-by: NGeert Uytterhoeven <Geert.Uytterhoeven@sonycom.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

If the platform doesn't support hpte_removebolted(), gracefully
return failure rather than success.
Signed-off-by: NBadari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

On pSeries, the hypervisor doesn't let us map in the eHEA ethernet
adapter using 64k pages, and thus the ehea driver will fail if 64k
pages are configured.  This works around the problem by always
using 4k pages for ioremap on pSeries (but not on other platforms).
A better fix would be to check whether the partition could ever
have an eHEA adapter, and only force 4k pages if it could, but this
will do for 2.6.25.

This is based on an earlier patch by Tony Breeds.
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Since the PMU is an NMI now, it can come at any time we are only soft
disabled.  We must hard disable around the two places we allow the kernel
stack SLB and r1 to go out of sync.  Otherwise the PMU exception can
force a kernel stack SLB into another slot, which can lead to it
getting evicted, which can lead to a nasty unrecoverable SLB miss
in the exception entry code.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: NOlof Johansson <olof@lixom.net>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

My recent hack to allocate the hash table under 1GB on cell was poorly
tested, *cough*. It turns out on blades with large amounts of memory we
fail to allocate the hash table at all. This is because RTAS has been
instantiated just below 768MB, and 0-x MB are used by the kernel,
leaving no areas that are both large enough and also naturally-aligned.

For the cell IOMMU hack the page tables must be under 2GB, so use that
as the limit instead. This has been tested on real hardware and boots
happily.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

For memory remove, we need to clean up htab mappings for the
section of the memory we are removing.

This implements support for removing htab bolted mappings for pSeries
logical partitions.  Other sub-archs may need to implement similar
functionality for hotplug memory remove to work on them.
Signed-off-by: NBadari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Background: I've implemented 1K/2K page tables for s390.  These sub-page
page tables are required to properly support the s390 virtualization
instruction with KVM.  The SIE instruction requires that the page tables
have 256 page table entries (pte) followed by 256 page status table entries
(pgste).  The pgstes are only required if the process is using the SIE
instruction.  The pgstes are updated by the hardware and by the hypervisor
for a number of reasons, one of them is dirty and reference bit tracking.
To avoid wasting memory the standard pte table allocation should return
1K/2K (31/64 bit) and 2K/4K if the process is using SIE.

Problem: Page size on s390 is 4K, page table size is 1K or 2K.  That means
the s390 version for pte_alloc_one cannot return a pointer to a struct
page.  Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one
cannot return a pointer to a pte either, since that would require more than
32 bit for the return value of pte_alloc_one (and the pte * would not be
accessible since its not kmapped).

Solution: The only solution I found to this dilemma is a new typedef: a
pgtable_t.  For s390 pgtable_t will be a (pte *) - to be introduced with a
later patch.  For everybody else it will be a (struct page *).  The
additional problem with the initialization of the ptl lock and the
NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and
a destructor pgtable_page_dtor.  The page table allocation and free
functions need to call these two whenever a page table page is allocated or
freed.  pmd_populate will get a pgtable_t instead of a struct page pointer.
 To get the pgtable_t back from a pmd entry that has been installed with
pmd_populate a new function pmd_pgtable is added.  It replaces the pmd_page
call in free_pte_range and apply_to_pte_range.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

walk_memory_resource() verifies if there are holes in a given memory
range, by checking against /proc/iomem.  On x86/ia64 system memory is
represented in /proc/iomem.  On powerpc, we don't show system memory as
IO resource in /proc/iomem - instead it's maintained in
/proc/device-tree.

This provides a way for an architecture to provide its own
walk_memory_resource() function.  On powerpc, the memory region is
small (16MB), contiguous and non-overlapping.  So extra checking
against the device-tree is not needed.
Signed-off-by: NBadari Pulavarty <pbadari@us.ibm.com>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Kumar Gala <galak@gate.crashing.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Supply remove_memory() function for 64-bit powerpc.  This is still
not quite complete as it needs to do some more arch-specific stuff,
which will be added in a later patch.
Signed-off-by: NBadari Pulavarty <pbadari@us.ibm.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This patchset adds a flags variable to reserve_bootmem() and uses the
BOOTMEM_EXCLUSIVE flag in crashkernel reservation code to detect collisions
between crashkernel area and already used memory.

This patch:

Change the reserve_bootmem() function to accept a new flag BOOTMEM_EXCLUSIVE.
If that flag is set, the function returns with -EBUSY if the memory already
has been reserved in the past.  This is to avoid conflicts.

Because that code runs before SMP initialisation, there's no race condition
inside reserve_bootmem_core().

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix powerpc build]
Signed-off-by: NBernhard Walle <bwalle@suse.de>
Cc: <linux-arch@vger.kernel.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Here's a dumb simple implementation of fake NUMA nodes for PowerPC.
Fake NUMA nodes can be specified using the following command line
option

numa=fake=<node range>

node range is of the format <range1>,<range2>,...<rangeN>

Each of the rangeX parameters is passed using memparse().  I find the
patch useful for fake NUMA emulation on my simple PowerPC machine.
I've tested it on a numa box with the following arguments

numa=fake=512M
numa=fake=512M,768M
numa=fake=256M,512M mem=512M
numa=fake=1G mem=768M
numa=fake=
without any numa= argument

The other side-effect introduced by this patch is that; in the case
where we don't have NUMA information, we now set a node online after
adding each LMB.  This node could very well be node 0, but in the case
that we enable fake NUMA nodes, when we cross node boundaries, we need
to set the new node online.
Signed-off-by: NBalbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Currently, update_mmu_cache will crash if given a no-access PTE.
There's no need to synchronize dcache/icache unless it's an exec
mapping -- however, due to the existence of older glibc versions that
execute out of a read-but-no-exec page, readability is tested instead.

This assumes no exec-only mappings; if such mappings become supported,
they will need to go through the kmap_atomic() version of
dcache/icache synchronization.

This fixes a bug reported by some users where the kernel would crash
while dumping core on a threaded program.
Signed-off-by: NScott Wood <scottwood@freescale.com>
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

(with Martin Schwidefsky <schwidefsky@de.ibm.com>)

The pgd/pud/pmd/pte page table allocation functions get a mm_struct pointer as
first argument.  The free functions do not get the mm_struct argument.  This
is 1) asymmetrical and 2) to do mm related page table allocations the mm
argument is needed on the free function as well.

[kamalesh@linux.vnet.ibm.com: i386 fix]
[akpm@linux-foundation.org: coding-syle fixes]
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: NKamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In order to support the fixed IOMMU mapping (in a subsequent patch),
we need the hash table to be inside the IOMMUs DMA window.  This is
usually 2G, but let's make sure the hash table is under 1G as that
will satisfy the IOMMU requirements and also means the hash table will
be on node 0.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This reverts commit 5c3f5892,
basically because it changes behaviour even when no fake NUMA
information is specified on the kernel command line.

Firstly, it changes the nid, thus destroying the real NUMA
information.  Secondly, it also changes behaviour in that if a node
ends up with no memory in it because of the memory limit, we used to
set it online and now we don't.

Also, in the non-NUMA case with no fake NUMA information, we do
node_set_online once for each LMB now, whereas previously we only did
it once.  I don't know if that is actually a problem, but it does seem
unnecessary.
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This makes the setjmp/longjmp code used by xmon, generically available
to other code.  It also removes the requirement for debugger hooks to
be only called on 0x300 (data storage) exception.
Signed-off-by: NMichael Neuling <mikey@neuling.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The e500 MMU init code previously assumed KERNELBASE always equaled
PAGE_OFFSET and PHYSICAL_START was 0.  This is useful for kdump
support as well as asymetric multicore.

For the initial kdump support the secondary kernel will run at 32M
but need access to all of memory so we bump the initial TLB up to
64M.  This also matches with the forth coming ePAPR spec.
Signed-off-by: NDale Farnsworth <dale@farnsworth.org>
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>

There were several issues if a memreserve range existed and happened
to be in highmem:

* The bootmem allocator is only aware of lowmem so calling
  reserve_bootmem with a highmem address would cause a BUG_ON
* All highmem pages were provided to the buddy allocator

Added a lmb_is_reserved() api that we now use to determine if a highem
page should continue to be PageReserved or provided to the buddy
allocator.

Also, we incorrectly reported the amount of pages reserved since all
highmem pages are initally marked reserved and we clear the
PageReserved flag as we "free" up the highmem pages.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>

Using 64k pages on 64-bit PowerPC systems makes life difficult for
emulators that are trying to emulate an ISA, such as x86, which use a
smaller page size, since the emulator can no longer use the MMU and
the normal system calls for controlling page protections.  Of course,
the emulator can emulate the MMU by checking and possibly remapping
the address for each memory access in software, but that is pretty
slow.

This provides a facility for such programs to control the access
permissions on individual 4k sub-pages of 64k pages.  The idea is
that the emulator supplies an array of protection masks to apply to a
specified range of virtual addresses.  These masks are applied at the
level where hardware PTEs are inserted into the hardware page table
based on the Linux PTEs, so the Linux PTEs are not affected.  Note
that this new mechanism does not allow any access that would otherwise
be prohibited; it can only prohibit accesses that would otherwise be
allowed.  This new facility is only available on 64-bit PowerPC and
only when the kernel is configured for 64k pages.

The masks are supplied using a new subpage_prot system call, which
takes a starting virtual address and length, and a pointer to an array
of protection masks in memory.  The array has a 32-bit word per 64k
page to be protected; each 32-bit word consists of 16 2-bit fields,
for which 0 allows any access (that is otherwise allowed), 1 prevents
write accesses, and 2 or 3 prevent any access.

Implicit in this is that the regions of the address space that are
protected are switched to use 4k hardware pages rather than 64k
hardware pages (on machines with hardware 64k page support).  In fact
the whole process is switched to use 4k hardware pages when the
subpage_prot system call is used, but this could be improved in future
to switch only the affected segments.

The subpage protection bits are stored in a 3 level tree akin to the
page table tree.  The top level of this tree is stored in a structure
that is appended to the top level of the page table tree, i.e., the
pgd array.  Since it will often only be 32-bit addresses (below 4GB)
that are protected, the pointers to the first four bottom level pages
are also stored in this structure (each bottom level page contains the
protection bits for 1GB of address space), so the protection bits for
addresses below 4GB can be accessed with one fewer loads than those
for higher addresses.
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This adds the hugepagesz boot-time parameter for ppc64.  It lets one
pick the size for huge pages.  The choices available are 64K and 16M
when the base page size is 4k.  It defaults to 16M (previously the
only only choice) if nothing or an invalid choice is specified.

Tested 64K huge pages successfully with the libhugetlbfs 1.2.
Signed-off-by: NJon Tollefson <kniht@linux.vnet.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>