This free up 11 bits in pte_t. In the later patch we also change
the pte_t format so that we can start supporting migration pte
at pmd level. We now track 4k subpage valid bit as below

If we have _PAGE_COMBO set, we override the _PAGE_F_GIX_SHIFT
and _PAGE_F_SECOND. Together we have 4 bits, each of them
used to indicate whether any of the 4 4k subpage in that group
is valid. ie,

[ group 1 bit ]   [ group 2 bit ]  ..... [ group 4 ]
[ subpage 1 - 4]  [ subpage 5- 8]  ..... [ subpage 13 - 16]

We still track each 4k subpage slot number and secondary hash
information in the second half of pgtable_t. Removing the subpage
tracking have some significant overhead on aim9 and ebizzy benchmark and
to support THP with 4K subpage, we do need a pgtable_t of 4096 bytes.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

We convert them static inline function here as we did with pte_val in
the previous patch
Acked-by: NScott Wood <scottwood@freescale.com>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

map_kernel() doesn't catch all places that create kernel PTEs.  In
particular, vmalloc() calls set_pte_at() directly.  This causes a
crash when booting a non-SMP kernel on e6500.

Move the sync to __set_pte(), to be executed only for kernel addresses.
Signed-off-by: NScott Wood <scottwood@freescale.com>

We have confusing functions to clear pmd, pmd_clear_* and pmd_clear.  Add
_huge_ to pmdp_clear functions so that we are clear that they operate on
hugepage pte.

We don't bother about other functions like pmdp_set_wrprotect,
pmdp_clear_flush_young, because they operate on PTE bits and hence
indicate they are operating on hugepage ptes
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Also move the pmd_trans_huge check to generic code.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Architectures like ppc64 [1] need to do special things while clearing pmd
before a collapse.  For them this operation is largely different from a
normal hugepage pte clear.  Hence add a separate function to clear pmd
before collapse.  After this patch pmdp_* functions operate only on
hugepage pte, and not on regular pmd_t values pointing to page table.

[1] ppc64 needs to invalidate all the normal page pte mappings we already
have inserted in the hardware hash page table.  But before doing that we
need to make sure there are no parallel hash page table insert going on.
So we need to do a kick_all_cpus_sync() before flushing the older hash
table entries.  By moving this to a separate function we capture these
details and mention how it is different from a hugepage pte clear.

This patch is a cleanup and only does code movement for clarity.  There
should not be any change in functionality.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Serialize against find_linux_pte_or_hugepte() which does lock-less
lookup in page tables with local interrupts disabled. For huge pages it
casts pmd_t to pte_t. Since the format of pte_t is different from pmd_t
we want to prevent transit from pmd pointing to page table to pmd
pointing to huge page (and back) while interrupts are disabled.  We
clear pmd to possibly replace it with page table pointer in different
code paths. So make sure we wait for the parallel
find_linux_pte_or_hugepage() to finish.

Without this patch, a find_linux_pte_or_hugepte() running in parallel to
__split_huge_zero_page_pmd() or do_huge_pmd_wp_page_fallback() or
zap_huge_pmd() can run into the above issue. With
__split_huge_zero_page_pmd() and do_huge_pmd_wp_page_fallback() we clear
the hugepage pte before inserting the pmd entry with a regular pgtable
address. Such a clear need to wait for the parallel
find_linux_pte_or_hugepte() to finish.

With zap_huge_pmd(), we can run into issues, with a hugepage pte getting
zapped due to a MADV_DONTNEED while other cpu fault it in as small
pages.
Reported-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

We have a powerpc specific global called mem_init_done which is "set on
boot once kmalloc can be called".

But that's not *quite* true. We set it at the bottom of mem_init(), and
rely on the fact that mm_init() calls kmem_cache_init() immediately
after that, and nothing is running in parallel.

So replace it with the generic and 100% correct slab_is_available().
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Fix the 32-bit code also]
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

We've replaced remap_file_pages(2) implementation with emulation.  Nobody
creates non-linear mapping anymore.
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Convert existing users of pte_numa and friends to the new helper.  Note
that the kernel is broken after this patch is applied until the other page
table modifiers are also altered.  This patch layout is to make review
easier.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Acked-by: NLinus Torvalds <torvalds@linux-foundation.org>
Acked-by: NAneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Tested-by: NSasha Levin <sasha.levin@oracle.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

upatepp can get called for a nohpte fault when we find from the linux
page table that the translation was hashed before. In that case
we are sure that there is no existing translation, hence we could
avoid doing tlbie.

We could possibly race with a parallel fault filling the TLB. But
that should be ok because updatepp is only ever relaxing permissions.
We also look at linux pte permission bits when filling hash pte
permission bits. We also hold the linux pte busy bits while
inserting/updating a hashpte entry, hence a paralle update of
linux pte is not possible. On the other hand mprotect involves
ptep_modify_prot_start which cause a hpte invalidate and not updatepp.

Performance number:
We use randbox_access_bench written by Anton.

Kernel with THP disabled and smaller hash page table size.

    86.60%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_updatepp
     2.10%  random_access_b  random_access_bench              [.] doit
     1.99%  random_access_b  [kernel.kallsyms]                [k] .do_raw_spin_lock
     1.85%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_insert
     1.26%  random_access_b  [kernel.kallsyms]                [k] .native_flush_hash_range
     1.18%  random_access_b  [kernel.kallsyms]                [k] .__delay
     0.69%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_remove
     0.37%  random_access_b  [kernel.kallsyms]                [k] .clear_user_page
     0.34%  random_access_b  [kernel.kallsyms]                [k] .__hash_page_64K
     0.32%  random_access_b  [kernel.kallsyms]                [k] fast_exception_return
     0.30%  random_access_b  [kernel.kallsyms]                [k] .hash_page_mm

With Fix:

    27.54%  random_access_b  random_access_bench              [.] doit
    22.90%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_insert
     5.76%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_remove
     5.20%  random_access_b  [kernel.kallsyms]                [k] fast_exception_return
     5.12%  random_access_b  [kernel.kallsyms]                [k] .__hash_page_64K
     4.80%  random_access_b  [kernel.kallsyms]                [k] .hash_page_mm
     3.31%  random_access_b  [kernel.kallsyms]                [k] data_access_common
     1.84%  random_access_b  [kernel.kallsyms]                [k] .trace_hardirqs_on_caller
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

If we know that user address space has never executed on other cpus
we could use tlbiel.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Rename invalidate_old_hpte to flush_hash_hugepage and use that in
other places.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This patch add documentation and missing accessors.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Lots of places included bootmem.h even when not using bootmem.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Tested-by: NEmil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Now bootmem is gone from powerpc we can remove comments mentioning it.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Tested-by: NEmil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

At the moment we transition from the memblock alloctor to the bootmem
allocator. Gitting rid of the bootmem allocator removes a bunch of
complicated code (most of which I owe the dubious honour of being
responsible for writing).
Signed-off-by: NAnton Blanchard <anton@samba.org>
Tested-by: NEmil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Add tracepoint to track hugepage invalidate. This help us
in debugging difficult to track bugs.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

If we changed base page size of the segment, either via sub_page_protect
or via remap_4k_pfn, we do a demote_segment which doesn't flush the hash
table entries. We do a lazy hash page table flush for all mapped pages
in the demoted segment. This happens when we handle hash page fault for
these pages.

We use _PAGE_COMBO bit along with _PAGE_HASHPTE to indicate whether a
pte is backed by 4K hash pte. If we find _PAGE_COMBO not set on the pte,
that implies that we could possibly have older 64K hash pte entries in
the hash page table and we need to invalidate those entries.

Use _PAGE_COMBO to determine the page size with which we should
invalidate the hash table entries on unmap.

CC: <stable@vger.kernel.org>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The segment identifier and segment size will remain the same in
the loop, So we can compute it outside. We also change the
hugepage_invalidate interface so that we can use it the later patch

CC: <stable@vger.kernel.org>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This silences a section mismatch warning.  early_alloc_pgtable() is
called from map_kernel_page() which cannot be __init, but only when
slab_is_available() returns false which can only happen during early
boot.
Signed-off-by: NScott Wood <scottwood@freescale.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

We have generic code like the one in get_futex_key that assume that
a local_irq_disable prevents a parallel THP split. Support that by
adding a dummy smp call function after setting _PAGE_SPLITTING. Code
paths like get_user_pages_fast still need to check for _PAGE_SPLITTING
after disabling IRQ which indicate that a parallel THP splitting is
ongoing. Now if they don't find _PAGE_SPLITTING set, then we can be
sure that parallel split will now block in pmdp_splitting flush
until we enables IRQ
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

pte_update() is a powerpc-ism used to change the bits of a PTE
when the access permission is being restricted (a flush is
potentially needed).

It uses atomic operations on when needed and handles the hash
synchronization on hash based processors.

It is currently only used to clear PTE bits and so the current
implementation doesn't provide a way to also set PTE bits.

The new _PAGE_NUMA bit, when set, is actually restricting access
so it must use that function too, so this change adds the ability
for pte_update() to also set bits.

We will use this later to set the _PAGE_NUMA bit.
Acked-by: NMel Gorman <mgorman@suse.de>
Acked-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

None of these files are actually using any __init type directives
and hence don't need to include <linux/init.h>.  Most are just a
left over from __devinit and __cpuinit removal, or simply due to
code getting copied from one driver to the next.

The one instance where we add an include for init.h covers off
a case where that file was implicitly getting it from another
header which itself didn't need it.
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

There is no barrier between something like ioremap() writing to
a PTE, and returning the value to a caller that may then store the
pointer in a place that is visible to other CPUs.  Such callers
generally don't perform barriers of their own.

Even if callers of ioremap() and similar things did use barriers,
the most logical choise would be smp_wmb(), which is not
architecturally sufficient when BookE hardware tablewalk is used.  A
full sync is specified by the architecture.

For userspace mappings, OTOH, we generally already have an lwsync due
to locking, and if we occasionally take a spurious fault due to not
having a full sync with hardware tablewalk, it will not be fatal
because we will retry rather than oops.
Signed-off-by: NScott Wood <scottwood@freescale.com>

We want to make sure we don't use these function when updating a pte
or pmd entry that have a valid hpte entry, because these functions
don't invalidate them. So limit the check to _PAGE_PRESENT bit.
Numafault core changes use these functions for updating _PAGE_NUMA bits.
That should be ok because when _PAGE_NUMA is set we can be sure that
hpte entries are not present.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Hugepage invalidate involves invalidating multiple hpte entries.
Optimize the operation using H_BULK_REMOVE on lpar platforms.
On native, reduce the number of tlb flush.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

We enable only if the we support 16MB page size.
Reviewed-by: NDavid Gibson <dwg@au1.ibm.com>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

We now have pmd entries covering 16MB range and the PMD table double its original size.
We use the second half of the PMD table to deposit the pgtable (PTE page).
The depoisted PTE page is further used to track the HPTE information. The information
include [ secondary group | 3 bit hidx | valid ]. We use one byte per each HPTE entry.
With 16MB hugepage and 64K HPTE we need 256 entries and with 4K HPTE we need
4096 entries. Both will fit in a 4K PTE page. On hugepage invalidate we need to walk
the PTE page and invalidate all valid HPTEs.

This patch implements necessary arch specific functions for THP support and also
hugepage invalidate logic. These PMD related functions are intentionally kept
similar to their PTE counter-part.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

We allocate one page for the last level of linux page table. With THP and
large page size of 16MB, that would mean we are wasting large part
of that page. To map 16MB area, we only need a PTE space of 2K with 64K
page size. This patch reduce the space wastage by sharing the page
allocated for the last level of linux page table with multiple pmd
entries. We call these smaller chunks PTE page fragments and allocated
page, PTE page.

In order to support systems which doesn't have 64K HPTE support, we also
add another 2K to PTE page fragment. The second half of the PTE fragments
is used for storing slot and secondary bit information of an HPTE. With this
we now have a 4K PTE fragment.

We use a simple approach to share the PTE page. On allocation, we bump the
PTE page refcount to 16 and share the PTE page with the next 16 pte alloc
request. This should help in the node locality of the PTE page fragment,
assuming that the immediate pte alloc request will mostly come from the
same NUMA node. We don't try to reuse the freed PTE page fragment. Hence
we could be waisting some space.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Now we use ESID_BITS of kernel address to build proto vsid. So rename
USER_ESIT_BITS to ESID_BITS
Acked-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org> [v3.8]

slice array size and slice mask size depend on PGTABLE_RANGE.
Reviewed-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

It's empty now, apart from other includes.

Fixup a few files that were getting things via this header.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Disintegrate asm/system.h for PowerPC.
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
cc: linuxppc-dev@lists.ozlabs.org

With module.h being implicitly everywhere via device.h, the absence
of explicitly including something for EXPORT_SYMBOL went unnoticed.
Since we are heading to fix things up and clean module.h from the
device.h file, we need to explicitly include these files now.
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

We have a confusing number of ioremap functions. Make things just a
bit simpler by merging ioremap_flags and ioremap_prot.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Add ioremap_wc so drivers can request write combining on kernel
mappings.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The vmalloc code can track the physical address of a vma, when the
vma is used for ioremap, if set it is displayed in /proc/vmallocinfo.

Because get_vm_area_caller() doesn't know it's being called for
ioremap() it's up to the arch code to set the phys_addr. A bunch
of other arch's do this, I'm not sure why powerpc doesn't?
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>