hmm_vma_walk->last is supposed to be updated after every write to the
pfns, so that it can be returned by hmm_range_fault(). However, this is
not done consistently. Fortunately nothing checks the return code of
hmm_range_fault() for anything other than error.

More importantly last must be set before returning -EBUSY as it is used to
prevent reading an output pfn as an input flags when the loop restarts.

For clarity and simplicity make hmm_range_fault() return 0 or -ERRNO. Only
set last when returning -EBUSY.

Link: https://lore.kernel.org/r/2-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.comAcked-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Tested-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The pagewalker does not call most ops with NULL vma, those are all routed
to hmm_vma_walk_hole() via ops->pte_hole instead.

Thus hmm_vma_fault() is only called with a NULL vma from
hmm_vma_walk_hole(), so hoist the NULL vma check to there.

Now it is clear that snapshotting with no vma is a HMM_PFN_ERROR as
without a vma we have no path to call hmm_vma_fault().

Link: https://lore.kernel.org/r/20200327200021.29372-10-jgg@ziepe.caReviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Most places that return an error code, like -EFAULT, do not set
HMM_PFN_ERROR, only two places do this.

Resolve this inconsistency by never setting the pfns on an error
exit. This doesn't seem like a worthwhile thing to do anyhow.

If for some reason it becomes important, it makes more sense to directly
return the address of the failing page rather than have the caller scan
for the HMM_PFN_ERROR.

No caller inspects the pnfs output array if hmm_range_fault() fails.

Link: https://lore.kernel.org/r/20200327200021.29372-9-jgg@ziepe.caReviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

In hmm_vma_handle_pte() and hmm_vma_walk_hugetlb_entry() if fault happens
then -EBUSY will be returned and the pfns input flags will have been
destroyed.

For hmm_vma_handle_pte() set HMM_PFN_NONE only on the success returns that
don't otherwise store to pfns.

For hmm_vma_walk_hugetlb_entry() all exit paths already set pfns, so
remove the redundant store.

Fixes: 2aee09d8 ("mm/hmm: change hmm_vma_fault() to allow write fault on page basis")
Link: https://lore.kernel.org/r/20200327200021.29372-8-jgg@ziepe.caReviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

swp_offset() should not be called directly, the wrappers are supposed to
abstract away the encoding of the device_private specific information in
the swap entry.

Link: https://lore.kernel.org/r/20200327200021.29372-7-jgg@ziepe.caReviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Tested-by: NRalph Campbell <rcampbell@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Now that flags are handled on a fine-grained per-page basis this global
flag is redundant and has a confusing overlap with the pfn_flags_mask and
default_flags.

Normalize the HMM_FAULT_SNAPSHOT behavior into one place. Callers needing
the SNAPSHOT behavior should set a pfn_flags_mask and default_flags that
always results in a cleared HMM_PFN_VALID. Then no pages will be faulted,
and HMM_FAULT_SNAPSHOT is not a special flow that overrides the masking
mechanism.

As this is the last flag, also remove the flags argument. If future flags
are needed they can be part of the struct hmm_range function arguments.

Link: https://lore.kernel.org/r/20200327200021.29372-5-jgg@ziepe.caReviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Delete several functions that are never called, fix some desync between
comments and structure content, toss the now out of date top of file
header, and move one function only used by hmm.c into hmm.c

Link: https://lore.kernel.org/r/20200327200021.29372-4-jgg@ziepe.caReviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Using two bools instead of flags return is not necessary and leads to
bugs. Returning a value is easier for the compiler to check and easier to
pass around the code flow.

Convert the two bools into flags and push the change to all callers.

Link: https://lore.kernel.org/r/20200327200021.29372-3-jgg@ziepe.caReviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The checking boils down to some racy check if the pagemap is still
available or not. Instead of checking this, rely entirely on the
notifiers, if a pagemap is destroyed then all pages that belong to it must
be removed from the tables and the notifiers triggered.

Link: https://lore.kernel.org/r/20200327200021.29372-2-jgg@ziepe.caReviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Tested-by: NRalph Campbell <rcampbell@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

hmm_range_fault() will succeed for any kind of device private memory, even
if it doesn't belong to the calling entity.  While nouveau has some crude
checks for that, they are broken because they assume nouveau is the only
user of device private memory.  Fix this by passing in an expected pgmap
owner in the hmm_range_fault structure.

If a device_private page is found and doesn't match the owner then it is
treated as an non-present and non-faultable page.

This prevents a bug in amdgpu, where it doesn't know how to handle
device_private pages, but hmm_range_fault would return them anyhow.

Fixes: 4ef589dc ("mm/hmm/devmem: device memory hotplug using ZONE_DEVICE")
Link: https://lore.kernel.org/r/20200316193216.920734-5-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Remove the HMM_PFN_DEVICE_PRIVATE flag, no driver has ever set this flag
on input, and the only place that uses it on output can be trivially
changed to use is_device_private_page().

This removes the ability to request that device_private pages are faulted
back into system memory.

Link: https://lore.kernel.org/r/20200316193216.920734-4-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

There is no good reason for this split, as it just obsfucates the flow.

Link: https://lore.kernel.org/r/20200316135310.899364-6-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Setting a pfns entry to NONE before returning -EBUSY is a bug that will
cause corruption of the input flags on the next loop.

There is just a single caller using hmm_vma_walk_hole_() for the non-fault
case.  Use hmm_pfns_fill() to fill the whole pfn array with zeroes in the
only caller for the non-fault case and remove the non-fault path from
hmm_vma_walk_hole_(). This avoids setting NONE before returning -EBUSY.

Also rename the function to hmm_vma_fault() to better describe what it
does.

Fixes: 2aee09d8 ("mm/hmm: change hmm_vma_fault() to allow write fault on page basis")
Link: https://lore.kernel.org/r/20200316135310.899364-5-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Remove the rather confusing goto label and just handle the fault case
directly in the branch checking for it.

Link: https://lore.kernel.org/r/20200316135310.899364-4-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The HMM_FAULT_ALLOW_RETRY isn't used anywhere in the tree.  Remove it and
the weird -EAGAIN handling where handle_mm_fault() drops the mmap_sem.

Link: https://lore.kernel.org/r/20200316135310.899364-3-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

pmd_to_hmm_pfn_flags() already checks it and makes the cpu flags 0. If no
fault is requested then the pfns should be returned with the not valid
flags.

It should not unconditionally fault if faulting is not requested.

Fixes: 2aee09d8 ("mm/hmm: change hmm_vma_fault() to allow write fault on page basis")
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Currently if a special PTE is encountered hmm_range_fault() immediately
returns EFAULT and sets the HMM_PFN_SPECIAL error output (which nothing
uses).

EFAULT should only be returned after testing with hmm_pte_need_fault().

Also pte_devmap() and pte_special() are exclusive, and there is no need to
check IS_ENABLED, pte_special() is stubbed out to return false on
unsupported architectures.

Fixes: 992de9a8 ("mm/hmm: allow to mirror vma of a file on a DAX backed filesystem")
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

hmm_range_fault() should never return 0 if the caller requested a valid
page, but the pfns output for that page would be HMM_PFN_ERROR.

hmm_pte_need_fault() must always be called before setting HMM_PFN_ERROR to
detect if the page is in faulting mode or not.

Fix two cases in hmm_vma_walk_pmd() and reorganize some of the duplicated
code.

Fixes: d08faca0 ("mm/hmm: properly handle migration pmd")
Fixes: da4c3c73 ("mm/hmm/mirror: helper to snapshot CPU page table")
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The intention with this code is to determine if the caller required the
pages to be valid, and if so, then take some action to make them valid.
The action varies depending on the page type.

In all cases, if the caller doesn't ask for the page, then
hmm_range_fault() should not return an error.

Revise the implementation to be clearer, and fix some bugs:

 - hmm_pte_need_fault() must always be called before testing fault or
   write_fault otherwise the defaults of false apply and the if()'s don't
   work. This was missed on the is_migration_entry() branch

 - -EFAULT should not be returned unless hmm_pte_need_fault() indicates
   fault is required - ie snapshotting should not fail.

 - For !pte_present() the cpu_flags are always 0, except in the special
   case of is_device_private_entry(), calling pte_to_hmm_pfn_flags() is
   confusing.

Reorganize the flow so that it always follows the pattern of calling
hmm_pte_need_fault() and then checking fault || write_fault.

Fixes: 2aee09d8 ("mm/hmm: change hmm_vma_fault() to allow write fault on page basis")
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

All return paths that do EFAULT must call hmm_range_need_fault() to
determine if the user requires this page to be valid.

If the page cannot be made valid if the user later requires it, due to vma
flags in this case, then the return should be HMM_PFN_ERROR.

Fixes: a3e0d41c ("mm/hmm: improve driver API to work and wait over a range")
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

All success exit paths from the walker functions must set the pfns array.

A migration entry with no required fault is a HMM_PFN_NONE return, just
like the pte case.

Fixes: d08faca0 ("mm/hmm: properly handle migration pmd")
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

This eventually calls into handle_mm_fault() which is a sleeping function.
Release the lock first.

hmm_vma_walk_hole() does not touch the contents of the PUD, so it does not
need the lock.

Fixes: 3afc4236 ("mm: pagewalk: add p4d_entry() and pgd_entry()")
Cc: Steven Price <steven.price@arm.com>
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NSteven Price <steven.price@arm.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Many of the direct returns of error skipped doing the pte_unmap(). All non
zero exit paths must unmap the pte.

The pte_unmap() is split unnaturally like this because some of the error
exit paths trigger a sleep and must release the lock before sleeping.

Fixes: 992de9a8 ("mm/hmm: allow to mirror vma of a file on a DAX backed filesystem")
Fixes: 53f5c3f4 ("mm/hmm: factor out pte and pmd handling to simplify hmm_vma_walk_pmd()")
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The pte_hole() callback is called at multiple levels of the page tables.
Code dumping the kernel page tables needs to know what at what depth the
missing entry is.  Add this is an extra parameter to pte_hole().  When the
depth isn't know (e.g.  processing a vma) then -1 is passed.

The depth that is reported is the actual level where the entry is missing
(ignoring any folding that is in place), i.e.  any levels where
PTRS_PER_P?D is set to 1 are ignored.

Note that depth starts at 0 for a PGD so that PUD/PMD/PTE retain their
natural numbers as levels 2/3/4.

Link: http://lkml.kernel.org/r/20191218162402.45610-16-steven.price@arm.comSigned-off-by: NSteven Price <steven.price@arm.com>
Tested-by: NZong Li <zong.li@sifive.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

pgd_entry() and pud_entry() were removed by commit 0b1fbfe5
("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no
users.  We're about to add users so reintroduce them, along with
p4d_entry() as we now have 5 levels of tables.

Note that commit a00cc7d9 ("mm, x86: add support for PUD-sized
transparent hugepages") already re-added pud_entry() but with different
semantics to the other callbacks.  This commit reverts the semantics back
to match the other callbacks.

To support hmm.c which now uses the new semantics of pud_entry() a new
member ('action') of struct mm_walk is added which allows the callbacks to
either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or
repeat the callback (ACTION_AGAIN).  hmm.c is then updated to call
pud_trans_huge_lock() itself and make use of the splitting/retry logic of
the core code.

After this change pud_entry() is called for all entries, not just
transparent huge pages.

[arnd@arndb.de: fix unused variable warning]
 Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de
Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.comSigned-off-by: NSteven Price <steven.price@arm.com>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zong Li <zong.li@sifive.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

These two functions have never been used since they were added.

Link: https://lore.kernel.org/r/20191113134528.21187-1-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJohn Hubbard <jhubbard@nvidia.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

hmm_range_fault() calls find_vma() and walk_page_range() in a loop.  This
is unnecessary duplication since walk_page_range() calls find_vma() in a
loop already.

Simplify hmm_range_fault() by defining a walk_test() callback function to
filter unhandled vmas.

This also fixes a bug where hmm_range_fault() was not checking start >=
vma->vm_start before checking vma->vm_flags so hmm_range_fault() could
return an error based on the wrong vma for the requested range.

It also fixes a bug when the vma has no read access and the caller did not
request a fault, there shouldn't be any error return code.

Link: https://lore.kernel.org/r/20191104222141.5173-2-rcampbell@nvidia.comSigned-off-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The only two users of this are now converted to use mmu_interval_notifier,
delete all the code and update hmm.rst.

Link: https://lore.kernel.org/r/20191112202231.3856-14-jgg@ziepe.caReviewed-by: NJérôme Glisse <jglisse@redhat.com>
Tested-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

hmm_mirror's handling of ranges does not use a sequence count which
results in this bug:

         CPU0                                   CPU1
                                     hmm_range_wait_until_valid(range)
                                         valid == true
                                     hmm_range_fault(range)
hmm_invalidate_range_start()
   range->valid = false
hmm_invalidate_range_end()
   range->valid = true
                                     hmm_range_valid(range)
                                          valid == true

Where the hmm_range_valid() should not have succeeded.

Adding the required sequence count would make it nearly identical to the
new mmu_interval_notifier. Instead replace the hmm_mirror stuff with
mmu_interval_notifier.

Co-existence of the two APIs is the first step.

Link: https://lore.kernel.org/r/20191112202231.3856-4-jgg@ziepe.caReviewed-by: NJérôme Glisse <jglisse@redhat.com>
Tested-by: NPhilip Yang <Philip.Yang@amd.com>
Tested-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

If a device driver like nouveau tries to use hmm_range_fault() to access
the special shared zero page in system memory, hmm_range_fault() will
return -EFAULT and kill the process.

Allow hmm_range_fault() to return success (0) when the CPU pagetable entry
points to the special shared zero page.

page_to_pfn() and pfn_to_page() are defined on the zero page so just
handle it like any other page.

Link: https://lore.kernel.org/r/20191023195515.13168-3-rcampbell@nvidia.comSigned-off-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: N"Jérôme Glisse" <jglisse@redhat.com>
Acked-by: NDavid Hildenbrand <david@redhat.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The mm_walk structure currently mixed data and code.  Split out the
operations vectors into a new mm_walk_ops structure, and while we are
changing the API also declare the mm_walk structure inside the
walk_page_range and walk_page_vma functions.

Based on patch from Linus Torvalds.

Link: https://lore.kernel.org/r/20190828141955.22210-3-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NThomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: NSteven Price <steven.price@arm.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Add a new header for the two handful of users of the walk_page_range /
walk_page_vma interface instead of polluting all users of mm.h with it.

Link: https://lore.kernel.org/r/20190828141955.22210-2-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NThomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: NSteven Price <steven.price@arm.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Normally, callers to handle_mm_fault() are supposed to check the
vma->vm_flags first. hmm_range_fault() checks for VM_READ but doesn't
check for VM_WRITE if the caller requests a page to be faulted in with
write permission (via the hmm_range.pfns[] value).  If the vma is write
protected, this can result in an infinite loop:

  hmm_range_fault()
    walk_page_range()
      ...
      hmm_vma_walk_hole()
        hmm_vma_walk_hole_()
          hmm_vma_do_fault()
            handle_mm_fault(FAULT_FLAG_WRITE)
            /* returns VM_FAULT_WRITE */
          /* returns -EBUSY */
        /* returns -EBUSY */
      /* returns -EBUSY */
    /* loops on -EBUSY and range->valid */

Prevent this by checking for vma->vm_flags & VM_WRITE before calling
handle_mm_fault().

Link: https://lore.kernel.org/r/20190823221753.2514-3-rcampbell@nvidia.comSigned-off-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Although hmm_range_fault() calls find_vma() to make sure that a vma exists
before calling walk_page_range(), hmm_vma_walk_hole() can still be called
with walk->vma == NULL if the start and end address are not contained
within the vma range.

 hmm_range_fault() /* calls find_vma() but no range check */
  walk_page_range() /* calls find_vma(), sets walk->vma = NULL */
   __walk_page_range()
    walk_pgd_range()
     walk_p4d_range()
      walk_pud_range()
       hmm_vma_walk_hole()
        hmm_vma_walk_hole_()
         hmm_vma_do_fault()
          handle_mm_fault(vma=0)

Link: https://lore.kernel.org/r/20190823221753.2514-2-rcampbell@nvidia.comSigned-off-by: NRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

hmm_range_fault() may return NULL pages because some of the pfns are equal
to HMM_PFN_NONE. This happens randomly under memory pressure. The reason
is during the swapped out page pte path, hmm_vma_handle_pte() doesn't
update the fault variable from cpu_flags, so it failed to call
hmm_vam_do_fault() to swap the page in.

The fix is to call hmm_pte_need_fault() to update fault variable.

Fixes: 74eee180 ("mm/hmm/mirror: device page fault handler")
Link: https://lore.kernel.org/r/20190815205227.7949-1-Philip.Yang@amd.comSigned-off-by: NPhilip Yang <Philip.Yang@amd.com>
Reviewed-by: N"Jérôme Glisse" <jglisse@redhat.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

This is a significant simplification, it eliminates all the remaining
'hmm' stuff in mm_struct, eliminates krefing along the critical notifier
paths, and takes away all the ugly locking and abuse of page_table_lock.

mmu_notifier_get() provides the single struct hmm per struct mm which
eliminates mm->hmm.

It also directly guarantees that no mmu_notifier op callback is callable
while concurrent free is possible, this eliminates all the krefs inside
the mmu_notifier callbacks.

The remaining krefs in the range code were overly cautious, drivers are
already not permitted to free the mirror while a range exists.

Link: https://lore.kernel.org/r/20190806231548.25242-6-jgg@ziepe.caReviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NRalph Campbell <rcampbell@nvidia.com>
Tested-by: NRalph Campbell <rcampbell@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Stub out the whole function and assign NULL to the .hugetlb_entry method
if CONFIG_HUGETLB_PAGE is not set, as the method won't ever be called in
that case.

Link: https://lore.kernel.org/r/20190806160554.14046-13-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Stub out the whole function when CONFIG_TRANSPARENT_HUGEPAGE is not set to
make the function easier to read.

Link: https://lore.kernel.org/r/20190806160554.14046-12-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

We only need the special pud_entry walker if PUD-sized hugepages and pte
mappings are supported, else the common pagewalk code will take care of
the iteration.  Not implementing this callback reduced the amount of code
compiled for non-x86 platforms, and also fixes compile failures with other
architectures when helpers like pud_pfn are not implemented.

Link: https://lore.kernel.org/r/20190806160554.14046-11-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

pte_index is an internal arch helper in various architectures, without
consistent semantics.  Open code that calculation of a PMD index based on
the virtual address instead.

Link: https://lore.kernel.org/r/20190806160554.14046-10-hch@lst.deSigned-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>