Currently DAX page fault locking is racy.

CPU0 (write fault)		CPU1 (read fault)

__dax_fault()			__dax_fault()
  get_block(inode, block, &bh, 0) -> not mapped
				  get_block(inode, block, &bh, 0)
				    -> not mapped
  if (!buffer_mapped(&bh))
    if (vmf->flags & FAULT_FLAG_WRITE)
      get_block(inode, block, &bh, 1) -> allocates blocks
  if (page) -> no
				  if (!buffer_mapped(&bh))
				    if (vmf->flags & FAULT_FLAG_WRITE) {
				    } else {
				      dax_load_hole();
				    }
  dax_insert_mapping()

And we are in a situation where we fail in dax_radix_entry() with -EIO.

Another problem with the current DAX page fault locking is that there is
no race-free way to clear dirty tag in the radix tree. We can always
end up with clean radix tree and dirty data in CPU cache.

We fix the first problem by introducing locking of exceptional radix
tree entries in DAX mappings acting very similarly to page lock and thus
synchronizing properly faults against the same mapping index. The same
lock can later be used to avoid races when clearing radix tree dirty
tag.
Reviewed-by: NNeilBrown <neilb@suse.com>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>

We will use lowest available bit in the radix tree exceptional entry for
locking of the entry. Define it. Also clean up definitions of DAX entry
type bits in DAX exceptional entries to use defined constants instead of
hardcoding numbers and cleanup checking of these bits to not rely on how
other bits in the entry are set.
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>

Currently the handling of huge pages for DAX is racy. For example the
following can happen:

CPU0 (THP write fault)			CPU1 (normal read fault)

__dax_pmd_fault()			__dax_fault()
  get_block(inode, block, &bh, 0) -> not mapped
					get_block(inode, block, &bh, 0)
					  -> not mapped
  if (!buffer_mapped(&bh) && write)
    get_block(inode, block, &bh, 1) -> allocates blocks
  truncate_pagecache_range(inode, lstart, lend);
					dax_load_hole();

This results in data corruption since process on CPU1 won't see changes
into the file done by CPU0.

The race can happen even if two normal faults race however with THP the
situation is even worse because the two faults don't operate on the same
entries in the radix tree and we want to use these entries for
serialization. So make THP support in DAX code depend on CONFIG_BROKEN
for now.
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>

Currently dax_pmd_fault() decides to fill a PMD-sized hole only if
returned buffer has BH_Uptodate set. However that doesn't get set for
any mapping buffer so that branch is actually a dead code. The
BH_Uptodate check doesn't make any sense so just remove it.
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>

The distinction between PAGE_SIZE and PAGE_CACHE_SIZE was removed in

09cbfeaf mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release}
macros

The comments for the above functions described a distinction between
those, that is now redundant, so remove those paragraphs

Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

In the truncate or hole-punch path in dax, we clear out sub-page ranges.
If these sub-page ranges are sector aligned and sized, we can do the
zeroing through the driver instead so that error-clearing is handled
automatically.

For sub-sector ranges, we still have to rely on clear_pmem and have the
possibility of tripping over errors.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jan Kara <jack@suse.cz>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

This allows XFS to perform zeroing using the iomap infrastructure and
avoid buffer heads.
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
[vishal: fix conflicts with dax-error-handling]
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

dax_clear_sectors() cannot handle poisoned blocks.  These must be
zeroed using the BIO interface instead.  Convert ext2 and XFS to use
only sb_issue_zerout().
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NMatthew Wilcox <matthew.r.wilcox@intel.com>
[vishal: Also remove the dax_clear_sectors function entirely]
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

In preparation for consulting a badblocks list in pmem_direct_access(),
teach dax_pmd_fault() to fallback rather than fail immediately upon
encountering an error.  The thought being that reducing the span of the
dax request may avoid the error region.
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

Callers of dax fault handlers must make sure these calls cannot race
with truncate. Thus it is enough to check inode size when entering the
function and we don't have to recheck it again later in the handler.
Note that inode size itself can be decreased while the fault handler
runs but filesystem locking prevents against any radix tree or block
mapping information changes resulting from the truncate and that is what
we really care about.
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

dax_do_io() is calling filemap_write_and_wait() if DIO_LOCKING flags is
set. Presumably this was copied over from direct IO code. However DAX
inodes have no pagecache pages to write so the call is pointless. Remove
it.
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

All the filesystems are now zeroing blocks themselves for DAX IO to avoid
races between dax_io() and dax_fault(). Remove the zeroing code from
dax_io() and add warning to catch the case when somebody unexpectedly
returns new or unwritten buffer.
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

Now that all filesystems zero out blocks allocated for a fault handler,
we can just remove the zeroing from the handler itself. Also add checks
that no filesystem returns to us unwritten or new buffer.
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

Fault handlers currently take complete_unwritten argument to convert
unwritten extents after PTEs are updated. However no filesystem uses
this anymore as the code is racy. Remove the unused argument.
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

These don't belong in radix-tree.c any more than PAGECACHE_TAG_* do.
Let's try to maintain the idea that radix-tree simply implements an
abstract data type.
Acked-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: NMatthew Wilcox <willy@linux.intel.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>

Currently, __dax_fault() does not call get_blocks() callback with create
argument set, when we got back unwritten extent from the initial
get_blocks() call during a write fault. This is because originally
filesystems were supposed to convert unwritten extents to written ones
using complete_unwritten() callback. Later this was abandoned in favor of
using pre-zeroed blocks however the condition whether get_blocks() needs
to be called with create == 1 remained.

Fix the condition so that filesystems are not forced to zero-out and
convert unwritten extents when get_blocks() is called with create == 0
(which introduces unnecessary overhead for read faults and can be
problematic as the filesystem may possibly be read-only).
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NTheodore Ts'o <tytso@mit.edu>

Mostly direct substitution with occasional adjustment or removing
outdated comments.
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: NMichal Hocko <mhocko@suse.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.

This promise never materialized.  And unlikely will.

We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE.  And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.

Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.

Let's stop pretending that pages in page cache are special.  They are
not.

The changes are pretty straight-forward:

 - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};

 - page_cache_get() -> get_page();

 - page_cache_release() -> put_page();

This patch contains automated changes generated with coccinelle using
script below.  For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.

The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.

There are few places in the code where coccinelle didn't reach.  I'll
fix them manually in a separate patch.  Comments and documentation also
will be addressed with the separate patch.

virtual patch

@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT

@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE

@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK

@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)

@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)

@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: NMichal Hocko <mhocko@suse.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

dax_pfn_mkwrite() previously wasn't checking the return value of the
call to dax_radix_entry(), which was a mistake.

Instead, capture this return value and return the appropriate VM_FAULT_
value.
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Previously calls to dax_writeback_mapping_range() for all DAX filesystems
(ext2, ext4 & xfs) were centralized in filemap_write_and_wait_range().

dax_writeback_mapping_range() needs a struct block_device, and it used
to get that from inode->i_sb->s_bdev.  This is correct for normal inodes
mounted on ext2, ext4 and XFS filesystems, but is incorrect for DAX raw
block devices and for XFS real-time files.

Instead, call dax_writeback_mapping_range() directly from the filesystem
->writepages function so that it can supply us with a valid block
device.  This also fixes DAX code to properly flush caches in response
to sync(2).
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

dax_clear_blocks() needs a valid struct block_device and previously it
was using inode->i_sb->s_bdev in all cases.  This is correct for normal
inodes on mounted ext2, ext4 and XFS filesystems, but is incorrect for
DAX raw block devices and for XFS real-time devices.

Instead, rename dax_clear_blocks() to dax_clear_sectors(), and change
its arguments to take a bdev and a sector instead of an inode and a
block.  This better reflects what the function does, and it allows the
filesystem and raw block device code to pass in an appropriate struct
block_device.
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This way we can pass back errors to the file system, and allow for
cleanup required for all direct I/O invocations.

Also allow the ->end_io handlers to return errors on their own, so that
I/O completion errors can be passed on to the callers.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NDave Chinner <david@fromorbit.com>

Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: NJan Kara <jack@suse.cz>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Avoid populating pagecache when the block device is in DAX mode.
Otherwise these page cache entries collide with the fsync/msync
implementation and break data durability guarantees.

Cc: Jan Kara <jack@suse.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Reported-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Tested-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: NMatthew Wilcox <willy@linux.intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Previously in DAX we assumed that calls to get_block() would set
bh.b_bdev, and we would then use that value even in error cases for
debugging.  This caused a NULL pointer dereference in __dax_dbg() which
was fixed by a previous commit, but that commit only changed the one
place where we were hitting an error.

Instead, update dax.c so that we always initialize bh.b_bdev as best we
can based on the information that DAX has.  get_block() may or may not
update to a new value, but this at least lets us get something helpful
from bh.b_bdev for error messages and not have to worry about whether it
was set by get_block() or not.
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reported-by: NJan Kara <jack@suse.cz>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

To properly handle fsync/msync in an efficient way DAX needs to track
dirty pages so it is able to flush them durably to media on demand.

The tracking of dirty pages is done via the radix tree in struct
address_space.  This radix tree is already used by the page writeback
infrastructure for tracking dirty pages associated with an open file,
and it already has support for exceptional (non struct page*) entries.
We build upon these features to add exceptional entries to the radix
tree for DAX dirty PMD or PTE pages at fault time.

[dan.j.williams@intel.com: fix dax_pmd_dbg build warning]
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jan Kara <jack@suse.com>
Cc: Jeff Layton <jlayton@poochiereds.net>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When we get a DAX PMD fault for a write it is possible that there could
be some number of 4k zero pages already present for the same range that
were inserted to service reads from a hole.  These 4k zero pages need to
be unmapped from the VMAs and removed from the struct address_space
radix tree before the real DAX PMD entry can be inserted.

For PTE faults this same use case also exists and is handled by a
combination of unmap_mapping_range() to unmap the VMAs and
delete_from_page_cache() to remove the page from the address_space radix
tree.

For PMD faults we do have a call to unmap_mapping_range() (protected by
a buffer_new() check), but nothing clears out the radix tree entry.  The
buffer_new() check is also incorrect as the current ext4 and XFS
filesystem code will never return a buffer_head with BH_New set, even
when allocating new blocks over a hole.  Instead the filesystem will
zero the blocks manually and return a buffer_head with only BH_Mapped
set.

Fix this situation by removing the buffer_new() check and adding a call
to truncate_inode_pages_range() to clear out the radix tree entries
before we insert the DAX PMD.
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reported-by: NDan Williams <dan.j.williams@intel.com>
Tested-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jeff Layton <jlayton@poochiereds.net>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In __dax_pmd_fault() we currently assume that get_block() will always
set bh.b_bdev and we unconditionally dereference it in __dax_dbg().

This assumption isn't always true - when called for reads of holes
ext4_dax_mmap_get_block() returns a buffer head where bh->b_bdev is
never set.  I hit this BUG while testing the DAX PMD fault path.

Instead, initialize bh.b_bdev before passing bh into get_block().  It is
possible that the filesystem's get_block() will update bh.b_bdev, and
this is fine - we just want to initialize bh.b_bdev to something
reasonable so that the calls to __dax_dbg() work and print something
useful.
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reported-by: NDan Williams <dan.j.williams@intel.com>
Cc: Jan Kara <jack@suse.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

parallel to mutex_{lock,unlock,trylock,is_locked,lock_nested},
inode_foo(inode) being mutex_foo(&inode->i_mutex).

Please, use those for access to ->i_mutex; over the coming cycle
->i_mutex will become rwsem, with ->lookup() done with it held
only shared.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Now that the get_user_pages() path knows how to handle dax-pmd mappings,
remove the protections that disabled dax-pmd support.

Tests available from github.com/pmem/ndctl:

    make TESTS="lib/test-dax.sh lib/test-mmap.sh" check
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

There is a wide gamut of conditions that can trigger the dax pmd path to
fallback to pte mappings.  Ideally we'd have a syscall interface to
determine mapping characteristics after the fact.  In the meantime
provide debug messages.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Suggested-by: NMatthew Wilcox <willy@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Similar to the conversion of vm_insert_mixed() use pfn_t in the
vmf_insert_pfn_pmd() to tag the resulting pte with _PAGE_DEVICE when the
pfn is backed by a devm_memremap_pages() mapping.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Convert the raw unsigned long 'pfn' argument to pfn_t for the purpose of
evaluating the PFN_MAP and PFN_DEV flags.  When both are set it triggers
_PAGE_DEVMAP to be set in the resulting pte.

There are no functional changes to the gpu drivers as a result of this
conversion.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: David Airlie <airlied@linux.ie>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

For the purpose of communicating the optional presence of a 'struct
page' for the pfn returned from ->direct_access(), introduce a type that
encapsulates a page-frame-number plus flags.  These flags contain the
historical "page_link" encoding for a scatterlist entry, but can also
denote "device memory".  Where "device memory" is a set of pfns that are
not part of the kernel's linear mapping by default, but are accessed via
the same memory controller as ram.

The motivation for this new type is large capacity persistent memory
that needs struct page entries in the 'memmap' to support 3rd party DMA
(i.e.  O_DIRECT I/O with a persistent memory source/target).  However,
we also need it in support of maintaining a list of mapped inodes which
need to be unmapped at driver teardown or freeze_bdev() time.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Hansen <dave@sr71.net>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

An infinite loop of PMD faults was observed when attempted to mlock() a
private read-only PMD mmap'd range of a DAX file.

__dax_pmd_fault() simply returns with VM_FAULT_FALLBACK when falling
back to PTE on COW.  However, __handle_mm_fault() returns without
falling back to handle_pte_fault() because a PMD map is present in this
case.

Change __dax_pmd_fault() to split the PMD map, if present, before
returning with VM_FAULT_FALLBACK.
Signed-off-by: NToshi Kani <toshi.kani@hpe.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The DAX implementation needs to protect new calls to ->direct_access()
and usage of its return value against the driver for the underlying
block device being disabled.  Use blk_queue_enter()/blk_queue_exit() to
hold off blk_cleanup_queue() from proceeding, or otherwise fail new
mapping requests if the request_queue is being torn down.

This also introduces blk_dax_ctl to simplify the interface from fs/dax.c
through dax_map_atomic() to bdev_direct_access().

[willy@linux.intel.com: fix read() of a hole]
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Cc: Jan Kara <jack@suse.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If a ->direct_access() implementation ever returns a map count less than
PAGE_SIZE, catch the error in bdev_direct_access().  This simplifies
error checking in upper layers.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Reported-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

dax_clear_blocks is currently performing a cond_resched() after every
PAGE_SIZE memset.  We need not check so frequently, for example md-raid
only calls cond_resched() at stripe granularity.  Also, in preparation
for introducing a dax_map_atomic() operation that temporarily pins a dax
mapping move the call to cond_resched() to the outer loop.

The worst case latency between calls to cond_resched() after this change
is 500us the average latency is 133us.  This is up from a 10us max and
4us average.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NJan Kara <jack@suse.com>
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

To date, we have implemented two I/O usage models for persistent memory,
PMEM (a persistent "ram disk") and DAX (mmap persistent memory into
userspace).  This series adds a third, DAX-GUP, that allows DAX mappings
to be the target of direct-i/o.  It allows userspace to coordinate
DMA/RDMA from/to persistent memory.

The implementation leverages the ZONE_DEVICE mm-zone that went into
4.3-rc1 (also discussed at kernel summit) to flag pages that are owned
and dynamically mapped by a device driver.  The pmem driver, after
mapping a persistent memory range into the system memmap via
devm_memremap_pages(), arranges for DAX to distinguish pfn-only versus
page-backed pmem-pfns via flags in the new pfn_t type.

The DAX code, upon seeing a PFN_DEV+PFN_MAP flagged pfn, flags the
resulting pte(s) inserted into the process page tables with a new
_PAGE_DEVMAP flag.  Later, when get_user_pages() is walking ptes it keys
off _PAGE_DEVMAP to pin the device hosting the page range active.
Finally, get_page() and put_page() are modified to take references
against the device driver established page mapping.

Finally, this need for "struct page" for persistent memory requires
memory capacity to store the memmap array.  Given the memmap array for a
large pool of persistent may exhaust available DRAM introduce a
mechanism to allocate the memmap from persistent memory.  The new
"struct vmem_altmap *" parameter to devm_memremap_pages() enables
arch_add_memory() to use reserved pmem capacity rather than the page
allocator.

This patch (of 25):

Both __dax_pmd_fault, and clear_pmem() were taking special steps to
clear memory a page at a time to take advantage of non-temporal
clear_page() implementations.  However, x86_64 does not use non-temporal
instructions for clear_page(), and arch_clear_pmem() was always
incurring the cost of __arch_wb_cache_pmem().

Clean up the assumption that doing clear_pmem() a page at a time is more
performant.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Reported-by: NDave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jan Kara <jack@suse.com>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

While dax pmd mappings are functional in the nominal path they trigger
kernel crashes in the following paths:

 BUG: unable to handle kernel paging request at ffffea0004098000
 IP: [<ffffffff812362f7>] follow_trans_huge_pmd+0x117/0x3b0
 [..]
 Call Trace:
  [<ffffffff811f6573>] follow_page_mask+0x2d3/0x380
  [<ffffffff811f6708>] __get_user_pages+0xe8/0x6f0
  [<ffffffff811f7045>] get_user_pages_unlocked+0x165/0x1e0
  [<ffffffff8106f5b1>] get_user_pages_fast+0xa1/0x1b0

 kernel BUG at arch/x86/mm/gup.c:131!
 [..]
 Call Trace:
  [<ffffffff8106f34c>] gup_pud_range+0x1bc/0x220
  [<ffffffff8106f634>] get_user_pages_fast+0x124/0x1b0

 BUG: unable to handle kernel paging request at ffffea0004088000
 IP: [<ffffffff81235f49>] copy_huge_pmd+0x159/0x350
 [..]
 Call Trace:
  [<ffffffff811fad3c>] copy_page_range+0x34c/0x9f0
  [<ffffffff810a0daf>] copy_process+0x1b7f/0x1e10
  [<ffffffff810a11c1>] _do_fork+0x91/0x590

All of these paths are interpreting a dax pmd mapping as a transparent
huge page and making the assumption that the pfn is covered by the
memmap, i.e. that the pfn has an associated struct page.  PTE mappings
do not suffer the same fate since they have the _PAGE_SPECIAL flag to
cause the gup path to fault.  We can do something similar for the PMD
path, or otherwise defer pmd support for cases where a struct page is
available.  For now, 4.4-rc and -stable need to disable dax pmd support
by default.

For development the "depends on BROKEN" line can be removed from
CONFIG_FS_DAX_PMD.

Cc: <stable@vger.kernel.org>
Cc: Jan Kara <jack@suse.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>