With address_space_operations missing for device dax, namely the
.set_page_dirty, we hit a kernel warning when running destructive
ndctl unit test: make TESTS=device-dax check

WARNING: CPU: 3 PID: 7380 at fs/buffer.c:581 __set_page_dirty+0xb1/0xc0

Setting address_space_operations to noop_set_page_dirty and
noop_invalidatepage for device dax to prevent fallback to
__set_page_dirty_buffers() and block_invalidatepage() respectively.

Fixes: 2232c638 ("device-dax: Enable page_mapping()")
Acked-by: NJeff Moyer <jmoyer@redhat.com>
Reported-by: NVishal Verma <vishal.l.verma@intel.com>
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

As part of 226ab561 ("device-dax: Convert to vmf_insert_mixed and
vm_fault_t") in 4.19-rc1, 'rc' was not converted to vm_fault_t.  Now
converted.

Link: http://lkml.kernel.org/r/20180830153813.GA26059@jordon-HP-15-Notebook-PCSigned-off-by: NSouptick Joarder <jrdr.linux@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch is reworked from an earlier patch that Dan has posted:
https://patchwork.kernel.org/patch/10131727/

VM_MIXEDMAP is used by dax to direct mm paths like vm_normal_page() that
the memory page it is dealing with is not typical memory from the linear
map.  The get_user_pages_fast() path, since it does not resolve the vma,
is already using {pte,pmd}_devmap() as a stand-in for VM_MIXEDMAP, so we
use that as a VM_MIXEDMAP replacement in some locations.  In the cases
where there is no pte to consult we fallback to using vma_is_dax() to
detect the VM_MIXEDMAP special case.

Now that we have explicit driver pfn_t-flag opt-in/opt-out for
get_user_pages() support for DAX we can stop setting VM_MIXEDMAP.  This
also means we no longer need to worry about safely manipulating vm_flags
in a future where we support dynamically changing the dax mode of a
file.

DAX should also now be supported with madvise_behavior(), vma_merge(),
and copy_page_range().

This patch has been tested against ndctl unit test.  It has also been
tested against xfstests commit: 625515d using fake pmem created by
memmap and no additional issues have been observed.

Link: http://lkml.kernel.org/r/152847720311.55924.16999195879201817653.stgit@djiang5-desk3.ch.intel.comSigned-off-by: NDave Jiang <dave.jiang@intel.com>
Acked-by: NDan Williams <dan.j.williams@intel.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In support of enabling memory_failure() handling for device-dax
mappings, set ->index to the pgoff of the page. The rmap implementation
requires ->index to bound the search through the vma interval tree.

The ->index value is never cleared. There is no possibility for the
page to become associated with another pgoff while the device is
enabled. When the device is disabled the 'struct page' array for the
device is destroyed and ->index is reinitialized to zero.
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NDave Jiang <dave.jiang@intel.com>

In support of enabling memory_failure() handling for device-dax
mappings, set the ->mapping association of pages backing device-dax
mappings. The rmap implementation requires page_mapping() to return the
address_space hosting the vmas that map the page.

The ->mapping pointer is never cleared. There is no possibility for the
page to become associated with another address_space while the device is
enabled. When the device is disabled the 'struct page' array for the
device is destroyed / later reinitialized to zero.
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NDave Jiang <dave.jiang@intel.com>

Use new return type vm_fault_t for fault and huge_fault handler. For
now, this is just documenting that the function returns a VM_FAULT value
rather than an errno.  Once all instances are converted, vm_fault_t will
become a distinct type.

Commit 1c8f4220 ("mm: change return type to vm_fault_t")

Previously vm_insert_mixed() returned an error code which driver mapped into
VM_FAULT_* type. The new function vmf_insert_mixed() will replace this
inefficiency by returning VM_FAULT_* type.
Signed-off-by: NSouptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: NMatthew Wilcox <willy@infradead.org>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NDave Jiang <dave.jiang@intel.com>

This is easily triggered from userspace, so let's ratelimit the
messages.
Signed-off-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

One of the more common cases of allocation size calculations is finding
the size of a structure that has a zero-sized array at the end, along
with memory for some number of elements for that array. For example:

struct foo {
    int stuff;
    void *entry[];
};

instance = kmalloc(sizeof(struct foo) + sizeof(void *) * count, GFP_KERNEL);

Instead of leaving these open-coded and prone to type mistakes, we can
now use the new struct_size() helper:

instance = kmalloc(struct_size(instance, entry, count), GFP_KERNEL);

This patch makes the changes for kmalloc()-family (and kvmalloc()-family)
uses. It was done via automatic conversion with manual review for the
"CHECKME" non-standard cases noted below, using the following Coccinelle
script:

// pkey_cache = kmalloc(sizeof *pkey_cache + tprops->pkey_tbl_len *
//                      sizeof *pkey_cache->table, GFP_KERNEL);
@@
identifier alloc =~ "kmalloc|kzalloc|kvmalloc|kvzalloc";
expression GFP;
identifier VAR, ELEMENT;
expression COUNT;
@@

- alloc(sizeof(*VAR) + COUNT * sizeof(*VAR->ELEMENT), GFP)
+ alloc(struct_size(VAR, ELEMENT, COUNT), GFP)

// mr = kzalloc(sizeof(*mr) + m * sizeof(mr->map[0]), GFP_KERNEL);
@@
identifier alloc =~ "kmalloc|kzalloc|kvmalloc|kvzalloc";
expression GFP;
identifier VAR, ELEMENT;
expression COUNT;
@@

- alloc(sizeof(*VAR) + COUNT * sizeof(VAR->ELEMENT[0]), GFP)
+ alloc(struct_size(VAR, ELEMENT, COUNT), GFP)

// Same pattern, but can't trivially locate the trailing element name,
// or variable name.
@@
identifier alloc =~ "kmalloc|kzalloc|kvmalloc|kvzalloc";
expression GFP;
expression SOMETHING, COUNT, ELEMENT;
@@

- alloc(sizeof(SOMETHING) + COUNT * sizeof(ELEMENT), GFP)
+ alloc(CHECKME_struct_size(&SOMETHING, ELEMENT, COUNT), GFP)
Signed-off-by: NKees Cook <keescook@chromium.org>

MAP_SYNC is a nop for device-dax. Allow MAP_SYNC to succeed on device-dax
to eliminate special casing between device-dax and fs-dax as to when the
flag can be specified. Device-dax users already implicitly assume that they do
not need to call fsync(), and this enables them to explicitly check for this
capability.

Cc: <stable@vger.kernel.org>
Fixes: b6fb293f ("mm: Define MAP_SYNC and VM_SYNC flags")
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Reviewed-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Given that device-dax is making similar page mapping size guarantees as
hugetlbfs, emit the size in smaps and any other kernel path that
requests the mapping size of a vma.

Link: http://lkml.kernel.org/r/151996255287.27922.18397777516059080245.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by: NDan Williams <dan.j.williams@intel.com>
Reported-by: NJane Chu <jane.chu@oracle.com>
Reviewed-by: NAndrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Dynamic debug can be instructed to add the function name to the debug
output using the +f switch, so there is no need for the dax modules to
do it again. If a user decides to add the +f switch for the dax modules'
dynamic debug this results in double prints of the function name.
Reported-by: NJohannes Thumshirn <jthumshirn@suse.de>
Reported-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

The trailing semicolon is an empty statement that does no operation.
Removing it since it doesn't do anything.
Signed-off-by: NLuis de Bethencourt <luisbg@kernel.org>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Similar to how device-dax enforces that the 'address', 'offset', and
'len' parameters to mmap() be aligned to the device's fundamental
alignment, the same constraints apply to munmap().  Implement ->split()
to fail munmap calls that violate the alignment constraint.

Otherwise, we later fail VM_BUG_ON checks in the unmap_page_range() path
with crash signatures of the form:

    vma ffff8800b60c8a88 start 00007f88c0000000 end 00007f88c0e00000
    next           (null) prev           (null) mm ffff8800b61150c0
    prot 8000000000000027 anon_vma           (null) vm_ops ffffffffa0091240
    pgoff 0 file ffff8800b638ef80 private_data           (null)
    flags: 0x380000fb(read|write|shared|mayread|maywrite|mayexec|mayshare|softdirty|mixedmap|hugepage)
    ------------[ cut here ]------------
    kernel BUG at mm/huge_memory.c:2014!
    [..]
    RIP: 0010:__split_huge_pud+0x12a/0x180
    [..]
    Call Trace:
     unmap_page_range+0x245/0xa40
     ? __vma_adjust+0x301/0x990
     unmap_vmas+0x4c/0xa0
     unmap_region+0xae/0x120
     ? __vma_rb_erase+0x11a/0x230
     do_munmap+0x276/0x410
     vm_munmap+0x6a/0xa0
     SyS_munmap+0x1d/0x30

Link: http://lkml.kernel.org/r/151130418681.4029.7118245855057952010.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: dee41079 ("/dev/dax, core: file operations and dax-mmap")
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Reported-by: NJeff Moyer <jmoyer@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fix this build warning:

warning: 'phys' may be used uninitialized in this function
[-Wuninitialized]

As reported here:

https://lkml.org/lkml/2017/10/16/152
http://kisskb.ellerman.id.au/kisskb/buildresult/13181373/log/Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Fix warnings of the form...

     WARNING: CPU: 10 PID: 4983 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x62/0x80
     sysfs: cannot create duplicate filename '/class/dax/dax12.0'
     Call Trace:
      dump_stack+0x63/0x86
      __warn+0xcb/0xf0
      warn_slowpath_fmt+0x5a/0x80
      ? kernfs_path_from_node+0x4f/0x60
      sysfs_warn_dup+0x62/0x80
      sysfs_do_create_link_sd.isra.2+0x97/0xb0
      sysfs_create_link+0x25/0x40
      device_add+0x266/0x630
      devm_create_dax_dev+0x2cf/0x340 [dax]
      dax_pmem_probe+0x1f5/0x26e [dax_pmem]
      nvdimm_bus_probe+0x71/0x120

...by reusing the namespace id for the device-dax instance name.

Now that we have decided that there will never by more than one
device-dax instance per libnvdimm-namespace parent device [1], we can
directly reuse the namepace ids. There are some possible follow-on
cleanups, but those are saved for a later patch to simplify the -stable
backport.

[1]: https://lists.01.org/pipermail/linux-nvdimm/2016-December/008266.html

Fixes: 98a29c39 ("libnvdimm, namespace: allow creation of multiple pmem...")
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: <stable@vger.kernel.org>
Reported-by: NDariusz Dokupil <dariusz.dokupil@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Dan Carpenter reports:

    The patch 7b6be844: "dax: refactor dax-fs into a generic provider
    of 'struct dax_device' instances" from Apr 11, 2017, leads to the
    following static checker warning:

        drivers/dax/device.c:643 devm_create_dev_dax()
        warn: passing zero to 'ERR_PTR'

Fix the case where we inadvertently leak 0 to ERR_PTR() by setting at
every error case, and make it clear that 'count' is never 0.
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Most filesystems currently use mapping_set_error and
filemap_check_errors for setting and reporting/clearing writeback errors
at the mapping level. filemap_check_errors is indirectly called from
most of the filemap_fdatawait_* functions and from
filemap_write_and_wait*. These functions are called from all sorts of
contexts to wait on writeback to finish -- e.g. mostly in fsync, but
also in truncate calls, getattr, etc.

The non-fsync callers are problematic. We should be reporting writeback
errors during fsync, but many places spread over the tree clear out
errors before they can be properly reported, or report errors at
nonsensical times.

If I get -EIO on a stat() call, there is no reason for me to assume that
it is because some previous writeback failed. The fact that it also
clears out the error such that a subsequent fsync returns 0 is a bug,
and a nasty one since that's potentially silent data corruption.

This patch adds a small bit of new infrastructure for setting and
reporting errors during address_space writeback. While the above was my
original impetus for adding this, I think it's also the case that
current fsync semantics are just problematic for userland. Most
applications that call fsync do so to ensure that the data they wrote
has hit the backing store.

In the case where there are multiple writers to the file at the same
time, this is really hard to determine. The first one to call fsync will
see any stored error, and the rest get back 0. The processes with open
fds may not be associated with one another in any way. They could even
be in different containers, so ensuring coordination between all fsync
callers is not really an option.

One way to remedy this would be to track what file descriptor was used
to dirty the file, but that's rather cumbersome and would likely be
slow. However, there is a simpler way to improve the semantics here
without incurring too much overhead.

This set adds an errseq_t to struct address_space, and a corresponding
one is added to struct file. Writeback errors are recorded in the
mapping's errseq_t, and the one in struct file is used as the "since"
value.

This changes the semantics of the Linux fsync implementation such that
applications can now use it to determine whether there were any
writeback errors since fsync(fd) was last called (or since the file was
opened in the case of fsync having never been called).

Note that those writeback errors may have occurred when writing data
that was dirtied via an entirely different fd, but that's the case now
with the current mapping_set_error/filemap_check_error infrastructure.
This will at least prevent you from getting a false report of success.

The new behavior is still consistent with the POSIX spec, and is more
reliable for application developers. This patch just adds some basic
infrastructure for doing this, and ensures that the f_wb_err "cursor"
is properly set when a file is opened. Later patches will change the
existing code to use this new infrastructure for reporting errors at
fsync time.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Reviewed-by: NJan Kara <jack@suse.cz>

Track a set of dax_operations per dax_device that can be set at
alloc_dax() time. These operations will be used to stop the abuse of
block_device_operations for communicating dax capabilities to
filesystems. It will also be used to replace the "pmem api" and move
pmem-specific cache maintenance, and other dax-driver-specific
filesystem-dax operations, to dax device methods. In particular this
allows us to stop abusing __copy_user_nocache(), via memcpy_to_pmem(),
with a driver specific replacement.

This is a standalone introduction of the operations. Follow on patches
convert each dax-driver and teach fs/dax.c to use ->direct_access() from
dax_operations instead of block_device_operations.
Suggested-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

For the current block_device based filesystem-dax path, we need a way
for it to lookup the dax_device associated with a block_device. Add a
'host' property of a dax_device that can be used for this purpose. It is
a free form string, but for a dax_device associated with a block device
it is the bdev name.

This is a stop-gap until filesystems are able to mount on a dax-inode
directly.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

We want dax capable drivers to be able to publish a set of dax
operations [1]. However, we do not want to further abuse block_devices
to advertise these operations. Instead we will attach these operations
to a dax device and add a lookup mechanism to go from block device path
to a dax device. A dax capable driver like pmem or brd is responsible
for registering a dax device, alongside a block device, and then a dax
capable filesystem is responsible for retrieving the dax device by path
name if it wants to call dax_operations.

For now, we refactor the dax pseudo-fs to be a generic facility, rather
than an implementation detail, of the device-dax use case. Where a "dax
device" is just an inode + dax infrastructure, and "Device DAX" is a
mapping service layered on top of that base 'struct dax_device'.
"Filesystem DAX" is then a mapping service that layers a filesystem on
top of that same base device. Filesystem DAX is associated with a
block_device for now, but perhaps directly to a dax device in the
future, or for new pmem-only filesystems.

[1]: https://lkml.org/lkml/2017/1/19/880Suggested-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

In preparation for introducing a struct dax_device type to the kernel
global type namespace, rename dax_dev to dev_dax. A 'dax_device'
instance will be a generic device-driver object for any provider of dax
functionality. A 'dev_dax' object is a device-dax-driver local /
internal instance.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

A couple of minor improvements to the debug output in the fault handlers:

a) Print the region alignment and fault size when we sent a SIGBUS
   because the region alignment is greater than the fault size.
b) Fix the message in the PFN_{DEV|MAP} check.
c) Additionally print the fault size enum value in the huge fault handler.
Signed-off-by: NOliver O'Halloran <oohall@gmail.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

The default case for dax_dev_huge_fault() fault size handling mistakenly
returns when it should unlock. This is not a problem in practice since
the only three possible fault sizes are handled. Going forward, if the
core mm adds a new fault size beyond pte, pmd, or pud device-dax should
abort VM_FAULT_SIGBUS requests not VM_FAULT_FALLBACK since device-dax
guarantees a configured fault granularity for all faults.
Signed-off-by: NPushkar Jambhlekar <pushkar.iit@gmail.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Provide a replacement pgoff_to_phys() that translates an nfit_test
resource (allocated by vmalloc()) to a pfn.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

The following warning triggers with a new unit test that stresses the
device-dax interface.

 ===============================
 [ ERR: suspicious RCU usage.  ]
 4.11.0-rc4+ #1049 Tainted: G           O
 -------------------------------
 ./include/linux/rcupdate.h:521 Illegal context switch in RCU read-side critical section!

 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 0
 2 locks held by fio/9070:
  #0:  (&mm->mmap_sem){++++++}, at: [<ffffffff8d0739d7>] __do_page_fault+0x167/0x4f0
  #1:  (rcu_read_lock){......}, at: [<ffffffffc03fbd02>] dax_dev_huge_fault+0x32/0x620 [dax]

 Call Trace:
  dump_stack+0x86/0xc3
  lockdep_rcu_suspicious+0xd7/0x110
  ___might_sleep+0xac/0x250
  __might_sleep+0x4a/0x80
  __alloc_pages_nodemask+0x23a/0x360
  alloc_pages_current+0xa1/0x1f0
  pte_alloc_one+0x17/0x80
  __pte_alloc+0x1e/0x120
  __get_locked_pte+0x1bf/0x1d0
  insert_pfn.isra.70+0x3a/0x100
  ? lookup_memtype+0xa6/0xd0
  vm_insert_mixed+0x64/0x90
  dax_dev_huge_fault+0x520/0x620 [dax]
  ? dax_dev_huge_fault+0x32/0x620 [dax]
  dax_dev_fault+0x10/0x20 [dax]
  __do_fault+0x1e/0x140
  __handle_mm_fault+0x9af/0x10d0
  handle_mm_fault+0x16d/0x370
  ? handle_mm_fault+0x47/0x370
  __do_page_fault+0x28c/0x4f0
  trace_do_page_fault+0x58/0x2a0
  do_async_page_fault+0x1a/0xa0
  async_page_fault+0x28/0x30

Inserting a page table entry may trigger an allocation while we are
holding a read lock to keep the device instance alive for the duration
of the fault. Use srcu for this keep-alive protection.

Fixes: dee41079 ("/dev/dax, core: file operations and dax-mmap")
Cc: <stable@vger.kernel.org>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Replace the open coded registration of the cdev and dev with the
new device_add_cdev() helper. The helper replaces a common pattern by
taking the proper reference against the parent device and adding both
the cdev and the device.
Signed-off-by: NLogan Gunthorpe <logang@deltatee.com>
Reviewed-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

If device_add() fails, cleanup the cdev. Otherwise, we leak a kobj_map()
with a stale device number.

As Jason points out, there is a small possibility that userspace has
opened and mapped the device in the time between cdev_add() and the
device_add() failure. We need a new kill_dax_dev() helper to invalidate
any established mappings.

Fixes: ba09c01d ("dax: convert to the cdev api")
Cc: <stable@vger.kernel.org>
Reported-by: NJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NLogan Gunthorpe <logang@deltatee.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

The debug output for return the return data of pgoff_to_phys() in the
fault handlers has 'phys' and 'pgoff' incorrectly swapped.
Reported-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Jeff Moyer reports:

    With a device dax alignment of 4KB or 2MB, I get sigbus when running
    the attached fio job file for the current kernel (4.11.0-rc1+).  If
    I specify an alignment of 1GB, it works.

    I turned on debug output, and saw that it was failing in the huge
    fault code.

     dax dax1.0: dax_open
     dax dax1.0: dax_mmap
     dax dax1.0: dax_dev_huge_fault: fio: write (0x7f08f0a00000 -
     dax dax1.0: __dax_dev_pud_fault: phys_to_pgoff(0xffffffffcf60)
     dax dax1.0: dax_release

    fio config for reproduce:
    [global]
    ioengine=dev-dax
    direct=0
    filename=/dev/dax0.0
    bs=2m

    [write]
    rw=write

    [read]
    stonewall
    rw=read

The driver fails to fallback when taking a fault that is larger than
the device alignment, or handling a larger fault when a smaller
mapping is already established. While we could support larger
mappings for a device with a smaller alignment, that change is
too large for the immediate fix. The simplest change is to force
fallback until the fault size matches the alignment.
Reported-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Jeff Moyer reports:

    With a device dax alignment of 4KB or 2MB, I get sigbus when running
    the attached fio job file for the current kernel (4.11.0-rc1+).  If
    I specify an alignment of 1GB, it works.

    I turned on debug output, and saw that it was failing in the huge
    fault code.

     dax dax1.0: dax_open
     dax dax1.0: dax_mmap
     dax dax1.0: dax_dev_huge_fault: fio: write (0x7f08f0a00000 -
     dax dax1.0: __dax_dev_pud_fault: phys_to_pgoff(0xffffffffcf60
     dax dax1.0: dax_release

    fio config for reproduce:
    [global]
    ioengine=dev-dax
    direct=0
    filename=/dev/dax0.0
    bs=2m

    [write]
    rw=write

    [read]
    stonewall
    rw=read

The driver fails to fallback when taking a fault that is larger than
the device alignment, or handling a larger fault when a smaller
mapping is already established. While we could support larger
mappings for a device with a smaller alignment, that change is
too large for the immediate fix. The simplest change is to force
fallback until the fault size matches the alignment.

Fixes: dee41079 ("/dev/dax, core: file operations and dax-mmap")
Cc: <stable@vger.kernel.org>
Reported-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Update files that depend on the magic.h inclusion.
Acked-by: NLinus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>

Since the introduction of FAULT_FLAG_SIZE to the vm_fault flag, it has
been somewhat painful with getting the flags set and removed at the
correct locations.  More than one kernel oops was introduced due to
difficulties of getting the placement correctly.

Remove the flag values and introduce an input parameter to huge_fault
that indicates the size of the page entry.  This makes the code easier
to trace and should avoid the issues we see with the fault flags where
removal of the flag was necessary in the fallback paths.

Link: http://lkml.kernel.org/r/148615748258.43180.1690152053774975329.stgit@djiang5-desk3.ch.intel.comSigned-off-by: NDave Jiang <dave.jiang@intel.com>
Tested-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add transparent huge PUD pages support for device DAX by adding a
pud_fault handler.

Link: http://lkml.kernel.org/r/148545060002.17912.6765687780007547551.stgit@djiang5-desk3.ch.intel.comSigned-off-by: NDave Jiang <dave.jiang@intel.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Patch series "1G transparent hugepage support for device dax", v2.

The following series implements support for 1G trasparent hugepage on
x86 for device dax.  The bulk of the code was written by Mathew Wilcox a
while back supporting transparent 1G hugepage for fs DAX.  I have
forward ported the relevant bits to 4.10-rc.  The current submission has
only the necessary code to support device DAX.

Comments from Dan Williams: So the motivation and intended user of this
functionality mirrors the motivation and users of 1GB page support in
hugetlbfs.  Given expected capacities of persistent memory devices an
in-memory database may want to reduce tlb pressure beyond what they can
already achieve with 2MB mappings of a device-dax file.  We have
customer feedback to that effect as Willy mentioned in his previous
version of these patches [1].

[1]: https://lkml.org/lkml/2016/1/31/52

Comments from Nilesh @ Oracle:

There are applications which have a process model; and if you assume
10,000 processes attempting to mmap all the 6TB memory available on a
server; we are looking at the following:

processes         : 10,000
memory            :    6TB
pte @ 4k page size: 8 bytes / 4K of memory * #processes = 6TB / 4k * 8 * 10000 = 1.5GB * 80000 = 120,000GB
pmd @ 2M page size: 120,000 / 512 = ~240GB
pud @ 1G page size: 240GB / 512 = ~480MB

As you can see with 2M pages, this system will use up an exorbitant
amount of DRAM to hold the page tables; but the 1G pages finally brings
it down to a reasonable level.  Memory sizes will keep increasing; so
this number will keep increasing.

An argument can be made to convert the applications from process model
to thread model, but in the real world that may not be always practical.
Hopefully this helps explain the use case where this is valuable.

This patch (of 3):

In preparation for adding the ability to handle PUD pages, convert
vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault.  The
vm_fault structure is extended to include a union of the different page
table pointers that may be needed, and three flag bits are reserved to
indicate which type of pointer is in the union.

[ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()]
  Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com
[dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path]
  Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com
Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.comSigned-off-by: NMatthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

->fault(), ->page_mkwrite(), and ->pfn_mkwrite() calls do not need to
take a vma and vmf parameter when the vma already resides in vmf.

Remove the vma parameter to simplify things.

[arnd@arndb.de: fix ARM build]
  Link: http://lkml.kernel.org/r/20170125223558.1451224-1-arnd@arndb.de
Link: http://lkml.kernel.org/r/148521301778.19116.10840599906674778980.stgit@djiang5-desk3.ch.intel.comSigned-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jan Kara <jack@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

pmd_fault() and related functions really only need the vmf parameter since
the additional parameters are all included in the vmf struct.  Remove the
additional parameter and simplify pmd_fault() and friends.

Link: http://lkml.kernel.org/r/1484085142-2297-8-git-send-email-ross.zwisler@linux.intel.comSigned-off-by: NDave Jiang <dave.jiang@intel.com>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Instead of passing in multiple parameters in the pmd_fault() handler,
a vmf can be passed in just like a fault() handler. This will simplify
code and remove the need for the actual pmd fault handlers to allocate a
vmf. Related functions are also modified to do the same.

[dave.jiang@intel.com: fix issue with xfs_tests stall when DAX option is off]
  Link: http://lkml.kernel.org/r/148469861071.195597.3619476895250028518.stgit@djiang5-desk3.ch.intel.com
Link: http://lkml.kernel.org/r/1484085142-2297-7-git-send-email-ross.zwisler@linux.intel.comSigned-off-by: NDave Jiang <dave.jiang@intel.com>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

While this information is available by looking at the nvdimm parent
device that may not always be the case when/if we add support for other
memory regions. Tooling should not depend on walking a given ancestor
topology that is not guaranteed by the device's class. For example, a
device-dax instance will always have a dax_region parent, but it may not
always have a libnvdimm "dax" device as a grandparent.
Reported-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Every single user of vmf->virtual_address typed that entry to unsigned
long before doing anything with it so the type of virtual_address does
not really provide us any additional safety.  Just use masked
vmf->address which already has the appropriate type.

Link: http://lkml.kernel.org/r/1479460644-25076-3-git-send-email-jack@suse.czSigned-off-by: NJan Kara <jack@suse.cz>
Acked-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dan Williams <dan.j.williams@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>

Hugh notes in response to commit 4cb19355 "device-dax: fail all
private mapping attempts":

  "I think that is more restrictive than you intended: haven't tried, but I
  believe it rejects a PROT_READ, MAP_SHARED, O_RDONLY fd mmap, leaving no
  way to mmap /dev/dax without write permission to it."

Indeed it does restrict read-only mappings, switch to checking
VM_MAYSHARE, not VM_SHARED.

Cc: <stable@vger.kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Pawel Lebioda <pawel.lebioda@intel.com>
Fixes: 4cb19355 ("device-dax: fail all private mapping attempts")
Reported-by: NHugh Dickins <hughd@google.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>