linux-toradex.git/include/linux/pagemap.h, branch v5.10-rc2

mm/readahead: add page_cache_sync_ra and page_cache_async_ra

2020-10-16T18:11:16+00:00

Reimplement page_cache_sync_readahead() and page_cache_async_readahead()
as wrappers around versions of the function which take a readahead_control
in preparation for making do_sync_mmap_readahead() pass down an RAC
struct.

Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton 
Cc: David Howells 
Cc: Eric Biggers 
Link: https://lkml.kernel.org/r/20200903140844.14194-8-willy@infradead.org
Signed-off-by: Linus Torvalds

mm/readahead: make page_cache_ra_unbounded take a readahead_control

2020-10-16T18:11:16+00:00

Define it in the callers instead of in page_cache_ra_unbounded().

Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton 
Cc: David Howells 
Cc: Eric Biggers 
Link: https://lkml.kernel.org/r/20200903140844.14194-4-willy@infradead.org
Signed-off-by: Linus Torvalds

mm/readahead: add DEFINE_READAHEAD

2020-10-16T18:11:15+00:00

Patch series "Readahead patches for 5.9/5.10".

These are infrastructure for both the THP patchset and for the fscache
rewrite,

For both pieces of infrastructure being build on top of this patchset, we
want the ractl to be available higher in the call-stack.

For David's work, he wants to add the 'critical page' to the ractl so that
he knows which page NEEDS to be brought in from storage, and which ones
are nice-to-have.  We might want something similar in block storage too.
It used to be simple -- the first page was the critical one, but then mmap
added fault-around and so for that usecase, the middle page is the
critical one.  Anyway, I don't have any code to show that yet, we just
know that the lowest point in the callchain where we have that information
is do_sync_mmap_readahead() and so the ractl needs to start its life
there.

For THP, we havew the code that needs it.  It's actually the apex patch to
the series; the one which finally starts to allocate THPs and present them
to consenting filesystems:
http://git.infradead.org/users/willy/pagecache.git/commitdiff/798bcf30ab2eff278caad03a9edca74d2f8ae760

This patch (of 8):

Allow for a more concise definition of a struct readahead_control.

Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton 
Cc: Eric Biggers 
Cc: David Howells 
Link: https://lkml.kernel.org/r/20200903140844.14194-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200903140844.14194-3-willy@infradead.org
Signed-off-by: Linus Torvalds

fs: do not update nr_thps for mappings which support THPs

2020-10-16T18:11:15+00:00

The nr_thps counter is to support THPs in the page cache when the
filesystem doesn't understand THPs.  Eventually it will be removed, but we
should still support filesystems which do not understand THPs yet.  Move
the nr_thp manipulation functions to filemap.h since they're page-cache
specific.

Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton 
Cc: Alexander Viro 
Cc: "Matthew Wilcox (Oracle)" 
Cc: Hugh Dickins 
Cc: Song Liu 
Cc: Rik van Riel 
Cc: "Kirill A . Shutemov" 
Cc: Johannes Weiner 
Cc: Dave Chinner 
Cc: Christoph Hellwig 
Link: https://lkml.kernel.org/r/20200916032717.22917-2-willy@infradead.org
Signed-off-by: Linus Torvalds

fs: add a filesystem flag for THPs

2020-10-16T18:11:15+00:00

The page cache needs to know whether the filesystem supports THPs so that
it doesn't send THPs to filesystems which can't handle them.  Dave Chinner
points out that getting from the page mapping to the filesystem type is
too many steps (mapping->host->i_sb->s_type->fs_flags) so cache that
information in the address space flags.

Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton 
Cc: Alexander Viro 
Cc: "Matthew Wilcox (Oracle)" 
Cc: Hugh Dickins 
Cc: Song Liu 
Cc: Rik van Riel 
Cc: "Kirill A . Shutemov" 
Cc: Johannes Weiner 
Cc: Dave Chinner 
Cc: Christoph Hellwig 
Link: https://lkml.kernel.org/r/20200916032717.22917-1-willy@infradead.org
Signed-off-by: Linus Torvalds

Merge tag 'iomap-5.10-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

2020-10-14T19:23:00+00:00

Pull iomap updates from Darrick Wong:
 "There's not a lot of new stuff going on here -- a little bit of code
  refactoring to make iomap workable with btrfs' fsync locking model,
  cleanups in preparation for adding THP support for filesystems, and
  fixing a data corruption issue for blocksize < pagesize filesystems.

  Summary:

   - Don't WARN_ON weird states that unprivileged users can create.

   - Don't invalidate page cache when direct writes want to fall back to
     buffered.

   - Fix some problems when readahead ios fail.

   - Fix a problem where inline data pages weren't getting flushed
     during an unshare operation.

   - Rework iomap to support arbitrarily many blocks per page in
     preparation to support THP for the page cache.

   - Fix a bug in the blocksize < pagesize buffered io path where we
     could fail to initialize the many-blocks-per-page uptodate bitmap
     correctly when the backing page is actually up to date. This could
     cause us to forget to write out dirty pages.

   - Split out the generic_write_sync at the end of the directio write
     path so that btrfs can drop the inode lock before sync'ing the
     file.

   - Call inode_dio_end before trying to sync the file after a O_DSYNC
     direct write (instead of afterwards) to match the behavior of the
     old directio code"

* tag 'iomap-5.10-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  iomap: Call inode_dio_end() before generic_write_sync()
  iomap: Allow filesystem to call iomap_dio_complete without i_rwsem
  iomap: Set all uptodate bits for an Uptodate page
  iomap: Change calling convention for zeroing
  iomap: Convert iomap_write_end types
  iomap: Convert write_count to write_bytes_pending
  iomap: Convert read_count to read_bytes_pending
  iomap: Support arbitrarily many blocks per page
  iomap: Use bitmap ops to set uptodate bits
  iomap: Use kzalloc to allocate iomap_page
  fs: Introduce i_blocks_per_page
  iomap: Fix misplaced page flushing
  iomap: Use round_down/round_up macros in __iomap_write_begin
  iomap: Mark read blocks uptodate in write_begin
  iomap: Clear page error before beginning a write
  iomap: Fix direct I/O write consistency check
  iomap: fix WARN_ON_ONCE() from unprivileged users

mm: add find_lock_head

2020-10-14T01:38:29+00:00

Add a new FGP_HEAD flag which avoids calling find_subpage() and add a
convenience wrapper for it.

Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton 
Cc: Alexey Dobriyan 
Cc: Chris Wilson 
Cc: Huang Ying 
Cc: Hugh Dickins 
Cc: Jani Nikula 
Cc: Johannes Weiner 
Cc: Matthew Auld 
Cc: William Kucharski 
Link: https://lkml.kernel.org/r/20200910183318.20139-9-willy@infradead.org
Signed-off-by: Linus Torvalds

mm/shmem: return head page from find_lock_entry

2020-10-14T01:38:29+00:00

Convert shmem_getpage_gfp() (the only remaining caller of
find_lock_entry()) to cope with a head page being returned instead of
the subpage for the index.

[willy@infradead.org: fix BUG()s]
  Link https://lore.kernel.org/linux-mm/20200912032042.GA6583@casper.infradead.org/

Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton 
Cc: Alexey Dobriyan 
Cc: Chris Wilson 
Cc: Huang Ying 
Cc: Hugh Dickins 
Cc: Jani Nikula 
Cc: Johannes Weiner 
Cc: Matthew Auld 
Cc: William Kucharski 
Link: https://lkml.kernel.org/r/20200910183318.20139-8-willy@infradead.org
Signed-off-by: Linus Torvalds

i915: use find_lock_page instead of find_lock_entry

2020-10-14T01:38:29+00:00

i915 does not want to see value entries.  Switch it to use
find_lock_page() instead, and remove the export of find_lock_entry().
Move find_lock_entry() and find_get_entry() to mm/internal.h to discourage
any future use.

Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton 
Acked-by: Johannes Weiner 
Cc: Alexey Dobriyan 
Cc: Chris Wilson 
Cc: Huang Ying 
Cc: Hugh Dickins 
Cc: Jani Nikula 
Cc: Matthew Auld 
Cc: William Kucharski 
Link: https://lkml.kernel.org/r/20200910183318.20139-6-willy@infradead.org
Signed-off-by: Linus Torvalds

mm: validate inode in mapping_set_error()

2020-10-11T17:31:10+00:00

The swap address_space doesn't have host. Thus, it makes kernel crash once
swap write meets error. Fix it.

Fixes: 735e4ae5ba28 ("vfs: track per-sb writeback errors and report them to syncfs")
Signed-off-by: Minchan Kim 
Signed-off-by: Andrew Morton 
Acked-by: Jeff Layton 
Cc: Jan Kara 
Cc: Andres Freund 
Cc: Matthew Wilcox 
Cc: Al Viro 
Cc: Christoph Hellwig 
Cc: Dave Chinner 
Cc: David Howells 
Cc: 
Link: https://lkml.kernel.org/r/20201010000650.750063-1-minchan@kernel.org
Signed-off-by: Linus Torvalds