linux.git/fs/fuse/file.c, branch v6.7

fuse: disable FOPEN_PARALLEL_DIRECT_WRITES with FUSE_DIRECT_IO_ALLOW_MMAP

2023-12-04T09:19:32+00:00

The new fuse init flag FUSE_DIRECT_IO_ALLOW_MMAP breaks assumptions made by
FOPEN_PARALLEL_DIRECT_WRITES and causes test generic/095 to hit
BUG_ON(fi->writectr < 0) assertions in fuse_set_nowrite():

generic/095 5s ...
  kernel BUG at fs/fuse/dir.c:1756!
...
  ? fuse_set_nowrite+0x3d/0xdd
  ? do_raw_spin_unlock+0x88/0x8f
  ? _raw_spin_unlock+0x2d/0x43
  ? fuse_range_is_writeback+0x71/0x84
  fuse_sync_writes+0xf/0x19
  fuse_direct_io+0x167/0x5bd
  fuse_direct_write_iter+0xf0/0x146

Auto disable FOPEN_PARALLEL_DIRECT_WRITES when server negotiated
FUSE_DIRECT_IO_ALLOW_MMAP.

Fixes: e78662e818f9 ("fuse: add a new fuse init flag to relax restrictions in no cache mode")
Cc:  # v6.6
Signed-off-by: Amir Goldstein 
Signed-off-by: Miklos Szeredi

fuse: Rename DIRECT_IO_RELAX to DIRECT_IO_ALLOW_MMAP

2023-12-04T09:14:39+00:00

Although DIRECT_IO_RELAX's initial usage is to allow shared mmap, its
description indicates a purpose of reducing memory footprint. This
may imply that it could be further used to relax other DIRECT_IO
operations in the future.

Replace it with a flag DIRECT_IO_ALLOW_MMAP which does only one thing,
allow shared mmap of DIRECT_IO files while still bypassing the cache
on regular reads and writes.

[Miklos] Also Keep DIRECT_IO_RELAX definition for backward compatibility.

Signed-off-by: Tyler Fanelli 
Fixes: e78662e818f9 ("fuse: add a new fuse init flag to relax restrictions in no cache mode")
Cc:  # v6.6
Signed-off-by: Miklos Szeredi

fuse: write back dirty pages before direct write in direct_io_relax mode

2023-08-16T10:39:24+00:00

In direct_io_relax mode, there can be shared mmaped files and thus dirty
pages in its page cache.  Therefore those dirty pages should be written
back to backend before direct io to avoid data loss.

Signed-off-by: Hao Xu 
Reviewed-by: Jiachen Zhang 
Signed-off-by: Miklos Szeredi

fuse: add a new fuse init flag to relax restrictions in no cache mode

2023-08-16T10:39:16+00:00

FOPEN_DIRECT_IO is usually set by fuse daemon to indicate need of strong
coherency, e.g. network filesystems.  Thus shared mmap is disabled since it
leverages page cache and may write to it, which may cause inconsistence.

But FOPEN_DIRECT_IO can be used not for coherency but to reduce memory
footprint as well, e.g. reduce guest memory usage with virtiofs.
Therefore, add a new fuse init flag FUSE_DIRECT_IO_RELAX to relax
restrictions in that mode, currently, it allows shared mmap.  One thing to
note is to make sure it doesn't break coherency in your use case.

Signed-off-by: Hao Xu 
Signed-off-by: Miklos Szeredi

fuse: invalidate page cache pages before direct write

2023-08-16T10:20:37+00:00

In FOPEN_DIRECT_IO, page cache may still be there for a file since private
mmap is allowed.  Direct write should respect that and invalidate the
corresponding pages so that page cache readers don't get stale data.

Signed-off-by: Hao Xu 
Tested-by: Jiachen Zhang 
Signed-off-by: Miklos Szeredi

Revert "fuse: in fuse_flush only wait if someone wants the return code"

2023-08-14T14:23:06+00:00

This reverts commit 5a8bee63b10f6f2f52f6d22e109a4a147409842a.

Jürg Billeter reports the following regression:

  Since v6.3-rc1 commit 5a8bee63b1 ("fuse: in fuse_flush only wait if
  someone wants the return code") `fput()` is called asynchronously if a
  file is closed as part of a process exiting, i.e., if there was no
  explicit `close()` before exit.

  If the file was open for writing, also `put_write_access()` is called
  asynchronously as part of the async `fput()`.

  If that newly written file is an executable, attempting to `execve()` the
  new file can fail with `ETXTBSY` if it's called after the writer process
  exited but before the async `fput()` has run.

Reported-and-tested-by: "Jürg Billeter" 
Cc:  # v6.3
Link: https://lore.kernel.org/all/4f66cded234462964899f2a661750d6798a57ec0.camel@bitron.ch/
Signed-off-by: Miklos Szeredi

Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

2023-06-28T17:28:11+00:00

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

fuse: use direct_write_fallback

2023-06-09T23:25:54+00:00

Use the generic direct_write_fallback helper instead of duplicating the
logic.

Link: https://lkml.kernel.org/r/20230601145904.1385409-13-hch@lst.de
Signed-off-by: Christoph Hellwig 
Reviewed-by: Damien Le Moal 
Cc: Al Viro 
Cc: Andreas Gruenbacher 
Cc: Anna Schumaker 
Cc: Chao Yu 
Cc: Christian Brauner 
Cc: "Darrick J. Wong" 
Cc: Ilya Dryomov 
Cc: Jaegeuk Kim 
Cc: Jens Axboe 
Cc: Matthew Wilcox 
Cc: Miklos Szeredi 
Cc: Theodore Ts'o 
Cc: Trond Myklebust 
Cc: Xiubo Li 
Cc: Hannes Reinecke 
Cc: Johannes Thumshirn 
Cc: Miklos Szeredi 
Signed-off-by: Andrew Morton

fuse: drop redundant arguments to fuse_perform_write

2023-06-09T23:25:54+00:00

pos is always equal to iocb->ki_pos, and mapping is always equal to
iocb->ki_filp->f_mapping.

Link: https://lkml.kernel.org/r/20230601145904.1385409-12-hch@lst.de
Signed-off-by: Christoph Hellwig 
Reviewed-by: Damien Le Moal 
Reviewed-by: Hannes Reinecke 
Acked-by: Miklos Szeredi 
Cc: Al Viro 
Cc: Andreas Gruenbacher 
Cc: Anna Schumaker 
Cc: Chao Yu 
Cc: Christian Brauner 
Cc: "Darrick J. Wong" 
Cc: Ilya Dryomov 
Cc: Jaegeuk Kim 
Cc: Jens Axboe 
Cc: Johannes Thumshirn 
Cc: Matthew Wilcox 
Cc: Miklos Szeredi 
Cc: Theodore Ts'o 
Cc: Trond Myklebust 
Cc: Xiubo Li 
Signed-off-by: Andrew Morton

fuse: update ki_pos in fuse_perform_write

2023-06-09T23:25:54+00:00

Both callers of fuse_perform_write need to updated ki_pos, move it into
common code.

Link: https://lkml.kernel.org/r/20230601145904.1385409-11-hch@lst.de
Signed-off-by: Christoph Hellwig 
Reviewed-by: Damien Le Moal 
Cc: Al Viro 
Cc: Andreas Gruenbacher 
Cc: Anna Schumaker 
Cc: Chao Yu 
Cc: Christian Brauner 
Cc: "Darrick J. Wong" 
Cc: Hannes Reinecke 
Cc: Ilya Dryomov 
Cc: Jaegeuk Kim 
Cc: Jens Axboe 
Cc: Johannes Thumshirn 
Cc: Matthew Wilcox 
Cc: Miklos Szeredi 
Cc: Miklos Szeredi 
Cc: Theodore Ts'o 
Cc: Trond Myklebust 
Cc: Xiubo Li 
Signed-off-by: Andrew Morton