linux.git/fs/fuse/inode.c, branch v6.11

fuse: disable the combination of passthrough and writeback cache

2024-08-29T09:43:01+00:00

Current design and handling of passthrough is without fuse
caching and with that FUSE_WRITEBACK_CACHE is conflicting.

Fixes: 7dc4e97a4f9a ("fuse: introduce FUSE_PASSTHROUGH capability")
Cc: stable@kernel.org # v6.9
Signed-off-by: Bernd Schubert 
Acked-by: Amir Goldstein 
Reviewed-by: Josef Bacik 
Signed-off-by: Miklos Szeredi

fuse: Convert to new uid/gid option parsing helpers

2024-07-03T14:55:11+00:00

Convert to new uid/gid option parsing helpers

Signed-off-by: Eric Sandeen 
Link: https://lore.kernel.org/r/4e1a4efa-4ca5-4358-acee-40efd07c3c44@redhat.com
Reviewed-by: Christian Brauner 
Reviewed-by: Josef Bacik 
Signed-off-by: Christian Brauner

fuse: verify {g,u}id mount options correctly

2024-07-03T14:55:11+00:00

As was done in
0200679fc795 ("tmpfs: verify {g,u}id mount options correctly")
we need to validate that the requested uid and/or gid is representable in
the filesystem's idmapping.

Cribbing from the above commit log,

The contract for {g,u}id mount options and {g,u}id values in general set
from userspace has always been that they are translated according to the
caller's idmapping. In so far, fuse has been doing the correct thing.
But since fuse is mountable in unprivileged contexts it is also
necessary to verify that the resulting {k,g}uid is representable in the
namespace of the superblock.

Fixes: c30da2e981a7 ("fuse: convert to use the new mount API")
Cc: stable@vger.kernel.org # 5.4+
Signed-off-by: Eric Sandeen 
Link: https://lore.kernel.org/r/8f07d45d-c806-484d-a2e3-7a2199df1cd2@redhat.com
Reviewed-by: Christian Brauner 
Reviewed-by: Josef Bacik 
Signed-off-by: Christian Brauner

fuse: fix wrong ff->iomode state changes from parallel dio write

2024-04-15T08:12:03+00:00

There is a confusion with fuse_file_uncached_io_{start,end} interface.
These helpers do two things when called from passthrough open()/release():
1. Take/drop negative refcount of fi->iocachectr (inode uncached io mode)
2. State change ff->iomode IOM_NONE <-> IOM_UNCACHED (file uncached open)

The calls from parallel dio write path need to take a reference on
fi->iocachectr, but they should not be changing ff->iomode state, because
in this case, the fi->iocachectr reference does not stick around until file
release().

Factor out helpers fuse_inode_uncached_io_{start,end}, to be used from
parallel dio write path and rename fuse_file_*cached_io_{start,end} helpers
to fuse_file_*cached_io_{open,release} to clarify the difference.

Fixes: 205c1d802683 ("fuse: allow parallel dio writes with FUSE_DIRECT_IO_ALLOW_MMAP")
Signed-off-by: Amir Goldstein 
Signed-off-by: Miklos Szeredi

Merge tag 'fuse-update-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

2024-03-15T16:47:14+00:00

Pull fuse updates from Miklos Szeredi:

 - Add passthrough mode for regular file I/O.

   This allows performing read and write (also via memory maps) on a
   backing file without incurring the overhead of roundtrips to
   userspace. For now this is only allowed to privileged servers, but
   this limitation will go away in the future (Amir Goldstein)

 - Fix interaction of direct I/O mode with memory maps (Bernd Schubert)

 - Export filesystem tags through sysfs for virtiofs (Stefan Hajnoczi)

 - Allow resending queued requests for server crash recovery (Zhao Chen)

 - Misc fixes and cleanups

* tag 'fuse-update-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse: (38 commits)
  fuse: get rid of ff->readdir.lock
  fuse: remove unneeded lock which protecting update of congestion_threshold
  fuse: Fix missing FOLL_PIN for direct-io
  fuse: remove an unnecessary if statement
  fuse: Track process write operations in both direct and writethrough modes
  fuse: Use the high bit of request ID for indicating resend requests
  fuse: Introduce a new notification type for resend pending requests
  fuse: add support for explicit export disabling
  fuse: __kuid_val/__kgid_val helpers in fuse_fill_attr_from_inode()
  fuse: fix typo for fuse_permission comment
  fuse: Convert fuse_writepage_locked to take a folio
  fuse: Remove fuse_writepage
  virtio_fs: remove duplicate check if queue is broken
  fuse: use FUSE_ROOT_ID in fuse_get_root_inode()
  fuse: don't unhash root
  fuse: fix root lookup with nonzero generation
  fuse: replace remaining make_bad_inode() with fuse_make_bad()
  virtiofs: drop __exit from virtio_fs_sysfs_exit()
  fuse: implement passthrough for mmap
  fuse: implement splice read/write passthrough
  ...

fuse: Use the high bit of request ID for indicating resend requests

2024-03-06T08:56:35+00:00

Some FUSE daemons want to know if the received request is a resend
request. The high bit of the fuse request ID is utilized for indicating
this, enabling the receiver to perform appropriate handling.

The init flag "FUSE_HAS_RESEND" is added to indicate this feature.

Signed-off-by: Zhao Chen 
Signed-off-by: Miklos Szeredi

fuse: add support for explicit export disabling

2024-03-06T08:56:34+00:00

open_by_handle_at(2) can fail with -ESTALE with a valid handle returned
by a previous name_to_handle_at(2) for evicted fuse inodes, which is
especially common when entry_valid_timeout is 0, e.g. when the fuse
daemon is in "cache=none" mode.

The time sequence is like:

	name_to_handle_at(2)	# succeed
	evict fuse inode
	open_by_handle_at(2)	# fail

The root cause is that, with 0 entry_valid_timeout, the dput() called in
name_to_handle_at(2) will trigger iput -> evict(), which will send
FUSE_FORGET to the daemon.  The following open_by_handle_at(2) will send
a new FUSE_LOOKUP request upon inode cache miss since the previous inode
eviction.  Then the fuse daemon may fail the FUSE_LOOKUP request with
-ENOENT as the cached metadata of the requested inode has already been
cleaned up during the previous FUSE_FORGET.  The returned -ENOENT is
treated as -ESTALE when open_by_handle_at(2) returns.

This confuses the application somehow, as open_by_handle_at(2) fails
when the previous name_to_handle_at(2) succeeds.  The returned errno is
also confusing as the requested file is not deleted and already there.
It is reasonable to fail name_to_handle_at(2) early in this case, after
which the application can fallback to open(2) to access files.

Since this issue typically appears when entry_valid_timeout is 0 which
is configured by the fuse daemon, the fuse daemon is the right person to
explicitly disable the export when required.

Also considering FUSE_EXPORT_SUPPORT actually indicates the support for
lookups of "." and "..", and there are existing fuse daemons supporting
export without FUSE_EXPORT_SUPPORT set, for compatibility, we add a new
INIT flag for such purpose.

Reviewed-by: Amir Goldstein 
Signed-off-by: Jingbo Xu 
Signed-off-by: Miklos Szeredi

fuse: __kuid_val/__kgid_val helpers in fuse_fill_attr_from_inode()

2024-03-06T08:56:25+00:00

For the sake of consistency, let's use these helpers to extract
{u,g}id_t values from k{u,g}id_t ones.

There are no functional changes, just to make code cleaner.

Signed-off-by: Alexander Mikhalitsyn 
Reviewed-by: Christian Brauner 
Signed-off-by: Miklos Szeredi

fuse: use FUSE_ROOT_ID in fuse_get_root_inode()

2024-03-05T12:40:43+00:00

...when calling fuse_iget().

Signed-off-by: Miklos Szeredi

fuse: don't unhash root

2024-03-05T12:40:43+00:00

The root inode is assumed to be always hashed.  Do not unhash the root
inode even if it is marked BAD.

Fixes: 5d069dbe8aaf ("fuse: fix bad inode")
Cc:  # v5.11
Signed-off-by: Miklos Szeredi