linux.git/fs/fs_parser.c, branch v6.12.80

fs_parse: add uid & gid option option parsing helpers

2024-07-02T04:20:49+00:00

Multiple filesystems take uid and gid as options, and the code to
create the ID from an integer and validate it is standard boilerplate
that can be moved into common helper functions, so do that for
consistency and less cut&paste.

This also helps avoid the buggy pattern noted by Seth Jenkins at
https://lore.kernel.org/lkml/CALxfFW4BXhEwxR0Q5LSkg-8Vb4r2MONKCcUCVioehXQKr35eHg@mail.gmail.com/
because uid/gid parsing will fail before any assignment in most
filesystems.

Signed-off-by: Eric Sandeen 
Link: https://lore.kernel.org/r/de859d0a-feb9-473d-a5e2-c195a3d47abb@redhat.com
Signed-off-by: Christian Brauner

__fs_parse: Correct a documentation comment

2024-02-02T12:11:50+00:00

Commit 7f5d38141e30 ("new primitive: __fs_parse()")
taking p_log instead of fs_context.

So, update that comment to refer to p_log instead

Signed-off-by: Chen Hanxiao 
Link: https://lore.kernel.org/r/20240202072042.906-1-chenhx.fnst@fujitsu.com
Signed-off-by: Christian Brauner

ext4: journal_path mount options should follow links

2022-12-01T15:46:54+00:00

Before the commit 461c3af045d3 ("ext4: Change handle_mount_opt() to use
fs_parameter") ext4 mount option journal_path did follow links in the
provided path.

Bring this behavior back by allowing to pass pathwalk flags to
fs_lookup_param().

Fixes: 461c3af045d3 ("ext4: Change handle_mount_opt() to use fs_parameter")
Signed-off-by: Lukas Czerner 
Reviewed-by: Darrick J. Wong 
Link: https://lore.kernel.org/r/20221004135803.32283-1-lczerner@redhat.com
Signed-off-by: Theodore Ts'o 
Cc: stable@kernel.org

fs_parse: allow parameter value to be empty

2021-12-09T19:09:36+00:00

Allow parameter value to be empty by specifying fs_param_can_be_empty
flag.

Signed-off-by: Lukas Czerner 
Cc: Al Viro 
Reviewed-by: Carlos Maiolino 
Link: https://lore.kernel.org/r/20211027141857.33657-2-lczerner@redhat.com
Signed-off-by: Theodore Ts'o

namei: Standardize callers of filename_lookup()

2021-09-07T20:07:47+00:00

filename_lookup() has two variants, one which drops the caller's
reference to filename (filename_lookup), and one which does
not (__filename_lookup). This can be confusing as it's unusual to drop a
caller's reference. Remove filename_lookup, rename __filename_lookup
to filename_lookup, and convert all callers. The cost is a few slightly
longer functions, but the clarity is greater.

[AV: consuming a reference is not at all unusual, actually; look at
e.g. do_mkdirat(), for example.  It's more that we want non-consuming
variant for close relative of that function...]

Link: https://lore.kernel.org/linux-fsdevel/YS+dstZ3xfcLxhoB@zeniv-ca.linux.org.uk/
Cc: Christoph Hellwig 
Cc: Al Viro 
Signed-off-by: Stephen Brennan 
Signed-off-by: Al Viro

vfs: fs_parser: clean up kernel-doc warnings

2021-04-30T18:20:35+00:00

Fix kernel-doc notation function arguments to eliminate two kernel-doc
warnings:

  fs_parser.c:322: warning: Excess function parameter 'name' description in 'validate_constant_table'
  fs_parser.c:367: warning: Function parameter or member 'name' not described in 'fs_validate_description'

Link: https://lkml.kernel.org/r/20210407033743.9701-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap 
Cc: Alexander Viro 
Cc: David Howells 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

fs_parse: mark fs_param_bad_value() as static

2020-10-14T01:38:27+00:00

We found the following warning when build kernel with W=1:

fs/fs_parser.c:192:5: warning: no previous prototype for `fs_param_bad_value' [-Wmissing-prototypes]
int fs_param_bad_value(struct p_log *log, struct fs_parameter *param)
     ^
CC      drivers/usb/gadget/udc/snps_udc_core.o

And no header file define a prototype for this function, so we should mark
it as static.

Signed-off-by: Luo Jiaxing 
Signed-off-by: Andrew Morton 
Link: https://lkml.kernel.org/r/1601293463-25763-1-git-send-email-luojiaxing@huawei.com
Signed-off-by: Linus Torvalds

fs_parse: remove pr_notice() about each validation

2020-04-02T16:35:26+00:00

This notice fills my boot logs with scary-looking asterisks but doesn't
really tell me anything.  Let's just remove it; validation errors are
already reported separately, so this is just a redundant list of
filesystems.

$ dmesg | grep VALIDATE
[    0.306256] *** VALIDATE tmpfs ***
[    0.307422] *** VALIDATE proc ***
[    0.308355] *** VALIDATE cgroup ***
[    0.308741] *** VALIDATE cgroup2 ***
[    0.813256] *** VALIDATE bpf ***
[    0.815272] *** VALIDATE ramfs ***
[    0.815665] *** VALIDATE hugetlbfs ***
[    0.876970] *** VALIDATE nfs ***
[    0.877383] *** VALIDATE nfs4 ***

Signed-off-by: Kees Cook 
Signed-off-by: Andrew Morton 
Reviewed-by: Seth Arnold 
Cc: Alexander Viro 
Link: http://lkml.kernel.org/r/202003061617.A8835CAAF@keescook
Signed-off-by: Linus Torvalds

turn fs_param_is_... into functions

2020-02-07T19:48:38+00:00

Signed-off-by: Al Viro

fs_parse: handle optional arguments sanely

2020-02-07T19:48:37+00:00

Don't bother with "mixed" options that would allow both the
form with and without argument (i.e. both -o foo and -o foo=bar).
Rather than trying to shove both into a single fs_parameter_spec,
allow having with-argument and no-argument specs with the same
name and teach fs_parse to handle that.

There are very few options of that sort, and they are actually
easier to handle that way - callers end up with less postprocessing.

Signed-off-by: Al Viro