linux.git/fs/fs_parser.c, branch v6.6.131

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

fs_parse: fold fs_parameter_desc/fs_parameter_spec

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

The former contains nothing but a pointer to an array of the latter...

Signed-off-by: Al Viro

fs_parser: remove fs_parameter_description name field

2020-02-07T19:48:36+00:00

Unused now.

Signed-off-by: Eric Sandeen 
Acked-by: David Howells 
Signed-off-by: Al Viro