Re: [PATCH v3 00/24] Convert vfs.txt to vfs.rst

[Al Viro]

On Wed, Apr 03, 2019 at 06:25:20AM +1100, Tobin C. Harding wrote:
> On Tue, Apr 02, 2019 at 05:48:24PM +0100, Al Viro wrote:
> > On Tue, Apr 02, 2019 at 09:49:34AM -0600, Jonathan Corbet wrote:
> > > On Wed, 27 Mar 2019 16:16:53 +1100
> > > "Tobin C. Harding" <tobin@xxxxxxxxxx> wrote:
> > > 
> > > > Hi Al,
> > > > 
> > > > This series converts the VFS file Documentation/filesystems/vfs.txt to
> > > > reStructuredText format.  Please consider taking this series through
> > > > your tree as apposed to Jon's tree because this set makes a fair amount
> > > > of changes to VFS files (and also the VFS tree and docs tree are out of
> > > > sync right now with the recent work by Mauro and Neil).
> > > 
> > > Al, do you have any thoughts on how you want to handle this?  I was about
> > > to apply Jeff Layton's vfs.txt update, but would rather not create
> > > conflicts unnecessarily.  Let me know if you'd like me to pick this work
> > > up.
> > 
> > Frankly, I would rather see that file be eventually replaced by something
> > saner, and I'm not talking about the format.
> 
> Are you able to extrapolate on this comment please?  Is this something
> someone new to the VFS (me) can do with a little nudge in the right
> direction or is this something that needs thorough knowledge of the VFS? 

Put it that way - IMO the best way to do it is not a list of methods with
explanations what each does, but a bunch of per-data structure documents
describing their life cycles.  The fundamental ones for VFS would be
	* inode
	* dentry
	* super_block
	* (vfs)mount
	* file
	* files_struct
Having a list of methods is nice, but those would be better off with short
description along with "see <document> for details, including the locking,
etc."; said short descriptions make little sense without the background...