On 30.01.2023 08:46, Juergen Gross wrote: > On 30.01.23 08:36, Jan Beulich wrote: >> On 30.01.2023 07:37, Juergen Gross wrote: >>> The Xenstore related documentation is currently to be found in >>> docs/misc/9pfs.pandoc, instead of the related header file >>> xen/include/public/io/9pfs.h like for most other paravirtualized >>> device protocols. >>> >>> There is a comment in the header pointing at the document, but the >>> given file name is wrong. Additionally such headers are meant to be >>> copied into consuming projects (Linux kernel, qemu, etc.), so pointing >>> at a doc file in the Xen git repository isn't really helpful for the >>> consumers of the header. >>> >>> This situation is far from ideal, which is already being proved by the >>> fact that neither qemu nor the Linux kernel are implementing the >>> device attach/detach protocol correctly. Additionally the documented >>> Xenstore entries are not matching the reality, as the "tag" Xenstore >>> entry is on the frontend side, not on the backend one. >>> >>> Change that by moving the Xenstore related 9pfs documentation from >>> docs/misc/9pfs.pandoc into xen/include/public/io/9pfs.h while fixing >>> the wrong Xenstore entry detail. >>> >>> Signed-off-by: Juergen Gross <[email protected]> >>> --- >>> docs/misc/9pfs.pandoc | 151 -------------------------------- >>> xen/include/public/io/9pfs.h | 165 ++++++++++++++++++++++++++++++++++- >>> 2 files changed, 164 insertions(+), 152 deletions(-) >>> >>> diff --git a/docs/misc/9pfs.pandoc b/docs/misc/9pfs.pandoc >>> index b034fb5fa6..00f6817a01 100644 >>> --- a/docs/misc/9pfs.pandoc >>> +++ b/docs/misc/9pfs.pandoc >>> @@ -59,157 +59,6 @@ This document does not cover the 9pfs client/server >>> design or >>> implementation, only the transport for it. >>> >>> >>> -## Xenstore >> >> Maybe leave a reference here now pointing at the public header? > > Okay, Would you be fine with: > > ## Configuration > > The frontend and backend are configured via Xenstore. Have a look at > [header] for the detailed Xenstore entries and the connection protocol.
Sure. (Personally I'd use "See [header] ...", but as so often a native speaker might actually point out that one wouldn't word it like this.) Jan
