The Linux kernel’s “new mount API” that has been in the kernel since 2019 and recently made rounds for taking 6+ years to land the man page documentation on it will soon be the the only mount API internally within the kernel. Removing the “old” Linux kernel mount API internals is a candidate for the upcoming Linux 7.0 kernel cycle.
Christian Brauner has queued a patch by Red Hat’s Eric Sandeen to remove the kernel-internal portion of the old mount API code from the kernel.
With the last in-tree file-system driver having been converted to support the new mount API, all of the legacy mount API code for un-converted file-systems can be removed. This is just the kernel-internal code with the legacy mount system call from user-space still being supported as to not break existing user-space software that hasn’t been adapted to the new mount API system calls.
While all in-tree file-systems now support the new mount API, this slated removal will cause issue for any out-of-tree file-system drivers not supporting the new mount API.
The removal is queued via vfs.git’s vfs-7.0.namespace Git branch. This is work that Brauner is queuing for the next kernel cycle — either will be Linux 6.20 or more than likely per Linus Torvalds’ traditions will be bumped to Linux 7.0. The merge window is happening in February upon the v6.19 kernel release.
