Re: [PATCH v8 00/17] gfs2: Fix mmap + page fault deadlocks
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: 2021-10-20 20:11:42
Also in:
linux-fsdevel, lkml, ocfs2-devel
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: 2021-10-20 20:11:42
Also in:
linux-fsdevel, lkml, ocfs2-devel
On Wed, Oct 20, 2021 at 6:37 AM Catalin Marinas [off-list ref] wrote:
The atomic "add zero" trick isn't that simple for MTE since the arm64 atomic or exclusive instructions run with kernel privileges and therefore with the kernel tag checking mode.
Are there any instructions that are useful for "probe_user_write()"
kind of thing? We could always just add that as an arch function, with
a fallback to using the futex "add zero" if the architecture doesn't
need anything special.
Although at least for MTE, I think the solution was to do a regular
read, and that checks the tag, and then we could use the gup machinery
for the writability checks.
Linus