Mark Johnston

> > I don't really understand the last parenthetical - could you please elaborate? > > I'd bet that most users of mremap with `MREMAP_FIXED` will call it and not...

> > > > I don't really understand the last parenthetical - could you please elaborate? > > > > > > > > > I'd bet that most users...

> > > > > I don't really understand the last parenthetical - could you please elaborate? > > > > > > > > > > > > I'd...

Perhaps a stupid question, but since the new thread is going to spend all of its time in the kernel(?), why not extend the existing cheri_revoke system call to create...

I've got a simple implementation of a `CHERI_REVOKE_ASYNC` flag. The basic idea is that the cheri_revoke(2) caller will stop threads in the process and revoke from horders before signaling the...

Now that async support in the kernel has landed, most of this is done, but we still update bitmaps and drain quarantine arenas in the critical path. We might still...

Thanks, I'll try to test this in the coming days. Has this produced any results (i.e., kernel crashes) for you? Do you have some evidence that it's sufficient to get...

> I'm not familiar with the FreeBSD VM layer but it looks like the `mmap_mixed` test case manage to trip an assert. > > From the "vm2: serial console" log,...

> > I'm not familiar with the FreeBSD VM layer but it looks like the `mmap_mixed` test case manage to trip an assert. > > From the "vm2: serial console"...

> Given that snmalloc already did what jemalloc now does, I actually think it's more useful for MRS to not do its own bounds by default. No objection from me!...