COW and mprotect on non-shared memory

[David Schultz]

On Thu, Aug 07, 2003, Ed L Cashin wrote:
> "Luoqi Chen" <lchen at briontech.com> writes:
> 
> [Ed writes]
> >> That means that if I do this:
> >> 
> >>     for (i = 0; i < n; ++i) {
> >>       assert(!mprotect(p, pgsiz, PROT_NONE));
> >>       assert(!mprotect(p, pgsiz, PROT_READ|PROT_WRITE|PROT_EXEC));
> >>       p[i] = i & 0xff;
> >>     }
> >> 
> >> ... I get n minor page faults!  Pretty amazing, but I guess they
> >> figured nobody does that.  
> 
> ...
> > The first mprotect() removes the physical mapping from the page
> > table, the second mprotect() doesn't do anything because the mapping
> > isn't there. So when the page is accessed, a fault is needed to
> > insert the mapping back to the page table.
> 
> OK, thanks.  I can see that in sys/i386/i386/pmap.c.  It leaves me
> wondering what MAP_ENTRY_COW is for, though.

It's an optimization that makes the map entries and corresponding
vm_objects themselves copy-on-write.  Specifically, when a process
forks, FreeBSD does not allocate new shadow objects immediately.
This is deferred until the object needs to be modified, which is
usually never if the process subsequently calls exec.