Re: [PATCH v4 04/13] mm/mempolicy: allow preferred code to take a nodemask

[Feng Tang]

On Wed, Apr 14, 2021 at 02:55:39PM +0200, Michal Hocko wrote:
> On Wed 17-03-21 11:40:01, Feng Tang wrote:
> > From: Dave Hansen <dave.han...@linux.intel.com>
> > 
> > Create a helper function (mpol_new_preferred_many()) which is usable
> > both by the old, single-node MPOL_PREFERRED and the new
> > MPOL_PREFERRED_MANY.
> > 
> > Enforce the old single-node MPOL_PREFERRED behavior in the "new"
> > version of mpol_new_preferred() which calls mpol_new_preferred_many().
> > 
> > v3:
> >   * fix a stack overflow caused by emty nodemask (Feng)
> > 
> > Link: 
> > https://lore.kernel.org/r/20200630212517.308045-5-ben.widaw...@intel.com
> > Signed-off-by: Dave Hansen <dave.han...@linux.intel.com>
> > Signed-off-by: Ben Widawsky <ben.widaw...@intel.com>
> > Signed-off-by: Feng Tang <feng.t...@intel.com>
> > ---
> >  mm/mempolicy.c | 21 +++++++++++++++++++--
> >  1 file changed, 19 insertions(+), 2 deletions(-)
> > 
> > diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> > index 1228d8e..6fb2cab 100644
> > --- a/mm/mempolicy.c
> > +++ b/mm/mempolicy.c
> > @@ -203,17 +203,34 @@ static int mpol_new_interleave(struct mempolicy *pol, 
> > const nodemask_t *nodes)
> >     return 0;
> >  }
> >  
> > -static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t 
> > *nodes)
> > +static int mpol_new_preferred_many(struct mempolicy *pol,
> > +                              const nodemask_t *nodes)
> >  {
> >     if (!nodes)
> >             pol->flags |= MPOL_F_LOCAL;     /* local allocation */
> 
> Now you have confused me. I thought that MPOL_PREFERRED_MANY for NULL
> nodemask will be disallowed as it is effectively MPOL_PREFERRED aka
> MPOL_F_LOCAL. Or do I misread the code?

I think you are right, with current code, the 'nodes' can't be NULL for
MPOL_PREFERRED_MANY, we'll revisit this.

And I have to admit that I am confused by the current logic for MPOL_PREFERRED,
that the nodemask paramter changes between raw user input, empty nodes and NULL.

Maybe the following patch can make it more clear, as it doesn't play the
NULL nmask trick?

---
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index be160d4..9cabfca 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -200,12 +200,9 @@ static int mpol_new_interleave(struct mempolicy *pol, 
const nodemask_t *nodes)
 
 static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
 {
-       if (!nodes)
-               pol->flags |= MPOL_F_LOCAL;     /* local allocation */
-       else if (nodes_empty(*nodes))
+       if (nodes_empty(*nodes))
                return -EINVAL;                 /*  no allowed nodes */
-       else
-               pol->v.preferred_node = first_node(*nodes);
+       pol->v.preferred_node = first_node(*nodes);
        return 0;
 }
 
@@ -239,9 +236,11 @@ static int mpol_set_nodemask(struct mempolicy *pol,
                  cpuset_current_mems_allowed, node_states[N_MEMORY]);
 
        VM_BUG_ON(!nodes);
-       if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
-               nodes = NULL;   /* explicit local allocation */
-       else {
+       if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) {
+               /* explicit local allocation */
+               pol->flags |= MPOL_F_LOCAL;
+               return 0;
+       } else {
                if (pol->flags & MPOL_F_RELATIVE_NODES)
                        mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1);
                else
@@ -254,10 +253,7 @@ static int mpol_set_nodemask(struct mempolicy *pol,
                                                cpuset_current_mems_allowed;
        }
 
-       if (nodes)
-               ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
-       else
-               ret = mpol_ops[pol->mode].create(pol, NULL);
+       ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
        return ret;
 }


Thanks,
Feng