Re: [PATCH v4 11/11] mm/mempolicy: extend set_mempolicy2 and mbind2 to support weighted interleave

[Gregory Price]

On Tue, Dec 19, 2023 at 11:07:10AM +0800, Huang, Ying wrote:
> Gregory Price <gourry.memverge@xxxxxxxxx> writes:
> 
> > diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
> > index ec1402dae35b..16fedf966166 100644
> > --- a/include/uapi/linux/mempolicy.h
> > +++ b/include/uapi/linux/mempolicy.h
> > @@ -33,6 +33,7 @@ struct mpol_args {
> >  	__u16 mode_flags;
> >  	__s32 home_node;	/* mbind2: policy home node */
> >  	__aligned_u64 pol_nodes;
> > +	__aligned_u64 il_weights; /* size: pol_maxnodes * sizeof(char) */
> >  	__u64 pol_maxnodes;
> >  	__s32 policy_node;	/* get_mempolicy: policy node info */
> >  };
> 
> You break the ABI you introduced earlier in the patchset.  Although they
> are done within a patchset, I don't think that it's a good idea.  I
> suggest to finalize the ABI in the first place.  Otherwise, people check
> git log will be confused by ABI broken.  This makes it easier to be
> reviewed too.
> 

This is a result of fixing alignment/holes (suggested by Arnd) and my
not dropping policy_node, which I'd originally planned to do.

I figured that whenever we decided to move forward, mempolicy2 and
mbind2 syscalls would end up squashed into a single commit for the
purpose of ensuring the feature goes in as a whole.  I can fix this
though.

~Gregory