diff mbox series

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

Message ID 1615952410-36895-5-git-send-email-feng.tang@intel.com (mailing list archive)
State New, archived
Headers show
Series Introduced multi-preference mempolicy | expand

Commit Message

Feng Tang March 17, 2021, 3:40 a.m. UTC 
From: Dave Hansen <dave.hansen@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.widawsky@intel.com
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
---
 mm/mempolicy.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

Comments

Michal Hocko April 14, 2021, 12:55 p.m. UTC | #1 
On Wed 17-03-21 11:40:01, Feng Tang wrote:
> From: Dave Hansen <dave.hansen@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.widawsky@intel.com
> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
> Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
> Signed-off-by: Feng Tang <feng.tang@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?

>  	else if (nodes_empty(*nodes))
>  		return -EINVAL;			/*  no allowed nodes */
>  	else
> -		pol->v.preferred_nodes = nodemask_of_node(first_node(*nodes));
> +		pol->v.preferred_nodes = *nodes;
>  	return 0;
>  }
>  
> +static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
> +{
> +	if (nodes) {
> +		/* MPOL_PREFERRED can only take a single node: */
> +		nodemask_t tmp;
> +
> +		if (nodes_empty(*nodes))
> +			return -EINVAL;
> +
> +		tmp = nodemask_of_node(first_node(*nodes));
> +		return mpol_new_preferred_many(pol, &tmp);
> +	}
> +
> +	return mpol_new_preferred_many(pol, NULL);
> +}
> +
>  static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
>  {
>  	if (nodes_empty(*nodes))
> -- 
> 2.7.4
Feng Tang April 19, 2021, 8:49 a.m. UTC | #2 
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.hansen@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.widawsky@intel.com
> > Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
> > Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
> > Signed-off-by: Feng Tang <feng.tang@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
diff mbox series

Patch

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 */
 	else if (nodes_empty(*nodes))
 		return -EINVAL;			/*  no allowed nodes */
 	else
-		pol->v.preferred_nodes = nodemask_of_node(first_node(*nodes));
+		pol->v.preferred_nodes = *nodes;
 	return 0;
 }
 
+static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
+{
+	if (nodes) {
+		/* MPOL_PREFERRED can only take a single node: */
+		nodemask_t tmp;
+
+		if (nodes_empty(*nodes))
+			return -EINVAL;
+
+		tmp = nodemask_of_node(first_node(*nodes));
+		return mpol_new_preferred_many(pol, &tmp);
+	}
+
+	return mpol_new_preferred_many(pol, NULL);
+}
+
 static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
 {
 	if (nodes_empty(*nodes))