[RFC Patch v2 4/4] mm/mempolicy: kill MPOL_F_LOCAL bit
From: Feng Tang
Date: Thu May 20 2021 - 04:30:47 EST
Now the only remaining case of a real 'local' policy faked by
'prefer' policy plus MPOL_F_LOCAL bit is:
A valid 'prefer' policy with a valid 'preferred' node is 'rebind'
to a nodemask which doesn't contains the 'preferred' node, then it
will handle allocation with 'local' policy.
Add a new 'MPOL_F_LOCAL_TEMP' bit for this case, and kill the
MPOL_F_LOCAL bit, which could simplify the code much.
Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Signed-off-by: Feng Tang <feng.tang@xxxxxxxxx>
---
include/uapi/linux/mempolicy.h | 1 +
mm/mempolicy.c | 77 +++++++++++++++++++++++-------------------
2 files changed, 43 insertions(+), 35 deletions(-)
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 4832fd0..942844a 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -63,6 +63,7 @@ enum {
#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */
#define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */
#define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */
+#define MPOL_F_LOCAL_TEMP (1 << 5) /* a policy temporarily changed from 'prefer' to 'local' */
/*
* These bit locations are exposed in the vm.zone_reclaim_mode sysctl
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 833ed2d..53a480f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -332,6 +332,22 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
pol->v.nodes = tmp;
}
+static void mpol_rebind_local(struct mempolicy *pol,
+ const nodemask_t *nodes)
+{
+ if (unlikely(pol->flags & MPOL_F_STATIC_NODES)) {
+ int node = first_node(pol->w.user_nodemask);
+
+ BUG_ON(!(pol->flags & MPOL_F_LOCAL_TEMP));
+
+ if (node_isset(node, *nodes)) {
+ pol->v.preferred_node = node;
+ pol->mode = MPOL_PREFERRED;
+ pol->flags &= ~MPOL_F_LOCAL_TEMP;
+ }
+ }
+}
+
static void mpol_rebind_preferred(struct mempolicy *pol,
const nodemask_t *nodes)
{
@@ -342,13 +358,19 @@ static void mpol_rebind_preferred(struct mempolicy *pol,
if (node_isset(node, *nodes)) {
pol->v.preferred_node = node;
- pol->flags &= ~MPOL_F_LOCAL;
- } else
- pol->flags |= MPOL_F_LOCAL;
+ } else {
+ /*
+ * If there is no valid node, change the mode to
+ * MPOL_LOCAL, which will be restored back when
+ * next rebind() see a valid node.
+ */
+ pol->mode = MPOL_LOCAL;
+ pol->flags |= MPOL_F_LOCAL_TEMP;
+ }
} else if (pol->flags & MPOL_F_RELATIVE_NODES) {
mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
pol->v.preferred_node = first_node(tmp);
- } else if (!(pol->flags & MPOL_F_LOCAL)) {
+ } else {
pol->v.preferred_node = node_remap(pol->v.preferred_node,
pol->w.cpuset_mems_allowed,
*nodes);
@@ -367,7 +389,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask)
{
if (!pol)
return;
- if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) &&
+ if (!mpol_store_user_nodemask(pol) &&
nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
return;
@@ -419,7 +441,7 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
.rebind = mpol_rebind_nodemask,
},
[MPOL_LOCAL] = {
- .rebind = mpol_rebind_default,
+ .rebind = mpol_rebind_local,
},
};
@@ -913,10 +935,12 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
case MPOL_INTERLEAVE:
*nodes = p->v.nodes;
break;
+ case MPOL_LOCAL:
+ /* return empty node mask for local allocation */
+ break;
+
case MPOL_PREFERRED:
- if (!(p->flags & MPOL_F_LOCAL))
- node_set(p->v.preferred_node, *nodes);
- /* else return empty node mask for local allocation */
+ node_set(p->v.preferred_node, *nodes);
break;
default:
BUG();
@@ -1880,9 +1904,9 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
/* Return the node id preferred by the given mempolicy, or the given id */
static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd)
{
- if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL))
+ if (policy->mode == MPOL_PREFERRED) {
nd = policy->v.preferred_node;
- else {
+ } else {
/*
* __GFP_THISNODE shouldn't even be used with the bind policy
* because we might easily break the expectation to stay on the
@@ -1919,14 +1943,11 @@ unsigned int mempolicy_slab_node(void)
return node;
policy = current->mempolicy;
- if (!policy || policy->flags & MPOL_F_LOCAL)
+ if (!policy)
return node;
switch (policy->mode) {
case MPOL_PREFERRED:
- /*
- * handled MPOL_F_LOCAL above
- */
return policy->v.preferred_node;
case MPOL_INTERLEAVE:
@@ -2060,16 +2081,13 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask)
mempolicy = current->mempolicy;
switch (mempolicy->mode) {
case MPOL_PREFERRED:
- if (mempolicy->flags & MPOL_F_LOCAL)
- nid = numa_node_id();
- else
- nid = mempolicy->v.preferred_node;
+ nid = mempolicy->v.preferred_node;
init_nodemask_of_node(mask, nid);
break;
case MPOL_BIND:
case MPOL_INTERLEAVE:
- *mask = mempolicy->v.nodes;
+ *mask = mempolicy->v.nodes;
break;
case MPOL_LOCAL:
@@ -2181,7 +2199,7 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
* If the policy is interleave, or does not allow the current
* node in its nodemask, we allocate the standard way.
*/
- if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
+ if (pol->mode == MPOL_PREFERRED)
hpage_node = pol->v.preferred_node;
nmask = policy_nodemask(gfp, pol);
@@ -2317,9 +2335,6 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
case MPOL_INTERLEAVE:
return !!nodes_equal(a->v.nodes, b->v.nodes);
case MPOL_PREFERRED:
- /* a's ->flags is the same as b's */
- if (a->flags & MPOL_F_LOCAL)
- return true;
return a->v.preferred_node == b->v.preferred_node;
case MPOL_LOCAL:
return true;
@@ -2460,10 +2475,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
break;
case MPOL_PREFERRED:
- if (pol->flags & MPOL_F_LOCAL)
- polnid = numa_node_id();
- else
- polnid = pol->v.preferred_node;
+ polnid = pol->v.preferred_node;
break;
case MPOL_LOCAL:
@@ -2834,9 +2846,6 @@ void numa_default_policy(void)
* Parse and format mempolicy from/to strings
*/
-/*
- * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag.
- */
static const char * const policy_modes[] =
{
[MPOL_DEFAULT] = "default",
@@ -3003,12 +3012,10 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
switch (mode) {
case MPOL_DEFAULT:
+ case MPOL_LOCAL:
break;
case MPOL_PREFERRED:
- if (flags & MPOL_F_LOCAL)
- mode = MPOL_LOCAL;
- else
- node_set(pol->v.preferred_node, nodes);
+ node_set(pol->v.preferred_node, nodes);
break;
case MPOL_BIND:
case MPOL_INTERLEAVE:
--
2.7.4