[PATCH 03/12] mm/mempolicy: Add MPOL_PREFERRED_MANY for multiple preferred nodes

From: Ben Widawsky
Date: Fri Oct 30 2020 - 15:03:26 EST


From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>

MPOL_PREFERRED honors only a single node set in the nodemask. Add the
bare define for a new mode which will allow more than one.

The patch does all the plumbing without actually adding the new policy
type.

v2:
Plumb most MPOL_PREFERRED_MANY without exposing UAPI (Ben)
Fixes for checkpatch (Ben)

Link: https://lore.kernel.org/r/20200630212517.308045-4-ben.widawsky@xxxxxxxxx
Co-developed-by: Ben Widawsky <ben.widawsky@xxxxxxxxx>
Signed-off-by: Ben Widawsky <ben.widawsky@xxxxxxxxx>
Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
---
mm/mempolicy.c | 46 ++++++++++++++++++++++++++++++++++++++++------
1 file changed, 40 insertions(+), 6 deletions(-)

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ba3bc4f28d27..21a6f80f91a9 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -31,6 +31,9 @@
* but useful to set in a VMA when you have a non default
* process policy.
*
+ * preferred many Try a set of nodes first before normal fallback. This is
+ * similar to preferred without the special case.
+ *
* default Allocate on the local node first, or when on a VMA
* use the process policy. This is what Linux always did
* in a NUMA aware kernel and still does by, ahem, default.
@@ -105,6 +108,8 @@

#include "internal.h"

+#define MPOL_PREFERRED_MANY MPOL_MAX
+
/* Internal flags */
#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */
@@ -175,7 +180,7 @@ struct mempolicy *get_task_policy(struct task_struct *p)
static const struct mempolicy_operations {
int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes);
-} mpol_ops[MPOL_MAX];
+} mpol_ops[MPOL_MAX + 1];

static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
{
@@ -415,7 +420,7 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
mmap_write_unlock(mm);
}

-static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
+static const struct mempolicy_operations mpol_ops[MPOL_MAX + 1] = {
[MPOL_DEFAULT] = {
.rebind = mpol_rebind_default,
},
@@ -432,6 +437,10 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
.rebind = mpol_rebind_nodemask,
},
/* [MPOL_LOCAL] - see mpol_new() */
+ [MPOL_PREFERRED_MANY] = {
+ .create = NULL,
+ .rebind = NULL,
+ },
};

static int migrate_page_add(struct page *page, struct list_head *pagelist,
@@ -914,6 +923,9 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
case MPOL_INTERLEAVE:
*nodes = p->v.nodes;
break;
+ case MPOL_PREFERRED_MANY:
+ *nodes = p->v.preferred_nodes;
+ break;
case MPOL_PREFERRED:
if (!(p->flags & MPOL_F_LOCAL))
*nodes = p->v.preferred_nodes;
@@ -1889,7 +1901,9 @@ 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 ||
+ policy->mode == MPOL_PREFERRED_MANY) &&
+ !(policy->flags & MPOL_F_LOCAL)) {
nd = first_node(policy->v.preferred_nodes);
} else {
/*
@@ -1932,6 +1946,7 @@ unsigned int mempolicy_slab_node(void)
return node;

switch (policy->mode) {
+ case MPOL_PREFERRED_MANY:
case MPOL_PREFERRED:
/*
* handled MPOL_F_LOCAL above
@@ -2066,6 +2081,9 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask)
task_lock(current);
mempolicy = current->mempolicy;
switch (mempolicy->mode) {
+ case MPOL_PREFERRED_MANY:
+ *mask = mempolicy->v.preferred_nodes;
+ break;
case MPOL_PREFERRED:
if (mempolicy->flags & MPOL_F_LOCAL)
nid = numa_node_id();
@@ -2120,6 +2138,9 @@ bool mempolicy_nodemask_intersects(struct task_struct *tsk,
* nodes in mask.
*/
break;
+ case MPOL_PREFERRED_MANY:
+ ret = nodes_intersects(mempolicy->v.preferred_nodes, *mask);
+ break;
case MPOL_BIND:
case MPOL_INTERLEAVE:
ret = nodes_intersects(mempolicy->v.nodes, *mask);
@@ -2204,10 +2225,13 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
* node and don't fall back to other nodes, as the cost of
* remote accesses would likely offset THP benefits.
*
- * If the policy is interleave, or does not allow the current
- * node in its nodemask, we allocate the standard way.
+ * If the policy is interleave or multiple preferred nodes, 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 ||
+ pol->mode == MPOL_PREFERRED_MANY) &&
+ !(pol->flags & MPOL_F_LOCAL))
hpage_node = first_node(pol->v.preferred_nodes);

nmask = policy_nodemask(gfp, pol);
@@ -2343,6 +2367,9 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
case MPOL_BIND:
case MPOL_INTERLEAVE:
return !!nodes_equal(a->v.nodes, b->v.nodes);
+ case MPOL_PREFERRED_MANY:
+ return !!nodes_equal(a->v.preferred_nodes,
+ b->v.preferred_nodes);
case MPOL_PREFERRED:
/* a's ->flags is the same as b's */
if (a->flags & MPOL_F_LOCAL)
@@ -2511,6 +2538,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
polnid = zone_to_nid(z->zone);
break;

+ /* case MPOL_PREFERRED_MANY: */
+
default:
BUG();
}
@@ -2862,6 +2891,7 @@ static const char * const policy_modes[] =
[MPOL_BIND] = "bind",
[MPOL_INTERLEAVE] = "interleave",
[MPOL_LOCAL] = "local",
+ [MPOL_PREFERRED_MANY] = "prefer (many)",
};


@@ -2941,6 +2971,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
if (!nodelist)
err = 0;
goto out;
+ case MPOL_PREFERRED_MANY:
case MPOL_BIND:
/*
* Insist on a nodelist
@@ -3023,6 +3054,9 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
switch (mode) {
case MPOL_DEFAULT:
break;
+ case MPOL_PREFERRED_MANY:
+ WARN_ON(flags & MPOL_F_LOCAL);
+ fallthrough;
case MPOL_PREFERRED:
if (flags & MPOL_F_LOCAL)
mode = MPOL_LOCAL;
--
2.29.2