[PATCH v5 2/3] mm: hugetlb: Move mpol interpretation out of alloc_buddy_hugetlb_folio_with_mpol()

Move memory policy interpretation out of
alloc_buddy_hugetlb_folio_with_mpol() and into alloc_hugetlb_folio() to
separate reading and interpretation of memory policy from actual
allocation.

This will later allow memory policy to be interpreted outside of the
process of allocating a hugetlb folio entirely. This opens doors for other
callers of the HugeTLB folio allocation function, such as guest_memfd,
where memory may not always be mapped and hence may not have an associated
vma.

Introduce struct mempolicy_interpreted to hold all the components of an
interpreted memory policy.

Rename alloc_buddy_hugetlb_folio_with_mpol() to alloc_buddy_hugetlb_folio()
since the function no longer interprets memory policy.

No functional change intended.

Reviewed-by: James Houghton <[email protected]>
Acked-by: Oscar Salvador <[email protected]>
Signed-off-by: Ackerley Tng <[email protected]>
---
 include/uapi/linux/mempolicy.h |  2 +-
 mm/hugetlb.c                   | 54 ++++++++++++++++++++++++++++--------------
 2 files changed, 37 insertions(+), 19 deletions(-)

diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 6c962d866e864..7f6fc9599693b 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -16,7 +16,7 @@
  */
 
 /* Policies */
-enum {
+enum mempolicy_mode {
 	MPOL_DEFAULT,
 	MPOL_PREFERRED,
 	MPOL_BIND,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7985cfd21a03c..3a159de08a0b6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1317,6 +1317,12 @@ static unsigned long available_huge_pages(struct hstate *h)
 	return h->free_huge_pages - h->resv_huge_pages;
 }
 
+struct mempolicy_interpreted {
+	int nid;
+	nodemask_t *nodemask;
+	enum mempolicy_mode mode;
+};
+
 static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address)
@@ -2138,32 +2144,28 @@ static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mas
 	return folio;
 }
 
-/*
- * Use the VMA's mpolicy to allocate a huge page from the buddy.
- */
 static
-struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h,
-		struct vm_area_struct *vma, unsigned long addr)
+struct folio *alloc_buddy_hugetlb_folio(struct hstate *h,
+		gfp_t gfp_mask, struct mempolicy_interpreted *mpoli)
 {
 	struct folio *folio = NULL;
-	struct mempolicy *mpol;
-	gfp_t gfp_mask = htlb_alloc_mask(h);
-	int nid;
-	nodemask_t *nodemask;
+	nodemask_t *nodemask = mpoli->nodemask;
 
-	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
-	if (mpol_is_preferred_many(mpol)) {
+	if (mpoli->mode == MPOL_PREFERRED_MANY) {
 		gfp_t gfp = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
 
-		folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask);
+		folio = alloc_surplus_hugetlb_folio(h, gfp, mpoli->nid,
+						    nodemask);
 
 		/* Fallback to all nodes if page==NULL */
 		nodemask = NULL;
 	}
 
-	if (!folio)
-		folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask);
-	mpol_cond_put(mpol);
+	if (!folio) {
+		folio = alloc_surplus_hugetlb_folio(h, gfp_mask, mpoli->nid,
+						    nodemask);
+	}
+
 	return folio;
 }
 
@@ -2853,7 +2855,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	int ret, idx;
 	struct hugetlb_cgroup *h_cg = NULL;
 	struct hugetlb_cgroup *h_cg_rsvd = NULL;
-	gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL;
+	gfp_t gfp = htlb_alloc_mask(h);
 
 	idx = hstate_index(h);
 
@@ -2926,8 +2928,24 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 		folio = dequeue_hugetlb_folio_vma(h, vma, addr);
 
 	if (!folio) {
+		struct mempolicy_interpreted mpoli;
+		struct mempolicy *mpol;
+		nodemask_t *nodemask;
+		int nid;
+
 		spin_unlock_irq(&hugetlb_lock);
-		folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr);
+		nid = huge_node(vma, addr, gfp, &mpol, &nodemask);
+		mpoli = (struct mempolicy_interpreted){
+			.nid = nid,
+#ifdef CONFIG_NUMA
+			.mode = mpol ? mpol->mode : MPOL_DEFAULT,
+#else
+			.mode = MPOL_DEFAULT,
+#endif
+			.nodemask = nodemask,
+		};
+		folio = alloc_buddy_hugetlb_folio(h, gfp, &mpoli);
+		mpol_cond_put(mpol);
 		if (!folio)
 			goto out_uncharge_cgroup;
 		spin_lock_irq(&hugetlb_lock);
@@ -2983,7 +3001,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 		}
 	}
 
-	ret = mem_cgroup_charge_hugetlb(folio, gfp);
+	ret = mem_cgroup_charge_hugetlb(folio, gfp | __GFP_RETRY_MAYFAIL);
 	/*
 	 * Unconditionally increment NR_HUGETLB here. If it turns out that
 	 * mem_cgroup_charge_hugetlb failed, then immediately free the page and

-- 
2.55.0.508.g3f0d502094-goog