linux-kernel - [RFC PATCH 05/39] mm: hugetlb: Refactor alloc_buddy_hugetlb_folio_with_mpol() to interpret mempolicy instead of vma

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1778a7324a1242fa907981576ebd69716a94d778.1726009989.git.ackerleytng@google.com>
Date: Tue, 10 Sep 2024 23:43:36 +0000
From: Ackerley Tng <ackerleytng@...gle.com>
To: tabba@...gle.com, quic_eberman@...cinc.com, roypat@...zon.co.uk, 
	jgg@...dia.com, peterx@...hat.com, david@...hat.com, rientjes@...gle.com, 
	fvdl@...gle.com, jthoughton@...gle.com, seanjc@...gle.com, 
	pbonzini@...hat.com, zhiquan1.li@...el.com, fan.du@...el.com, 
	jun.miao@...el.com, isaku.yamahata@...el.com, muchun.song@...ux.dev, 
	mike.kravetz@...cle.com
Cc: erdemaktas@...gle.com, vannapurve@...gle.com, ackerleytng@...gle.com, 
	qperret@...gle.com, jhubbard@...dia.com, willy@...radead.org, 
	shuah@...nel.org, brauner@...nel.org, bfoster@...hat.com, 
	kent.overstreet@...ux.dev, pvorel@...e.cz, rppt@...nel.org, 
	richard.weiyang@...il.com, anup@...infault.org, haibo1.xu@...el.com, 
	ajones@...tanamicro.com, vkuznets@...hat.com, maciej.wieczor-retman@...el.com, 
	pgonda@...gle.com, oliver.upton@...ux.dev, linux-kernel@...r.kernel.org, 
	linux-mm@...ck.org, kvm@...r.kernel.org, linux-kselftest@...r.kernel.org, 
	linux-fsdevel@...ck.org
Subject: [RFC PATCH 05/39] mm: hugetlb: Refactor alloc_buddy_hugetlb_folio_with_mpol()
 to interpret mempolicy instead of vma

Reducing dependence on vma avoids the hugetlb-specific assumption of
where the mempolicy is stored. This will open up other ways of using
hugetlb.

Signed-off-by: Ackerley Tng <ackerleytng@...gle.com>
---
 mm/hugetlb.c | 37 +++++++++++++++++++++++--------------
 1 file changed, 23 insertions(+), 14 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5cf7fb117e9d..2f2bd2444ae2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2536,32 +2536,31 @@ static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mas
 }
 
 /*
- * Use the VMA's mpolicy to allocate a huge page from the buddy.
+ * Allocate a huge page from the buddy allocator, given memory policy, node id
+ * and nodemask.
  */
-static
-struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h,
-		struct vm_area_struct *vma, unsigned long addr)
+static struct folio *alloc_buddy_hugetlb_folio_from_node(struct hstate *h,
+							 struct mempolicy *mpol,
+							 int nid,
+							 nodemask_t *nodemask)
 {
-	struct folio *folio = NULL;
-	struct mempolicy *mpol;
 	gfp_t gfp_mask = htlb_alloc_mask(h);
-	int nid;
-	nodemask_t *nodemask;
+	struct folio *folio = NULL;
 
-	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
 	if (mpol_is_preferred_many(mpol)) {
 		gfp_t gfp = gfp_mask | __GFP_NOWARN;
 
 		gfp &=  ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
 		folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask);
+	}
 
-		/* Fallback to all nodes if page==NULL */
+	if (!folio) {
+		/* Fallback to all nodes if earlier allocation failed */
 		nodemask = NULL;
-	}
 
-	if (!folio)
 		folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask);
-	mpol_cond_put(mpol);
+	}
+
 	return folio;
 }
 
@@ -3187,8 +3186,18 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	spin_lock_irq(&hugetlb_lock);
 	folio = dequeue_hugetlb_folio_vma(h, vma, addr, use_hstate_resv);
 	if (!folio) {
+		struct mempolicy *mpol;
+		nodemask_t *nodemask;
+		pgoff_t ilx;
+		int nid;
+
 		spin_unlock_irq(&hugetlb_lock);
-		folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr);
+
+		mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx);
+		nid = policy_node_nodemask(mpol, htlb_alloc_mask(h), ilx, &nodemask);
+		folio = alloc_buddy_hugetlb_folio_from_node(h, mpol, nid, nodemask);
+		mpol_cond_put(mpol);
+
 		if (!folio)
 			goto out_uncharge_cgroup;
 		spin_lock_irq(&hugetlb_lock);
-- 
2.46.0.598.g6f2099f65c-goog