Commit adef0803 authored by Ackerley Tng's avatar Ackerley Tng Committed by Andrew Morton
Browse files

fs: hugetlbfs: set vma policy only when needed for allocating folio

Calling hugetlb_set_vma_policy() later avoids setting the vma policy
and then dropping it on a page cache hit.

Link: https://lkml.kernel.org/r/20230502235622.3652586-1-ackerleytng@google.com


Signed-off-by: default avatarAckerley Tng <ackerleytng@google.com>
Reviewed-by: default avatarMike Kravetz <mike.kravetz@oracle.com>
Cc: Erdem Aktas <erdemaktas@google.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 88537aac
Loading
Loading
Loading
Loading
+1 −4
Original line number Diff line number Diff line
@@ -834,9 +834,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
			break;
		}

		/* Set numa allocation policy based on index */
		hugetlb_set_vma_policy(&pseudo_vma, inode, index);

		/* addr is the offset within the file (zero based) */
		addr = index * hpage_size;

@@ -850,7 +847,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
		rcu_read_unlock();
		if (present) {
			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
			hugetlb_drop_vma_policy(&pseudo_vma);
			continue;
		}

@@ -862,6 +858,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
		 * folios in these areas, we need to consume the reserves
		 * to keep reservation accounting consistent.
		 */
		hugetlb_set_vma_policy(&pseudo_vma, inode, index);
		folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0);
		hugetlb_drop_vma_policy(&pseudo_vma);
		if (IS_ERR(folio)) {