@@ -1844,11 +1844,6 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		if (mm_has_pgste(vma->vm_mm))
 			return 0;
 #endif
-		/*
-		 * Be somewhat over-protective like KSM for now!
-		 */
-		if (*vm_flags & VM_NO_THP)
-			return -EINVAL;
 		*vm_flags &= ~VM_NOHUGEPAGE;
 		*vm_flags |= VM_HUGEPAGE;
 		/*

@@ -1856,15 +1851,11 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 * register it here without waiting a page fault that
 		 * may not happen any time soon.
 		 */
-		if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
+		if ((*vm_flags & VM_NO_THP) &&
+				khugepaged_enter_vma_merge(vma, *vm_flags))
 			return -ENOMEM;
 		break;
 	case MADV_NOHUGEPAGE:
-		/*
-		 * Be somewhat over-protective like KSM for now!
-		 */
-		if (*vm_flags & VM_NO_THP)
-			return -EINVAL;
 		*vm_flags &= ~VM_HUGEPAGE;
 		*vm_flags |= VM_NOHUGEPAGE;
 		/*

@@ -101,6 +101,8 @@ struct shmem_falloc {
 enum sgp_type {
 	SGP_READ,	/* don't exceed i_size, don't allocate page */
 	SGP_CACHE,	/* don't exceed i_size, may allocate page */
+	SGP_NOHUGE,	/* like SGP_CACHE, but no huge pages */
+	SGP_HUGE,	/* like SGP_CACHE, huge pages preferred */
 	SGP_DIRTY,	/* like SGP_CACHE, but set new page dirty */
 	SGP_WRITE,	/* may exceed i_size, may allocate !Uptodate page */
 	SGP_FALLOC,	/* like SGP_WRITE, but make existing page Uptodate */

@@ -1371,6 +1373,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	struct mem_cgroup *memcg;
 	struct page *page;
 	swp_entry_t swap;
+	enum sgp_type sgp_huge = sgp;
 	pgoff_t hindex = index;
 	int error;
 	int once = 0;

@@ -1378,6 +1381,8 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 
 	if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT))
 		return -EFBIG;
+	if (sgp == SGP_NOHUGE || sgp == SGP_HUGE)
+		sgp = SGP_CACHE;
 repeat:
 	swap.val = 0;
 	page = find_lock_entry(mapping, index);

@@ -1491,7 +1496,7 @@ repeat:
 		/* shmem_symlink() */
 		if (mapping->a_ops != &shmem_aops)
 			goto alloc_nohuge;
-		if (shmem_huge == SHMEM_HUGE_DENY)
+		if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE)
 			goto alloc_nohuge;
 		if (shmem_huge == SHMEM_HUGE_FORCE)
 			goto alloc_huge;

@@ -1507,7 +1512,9 @@ repeat:
 				goto alloc_huge;
 			/* fallthrough */
 		case SHMEM_HUGE_ADVISE:
-			/* TODO: wire up fadvise()/madvise() */
+			if (sgp_huge == SGP_HUGE)
+				goto alloc_huge;
+			/* TODO: implement fadvise() hints */
 			goto alloc_nohuge;
 		}
 

@@ -1639,6 +1646,7 @@ unlock:
 static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vma->vm_file);
+	enum sgp_type sgp;
 	int error;
 	int ret = VM_FAULT_LOCKED;
 

@@ -1700,7 +1708,13 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		spin_unlock(&inode->i_lock);
 	}
 
-	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
+	sgp = SGP_CACHE;
+	if (vma->vm_flags & VM_HUGEPAGE)
+		sgp = SGP_HUGE;
+	else if (vma->vm_flags & VM_NOHUGEPAGE)
+		sgp = SGP_NOHUGE;
+
+	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, sgp, &ret);
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);