1 files changed, 231 insertions, 276 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 790d2727141a..3b4c152c5c73 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -39,8 +39,11 @@
 #include <linux/uaccess.h>
 #include <linux/sched/mm.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/hugetlbfs.h>
+
 static const struct address_space_operations hugetlbfs_aops;
-const struct file_operations hugetlbfs_file_operations;
+static const struct file_operations hugetlbfs_file_operations;
 static const struct inode_operations hugetlbfs_dir_inode_operations;
 static const struct inode_operations hugetlbfs_inode_operations;
 
@@ -73,39 +76,16 @@ enum hugetlb_param {
 };
 
 static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
-	fsparam_u32   ("gid",		Opt_gid),
+	fsparam_gid   ("gid",		Opt_gid),
 	fsparam_string("min_size",	Opt_min_size),
 	fsparam_u32oct("mode",		Opt_mode),
 	fsparam_string("nr_inodes",	Opt_nr_inodes),
 	fsparam_string("pagesize",	Opt_pagesize),
 	fsparam_string("size",		Opt_size),
-	fsparam_u32   ("uid",		Opt_uid),
+	fsparam_uid   ("uid",		Opt_uid),
 	{}
 };
 
-#ifdef CONFIG_NUMA
-static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma,
-					struct inode *inode, pgoff_t index)
-{
-	vma->vm_policy = mpol_shared_policy_lookup(&HUGETLBFS_I(inode)->policy,
-							index);
-}
-
-static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
-{
-	mpol_cond_put(vma->vm_policy);
-}
-#else
-static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma,
-					struct inode *inode, pgoff_t index)
-{
-}
-
-static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
-{
-}
-#endif
-
 /*
  * Mask used when checking the page offset value passed in via system
  * calls.  This value will be converted to a loff_t which is signed.
@@ -116,13 +96,20 @@ static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
 #define PGOFF_LOFFT_MAX \
 	(((1UL << (PAGE_SHIFT + 1)) - 1) <<  (BITS_PER_LONG - (PAGE_SHIFT + 1)))
 
-static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int hugetlb_file_mmap_prepare_success(const struct vm_area_struct *vma)
+{
+	/* Unfortunate we have to reassign vma->vm_private_data. */
+	return hugetlb_vma_lock_alloc((struct vm_area_struct *)vma);
+}
+
+static int hugetlbfs_file_mmap_prepare(struct vm_area_desc *desc)
 {
+	struct file *file = desc->file;
 	struct inode *inode = file_inode(file);
-	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 	loff_t len, vma_len;
 	int ret;
 	struct hstate *h = hstate_file(file);
+	vm_flags_t vm_flags;
 
 	/*
 	 * vma address alignment (but not the pgoff alignment) has
@@ -132,12 +119,8 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * way when do_mmap unwinds (may be important on powerpc
 	 * and ia64).
 	 */
-	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
-	vma->vm_ops = &hugetlb_vm_ops;
-
-	ret = seal_check_future_write(info->seals, vma);
-	if (ret)
-		return ret;
+	desc->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
+	desc->vm_ops = &hugetlb_vm_ops;
 
 	/*
 	 * page based offset in vm_pgoff could be sufficiently large to
@@ -146,16 +129,16 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * sizeof(unsigned long).  So, only check in those instances.
 	 */
 	if (sizeof(unsigned long) == sizeof(loff_t)) {
-		if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
+		if (desc->pgoff & PGOFF_LOFFT_MAX)
 			return -EINVAL;
 	}
 
 	/* must be huge page aligned */
-	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
+	if (desc->pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
-	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
-	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	vma_len = (loff_t)vma_desc_size(desc);
+	len = vma_len + ((loff_t)desc->pgoff << PAGE_SHIFT);
 	/* check for overflow */
 	if (len < vma_len)
 		return -EINVAL;
@@ -164,18 +147,41 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 
 	ret = -ENOMEM;
-	if (!hugetlb_reserve_pages(inode,
-				vma->vm_pgoff >> huge_page_order(h),
-				len >> huge_page_shift(h), vma,
-				vma->vm_flags))
+
+	vm_flags = desc->vm_flags;
+	/*
+	 * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip
+	 * reserving here. Note: only for SHM hugetlbfs file, the inode
+	 * flag S_PRIVATE is set.
+	 */
+	if (inode->i_flags & S_PRIVATE)
+		vm_flags |= VM_NORESERVE;
+
+	if (hugetlb_reserve_pages(inode,
+			desc->pgoff >> huge_page_order(h),
+			len >> huge_page_shift(h), desc,
+			vm_flags) < 0)
 		goto out;
 
 	ret = 0;
-	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
+	if ((desc->vm_flags & VM_WRITE) && inode->i_size < len)
 		i_size_write(inode, len);
 out:
 	inode_unlock(inode);
 
+	if (!ret) {
+		/* Allocate the VMA lock after we set it up. */
+		desc->action.success_hook = hugetlb_file_mmap_prepare_success;
+		/*
+		 * We cannot permit the rmap finding this VMA in the time
+		 * between the VMA being inserted into the VMA tree and the
+		 * completion/success hook being invoked.
+		 *
+		 * This is because we establish a per-VMA hugetlb lock which can
+		 * be raced by rmap.
+		 */
+		desc->action.hide_from_rmap_until_complete = true;
+	}
 	return ret;
 }
 
@@ -183,104 +189,48 @@ out:
  * Called under mmap_write_lock(mm).
  */
 
-static unsigned long
-hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info;
-
-	info.flags = 0;
-	info.length = len;
-	info.low_limit = current->mm->mmap_base;
-	info.high_limit = arch_get_mmap_end(addr, len, flags);
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
-	return vm_unmapped_area(&info);
-}
-
-static unsigned long
-hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info;
-
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
-	info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base);
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
-	addr = vm_unmapped_area(&info);
-
-	/*
-	 * A failed mmap() very likely causes application failure,
-	 * so fall back to the bottom-up function here. This scenario
-	 * can happen with large stack limits and large mmap()
-	 * allocations.
-	 */
-	if (unlikely(offset_in_page(addr))) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.flags = 0;
-		info.low_limit = current->mm->mmap_base;
-		info.high_limit = arch_get_mmap_end(addr, len, flags);
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
-}
-
 unsigned long
-generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-				  unsigned long len, unsigned long pgoff,
-				  unsigned long flags)
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+			    unsigned long len, unsigned long pgoff,
+			    unsigned long flags)
 {
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
+	unsigned long addr0 = 0;
 	struct hstate *h = hstate_file(file);
-	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (len > TASK_SIZE)
-		return -ENOMEM;
-
-	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-		return addr;
-	}
-
-	if (addr) {
-		addr = ALIGN(addr, huge_page_size(h));
-		vma = find_vma(mm, addr);
-		if (mmap_end - len >= addr &&
-		    (!vma || addr + len <= vm_start_gap(vma)))
-			return addr;
-	}
+	if ((flags & MAP_FIXED) && (addr & ~huge_page_mask(h)))
+		return -EINVAL;
+	if (addr)
+		addr0 = ALIGN(addr, huge_page_size(h));
 
-	/*
-	 * Use mm->get_unmapped_area value as a hint to use topdown routine.
-	 * If architectures have special needs, they should define their own
-	 * version of hugetlb_get_unmapped_area.
-	 */
-	if (mm->get_unmapped_area == arch_get_unmapped_area_topdown)
-		return hugetlb_get_unmapped_area_topdown(file, addr, len,
-				pgoff, flags);
-	return hugetlb_get_unmapped_area_bottomup(file, addr, len,
-			pgoff, flags);
+	return mm_get_unmapped_area_vmflags(file, addr0, len, pgoff, flags, 0);
 }
 
-#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-static unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-			  unsigned long len, unsigned long pgoff,
-			  unsigned long flags)
+/*
+ * Someone wants to read @bytes from a HWPOISON hugetlb @folio from @offset.
+ * Returns the maximum number of bytes one can read without touching the 1st raw
+ * HWPOISON page.
+ */
+static size_t adjust_range_hwpoison(struct folio *folio, size_t offset,
+		size_t bytes)
 {
-	return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
+	struct page *page = folio_page(folio, offset / PAGE_SIZE);
+	size_t safe_bytes;
+
+	if (is_raw_hwpoison_page_in_hugepage(page))
+		return 0;
+	/* Safe to read the remaining bytes in this page. */
+	safe_bytes = PAGE_SIZE - (offset % PAGE_SIZE);
+	page++;
+
+	/* Check each remaining page as long as we are not done yet. */
+	for (; safe_bytes < bytes; safe_bytes += PAGE_SIZE, page++)
+		if (is_raw_hwpoison_page_in_hugepage(page))
+			break;
+
+	return min(safe_bytes, bytes);
 }
-#endif
 
 /*
  * Support for read() - Find the page attached to f_mapping and copy out the
@@ -299,8 +249,8 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	ssize_t retval = 0;
 
 	while (iov_iter_count(to)) {
-		struct page *page;
-		size_t nr, copied;
+		struct folio *folio;
+		size_t nr, copied, want;
 
 		/* nr is the maximum number of bytes to copy from this page */
 		nr = huge_page_size(h);
@@ -317,28 +267,38 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		}
 		nr = nr - offset;
 
-		/* Find the page */
-		page = find_lock_page(mapping, index);
-		if (unlikely(page == NULL)) {
+		/* Find the folio */
+		folio = filemap_lock_hugetlb_folio(h, mapping, index);
+		if (IS_ERR(folio)) {
 			/*
 			 * We have a HOLE, zero out the user-buffer for the
 			 * length of the hole or request.
 			 */
 			copied = iov_iter_zero(nr, to);
 		} else {
-			unlock_page(page);
-
-			if (PageHWPoison(page)) {
-				put_page(page);
-				retval = -EIO;
-				break;
+			folio_unlock(folio);
+
+			if (!folio_test_hwpoison(folio))
+				want = nr;
+			else {
+				/*
+				 * Adjust how many bytes safe to read without
+				 * touching the 1st raw HWPOISON page after
+				 * offset.
+				 */
+				want = adjust_range_hwpoison(folio, offset, nr);
+				if (want == 0) {
+					folio_put(folio);
+					retval = -EIO;
+					break;
+				}
 			}
 
 			/*
-			 * We have the page, copy it to user space buffer.
+			 * We have the folio, copy it to user space buffer.
 			 */
-			copied = copy_page_to_iter(page, offset, nr, to);
-			put_page(page);
+			copied = copy_folio_to_iter(folio, offset, want, to);
+			folio_put(folio);
 		}
 		offset += copied;
 		retval += copied;
@@ -354,17 +314,18 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	return retval;
 }
 
-static int hugetlbfs_write_begin(struct file *file,
+static int hugetlbfs_write_begin(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	return -EINVAL;
 }
 
-static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+static int hugetlbfs_write_end(const struct kiocb *iocb,
+			       struct address_space *mapping,
+			       loff_t pos, unsigned len, unsigned copied,
+			       struct folio *folio, void *fsdata)
 {
 	BUG();
 	return -EINVAL;
@@ -383,22 +344,20 @@ static void hugetlb_delete_from_page_cache(struct folio *folio)
  * mutex for the page in the mapping.  So, we can not race with page being
  * faulted into the vma.
  */
-static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
-				unsigned long addr, struct page *page)
+static bool hugetlb_vma_maps_pfn(struct vm_area_struct *vma,
+				unsigned long addr, unsigned long pfn)
 {
 	pte_t *ptep, pte;
 
-	ptep = huge_pte_offset(vma->vm_mm, addr,
-			huge_page_size(hstate_vma(vma)));
-
+	ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma)));
 	if (!ptep)
 		return false;
 
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(vma->vm_mm, addr, ptep);
 	if (huge_pte_none(pte) || !pte_present(pte))
 		return false;
 
-	if (pte_page(pte) == page)
+	if (pte_pfn(pte) == pfn)
 		return true;
 
 	return false;
@@ -412,10 +371,12 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
  */
 static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start)
 {
+	unsigned long offset = 0;
+
 	if (vma->vm_pgoff < start)
-		return (start - vma->vm_pgoff) << PAGE_SHIFT;
-	else
-		return 0;
+		offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
+
+	return vma->vm_start + offset;
 }
 
 static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end)
@@ -441,7 +402,7 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 {
 	struct rb_root_cached *root = &mapping->i_mmap;
 	struct hugetlb_vma_lock *vma_lock;
-	struct page *page = &folio->page;
+	unsigned long pfn = folio_pfn(folio);
 	struct vm_area_struct *vma;
 	unsigned long v_start;
 	unsigned long v_end;
@@ -457,7 +418,7 @@ retry:
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
 
-		if (!hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page))
+		if (!hugetlb_vma_maps_pfn(vma, v_start, pfn))
 			continue;
 
 		if (!hugetlb_vma_trylock_write(vma)) {
@@ -473,8 +434,8 @@ retry:
 			break;
 		}
 
-		unmap_hugepage_range(vma, vma->vm_start + v_start, v_end,
-				NULL, ZAP_FLAG_DROP_MARKER);
+		unmap_hugepage_range(vma, v_start, v_end, NULL,
+				     ZAP_FLAG_DROP_MARKER);
 		hugetlb_vma_unlock_write(vma);
 	}
 
@@ -507,10 +468,9 @@ retry:
 		 */
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
-		if (hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page))
-			unmap_hugepage_range(vma, vma->vm_start + v_start,
-						v_end, NULL,
-						ZAP_FLAG_DROP_MARKER);
+		if (hugetlb_vma_maps_pfn(vma, v_start, pfn))
+			unmap_hugepage_range(vma, v_start, v_end, NULL,
+					     ZAP_FLAG_DROP_MARKER);
 
 		kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
 		hugetlb_vma_unlock_write(vma);
@@ -540,8 +500,7 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
 
-		unmap_hugepage_range(vma, vma->vm_start + v_start, v_end,
-				     NULL, zap_flags);
+		unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags);
 
 		/*
 		 * Note that vma lock only exists for shared/non-private
@@ -565,14 +524,16 @@ static bool remove_inode_single_folio(struct hstate *h, struct inode *inode,
 
 	/*
 	 * If folio is mapped, it was faulted in after being
-	 * unmapped in caller.  Unmap (again) while holding
-	 * the fault mutex.  The mutex will prevent faults
-	 * until we finish removing the folio.
+	 * unmapped in caller or hugetlb_vmdelete_list() skips
+	 * unmapping it due to fail to grab lock.  Unmap (again)
+	 * while holding the fault mutex.  The mutex will prevent
+	 * faults until we finish removing the folio.  Hold folio
+	 * lock to guarantee no concurrent migration.
 	 */
+	folio_lock(folio);
 	if (unlikely(folio_mapped(folio)))
 		hugetlb_unmap_file_folio(h, mapping, folio, index);
 
-	folio_lock(folio);
 	/*
 	 * We must remove the folio from page cache before removing
 	 * the region/ reserve map (hugetlb_unreserve_pages).  In
@@ -618,21 +579,20 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 {
 	struct hstate *h = hstate_inode(inode);
 	struct address_space *mapping = &inode->i_data;
-	const pgoff_t start = lstart >> huge_page_shift(h);
-	const pgoff_t end = lend >> huge_page_shift(h);
+	const pgoff_t end = lend >> PAGE_SHIFT;
 	struct folio_batch fbatch;
 	pgoff_t next, index;
 	int i, freed = 0;
 	bool truncate_op = (lend == LLONG_MAX);
 
 	folio_batch_init(&fbatch);
-	next = start;
+	next = lstart >> PAGE_SHIFT;
 	while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) {
 		for (i = 0; i < folio_batch_count(&fbatch); ++i) {
 			struct folio *folio = fbatch.folios[i];
 			u32 hash = 0;
 
-			index = folio->index;
+			index = folio->index >> huge_page_order(h);
 			hash = hugetlb_fault_mutex_hash(mapping, index);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
@@ -650,13 +610,16 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	}
 
 	if (truncate_op)
-		(void)hugetlb_unreserve_pages(inode, start, LONG_MAX, freed);
+		(void)hugetlb_unreserve_pages(inode,
+				lstart >> huge_page_shift(h),
+				LONG_MAX, freed);
 }
 
 static void hugetlbfs_evict_inode(struct inode *inode)
 {
 	struct resv_map *resv_map;
 
+	trace_hugetlbfs_evict_inode(inode);
 	remove_inode_hugepages(inode, 0, LLONG_MAX);
 
 	/*
@@ -665,7 +628,7 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 	 * at inode creation time.  If this is a device special inode,
 	 * i_mapping may not point to the original address space.
 	 */
-	resv_map = (struct resv_map *)(&inode->i_data)->private_data;
+	resv_map = (struct resv_map *)(&inode->i_data)->i_private_data;
 	/* Only regular and link inodes have associated reserve maps */
 	if (resv_map)
 		resv_map_release(&resv_map->refs);
@@ -698,8 +661,8 @@ static void hugetlbfs_zero_partial_page(struct hstate *h,
 	pgoff_t idx = start >> huge_page_shift(h);
 	struct folio *folio;
 
-	folio = filemap_lock_folio(mapping, idx);
-	if (!folio)
+	folio = filemap_lock_hugetlb_folio(h, mapping, idx);
+	if (IS_ERR(folio))
 		return;
 
 	start = start & ~huge_page_mask(h);
@@ -784,8 +747,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return -EOPNOTSUPP;
 
-	if (mode & FALLOC_FL_PUNCH_HOLE)
-		return hugetlbfs_punch_hole(inode, offset, len);
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		error = hugetlbfs_punch_hole(inode, offset, len);
+		goto out_nolock;
+	}
 
 	/*
 	 * Default preallocate case.
@@ -809,11 +774,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 
 	/*
 	 * Initialize a pseudo vma as this is required by the huge page
-	 * allocation routines.  If NUMA is configured, use page index
-	 * as input to create an allocation policy.
+	 * allocation routines.
 	 */
 	vma_init(&pseudo_vma, mm);
-	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
+	vm_flags_init(&pseudo_vma, VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pseudo_vma.vm_file = file;
 
 	for (index = start; index < end; index++) {
@@ -821,7 +785,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		 * This is supposed to be the vaddr where the page is being
 		 * faulted in, but we have no vaddr here.
 		 */
-		struct page *page;
+		struct folio *folio;
 		unsigned long addr;
 
 		cond_resched();
@@ -835,9 +799,6 @@ 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;
 
@@ -846,59 +807,60 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 		/* See if already present in mapping to avoid alloc/free */
-		page = find_get_page(mapping, index);
-		if (page) {
-			put_page(page);
+		folio = filemap_get_folio(mapping, index << huge_page_order(h));
+		if (!IS_ERR(folio)) {
+			folio_put(folio);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-			hugetlb_drop_vma_policy(&pseudo_vma);
 			continue;
 		}
 
 		/*
-		 * Allocate page without setting the avoid_reserve argument.
+		 * Allocate folio without setting the avoid_reserve argument.
 		 * There certainly are no reserves associated with the
 		 * pseudo_vma.  However, there could be shared mappings with
 		 * reserves for the file at the inode level.  If we fallocate
-		 * pages in these areas, we need to consume the reserves
+		 * folios in these areas, we need to consume the reserves
 		 * to keep reservation accounting consistent.
 		 */
-		page = alloc_huge_page(&pseudo_vma, addr, 0);
-		hugetlb_drop_vma_policy(&pseudo_vma);
-		if (IS_ERR(page)) {
+		folio = alloc_hugetlb_folio(&pseudo_vma, addr, false);
+		if (IS_ERR(folio)) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-			error = PTR_ERR(page);
+			error = PTR_ERR(folio);
 			goto out;
 		}
-		clear_huge_page(page, addr, pages_per_huge_page(h));
-		__SetPageUptodate(page);
-		error = hugetlb_add_to_page_cache(page, mapping, index);
+		folio_zero_user(folio, addr);
+		__folio_mark_uptodate(folio);
+		error = hugetlb_add_to_page_cache(folio, mapping, index);
 		if (unlikely(error)) {
-			restore_reserve_on_error(h, &pseudo_vma, addr, page);
-			put_page(page);
+			restore_reserve_on_error(h, &pseudo_vma, addr, folio);
+			folio_put(folio);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			goto out;
 		}
 
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 
-		SetHPageMigratable(page);
+		folio_set_hugetlb_migratable(folio);
 		/*
-		 * unlock_page because locked by hugetlb_add_to_page_cache()
-		 * put_page() due to reference from alloc_huge_page()
+		 * folio_unlock because locked by hugetlb_add_to_page_cache()
+		 * folio_put() due to reference from alloc_hugetlb_folio()
 		 */
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
 		i_size_write(inode, offset + len);
-	inode->i_ctime = current_time(inode);
+	inode_set_ctime_current(inode);
 out:
 	inode_unlock(inode);
+
+out_nolock:
+	trace_hugetlbfs_fallocate(inode, mode, offset, len, error);
 	return error;
 }
 
-static int hugetlbfs_setattr(struct user_namespace *mnt_userns,
+static int hugetlbfs_setattr(struct mnt_idmap *idmap,
 			     struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -907,10 +869,12 @@ static int hugetlbfs_setattr(struct user_namespace *mnt_userns,
 	unsigned int ia_valid = attr->ia_valid;
 	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
-	error = setattr_prepare(&init_user_ns, dentry, attr);
+	error = setattr_prepare(idmap, dentry, attr);
 	if (error)
 		return error;
 
+	trace_hugetlbfs_setattr(inode, dentry, attr);
+
 	if (ia_valid & ATTR_SIZE) {
 		loff_t oldsize = inode->i_size;
 		loff_t newsize = attr->ia_size;
@@ -924,7 +888,7 @@ static int hugetlbfs_setattr(struct user_namespace *mnt_userns,
 		hugetlb_vmtruncate(inode, newsize);
 	}
 
-	setattr_copy(&init_user_ns, inode, attr);
+	setattr_copy(idmap, inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
 }
@@ -940,7 +904,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 		inode->i_mode = S_IFDIR | ctx->mode;
 		inode->i_uid = ctx->uid;
 		inode->i_gid = ctx->gid;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+		simple_inode_init_ts(inode);
 		inode->i_op = &hugetlbfs_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		/* directory inodes start off with i_nlink == 2 (for "." entry) */
@@ -959,6 +923,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
 
 static struct inode *hugetlbfs_get_inode(struct super_block *sb,
+					struct mnt_idmap *idmap,
 					struct inode *dir,
 					umode_t mode, dev_t dev)
 {
@@ -980,12 +945,12 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
 		inode->i_ino = get_next_ino();
-		inode_init_owner(&init_user_ns, inode, dir, mode);
+		inode_init_owner(idmap, inode, dir, mode);
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
-		inode->i_mapping->private_data = resv_map;
+		simple_inode_init_ts(inode);
+		inode->i_mapping->i_private_data = resv_map;
 		info->seals = F_SEAL_SEAL;
 		switch (mode & S_IFMT) {
 		default:
@@ -1008,6 +973,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 			break;
 		}
 		lockdep_annotate_inode_mutex_key(inode);
+		trace_hugetlbfs_alloc_inode(inode, dir, mode);
 	} else {
 		if (resv_map)
 			kref_put(&resv_map->refs, resv_map_release);
@@ -1019,69 +985,68 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 /*
  * File creation. Allocate an inode, and we're done..
  */
-static int hugetlbfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 			   struct dentry *dentry, umode_t mode, dev_t dev)
 {
 	struct inode *inode;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, dev);
 	if (!inode)
 		return -ENOSPC;
-	dir->i_ctime = dir->i_mtime = current_time(dir);
-	d_instantiate(dentry, inode);
-	dget(dentry);/* Extra count - pin the dentry in core */
+	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
+	d_make_persistent(dentry, inode);
 	return 0;
 }
 
-static int hugetlbfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
-			   struct dentry *dentry, umode_t mode)
+static struct dentry *hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+				      struct dentry *dentry, umode_t mode)
 {
-	int retval = hugetlbfs_mknod(&init_user_ns, dir, dentry,
+	int retval = hugetlbfs_mknod(idmap, dir, dentry,
 				     mode | S_IFDIR, 0);
 	if (!retval)
 		inc_nlink(dir);
-	return retval;
+	return ERR_PTR(retval);
 }
 
-static int hugetlbfs_create(struct user_namespace *mnt_userns,
+static int hugetlbfs_create(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *dentry,
 			    umode_t mode, bool excl)
 {
-	return hugetlbfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0);
+	return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0);
 }
 
-static int hugetlbfs_tmpfile(struct user_namespace *mnt_userns,
+static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
 			     struct inode *dir, struct file *file,
 			     umode_t mode)
 {
 	struct inode *inode;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode | S_IFREG, 0);
 	if (!inode)
 		return -ENOSPC;
-	dir->i_ctime = dir->i_mtime = current_time(dir);
+	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
 	d_tmpfile(file, inode);
 	return finish_open_simple(file, 0);
 }
 
-static int hugetlbfs_symlink(struct user_namespace *mnt_userns,
+static int hugetlbfs_symlink(struct mnt_idmap *idmap,
 			     struct inode *dir, struct dentry *dentry,
 			     const char *symname)
 {
+	const umode_t mode = S_IFLNK|S_IRWXUGO;
 	struct inode *inode;
 	int error = -ENOSPC;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, 0);
 	if (inode) {
 		int l = strlen(symname)+1;
 		error = page_symlink(inode, symname, l);
-		if (!error) {
-			d_instantiate(dentry, inode);
-			dget(dentry);
-		} else
+		if (!error)
+			d_make_persistent(dentry, inode);
+		else
 			iput(inode);
 	}
-	dir->i_ctime = dir->i_mtime = current_time(dir);
+	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
 
 	return error;
 }
@@ -1094,7 +1059,7 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping,
 	int rc;
 
 	rc = migrate_huge_page_move_mapping(mapping, dst, src);
-	if (rc != MIGRATEPAGE_SUCCESS)
+	if (rc)
 		return rc;
 
 	if (hugetlb_folio_subpool(src)) {
@@ -1103,19 +1068,16 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping,
 		hugetlb_set_folio_subpool(src, NULL);
 	}
 
-	if (mode != MIGRATE_SYNC_NO_COPY)
-		folio_migrate_copy(dst, src);
-	else
-		folio_migrate_flags(dst, src);
+	folio_migrate_flags(dst, src);
 
-	return MIGRATEPAGE_SUCCESS;
+	return 0;
 }
 #else
 #define hugetlbfs_migrate_folio NULL
 #endif
 
-static int hugetlbfs_error_remove_page(struct address_space *mapping,
-				struct page *page)
+static int hugetlbfs_error_remove_folio(struct address_space *mapping,
+				struct folio *folio)
 {
 	return 0;
 }
@@ -1164,7 +1126,9 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
 	struct hstate *h = hstate_inode(d_inode(dentry));
+	u64 id = huge_encode_dev(dentry->d_sb->s_dev);
 
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_type = HUGETLBFS_MAGIC;
 	buf->f_bsize = huge_page_size(h);
 	if (sbinfo) {
@@ -1242,30 +1206,18 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
 		hugetlbfs_inc_free_inodes(sbinfo);
 		return NULL;
 	}
-
-	/*
-	 * Any time after allocation, hugetlbfs_destroy_inode can be called
-	 * for the inode.  mpol_free_shared_policy is unconditionally called
-	 * as part of hugetlbfs_destroy_inode.  So, initialize policy here
-	 * in case of a quick call to destroy.
-	 *
-	 * Note that the policy is initialized even if we are creating a
-	 * private inode.  This simplifies hugetlbfs_destroy_inode.
-	 */
-	mpol_shared_policy_init(&p->policy, NULL);
-
 	return &p->vfs_inode;
 }
 
 static void hugetlbfs_free_inode(struct inode *inode)
 {
+	trace_hugetlbfs_free_inode(inode);
 	kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
 }
 
 static void hugetlbfs_destroy_inode(struct inode *inode)
 {
 	hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
-	mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy);
 }
 
 static const struct address_space_operations hugetlbfs_aops = {
@@ -1273,7 +1225,7 @@ static const struct address_space_operations hugetlbfs_aops = {
 	.write_end	= hugetlbfs_write_end,
 	.dirty_folio	= noop_dirty_folio,
 	.migrate_folio  = hugetlbfs_migrate_folio,
-	.error_remove_page	= hugetlbfs_error_remove_page,
+	.error_remove_folio	= hugetlbfs_error_remove_folio,
 };
 
 
@@ -1284,13 +1236,14 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-const struct file_operations hugetlbfs_file_operations = {
+static const struct file_operations hugetlbfs_file_operations = {
 	.read_iter		= hugetlbfs_read_iter,
-	.mmap			= hugetlbfs_file_mmap,
+	.mmap_prepare		= hugetlbfs_file_mmap_prepare,
 	.fsync			= noop_fsync,
 	.get_unmapped_area	= hugetlb_get_unmapped_area,
 	.llseek			= default_llseek,
 	.fallocate		= hugetlbfs_fallocate,
+	.fop_flags		= FOP_HUGE_PAGES,
 };
 
 static const struct inode_operations hugetlbfs_dir_inode_operations = {
@@ -1350,6 +1303,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 {
 	struct hugetlbfs_fs_context *ctx = fc->fs_private;
 	struct fs_parse_result result;
+	struct hstate *h;
 	char *rest;
 	unsigned long ps;
 	int opt;
@@ -1360,15 +1314,11 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	switch (opt) {
 	case Opt_uid:
-		ctx->uid = make_kuid(current_user_ns(), result.uint_32);
-		if (!uid_valid(ctx->uid))
-			goto bad_val;
+		ctx->uid = result.uid;
 		return 0;
 
 	case Opt_gid:
-		ctx->gid = make_kgid(current_user_ns(), result.uint_32);
-		if (!gid_valid(ctx->gid))
-			goto bad_val;
+		ctx->gid = result.gid;
 		return 0;
 
 	case Opt_mode:
@@ -1394,11 +1344,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	case Opt_pagesize:
 		ps = memparse(param->string, &rest);
-		ctx->hstate = size_to_hstate(ps);
-		if (!ctx->hstate) {
+		h = size_to_hstate(ps);
+		if (!h) {
 			pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
 			return -EINVAL;
 		}
+		ctx->hstate = h;
 		return 0;
 
 	case Opt_min_size:
@@ -1486,6 +1437,7 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_blocksize_bits = huge_page_shift(ctx->hstate);
 	sb->s_magic = HUGETLBFS_MAGIC;
 	sb->s_op = &hugetlbfs_ops;
+	sb->s_d_flags = DCACHE_DONTCACHE;
 	sb->s_time_gran = 1;
 
 	/*
@@ -1548,7 +1500,8 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.name			= "hugetlbfs",
 	.init_fs_context	= hugetlbfs_init_fs_context,
 	.parameters		= hugetlb_fs_parameters,
-	.kill_sb		= kill_litter_super,
+	.kill_sb		= kill_anon_super,
+	.fs_flags               = FS_ALLOW_IDMAP,
 };
 
 static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
@@ -1602,7 +1555,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	}
 
 	file = ERR_PTR(-ENOSPC);
-	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
+	/* hugetlbfs_vfsmount[] mounts do not use idmapped mounts.  */
+	inode = hugetlbfs_get_inode(mnt->mnt_sb, &nop_mnt_idmap, NULL,
+				    S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out;
 	if (creat_flags == HUGETLB_SHMFS_INODE)
@@ -1611,9 +1566,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	if (!hugetlb_reserve_pages(inode, 0,
+	if (hugetlb_reserve_pages(inode, 0,
 			size >> huge_page_shift(hstate_inode(inode)), NULL,
-			acctflag))
+			acctflag) < 0)
 		file = ERR_PTR(-ENOMEM);
 	else
 		file = alloc_file_pseudo(inode, mnt, name, O_RDWR,
@@ -1637,7 +1592,7 @@ static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h)
 	} else {
 		struct hugetlbfs_fs_context *ctx = fc->fs_private;
 		ctx->hstate = h;
-		mnt = fc_mount(fc);
+		mnt = fc_mount_longterm(fc);
 		put_fs_context(fc);
 	}
 	if (IS_ERR(mnt))