1 files changed, 460 insertions, 273 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index aff8642f0c2e..df7772335dc0 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -11,7 +11,6 @@
 
 #include <linux/thread_info.h>
 #include <asm/current.h>
-#include <linux/sched/signal.h>		/* remove ASAP */
 #include <linux/falloc.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -38,8 +37,8 @@
 #include <linux/uio.h>
 
 #include <linux/uaccess.h>
+#include <linux/sched/mm.h>
 
-static const struct super_operations hugetlbfs_ops;
 static const struct address_space_operations hugetlbfs_aops;
 const struct file_operations hugetlbfs_file_operations;
 static const struct inode_operations hugetlbfs_dir_inode_operations;
@@ -76,7 +75,7 @@ enum hugetlb_param {
 static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
 	fsparam_u32   ("gid",		Opt_gid),
 	fsparam_string("min_size",	Opt_min_size),
-	fsparam_u32   ("mode",		Opt_mode),
+	fsparam_u32oct("mode",		Opt_mode),
 	fsparam_string("nr_inodes",	Opt_nr_inodes),
 	fsparam_string("pagesize",	Opt_pagesize),
 	fsparam_string("size",		Opt_size),
@@ -107,16 +106,6 @@ static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
 }
 #endif
 
-static void huge_pagevec_release(struct pagevec *pvec)
-{
-	int i;
-
-	for (i = 0; i < pagevec_count(pvec); ++i)
-		put_page(pvec->pages[i]);
-
-	pagevec_reinit(pvec);
-}
-
 /*
  * 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.
@@ -130,6 +119,7 @@ static void huge_pagevec_release(struct pagevec *pvec)
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	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);
@@ -139,12 +129,16 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * already been checked by prepare_hugepage_range.  If you add
 	 * any error returns here, do so after setting VM_HUGETLB, so
 	 * is_vm_hugetlb_page tests below unmap_region go the right
-	 * way when do_mmap_pgoff unwinds (may be important on powerpc
+	 * 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;
+
 	/*
 	 * page based offset in vm_pgoff could be sufficiently large to
 	 * overflow a loff_t when converted to byte offset.  This can
@@ -170,7 +164,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 
 	ret = -ENOMEM;
-	if (hugetlb_reserve_pages(inode,
+	if (!hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
 				vma->vm_flags))
@@ -186,18 +180,66 @@ out:
 }
 
 /*
- * Called under down_write(mmap_sem).
+ * Called under mmap_write_lock(mm).
  */
 
-#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 static unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+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)
+{
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info;
+	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
@@ -213,54 +255,36 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	if (addr) {
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (mmap_end - len >= addr &&
 		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
-	info.flags = 0;
-	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
-	info.high_limit = TASK_SIZE;
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
-	return vm_unmapped_area(&info);
+	/*
+	 * 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);
 }
-#endif
 
-static size_t
-hugetlbfs_read_actor(struct page *page, unsigned long offset,
-			struct iov_iter *to, unsigned long size)
+#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)
 {
-	size_t copied = 0;
-	int i, chunksize;
-
-	/* Find which 4k chunk and offset with in that chunk */
-	i = offset >> PAGE_SHIFT;
-	offset = offset & ~PAGE_MASK;
-
-	while (size) {
-		size_t n;
-		chunksize = PAGE_SIZE;
-		if (offset)
-			chunksize -= offset;
-		if (chunksize > size)
-			chunksize = size;
-		n = copy_page_to_iter(&page[i], offset, chunksize, to);
-		copied += n;
-		if (n != chunksize)
-			return copied;
-		offset = 0;
-		size -= chunksize;
-		i++;
-	}
-	return copied;
+	return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
 }
+#endif
 
 /*
  * Support for read() - Find the page attached to f_mapping and copy out the
- * data. Its *very* similar to do_generic_mapping_read(), we can't use that
- * since it has PAGE_SIZE assumptions.
+ * data. This provides functionality similar to filemap_read().
  */
 static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
@@ -304,10 +328,16 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		} else {
 			unlock_page(page);
 
+			if (PageHWPoison(page)) {
+				put_page(page);
+				retval = -EIO;
+				break;
+			}
+
 			/*
 			 * We have the page, copy it to user space buffer.
 			 */
-			copied = hugetlbfs_read_actor(page, offset, to, nr);
+			copied = copy_page_to_iter(page, offset, nr, to);
 			put_page(page);
 		}
 		offset += copied;
@@ -326,7 +356,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static int hugetlbfs_write_begin(struct file *file,
 			struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	return -EINVAL;
@@ -340,49 +370,227 @@ static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
 	return -EINVAL;
 }
 
-static void remove_huge_page(struct page *page)
+static void hugetlb_delete_from_page_cache(struct page *page)
 {
 	ClearPageDirty(page);
 	ClearPageUptodate(page);
 	delete_from_page_cache(page);
 }
 
+/*
+ * Called with i_mmap_rwsem held for inode based vma maps.  This makes
+ * sure vma (and vm_mm) will not go away.  We also hold the hugetlb fault
+ * 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)
+{
+	pte_t *ptep, pte;
+
+	ptep = huge_pte_offset(vma->vm_mm, addr,
+			huge_page_size(hstate_vma(vma)));
+
+	if (!ptep)
+		return false;
+
+	pte = huge_ptep_get(ptep);
+	if (huge_pte_none(pte) || !pte_present(pte))
+		return false;
+
+	if (pte_page(pte) == page)
+		return true;
+
+	return false;
+}
+
+/*
+ * Can vma_offset_start/vma_offset_end overflow on 32-bit arches?
+ * No, because the interval tree returns us only those vmas
+ * which overlap the truncated area starting at pgoff,
+ * and no vma on a 32-bit arch can span beyond the 4GB.
+ */
+static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start)
+{
+	if (vma->vm_pgoff < start)
+		return (start - vma->vm_pgoff) << PAGE_SHIFT;
+	else
+		return 0;
+}
+
+static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end)
+{
+	unsigned long t_end;
+
+	if (!end)
+		return vma->vm_end;
+
+	t_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + vma->vm_start;
+	if (t_end > vma->vm_end)
+		t_end = vma->vm_end;
+	return t_end;
+}
+
+/*
+ * Called with hugetlb fault mutex held.  Therefore, no more mappings to
+ * this folio can be created while executing the routine.
+ */
+static void hugetlb_unmap_file_folio(struct hstate *h,
+					struct address_space *mapping,
+					struct folio *folio, pgoff_t index)
+{
+	struct rb_root_cached *root = &mapping->i_mmap;
+	struct hugetlb_vma_lock *vma_lock;
+	struct page *page = &folio->page;
+	struct vm_area_struct *vma;
+	unsigned long v_start;
+	unsigned long v_end;
+	pgoff_t start, end;
+
+	start = index * pages_per_huge_page(h);
+	end = (index + 1) * pages_per_huge_page(h);
+
+	i_mmap_lock_write(mapping);
+retry:
+	vma_lock = NULL;
+	vma_interval_tree_foreach(vma, root, start, end - 1) {
+		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))
+			continue;
+
+		if (!hugetlb_vma_trylock_write(vma)) {
+			vma_lock = vma->vm_private_data;
+			/*
+			 * If we can not get vma lock, we need to drop
+			 * immap_sema and take locks in order.  First,
+			 * take a ref on the vma_lock structure so that
+			 * we can be guaranteed it will not go away when
+			 * dropping immap_sema.
+			 */
+			kref_get(&vma_lock->refs);
+			break;
+		}
+
+		unmap_hugepage_range(vma, vma->vm_start + v_start, v_end,
+				NULL, ZAP_FLAG_DROP_MARKER);
+		hugetlb_vma_unlock_write(vma);
+	}
+
+	i_mmap_unlock_write(mapping);
+
+	if (vma_lock) {
+		/*
+		 * Wait on vma_lock.  We know it is still valid as we have
+		 * a reference.  We must 'open code' vma locking as we do
+		 * not know if vma_lock is still attached to vma.
+		 */
+		down_write(&vma_lock->rw_sema);
+		i_mmap_lock_write(mapping);
+
+		vma = vma_lock->vma;
+		if (!vma) {
+			/*
+			 * If lock is no longer attached to vma, then just
+			 * unlock, drop our reference and retry looking for
+			 * other vmas.
+			 */
+			up_write(&vma_lock->rw_sema);
+			kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
+			goto retry;
+		}
+
+		/*
+		 * vma_lock is still attached to vma.  Check to see if vma
+		 * still maps page and if so, unmap.
+		 */
+		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);
+
+		kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
+		hugetlb_vma_unlock_write(vma);
+
+		goto retry;
+	}
+}
+
 static void
-hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
+hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
+		      zap_flags_t zap_flags)
 {
 	struct vm_area_struct *vma;
 
 	/*
-	 * end == 0 indicates that the entire range after
-	 * start should be unmapped.
+	 * end == 0 indicates that the entire range after start should be
+	 * unmapped.  Note, end is exclusive, whereas the interval tree takes
+	 * an inclusive "last".
 	 */
-	vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) {
-		unsigned long v_offset;
+	vma_interval_tree_foreach(vma, root, start, end ? end - 1 : ULONG_MAX) {
+		unsigned long v_start;
 		unsigned long v_end;
 
+		if (!hugetlb_vma_trylock_write(vma))
+			continue;
+
+		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);
+
 		/*
-		 * Can the expression below overflow on 32-bit arches?
-		 * No, because the interval tree returns us only those vmas
-		 * which overlap the truncated area starting at pgoff,
-		 * and no vma on a 32-bit arch can span beyond the 4GB.
+		 * Note that vma lock only exists for shared/non-private
+		 * vmas.  Therefore, lock is not held when calling
+		 * unmap_hugepage_range for private vmas.
 		 */
-		if (vma->vm_pgoff < start)
-			v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
-		else
-			v_offset = 0;
-
-		if (!end)
-			v_end = vma->vm_end;
-		else {
-			v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT)
-							+ vma->vm_start;
-			if (v_end > vma->vm_end)
-				v_end = vma->vm_end;
-		}
+		hugetlb_vma_unlock_write(vma);
+	}
+}
 
-		unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
-									NULL);
+/*
+ * Called with hugetlb fault mutex held.
+ * Returns true if page was actually removed, false otherwise.
+ */
+static bool remove_inode_single_folio(struct hstate *h, struct inode *inode,
+					struct address_space *mapping,
+					struct folio *folio, pgoff_t index,
+					bool truncate_op)
+{
+	bool ret = false;
+
+	/*
+	 * 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.
+	 */
+	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
+	 * rare out of memory conditions, removal of the region/reserve
+	 * map could fail.  Correspondingly, the subpool and global
+	 * reserve usage count can need to be adjusted.
+	 */
+	VM_BUG_ON(HPageRestoreReserve(&folio->page));
+	hugetlb_delete_from_page_cache(&folio->page);
+	ret = true;
+	if (!truncate_op) {
+		if (unlikely(hugetlb_unreserve_pages(inode, index,
+							index + 1, 1)))
+			hugetlb_fix_reserve_counts(inode);
 	}
+
+	folio_unlock(folio);
+	return ret;
 }
 
 /*
@@ -391,16 +599,15 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
  *
  * truncation is indicated by end of range being LLONG_MAX
  *	In this case, we first scan the range and release found pages.
- *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
- *	maps and global counts.  Page faults can not race with truncation
- *	in this routine.  hugetlb_no_page() prevents page faults in the
- *	truncated range.  It checks i_size before allocation, and again after
- *	with the page table lock for the page held.  The same lock must be
- *	acquired to unmap a page.
+ *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserve
+ *	maps and global counts.  Page faults can race with truncation.
+ *	During faults, hugetlb_no_page() checks i_size before page allocation,
+ *	and again after obtaining page table lock.  It will 'back out'
+ *	allocations in the truncated range.
  * hole punch is indicated if end is not LLONG_MAX
  *	In the hole punch case we scan the range and release found pages.
- *	Only when releasing a page is the associated region/reserv map
- *	deleted.  The region/reserv map for ranges without associated
+ *	Only when releasing a page is the associated region/reserve map
+ *	deleted.  The region/reserve map for ranges without associated
  *	pages are not modified.  Page faults can race with hole punch.
  *	This is indicated if we find a mapped page.
  * Note: If the passed end of range value is beyond the end of file, but
@@ -413,73 +620,32 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	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);
-	struct vm_area_struct pseudo_vma;
-	struct pagevec pvec;
+	struct folio_batch fbatch;
 	pgoff_t next, index;
 	int i, freed = 0;
 	bool truncate_op = (lend == LLONG_MAX);
 
-	vma_init(&pseudo_vma, current->mm);
-	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
-	pagevec_init(&pvec);
+	folio_batch_init(&fbatch);
 	next = start;
-	while (next < end) {
-		/*
-		 * When no more pages are found, we are done.
-		 */
-		if (!pagevec_lookup_range(&pvec, mapping, &next, end - 1))
-			break;
+	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;
 
-		for (i = 0; i < pagevec_count(&pvec); ++i) {
-			struct page *page = pvec.pages[i];
-			u32 hash;
-
-			index = page->index;
+			index = folio->index;
 			hash = hugetlb_fault_mutex_hash(mapping, index);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 			/*
-			 * If page is mapped, it was faulted in after being
-			 * unmapped in caller.  Unmap (again) now after taking
-			 * the fault mutex.  The mutex will prevent faults
-			 * until we finish removing the page.
-			 *
-			 * This race can only happen in the hole punch case.
-			 * Getting here in a truncate operation is a bug.
+			 * Remove folio that was part of folio_batch.
 			 */
-			if (unlikely(page_mapped(page))) {
-				BUG_ON(truncate_op);
-
-				i_mmap_lock_write(mapping);
-				hugetlb_vmdelete_list(&mapping->i_mmap,
-					index * pages_per_huge_page(h),
-					(index + 1) * pages_per_huge_page(h));
-				i_mmap_unlock_write(mapping);
-			}
+			if (remove_inode_single_folio(h, inode, mapping, folio,
+							index, truncate_op))
+				freed++;
 
-			lock_page(page);
-			/*
-			 * We must free the huge page and remove from page
-			 * cache (remove_huge_page) BEFORE removing the
-			 * region/reserve map (hugetlb_unreserve_pages).  In
-			 * rare out of memory conditions, removal of the
-			 * region/reserve map could fail. Correspondingly,
-			 * the subpool and global reserve usage count can need
-			 * to be adjusted.
-			 */
-			VM_BUG_ON(PagePrivate(page));
-			remove_huge_page(page);
-			freed++;
-			if (!truncate_op) {
-				if (unlikely(hugetlb_unreserve_pages(inode,
-							index, index + 1, 1)))
-					hugetlb_fix_reserve_counts(inode);
-			}
-
-			unlock_page(page);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
-		huge_pagevec_release(&pvec);
+		folio_batch_release(&fbatch);
 		cond_resched();
 	}
 
@@ -506,7 +672,7 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
-static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
+static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 {
 	pgoff_t pgoff;
 	struct address_space *mapping = inode->i_mapping;
@@ -518,47 +684,85 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	i_size_write(inode, offset);
 	i_mmap_lock_write(mapping);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
-		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
+		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0,
+				      ZAP_FLAG_DROP_MARKER);
 	i_mmap_unlock_write(mapping);
 	remove_inode_hugepages(inode, offset, LLONG_MAX);
-	return 0;
+}
+
+static void hugetlbfs_zero_partial_page(struct hstate *h,
+					struct address_space *mapping,
+					loff_t start,
+					loff_t end)
+{
+	pgoff_t idx = start >> huge_page_shift(h);
+	struct folio *folio;
+
+	folio = filemap_lock_folio(mapping, idx);
+	if (!folio)
+		return;
+
+	start = start & ~huge_page_mask(h);
+	end = end & ~huge_page_mask(h);
+	if (!end)
+		end = huge_page_size(h);
+
+	folio_zero_segment(folio, (size_t)start, (size_t)end);
+
+	folio_unlock(folio);
+	folio_put(folio);
 }
 
 static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 {
+	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
+	struct address_space *mapping = inode->i_mapping;
 	struct hstate *h = hstate_inode(inode);
 	loff_t hpage_size = huge_page_size(h);
 	loff_t hole_start, hole_end;
 
 	/*
-	 * For hole punch round up the beginning offset of the hole and
-	 * round down the end.
+	 * hole_start and hole_end indicate the full pages within the hole.
 	 */
 	hole_start = round_up(offset, hpage_size);
 	hole_end = round_down(offset + len, hpage_size);
 
-	if (hole_end > hole_start) {
-		struct address_space *mapping = inode->i_mapping;
-		struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
+	inode_lock(inode);
 
-		inode_lock(inode);
+	/* protected by i_rwsem */
+	if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
+		inode_unlock(inode);
+		return -EPERM;
+	}
 
-		/* protected by i_mutex */
-		if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
-			inode_unlock(inode);
-			return -EPERM;
-		}
+	i_mmap_lock_write(mapping);
 
-		i_mmap_lock_write(mapping);
+	/* If range starts before first full page, zero partial page. */
+	if (offset < hole_start)
+		hugetlbfs_zero_partial_page(h, mapping,
+				offset, min(offset + len, hole_start));
+
+	/* Unmap users of full pages in the hole. */
+	if (hole_end > hole_start) {
 		if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
 			hugetlb_vmdelete_list(&mapping->i_mmap,
-						hole_start >> PAGE_SHIFT,
-						hole_end  >> PAGE_SHIFT);
-		i_mmap_unlock_write(mapping);
-		remove_inode_hugepages(inode, hole_start, hole_end);
-		inode_unlock(inode);
+					      hole_start >> PAGE_SHIFT,
+					      hole_end >> PAGE_SHIFT, 0);
 	}
 
+	/* If range extends beyond last full page, zero partial page. */
+	if ((offset + len) > hole_end && (offset + len) > hole_start)
+		hugetlbfs_zero_partial_page(h, mapping,
+				hole_end, offset + len);
+
+	i_mmap_unlock_write(mapping);
+
+	/* Remove full pages from the file. */
+	if (hole_end > hole_start)
+		remove_inode_hugepages(inode, hole_start, hole_end);
+
+	inode_unlock(inode);
+
 	return 0;
 }
 
@@ -619,7 +823,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		 */
 		struct page *page;
 		unsigned long addr;
-		int avoid_reserve = 0;
 
 		cond_resched();
 
@@ -651,8 +854,15 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 			continue;
 		}
 
-		/* Allocate page and add to page cache */
-		page = alloc_huge_page(&pseudo_vma, addr, avoid_reserve);
+		/*
+		 * Allocate page 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
+		 * to keep reservation accounting consistent.
+		 */
+		page = alloc_huge_page(&pseudo_vma, addr, 0);
 		hugetlb_drop_vma_policy(&pseudo_vma);
 		if (IS_ERR(page)) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
@@ -661,8 +871,9 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		}
 		clear_huge_page(page, addr, pages_per_huge_page(h));
 		__SetPageUptodate(page);
-		error = huge_add_to_page_cache(page, mapping, index);
+		error = hugetlb_add_to_page_cache(page, mapping, index);
 		if (unlikely(error)) {
+			restore_reserve_on_error(h, &pseudo_vma, addr, page);
 			put_page(page);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			goto out;
@@ -670,9 +881,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 
+		SetHPageMigratable(page);
 		/*
-		 * unlock_page because locked by add_to_page_cache()
-		 * page_put due to reference from alloc_huge_page()
+		 * unlock_page because locked by hugetlb_add_to_page_cache()
+		 * put_page() due to reference from alloc_huge_page()
 		 */
 		unlock_page(page);
 		put_page(page);
@@ -686,7 +898,8 @@ out:
 	return error;
 }
 
-static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
+static int hugetlbfs_setattr(struct user_namespace *mnt_userns,
+			     struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
 	struct hstate *h = hstate_inode(inode);
@@ -694,9 +907,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
 	unsigned int ia_valid = attr->ia_valid;
 	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
-	BUG_ON(!inode);
-
-	error = setattr_prepare(dentry, attr);
+	error = setattr_prepare(&init_user_ns, dentry, attr);
 	if (error)
 		return error;
 
@@ -706,16 +917,14 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
 
 		if (newsize & ~huge_page_mask(h))
 			return -EINVAL;
-		/* protected by i_mutex */
+		/* protected by i_rwsem */
 		if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
 		    (newsize > oldsize && (info->seals & F_SEAL_GROW)))
 			return -EPERM;
-		error = hugetlb_vmtruncate(inode, newsize);
-		if (error)
-			return error;
+		hugetlb_vmtruncate(inode, newsize);
 	}
 
-	setattr_copy(inode, attr);
+	setattr_copy(&init_user_ns, inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
 }
@@ -771,7 +980,7 @@ 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(inode, dir, mode);
+		inode_init_owner(&init_user_ns, inode, dir, mode);
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
@@ -810,56 +1019,54 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 /*
  * File creation. Allocate an inode, and we're done..
  */
-static int do_hugetlbfs_mknod(struct inode *dir,
-			struct dentry *dentry,
-			umode_t mode,
-			dev_t dev,
-			bool tmpfile)
+static int hugetlbfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+			   struct dentry *dentry, umode_t mode, dev_t dev)
 {
 	struct inode *inode;
-	int error = -ENOSPC;
 
 	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
-	if (inode) {
-		dir->i_ctime = dir->i_mtime = current_time(dir);
-		if (tmpfile) {
-			d_tmpfile(dentry, inode);
-		} else {
-			d_instantiate(dentry, inode);
-			dget(dentry);/* Extra count - pin the dentry in core */
-		}
-		error = 0;
-	}
-	return error;
-}
-
-static int hugetlbfs_mknod(struct inode *dir,
-			struct dentry *dentry, umode_t mode, dev_t dev)
-{
-	return do_hugetlbfs_mknod(dir, dentry, mode, dev, false);
+	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 */
+	return 0;
 }
 
-static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int hugetlbfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+			   struct dentry *dentry, umode_t mode)
 {
-	int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
+	int retval = hugetlbfs_mknod(&init_user_ns, dir, dentry,
+				     mode | S_IFDIR, 0);
 	if (!retval)
 		inc_nlink(dir);
 	return retval;
 }
 
-static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
+static int hugetlbfs_create(struct user_namespace *mnt_userns,
+			    struct inode *dir, struct dentry *dentry,
+			    umode_t mode, bool excl)
 {
-	return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
+	return hugetlbfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0);
 }
 
-static int hugetlbfs_tmpfile(struct inode *dir,
-			struct dentry *dentry, umode_t mode)
+static int hugetlbfs_tmpfile(struct user_namespace *mnt_userns,
+			     struct inode *dir, struct file *file,
+			     umode_t mode)
 {
-	return do_hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0, true);
+	struct inode *inode;
+
+	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0);
+	if (!inode)
+		return -ENOSPC;
+	dir->i_ctime = dir->i_mtime = current_time(dir);
+	d_tmpfile(file, inode);
+	return finish_open_simple(file, 0);
 }
 
-static int hugetlbfs_symlink(struct inode *dir,
-			struct dentry *dentry, const char *symname)
+static int hugetlbfs_symlink(struct user_namespace *mnt_userns,
+			     struct inode *dir, struct dentry *dentry,
+			     const char *symname)
 {
 	struct inode *inode;
 	int error = -ENOSPC;
@@ -879,56 +1086,37 @@ static int hugetlbfs_symlink(struct inode *dir,
 	return error;
 }
 
-/*
- * mark the head page dirty
- */
-static int hugetlbfs_set_page_dirty(struct page *page)
-{
-	struct page *head = compound_head(page);
-
-	SetPageDirty(head);
-	return 0;
-}
-
-static int hugetlbfs_migrate_page(struct address_space *mapping,
-				struct page *newpage, struct page *page,
+#ifdef CONFIG_MIGRATION
+static int hugetlbfs_migrate_folio(struct address_space *mapping,
+				struct folio *dst, struct folio *src,
 				enum migrate_mode mode)
 {
 	int rc;
 
-	rc = migrate_huge_page_move_mapping(mapping, newpage, page);
+	rc = migrate_huge_page_move_mapping(mapping, dst, src);
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 
-	/*
-	 * page_private is subpool pointer in hugetlb pages.  Transfer to
-	 * new page.  PagePrivate is not associated with page_private for
-	 * hugetlb pages and can not be set here as only page_huge_active
-	 * pages can be migrated.
-	 */
-	if (page_private(page)) {
-		set_page_private(newpage, page_private(page));
-		set_page_private(page, 0);
+	if (hugetlb_page_subpool(&src->page)) {
+		hugetlb_set_page_subpool(&dst->page,
+					hugetlb_page_subpool(&src->page));
+		hugetlb_set_page_subpool(&src->page, NULL);
 	}
 
 	if (mode != MIGRATE_SYNC_NO_COPY)
-		migrate_page_copy(newpage, page);
+		folio_migrate_copy(dst, src);
 	else
-		migrate_page_states(newpage, page);
+		folio_migrate_flags(dst, src);
 
 	return MIGRATEPAGE_SUCCESS;
 }
+#else
+#define hugetlbfs_migrate_folio NULL
+#endif
 
 static int hugetlbfs_error_remove_page(struct address_space *mapping,
 				struct page *page)
 {
-	struct inode *inode = mapping->host;
-	pgoff_t index = page->index;
-
-	remove_huge_page(page);
-	if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1)))
-		hugetlb_fix_reserve_counts(inode);
-
 	return 0;
 }
 
@@ -981,17 +1169,17 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bsize = huge_page_size(h);
 	if (sbinfo) {
 		spin_lock(&sbinfo->stat_lock);
-		/* If no limits set, just report 0 for max/free/used
+		/* If no limits set, just report 0 or -1 for max/free/used
 		 * blocks, like simple_statfs() */
 		if (sbinfo->spool) {
 			long free_pages;
 
-			spin_lock(&sbinfo->spool->lock);
+			spin_lock_irq(&sbinfo->spool->lock);
 			buf->f_blocks = sbinfo->spool->max_hpages;
 			free_pages = sbinfo->spool->max_hpages
 				- sbinfo->spool->used_hpages;
 			buf->f_bavail = buf->f_bfree = free_pages;
-			spin_unlock(&sbinfo->spool->lock);
+			spin_unlock_irq(&sbinfo->spool->lock);
 			buf->f_files = sbinfo->max_inodes;
 			buf->f_ffree = sbinfo->free_inodes;
 		}
@@ -1049,7 +1237,7 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
 
 	if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo)))
 		return NULL;
-	p = kmem_cache_alloc(hugetlbfs_inode_cachep, GFP_KERNEL);
+	p = alloc_inode_sb(sb, hugetlbfs_inode_cachep, GFP_KERNEL);
 	if (unlikely(!p)) {
 		hugetlbfs_inc_free_inodes(sbinfo);
 		return NULL;
@@ -1083,8 +1271,8 @@ static void hugetlbfs_destroy_inode(struct inode *inode)
 static const struct address_space_operations hugetlbfs_aops = {
 	.write_begin	= hugetlbfs_write_begin,
 	.write_end	= hugetlbfs_write_end,
-	.set_page_dirty	= hugetlbfs_set_page_dirty,
-	.migratepage    = hugetlbfs_migrate_page,
+	.dirty_folio	= noop_dirty_folio,
+	.migrate_folio  = hugetlbfs_migrate_folio,
 	.error_remove_page	= hugetlbfs_error_remove_page,
 };
 
@@ -1208,7 +1396,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 		ps = memparse(param->string, &rest);
 		ctx->hstate = size_to_hstate(ps);
 		if (!ctx->hstate) {
-			pr_err("Unsupported page size %lu MB\n", ps >> 20);
+			pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
 			return -EINVAL;
 		}
 		return 0;
@@ -1283,8 +1471,8 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	/*
 	 * Allocate and initialize subpool if maximum or minimum size is
-	 * specified.  Any needed reservations (for minimim size) are taken
-	 * taken when the subpool is created.
+	 * specified.  Any needed reservations (for minimum size) are taken
+	 * when the subpool is created.
 	 */
 	if (ctx->max_hpages != -1 || ctx->min_hpages != -1) {
 		sbinfo->spool = hugepage_new_subpool(ctx->hstate,
@@ -1299,6 +1487,12 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_magic = HUGETLBFS_MAGIC;
 	sb->s_op = &hugetlbfs_ops;
 	sb->s_time_gran = 1;
+
+	/*
+	 * Due to the special and limited functionality of hugetlbfs, it does
+	 * not work well as a stacking filesystem.
+	 */
+	sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
 	sb->s_root = d_make_root(hugetlbfs_get_root(sb, ctx));
 	if (!sb->s_root)
 		goto out_free;
@@ -1372,7 +1566,7 @@ static int get_hstate_idx(int page_size_log)
 
 	if (!h)
 		return -1;
-	return h - hstates;
+	return hstate_index(h);
 }
 
 /*
@@ -1380,8 +1574,8 @@ static int get_hstate_idx(int page_size_log)
  * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
  */
 struct file *hugetlb_file_setup(const char *name, size_t size,
-				vm_flags_t acctflag, struct user_struct **user,
-				int creat_flags, int page_size_log)
+				vm_flags_t acctflag, int creat_flags,
+				int page_size_log)
 {
 	struct inode *inode;
 	struct vfsmount *mnt;
@@ -1392,22 +1586,19 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	if (hstate_idx < 0)
 		return ERR_PTR(-ENODEV);
 
-	*user = NULL;
 	mnt = hugetlbfs_vfsmount[hstate_idx];
 	if (!mnt)
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
-		*user = current_user();
-		if (user_shm_lock(size, *user)) {
-			task_lock(current);
-			pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+		struct ucounts *ucounts = current_ucounts();
+
+		if (user_shm_lock(size, ucounts)) {
+			pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is obsolete\n",
 				current->comm, current->pid);
-			task_unlock(current);
-		} else {
-			*user = NULL;
-			return ERR_PTR(-EPERM);
+			user_shm_unlock(size, ucounts);
 		}
+		return ERR_PTR(-EPERM);
 	}
 
 	file = ERR_PTR(-ENOSPC);
@@ -1420,7 +1611,7 @@ 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))
 		file = ERR_PTR(-ENOMEM);
@@ -1432,10 +1623,6 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 
 	iput(inode);
 out:
-	if (*user) {
-		user_shm_unlock(size, *user);
-		*user = NULL;
-	}
 	return file;
 }
 
@@ -1454,8 +1641,8 @@ static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h)
 		put_fs_context(fc);
 	}
 	if (IS_ERR(mnt))
-		pr_err("Cannot mount internal hugetlbfs for page size %uK",
-		       1U << (h->order + PAGE_SHIFT - 10));
+		pr_err("Cannot mount internal hugetlbfs for page size %luK",
+		       huge_page_size(h) / SZ_1K);
 	return mnt;
 }
 
@@ -1483,7 +1670,7 @@ static int __init init_hugetlbfs_fs(void)
 		goto out_free;
 
 	/* default hstate mount is required */
-	mnt = mount_one_hugetlbfs(&hstates[default_hstate_idx]);
+	mnt = mount_one_hugetlbfs(&default_hstate);
 	if (IS_ERR(mnt)) {
 		error = PTR_ERR(mnt);
 		goto out_unreg;