1 files changed, 87 insertions, 85 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a4441fb77f7c..3b4c152c5c73 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -96,10 +96,16 @@ static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
 #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);
@@ -113,12 +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).
 	 */
-	vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND | VM_MTE_ALLOWED);
-	vma->vm_ops = &hugetlb_vm_ops;
-
-	ret = seal_check_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
@@ -127,16 +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;
@@ -146,7 +148,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ret = -ENOMEM;
 
-	vm_flags = 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
@@ -155,18 +157,31 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (inode->i_flags & S_PRIVATE)
 		vm_flags |= VM_NORESERVE;
 
-	if (!hugetlb_reserve_pages(inode,
-				vma->vm_pgoff >> huge_page_order(h),
-				len >> huge_page_shift(h), vma,
-				vm_flags))
+	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;
 }
 
@@ -184,52 +199,37 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (flags & MAP_FIXED) {
-		if (addr & ~huge_page_mask(h))
-			return -EINVAL;
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-	}
+	if ((flags & MAP_FIXED) && (addr & ~huge_page_mask(h)))
+		return -EINVAL;
 	if (addr)
 		addr0 = ALIGN(addr, huge_page_size(h));
 
-	return mm_get_unmapped_area_vmflags(current->mm, file, addr0, len, pgoff,
-					    flags, 0);
+	return mm_get_unmapped_area_vmflags(file, addr0, len, pgoff, flags, 0);
 }
 
 /*
- * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset.
+ * 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 subpage.
- *
- * The implementation borrows the iteration logic from copy_page_to_iter*.
+ * HWPOISON page.
  */
-static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t bytes)
+static size_t adjust_range_hwpoison(struct folio *folio, size_t offset,
+		size_t bytes)
 {
-	size_t n = 0;
-	size_t res = 0;
+	struct page *page = folio_page(folio, offset / PAGE_SIZE);
+	size_t safe_bytes;
 
-	/* First subpage to start the loop. */
-	page = nth_page(page, offset / PAGE_SIZE);
-	offset %= PAGE_SIZE;
-	while (1) {
-		if (is_raw_hwpoison_page_in_hugepage(page))
-			break;
+	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++;
 
-		/* Safe to read n bytes without touching HWPOISON subpage. */
-		n = min(bytes, (size_t)PAGE_SIZE - offset);
-		res += n;
-		bytes -= n;
-		if (!bytes || !n)
+	/* 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;
-		offset += n;
-		if (offset == PAGE_SIZE) {
-			page = nth_page(page, 1);
-			offset = 0;
-		}
-	}
 
-	return res;
+	return min(safe_bytes, bytes);
 }
 
 /*
@@ -283,10 +283,10 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			else {
 				/*
 				 * Adjust how many bytes safe to read without
-				 * touching the 1st raw HWPOISON subpage after
+				 * touching the 1st raw HWPOISON page after
 				 * offset.
 				 */
-				want = adjust_range_hwpoison(&folio->page, offset, nr);
+				want = adjust_range_hwpoison(folio, offset, nr);
 				if (want == 0) {
 					folio_put(folio);
 					retval = -EIO;
@@ -314,7 +314,7 @@ 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 folio **foliop, void **fsdata)
@@ -322,9 +322,10 @@ static int hugetlbfs_write_begin(struct file *file,
 	return -EINVAL;
 }
 
-static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, 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;
@@ -343,8 +344,8 @@ 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;
 
@@ -356,7 +357,7 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
 	if (huge_pte_none(pte) || !pte_present(pte))
 		return false;
 
-	if (pte_page(pte) == page)
+	if (pte_pfn(pte) == pfn)
 		return true;
 
 	return false;
@@ -401,7 +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;
@@ -417,7 +418,7 @@ retry:
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
 
-		if (!hugetlb_vma_maps_page(vma, v_start, page))
+		if (!hugetlb_vma_maps_pfn(vma, v_start, pfn))
 			continue;
 
 		if (!hugetlb_vma_trylock_write(vma)) {
@@ -467,7 +468,7 @@ retry:
 		 */
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
-		if (hugetlb_vma_maps_page(vma, v_start, page))
+		if (hugetlb_vma_maps_pfn(vma, v_start, pfn))
 			unmap_hugepage_range(vma, v_start, v_end, NULL,
 					     ZAP_FLAG_DROP_MARKER);
 
@@ -523,14 +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
@@ -819,13 +822,13 @@ 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.
 		 */
-		folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0);
+		folio = alloc_hugetlb_folio(&pseudo_vma, addr, false);
 		if (IS_ERR(folio)) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			error = PTR_ERR(folio);
 			goto out;
 		}
-		folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size));
+		folio_zero_user(folio, addr);
 		__folio_mark_uptodate(folio);
 		error = hugetlb_add_to_page_cache(folio, mapping, index);
 		if (unlikely(error)) {
@@ -991,19 +994,18 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	if (!inode)
 		return -ENOSPC;
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
-	d_instantiate(dentry, inode);
-	dget(dentry);/* Extra count - pin the dentry in core */
+	d_make_persistent(dentry, inode);
 	return 0;
 }
 
-static int hugetlbfs_mkdir(struct mnt_idmap *idmap, 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(idmap, dir, dentry,
 				     mode | S_IFDIR, 0);
 	if (!retval)
 		inc_nlink(dir);
-	return retval;
+	return ERR_PTR(retval);
 }
 
 static int hugetlbfs_create(struct mnt_idmap *idmap,
@@ -1039,10 +1041,9 @@ static int hugetlbfs_symlink(struct mnt_idmap *idmap,
 	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);
 	}
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -1058,7 +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)) {
@@ -1069,7 +1070,7 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping,
 
 	folio_migrate_flags(dst, src);
 
-	return MIGRATEPAGE_SUCCESS;
+	return 0;
 }
 #else
 #define hugetlbfs_migrate_folio NULL
@@ -1237,7 +1238,7 @@ static void init_once(void *foo)
 
 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,
@@ -1436,6 +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;
 
 	/*
@@ -1498,7 +1500,7 @@ 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,
 };
 
@@ -1564,9 +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,
@@ -1590,7 +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))