Merge branch 'dax-4.10-iomap-pmd' into for-next

fs/Kconfig

@@ -55,7 +55,6 @@ config FS_DAX_PMD
 	depends on FS_DAX
 	depends on ZONE_DEVICE
 	depends on TRANSPARENT_HUGEPAGE
-	depends on BROKEN
 
 endif # BLOCK
 

fs/ext2/file.c

@@ -38,7 +38,7 @@ static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		return 0; /* skip atime */
 
 	inode_lock_shared(inode);
-	ret = iomap_dax_rw(iocb, to, &ext2_iomap_ops);
+	ret = dax_iomap_rw(iocb, to, &ext2_iomap_ops);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);
@@ -62,7 +62,7 @@ static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret)
 		goto out_unlock;
 
-	ret = iomap_dax_rw(iocb, from, &ext2_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &ext2_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		mark_inode_dirty(inode);
@@ -99,7 +99,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 	down_read(&ei->dax_sem);
 
-	ret = iomap_dax_fault(vma, vmf, &ext2_iomap_ops);
+	ret = dax_iomap_fault(vma, vmf, &ext2_iomap_ops);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)
@@ -107,27 +107,6 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return ret;
 }
 
-static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
-{
-	struct inode *inode = file_inode(vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	int ret;
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
-	}
-	down_read(&ei->dax_sem);
-
-	ret = dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
-
-	up_read(&ei->dax_sem);
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
 static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
@@ -154,7 +133,11 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
-	.pmd_fault	= ext2_dax_pmd_fault,
+	/*
+	 * .pmd_fault is not supported for DAX because allocation in ext2
+	 * cannot be reliably aligned to huge page sizes and so pmd faults
+	 * will always fail and fail back to regular faults.
+	 */
 	.page_mkwrite	= ext2_dax_fault,
 	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
 };
@@ -166,7 +149,7 @@ static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	file_accessed(file);
 	vma->vm_ops = &ext2_dax_vm_ops;
-	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+	vma->vm_flags |= VM_MIXEDMAP;
 	return 0;
 }
 #else

fs/ext4/inode.c

@@ -767,6 +767,9 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_update_bh_state(bh, map.m_flags);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 		ret = 0;
+	} else if (ret == 0) {
+		/* hole case, need to fill in bh->b_size */
+		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 	}
 	return ret;
 }

fs/iomap.c

@@ -467,8 +467,9 @@ int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	offset = page_offset(page);
 	while (length > 0) {
-		ret = iomap_apply(inode, offset, length, IOMAP_WRITE,
+		ret = iomap_apply(inode, offset, length,
-				ops, page, iomap_page_mkwrite_actor);
+				IOMAP_WRITE | IOMAP_FAULT, ops, page,
+				iomap_page_mkwrite_actor);
 		if (unlikely(ret <= 0))
 			goto out_unlock;
 		offset += ret;

fs/xfs/xfs_aops.c

@@ -1298,8 +1298,7 @@ __xfs_get_blocks(
 	sector_t		iblock,
 	struct buffer_head	*bh_result,
 	int			create,
-	bool			direct,
+	bool			direct)
-	bool			dax_fault)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1420,13 +1419,8 @@ __xfs_get_blocks(
 		if (ISUNWRITTEN(&imap))
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
-		if (create) {
+		if (create)
-			if (dax_fault)
+			xfs_map_direct(inode, bh_result, &imap, offset, is_cow);
-				ASSERT(!ISUNWRITTEN(&imap));
-			else
-				xfs_map_direct(inode, bh_result, &imap, offset,
-						is_cow);
-		}
 	}
 
 	/*
@@ -1466,7 +1460,7 @@ xfs_get_blocks(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, false, false);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, false);
 }
 
 int
@@ -1476,17 +1470,7 @@ xfs_get_blocks_direct(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true, false);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true);
-}
-
-int
-xfs_get_blocks_dax_fault(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	int			create)
-{
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true, true);
 }
 
 /*

fs/xfs/xfs_aops.h

@@ -59,9 +59,6 @@ int	xfs_get_blocks(struct inode *inode, sector_t offset,
 		       struct buffer_head *map_bh, int create);
 int	xfs_get_blocks_direct(struct inode *inode, sector_t offset,
 			      struct buffer_head *map_bh, int create);
-int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
-			         struct buffer_head *map_bh, int create);
-
 int	xfs_end_io_direct_write(struct kiocb *iocb, loff_t offset,
 		ssize_t size, void *private);
 int	xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size);

fs/xfs/xfs_file.c

@@ -318,7 +318,7 @@ xfs_file_dax_read(
 		return 0; /* skip atime */
 
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-	ret = iomap_dax_rw(iocb, to, &xfs_iomap_ops);
+	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	file_accessed(iocb->ki_filp);
@@ -653,7 +653,7 @@ xfs_file_dax_write(
 
 	trace_xfs_file_dax_write(ip, count, pos);
 
-	ret = iomap_dax_rw(iocb, from, &xfs_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &xfs_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		error = xfs_setfilesize(ip, pos, ret);
@@ -1474,7 +1474,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
 	} else {
 		ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
 		ret = block_page_mkwrite_return(ret);
@@ -1508,7 +1508,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1545,7 +1545,7 @@ xfs_filemap_pmd_fault(
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
+	ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (flags & FAULT_FLAG_WRITE)

include/linux/dax.h

@@ -8,21 +8,46 @@
 
 struct iomap_ops;
 
-/* We use lowest available exceptional entry bit for locking */
+/*
+ * We use lowest available bit in exceptional entry for locking, one bit for
+ * the entry size (PMD) and two more to tell us if the entry is a huge zero
+ * page (HZP) or an empty entry that is just used for locking.  In total four
+ * special bits.
+ *
+ * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and
+ * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
+ * block allocation.
+ */
+#define RADIX_DAX_SHIFT	(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
 #define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
+#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
+#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
+#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
 
-ssize_t iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
+static inline unsigned long dax_radix_sector(void *entry)
+{
+	return (unsigned long)entry >> RADIX_DAX_SHIFT;
+}
+
+static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
+{
+	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
+			((unsigned long)sector << RADIX_DAX_SHIFT) |
+			RADIX_DAX_ENTRY_LOCK);
+}
+
+ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		struct iomap_ops *ops);
 ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
 		  get_block_t, dio_iodone_t, int flags);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			struct iomap_ops *ops);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 void dax_wake_mapping_entry_waiter(struct address_space *mapping,
-				   pgoff_t index, bool wake_all);
+		pgoff_t index, void *entry, bool wake_all);
 
 #ifdef CONFIG_FS_DAX
 struct page *read_dax_sector(struct block_device *bdev, sector_t n);
@@ -48,15 +73,32 @@ static inline int __dax_zero_page_range(struct block_device *bdev,
 }
 #endif
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
-int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
-				unsigned int flags, get_block_t);
-#else
 static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 				pmd_t *pmd, unsigned int flags, get_block_t gb)
 {
 	return VM_FAULT_FALLBACK;
 }
+
+#ifdef CONFIG_FS_DAX_PMD
+static inline unsigned int dax_radix_order(void *entry)
+{
+	if ((unsigned long)entry & RADIX_DAX_PMD)
+		return PMD_SHIFT - PAGE_SHIFT;
+	return 0;
+}
+int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops);
+#else
+static inline unsigned int dax_radix_order(void *entry)
+{
+	return 0;
+}
+static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmd, unsigned int flags,
+		struct iomap_ops *ops)
+{
+	return VM_FAULT_FALLBACK;
+}
 #endif
 int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
 #define dax_mkwrite(vma, vmf, gb)	dax_fault(vma, vmf, gb)

include/linux/iomap.h

@@ -49,6 +49,7 @@ struct iomap {
 #define IOMAP_WRITE		(1 << 0) /* writing, must allocate blocks */
 #define IOMAP_ZERO		(1 << 1) /* zeroing operation, may skip holes */
 #define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
+#define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
 
 struct iomap_ops {
 	/*

mm/filemap.c

@@ -137,13 +137,12 @@ static int page_cache_tree_insert(struct address_space *mapping,
 		} else {
 			/* DAX can replace empty locked entry with a hole */
 			WARN_ON_ONCE(p !=
-				(void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
+				dax_radix_locked_entry(0, RADIX_DAX_EMPTY));
-					 RADIX_DAX_ENTRY_LOCK));
 			/* DAX accounts exceptional entries as normal pages */
 			if (node)
 				workingset_node_pages_dec(node);
 			/* Wakeup waiters for exceptional entry lock */
-			dax_wake_mapping_entry_waiter(mapping, page->index,
+			dax_wake_mapping_entry_waiter(mapping, page->index, p,
 						      false);
 		}
 	}