Support ext4 on NV-DIMMs

index 47b6b9f..830edc8 100644
@@ -156,7 +156,7 @@ axon_ram_direct_access(struct block_device *device, sector_t sector,
 	}
 
 	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
+	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
 	return 0;
 }

index 830edc8..741293f 100644
@@ -139,26 +139,17 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
  * axon_ram_direct_access - direct_access() method for block device
  * @device, @sector, @data: see block_device_operations method
  */
-static int
+static long
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       void **kaddr, unsigned long *pfn)
+		       void **kaddr, unsigned long *pfn, long size)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
-	loff_t offset;
-
-	offset = sector;
-	if (device->bd_part != NULL)
-		offset += device->bd_part->start_sect;
-	offset <<= AXON_RAM_SECTOR_SHIFT;
-	if (offset >= bank->size) {
-		dev_err(&bank->device->dev, "Access outside of address space\n");
-		return -ERANGE;
-	}
+	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
 
 	*kaddr = (void *)(bank->ph_addr + offset);
 	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
-	return 0;
+	return min_t(long, size, bank->size - offset);
 }
 
 static const struct block_device_operations axon_ram_devops = {

index c7d138e..a10a0a9 100644
@@ -370,25 +370,23 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 }
 
 #ifdef CONFIG_BLK_DEV_XIP
-static int brd_direct_access(struct block_device *bdev, sector_t sector,
-			void **kaddr, unsigned long *pfn)
+static long brd_direct_access(struct block_device *bdev, sector_t sector,
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
 
 	if (!brd)
 		return -ENODEV;
-	if (sector & (PAGE_SECTORS-1))
-		return -EINVAL;
-	if (sector + PAGE_SECTORS > get_capacity(bdev->bd_disk))
-		return -ERANGE;
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOSPC;
 	*kaddr = page_address(page);
 	*pfn = page_to_pfn(page);
 
-	return 0;
+	/* Could optimistically check to see if the next page in the
+	 * file is mapped to the next page of physical RAM */
+	return min_t(long, PAGE_SIZE, size);
 }
 #endif
 

index 0f47175..2ee5556 100644
@@ -28,8 +28,8 @@
 static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
-static int dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-				 void **kaddr, unsigned long *pfn);
+static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
+				 void **kaddr, unsigned long *pfn, long size);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 

@@ -866,25 +866,22 @@ fail:
 	bio_io_error(bio);
 }
 
-static int
+static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void **kaddr, unsigned long *pfn)
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct dcssblk_dev_info *dev_info;
-	unsigned long pgoff;
+	unsigned long offset, dev_sz;
 
 	dev_info = bdev->bd_disk->private_data;
 	if (!dev_info)
 		return -ENODEV;
-	if (secnum % (PAGE_SIZE/512))
-		return -EINVAL;
-	pgoff = secnum / (PAGE_SIZE / 512);
-	if ((pgoff+1)*PAGE_SIZE-1 > dev_info->end - dev_info->start)
-		return -ERANGE;
-	*kaddr = (void *) (dev_info->start+pgoff*PAGE_SIZE);
+	dev_sz = dev_info->end - dev_info->start;
+	offset = secnum * 512;
+	*kaddr = (void *) (dev_info->start + offset);
 	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
-	return 0;
+	return min_t(long, size, dev_sz - offset);
 }
 
 static void

index 6d72746..93ebdd53 100644
@@ -427,6 +427,40 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);
 
+/**
+ * bdev_direct_access() - Get the address for directly-accessibly memory
+ * @bdev: The device containing the memory
+ * @sector: The offset within the device
+ * @addr: Where to put the address of the memory
+ * @pfn: The Page Frame Number for the memory
+ * @size: The number of bytes requested
+ *
+ * If a block device is made up of directly addressable memory, this function
+ * will tell the caller the PFN and the address of the memory.  The address
+ * may be directly dereferenced within the kernel without the need to call
+ * ioremap(), kmap() or similar.  THe PFN is suitable for inserting into
+ * page tables.
+ *
+ * Return: negative errno if an error occurs, otherwise the number of bytes
+ * accessible at this address.
+ */
+long bdev_direct_access(struct block_device *bdev, sector_t sector,
+			void **addr, unsigned long *pfn, long size)
+{
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	if (!ops->direct_access)
+		return -EOPNOTSUPP;
+	if ((sector + DIV_ROUND_UP(size, 512)) >
+					part_nr_sects_read(bdev->bd_part))
+		return -ERANGE;
+	sector += get_start_sect(bdev);
+	if (sector % (PAGE_SIZE / 512))
+		return -EINVAL;
+	size = ops->direct_access(bdev, sector, addr, pfn, size);
+	return size ? size : -ERANGE;
+}
+EXPORT_SYMBOL_GPL(bdev_direct_access);
+
 /*
  * pseudo-fs
  */

index e98171a..bbc5fec 100644
@@ -13,18 +13,12 @@
 #include "ext2.h"
 #include "xip.h"
 
-static inline int
-__inode_direct_access(struct inode *inode, sector_t block,
-		      void **kaddr, unsigned long *pfn)
+static inline long __inode_direct_access(struct inode *inode, sector_t block,
+				void **kaddr, unsigned long *pfn, long size)
 {
 	struct block_device *bdev = inode->i_sb->s_bdev;
-	const struct block_device_operations *ops = bdev->bd_disk->fops;
-	sector_t sector;
-
-	sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
-
-	BUG_ON(!ops->direct_access);
-	return ops->direct_access(bdev, sector, kaddr, pfn);
+	sector_t sector = block * (PAGE_SIZE / 512);
+	return bdev_direct_access(bdev, sector, kaddr, pfn, size);
 }
 
 static inline int

@@ -53,12 +47,13 @@ ext2_clear_xip_target(struct inode *inode, sector_t block)
 {
 	void *kaddr;
 	unsigned long pfn;
-	int rc;
+	long size;
 
-	rc = __inode_direct_access(inode, block, &kaddr, &pfn);
-	if (!rc)
-		clear_page(kaddr);
-	return rc;
+	size = __inode_direct_access(inode, block, &kaddr, &pfn, PAGE_SIZE);
+	if (size < 0)
+		return size;
+	clear_page(kaddr);
+	return 0;
 }
 
 void ext2_xip_verify_sb(struct super_block *sb)

@@ -77,7 +72,7 @@ void ext2_xip_verify_sb(struct super_block *sb)
 int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
 				void **kmem, unsigned long *pfn)
 {
-	int rc;
+	long rc;
 	sector_t block;
 
 	/* first, retrieve the sector number */

@@ -86,6 +81,6 @@ int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
 		return rc;
 
 	/* retrieve address of the target data */
-	rc = __inode_direct_access(mapping->host, block, kmem, pfn);
-	return rc;
+	rc = __inode_direct_access(mapping->host, block, kmem, pfn, PAGE_SIZE);
+	return (rc < 0) ? rc : 0;
 }

index 8699bcf..bc5ea9e 100644
@@ -1613,8 +1613,8 @@ struct block_device_operations {
 	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t,
-						void **, unsigned long *);
+	long (*direct_access) (struct block_device *, sector_t,
+					void **, unsigned long *pfn, long size);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */

@@ -1632,6 +1632,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
+extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
+						unsigned long *pfn, long size);
 #else /* CONFIG_BLOCK */
 
 struct block_device;

index d8d9fe3..c8d23e9 100644
@@ -260,8 +260,17 @@ again:
 		__xip_unmap(mapping, vmf->pgoff);
 
 found:
+		/* We must recheck i_size under i_mmap_mutex */
+		mutex_lock(&mapping->i_mmap_mutex);
+		size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+							PAGE_CACHE_SHIFT;
+		if (unlikely(vmf->pgoff >= size)) {
+			mutex_unlock(&mapping->i_mmap_mutex);
+			return VM_FAULT_SIGBUS;
+		}
 		err = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address,
 							xip_pfn);
+		mutex_unlock(&mapping->i_mmap_mutex);
 		if (err == -ENOMEM)
 			return VM_FAULT_OOM;
 		/*

@@ -285,16 +294,27 @@ found:
 		}
 		if (error != -ENODATA)
 			goto out;
+
+		/* We must recheck i_size under i_mmap_mutex */
+		mutex_lock(&mapping->i_mmap_mutex);
+		size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+							PAGE_CACHE_SHIFT;
+		if (unlikely(vmf->pgoff >= size)) {
+			ret = VM_FAULT_SIGBUS;
+			goto unlock;
+		}
 		/* not shared and writable, use xip_sparse_page() */
 		page = xip_sparse_page();
 		if (!page)
-			goto out;
+			goto unlock;
 		err = vm_insert_page(vma, (unsigned long)vmf->virtual_address,
 							page);
 		if (err == -ENOMEM)
-			goto out;
+			goto unlock;
 
 		ret = VM_FAULT_NOPAGE;
+unlock:
+		mutex_unlock(&mapping->i_mmap_mutex);
 out:
 		write_seqcount_end(&xip_sparse_seq);
 		mutex_unlock(&xip_sparse_mutex);

index e03dd29..e04f531 100644
@@ -208,6 +208,7 @@ struct vm_fault {
 	pgoff_t pgoff;			/* Logical page offset based on vma */
 	void __user *virtual_address;	/* Faulting virtual address */
 
+	struct page *cow_page;		/* Handler may choose to COW */
 	struct page *page;		/* ->fault handlers should return a
 					 * page here, unless VM_FAULT_NOPAGE
 					 * is set (which is also implied by

index 8b44f76..f37a044 100644
@@ -2003,6 +2003,7 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
 	vmf.pgoff = page->index;
 	vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
 	vmf.page = page;
+	vmf.cow_page = NULL;
 
 	ret = vma->vm_ops->page_mkwrite(vma, &vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))

@@ -2689,7 +2690,8 @@ oom:
 }
 
 static int __do_fault(struct vm_area_struct *vma, unsigned long address,
-		pgoff_t pgoff, unsigned int flags, struct page **page)
+			pgoff_t pgoff, unsigned int flags,
+			struct page *cow_page, struct page **page)
 {
 	struct vm_fault vmf;
 	int ret;

@@ -2698,10 +2700,13 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.page = NULL;
+	vmf.cow_page = cow_page;
 
 	ret = vma->vm_ops->fault(vma, &vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
+	if (!vmf.page)
+		goto out;
 
 	if (unlikely(PageHWPoison(vmf.page))) {
 		if (ret & VM_FAULT_LOCKED)

@@ -2715,6 +2720,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
 	else
 		VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page);
 
+ out:
 	*page = vmf.page;
 	return ret;
 }

@@ -2894,7 +2900,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		pte_unmap_unlock(pte, ptl);
 	}
 
-	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
+	ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 

@@ -2933,24 +2939,33 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_OOM;
 	}
 
-	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
+	ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		goto uncharge_out;
 
-	copy_user_highpage(new_page, fault_page, address, vma);
+	if (fault_page)
+		copy_user_highpage(new_page, fault_page, address, vma);
 	__SetPageUptodate(new_page);
 
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	if (unlikely(!pte_same(*pte, orig_pte))) {
 		pte_unmap_unlock(pte, ptl);
-		unlock_page(fault_page);
-		page_cache_release(fault_page);
+		if (fault_page) {
+			unlock_page(fault_page);
+			page_cache_release(fault_page);
+		} else {
+			mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+		}
 		goto uncharge_out;
 	}
 	do_set_pte(vma, address, new_page, pte, true, true);
 	pte_unmap_unlock(pte, ptl);
-	unlock_page(fault_page);
-	page_cache_release(fault_page);
+	if (fault_page) {
+		unlock_page(fault_page);
+		page_cache_release(fault_page);
+	} else {
+		mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+	}
 	return ret;
 uncharge_out:
 	mem_cgroup_uncharge_page(new_page);

@@ -2969,7 +2984,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	int dirtied = 0;
 	int ret, tmp;
 
-	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
+	ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 

index 36d35c3..0cb0448 100644
@@ -731,7 +731,7 @@ static int ext2_get_blocks(struct inode *inode,
 		goto cleanup;
 	}
 
-	if (ext2_use_xip(inode->i_sb)) {
+	if (IS_DAX(inode)) {
 		/*
 		 * we need to clear the block
 		 */

@@ -1201,7 +1201,7 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 
 	inode_dio_wait(inode);
 
-	if (mapping_is_xip(inode->i_mapping))
+	if (IS_DAX(inode))
 		error = xip_truncate_page(inode->i_mapping, newsize);
 	else if (test_opt(inode->i_sb, NOBH))
 		error = nobh_truncate_page(inode->i_mapping,

@@ -1273,7 +1273,8 @@ void ext2_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = EXT2_I(inode)->i_flags;
 
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
+				S_DIRSYNC | S_DAX);
 	if (flags & EXT2_SYNC_FL)
 		inode->i_flags |= S_SYNC;
 	if (flags & EXT2_APPEND_FL)

@@ -1284,6 +1285,8 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_NOATIME;
 	if (flags & EXT2_DIRSYNC_FL)
 		inode->i_flags |= S_DIRSYNC;
+	if (test_opt(inode->i_sb, XIP))
+		inode->i_flags |= S_DAX;
 }
 
 /* Propagate flags from i_flags to EXT2_I(inode)->i_flags */

index 18b34d2..29be737 100644
@@ -16,9 +16,7 @@ static inline int ext2_use_xip (struct super_block *sb)
 }
 int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
 				void **, unsigned long *);
-#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_mem)
 #else
-#define mapping_is_xip(map)			0
 #define ext2_xip_verify_sb(sb)			do { } while (0)
 #define ext2_use_xip(sb)			0
 #define ext2_clear_xip_target(inode, chain)	0

index e11d60c..a94e5d7 100644
@@ -1579,6 +1579,7 @@ struct super_operations {
 #define S_IMA		1024	/* Inode has an associated IMA struct */
 #define S_AUTOMOUNT	2048	/* Automount/referral quasi-directory */
 #define S_NOSEC		4096	/* no suid or xattr security attributes */
+#define S_DAX		8192	/* Direct Access, avoiding the page cache */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system

@@ -1616,6 +1617,11 @@ struct super_operations {
 #define IS_IMA(inode)		((inode)->i_flags & S_IMA)
 #define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
 #define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
+#ifdef CONFIG_FS_XIP
+#define IS_DAX(inode)		((inode)->i_flags & S_DAX)
+#else
+#define IS_DAX(inode)		0
+#endif
 
 /*
  * Inode state bits.  Protected by inode->i_lock

index 09a7cff..86fb3e9 100644
@@ -80,6 +80,9 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
+size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);

303 lines not on this page · raw message

index 108c68e..02e226f 100644
@@ -20,8 +20,43 @@
 #include <linux/fs.h>
 #include <linux/genhd.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
 #include <linux/uio.h>
 
+int dax_clear_blocks(struct inode *inode, sector_t block, long size)
+{
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	sector_t sector = block << (inode->i_blkbits - 9);
+
+	might_sleep();
+	do {
+		void *addr;
+		unsigned long pfn;
+		long count;
+
+		count = bdev_direct_access(bdev, sector, &addr, &pfn, size);
+		if (count < 0)
+			return count;
+		while (count > 0) {
+			unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
+			if (pgsz > count)
+				pgsz = count;
+			if (pgsz < PAGE_SIZE)
+				memset(addr, 0, pgsz);
+			else
+				clear_page(addr);
+			addr += pgsz;
+			size -= pgsz;
+			count -= pgsz;
+			sector += pgsz / 512;
+			cond_resched();
+		}
+	} while (size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_clear_blocks);
+
 static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
 {
 	unsigned long pfn;

index 3ccd5fd..52978b8 100644
@@ -733,10 +733,12 @@ static int ext2_get_blocks(struct inode *inode,
 
 	if (IS_DAX(inode)) {
 		/*
-		 * we need to clear the block
+		 * block must be initialised before we put it in the tree
+		 * so that it's not found by another thread before it's
+		 * initialised
 		 */
-		err = ext2_clear_xip_target (inode,
-			le32_to_cpu(chain[depth-1].key));
+		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
+						1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;

index bbc5fec..8cfca3a 100644
@@ -42,20 +42,6 @@ __ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
 	return rc;
 }
 
-int
-ext2_clear_xip_target(struct inode *inode, sector_t block)
-{
-	void *kaddr;
-	unsigned long pfn;
-	long size;
-
-	size = __inode_direct_access(inode, block, &kaddr, &pfn, PAGE_SIZE);
-	if (size < 0)
-		return size;
-	clear_page(kaddr);
-	return 0;
-}
-
 void ext2_xip_verify_sb(struct super_block *sb)
 {
 	struct ext2_sb_info *sbi = EXT2_SB(sb);

index 29be737..b2592f2 100644
@@ -7,8 +7,6 @@
 
 #ifdef CONFIG_EXT2_FS_XIP
 extern void ext2_xip_verify_sb (struct super_block *);
-extern int ext2_clear_xip_target (struct inode *, sector_t);
-
 static inline int ext2_use_xip (struct super_block *sb)
 {
 	struct ext2_sb_info *sbi = EXT2_SB(sb);

@@ -19,6 +17,5 @@ int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
 #else
 #define ext2_xip_verify_sb(sb)			do { } while (0)
 #define ext2_use_xip(sb)			0
-#define ext2_clear_xip_target(inode, chain)	0
 #define ext2_get_xip_mem			NULL
 #endif

index 87a135a..e38138b 100644
@@ -2463,11 +2463,17 @@ extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
 #ifdef CONFIG_FS_XIP
+int dax_clear_blocks(struct inode *, sector_t block, long size);
 extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
 extern int xip_truncate_page(struct address_space *mapping, loff_t from);
 ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
 		loff_t, get_block_t, dio_iodone_t, int flags);
 #else
+static inline int dax_clear_blocks(struct inode *i, sector_t blk, long sz)
+{
+	return 0;
+}
+
 static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
 {
 	return 0;

index 02e226f..97fd885 100644
@@ -19,9 +19,13 @@
 #include <linux/buffer_head.h>
 #include <linux/fs.h>
 #include <linux/genhd.h>
+#include <linux/highmem.h>
+#include <linux/memcontrol.h>
+#include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
 #include <linux/uio.h>
+#include <linux/vmstat.h>
 
 int dax_clear_blocks(struct inode *inode, sector_t block, long size)
 {

@@ -64,6 +68,14 @@ static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
 	return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
 }
 
+static long dax_get_pfn(struct buffer_head *bh, unsigned long *pfn,
+							unsigned blkbits)
+{
+	void *addr;
+	sector_t sector = bh->b_blocknr << (blkbits - 9);
+	return bdev_direct_access(bh->b_bdev, sector, &addr, pfn, bh->b_size);
+}
+
 static void dax_new_buf(void *addr, unsigned size, unsigned first, loff_t pos,
 			loff_t end)
 {

@@ -228,3 +240,185 @@ ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
 	return retval;
 }
 EXPORT_SYMBOL_GPL(dax_do_io);
+
+/*
+ * The user has performed a load from a hole in the file.  Allocating
+ * a new page in the file would cause excessive storage usage for
+ * workloads with sparse files.  We allocate a page cache page instead.
+ * We'll kick it out of the page cache if it's ever written to,
+ * otherwise it will simply fall out of the page cache under memory
+ * pressure without ever having been dirtied.
+ */
+static int dax_load_hole(struct address_space *mapping, struct page *page,
+							struct vm_fault *vmf)
+{
+	unsigned long size;
+	struct inode *inode = mapping->host;
+	if (!page)
+		page = find_or_create_page(mapping, vmf->pgoff,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!page)
+		return VM_FAULT_OOM;
+	/* Recheck i_size under page lock to avoid truncate race */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size) {
+		unlock_page(page);
+		page_cache_release(page);
+		return VM_FAULT_SIGBUS;
+	}
+
+	vmf->page = page;
+	return VM_FAULT_LOCKED;
+}
+
+static int copy_user_bh(struct page *to, struct buffer_head *bh,
+			unsigned blkbits, unsigned long vaddr)
+{
+	void *vfrom, *vto;
+	if (dax_get_addr(bh, &vfrom, blkbits) < 0)
+		return -EIO;
+	vto = kmap_atomic(to);
+	copy_user_page(vto, vfrom, vaddr, to);
+	kunmap_atomic(vto);
+	return 0;
+}
+
+static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			get_block_t get_block)
+{
+	struct file *file = vma->vm_file;
+	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
+	struct page *page;
+	struct buffer_head bh;
+	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	unsigned blkbits = inode->i_blkbits;
+	sector_t block;
+	pgoff_t size;
+	unsigned long pfn;
+	int error;
+	int major = 0;
+
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		return VM_FAULT_SIGBUS;
+
+	memset(&bh, 0, sizeof(bh));
+	block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
+	bh.b_size = PAGE_SIZE;
+
+ repeat:
+	page = find_get_page(mapping, vmf->pgoff);
+	if (page) {
+		if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
+			page_cache_release(page);
+			return VM_FAULT_RETRY;
+		}
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			page_cache_release(page);
+			goto repeat;
+		}
+	} else {
+		mutex_lock(&mapping->i_mmap_mutex);
+	}
+
+	/* Guard against a race with truncate */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (unlikely(vmf->pgoff >= size))
+		goto sigbus;
+
+	error = get_block(inode, block, &bh, 0);
+	if (error || bh.b_size < PAGE_SIZE)
+		goto sigbus;
+
+	if (!buffer_written(&bh) && !vmf->cow_page) {
+		if (vmf->flags & FAULT_FLAG_WRITE) {
+			error = get_block(inode, block, &bh, 1);
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			major = VM_FAULT_MAJOR;
+			if (error || bh.b_size < PAGE_SIZE)
+				goto sigbus;
+		} else {
+			if (!page)
+				mutex_unlock(&mapping->i_mmap_mutex);
+			return dax_load_hole(mapping, page, vmf);
+		}
+	}
+
+	if (vmf->cow_page) {
+		struct page *new_page = vmf->cow_page;
+		if (buffer_written(&bh))
+			error = copy_user_bh(new_page, &bh, blkbits, vaddr);
+		else
+			clear_user_highpage(new_page, vaddr);
+		if (error)
+			goto sigbus;
+		vmf->page = page;
+		return VM_FAULT_LOCKED;
+	}
+
+	if (buffer_unwritten(&bh) || buffer_new(&bh))
+		dax_clear_blocks(inode, bh.b_blocknr, bh.b_size);
+
+	if (page) {
+		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
+							PAGE_CACHE_SIZE, 0);
+		delete_from_page_cache(page);
+		unlock_page(page);
+		page_cache_release(page);
+		mutex_lock(&mapping->i_mmap_mutex);
+	}
+
+	error = dax_get_pfn(&bh, &pfn, blkbits);
+	if (error > 0)
+		error = vm_insert_mixed(vma, vaddr, pfn);
+
+	mutex_unlock(&mapping->i_mmap_mutex);
+
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (error == -EIO)
+		return VM_FAULT_SIGBUS;
+	/* -EBUSY is fine, somebody else faulted on the same PTE */
+	if (error != -EBUSY)
+		BUG_ON(error);
+	return VM_FAULT_NOPAGE | major;
+
+ sigbus:
+	if (page) {
+		unlock_page(page);
+		page_cache_release(page);
+	} else {
+		mutex_unlock(&mapping->i_mmap_mutex);
+	}
+	return VM_FAULT_SIGBUS;
+}
+
+/**
+ * dax_fault - handle a page fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * fault handler for DAX files.
+ */
+int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			get_block_t get_block)
+{
+	int result;
+	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+
+	if (vmf->flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(sb);
+		file_update_time(vma->vm_file);
+	}
+	result = do_dax_fault(vma, vmf, get_block);
+	if (vmf->flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(sb);
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(dax_fault);

index a247123..da8dc64 100644
@@ -25,6 +25,37 @@
 #include "xattr.h"
 #include "acl.h"
 
+#ifdef CONFIG_EXT2_FS_XIP
+static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_fault(vma, vmf, ext2_get_block);
+}
+
+static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_mkwrite(vma, vmf, ext2_get_block);
+}
+
+static const struct vm_operations_struct ext2_dax_vm_ops = {
+	.fault		= ext2_dax_fault,
+	.page_mkwrite	= ext2_dax_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
+};
+
+static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!IS_DAX(file_inode(file)))
+		return generic_file_mmap(file, vma);
+
+	file_accessed(file);
+	vma->vm_ops = &ext2_dax_vm_ops;
+	vma->vm_flags |= VM_MIXEDMAP;
+	return 0;
+}
+#else
+#define ext2_file_mmap	generic_file_mmap
+#endif
+
 /*
  * Called when filp is released. This happens when all file descriptors
  * for a single struct file are closed. Note that different open() calls

@@ -70,7 +101,7 @@ const struct file_operations ext2_file_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,
 #endif
-	.mmap		= generic_file_mmap,
+	.mmap		= ext2_file_mmap,
 	.open		= dquot_file_open,
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,

@@ -89,7 +120,7 @@ const struct file_operations ext2_xip_file_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,
 #endif
-	.mmap		= xip_file_mmap,
+	.mmap		= ext2_file_mmap,
 	.open		= dquot_file_open,
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,

index e38138b..d628b50 100644
@@ -49,6 +49,7 @@ struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
 struct iov_iter;
+struct vm_fault;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);

@@ -2464,10 +2465,11 @@ extern int nonseekable_open(struct inode * inode, struct file * filp);
 
 #ifdef CONFIG_FS_XIP
 int dax_clear_blocks(struct inode *, sector_t block, long size);
-extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
 extern int xip_truncate_page(struct address_space *mapping, loff_t from);
 ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
 		loff_t, get_block_t, dio_iodone_t, int flags);
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
+#define dax_mkwrite(vma, vmf, gb)	dax_fault(vma, vmf, gb)
 #else
 static inline int dax_clear_blocks(struct inode *i, sector_t blk, long sz)
 {

212 lines not on this page · raw message

index 97fd885..15654ce 100644
@@ -422,3 +422,47 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	return result;
 }
 EXPORT_SYMBOL_GPL(dax_fault);
+
+/**
+ * dax_truncate_page - handle a partial page being truncated in a DAX file
+ * @inode: The file being truncated
+ * @from: The file offset that is being truncated to
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * Similar to block_truncate_page(), this function can be called by a
+ * filesystem when it is truncating an DAX file to handle the partial page.
+ *
+ * We work in terms of PAGE_CACHE_SIZE here for commonality with
+ * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
+ * took care of disposing of the unnecessary blocks.  Even if the filesystem
+ * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
+ * since the file might be mmaped.
+ */
+int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
+{
+	struct buffer_head bh;
+	pgoff_t index = from >> PAGE_CACHE_SHIFT;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned length = PAGE_CACHE_ALIGN(from) - from;
+	int err;
+
+	/* Block boundary? Nothing to do */
+	if (!length)
+		return 0;
+
+	memset(&bh, 0, sizeof(bh));
+	bh.b_size = PAGE_CACHE_SIZE;
+	err = get_block(inode, index, &bh, 0);
+	if (err < 0)
+		return err;
+	if (buffer_written(&bh)) {
+		void *addr;
+		err = dax_get_addr(&bh, &addr, inode->i_blkbits);
+		if (err < 0)
+			return err;
+		memset(addr + offset, 0, length);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_truncate_page);

index 52978b8..5ac0a34 100644
@@ -1210,7 +1210,7 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 	inode_dio_wait(inode);
 
 	if (IS_DAX(inode))
-		error = xip_truncate_page(inode->i_mapping, newsize);
+		error = dax_truncate_page(inode, newsize, ext2_get_block);
 	else if (test_opt(inode->i_sb, NOBH))
 		error = nobh_truncate_page(inode->i_mapping,
 				newsize, ext2_get_block);

index d628b50..0cdb57b 100644
@@ -2465,7 +2465,7 @@ extern int nonseekable_open(struct inode * inode, struct file * filp);
 
 #ifdef CONFIG_FS_XIP
 int dax_clear_blocks(struct inode *, sector_t block, long size);
-extern int xip_truncate_page(struct address_space *mapping, loff_t from);
+int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
 		loff_t, get_block_t, dio_iodone_t, int flags);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);

@@ -2476,7 +2476,7 @@ static inline int dax_clear_blocks(struct inode *i, sector_t blk, long sz)
 	return 0;
 }
 
-static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
+static inline int dax_truncate_page(struct inode *i, loff_t frm, get_block_t gb)
 {
 	return 0;
 }

index 9dd45f3..6316578 100644
@@ -21,43 +21,3 @@
 #include <asm/tlbflush.h>
 #include <asm/io.h>
 
-/*
- * truncate a page used for execute in place
- * functionality is analog to block_truncate_page but does use get_xip_mem
- * to get the page instead of page cache
- */
-int
-xip_truncate_page(struct address_space *mapping, loff_t from)
-{
-	pgoff_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize;
-	unsigned length;
-	void *xip_mem;
-	unsigned long xip_pfn;
-	int err;
-
-	BUG_ON(!mapping->a_ops->get_xip_mem);
-
-	blocksize = 1 << mapping->host->i_blkbits;
-	length = offset & (blocksize - 1);
-
-	/* Block boundary? Nothing to do */
-	if (!length)
-		return 0;
-
-	length = blocksize - length;
-
-	err = mapping->a_ops->get_xip_mem(mapping, index, 0,
-						&xip_mem, &xip_pfn);
-	if (unlikely(err)) {
-		if (err == -ENODATA)
-			/* Hole? No need to truncate */
-			return 0;
-		else
-			return err;
-	}
-	memset(xip_mem + offset, 0, length);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xip_truncate_page);

index 3f9cafd..c408a53 100644
@@ -985,7 +985,6 @@ const struct address_space_operations exofs_aops = {
 	.direct_IO	= exofs_direct_IO,
 
 	/* With these NULL has special meaning or default is not exported */
-	.get_xip_mem	= NULL,
 	.migratepage	= NULL,
 	.launder_page	= NULL,
 	.is_partially_uptodate = NULL,

index 5ac0a34..59d6c7d 100644
@@ -894,7 +894,6 @@ const struct address_space_operations ext2_aops = {
 
 const struct address_space_operations ext2_aops_xip = {
 	.bmap			= ext2_bmap,
-	.get_xip_mem		= ext2_get_xip_mem,
 	.direct_IO		= ext2_direct_IO,
 };
 

54 lines not on this page · raw message

index b2592f2..e7b9f0a 100644
@@ -12,10 +12,7 @@ static inline int ext2_use_xip (struct super_block *sb)
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
 }
-int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
-				void **, unsigned long *);
 #else
 #define ext2_xip_verify_sb(sb)			do { } while (0)
 #define ext2_use_xip(sb)			0
-#define ext2_get_xip_mem			NULL
 #endif

index 36662d0..1a9f0d6 100644
@@ -656,11 +656,8 @@ int open_check_o_direct(struct file *f)
 {
 	/* NB: we're sure to have correct a_ops only after f_op->open */
 	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops ||
-		    ((!f->f_mapping->a_ops->direct_IO) &&
-		    (!f->f_mapping->a_ops->get_xip_mem))) {
+		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
 			return -EINVAL;
-		}
 	}
 	return 0;
 }

index 0cdb57b..67edd2c 100644
@@ -349,8 +349,6 @@ struct address_space_operations {
 	int (*releasepage) (struct page *, gfp_t);
 	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
-	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
-						void **, unsigned long *);
 	/*
 	 * migrate the contents of a page to the specified target. If
 	 * migrate_mode is MIGRATE_ASYNC, it must not block.

index 3bcfd81..1f1925f 100644
@@ -28,6 +28,7 @@
 SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 {
 	struct fd f = fdget(fd);
+	struct inode *inode;
 	struct address_space *mapping;
 	struct backing_dev_info *bdi;
 	loff_t endbyte;			/* inclusive */

@@ -39,7 +40,8 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 	if (!f.file)
 		return -EBADF;
 
-	if (S_ISFIFO(file_inode(f.file)->i_mode)) {
+	inode = file_inode(f.file);
+	if (S_ISFIFO(inode->i_mode)) {
 		ret = -ESPIPE;
 		goto out;
 	}

@@ -50,7 +52,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 		goto out;
 	}
 
-	if (mapping->a_ops->get_xip_mem) {
+	if (IS_DAX(inode)) {
 		switch (advice) {
 		case POSIX_FADV_NORMAL:
 		case POSIX_FADV_RANDOM:

deleted file mode 100644
index 6316578..0000000
@@ -1,23 +0,0 @@
-/*
- *	linux/mm/filemap_xip.c
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte <[email protected]>
- *
- * derived from linux/mm/filemap.c - Copyright (C) Linus Torvalds
- *
- */
-
-#include <linux/fs.h>
-#include <linux/pagemap.h>
-#include <linux/export.h>
-#include <linux/uio.h>
-#include <linux/rmap.h>
-#include <linux/mmu_notifier.h>
-#include <linux/sched.h>
-#include <linux/seqlock.h>
-#include <linux/mutex.h>
-#include <linux/gfp.h>
-#include <asm/tlbflush.h>
-#include <asm/io.h>
-

index a402f8f..dee5dff 100644
@@ -236,7 +236,7 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	if (!file)
 		return -EBADF;
 
-	if (file->f_mapping->a_ops->get_xip_mem) {
+	if (IS_DAX(file_inode(file))) {
 		/* no bad return value, but ignore advice */
 		return 0;
 	}

index 3750031..3ac6555 100644
@@ -868,9 +868,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
 		 MS_POSIXACL : 0);
 
-	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
-				    EXT2_MOUNT_XIP if not */
-
 	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
 	    (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
 	     EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||

@@ -900,11 +897,17 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
-	if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) {
-		if (!silent)
+	if (sbi->s_mount_opt & EXT2_MOUNT_XIP) {
+		if (blocksize != PAGE_SIZE) {
 			ext2_msg(sb, KERN_ERR,
-				"error: unsupported blocksize for xip");
-		goto failed_mount;
+					"error: unsupported blocksize for xip");
+			goto failed_mount;
+		}
+		if (!sb->s_bdev->bd_disk->fops->direct_access) {
+			ext2_msg(sb, KERN_ERR,
+					"error: device does not support xip");
+			goto failed_mount;
+		}
 	}
 
 	/* If the blocksize doesn't match, re-read the thing.. */

@@ -1249,7 +1252,6 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 {
 	struct ext2_sb_info * sbi = EXT2_SB(sb);
 	struct ext2_super_block * es;
-	unsigned long old_mount_opt = sbi->s_mount_opt;
 	struct ext2_mount_options old_opts;
 	unsigned long old_sb_flags;
 	int err;

@@ -1274,22 +1276,11 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
 
-	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
-				    EXT2_MOUNT_XIP if not */
-
-	if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
-		ext2_msg(sb, KERN_WARNING,
-			"warning: unsupported blocksize for xip");
-		err = -EINVAL;
-		goto restore_opts;
-	}
-
 	es = sbi->s_es;
-	if ((sbi->s_mount_opt ^ old_mount_opt) & EXT2_MOUNT_XIP) {
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT2_MOUNT_XIP) {
 		ext2_msg(sb, KERN_WARNING, "warning: refusing change of "
 			 "xip flag with busy inodes while remounting");
-		sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
-		sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
+		sbi->s_mount_opt ^= EXT2_MOUNT_XIP;
 	}
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		spin_unlock(&sbi->s_lock);

index 132d4da..66ca113 100644
@@ -13,15 +13,3 @@
 #include "ext2.h"
 #include "xip.h"
 
-void ext2_xip_verify_sb(struct super_block *sb)
-{
-	struct ext2_sb_info *sbi = EXT2_SB(sb);
-
-	if ((sbi->s_mount_opt & EXT2_MOUNT_XIP) &&
-	    !sb->s_bdev->bd_disk->fops->direct_access) {
-		sbi->s_mount_opt &= (~EXT2_MOUNT_XIP);
-		ext2_msg(sb, KERN_WARNING,
-			     "warning: ignoring xip option - "
-			     "not supported by bdev");
-	}
-}

index e7b9f0a..87eeb04 100644
@@ -6,13 +6,11 @@
  */
 
 #ifdef CONFIG_EXT2_FS_XIP
-extern void ext2_xip_verify_sb (struct super_block *);
 static inline int ext2_use_xip (struct super_block *sb)
 {
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
 }
 #else
-#define ext2_xip_verify_sb(sb)			do { } while (0)
 #define ext2_use_xip(sb)			0
 #endif

index d9a17d0..5ecf570 100644
@@ -380,7 +380,11 @@ struct ext2_inode {
 #define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
 #define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
 #define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
+#ifdef CONFIG_FS_XIP
 #define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
+#else
+#define EXT2_MOUNT_XIP			0
+#endif
 #define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
 #define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
 #define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */

index 59d6c7d..cba3833 100644
@@ -1394,7 +1394,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext2_file_inode_operations;
-		if (ext2_use_xip(inode->i_sb)) {
+		if (test_opt(inode->i_sb, XIP)) {
 			inode->i_mapping->a_ops = &ext2_aops_xip;
 			inode->i_fop = &ext2_xip_file_operations;
 		} else if (test_opt(inode->i_sb, NOBH)) {

index c268d0a..846c356 100644
@@ -105,7 +105,7 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode
 		return PTR_ERR(inode);
 
 	inode->i_op = &ext2_file_inode_operations;
-	if (ext2_use_xip(inode->i_sb)) {
+	if (test_opt(inode->i_sb, XIP)) {
 		inode->i_mapping->a_ops = &ext2_aops_xip;
 		inode->i_fop = &ext2_xip_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {

@@ -126,7 +126,7 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 		return PTR_ERR(inode);
 
 	inode->i_op = &ext2_file_inode_operations;
-	if (ext2_use_xip(inode->i_sb)) {
+	if (test_opt(inode->i_sb, XIP)) {
 		inode->i_mapping->a_ops = &ext2_aops_xip;
 		inode->i_fop = &ext2_xip_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {

index cba3833..154cbcf 100644
@@ -34,7 +34,6 @@
 #include <linux/aio.h>
 #include "ext2.h"
 #include "acl.h"
-#include "xip.h"
 #include "xattr.h"
 
 static int __ext2_write_inode(struct inode *inode, int do_sync);

index 846c356..7ca803f 100644
@@ -35,7 +35,6 @@
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "xip.h"
 
 static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 {

index 3ac6555..747e293 100644
@@ -35,7 +35,6 @@
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "xip.h"
 
 static void ext2_sync_super(struct super_block *sb,
 			    struct ext2_super_block *es, int wait);

deleted file mode 100644
index 66ca113..0000000
@@ -1,15 +0,0 @@
-/*
- *  linux/fs/ext2/xip.c
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte ([email protected])
- */
-
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/buffer_head.h>
-#include <linux/blkdev.h>
-#include "ext2.h"
-#include "xip.h"
-

deleted file mode 100644
index 87eeb04..0000000
@@ -1,16 +0,0 @@
-/*
- *  linux/fs/ext2/xip.h
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte ([email protected])
- */
-
-#ifdef CONFIG_EXT2_FS_XIP
-static inline int ext2_use_xip (struct super_block *sb)
-{
-	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
-}
-#else
-#define ext2_use_xip(sb)			0
-#endif

index 5ecf570..b30c3bd 100644
@@ -380,7 +380,7 @@ struct ext2_inode {
 #define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
 #define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
 #define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
-#ifdef CONFIG_FS_XIP
+#ifdef CONFIG_FS_DAX
 #define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
 #else
 #define EXT2_MOUNT_XIP			0

index da8dc64..46b333d 100644
@@ -25,7 +25,7 @@
 #include "xattr.h"
 #include "acl.h"
 
-#ifdef CONFIG_EXT2_FS_XIP
+#ifdef CONFIG_FS_DAX
 static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	return dax_fault(vma, vmf, ext2_get_block);

@@ -109,7 +109,7 @@ const struct file_operations ext2_file_operations = {
 	.splice_write	= iter_file_splice_write,
 };
 
-#ifdef CONFIG_EXT2_FS_XIP
+#ifdef CONFIG_FS_DAX
 const struct file_operations ext2_xip_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= new_sync_read,

index 747e293..2b58c48 100644
@@ -287,7 +287,7 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",grpquota");
 #endif
 
-#if defined(CONFIG_EXT2_FS_XIP)
+#ifdef CONFIG_FS_DAX
 	if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
 		seq_puts(seq, ",xip");
 #endif

@@ -549,7 +549,7 @@ static int parse_options(char *options, struct super_block *sb)
 			break;
 #endif
 		case Opt_xip:
-#ifdef CONFIG_EXT2_FS_XIP
+#ifdef CONFIG_FS_DAX
 			set_opt (sbi->s_mount_opt, XIP);
 #else
 			ext2_msg(sb, KERN_INFO, "xip option not supported");

index 67edd2c..79b0cbe 100644
@@ -1616,7 +1616,7 @@ struct super_operations {
 #define IS_IMA(inode)		((inode)->i_flags & S_IMA)
 #define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
 #define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
-#ifdef CONFIG_FS_XIP
+#ifdef CONFIG_FS_DAX
 #define IS_DAX(inode)		((inode)->i_flags & S_DAX)
 #else
 #define IS_DAX(inode)		0

@@ -2461,7 +2461,7 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
-#ifdef CONFIG_FS_XIP
+#ifdef CONFIG_FS_DAX
 int dax_clear_blocks(struct inode *, sector_t block, long size);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,

index b30c3bd..b8b1c11 100644
@@ -793,7 +793,6 @@ extern const struct file_operations ext2_xip_file_operations;
 
 /* inode.c */
 extern const struct address_space_operations ext2_aops;
-extern const struct address_space_operations ext2_aops_xip;
 extern const struct address_space_operations ext2_nobh_aops;
 
 /* namei.c */

index 154cbcf..034fd42 100644
@@ -891,11 +891,6 @@ const struct address_space_operations ext2_aops = {
 	.error_remove_page	= generic_error_remove_page,
 };
 
-const struct address_space_operations ext2_aops_xip = {
-	.bmap			= ext2_bmap,
-	.direct_IO		= ext2_direct_IO,
-};
-
 const struct address_space_operations ext2_nobh_aops = {
 	.readpage		= ext2_readpage,
 	.readpages		= ext2_readpages,

@@ -1394,7 +1389,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext2_file_inode_operations;
 		if (test_opt(inode->i_sb, XIP)) {
-			inode->i_mapping->a_ops = &ext2_aops_xip;
+			inode->i_mapping->a_ops = &ext2_aops;
 			inode->i_fop = &ext2_xip_file_operations;
 		} else if (test_opt(inode->i_sb, NOBH)) {
 			inode->i_mapping->a_ops = &ext2_nobh_aops;

index 7ca803f..0db888c 100644
@@ -105,7 +105,7 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode
 
 	inode->i_op = &ext2_file_inode_operations;
 	if (test_opt(inode->i_sb, XIP)) {
-		inode->i_mapping->a_ops = &ext2_aops_xip;
+		inode->i_mapping->a_ops = &ext2_aops;
 		inode->i_fop = &ext2_xip_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {
 		inode->i_mapping->a_ops = &ext2_nobh_aops;

@@ -126,7 +126,7 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	inode->i_op = &ext2_file_inode_operations;
 	if (test_opt(inode->i_sb, XIP)) {
-		inode->i_mapping->a_ops = &ext2_aops_xip;
+		inode->i_mapping->a_ops = &ext2_aops;
 		inode->i_fop = &ext2_xip_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {
 		inode->i_mapping->a_ops = &ext2_nobh_aops;

index b8b1c11..46133a0 100644
@@ -380,14 +380,15 @@ struct ext2_inode {
 #define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
 #define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
 #define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
-#ifdef CONFIG_FS_DAX
-#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
-#else
-#define EXT2_MOUNT_XIP			0
-#endif
+#define EXT2_MOUNT_XIP			0x010000  /* Obsolete, use DAX */
 #define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
 #define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
 #define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */
+#ifdef CONFIG_FS_DAX
+#define EXT2_MOUNT_DAX			0x100000  /* Direct Access */
+#else
+#define EXT2_MOUNT_DAX			0
+#endif
 
 
 #define clear_opt(o, opt)		o &= ~EXT2_MOUNT_##opt

@@ -789,7 +790,7 @@ extern int ext2_fsync(struct file *file, loff_t start, loff_t end,
 		      int datasync);
 extern const struct inode_operations ext2_file_inode_operations;
 extern const struct file_operations ext2_file_operations;
-extern const struct file_operations ext2_xip_file_operations;
+extern const struct file_operations ext2_dax_file_operations;
 
 /* inode.c */
 extern const struct address_space_operations ext2_aops;

index 46b333d..5b8cab5 100644
@@ -110,7 +110,7 @@ const struct file_operations ext2_file_operations = {
 };
 
 #ifdef CONFIG_FS_DAX
-const struct file_operations ext2_xip_file_operations = {
+const struct file_operations ext2_dax_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= new_sync_read,
 	.write		= new_sync_write,

index 034fd42..6434bc0 100644
@@ -1286,7 +1286,7 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_NOATIME;
 	if (flags & EXT2_DIRSYNC_FL)
 		inode->i_flags |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, XIP))
+	if (test_opt(inode->i_sb, DAX))
 		inode->i_flags |= S_DAX;
 }
 

@@ -1388,9 +1388,9 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext2_file_inode_operations;
-		if (test_opt(inode->i_sb, XIP)) {
+		if (test_opt(inode->i_sb, DAX)) {
 			inode->i_mapping->a_ops = &ext2_aops;
-			inode->i_fop = &ext2_xip_file_operations;
+			inode->i_fop = &ext2_dax_file_operations;
 		} else if (test_opt(inode->i_sb, NOBH)) {
 			inode->i_mapping->a_ops = &ext2_nobh_aops;
 			inode->i_fop = &ext2_file_operations;

index 0db888c..148f6e3 100644
@@ -104,9 +104,9 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode
 		return PTR_ERR(inode);
 
 	inode->i_op = &ext2_file_inode_operations;
-	if (test_opt(inode->i_sb, XIP)) {
+	if (test_opt(inode->i_sb, DAX)) {
 		inode->i_mapping->a_ops = &ext2_aops;
-		inode->i_fop = &ext2_xip_file_operations;
+		inode->i_fop = &ext2_dax_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {
 		inode->i_mapping->a_ops = &ext2_nobh_aops;
 		inode->i_fop = &ext2_file_operations;

@@ -125,9 +125,9 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 		return PTR_ERR(inode);
 
 	inode->i_op = &ext2_file_inode_operations;
-	if (test_opt(inode->i_sb, XIP)) {
+	if (test_opt(inode->i_sb, DAX)) {
 		inode->i_mapping->a_ops = &ext2_aops;
-		inode->i_fop = &ext2_xip_file_operations;
+		inode->i_fop = &ext2_dax_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {
 		inode->i_mapping->a_ops = &ext2_nobh_aops;
 		inode->i_fop = &ext2_file_operations;

index 2b58c48..29633627 100644
@@ -290,6 +290,8 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
 #ifdef CONFIG_FS_DAX
 	if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
 		seq_puts(seq, ",xip");
+	if (sbi->s_mount_opt & EXT2_MOUNT_DAX)
+		seq_puts(seq, ",dax");
 #endif
 
 	if (!test_opt(sb, RESERVATION))

@@ -393,7 +395,7 @@ enum {
 	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic,
 	Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
 	Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
-	Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota,
+	Opt_acl, Opt_noacl, Opt_xip, Opt_dax, Opt_ignore, Opt_err, Opt_quota,
 	Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
 };
 

@@ -422,6 +424,7 @@ static const match_table_t tokens = {
 	{Opt_acl, "acl"},
 	{Opt_noacl, "noacl"},
 	{Opt_xip, "xip"},
+	{Opt_dax, "dax"},
 	{Opt_grpquota, "grpquota"},
 	{Opt_ignore, "noquota"},
 	{Opt_quota, "quota"},

@@ -549,10 +552,14 @@ static int parse_options(char *options, struct super_block *sb)
 			break;
 #endif
 		case Opt_xip:
+			ext2_msg(sb, KERN_INFO, "use dax instead of xip");
+			set_opt(sbi->s_mount_opt, XIP);
+			/* Fall through */
+		case Opt_dax:
 #ifdef CONFIG_FS_DAX
-			set_opt (sbi->s_mount_opt, XIP);
+			set_opt(sbi->s_mount_opt, DAX);
 #else
-			ext2_msg(sb, KERN_INFO, "xip option not supported");
+			ext2_msg(sb, KERN_INFO, "dax option not supported");
 #endif
 			break;
 

@@ -896,15 +903,15 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
-	if (sbi->s_mount_opt & EXT2_MOUNT_XIP) {
+	if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
 		if (blocksize != PAGE_SIZE) {
 			ext2_msg(sb, KERN_ERR,
-					"error: unsupported blocksize for xip");
+					"error: unsupported blocksize for dax");
 			goto failed_mount;
 		}
 		if (!sb->s_bdev->bd_disk->fops->direct_access) {
 			ext2_msg(sb, KERN_ERR,
-					"error: device does not support xip");
+					"error: device does not support dax");
 			goto failed_mount;
 		}
 	}

@@ -1276,10 +1283,10 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
 
 	es = sbi->s_es;
-	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT2_MOUNT_XIP) {
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT2_MOUNT_DAX) {
 		ext2_msg(sb, KERN_WARNING, "warning: refusing change of "
-			 "xip flag with busy inodes while remounting");
-		sbi->s_mount_opt ^= EXT2_MOUNT_XIP;
+			 "dax flag with busy inodes while remounting");
+		sbi->s_mount_opt ^= EXT2_MOUNT_DAX;
 	}
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		spin_unlock(&sbi->s_lock);

index 15654ce..c6c15c3 100644
@@ -424,13 +424,16 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 EXPORT_SYMBOL_GPL(dax_fault);
 
 /**
- * dax_truncate_page - handle a partial page being truncated in a DAX file
+ * dax_zero_page_range - zero a range within a page of a DAX file
  * @inode: The file being truncated
  * @from: The file offset that is being truncated to
+ * @length: The number of bytes to zero
  * @get_block: The filesystem method used to translate file offsets to blocks
  *
- * Similar to block_truncate_page(), this function can be called by a
- * filesystem when it is truncating an DAX file to handle the partial page.
+ * This function can be called by a filesystem when it is zeroing part of a
+ * page in a DAX file.  This is intended for hole-punch operations.  If
+ * you are truncating a file, the helper function dax_truncate_page() may be
+ * more convenient.
  *
  * We work in terms of PAGE_CACHE_SIZE here for commonality with
  * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem

@@ -438,12 +441,12 @@ EXPORT_SYMBOL_GPL(dax_fault);
  * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
  * since the file might be mmaped.
  */
-int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
+int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
+							get_block_t get_block)
 {
 	struct buffer_head bh;
 	pgoff_t index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned length = PAGE_CACHE_ALIGN(from) - from;
 	int err;
 
 	/* Block boundary? Nothing to do */

@@ -460,9 +463,14 @@ int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
 		err = dax_get_addr(&bh, &addr, inode->i_blkbits);
 		if (err < 0)
 			return err;
+		/*
+		 * ext4 sometimes asks to zero past the end of a block.  It
+		 * really just wants to zero to the end of the block.
+		 */
+		length = min_t(unsigned, length, PAGE_CACHE_SIZE - offset);
 		memset(addr + offset, 0, length);
 	}
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dax_truncate_page);
+EXPORT_SYMBOL_GPL(dax_zero_page_range);

index 79b0cbe..8da9a0e 100644
@@ -2463,6 +2463,7 @@ extern int nonseekable_open(struct inode * inode, struct file * filp);
 
 #ifdef CONFIG_FS_DAX
 int dax_clear_blocks(struct inode *, sector_t block, long size);
+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);
 ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
 		loff_t, get_block_t, dio_iodone_t, int flags);

@@ -2474,7 +2475,8 @@ static inline int dax_clear_blocks(struct inode *i, sector_t blk, long sz)
 	return 0;
 }
 
-static inline int dax_truncate_page(struct inode *i, loff_t frm, get_block_t gb)
+static inline int dax_zero_page_range(struct inode *inode, loff_t from,
+						unsigned len, get_block_t gb)
 {
 	return 0;
 }

@@ -2487,6 +2489,11 @@ static inline ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
 }
 #endif
 
+/* Can't be a function because PAGE_CACHE_SIZE is defined in pagemap.h */
+#define dax_truncate_page(inode, from, get_block)	\
+	dax_zero_page_range(inode, from, PAGE_CACHE_SIZE, get_block)
+
+
 #ifdef CONFIG_BLOCK
 typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
 			    loff_t file_offset);

index 8a06473..494a864 100644
@@ -3631,13 +3631,19 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
-	/* Now release the pages again to reduce race window */
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+
+	/*
+	 * Now release the pages again to reduce race window. This has to happen
+	 * outside of a transaction to avoid lock inversion on i_mmap_mutex
+	 * when DAX is enabled.
+	 */
 	if (last_block_offset > first_block_offset)
 		truncate_pagecache_range(inode, first_block_offset,
 					 last_block_offset);
-
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
+	goto out_dio;
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:

index 7cc5a0e..a9687b3 100644
@@ -970,6 +970,11 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_ERRORS_MASK		0x00070
 #define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
 #define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
+#ifdef CONFIG_FS_DAX
+#define EXT4_MOUNT_DAX			0x00200	/* Execute in place */
+#else
+#define EXT4_MOUNT_DAX			0
+#endif
 #define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
 #define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */
 #define EXT4_MOUNT_ORDERED_DATA		0x00800	/* Flush data before commit */

@@ -2557,6 +2562,7 @@ extern const struct file_operations ext4_dir_operations;
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
+extern const struct file_operations ext4_dax_file_operations;
 extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
 
 /* inline.c */

78 lines not on this page · raw message

index fd69da1..a07578c 100644
@@ -691,14 +691,22 @@ retry:
 			inode_dio_done(inode);
 			goto locked;
 		}
-		ret = __blockdev_direct_IO(rw, iocb, inode,
-				 inode->i_sb->s_bdev, iter, offset,
-				 ext4_get_block, NULL, NULL, 0);
+		if (IS_DAX(inode))
+			ret = dax_do_io(rw, iocb, inode, iter, offset,
+					ext4_get_block, NULL, 0);
+		else
+			ret = __blockdev_direct_IO(rw, iocb, inode,
+					inode->i_sb->s_bdev, iter, offset,
+					ext4_get_block, NULL, NULL, 0);
 		inode_dio_done(inode);
 	} else {
 locked:
-		ret = blockdev_direct_IO(rw, iocb, inode, iter,
-				 offset, ext4_get_block);
+		if (IS_DAX(inode))
+			ret = dax_do_io(rw, iocb, inode, iter, offset,
+					ext4_get_block, NULL, DIO_LOCKING);
+		else
+			ret = blockdev_direct_IO(rw, iocb, inode, iter,
+					offset, ext4_get_block);
 
 		if (unlikely((rw & WRITE) && ret < 0)) {
 			loff_t isize = i_size_read(inode);

88 lines not on this page · raw message

index 3520ab8..2ef6adf 100644
@@ -2251,7 +2251,10 @@ retry:
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 		err = ext4_add_nondir(handle, dentry, inode);
 		if (!err && IS_DIRSYNC(dir))

@@ -2315,7 +2318,10 @@ retry:
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 		d_tmpfile(dentry, inode);
 		err = ext4_orphan_add(handle, inode);

index 6df7bc6..41bb01e 100644
@@ -1162,7 +1162,7 @@ enum {
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
-	Opt_usrquota, Opt_grpquota, Opt_i_version,
+	Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_dax,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,

@@ -1224,6 +1224,7 @@ static const match_table_t tokens = {
 	{Opt_barrier, "barrier"},
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_i_version, "i_version"},
+	{Opt_dax, "dax"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_nodelalloc, "nodelalloc"},

@@ -1406,6 +1407,7 @@ static const struct mount_opts {
 	{Opt_min_batch_time, 0, MOPT_GTE0},
 	{Opt_inode_readahead_blks, 0, MOPT_GTE0},
 	{Opt_init_itable, 0, MOPT_GTE0},
+	{Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
 	{Opt_stripe, 0, MOPT_GTE0},
 	{Opt_resuid, 0, MOPT_GTE0},
 	{Opt_resgid, 0, MOPT_GTE0},

@@ -1642,6 +1644,11 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
+#ifndef CONFIG_FS_DAX
+	} else if (token == Opt_dax) {
+		ext4_msg(sb, KERN_INFO, "dax option not supported");
+		return -1;
+#endif
 	} else {
 		if (!args->from)
 			arg = 1;

@@ -3575,6 +3582,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "both data=journal and dioread_nolock");
 			goto failed_mount;
 		}
+		if (test_opt(sb, DAX)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and dax");
+			goto failed_mount;
+		}
 		if (test_opt(sb, DELALLOC))
 			clear_opt(sb, DELALLOC);
 	}

@@ -3638,6 +3650,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+	if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+		if (blocksize != PAGE_SIZE) {
+			ext4_msg(sb, KERN_ERR,
+					"error: unsupported blocksize for dax");
+			goto failed_mount;
+		}
+		if (!sb->s_bdev->bd_disk->fops->direct_access) {
+			ext4_msg(sb, KERN_ERR,
+					"error: device does not support dax");
+			goto failed_mount;
+		}
+	}
+
 	if (sb->s_blocksize != blocksize) {
 		/* Validate the filesystem blocksize */
 		if (!sb_set_blocksize(sb, blocksize)) {

@@ -4846,6 +4871,18 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			err = -EINVAL;
 			goto restore_opts;
 		}
+		if (test_opt(sb, DAX)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and dax");
+			err = -EINVAL;
+			goto restore_opts;
+		}
+	}
+
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
+		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
+			"dax flag with busy inodes while remounting");
+		sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
 	}
 
 	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)

index a10a0a9..3483458 100644
@@ -97,13 +97,13 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
 	 * Must use NOIO because we don't want to recurse back into the
 	 * block or filesystem layers from page reclaim.
 	 *
-	 * Cannot support XIP and highmem, because our ->direct_access
-	 * routine for XIP must return memory that is always addressable.
-	 * If XIP was reworked to use pfns and kmap throughout, this
+	 * Cannot support DAX and highmem, because our ->direct_access
+	 * routine for DAX must return memory that is always addressable.
+	 * If DAX was reworked to use pfns and kmap throughout, this
 	 * restriction might be able to be lifted.
 	 */
 	gfp_flags = GFP_NOIO | __GFP_ZERO;
-#ifndef CONFIG_BLK_DEV_XIP
+#ifndef CONFIG_BLK_DEV_RAM_DAX
 	gfp_flags |= __GFP_HIGHMEM;
 #endif
 	page = alloc_page(gfp_flags);

@@ -369,7 +369,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 	return err;
 }
 
-#ifdef CONFIG_BLK_DEV_XIP
+#ifdef CONFIG_BLK_DEV_RAM_DAX
 static long brd_direct_access(struct block_device *bdev, sector_t sector,
 			void **kaddr, unsigned long *pfn, long size)
 {

@@ -388,6 +388,8 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
 	 * file is mapped to the next page of physical RAM */
 	return min_t(long, PAGE_SIZE, size);
 }
+#else
+#define brd_direct_access NULL
 #endif
 
 static int brd_ioctl(struct block_device *bdev, fmode_t mode,

@@ -428,9 +430,7 @@ static const struct block_device_operations brd_fops = {
 	.owner =		THIS_MODULE,
 	.rw_page =		brd_rw_page,
 	.ioctl =		brd_ioctl,
-#ifdef CONFIG_BLK_DEV_XIP
 	.direct_access =	brd_direct_access,
-#endif
 };
 
 /*

195 lines not on this page · raw message

index 7c87b22..a247123 100644
@@ -81,8 +81,10 @@ const struct file_operations ext2_file_operations = {
 #ifdef CONFIG_EXT2_FS_XIP
 const struct file_operations ext2_xip_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= xip_file_read,
-	.write		= xip_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.unlocked_ioctl = ext2_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,

index 0cb0448..3ccd5fd 100644
@@ -859,7 +859,12 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext2_get_block);
+	if (IS_DAX(inode))
+		ret = dax_do_io(rw, iocb, inode, iter, offset, ext2_get_block,
+				NULL, DIO_LOCKING);
+	else
+		ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+					 ext2_get_block);
 	if (ret < 0 && (rw & WRITE))
 		ext2_write_failed(mapping, offset + count);
 	return ret;

@@ -888,6 +893,7 @@ const struct address_space_operations ext2_aops = {
 const struct address_space_operations ext2_aops_xip = {
 	.bmap			= ext2_bmap,
 	.get_xip_mem		= ext2_get_xip_mem,
+	.direct_IO		= ext2_direct_IO,
 };
 
 const struct address_space_operations ext2_nobh_aops = {

index a94e5d7..87a135a 100644
@@ -2463,17 +2463,22 @@ extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
 #ifdef CONFIG_FS_XIP
-extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
-			     loff_t *ppos);
 extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
-extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
-			      size_t len, loff_t *ppos);
 extern int xip_truncate_page(struct address_space *mapping, loff_t from);
+ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
+		loff_t, get_block_t, dio_iodone_t, int flags);
 #else
 static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
 {
 	return 0;
 }
+
+static inline ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
+		const struct iovec *iov, loff_t pos, unsigned nr_segs,
+		get_block_t get_block, dio_iodone_t end_io, int flags)
+{
+	return -ENOTTY;
+}
 #endif
 
 #ifdef CONFIG_BLOCK

@@ -2630,6 +2635,11 @@ extern int generic_show_options(struct seq_file *m, struct dentry *root);
 extern void save_mount_options(struct super_block *sb, char *options);
 extern void replace_mount_options(struct super_block *sb, char *options);
 
+static inline bool io_is_direct(struct file *filp)
+{
+	return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
+}
+
 static inline ino_t parent_ino(struct dentry *dentry)
 {
 	ino_t res;

index 900edfa..bc588fa 100644
@@ -1684,8 +1684,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	loff_t *ppos = &iocb->ki_pos;
 	loff_t pos = *ppos;
 
-	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (file->f_flags & O_DIRECT) {
+	if (io_is_direct(file)) {
 		struct address_space *mapping = file->f_mapping;
 		struct inode *inode = mapping->host;
 		size_t count = iov_iter_count(iter);

@@ -2561,8 +2560,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (err)
 		goto out;
 
-	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (unlikely(file->f_flags & O_DIRECT)) {
+	if (io_is_direct(file)) {
 		loff_t endbyte;
 
 		written = generic_file_direct_write(iocb, from, pos);

246 lines not on this page · raw message