Merge branch 'akpm' (patches from Andrew)

Merge fifth set of updates from Andrew Morton:

 - A few things which were awaiting merges from linux-next:
     - rtc
     - ocfs2
     - misc others

 - Willy's "dax" feature: direct fs access to memory (mainly NV-DIMMs)
   which isn't backed by pageframes.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (37 commits)
  rtc: add driver for DS1685 family of real time clocks
  MAINTAINERS: add entry for Maxim PMICs on Samsung boards
  lib/Kconfig: use bool instead of boolean
  powerpc: drop _PAGE_FILE and pte_file()-related helpers
  ocfs2: set append dio as a ro compat feature
  ocfs2: wait for orphan recovery first once append O_DIRECT write crash
  ocfs2: complete the rest request through buffer io
  ocfs2: do not fallback to buffer I/O write if appending
  ocfs2: allocate blocks in ocfs2_direct_IO_get_blocks
  ocfs2: implement ocfs2_direct_IO_write
  ocfs2: add orphan recovery types in ocfs2_recover_orphans
  ocfs2: add functions to add and remove inode in orphan dir
  ocfs2: prepare some interfaces used in append direct io
  MAINTAINERS: fix spelling mistake & remove trailing WS
  dax: does not work correctly with virtual aliasing caches
  brd: rename XIP to DAX
  ext4: add DAX functionality
  dax: add dax_zero_page_range
  ext2: get rid of most mentions of XIP in ext2
  ext2: remove ext2_aops_xip
  ...

Documentation/filesystems/00-INDEX

@@ -34,6 +34,9 @@ configfs/
 	- directory containing configfs documentation and example code.
 cramfs.txt
 	- info on the cram filesystem for small storage (ROMs etc).
+dax.txt
+	- info on avoiding the page cache for files stored on CPU-addressable
+	  storage devices.
 debugfs.txt
 	- info on the debugfs filesystem.
 devpts.txt
@@ -154,5 +157,3 @@ xfs-self-describing-metadata.txt
 	- info on XFS Self Describing Metadata.
 xfs.txt
 	- info and mount options for the XFS filesystem.
-xip.txt
-	- info on execute-in-place for file mappings.

Documentation/filesystems/Locking

@@ -199,8 +199,6 @@ prototypes:
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
 	int (*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 *);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
 	int (*launder_page)(struct page *);
 	int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
@@ -225,7 +223,6 @@ invalidatepage:		yes
 releasepage:		yes
 freepage:		yes
 direct_IO:
-get_xip_mem:					maybe
 migratepage:		yes (both)
 launder_page:		yes
 is_partially_uptodate:	yes

Documentation/filesystems/dax.txt

+Direct Access for files
+-----------------------
+
+Motivation
+----------
+
+The page cache is usually used to buffer reads and writes to files.
+It is also used to provide the pages which are mapped into userspace
+by a call to mmap.
+
+For block devices that are memory-like, the page cache pages would be
+unnecessary copies of the original storage.  The DAX code removes the
+extra copy by performing reads and writes directly to the storage device.
+For file mappings, the storage device is mapped directly into userspace.
+
+
+Usage
+-----
+
+If you have a block device which supports DAX, you can make a filesystem
+on it as usual.  When mounting it, use the -o dax option manually
+or add 'dax' to the options in /etc/fstab.
+
+
+Implementation Tips for Block Driver Writers
+--------------------------------------------
+
+To support DAX in your block driver, implement the 'direct_access'
+block device operation.  It is used to translate the sector number
+(expressed in units of 512-byte sectors) to a page frame number (pfn)
+that identifies the physical page for the memory.  It also returns a
+kernel virtual address that can be used to access the memory.
+
+The direct_access method takes a 'size' parameter that indicates the
+number of bytes being requested.  The function should return the number
+of bytes that can be contiguously accessed at that offset.  It may also
+return a negative errno if an error occurs.
+
+In order to support this method, the storage must be byte-accessible by
+the CPU at all times.  If your device uses paging techniques to expose
+a large amount of memory through a smaller window, then you cannot
+implement direct_access.  Equally, if your device can occasionally
+stall the CPU for an extended period, you should also not attempt to
+implement direct_access.
+
+These block devices may be used for inspiration:
+- axonram: Axon DDR2 device driver
+- brd: RAM backed block device driver
+- dcssblk: s390 dcss block device driver
+
+
+Implementation Tips for Filesystem Writers
+------------------------------------------
+
+Filesystem support consists of
+- adding support to mark inodes as being DAX by setting the S_DAX flag in
+  i_flags
+- implementing the direct_IO address space operation, and calling
+  dax_do_io() instead of blockdev_direct_IO() if S_DAX is set
+- implementing an mmap file operation for DAX files which sets the
+  VM_MIXEDMAP flag on the VMA, and setting the vm_ops to include handlers
+  for fault and page_mkwrite (which should probably call dax_fault() and
+  dax_mkwrite(), passing the appropriate get_block() callback)
+- calling dax_truncate_page() instead of block_truncate_page() for DAX files
+- calling dax_zero_page_range() instead of zero_user() for DAX files
+- ensuring that there is sufficient locking between reads, writes,
+  truncates and page faults
+
+The get_block() callback passed to the DAX functions may return
+uninitialised extents.  If it does, it must ensure that simultaneous
+calls to get_block() (for example by a page-fault racing with a read()
+or a write()) work correctly.
+
+These filesystems may be used for inspiration:
+- ext2: the second extended filesystem, see Documentation/filesystems/ext2.txt
+- ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt
+
+
+Shortcomings
+------------
+
+Even if the kernel or its modules are stored on a filesystem that supports
+DAX on a block device that supports DAX, they will still be copied into RAM.
+
+The DAX code does not work correctly on architectures which have virtually
+mapped caches such as ARM, MIPS and SPARC.
+
+Calling get_user_pages() on a range of user memory that has been mmaped
+from a DAX file will fail as there are no 'struct page' to describe
+those pages.  This problem is being worked on.  That means that O_DIRECT
+reads/writes to those memory ranges from a non-DAX file will fail (note
+that O_DIRECT reads/writes _of a DAX file_ do work, it is the memory
+that is being accessed that is key here).  Other things that will not
+work include RDMA, sendfile() and splice().

Documentation/filesystems/ext2.txt

@@ -20,6 +20,9 @@ minixdf				Makes `df' act like Minix.
 check=none, nocheck	(*)	Don't do extra checking of bitmaps on mount
 				(check=normal and check=strict options removed)
 
+dax				Use direct access (no page cache).  See
+				Documentation/filesystems/dax.txt.
+
 debug				Extra debugging information is sent to the
 				kernel syslog.  Useful for developers.
 
@@ -56,8 +59,6 @@ noacl				Don't support POSIX ACLs.
 
 nobh				Do not attach buffer_heads to file pagecache.
 
-xip				Use execute in place (no caching) if possible
-
 grpquota,noquota,quota,usrquota	Quota options are silently ignored by ext2.
 
 

Documentation/filesystems/ext4.txt

@@ -386,6 +386,10 @@ max_dir_size_kb=n	This limits the size of directories so that any
 i_version		Enable 64-bit inode version support. This option is
 			off by default.
 
+dax			Use direct access (no page cache).  See
+			Documentation/filesystems/dax.txt.  Note that
+			this option is incompatible with data=journal.
+
 Data Mode
 =========
 There are 3 different data modes:

Documentation/filesystems/vfs.txt

@@ -591,8 +591,6 @@ struct address_space_operations {
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
-	struct page* (*get_xip_page)(struct address_space *, sector_t,
-			int);
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
@@ -748,11 +746,6 @@ struct address_space_operations {
         and transfer data directly between the storage and the
         application's address space.
 
-  get_xip_page: called by the VM to translate a block number to a page.
-	The page is valid until the corresponding filesystem is unmounted.
-	Filesystems that want to use execute-in-place (XIP) need to implement
-	it.  An example implementation can be found in fs/ext2/xip.c.
-
   migrate_page:  This is used to compact the physical memory usage.
         If the VM wants to relocate a page (maybe off a memory card
         that is signalling imminent failure) it will pass a new page

Documentation/filesystems/xip.txt

-Execute-in-place for file mappings
-----------------------------------
-
-Motivation
-----------
-File mappings are performed by mapping page cache pages to userspace. In
-addition, read&write type file operations also transfer data from/to the page
-cache.
-
-For memory backed storage devices that use the block device interface, the page
-cache pages are in fact copies of the original storage. Various approaches
-exist to work around the need for an extra copy. The ramdisk driver for example
-does read the data into the page cache, keeps a reference, and discards the
-original data behind later on.
-
-Execute-in-place solves this issue the other way around: instead of keeping
-data in the page cache, the need to have a page cache copy is eliminated
-completely. With execute-in-place, read&write type operations are performed
-directly from/to the memory backed storage device. For file mappings, the
-storage device itself is mapped directly into userspace.
-
-This implementation was initially written for shared memory segments between
-different virtual machines on s390 hardware to allow multiple machines to
-share the same binaries and libraries.
-
-Implementation
---------------
-Execute-in-place is implemented in three steps: block device operation,
-address space operation, and file operations.
-
-A block device operation named direct_access is used to translate the
-block device sector number to a page frame number (pfn) that identifies
-the physical page for the memory.  It also returns a kernel virtual
-address that can be used to access the memory.
-
-The direct_access method takes a 'size' parameter that indicates the
-number of bytes being requested.  The function should return the number
-of bytes that can be contiguously accessed at that offset.  It may also
-return a negative errno if an error occurs.
-
-The block device operation is optional, these block devices support it as of
-today:
-- dcssblk: s390 dcss block device driver
-
-An address space operation named get_xip_mem is used to retrieve references
-to a page frame number and a kernel address. To obtain these values a reference
-to an address_space is provided. This function assigns values to the kmem and
-pfn parameters. The third argument indicates whether the function should allocate
-blocks if needed.
-
-This address space operation is mutually exclusive with readpage&writepage that
-do page cache read/write operations.
-The following filesystems support it as of today:
-- ext2: the second extended filesystem, see Documentation/filesystems/ext2.txt
-
-A set of file operations that do utilize get_xip_page can be found in
-mm/filemap_xip.c . The following file operation implementations are provided:
-- aio_read/aio_write
-- readv/writev
-- sendfile
-
-The generic file operations do_sync_read/do_sync_write can be used to implement
-classic synchronous IO calls.
-
-Shortcomings
-------------
-This implementation is limited to storage devices that are cpu addressable at
-all times (no highmem or such). It works well on rom/ram, but enhancements are
-needed to make it work with flash in read+write mode.
-Putting the Linux kernel and/or its modules on a xip filesystem does not mean
-they are not copied.

MAINTAINERS

@@ -34,7 +34,7 @@ trivial patch so apply some common sense.
 	generalized kernel feature ready for next time.
 
 	PLEASE check your patch with the automated style checker
-	(scripts/checkpatch.pl) to catch trival style violations.
+	(scripts/checkpatch.pl) to catch trivial style violations.
 	See Documentation/CodingStyle for guidance here.
 
 	PLEASE CC: the maintainers and mailing lists that are generated
@@ -2965,6 +2965,12 @@ S:	Supported
 F:	drivers/input/touchscreen/cyttsp*
 F:	include/linux/input/cyttsp.h
 
+DALLAS/MAXIM DS1685-FAMILY REAL TIME CLOCK
+M:	Joshua Kinard <kumba@gentoo.org>
+S:	Maintained
+F:	drivers/rtc/rtc-ds1685.c
+F:	include/linux/rtc/ds1685.h
+
 DAMA SLAVE for AX.25
 M:	Joerg Reuter <jreuter@yaina.de>
 W:	http://yaina.de/jreuter/
@@ -3153,6 +3159,12 @@ L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-diolan-u2c.c
 
+DIRECT ACCESS (DAX)
+M:	Matthew Wilcox <willy@linux.intel.com>
+L:	linux-fsdevel@vger.kernel.org
+S:	Supported
+F:	fs/dax.c
+
 DIRECTORY NOTIFICATION (DNOTIFY)
 M:	Eric Paris <eparis@parisplace.org>
 S:	Maintained
@@ -6212,6 +6224,26 @@ S:	Supported
 F:	drivers/power/max14577_charger.c
 F:	drivers/power/max77693_charger.c
 
+MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS
+M:	Chanwoo Choi <cw00.choi@samsung.com>
+M:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+F:	drivers/*/max14577.c
+F:	drivers/*/max77686.c
+F:	drivers/*/max77693.c
+F:	drivers/extcon/extcon-max14577.c
+F:	drivers/extcon/extcon-max77693.c
+F:	drivers/rtc/rtc-max77686.c
+F:	drivers/clk/clk-max77686.c
+F:	Documentation/devicetree/bindings/mfd/max14577.txt
+F:	Documentation/devicetree/bindings/mfd/max77686.txt
+F:	Documentation/devicetree/bindings/mfd/max77693.txt
+F:	Documentation/devicetree/bindings/clock/maxim,max77686.txt
+F:	include/linux/mfd/max14577*.h
+F:	include/linux/mfd/max77686*.h
+F:	include/linux/mfd/max77693*.h
+
 MAXIRADIO FM RADIO RECEIVER DRIVER
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org

arch/arm/boot/dts/zynq-parallella.dts

@@ -58,7 +58,7 @@ &i2c0 {
 	status = "okay";
 
 	isl9305: isl9305@68 {
-		compatible = "isl,isl9305";
+		compatible = "isil,isl9305";
 		reg = <0x68>;
 
 		regulators {

arch/powerpc/include/asm/pgtable-ppc32.h

@@ -333,8 +333,8 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 /*
  * Encode and decode a swap entry.
  * Note that the bits we use in a PTE for representing a swap entry
- * must not include the _PAGE_PRESENT bit, the _PAGE_FILE bit, or the
- *_PAGE_HASHPTE bit (if used).  -- paulus
+ * must not include the _PAGE_PRESENT bit or the _PAGE_HASHPTE bit (if used).
+ *   -- paulus
  */
 #define __swp_type(entry)		((entry).val & 0x1f)
 #define __swp_offset(entry)		((entry).val >> 5)
@@ -342,11 +342,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
-/* Encode and decode a nonlinear file mapping entry */
-#define PTE_FILE_MAX_BITS	29
-#define pte_to_pgoff(pte)	(pte_val(pte) >> 3)
-#define pgoff_to_pte(off)	((pte_t) { ((off) << 3) | _PAGE_FILE })
-
 #ifndef CONFIG_PPC_4K_PAGES
 void pgtable_cache_init(void);
 #else

arch/powerpc/include/asm/pgtable-ppc64.h

@@ -352,9 +352,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define __swp_entry(type, offset) ((swp_entry_t){((type)<< 1)|((offset)<<8)})
 #define __pte_to_swp_entry(pte)	((swp_entry_t){pte_val(pte) >> PTE_RPN_SHIFT})
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val << PTE_RPN_SHIFT })
-#define pte_to_pgoff(pte)	(pte_val(pte) >> PTE_RPN_SHIFT)
-#define pgoff_to_pte(off)	((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})
-#define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_RPN_SHIFT)
 
 void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
@@ -389,7 +386,7 @@ void pgtable_cache_init(void);
  * The last three bits are intentionally left to zero. This memory location
  * are also used as normal page PTE pointers. So if we have any pointers
  * left around while we collapse a hugepage, we need to make sure
- * _PAGE_PRESENT and _PAGE_FILE bits of that are zero when we look at them
+ * _PAGE_PRESENT bit of that is zero when we look at them
  */
 static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
 {

arch/powerpc/include/asm/pgtable.h

@@ -34,7 +34,6 @@ static inline int pte_write(pte_t pte)
 {	return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO; }
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
-static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
 static inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL; }
 static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
 static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }

arch/powerpc/include/asm/pte-40x.h

@@ -38,7 +38,6 @@
  */
 
 #define	_PAGE_GUARDED	0x001	/* G: page is guarded from prefetch */
-#define _PAGE_FILE	0x001	/* when !present: nonlinear file mapping */
 #define _PAGE_PRESENT	0x002	/* software: PTE contains a translation */
 #define	_PAGE_NO_CACHE	0x004	/* I: caching is inhibited */
 #define	_PAGE_WRITETHRU	0x008	/* W: caching is write-through */

arch/powerpc/include/asm/pte-44x.h

@@ -44,9 +44,6 @@
  *   - PRESENT *must* be in the bottom three bits because swap cache
  *     entries use the top 29 bits for TLB2.
  *
- *   - FILE *must* be in the bottom three bits because swap cache
- *     entries use the top 29 bits for TLB2.
- *
  *   - CACHE COHERENT bit (M) has no effect on original PPC440 cores,
  *     because it doesn't support SMP. However, some later 460 variants
  *     have -some- form of SMP support and so I keep the bit there for
@@ -68,7 +65,6 @@
  *
  * There are three protection bits available for SWAP entry:
  *	_PAGE_PRESENT
- *	_PAGE_FILE
  *	_PAGE_HASHPTE (if HW has)
  *
  * So those three bits have to be inside of 0-2nd LSB of PTE.
@@ -77,7 +73,6 @@
 
 #define _PAGE_PRESENT	0x00000001		/* S: PTE valid */
 #define _PAGE_RW	0x00000002		/* S: Write permission */
-#define _PAGE_FILE	0x00000004		/* S: nonlinear file mapping */
 #define _PAGE_EXEC	0x00000004		/* H: Execute permission */
 #define _PAGE_ACCESSED	0x00000008		/* S: Page referenced */
 #define _PAGE_DIRTY	0x00000010		/* S: Page dirty */

arch/powerpc/include/asm/pte-8xx.h

@@ -29,7 +29,6 @@
 
 /* Definitions for 8xx embedded chips. */
 #define _PAGE_PRESENT	0x0001	/* Page is valid */
-#define _PAGE_FILE	0x0002	/* when !present: nonlinear file mapping */
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
 #define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */

arch/powerpc/include/asm/pte-book3e.h

@@ -10,7 +10,6 @@
 
 /* Architected bits */
 #define _PAGE_PRESENT	0x000001 /* software: pte contains a translation */
-#define _PAGE_FILE	0x000002 /* (!present only) software: pte holds file offset */
 #define _PAGE_SW1	0x000002
 #define _PAGE_BAP_SR	0x000004
 #define _PAGE_BAP_UR	0x000008

arch/powerpc/include/asm/pte-fsl-booke.h

@@ -13,14 +13,11 @@
    - PRESENT *must* be in the bottom three bits because swap cache
      entries use the top 29 bits.
 
-   - FILE *must* be in the bottom three bits because swap cache
-     entries use the top 29 bits.
 */
 
 /* Definitions for FSL Book-E Cores */
 #define _PAGE_PRESENT	0x00001	/* S: PTE contains a translation */
 #define _PAGE_USER	0x00002	/* S: User page (maps to UR) */
-#define _PAGE_FILE	0x00002	/* S: when !present: nonlinear file mapping */
 #define _PAGE_RW	0x00004	/* S: Write permission (SW) */
 #define _PAGE_DIRTY	0x00008	/* S: Page dirty */
 #define _PAGE_EXEC	0x00010	/* H: SX permission */

arch/powerpc/include/asm/pte-hash32.h

@@ -18,7 +18,6 @@
 
 #define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
 #define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
-#define _PAGE_FILE	0x004	/* when !present: nonlinear file mapping */
 #define _PAGE_USER	0x004	/* usermode access allowed */
 #define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
 #define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */

arch/powerpc/include/asm/pte-hash64.h

@@ -16,7 +16,6 @@
  */
 #define _PAGE_PRESENT		0x0001 /* software: pte contains a translation */
 #define _PAGE_USER		0x0002 /* matches one of the PP bits */
-#define _PAGE_FILE		0x0002 /* (!present only) software: pte holds file offset */
 #define _PAGE_EXEC		0x0004 /* No execute on POWER4 and newer (we invert) */
 #define _PAGE_GUARDED		0x0008
 /* We can derive Memory coherence from _PAGE_NO_CACHE */

arch/powerpc/mm/pgtable_64.c

@@ -782,7 +782,7 @@ pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
 {
 	pmd_t pmd;
 	/*
-	 * For a valid pte, we would have _PAGE_PRESENT or _PAGE_FILE always
+	 * For a valid pte, we would have _PAGE_PRESENT always
 	 * set. We use this to check THP page at pmd level.
 	 * leaf pte for huge page, bottom two bits != 00
 	 */

drivers/block/Kconfig

@@ -393,14 +393,15 @@ config BLK_DEV_RAM_SIZE
 	  The default value is 4096 kilobytes. Only change this if you know
 	  what you are doing.
 
-config BLK_DEV_XIP
-	bool "Support XIP filesystems on RAM block device"
-	depends on BLK_DEV_RAM
+config BLK_DEV_RAM_DAX
+	bool "Support Direct Access (DAX) to RAM block devices"
+	depends on BLK_DEV_RAM && FS_DAX
 	default n
 	help
-	  Support XIP filesystems (such as ext2 with XIP support on) on
-	  top of block ram device. This will slightly enlarge the kernel, and
-	  will prevent RAM block device backing store memory from being
+	  Support filesystems using DAX to access RAM block devices.  This
+	  avoids double-buffering data in the page cache before copying it
+	  to the block device.  Answering Y will slightly enlarge the kernel,
+	  and will prevent RAM block device backing store memory from being
 	  allocated from highmem (only a problem for highmem systems).
 
 config CDROM_PKTCDVD

drivers/block/brd.c

@@ -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)
 {
@@ -390,6 +390,8 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
 	 */
 	return PAGE_SIZE;
 }
+#else
+#define brd_direct_access NULL
 #endif
 
 static int brd_ioctl(struct block_device *bdev, fmode_t mode,
@@ -430,9 +432,7 @@ 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
 };
 
 /*

drivers/rtc/Kconfig

@@ -801,6 +801,96 @@ config RTC_DRV_DS1553
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-ds1553.
 
+config RTC_DRV_DS1685_FAMILY
+	tristate "Dallas/Maxim DS1685 Family"
+	help
+	  If you say yes here you get support for the Dallas/Maxim DS1685
+	  family of real time chips.  This family includes the DS1685/DS1687,
+	  DS1689/DS1693, DS17285/DS17287, DS17485/DS17487, and
+	  DS17885/DS17887 chips.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-ds1685.
+
+choice
+	prompt "Subtype"
+	depends on RTC_DRV_DS1685_FAMILY
+	default RTC_DRV_DS1685
+
+config RTC_DRV_DS1685
+	bool "DS1685/DS1687"
+	help
+	  This enables support for the Dallas/Maxim DS1685/DS1687 real time
+	  clock chip.
+
+	  This chip is commonly found in SGI O2 (IP32) and SGI Octane (IP30)
+	  systems, as well as EPPC-405-UC modules by electronic system design
+	  GmbH.
+
+config RTC_DRV_DS1689
+	bool "DS1689/DS1693"
+	help
+	  This enables support for the Dallas/Maxim DS1689/DS1693 real time
+	  clock chip.
+
+	  This is an older RTC chip, supplanted by the DS1685/DS1687 above,
+	  which supports a few minor features such as Vcc, Vbat, and Power
+	  Cycle counters, plus a customer-specific, 8-byte ROM/Serial number.
+
+	  It also works for the even older DS1688/DS1691 RTC chips, which are
+	  virtually the same and carry the same model number.  Both chips
+	  have 114 bytes of user NVRAM.
+
+config RTC_DRV_DS17285
+	bool "DS17285/DS17287"
+	help
+	  This enables support for the Dallas/Maxim DS17285/DS17287 real time
+	  clock chip.
+
+	  This chip features 2kb of extended NV-SRAM.  It may possibly be
+	  found in some SGI O2 systems (rare).
+
+config RTC_DRV_DS17485
+	bool "DS17485/DS17487"
+	help
+	  This enables support for the Dallas/Maxim DS17485/DS17487 real time
+	  clock chip.
+
+	  This chip features 4kb of extended NV-SRAM.
+
+config RTC_DRV_DS17885
+	bool "DS17885/DS17887"
+	help
+	  This enables support for the Dallas/Maxim DS17885/DS17887 real time
+	  clock chip.
+
+	  This chip features 8kb of extended NV-SRAM.
+
+endchoice
+
+config RTC_DS1685_PROC_REGS
+	bool "Display register values in /proc"
+	depends on RTC_DRV_DS1685_FAMILY && PROC_FS
+	help
+	  Enable this to display a readout of all of the RTC registers in
+	  /proc/drivers/rtc.  Keep in mind that this can potentially lead
+	  to lost interrupts, as reading Control Register C will clear
+	  all pending IRQ flags.
+
+	  Unless you are debugging this driver, choose N.
+
+config RTC_DS1685_SYSFS_REGS
+	bool "SysFS access to RTC register bits"
+	depends on RTC_DRV_DS1685_FAMILY && SYSFS
+	help
+	  Enable this to provide access to the RTC control register bits
+	  in /sys.  Some of the bits are read-write, others are read-only.
+
+	  Keep in mind that reading Control C's bits automatically clears
+	  all pending IRQ flags - this can cause lost interrupts.
+
+	  If you know that you need access to these bits, choose Y, Else N.
+
 config RTC_DRV_DS1742
 	tristate "Maxim/Dallas DS1742/1743"
 	depends on HAS_IOMEM

drivers/rtc/Makefile

@@ -54,6 +54,7 @@ obj-$(CONFIG_RTC_DRV_DS1390)	+= rtc-ds1390.o
 obj-$(CONFIG_RTC_DRV_DS1511)	+= rtc-ds1511.o
 obj-$(CONFIG_RTC_DRV_DS1553)	+= rtc-ds1553.o
 obj-$(CONFIG_RTC_DRV_DS1672)	+= rtc-ds1672.o
+obj-$(CONFIG_RTC_DRV_DS1685_FAMILY)	+= rtc-ds1685.o
 obj-$(CONFIG_RTC_DRV_DS1742)	+= rtc-ds1742.o
 obj-$(CONFIG_RTC_DRV_DS2404)    += rtc-ds2404.o
 obj-$(CONFIG_RTC_DRV_DS3232)	+= rtc-ds3232.o

drivers/rtc/rtc-isl12022.c

@@ -275,7 +275,8 @@ static int isl12022_probe(struct i2c_client *client,
 
 #ifdef CONFIG_OF
 static const struct of_device_id isl12022_dt_match[] = {
-	{ .compatible = "isl,isl12022" },
+	{ .compatible = "isl,isl12022" }, /* for backward compat., don't use */
+	{ .compatible = "isil,isl12022" },
 	{ },
 };
 #endif

drivers/rtc/rtc-isl12057.c

@@ -644,7 +644,8 @@ static SIMPLE_DEV_PM_OPS(isl12057_rtc_pm_ops, isl12057_rtc_suspend,
 
 #ifdef CONFIG_OF
 static const struct of_device_id isl12057_dt_match[] = {
-	{ .compatible = "isl,isl12057" },
+	{ .compatible = "isl,isl12057" }, /* for backward compat., don't use */
+	{ .compatible = "isil,isl12057" },
 	{ },
 };
 #endif

drivers/staging/iio/light/isl29028.c

@@ -537,8 +537,8 @@ static const struct i2c_device_id isl29028_id[] = {
 MODULE_DEVICE_TABLE(i2c, isl29028_id);
 
 static const struct of_device_id isl29028_of_match[] = {
-	{ .compatible = "isl,isl29028", },
-	{ .compatible = "isil,isl29028", },/* deprecated, don't use */
+	{ .compatible = "isl,isl29028", }, /* for backward compat., don't use */
+	{ .compatible = "isil,isl29028", },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, isl29028_of_match);

fs/Kconfig

@@ -13,13 +13,6 @@ if BLOCK
 source "fs/ext2/Kconfig"
 source "fs/ext3/Kconfig"
 source "fs/ext4/Kconfig"
-
-config FS_XIP
-# execute in place
-	bool
-	depends on EXT2_FS_XIP
-	default y
-
 source "fs/jbd/Kconfig"
 source "fs/jbd2/Kconfig"
 
@@ -40,6 +33,21 @@ source "fs/ocfs2/Kconfig"
 source "fs/btrfs/Kconfig"
 source "fs/nilfs2/Kconfig"
 
+config FS_DAX
+	bool "Direct Access (DAX) support"
+	depends on MMU
+	depends on !(ARM || MIPS || SPARC)
+	help
+	  Direct Access (DAX) can be used on memory-backed block devices.
+	  If the block device supports DAX and the filesystem supports DAX,
+	  then you can avoid using the pagecache to buffer I/Os.  Turning
+	  on this option will compile in support for DAX; you will need to
+	  mount the filesystem using the -o dax option.
+
+	  If you do not have a block device that is capable of using this,
+	  or if unsure, say N.  Saying Y will increase the size of the kernel
+	  by about 5kB.
+
 endif # BLOCK
 
 # Posix ACL utility routines

fs/Makefile

@@ -28,6 +28,7 @@ obj-$(CONFIG_SIGNALFD)		+= signalfd.o
 obj-$(CONFIG_TIMERFD)		+= timerfd.o
 obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_AIO)               += aio.o
+obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o

fs/exofs/inode.c

@@ -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,

fs/ext2/Kconfig

@@ -42,14 +42,3 @@ config EXT2_FS_SECURITY
 
 	  If you are not using a security module that requires using
 	  extended attributes for file security labels, say N.
-
-config EXT2_FS_XIP
-	bool "Ext2 execute in place support"
-	depends on EXT2_FS && MMU
-	help
-	  Execute in place can be used on memory-backed block devices. If you
-	  enable this option, you can select to mount block devices which are
-	  capable of this feature without using the page cache.
-
-	  If you do not use a block device that is capable of using this,
-	  or if unsure, say N.

fs/ext2/Makefile

@@ -10,4 +10,3 @@ ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
 ext2-$(CONFIG_EXT2_FS_XATTR)	 += xattr.o xattr_user.o xattr_trusted.o
 ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o
 ext2-$(CONFIG_EXT2_FS_SECURITY)	 += xattr_security.o
-ext2-$(CONFIG_EXT2_FS_XIP)	 += xip.o

fs/ext2/ext2.h

@@ -380,10 +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 */
-#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
+#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
@@ -788,11 +793,10 @@ 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;
-extern const struct address_space_operations ext2_aops_xip;
 extern const struct address_space_operations ext2_nobh_aops;
 
 /* namei.c */

fs/ext2/file.c

@@ -25,6 +25,36 @@
 #include "xattr.h"
 #include "acl.h"
 
+#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);
+}
+
+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,
+};
+
+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 +100,7 @@ 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,
@@ -78,16 +108,18 @@ const struct file_operations ext2_file_operations = {
 	.splice_write	= iter_file_splice_write,
 };
 
-#ifdef CONFIG_EXT2_FS_XIP
-const struct file_operations ext2_xip_file_operations = {
+#ifdef CONFIG_FS_DAX
+const struct file_operations ext2_dax_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,
 #endif
-	.mmap		= xip_file_mmap,
+	.mmap		= ext2_file_mmap,
 	.open		= dquot_file_open,
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,

fs/ext2/inode.c

@@ -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);
@@ -731,12 +730,14 @@ 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
+		 * 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;
@@ -859,7 +860,12 @@ 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;
@@ -885,11 +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,
-	.get_xip_mem		= ext2_get_xip_mem,
-};
-
 const struct address_space_operations ext2_nobh_aops = {
 	.readpage		= ext2_readpage,
 	.readpages		= ext2_readpages,
@@ -1201,8 +1202,8 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 
 	inode_dio_wait(inode);
 
-	if (mapping_is_xip(inode->i_mapping))
-		error = xip_truncate_page(inode->i_mapping, newsize);
+	if (IS_DAX(inode))
+		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);
@@ -1273,7 +1274,8 @@ 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 +1286,8 @@ 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, DAX))
+		inode->i_flags |= S_DAX;
 }
 
 /* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
@@ -1384,9 +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 (ext2_use_xip(inode->i_sb)) {
-			inode->i_mapping->a_ops = &ext2_aops_xip;
-			inode->i_fop = &ext2_xip_file_operations;
+		if (test_opt(inode->i_sb, DAX)) {
+			inode->i_mapping->a_ops = &ext2_aops;
+			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;

fs/ext2/namei.c

@@ -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)
 {
@@ -105,9 +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 (ext2_use_xip(inode->i_sb)) {
-		inode->i_mapping->a_ops = &ext2_aops_xip;
-		inode->i_fop = &ext2_xip_file_operations;
+	if (test_opt(inode->i_sb, DAX)) {
+		inode->i_mapping->a_ops = &ext2_aops;
+		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;
@@ -126,9 +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 (ext2_use_xip(inode->i_sb)) {
-		inode->i_mapping->a_ops = &ext2_aops_xip;
-		inode->i_fop = &ext2_xip_file_operations;
+	if (test_opt(inode->i_sb, DAX)) {
+		inode->i_mapping->a_ops = &ext2_aops;
+		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;

fs/ext2/super.c

@@ -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);
@@ -292,9 +291,11 @@ 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");
+	if (sbi->s_mount_opt & EXT2_MOUNT_DAX)
+		seq_puts(seq, ",dax");
 #endif
 
 	if (!test_opt(sb, RESERVATION))
@@ -403,7 +404,7 @@ 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
 };
 
@@ -432,6 +433,7 @@ 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"},
@@ -559,10 +561,14 @@ static int parse_options(char *options, struct super_block *sb)
 			break;
 #endif
 		case Opt_xip:
-#ifdef CONFIG_EXT2_FS_XIP
-			set_opt (sbi->s_mount_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, DAX);
 #else
-			ext2_msg(sb, KERN_INFO, "xip option not supported");
+			ext2_msg(sb, KERN_INFO, "dax option not supported");
 #endif
 			break;
 
@@ -877,9 +883,6 @@ 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) ||
@@ -909,12 +912,18 @@ 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_DAX) {
+		if (blocksize != PAGE_SIZE) {
+			ext2_msg(sb, KERN_ERR,
+					"error: unsupported blocksize for dax");
+			goto failed_mount;
+		}
+		if (!sb->s_bdev->bd_disk->fops->direct_access) {
 			ext2_msg(sb, KERN_ERR,
-				"error: unsupported blocksize for xip");
+					"error: device does not support dax");
 			goto failed_mount;
 		}
+	}
 
 	/* If the blocksize doesn't match, re-read the thing.. */
 	if (sb->s_blocksize != blocksize) {
@@ -1259,7 +1268,6 @@ 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;
@@ -1284,22 +1292,11 @@ 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_DAX) {
 		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;
+			 "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);

fs/ext2/xip.c

-/*
- *  linux/fs/ext2/xip.c
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte (cotte@de.ibm.com)
- */
-
-#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"
-
-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;
-	sector_t sector = block * (PAGE_SIZE / 512);
-	return bdev_direct_access(bdev, sector, kaddr, pfn, size);
-}
-
-static inline int
-__ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
-		   sector_t *result)
-{
-	struct buffer_head tmp;
-	int rc;
-
-	memset(&tmp, 0, sizeof(struct buffer_head));
-	tmp.b_size = 1 << inode->i_blkbits;
-	rc = ext2_get_block(inode, pgoff, &tmp, create);
-	*result = tmp.b_blocknr;
-
-	/* did we get a sparse block (hole in the file)? */
-	if (!tmp.b_blocknr && !rc) {
-		BUG_ON(create);
-		rc = -ENODATA;
-	}
-
-	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);
-
-	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");
-	}
-}
-
-int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
-				void **kmem, unsigned long *pfn)
-{
-	long rc;
-	sector_t block;
-
-	/* first, retrieve the sector number */
-	rc = __ext2_get_block(mapping->host, pgoff, create, &block);
-	if (rc)
-		return rc;
-
-	/* retrieve address of the target data */
-	rc = __inode_direct_access(mapping->host, block, kmem, pfn, PAGE_SIZE);
-	return (rc < 0) ? rc : 0;
-}

fs/ext2/xip.h

-/*
- *  linux/fs/ext2/xip.h
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte (cotte@de.ibm.com)
- */
-
-#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);
-	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
-}
-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
-#define ext2_get_xip_mem			NULL
-#endif

fs/ext4/ext4.h

@@ -965,6 +965,11 @@ 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	/* Direct Access */
+#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 */
@@ -2578,6 +2583,7 @@ 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 */

fs/ext4/file.c

@@ -95,7 +95,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct mutex *aio_mutex = NULL;
 	struct blk_plug plug;
-	int o_direct = file->f_flags & O_DIRECT;
+	int o_direct = io_is_direct(file);
 	int overwrite = 0;
 	size_t length = iov_iter_count(from);
 	ssize_t ret;
@@ -191,6 +191,26 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	return ret;
 }
 
+#ifdef CONFIG_FS_DAX
+static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_fault(vma, vmf, ext4_get_block);
+					/* Is this the right get_block? */
+}
+
+static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_mkwrite(vma, vmf, ext4_get_block);
+}
+
+static const struct vm_operations_struct ext4_dax_vm_ops = {
+	.fault		= ext4_dax_fault,
+	.page_mkwrite	= ext4_dax_mkwrite,
+};
+#else
+#define ext4_dax_vm_ops	ext4_file_vm_ops
+#endif
+
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
@@ -200,7 +220,12 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	file_accessed(file);
+	if (IS_DAX(file_inode(file))) {
+		vma->vm_ops = &ext4_dax_vm_ops;
+		vma->vm_flags |= VM_MIXEDMAP;
+	} else {
 		vma->vm_ops = &ext4_file_vm_ops;
+	}
 	return 0;
 }
 
@@ -599,6 +624,26 @@ const struct file_operations ext4_file_operations = {
 	.fallocate	= ext4_fallocate,
 };
 
+#ifdef CONFIG_FS_DAX
+const struct file_operations ext4_dax_file_operations = {
+	.llseek		= ext4_llseek,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= ext4_file_write_iter,
+	.unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext4_compat_ioctl,
+#endif
+	.mmap		= ext4_file_mmap,
+	.open		= ext4_file_open,
+	.release	= ext4_release_file,
+	.fsync		= ext4_sync_file,
+	/* Splice not yet supported with DAX */
+	.fallocate	= ext4_fallocate,
+};
+#endif
+
 const struct inode_operations ext4_file_inode_operations = {
 	.setattr	= ext4_setattr,
 	.getattr	= ext4_getattr,

fs/ext4/indirect.c

@@ -689,12 +689,20 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 			inode_dio_done(inode);
 			goto locked;
 		}
+		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:
+		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);
 

fs/ext4/inode.c

@@ -657,6 +657,18 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	return retval;
 }
 
+static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
+{
+	struct inode *inode = bh->b_assoc_map->host;
+	/* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+	loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
+	int err;
+	if (!uptodate)
+		return;
+	WARN_ON(!buffer_unwritten(bh));
+	err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -694,6 +706,11 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) {
+			bh->b_assoc_map = inode->i_mapping;
+			bh->b_private = (void *)(unsigned long)iblock;
+			bh->b_end_io = ext4_end_io_unwritten;
+		}
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -3010,13 +3027,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}
+	if (IS_DAX(inode))
+		ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func,
+				ext4_end_io_dio, dio_flags);
+	else
 		ret = __blockdev_direct_IO(rw, iocb, inode,
-				   inode->i_sb->s_bdev, iter,
-				   offset,
+					   inode->i_sb->s_bdev, iter, offset,
 					   get_block_func,
-				   ext4_end_io_dio,
-				   NULL,
-				   dio_flags);
+					   ext4_end_io_dio, NULL, dio_flags);
 
 	/*
 	 * Put our reference to io_end. This can free the io_end structure e.g.
@@ -3180,19 +3198,12 @@ void ext4_set_aops(struct inode *inode)
 		inode->i_mapping->a_ops = &ext4_aops;
 }
 
-/*
- * ext4_block_zero_page_range() zeros out a mapping of length 'length'
- * starting from file offset 'from'.  The range to be zero'd must
- * be contained with in one block.  If the specified range exceeds
- * the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
- */
-static int ext4_block_zero_page_range(handle_t *handle,
+static int __ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length)
 {
 	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize, max, pos;
+	unsigned blocksize, pos;
 	ext4_lblk_t iblock;
 	struct inode *inode = mapping->host;
 	struct buffer_head *bh;
@@ -3205,14 +3216,6 @@ static int ext4_block_zero_page_range(handle_t *handle,
 		return -ENOMEM;
 
 	blocksize = inode->i_sb->s_blocksize;
-	max = blocksize - (offset & (blocksize - 1));
-
-	/*
-	 * correct length if it does not fall between
-	 * 'from' and the end of the block
-	 */
-	if (length > max || length < 0)
-		length = max;
 
 	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
 
@@ -3277,6 +3280,33 @@ static int ext4_block_zero_page_range(handle_t *handle,
 	return err;
 }
 
+/*
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'.  The range to be zero'd must
+ * be contained with in one block.  If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
+ */
+static int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length)
+{
+	struct inode *inode = mapping->host;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned blocksize = inode->i_sb->s_blocksize;
+	unsigned max = blocksize - (offset & (blocksize - 1));
+
+	/*
+	 * correct length if it does not fall between
+	 * 'from' and the end of the block
+	 */
+	if (length > max || length < 0)
+		length = max;
+
+	if (IS_DAX(inode))
+		return dax_zero_page_range(inode, from, length, ext4_get_block);
+	return __ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
 /*
  * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
  * up to the end of the block which corresponds to `from'.
@@ -3798,8 +3828,10 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
+	if (test_opt(inode->i_sb, DAX))
+		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
-			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4052,6 +4084,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_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);
 	} else if (S_ISDIR(inode->i_mode)) {

fs/ext4/namei.c

@@ -2235,6 +2235,9 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_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);
@@ -2299,6 +2302,9 @@ static int ext4_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_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);

fs/ext4/super.c

@@ -1124,7 +1124,7 @@ 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,
@@ -1187,6 +1187,7 @@ 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"},
@@ -1371,6 +1372,7 @@ 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},
@@ -1606,6 +1608,11 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			return -1;
 		}
 		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)
@@ -3589,6 +3596,11 @@ 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);
 	}
@@ -3652,6 +3664,19 @@ 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)) {
@@ -4869,6 +4894,18 @@ 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)

fs/ocfs2/aops.c

@@ -28,6 +28,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 
 #include <cluster/masklog.h>
 
@@ -47,6 +48,9 @@
 #include "ocfs2_trace.h"
 
 #include "buffer_head_io.h"
+#include "dir.h"
+#include "namei.h"
+#include "sysfile.h"
 
 static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -506,18 +510,21 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
  *
  * called like this: dio->get_blocks(dio->inode, fs_startblk,
  * 					fs_count, map_bh, dio->rw == WRITE);
- *
- * Note that we never bother to allocate blocks here, and thus ignore the
- * create argument.
  */
 static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 				     struct buffer_head *bh_result, int create)
 {
 	int ret;
+	u32 cpos = 0;
+	int alloc_locked = 0;
 	u64 p_blkno, inode_blocks, contig_blocks;
 	unsigned int ext_flags;
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
 	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	unsigned long len = bh_result->b_size;
+	unsigned int clusters_to_alloc = 0;
+
+	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
 
 	/* This function won't even be called if the request isn't all
 	 * nicely aligned and of the right size, so there's no need
@@ -539,6 +546,40 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	/* We should already CoW the refcounted extent in case of create. */
 	BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
 
+	/* allocate blocks if no p_blkno is found, and create == 1 */
+	if (!p_blkno && create) {
+		ret = ocfs2_inode_lock(inode, NULL, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		alloc_locked = 1;
+
+		/* fill hole, allocate blocks can't be larger than the size
+		 * of the hole */
+		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
+		if (clusters_to_alloc > contig_blocks)
+			clusters_to_alloc = contig_blocks;
+
+		/* allocate extent and insert them into the extent tree */
+		ret = ocfs2_extend_allocation(inode, cpos,
+				clusters_to_alloc, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
+				&contig_blocks, &ext_flags);
+		if (ret < 0) {
+			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
+					(unsigned long long)iblock);
+			ret = -EIO;
+			goto bail;
+		}
+	}
+
 	/*
 	 * get_more_blocks() expects us to describe a hole by clearing
 	 * the mapped bit on bh_result().
@@ -556,6 +597,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 		contig_blocks = max_blocks;
 	bh_result->b_size = contig_blocks << blocksize_bits;
 bail:
+	if (alloc_locked)
+		ocfs2_inode_unlock(inode, 1);
 	return ret;
 }
 
@@ -597,6 +640,184 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int ocfs2_is_overwrite(struct ocfs2_super *osb,
+		struct inode *inode, loff_t offset)
+{
+	int ret = 0;
+	u32 v_cpos = 0;
+	u32 p_cpos = 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+			&num_clusters, &ext_flags);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
+		return 1;
+
+	return 0;
+}
+
+static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
+		struct iov_iter *iter,
+		loff_t offset)
+{
+	ssize_t ret = 0;
+	ssize_t written = 0;
+	bool orphaned = false;
+	int is_overwrite = 0;
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *di_bh = NULL;
+	size_t count = iter->count;
+	journal_t *journal = osb->journal->j_journal;
+	u32 zero_len;
+	int cluster_align;
+	loff_t final_size = offset + count;
+	int append_write = offset >= i_size_read(inode) ? 1 : 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	{
+		u64 o = offset;
+
+		zero_len = do_div(o, 1 << osb->s_clustersize_bits);
+		cluster_align = !zero_len;
+	}
+
+	/*
+	 * when final_size > inode->i_size, inode->i_size will be
+	 * updated after direct write, so add the inode to orphan
+	 * dir first.
+	 */
+	if (final_size > i_size_read(inode)) {
+		ret = ocfs2_add_inode_to_orphan(osb, inode);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+		orphaned = true;
+	}
+
+	if (append_write) {
+		ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_extend(inode, di_bh, offset);
+		else
+			ret = ocfs2_extend_no_holes(inode, di_bh, offset,
+					offset);
+		if (ret < 0) {
+			mlog_errno(ret);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
+		if (is_overwrite < 0) {
+			mlog_errno(is_overwrite);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+		di_bh = NULL;
+	}
+
+	written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
+			iter, offset,
+			ocfs2_direct_IO_get_blocks,
+			ocfs2_dio_end_io, NULL, 0);
+	if (unlikely(written < 0)) {
+		loff_t i_size = i_size_read(inode);
+
+		if (offset + count > i_size) {
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto clean_orphan;
+			}
+
+			if (i_size == i_size_read(inode)) {
+				ret = ocfs2_truncate_file(inode, di_bh,
+						i_size);
+				if (ret < 0) {
+					if (ret != -ENOSPC)
+						mlog_errno(ret);
+
+					ocfs2_inode_unlock(inode, 1);
+					brelse(di_bh);
+					goto clean_orphan;
+				}
+			}
+
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+
+			ret = jbd2_journal_force_commit(journal);
+			if (ret < 0)
+				mlog_errno(ret);
+		}
+	} else if (written < 0 && append_write && !is_overwrite &&
+			!cluster_align) {
+		u32 p_cpos = 0;
+		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+
+		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+				&num_clusters, &ext_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
+
+		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
+				p_cpos << (osb->s_clustersize_bits - 9),
+				zero_len >> 9, GFP_KERNEL, false);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+clean_orphan:
+	if (orphaned) {
+		int tmp_ret;
+		int update_isize = written > 0 ? 1 : 0;
+		loff_t end = update_isize ? offset + written : 0;
+
+		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode,
+				update_isize, end);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			goto out;
+		}
+
+		tmp_ret = jbd2_journal_force_commit(journal);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			mlog_errno(tmp_ret);
+		}
+	}
+
+out:
+	if (ret >= 0)
+		ret = written;
+	return ret;
+}
+
 static ssize_t ocfs2_direct_IO(int rw,
 			       struct kiocb *iocb,
 			       struct iov_iter *iter,
@@ -604,6 +825,9 @@ static ssize_t ocfs2_direct_IO(int rw,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+			OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * Fallback to buffered I/O if we see an inode without
@@ -612,14 +836,20 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	/* Fallback to buffered I/O if we are appending. */
-	if (i_size_read(inode) <= offset)
+	/* Fallback to buffered I/O if we are appending and
+	 * concurrent O_DIRECT writes are allowed.
+	 */
+	if (i_size_read(inode) <= offset && !full_coherency)
 		return 0;
 
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
+	if (rw == READ)
+		return __blockdev_direct_IO(rw, iocb, inode,
+				    inode->i_sb->s_bdev,
 				    iter, offset,
 				    ocfs2_direct_IO_get_blocks,
 				    ocfs2_dio_end_io, NULL, 0);
+	else
+		return ocfs2_direct_IO_write(iocb, iter, offset);
 }
 
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,

fs/ocfs2/file.c

@@ -295,7 +295,7 @@ int ocfs2_update_inode_atime(struct inode *inode,
 	return ret;
 }
 
-static int ocfs2_set_inode_size(handle_t *handle,
+int ocfs2_set_inode_size(handle_t *handle,
 				struct inode *inode,
 				struct buffer_head *fe_bh,
 				u64 new_i_size)
@@ -441,7 +441,7 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb,
 	return status;
 }
 
-static int ocfs2_truncate_file(struct inode *inode,
+int ocfs2_truncate_file(struct inode *inode,
 			       struct buffer_head *di_bh,
 			       u64 new_i_size)
 {
@@ -709,6 +709,13 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
 	return status;
 }
 
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten)
+{
+	return __ocfs2_extend_allocation(inode, logical_start,
+			clusters_to_add, mark_unwritten);
+}
+
 /*
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.
@@ -2109,6 +2116,9 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	loff_t saved_pos = 0, end;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+		OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
@@ -2197,7 +2207,16 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 * one node could wind up truncating another
 		 * nodes writes.
 		 */
-		if (end > i_size_read(inode)) {
+		if (end > i_size_read(inode) && !full_coherency) {
+			*direct_io = 0;
+			break;
+		}
+
+		/*
+		 * Fallback to old way if the feature bit is not set.
+		 */
+		if (end > i_size_read(inode) &&
+				!ocfs2_supports_append_dio(osb)) {
 			*direct_io = 0;
 			break;
 		}
@@ -2210,6 +2229,12 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 */
 		ret = ocfs2_check_range_for_holes(inode, saved_pos, count);
 		if (ret == 1) {
+			/*
+			 * Fallback to old way if the feature bit is not set.
+			 * Otherwise try dio first and then complete the rest
+			 * request through buffer io.
+			 */
+			if (!ocfs2_supports_append_dio(osb))
 				*direct_io = 0;
 			ret = 0;
 		} else if (ret < 0)
@@ -2243,6 +2268,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	u32 old_clusters;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
@@ -2357,11 +2383,51 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 
 	iov_iter_truncate(from, count);
 	if (direct_io) {
+		loff_t endbyte;
+		ssize_t written_buffered;
 		written = generic_file_direct_write(iocb, from, *ppos);
-		if (written < 0) {
+		if (written < 0 || written == count) {
 			ret = written;
 			goto out_dio;
 		}
+
+		/*
+		 * for completing the rest of the request.
+		 */
+		*ppos += written;
+		count -= written;
+		written_buffered = generic_perform_write(file, from, *ppos);
+		/*
+		 * If generic_file_buffered_write() returned a synchronous error
+		 * then we want to return the number of bytes which were
+		 * direct-written, or the error code if that was zero. Note
+		 * that this differs from normal direct-io semantics, which
+		 * will return -EFOO even if some bytes were written.
+		 */
+		if (written_buffered < 0) {
+			ret = written_buffered;
+			goto out_dio;
+		}
+
+		iocb->ki_pos = *ppos + written_buffered;
+		/* We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		endbyte = *ppos + written_buffered - 1;
+		ret = filemap_write_and_wait_range(file->f_mapping, *ppos,
+				endbyte);
+		if (ret == 0) {
+			written += written_buffered;
+			invalidate_mapping_pages(mapping,
+					*ppos >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
 	} else {
 		current->backing_dev_info = inode_to_bdi(inode);
 		written = generic_perform_write(file, from, *ppos);

fs/ocfs2/file.h

@@ -51,13 +51,22 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 			 struct ocfs2_alloc_context *data_ac,
 			 struct ocfs2_alloc_context *meta_ac,
 			 enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_set_inode_size(handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		u64 new_i_size);
 int ocfs2_simple_size_update(struct inode *inode,
 			     struct buffer_head *di_bh,
 			     u64 new_i_size);
+int ocfs2_truncate_file(struct inode *inode,
+		struct buffer_head *di_bh,
+		u64 new_i_size);
 int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
 			  u64 new_i_size, u64 zero_to);
 int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 		      loff_t zero_to);
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);

fs/ocfs2/inode.c

@@ -648,7 +648,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 
 	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
 		status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
-					  orphan_dir_bh);
+					  orphan_dir_bh, false);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail_commit;

fs/ocfs2/inode.h

@@ -81,6 +81,8 @@ struct ocfs2_inode_info
 	tid_t i_sync_tid;
 	tid_t i_datasync_tid;
 
+	wait_queue_head_t append_dio_wq;
+
 	struct dquot *i_dquot[MAXQUOTAS];
 };
 

fs/ocfs2/journal.c

@@ -50,6 +50,8 @@
 #include "sysfile.h"
 #include "uptodate.h"
 #include "quota.h"
+#include "file.h"
+#include "namei.h"
 
 #include "buffer_head_io.h"
 #include "ocfs2_trace.h"
@@ -69,13 +71,15 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
 static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 				 int slot_num);
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot);
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type);
 static int ocfs2_commit_thread(void *arg);
 static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec);
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type);
 
 static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb)
 {
@@ -149,7 +153,8 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
 	return 0;
 }
 
-void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
+void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
+		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
 	int i;
@@ -163,7 +168,8 @@ void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
 	for (i = 0; i < replay_map->rm_slots; i++)
 		if (replay_map->rm_replay_slots[i])
 			ocfs2_queue_recovery_completion(osb->journal, i, NULL,
-							NULL, NULL);
+							NULL, NULL,
+							orphan_reco_type);
 	replay_map->rm_state = REPLAY_DONE;
 }
 
@@ -1174,6 +1180,7 @@ struct ocfs2_la_recovery_item {
 	struct ocfs2_dinode	*lri_la_dinode;
 	struct ocfs2_dinode	*lri_tl_dinode;
 	struct ocfs2_quota_recovery *lri_qrec;
+	enum ocfs2_orphan_reco_type  lri_orphan_reco_type;
 };
 
 /* Does the second half of the recovery process. By this point, the
@@ -1195,6 +1202,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 	struct ocfs2_dinode *la_dinode, *tl_dinode;
 	struct ocfs2_la_recovery_item *item, *n;
 	struct ocfs2_quota_recovery *qrec;
+	enum ocfs2_orphan_reco_type orphan_reco_type;
 	LIST_HEAD(tmp_la_list);
 
 	trace_ocfs2_complete_recovery(
@@ -1212,6 +1220,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 		la_dinode = item->lri_la_dinode;
 		tl_dinode = item->lri_tl_dinode;
 		qrec = item->lri_qrec;
+		orphan_reco_type = item->lri_orphan_reco_type;
 
 		trace_ocfs2_complete_recovery_slot(item->lri_slot,
 			la_dinode ? le64_to_cpu(la_dinode->i_blkno) : 0,
@@ -1236,7 +1245,8 @@ void ocfs2_complete_recovery(struct work_struct *work)
 			kfree(tl_dinode);
 		}
 
-		ret = ocfs2_recover_orphans(osb, item->lri_slot);
+		ret = ocfs2_recover_orphans(osb, item->lri_slot,
+				orphan_reco_type);
 		if (ret < 0)
 			mlog_errno(ret);
 
@@ -1261,7 +1271,8 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec)
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_la_recovery_item *item;
 
@@ -1285,6 +1296,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 	item->lri_slot = slot_num;
 	item->lri_tl_dinode = tl_dinode;
 	item->lri_qrec = qrec;
+	item->lri_orphan_reco_type = orphan_reco_type;
 
 	spin_lock(&journal->j_lock);
 	list_add_tail(&item->lri_list, &journal->j_la_cleanups);
@@ -1304,7 +1316,8 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 	/* No need to queue up our truncate_log as regular cleanup will catch
 	 * that */
 	ocfs2_queue_recovery_completion(journal, osb->slot_num,
-					osb->local_alloc_copy, NULL, NULL);
+					osb->local_alloc_copy, NULL, NULL,
+					ORPHAN_NEED_TRUNCATE);
 	ocfs2_schedule_truncate_log_flush(osb, 0);
 
 	osb->local_alloc_copy = NULL;
@@ -1312,7 +1325,7 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 
 	/* queue to recover orphan slots for all offline slots */
 	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 	ocfs2_free_replay_slots(osb);
 }
 
@@ -1323,7 +1336,8 @@ void ocfs2_complete_quota_recovery(struct ocfs2_super *osb)
 						osb->slot_num,
 						NULL,
 						NULL,
-						osb->quota_rec);
+						osb->quota_rec,
+						ORPHAN_NEED_TRUNCATE);
 		osb->quota_rec = NULL;
 	}
 }
@@ -1360,7 +1374,7 @@ static int __ocfs2_recovery_thread(void *arg)
 
 	/* queue recovery for our own slot */
 	ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL,
-					NULL, NULL);
+					NULL, NULL, ORPHAN_NO_NEED_TRUNCATE);
 
 	spin_lock(&osb->osb_lock);
 	while (rm->rm_used) {
@@ -1419,13 +1433,14 @@ static int __ocfs2_recovery_thread(void *arg)
 			continue;
 		}
 		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec);
+						NULL, NULL, qrec,
+						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
 
 	/* queue recovery for offline slots */
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 
 bail:
 	mutex_lock(&osb->recovery_lock);
@@ -1711,7 +1726,7 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 
 	/* This will kfree the memory pointed to by la_copy and tl_copy */
 	ocfs2_queue_recovery_completion(osb->journal, slot_num, la_copy,
-					tl_copy, NULL);
+					tl_copy, NULL, ORPHAN_NEED_TRUNCATE);
 
 	status = 0;
 done:
@@ -1901,7 +1916,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 
 	for (i = 0; i < osb->max_slots; i++)
 		ocfs2_queue_recovery_completion(osb->journal, i, NULL, NULL,
-						NULL);
+						NULL, ORPHAN_NO_NEED_TRUNCATE);
 	/*
 	 * We queued a recovery on orphan slots, increment the sequence
 	 * number and update LVB so other node will skip the scan for a while
@@ -2000,6 +2015,13 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
 	if (IS_ERR(iter))
 		return 0;
 
+	/* Skip inodes which are already added to recover list, since dio may
+	 * happen concurrently with unlink/rename */
+	if (OCFS2_I(iter)->ip_next_orphan) {
+		iput(iter);
+		return 0;
+	}
+
 	trace_ocfs2_orphan_filldir((unsigned long long)OCFS2_I(iter)->ip_blkno);
 	/* No locking is required for the next_orphan queue as there
 	 * is only ever a single process doing orphan recovery. */
@@ -2108,7 +2130,8 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
  *   advertising our state to ocfs2_delete_inode().
  */
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot)
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	int ret = 0;
 	struct inode *inode = NULL;
@@ -2132,13 +2155,60 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 					(unsigned long long)oi->ip_blkno);
 
 		iter = oi->ip_next_orphan;
+		oi->ip_next_orphan = NULL;
 
+		/*
+		 * We need to take and drop the inode lock to
+		 * force read inode from disk.
+		 */
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto next;
+		}
+		ocfs2_inode_unlock(inode, 0);
+
+		if (inode->i_nlink == 0) {
 			spin_lock(&oi->ip_lock);
 			/* Set the proper information to get us going into
 			 * ocfs2_delete_inode. */
 			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
 			spin_unlock(&oi->ip_lock);
+		} else if (orphan_reco_type == ORPHAN_NEED_TRUNCATE) {
+			struct buffer_head *di_bh = NULL;
+
+			ret = ocfs2_rw_lock(inode, 1);
+			if (ret) {
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				ocfs2_rw_unlock(inode, 1);
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_truncate_file(inode, di_bh,
+					i_size_read(inode));
+			ocfs2_inode_unlock(inode, 1);
+			ocfs2_rw_unlock(inode, 1);
+			brelse(di_bh);
+			if (ret < 0) {
+				if (ret != -ENOSPC)
+					mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
+			if (ret)
+				mlog_errno(ret);
+
+			wake_up(&OCFS2_I(inode)->append_dio_wq);
+		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
 
+next:
 		iput(inode);
 
 		inode = iter;

fs/ocfs2/journal.h

@@ -472,6 +472,11 @@ static inline int ocfs2_unlink_credits(struct super_block *sb)
  * orphan dir index leaf */
 #define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 4)
 
+/* dinode + orphan dir dinode + extent tree leaf block + orphan dir entry +
+ * orphan dir index root + orphan dir index leaf */
+#define OCFS2_INODE_ADD_TO_ORPHAN_CREDITS  (2 * OCFS2_INODE_UPDATE_CREDITS + 4)
+#define OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS  OCFS2_INODE_ADD_TO_ORPHAN_CREDITS
+
 /* dinode update, old dir dinode update, new dir dinode update, old
  * dir dir entry, new dir dir entry, dir entry update for renaming
  * directory + target unlink + 3 x dir index leaves */

fs/ocfs2/namei.h

@@ -34,10 +34,16 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
 		     struct inode *inode,
-		     struct buffer_head *orphan_dir_bh);
+		     struct buffer_head *orphan_dir_bh,
+		     bool dio);
 int ocfs2_create_inode_in_orphan(struct inode *dir,
 				 int mode,
 				 struct inode **new_inode);
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+		struct inode *inode);
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end);
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *new_inode,
 				   struct dentry *new_dentry);