241 files changed, 4333 insertions, 1377 deletions
diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index a5fbc8e897fa..614de3124901 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -50,9 +50,14 @@ userspace utilities, etc.
 Features
 ========
- This is a complete rewrite of the NTFS driver that used to be in the kernel.
+- This is a complete rewrite of the NTFS driver that used to be in the 2.4 and
-  This new driver implements NTFS read support and is functionally equivalent
+  earlier kernels.  This new driver implements NTFS read support and is
-  to the old ntfs driver.
+  functionally equivalent to the old ntfs driver and it also implements limited
+  write support.  The biggest limitation at present is that files/directories
+  cannot be created or deleted.  See below for the list of write features that
+  are so far supported.  Another limitation is that writing to compressed files
+  is not implemented at all.  Also, neither read nor write access to encrypted
+  files is so far implemented.
 - The new driver has full support for sparse files on NTFS 3.x volumes which
  the old driver isn't happy with.
 - The new driver supports execution of binaries due to mmap() now being
@@ -78,7 +83,20 @@ Features
 - The new driver supports fsync(2), fdatasync(2), and msync(2).
 - The new driver supports readv(2) and writev(2).
 - The new driver supports access time updates (including mtime and ctime).
+- The new driver supports truncate(2) and open(2) with O_TRUNC.  But at present
+  only very limited support for highly fragmented files, i.e. ones which have
+  their data attribute split across multiple extents, is included.  Another
+  limitation is that at present truncate(2) will never create sparse files,
+  since to mark a file sparse we need to modify the directory entry for the
+  file and we do not implement directory modifications yet.
+- The new driver supports write(2) which can both overwrite existing data and
+  extend the file size so that you can write beyond the existing data.  Also,
+  writing into sparse regions is supported and the holes are filled in with
+  clusters.  But at present only limited support for highly fragmented files,
+  i.e. ones which have their data attribute split across multiple extents, is
+  included.  Another limitation is that write(2) will never create sparse
+  files, since to mark a file sparse we need to modify the directory entry for
+  the file and we do not implement directory modifications yet.
 Supported mount options
 =======================
@@ -439,6 +457,22 @@ ChangeLog
 Note, a technical ChangeLog aimed at kernel hackers is in fs/ntfs/ChangeLog.
+2.1.25:
+        - Write support is now extended with write(2) being able to both
+          overwrite existing file data and to extend files.  Also, if a write
+          to a sparse region occurs, write(2) will fill in the hole.  Note,
+          mmap(2) based writes still do not support writing into holes or
+          writing beyond the initialized size.
+        - Write support has a new feature and that is that truncate(2) and
+          open(2) with O_TRUNC are now implemented thus files can be both made
+          smaller and larger.
+        - Note: Both write(2) and truncate(2)/open(2) with O_TRUNC still have
+          limitations in that they
+          - only provide limited support for highly fragmented files.
+          - only work on regular, i.e. uncompressed and unencrypted files.
+          - never create sparse files although this will change once directory
+            operations are implemented.
+        - Lots of bug fixes and enhancements across the board.
 2.1.24:
        - Support journals ($LogFile) which have been modified by chkdsk.  This
          means users can boot into Windows after we marked the volume dirty.
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 5cdb4122f057..ad55680726ed 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -22,7 +22,7 @@
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 21e2a518ad3a..174aa86ee816 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -22,7 +22,7 @@
 #include <linux/ptrace.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/dma-mapping.h>
diff --git a/arch/arm/common/scoop.c b/arch/arm/common/scoop.c
index 4af0cf5f3bfb..bb4eff614413 100644
--- a/arch/arm/common/scoop.c
+++ b/arch/arm/common/scoop.c
@@ -13,8 +13,7 @@
 #include <linux/device.h>
 #include <linux/string.h>
-#include <linux/slab.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/hardware/scoop.h>
diff --git a/arch/arm/mach-aaec2000/core.c b/arch/arm/mach-aaec2000/core.c
index 0c53dab80905..4e706d9ad368 100644
--- a/arch/arm/mach-aaec2000/core.c
+++ b/arch/arm/mach-aaec2000/core.c
@@ -13,7 +13,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/list.h>
 #include <linux/errno.h>
 #include <linux/dma-mapping.h>
diff --git a/arch/arm/mach-h720x/h7202-eval.c b/arch/arm/mach-h720x/h7202-eval.c
index db9078ad008c..d75c8221d2a5 100644
--- a/arch/arm/mach-h720x/h7202-eval.c
+++ b/arch/arm/mach-h720x/h7202-eval.c
@@ -18,7 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/string.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/setup.h>
 #include <asm/types.h>
diff --git a/arch/arm/mach-imx/generic.c b/arch/arm/mach-imx/generic.c
index 837d7f0bda4c..37613ad68366 100644
--- a/arch/arm/mach-imx/generic.c
+++ b/arch/arm/mach-imx/generic.c
@@ -22,7 +22,7 @@
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 */
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/arch/arm/mach-imx/mx1ads.c b/arch/arm/mach-imx/mx1ads.c
index 4cbdc1fe04b1..708e1b3faa14 100644
--- a/arch/arm/mach-imx/mx1ads.c
+++ b/arch/arm/mach-imx/mx1ads.c
@@ -14,6 +14,7 @@
 #include <linux/device.h>
 #include <linux/init.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/hardware.h>
 #include <asm/irq.h>
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 764ceb49470a..4c0f7c65facf 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -21,7 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/list.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/sysdev.h>
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index aa34c58b96c4..93f7ccb22c27 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -11,7 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/list.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/string.h>
diff --git a/arch/arm/mach-iop3xx/iop321-setup.c b/arch/arm/mach-iop3xx/iop321-setup.c
index bb5091223b63..80770233b8d4 100644
--- a/arch/arm/mach-iop3xx/iop321-setup.c
+++ b/arch/arm/mach-iop3xx/iop321-setup.c
@@ -16,7 +16,7 @@
 #include <linux/init.h>
 #include <linux/major.h>
 #include <linux/fs.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_core.h>
diff --git a/arch/arm/mach-iop3xx/iop331-setup.c b/arch/arm/mach-iop3xx/iop331-setup.c
index a2533c3ab42f..53f60614498b 100644
--- a/arch/arm/mach-iop3xx/iop331-setup.c
+++ b/arch/arm/mach-iop3xx/iop331-setup.c
@@ -15,7 +15,7 @@
 #include <linux/init.h>
 #include <linux/major.h>
 #include <linux/fs.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_core.h>
diff --git a/arch/arm/mach-ixp2000/enp2611.c b/arch/arm/mach-ixp2000/enp2611.c
index 9aa54de44740..643f5e1c3d93 100644
--- a/arch/arm/mach-ixp2000/enp2611.c
+++ b/arch/arm/mach-ixp2000/enp2611.c
@@ -32,7 +32,7 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_core.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/arm/mach-ixp2000/ixdp2x00.c b/arch/arm/mach-ixp2000/ixdp2x00.c
index 8b4a839b6279..05dfcb48c2b6 100644
--- a/arch/arm/mach-ixp2000/ixdp2x00.c
+++ b/arch/arm/mach-ixp2000/ixdp2x00.c
@@ -20,7 +20,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/bitops.h>
 #include <linux/pci.h>
 #include <linux/ioport.h>
diff --git a/arch/arm/mach-ixp2000/ixdp2x01.c b/arch/arm/mach-ixp2000/ixdp2x01.c
index fee1d7b73503..b21249908ae4 100644
--- a/arch/arm/mach-ixp2000/ixdp2x01.c
+++ b/arch/arm/mach-ixp2000/ixdp2x01.c
@@ -29,7 +29,7 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_core.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 6c396447c4e0..f3c687cf0071 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -20,6 +20,7 @@
 #include <linux/serial.h>
 #include <linux/sched.h>
 #include <linux/tty.h>
+#include <linux/platform_device.h>
 #include <linux/serial_core.h>
 #include <linux/bootmem.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/mach-lh7a40x/arch-lpd7a40x.c b/arch/arm/mach-lh7a40x/arch-lpd7a40x.c
index a20eabc132b0..4eb962fdb3a8 100644
--- a/arch/arm/mach-lh7a40x/arch-lpd7a40x.c
+++ b/arch/arm/mach-lh7a40x/arch-lpd7a40x.c
@@ -10,7 +10,7 @@
 #include <linux/tty.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <asm/hardware.h>
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index d46a70063b0c..4ee6bd8a50b8 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -21,7 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index 2798613696fa..fc824361430d 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -19,7 +19,7 @@
 #include <linux/init.h>
 #include <linux/major.h>
 #include <linux/kernel.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/errno.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index fd9183ff2ed5..a2eac853b2da 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -18,7 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-omap1/board-netstar.c b/arch/arm/mach-omap1/board-netstar.c
index d904e643f5ec..c851c2e4dfcb 100644
--- a/arch/arm/mach-omap1/board-netstar.c
+++ b/arch/arm/mach-omap1/board-netstar.c
@@ -11,7 +11,7 @@
 */
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index 21103df50415..a88524e7c315 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -28,7 +28,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/mtd/mtd.h>
diff --git a/arch/arm/mach-omap1/board-perseus2.c b/arch/arm/mach-omap1/board-perseus2.c
index 2ba26e239108..354b157acb3a 100644
--- a/arch/arm/mach-omap1/board-perseus2.c
+++ b/arch/arm/mach-omap1/board-perseus2.c
@@ -13,7 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-omap1/board-voiceblue.c b/arch/arm/mach-omap1/board-voiceblue.c
index bf30b1acda0b..3f018b296861 100644
--- a/arch/arm/mach-omap1/board-voiceblue.c
+++ b/arch/arm/mach-omap1/board-voiceblue.c
@@ -13,7 +13,7 @@
 */
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c
index e8b3981444cd..3c5d901efeaa 100644
--- a/arch/arm/mach-omap1/devices.c
+++ b/arch/arm/mach-omap1/devices.c
@@ -13,7 +13,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/io.h>
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 656f73bbcb5a..eb5f6d744a4a 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -14,7 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/mach-pxa/corgi_lcd.c b/arch/arm/mach-pxa/corgi_lcd.c
index 370df113dc06..54162ba95414 100644
--- a/arch/arm/mach-pxa/corgi_lcd.c
+++ b/arch/arm/mach-pxa/corgi_lcd.c
@@ -17,7 +17,7 @@
 #include <linux/delay.h>
 #include <linux/kernel.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/module.h>
 #include <asm/arch/akita.h>
 #include <asm/arch/corgi.h>
diff --git a/arch/arm/mach-pxa/corgi_ssp.c b/arch/arm/mach-pxa/corgi_ssp.c
index 136c269db0b7..591e5f32dbec 100644
--- a/arch/arm/mach-pxa/corgi_ssp.c
+++ b/arch/arm/mach-pxa/corgi_ssp.c
@@ -15,7 +15,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index 9c0289333301..9b48a90aefce 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -20,7 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/ioport.h>
 #include <linux/pm.h>
 #include <linux/string.h>
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index 01a83ab09ac3..7de159e2ab42 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -18,7 +18,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/fb.h>
 #include <asm/setup.h>
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index beccf455f796..1f6857d7747d 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -14,7 +14,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/sysdev.h>
 #include <linux/major.h>
 #include <linux/fb.h>
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index a48c64026e1f..887a8cb7b721 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -14,7 +14,7 @@
 */
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/sysdev.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 6d413f6701a7..ad6a13f95a62 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -16,7 +16,7 @@
 */
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/fb.h>
 #include <asm/hardware.h>
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 09a5d593f04b..c722a9a91fcc 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -16,7 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/pm.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/irq.h>
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index b838842b6a20..6c6878cd2207 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -14,7 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/major.h>
 #include <linux/fs.h>
diff --git a/arch/arm/mach-s3c2410/clock.c b/arch/arm/mach-s3c2410/clock.c
index 8b3d5dc35de5..82e8253b1fa0 100644
--- a/arch/arm/mach-s3c2410/clock.c
+++ b/arch/arm/mach-s3c2410/clock.c
@@ -32,7 +32,7 @@
 #include <linux/list.h>
 #include <linux/errno.h>
 #include <linux/err.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/sysdev.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/mach-s3c2410/cpu.c b/arch/arm/mach-s3c2410/cpu.c
index ca366e9e264d..687fe371369d 100644
--- a/arch/arm/mach-s3c2410/cpu.c
+++ b/arch/arm/mach-s3c2410/cpu.c
@@ -26,7 +26,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/irq.h>
diff --git a/arch/arm/mach-s3c2410/devs.c b/arch/arm/mach-s3c2410/devs.c
index 08bc7d95a45d..f58406e6ef5a 100644
--- a/arch/arm/mach-s3c2410/devs.c
+++ b/arch/arm/mach-s3c2410/devs.c
@@ -24,7 +24,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s3c2410/devs.h b/arch/arm/mach-s3c2410/devs.h
index d6328f96728b..52c4bab5c761 100644
--- a/arch/arm/mach-s3c2410/devs.h
+++ b/arch/arm/mach-s3c2410/devs.h
@@ -15,6 +15,7 @@
 *      10-Feb-2005 BJD  Added camera from guillaume.gourat@nexvision.tv
 */
 #include <linux/config.h>
+#include <linux/platform_device.h>
 extern struct platform_device *s3c24xx_uart_devs[];
diff --git a/arch/arm/mach-s3c2410/mach-anubis.c b/arch/arm/mach-s3c2410/mach-anubis.c
index 5ae80f4e3e67..8390b685c2b6 100644
--- a/arch/arm/mach-s3c2410/mach-anubis.c
+++ b/arch/arm/mach-s3c2410/mach-anubis.c
@@ -21,7 +21,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s3c2410/mach-bast.c b/arch/arm/mach-s3c2410/mach-bast.c
index c1b5c63ec24a..0b71c896bbd1 100644
--- a/arch/arm/mach-s3c2410/mach-bast.c
+++ b/arch/arm/mach-s3c2410/mach-bast.c
@@ -41,7 +41,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dm9000.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-s3c2410/mach-h1940.c b/arch/arm/mach-s3c2410/mach-h1940.c
index 7efeaaad2361..0aa8760598f7 100644
--- a/arch/arm/mach-s3c2410/mach-h1940.c
+++ b/arch/arm/mach-s3c2410/mach-h1940.c
@@ -34,6 +34,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
+#include <linux/platform_device.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s3c2410/mach-n30.c b/arch/arm/mach-s3c2410/mach-n30.c
index 5c0f2b091f95..378d640ab00b 100644
--- a/arch/arm/mach-s3c2410/mach-n30.c
+++ b/arch/arm/mach-s3c2410/mach-n30.c
@@ -20,7 +20,7 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/kthread.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-s3c2410/mach-nexcoder.c b/arch/arm/mach-s3c2410/mach-nexcoder.c
index c22f8216032d..42b0eeff2e0f 100644
--- a/arch/arm/mach-s3c2410/mach-nexcoder.c
+++ b/arch/arm/mach-s3c2410/mach-nexcoder.c
@@ -19,7 +19,7 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/map.h>
diff --git a/arch/arm/mach-s3c2410/mach-otom.c b/arch/arm/mach-s3c2410/mach-otom.c
index ad1459e402e2..a2eb9ed48fcd 100644
--- a/arch/arm/mach-s3c2410/mach-otom.c
+++ b/arch/arm/mach-s3c2410/mach-otom.c
@@ -15,7 +15,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s3c2410/mach-rx3715.c b/arch/arm/mach-s3c2410/mach-rx3715.c
index 22d9e070fd68..8f2a90bf940b 100644
--- a/arch/arm/mach-s3c2410/mach-rx3715.c
+++ b/arch/arm/mach-s3c2410/mach-rx3715.c
@@ -27,6 +27,7 @@
 #include <linux/init.h>
 #include <linux/tty.h>
 #include <linux/console.h>
+#include <linux/platform_device.h>
 #include <linux/serial_core.h>
 #include <linux/serial.h>
diff --git a/arch/arm/mach-s3c2410/mach-smdk2410.c b/arch/arm/mach-s3c2410/mach-smdk2410.c
index 2eda55a6b678..2c91965ee1c8 100644
--- a/arch/arm/mach-s3c2410/mach-smdk2410.c
+++ b/arch/arm/mach-s3c2410/mach-smdk2410.c
@@ -38,6 +38,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
+#include <linux/platform_device.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s3c2410/mach-smdk2440.c b/arch/arm/mach-s3c2410/mach-smdk2440.c
index 6950e61b7914..d666c621ad06 100644
--- a/arch/arm/mach-s3c2410/mach-smdk2440.c
+++ b/arch/arm/mach-s3c2410/mach-smdk2440.c
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
+#include <linux/platform_device.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s3c2410/s3c2410.c b/arch/arm/mach-s3c2410/s3c2410.c
index a8bf5ec82602..0a2013a76549 100644
--- a/arch/arm/mach-s3c2410/s3c2410.c
+++ b/arch/arm/mach-s3c2410/s3c2410.c
@@ -27,7 +27,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s3c2410/s3c2440.c b/arch/arm/mach-s3c2410/s3c2440.c
index 833fa36bce05..4d63e7133b48 100644
--- a/arch/arm/mach-s3c2410/s3c2440.c
+++ b/arch/arm/mach-s3c2410/s3c2440.c
@@ -26,7 +26,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/sysdev.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-sa1100/badge4.c b/arch/arm/mach-sa1100/badge4.c
index c92cebff7f8e..edccd5eb06be 100644
--- a/arch/arm/mach-sa1100/badge4.c
+++ b/arch/arm/mach-sa1100/badge4.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/tty.h>
 #include <linux/mtd/mtd.h>
diff --git a/arch/arm/mach-sa1100/cerf.c b/arch/arm/mach-sa1100/cerf.c
index 23cb74885275..508593722bc7 100644
--- a/arch/arm/mach-sa1100/cerf.c
+++ b/arch/arm/mach-sa1100/cerf.c
@@ -14,7 +14,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/tty.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index 7fd6e29c36b7..522abc036d3a 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -21,7 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/tty.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/timer.h>
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index 83eba8b54816..2abdc419e984 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -18,6 +18,7 @@
 #include <linux/cpufreq.h>
 #include <linux/ioport.h>
 #include <linux/sched.h>        /* just for sched_clock() - funny that */
+#include <linux/platform_device.h>
 #include <asm/div64.h>
 #include <asm/hardware.h>
diff --git a/arch/arm/mach-sa1100/jornada720.c b/arch/arm/mach-sa1100/jornada720.c
index 89af0c831e8f..2f671cc3cb99 100644
--- a/arch/arm/mach-sa1100/jornada720.c
+++ b/arch/arm/mach-sa1100/jornada720.c
@@ -6,7 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/tty.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/ioport.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index 052e4caedb89..69f1970646c6 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -8,7 +8,7 @@
 #include <linux/tty.h>
 #include <linux/ioport.h>
 #include <linux/serial_core.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <asm/hardware.h>
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index e17b58fb9c9c..58c18f9e9b7b 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -6,7 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/tty.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
index cfb6658e5cdf..439ddc9b06d6 100644
--- a/arch/arm/mach-sa1100/simpad.c
+++ b/arch/arm/mach-sa1100/simpad.c
@@ -10,7 +10,7 @@
 #include <linux/proc_fs.h>
 #include <linux/string.h> 
 #include <linux/pm.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index 7e4bdd07f4af..a1ca46630dda 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
 #include <linux/sysdev.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/plat-omap/usb.c b/arch/arm/plat-omap/usb.c
index 14a836d7ac25..205e2d0b826d 100644
--- a/arch/arm/plat-omap/usb.c
+++ b/arch/arm/plat-omap/usb.c
@@ -26,7 +26,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/usb_otg.h>
 #include <asm/io.h>
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 5383e5e2d9b7..bac0da731ee3 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -1042,8 +1042,3 @@ config X86_TRAMPOLINE
        bool
        depends on X86_SMP || (X86_VOYAGER && SMP)
        default y
-config PC
-        bool
-        depends on X86 && !EMBEDDED
-        default y
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index 9204be6eedb3..7c724ffa08bb 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -803,7 +803,6 @@ no_apic:
 void __init init_apic_mappings(void)
 {
-        unsigned int orig_apicid;
        unsigned long apic_phys;
        /*
@@ -825,11 +824,8 @@ void __init init_apic_mappings(void)
         * Fetch the APIC ID of the BSP in case we have a
         * default configuration (or the MP table is broken).
         */
-        orig_apicid = boot_cpu_physical_apicid;
+        if (boot_cpu_physical_apicid == -1U)
-        boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID));
+                boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID));
-        if ((orig_apicid != -1U) && (orig_apicid != boot_cpu_physical_apicid))
-                printk(KERN_WARNING "Boot APIC ID in local APIC unexpected (%d vs %d)",
-                        orig_apicid, boot_cpu_physical_apicid);
 #ifdef CONFIG_X86_IO_APIC
        {
@@ -1259,81 +1255,40 @@ fastcall void smp_error_interrupt(struct pt_regs *regs)
 }
 /*
- * This initializes the IO-APIC and APIC hardware.
+ * This initializes the IO-APIC and APIC hardware if this is
+ * a UP kernel.
 */
-int __init APIC_init(void)
+int __init APIC_init_uniprocessor (void)
 {
-        if (enable_local_apic < 0) {
+        if (enable_local_apic < 0)
-                printk(KERN_INFO "APIC disabled\n");
+                clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
-                return -1;
-        }
-        /* See if we have a SMP configuration or have forced enabled
+        if (!smp_found_config && !cpu_has_apic)
-         * the local apic.
-         */
-        if (!smp_found_config && !acpi_lapic && !cpu_has_apic) {
-                enable_local_apic = -1;
                return -1;
-        }
        /*
-         * Complain if the BIOS pretends there is an apic.
+         * Complain if the BIOS pretends there is one.
-         * Then get out because we don't have an a local apic.
         */
        if (!cpu_has_apic && APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
                printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
                        boot_cpu_physical_apicid);
-                printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n");
-                enable_local_apic = -1;
                return -1;
        }
        verify_local_APIC();
-        /*
-         * Should not be necessary because the MP table should list the boot
-         * CPU too, but we do it for the sake of robustness anyway.
-         * Makes no sense to do this check in clustered apic mode, so skip it
-         */
-        if (!check_phys_apicid_present(boot_cpu_physical_apicid)) {
-                printk("weird, boot CPU (#%d) not listed by the BIOS.\n",
-                                boot_cpu_physical_apicid);
-                physid_set(boot_cpu_physical_apicid, phys_cpu_present_map);
-        }
-        /*
-         * Switch from PIC to APIC mode.
-         */
        connect_bsp_APIC();
-        setup_local_APIC();
-#ifdef CONFIG_X86_IO_APIC
+        phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
-        /*
-         * Now start the IO-APICs
-         */
-        if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
-                setup_IO_APIC();
-#endif
-        return 0;
-}
-void __init APIC_late_time_init(void)
+        setup_local_APIC();
-{
-        /* Improve our loops per jiffy estimate */
-        loops_per_jiffy = ((1000 + HZ - 1)/HZ)*cpu_khz;
-        boot_cpu_data.loops_per_jiffy = loops_per_jiffy;
-        cpu_data[0].loops_per_jiffy = loops_per_jiffy;
-        /* setup_apic_nmi_watchdog doesn't work properly before cpu_khz is
-         * initialized.  So redo it here to ensure the boot cpu is setup
-         * properly.
-         */
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                setup_apic_nmi_watchdog();
 #ifdef CONFIG_X86_IO_APIC
-        if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
+        if (smp_found_config)
-                IO_APIC_late_time_init();
+                if (!skip_ioapic_setup && nr_ioapics)
+                        setup_IO_APIC();
 #endif
        setup_boot_APIC_clock();
+        return 0;
 }
diff --git a/arch/i386/kernel/i8259.c b/arch/i386/kernel/i8259.c
index d86f24909284..323ef8ab3244 100644
--- a/arch/i386/kernel/i8259.c
+++ b/arch/i386/kernel/i8259.c
@@ -435,8 +435,4 @@ void __init init_IRQ(void)
                setup_irq(FPU_IRQ, &fpu_irq);
        irq_ctx_init(smp_processor_id());
-#ifdef CONFIG_X86_LOCAL_APIC
-        APIC_init();
-#endif
 }
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 5a77c52b20a9..cc5d7ac5b2e7 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -2387,15 +2387,11 @@ void __init setup_IO_APIC(void)
        sync_Arb_IDs();
        setup_IO_APIC_irqs();
        init_IO_APIC_traps();
+        check_timer();
        if (!acpi_ioapic)
                print_IO_APIC();
 }
-void __init IO_APIC_late_time_init(void)
-{
-        check_timer();
-}
 /*
 *      Called after all the initialization is done. If we didnt find any
 *      APIC bugs then we can allow the modify fast path
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 5a2bbe0c4fff..01b618e73ecd 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -1078,16 +1078,6 @@ void *xquad_portio;
 EXPORT_SYMBOL(xquad_portio);
 #endif
-/*
- * Fall back to non SMP mode after errors.
- *
- */
-static __init void disable_smp(void)
-{
-        cpu_set(0, cpu_sibling_map[0]);
-        cpu_set(0, cpu_core_map[0]);
-}
 static void __init smp_boot_cpus(unsigned int max_cpus)
 {
        int apicid, cpu, bit, kicked;
@@ -1100,6 +1090,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
        printk("CPU%d: ", 0);
        print_cpu_info(&cpu_data[0]);
+        boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID));
        boot_cpu_logical_apicid = logical_smp_processor_id();
        x86_cpu_to_apicid[0] = boot_cpu_physical_apicid;
@@ -1111,27 +1102,68 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
        cpus_clear(cpu_core_map[0]);
        cpu_set(0, cpu_core_map[0]);
-        map_cpu_to_logical_apicid();
        /*
         * If we couldn't find an SMP configuration at boot time,
         * get out of here now!
         */
        if (!smp_found_config && !acpi_lapic) {
                printk(KERN_NOTICE "SMP motherboard not detected.\n");
-                disable_smp();
+                smpboot_clear_io_apic_irqs();
+                phys_cpu_present_map = physid_mask_of_physid(0);
+                if (APIC_init_uniprocessor())
+                        printk(KERN_NOTICE "Local APIC not detected."
+                                           " Using dummy APIC emulation.\n");
+                map_cpu_to_logical_apicid();
+                cpu_set(0, cpu_sibling_map[0]);
+                cpu_set(0, cpu_core_map[0]);
+                return;
+        }
+        /*
+         * Should not be necessary because the MP table should list the boot
+         * CPU too, but we do it for the sake of robustness anyway.
+         * Makes no sense to do this check in clustered apic mode, so skip it
+         */
+        if (!check_phys_apicid_present(boot_cpu_physical_apicid)) {
+                printk("weird, boot CPU (#%d) not listed by the BIOS.\n",
+                                boot_cpu_physical_apicid);
+                physid_set(hard_smp_processor_id(), phys_cpu_present_map);
+        }
+        /*
+         * If we couldn't find a local APIC, then get out of here now!
+         */
+        if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && !cpu_has_apic) {
+                printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
+                        boot_cpu_physical_apicid);
+                printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n");
+                smpboot_clear_io_apic_irqs();
+                phys_cpu_present_map = physid_mask_of_physid(0);
+                cpu_set(0, cpu_sibling_map[0]);
+                cpu_set(0, cpu_core_map[0]);
                return;
        }
+        verify_local_APIC();
        /*
         * If SMP should be disabled, then really disable it!
         */
-        if (!max_cpus || (enable_local_apic < 0)) {
+        if (!max_cpus) {
-                printk(KERN_INFO "SMP mode deactivated.\n");
+                smp_found_config = 0;
-                disable_smp();
+                printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n");
+                smpboot_clear_io_apic_irqs();
+                phys_cpu_present_map = physid_mask_of_physid(0);
+                cpu_set(0, cpu_sibling_map[0]);
+                cpu_set(0, cpu_core_map[0]);
                return;
        }
+        connect_bsp_APIC();
+        setup_local_APIC();
+        map_cpu_to_logical_apicid();
        setup_portio_remap();
        /*
@@ -1212,6 +1244,10 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
        cpu_set(0, cpu_sibling_map[0]);
        cpu_set(0, cpu_core_map[0]);
+        smpboot_setup_io_apic();
+        setup_boot_APIC_clock();
        /*
         * Synchronize the TSC with the AP
         */
diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index 07471bba2dc6..41c5b2dc6200 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -440,8 +440,8 @@ static int time_init_device(void)
 device_initcall(time_init_device);
-extern void (*late_time_init)(void);
 #ifdef CONFIG_HPET_TIMER
+extern void (*late_time_init)(void);
 /* Duplicate of time_init() below, with hpet_enable part added */
 static void __init hpet_time_init(void)
 {
@@ -458,11 +458,6 @@ static void __init hpet_time_init(void)
        printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name);
        time_init_hook();
-#ifdef CONFIG_X86_LOCAL_APIC
-        if (enable_local_apic >= 0)
-                APIC_late_time_init();
-#endif
 }
 #endif
@@ -487,9 +482,4 @@ void __init time_init(void)
        printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name);
        time_init_hook();
-#ifdef CONFIG_X86_LOCAL_APIC
-        if (enable_local_apic >= 0)
-                late_time_init = APIC_late_time_init;
-#endif
 }
diff --git a/arch/m32r/kernel/setup_m32700ut.c b/arch/m32r/kernel/setup_m32700ut.c
index 708634b685e4..cb76916b014d 100644
--- a/arch/m32r/kernel/setup_m32700ut.c
+++ b/arch/m32r/kernel/setup_m32700ut.c
@@ -15,7 +15,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/m32r.h>
diff --git a/arch/m32r/kernel/setup_mappi.c b/arch/m32r/kernel/setup_mappi.c
index 4e709809efc5..501d798cf050 100644
--- a/arch/m32r/kernel/setup_mappi.c
+++ b/arch/m32r/kernel/setup_mappi.c
@@ -11,7 +11,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/m32r.h>
diff --git a/arch/m32r/kernel/setup_mappi2.c b/arch/m32r/kernel/setup_mappi2.c
index a1d801598aa4..7f2db5bfd626 100644
--- a/arch/m32r/kernel/setup_mappi2.c
+++ b/arch/m32r/kernel/setup_mappi2.c
@@ -11,7 +11,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/m32r.h>
diff --git a/arch/m32r/kernel/setup_mappi3.c b/arch/m32r/kernel/setup_mappi3.c
index a76412e883e8..9c79341a7b45 100644
--- a/arch/m32r/kernel/setup_mappi3.c
+++ b/arch/m32r/kernel/setup_mappi3.c
@@ -11,7 +11,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/m32r.h>
diff --git a/arch/m32r/kernel/setup_opsput.c b/arch/m32r/kernel/setup_opsput.c
index d7b7ec6d30f8..1fbb140854e7 100644
--- a/arch/m32r/kernel/setup_opsput.c
+++ b/arch/m32r/kernel/setup_opsput.c
@@ -16,7 +16,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/m32r.h>
diff --git a/arch/mips/au1000/common/platform.c b/arch/mips/au1000/common/platform.c
index 1f7b465c8038..48d3f54f88f8 100644
--- a/arch/mips/au1000/common/platform.c
+++ b/arch/mips/au1000/common/platform.c
@@ -9,6 +9,7 @@
 */
 #include <linux/config.h>
 #include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/resource.h>
diff --git a/arch/ppc/platforms/4xx/ibm440ep.c b/arch/ppc/platforms/4xx/ibm440ep.c
index 4712de8ff80f..65ac0b9c2d05 100644
--- a/arch/ppc/platforms/4xx/ibm440ep.c
+++ b/arch/ppc/platforms/4xx/ibm440ep.c
@@ -14,6 +14,7 @@
 */
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/platform_device.h>
 #include <platforms/4xx/ibm440ep.h>
 #include <asm/ocp.h>
 #include <asm/ppc4xx_pic.h>
diff --git a/arch/ppc/platforms/4xx/ibmstb4.c b/arch/ppc/platforms/4xx/ibmstb4.c
index d90627b68faa..7e33bb635443 100644
--- a/arch/ppc/platforms/4xx/ibmstb4.c
+++ b/arch/ppc/platforms/4xx/ibmstb4.c
@@ -10,6 +10,7 @@
 */
 #include <linux/init.h>
+#include <linux/platform_device.h>
 #include <asm/ocp.h>
 #include <asm/ppc4xx_pic.h>
 #include <platforms/4xx/ibmstb4.h>
diff --git a/arch/ppc/platforms/4xx/redwood5.c b/arch/ppc/platforms/4xx/redwood5.c
index bee8b4ac8afd..611ac861804d 100644
--- a/arch/ppc/platforms/4xx/redwood5.c
+++ b/arch/ppc/platforms/4xx/redwood5.c
@@ -14,7 +14,7 @@
 #include <linux/config.h>
 #include <linux/init.h>
 #include <linux/pagemap.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/ioport.h>
 #include <asm/io.h>
 #include <asm/machdep.h>
diff --git a/arch/ppc/platforms/4xx/redwood6.c b/arch/ppc/platforms/4xx/redwood6.c
index 8b1012994dfc..b13116691289 100644
--- a/arch/ppc/platforms/4xx/redwood6.c
+++ b/arch/ppc/platforms/4xx/redwood6.c
@@ -12,7 +12,7 @@
 #include <linux/config.h>
 #include <linux/init.h>
 #include <linux/pagemap.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/ioport.h>
 #include <asm/io.h>
 #include <asm/ppc4xx_pic.h>
diff --git a/arch/ppc/platforms/chrp_pegasos_eth.c b/arch/ppc/platforms/chrp_pegasos_eth.c
index a9052305c35d..108a6e265185 100644
--- a/arch/ppc/platforms/chrp_pegasos_eth.c
+++ b/arch/ppc/platforms/chrp_pegasos_eth.c
@@ -13,7 +13,7 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/mv643xx.h>
 #include <linux/pci.h>
diff --git a/arch/ppc/platforms/cpci690.c b/arch/ppc/platforms/cpci690.c
index f64ac2acb603..6ca7bcac9474 100644
--- a/arch/ppc/platforms/cpci690.c
+++ b/arch/ppc/platforms/cpci690.c
@@ -21,6 +21,7 @@
 #include <linux/initrd.h>
 #include <linux/root_dev.h>
 #include <linux/mv643xx.h>
+#include <linux/platform_device.h>
 #include <asm/bootinfo.h>
 #include <asm/machdep.h>
 #include <asm/todc.h>
diff --git a/arch/ppc/platforms/ev64260.c b/arch/ppc/platforms/ev64260.c
index aa50637a5cfb..32358b3fb236 100644
--- a/arch/ppc/platforms/ev64260.c
+++ b/arch/ppc/platforms/ev64260.c
@@ -33,6 +33,7 @@
 #include <linux/console.h>
 #include <linux/initrd.h>
 #include <linux/root_dev.h>
+#include <linux/platform_device.h>
 #if !defined(CONFIG_SERIAL_MPSC_CONSOLE)
 #include <linux/serial.h>
 #include <linux/tty.h>
diff --git a/arch/ppc/platforms/ev64360.c b/arch/ppc/platforms/ev64360.c
index 53388a1c334f..b1324564456e 100644
--- a/arch/ppc/platforms/ev64360.c
+++ b/arch/ppc/platforms/ev64360.c
@@ -25,6 +25,7 @@
 #include <linux/bootmem.h>
 #include <linux/mtd/physmap.h>
 #include <linux/mv643xx.h>
+#include <linux/platform_device.h>
 #ifdef CONFIG_BOOTIMG
 #include <linux/bootimg.h>
 #endif
diff --git a/arch/ppc/platforms/hdpu.c b/arch/ppc/platforms/hdpu.c
index b6a66d5e9d83..50039a204c24 100644
--- a/arch/ppc/platforms/hdpu.c
+++ b/arch/ppc/platforms/hdpu.c
@@ -22,6 +22,7 @@
 #include <linux/irq.h>
 #include <linux/ide.h>
 #include <linux/seq_file.h>
+#include <linux/platform_device.h>
 #include <linux/initrd.h>
 #include <linux/root_dev.h>
diff --git a/arch/ppc/platforms/katana.c b/arch/ppc/platforms/katana.c
index a301c5ac58dd..6e58e30ceed1 100644
--- a/arch/ppc/platforms/katana.c
+++ b/arch/ppc/platforms/katana.c
@@ -29,6 +29,7 @@
 #include <linux/seq_file.h>
 #include <linux/mtd/physmap.h>
 #include <linux/mv643xx.h>
+#include <linux/platform_device.h>
 #ifdef CONFIG_BOOTIMG
 #include <linux/bootimg.h>
 #endif
diff --git a/arch/ppc/platforms/radstone_ppc7d.c b/arch/ppc/platforms/radstone_ppc7d.c
index 6f97911c330d..708b8739ecdd 100644
--- a/arch/ppc/platforms/radstone_ppc7d.c
+++ b/arch/ppc/platforms/radstone_ppc7d.c
@@ -40,6 +40,7 @@
 #include <linux/serial_core.h>
 #include <linux/mv643xx.h>
 #include <linux/netdevice.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
diff --git a/arch/ppc/syslib/mpc52xx_devices.c b/arch/ppc/syslib/mpc52xx_devices.c
index ad5182efca1d..da3c74bfdc92 100644
--- a/arch/ppc/syslib/mpc52xx_devices.c
+++ b/arch/ppc/syslib/mpc52xx_devices.c
@@ -15,6 +15,7 @@
 #include <linux/fsl_devices.h>
 #include <linux/resource.h>
+#include <linux/platform_device.h>
 #include <asm/mpc52xx.h>
 #include <asm/ppc_sys.h>
diff --git a/arch/ppc/syslib/mv64x60.c b/arch/ppc/syslib/mv64x60.c
index a781c50d2f4c..94ea346b7b4b 100644
--- a/arch/ppc/syslib/mv64x60.c
+++ b/arch/ppc/syslib/mv64x60.c
@@ -19,6 +19,7 @@
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/mv643xx.h>
+#include <linux/platform_device.h>
 #include <asm/byteorder.h>
 #include <asm/io.h>
diff --git a/arch/ppc/syslib/pq2_devices.c b/arch/ppc/syslib/pq2_devices.c
index 6f88ba93412b..e960fe935325 100644
--- a/arch/ppc/syslib/pq2_devices.c
+++ b/arch/ppc/syslib/pq2_devices.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/ioport.h>
 #include <asm/cpm2.h>
 #include <asm/irq.h>
diff --git a/arch/sh/boards/superh/microdev/setup.c b/arch/sh/boards/superh/microdev/setup.c
index c18919941ec0..1c1d65fb12df 100644
--- a/arch/sh/boards/superh/microdev/setup.c
+++ b/arch/sh/boards/superh/microdev/setup.c
@@ -13,7 +13,7 @@
 #include <linux/config.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/ioport.h>
 #include <asm/io.h>
 #include <asm/mach/irq.h>
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 1495007bf6c0..721e2601a75d 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -20,6 +20,7 @@
 #include "linux/ctype.h"
 #include "linux/bootmem.h"
 #include "linux/ethtool.h"
+#include "linux/platform_device.h"
 #include "asm/uaccess.h"
 #include "user_util.h"
 #include "kern_util.h"
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index f73134333f64..b2c86257b0f8 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -35,6 +35,7 @@
 #include "linux/blkpg.h"
 #include "linux/genhd.h"
 #include "linux/spinlock.h"
+#include "linux/platform_device.h"
 #include "asm/segment.h"
 #include "asm/uaccess.h"
 #include "asm/irq.h"
diff --git a/arch/xtensa/platform-iss/network.c b/arch/xtensa/platform-iss/network.c
index 498d7dced1f4..0682ffd38175 100644
--- a/arch/xtensa/platform-iss/network.c
+++ b/arch/xtensa/platform-iss/network.c
@@ -33,6 +33,7 @@
 #include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
 #include <linux/timer.h>
+#include <linux/platform_device.h>
 #include <xtensa/simcall.h>
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 08d9cc99c7de..d597c922af11 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -10,7 +10,7 @@
 * information.
 */
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
diff --git a/drivers/block/cfq-iosched.c b/drivers/block/cfq-iosched.c
index 5281f8e70510..ecacca9c877e 100644
--- a/drivers/block/cfq-iosched.c
+++ b/drivers/block/cfq-iosched.c
@@ -2059,10 +2059,8 @@ static void cfq_put_cfqd(struct cfq_data *cfqd)
        if (!atomic_dec_and_test(&cfqd->ref))
                return;
-        blk_put_queue(q);
        cfq_shutdown_timer_wq(cfqd);
-        q->elevator->elevator_data = NULL;
+        blk_put_queue(q);
        mempool_destroy(cfqd->crq_pool);
        kfree(cfqd->crq_hash);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 00895477155e..5eadbb9d4d71 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -177,7 +177,7 @@ static int print_unex = 1;
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/devfs_fs_kernel.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/buffer_head.h>  /* for invalidate_buffers() */
 /*
diff --git a/drivers/block/noop-iosched.c b/drivers/block/noop-iosched.c
index f56b8edb06e4..e54f006e7e60 100644
--- a/drivers/block/noop-iosched.c
+++ b/drivers/block/noop-iosched.c
@@ -9,6 +9,7 @@
 static void elevator_noop_add_request(request_queue_t *q, struct request *rq)
 {
+        rq->flags |= REQ_NOMERGE;
        elv_dispatch_add_tail(q, rq);
 }
diff --git a/drivers/char/s3c2410-rtc.c b/drivers/char/s3c2410-rtc.c
index 887b8b2d7882..d724c0de4f28 100644
--- a/drivers/char/s3c2410-rtc.c
+++ b/drivers/char/s3c2410-rtc.c
@@ -20,7 +20,7 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/rtc.h>
 #include <linux/bcd.h>
diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c
index f86c15587238..d05067dcea01 100644
--- a/drivers/char/sonypi.c
+++ b/drivers/char/sonypi.c
@@ -48,6 +48,7 @@
 #include <linux/dmi.h>
 #include <linux/err.h>
 #include <linux/kfifo.h>
+#include <linux/platform_device.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
diff --git a/drivers/char/tb0219.c b/drivers/char/tb0219.c
index eb7058cbf015..24355b23b2ca 100644
--- a/drivers/char/tb0219.c
+++ b/drivers/char/tb0219.c
@@ -17,7 +17,7 @@
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/module.h>
diff --git a/drivers/char/vr41xx_giu.c b/drivers/char/vr41xx_giu.c
index 683278bc5241..94641085faf8 100644
--- a/drivers/char/vr41xx_giu.c
+++ b/drivers/char/vr41xx_giu.c
@@ -19,7 +19,7 @@
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/init.h>
diff --git a/drivers/char/vr41xx_rtc.c b/drivers/char/vr41xx_rtc.c
index a6dbe4da030c..5e3292df69d8 100644
--- a/drivers/char/vr41xx_rtc.c
+++ b/drivers/char/vr41xx_rtc.c
@@ -17,7 +17,7 @@
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
diff --git a/drivers/char/watchdog/mpcore_wdt.c b/drivers/char/watchdog/mpcore_wdt.c
index 75ca84ed4adf..47a5f6ab4879 100644
--- a/drivers/char/watchdog/mpcore_wdt.c
+++ b/drivers/char/watchdog/mpcore_wdt.c
@@ -29,7 +29,7 @@
 #include <linux/reboot.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/hardware/arm_twd.h>
 #include <asm/uaccess.h>
diff --git a/drivers/char/watchdog/mv64x60_wdt.c b/drivers/char/watchdog/mv64x60_wdt.c
index 6d3ff0836c44..04e0d7e9680d 100644
--- a/drivers/char/watchdog/mv64x60_wdt.c
+++ b/drivers/char/watchdog/mv64x60_wdt.c
@@ -22,6 +22,8 @@
 #include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/watchdog.h>
+#include <linux/platform_device.h>
 #include <asm/mv64x60.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
diff --git a/drivers/char/watchdog/s3c2410_wdt.c b/drivers/char/watchdog/s3c2410_wdt.c
index b732020acadb..e7e20a6d64b0 100644
--- a/drivers/char/watchdog/s3c2410_wdt.c
+++ b/drivers/char/watchdog/s3c2410_wdt.c
@@ -44,7 +44,7 @@
 #include <linux/watchdog.h>
 #include <linux/fs.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <asm/uaccess.h>
diff --git a/drivers/eisa/virtual_root.c b/drivers/eisa/virtual_root.c
index 15677f20bd85..0f97a0cb0ff4 100644
--- a/drivers/eisa/virtual_root.c
+++ b/drivers/eisa/virtual_root.c
@@ -9,7 +9,7 @@
 #include <linux/config.h>
 #include <linux/kernel.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/eisa.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c
index 955537fe9958..8ed6ddbb9c5d 100644
--- a/drivers/firmware/dcdbas.c
+++ b/drivers/firmware/dcdbas.c
@@ -20,7 +20,7 @@
 *  GNU General Public License for more details.
 */
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/errno.h>
 #include <linux/init.h>
diff --git a/drivers/firmware/dell_rbu.c b/drivers/firmware/dell_rbu.c
index 4f4ba9b6d182..125929c9048f 100644
--- a/drivers/firmware/dell_rbu.c
+++ b/drivers/firmware/dell_rbu.c
@@ -41,7 +41,7 @@
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/blkdev.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/spinlock.h>
 #include <linux/moduleparam.h>
 #include <linux/firmware.h>
diff --git a/drivers/hwmon/hdaps.c b/drivers/hwmon/hdaps.c
index 0015da5668a1..1e5dfc7805e2 100644
--- a/drivers/hwmon/hdaps.c
+++ b/drivers/hwmon/hdaps.c
@@ -27,7 +27,7 @@
 */
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/input.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/i2c/busses/i2c-iop3xx.c b/drivers/i2c/busses/i2c-iop3xx.c
index 9888fae1f37a..13752bcb2afd 100644
--- a/drivers/i2c/busses/i2c-iop3xx.c
+++ b/drivers/i2c/busses/i2c-iop3xx.c
@@ -35,7 +35,7 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/i2c.h>
 #include <asm/io.h>
diff --git a/drivers/i2c/busses/i2c-isa.c b/drivers/i2c/busses/i2c-isa.c
index 4fdc02411609..03672c9ca409 100644
--- a/drivers/i2c/busses/i2c-isa.c
+++ b/drivers/i2c/busses/i2c-isa.c
@@ -38,6 +38,7 @@
 #include <linux/errno.h>
 #include <linux/i2c.h>
 #include <linux/i2c-isa.h>
+#include <linux/platform_device.h>
 static u32 isa_func(struct i2c_adapter *adapter);
diff --git a/drivers/i2c/busses/i2c-ixp2000.c b/drivers/i2c/busses/i2c-ixp2000.c
index 42016ee6ef13..64552a376f2d 100644
--- a/drivers/i2c/busses/i2c-ixp2000.c
+++ b/drivers/i2c/busses/i2c-ixp2000.c
@@ -28,7 +28,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
diff --git a/drivers/i2c/busses/i2c-ixp4xx.c b/drivers/i2c/busses/i2c-ixp4xx.c
index 69303ab65e04..cc652c350814 100644
--- a/drivers/i2c/busses/i2c-ixp4xx.c
+++ b/drivers/i2c/busses/i2c-ixp4xx.c
@@ -28,7 +28,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c
index 8491633005b8..65b939a059e9 100644
--- a/drivers/i2c/busses/i2c-mpc.c
+++ b/drivers/i2c/busses/i2c-mpc.c
@@ -19,6 +19,8 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <linux/fsl_devices.h>
 #include <linux/i2c.h>
diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index d0d2a6f1386e..6b48027b2ee3 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -17,6 +17,8 @@
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/mv643xx.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 /* Register defines */
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 44b595d90a4a..67ccbea24ba4 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -30,6 +30,7 @@
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/i2c-pxa.h>
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/irq.h>
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 6ced28e90070..1b582262e677 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -33,7 +33,7 @@
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/err.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/irq.h>
@@ -918,8 +918,11 @@ static int __init i2c_adap_s3c_init(void)
        int ret;
        ret = driver_register(&s3c2410_i2c_driver);
-        if (ret == 0)
+        if (ret == 0) {
-                ret = driver_register(&s3c2440_i2c_driver); 
+                ret = driver_register(&s3c2440_i2c_driver);
+                if (ret)
+                        driver_unregister(&s3c2410_i2c_driver);
+        }
        return ret;
 }
diff --git a/drivers/i2c/chips/isp1301_omap.c b/drivers/i2c/chips/isp1301_omap.c
index eaa4742e04fa..9dbb72fffbe2 100644
--- a/drivers/i2c/chips/isp1301_omap.c
+++ b/drivers/i2c/chips/isp1301_omap.c
@@ -27,7 +27,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/usb_ch9.h>
 #include <linux/usb_gadget.h>
 #include <linux/usb.h>
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 02e335a04f09..82ea1b7ec914 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -30,6 +30,7 @@
 #include <linux/init.h>
 #include <linux/idr.h>
 #include <linux/seq_file.h>
+#include <linux/platform_device.h>
 #include <asm/uaccess.h>
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index ea14c8f1c82b..8af0bd1424d2 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -34,6 +34,7 @@
 #include <linux/init.h>
 #include <linux/i2c.h>
 #include <linux/i2c-dev.h>
+#include <linux/platform_device.h>
 #include <asm/uaccess.h>
 static struct i2c_client i2cdev_client_template;
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index a4696cd0978c..9f2352bd8348 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -565,6 +565,7 @@ static long evdev_ioctl_compat(struct file *file, unsigned int cmd, unsigned lon
                                                case EV_LED: bits = dev->ledbit; max = LED_MAX; break;
                                                case EV_SND: bits = dev->sndbit; max = SND_MAX; break;
                                                case EV_FF:  bits = dev->ffbit;  max = FF_MAX;  break;
+                                                case EV_SW:  bits = dev->swbit;  max = SW_MAX;  break;
                                                default: return -EINVAL;
                                        }
                                        bit_to_user(bits, max);
@@ -579,6 +580,9 @@ static long evdev_ioctl_compat(struct file *file, unsigned int cmd, unsigned lon
                                if (_IOC_NR(cmd) == _IOC_NR(EVIOCGSND(0)))
                                        bit_to_user(dev->snd, SND_MAX);
+                                if (_IOC_NR(cmd) == _IOC_NR(EVIOCGSW(0)))
+                                        bit_to_user(dev->sw, SW_MAX);
                                if (_IOC_NR(cmd) == _IOC_NR(EVIOCGNAME(0))) {
                                        int len;
                                        if (!dev->name) return -ENOENT;
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 3b1685ff9d10..1a1654caedd5 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -730,7 +730,7 @@ static void input_register_classdevice(struct input_dev *dev)
                 "input%ld", (unsigned long) atomic_inc_return(&input_no) - 1);
        path = kobject_get_path(&dev->cdev.class->subsys.kset.kobj, GFP_KERNEL);
-        printk(KERN_INFO "input: %s/%s as %s\n",
+        printk(KERN_INFO "input: %s as %s/%s\n",
                dev->name ? dev->name : "Unspecified device",
                path ? path : "", dev->cdev.class_id);
        kfree(path);
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 571a68691a4a..4a917748fd9f 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -13,11 +13,11 @@ menuconfig INPUT_KEYBOARD
 if INPUT_KEYBOARD
 config KEYBOARD_ATKBD
-        tristate "AT keyboard" if !PC
+        tristate "AT keyboard" if !X86_PC
        default y
        select SERIO
        select SERIO_LIBPS2
-        select SERIO_I8042 if PC
+        select SERIO_I8042 if X86_PC
        select SERIO_GSCPS2 if GSC
        help
          Say Y here if you want to use a standard AT or PS/2 keyboard. Usually
diff --git a/drivers/input/keyboard/corgikbd.c b/drivers/input/keyboard/corgikbd.c
index 3210d298b3bc..d00d14bb637a 100644
--- a/drivers/input/keyboard/corgikbd.c
+++ b/drivers/input/keyboard/corgikbd.c
@@ -12,7 +12,7 @@
 */
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
diff --git a/drivers/input/keyboard/lkkbd.c b/drivers/input/keyboard/lkkbd.c
index 7f06780a437f..9481132532d0 100644
--- a/drivers/input/keyboard/lkkbd.c
+++ b/drivers/input/keyboard/lkkbd.c
@@ -441,7 +441,7 @@ lkkbd_interrupt (struct serio *serio, unsigned char data, unsigned int flags,
                        input_sync (lk->dev);
                        break;
                case LK_METRONOME:
-                        DBG (KERN_INFO "Got %#d and don't "
+                        DBG (KERN_INFO "Got LK_METRONOME and don't "
                                        "know how to handle...\n");
                        break;
                case LK_OUTPUT_ERROR:
diff --git a/drivers/input/keyboard/spitzkbd.c b/drivers/input/keyboard/spitzkbd.c
index cee9c734a048..0fa38a559cdf 100644
--- a/drivers/input/keyboard/spitzkbd.c
+++ b/drivers/input/keyboard/spitzkbd.c
@@ -12,7 +12,7 @@
 */
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
diff --git a/drivers/input/misc/pcspkr.c b/drivers/input/misc/pcspkr.c
index e34633c37fdd..68ac97f101b0 100644
--- a/drivers/input/misc/pcspkr.c
+++ b/drivers/input/misc/pcspkr.c
@@ -71,7 +71,7 @@ static int __init pcspkr_init(void)
                return -ENOMEM;
        pcspkr_dev->name = "PC Speaker";
-        pcspkr_dev->name = "isa0061/input0";
+        pcspkr_dev->phys = "isa0061/input0";
        pcspkr_dev->id.bustype = BUS_ISA;
        pcspkr_dev->id.vendor = 0x001f;
        pcspkr_dev->id.product = 0x0001;
diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig
index 537154dd7a87..574b18a523af 100644
--- a/drivers/input/mouse/Kconfig
+++ b/drivers/input/mouse/Kconfig
@@ -17,7 +17,7 @@ config MOUSE_PS2
        default y
        select SERIO
        select SERIO_LIBPS2
-        select SERIO_I8042 if PC
+        select SERIO_I8042 if X86_PC
        select SERIO_GSCPS2 if GSC
        ---help---
          Say Y here if you have a PS/2 mouse connected to your system. This
diff --git a/drivers/input/serio/ct82c710.c b/drivers/input/serio/ct82c710.c
index dd0f5bd90241..4da6c86b5d76 100644
--- a/drivers/input/serio/ct82c710.c
+++ b/drivers/input/serio/ct82c710.c
@@ -37,6 +37,7 @@
 #include <linux/serio.h>
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 4bc40f159996..01e186422021 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -20,6 +20,7 @@
 #include <linux/serio.h>
 #include <linux/err.h>
 #include <linux/rcupdate.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
diff --git a/drivers/input/serio/maceps2.c b/drivers/input/serio/maceps2.c
index 9880fc145d90..d857f7081adb 100644
--- a/drivers/input/serio/maceps2.c
+++ b/drivers/input/serio/maceps2.c
@@ -14,7 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/err.h>
diff --git a/drivers/input/serio/q40kbd.c b/drivers/input/serio/q40kbd.c
index 46093c507988..b44d255596c2 100644
--- a/drivers/input/serio/q40kbd.c
+++ b/drivers/input/serio/q40kbd.c
@@ -37,6 +37,7 @@
 #include <linux/interrupt.h>
 #include <linux/err.h>
 #include <linux/bitops.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
diff --git a/drivers/input/serio/rpckbd.c b/drivers/input/serio/rpckbd.c
index 106f5eefd89a..52c49258f8a4 100644
--- a/drivers/input/serio/rpckbd.c
+++ b/drivers/input/serio/rpckbd.c
@@ -34,6 +34,7 @@
 #include <linux/init.h>
 #include <linux/serio.h>
 #include <linux/err.h>
+#include <linux/platform_device.h>
 #include <asm/irq.h>
 #include <asm/hardware.h>
diff --git a/drivers/input/touchscreen/corgi_ts.c b/drivers/input/touchscreen/corgi_ts.c
index 0ba3e6562bff..15e88eeae8d6 100644
--- a/drivers/input/touchscreen/corgi_ts.c
+++ b/drivers/input/touchscreen/corgi_ts.c
@@ -11,7 +11,7 @@
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
diff --git a/drivers/macintosh/adbhid.c b/drivers/macintosh/adbhid.c
index cdb6d0283195..8f02c155fdc0 100644
--- a/drivers/macintosh/adbhid.c
+++ b/drivers/macintosh/adbhid.c
@@ -723,6 +723,7 @@ adbhid_input_register(int id, int default_id, int original_handler_id,
        sprintf(hid->phys, "adb%d:%d.%02x/input", id, default_id, original_handler_id);
+        hid->input = input_dev;
        hid->id = default_id;
        hid->original_handler_id = original_handler_id;
        hid->current_handler_id = current_handler_id;
diff --git a/drivers/mfd/mcp-sa11x0.c b/drivers/mfd/mcp-sa11x0.c
index 720e7a326308..7daa0ed7331c 100644
--- a/drivers/mfd/mcp-sa11x0.c
+++ b/drivers/mfd/mcp-sa11x0.c
@@ -18,7 +18,7 @@
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/dma.h>
 #include <asm/hardware.h>
diff --git a/drivers/misc/hdpuftrs/hdpu_cpustate.c b/drivers/misc/hdpuftrs/hdpu_cpustate.c
index 46de5c940555..9c4dd682ac74 100644
--- a/drivers/misc/hdpuftrs/hdpu_cpustate.c
+++ b/drivers/misc/hdpuftrs/hdpu_cpustate.c
@@ -21,7 +21,7 @@
 #include <linux/miscdevice.h>
 #include <linux/pci.h>
 #include <linux/proc_fs.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/uaccess.h>
 #include <linux/hdpu_features.h>
diff --git a/drivers/misc/hdpuftrs/hdpu_nexus.c b/drivers/misc/hdpuftrs/hdpu_nexus.c
index c203b27269ea..165f3405df27 100644
--- a/drivers/misc/hdpuftrs/hdpu_nexus.c
+++ b/drivers/misc/hdpuftrs/hdpu_nexus.c
@@ -21,7 +21,7 @@
 #include <linux/hdpu_features.h>
 #include <linux/pci.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 static int hdpu_nexus_probe(struct device *ddev);
 static int hdpu_nexus_remove(struct device *ddev);
diff --git a/drivers/mmc/pxamci.c b/drivers/mmc/pxamci.c
index d575e3a018bc..f31e247b2cbe 100644
--- a/drivers/mmc/pxamci.c
+++ b/drivers/mmc/pxamci.c
@@ -20,7 +20,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
diff --git a/drivers/mmc/wbsd.c b/drivers/mmc/wbsd.c
index 3ace875decc4..942668e93a74 100644
--- a/drivers/mmc/wbsd.c
+++ b/drivers/mmc/wbsd.c
@@ -26,7 +26,7 @@
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/delay.h>
diff --git a/drivers/mtd/maps/bast-flash.c b/drivers/mtd/maps/bast-flash.c
index 63104c73ca3c..bfe994e59265 100644
--- a/drivers/mtd/maps/bast-flash.c
+++ b/drivers/mtd/maps/bast-flash.c
@@ -34,7 +34,7 @@
 #include <linux/ioport.h>
 #include <linux/device.h>
 #include <linux/slab.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/map.h>
 #include <linux/mtd/partitions.h>
diff --git a/drivers/mtd/maps/integrator-flash.c b/drivers/mtd/maps/integrator-flash.c
index e39a98a0171c..d14a0185b8f4 100644
--- a/drivers/mtd/maps/integrator-flash.c
+++ b/drivers/mtd/maps/integrator-flash.c
@@ -32,7 +32,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/mtd/mtd.h>
diff --git a/drivers/mtd/maps/ixp2000.c b/drivers/mtd/maps/ixp2000.c
index 1e5d6e1d05f3..00b9f67580f1 100644
--- a/drivers/mtd/maps/ixp2000.c
+++ b/drivers/mtd/maps/ixp2000.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/map.h>
diff --git a/drivers/mtd/maps/ixp4xx.c b/drivers/mtd/maps/ixp4xx.c
index da316e543237..733a9297a562 100644
--- a/drivers/mtd/maps/ixp4xx.c
+++ b/drivers/mtd/maps/ixp4xx.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/map.h>
diff --git a/drivers/mtd/maps/omap_nor.c b/drivers/mtd/maps/omap_nor.c
index fa84566245a7..7f370bb794fe 100644
--- a/drivers/mtd/maps/omap_nor.c
+++ b/drivers/mtd/maps/omap_nor.c
@@ -30,7 +30,7 @@
 * 675 Mass Ave, Cambridge, MA 02139, USA.
 */
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/drivers/mtd/maps/plat-ram.c b/drivers/mtd/maps/plat-ram.c
index a0577ea00c3c..104576b5be34 100644
--- a/drivers/mtd/maps/plat-ram.c
+++ b/drivers/mtd/maps/plat-ram.c
@@ -31,6 +31,7 @@
 #include <linux/ioport.h>
 #include <linux/device.h>
 #include <linux/slab.h>
+#include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/map.h>
diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c
index c81bec7b14d5..c8d0da19d897 100644
--- a/drivers/mtd/maps/sa1100-flash.c
+++ b/drivers/mtd/maps/sa1100-flash.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/err.h>
 #include <linux/mtd/mtd.h>
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index b58ba236a9eb..2df5e47d1f5c 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -48,7 +48,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/slab.h>
diff --git a/drivers/net/depca.c b/drivers/net/depca.c
index c4aa5fe2840e..4d26e5e7d18b 100644
--- a/drivers/net/depca.c
+++ b/drivers/net/depca.c
@@ -254,7 +254,7 @@
 #include <linux/unistd.h>
 #include <linux/ctype.h>
 #include <linux/moduleparam.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/bitops.h>
 #include <asm/uaccess.h>
diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c
index abce1f730d00..c0af6fb1fbba 100644
--- a/drivers/net/dm9000.c
+++ b/drivers/net/dm9000.c
@@ -66,6 +66,7 @@
 #include <linux/mii.h>
 #include <linux/dm9000.h>
 #include <linux/delay.h>
+#include <linux/platform_device.h>
 #include <asm/delay.h>
 #include <asm/irq.h>
diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c
index ae5a2ed3b264..962580f2c4ab 100644
--- a/drivers/net/gianfar.c
+++ b/drivers/net/gianfar.c
@@ -81,7 +81,7 @@
 #include <linux/if_vlan.h>
 #include <linux/spinlock.h>
 #include <linux/mm.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
diff --git a/drivers/net/gianfar_mii.c b/drivers/net/gianfar_mii.c
index 1eca1dbca7f1..5a74d3d3dbe1 100644
--- a/drivers/net/gianfar_mii.c
+++ b/drivers/net/gianfar_mii.c
@@ -33,6 +33,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/version.h>
+#include <linux/platform_device.h>
 #include <asm/ocp.h>
 #include <linux/crc32.h>
 #include <linux/mii.h>
diff --git a/drivers/net/irda/pxaficp_ir.c b/drivers/net/irda/pxaficp_ir.c
index b886b07412a6..e1aa9910503b 100644
--- a/drivers/net/irda/pxaficp_ir.c
+++ b/drivers/net/irda/pxaficp_ir.c
@@ -22,6 +22,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <net/irda/irda.h>
diff --git a/drivers/net/irda/sa1100_ir.c b/drivers/net/irda/sa1100_ir.c
index 06883309916d..76e0b9fb5e96 100644
--- a/drivers/net/irda/sa1100_ir.c
+++ b/drivers/net/irda/sa1100_ir.c
@@ -29,7 +29,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <net/irda/irda.h>
diff --git a/drivers/net/irda/smsc-ircc2.c b/drivers/net/irda/smsc-ircc2.c
index 140b7cdb1f7e..a1d207f2fa68 100644
--- a/drivers/net/irda/smsc-ircc2.c
+++ b/drivers/net/irda/smsc-ircc2.c
@@ -53,6 +53,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/serial_reg.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/dma.h>
diff --git a/drivers/net/jazzsonic.c b/drivers/net/jazzsonic.c
index 8423cb6875f0..a74a5cfaf5bc 100644
--- a/drivers/net/jazzsonic.c
+++ b/drivers/net/jazzsonic.c
@@ -33,7 +33,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <asm/bootinfo.h>
diff --git a/drivers/net/macsonic.c b/drivers/net/macsonic.c
index 405e18365ede..e9c999d7eb39 100644
--- a/drivers/net/macsonic.c
+++ b/drivers/net/macsonic.c
@@ -47,7 +47,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <asm/bootinfo.h>
diff --git a/drivers/net/mipsnet.c b/drivers/net/mipsnet.c
index f79f7ee72ab8..bbffb585b3b3 100644
--- a/drivers/net/mipsnet.c
+++ b/drivers/net/mipsnet.c
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/etherdevice.h>
 #include <linux/netdevice.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/mips-boards/simint.h>
diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c
index 8fbba21d975b..71f2c6705bc3 100644
--- a/drivers/net/mv643xx_eth.c
+++ b/drivers/net/mv643xx_eth.c
@@ -39,6 +39,8 @@
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/ethtool.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/types.h>
 #include <asm/pgtable.h>
diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c
index c573bb351d4c..74d5f1a6fdea 100644
--- a/drivers/net/smc91x.c
+++ b/drivers/net/smc91x.c
@@ -77,7 +77,7 @@ static const char version[] =
 #include <linux/errno.h>
 #include <linux/ioport.h>
 #include <linux/crc32.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/spinlock.h>
 #include <linux/ethtool.h>
 #include <linux/mii.h>
diff --git a/drivers/net/tokenring/proteon.c b/drivers/net/tokenring/proteon.c
index eb1423ede75c..d04c918ebef8 100644
--- a/drivers/net/tokenring/proteon.c
+++ b/drivers/net/tokenring/proteon.c
@@ -29,6 +29,7 @@ static const char version[] = "proteon.c: v1.00 02/01/2003 by Jochen Friedrich\n
 #include <linux/init.h>
 #include <linux/netdevice.h>
 #include <linux/trdevice.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/io.h>
diff --git a/drivers/net/tokenring/skisa.c b/drivers/net/tokenring/skisa.c
index 3c7c66204f74..72cf708396be 100644
--- a/drivers/net/tokenring/skisa.c
+++ b/drivers/net/tokenring/skisa.c
@@ -36,6 +36,7 @@ static const char version[] = "skisa.c: v1.03 09/12/2002 by Jochen Friedrich\n";
 #include <linux/init.h>
 #include <linux/netdevice.h>
 #include <linux/trdevice.h>
+#include <linux/platform_device.h>
 #include <asm/system.h>
 #include <asm/io.h>
diff --git a/drivers/pcmcia/au1000_generic.c b/drivers/pcmcia/au1000_generic.c
index ba48cef3a9dc..87302c548c24 100644
--- a/drivers/pcmcia/au1000_generic.c
+++ b/drivers/pcmcia/au1000_generic.c
@@ -42,7 +42,7 @@
 #include <linux/notifier.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/drivers/pcmcia/hd64465_ss.c b/drivers/pcmcia/hd64465_ss.c
index b57a0b98b4d6..561706ba4499 100644
--- a/drivers/pcmcia/hd64465_ss.c
+++ b/drivers/pcmcia/hd64465_ss.c
@@ -37,7 +37,7 @@
 #include <asm/errno.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/hd64465/hd64465.h>
diff --git a/drivers/pcmcia/i82365.c b/drivers/pcmcia/i82365.c
index 4a41f67d185d..7ce455d01cc9 100644
--- a/drivers/pcmcia/i82365.c
+++ b/drivers/pcmcia/i82365.c
@@ -47,7 +47,7 @@
 #include <linux/delay.h>
 #include <linux/workqueue.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/bitops.h>
 #include <asm/irq.h>
 #include <asm/io.h>
diff --git a/drivers/pcmcia/m32r_cfc.c b/drivers/pcmcia/m32r_cfc.c
index c6ed70ea4812..2c22b4b3619d 100644
--- a/drivers/pcmcia/m32r_cfc.c
+++ b/drivers/pcmcia/m32r_cfc.c
@@ -23,7 +23,7 @@
 #include <linux/delay.h>
 #include <linux/workqueue.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/bitops.h>
 #include <asm/irq.h>
 #include <asm/io.h>
diff --git a/drivers/pcmcia/m32r_pcc.c b/drivers/pcmcia/m32r_pcc.c
index 3397ff28de6a..356a6fb416a1 100644
--- a/drivers/pcmcia/m32r_pcc.c
+++ b/drivers/pcmcia/m32r_pcc.c
@@ -23,7 +23,7 @@
 #include <linux/delay.h>
 #include <linux/workqueue.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/irq.h>
 #include <asm/io.h>
 #include <asm/bitops.h>
diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c
index 2558c3cc91ec..47b5ade95bde 100644
--- a/drivers/pcmcia/omap_cf.c
+++ b/drivers/pcmcia/omap_cf.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/delay.h>
diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c
index c2a12d53f6c7..7fa18fb814bc 100644
--- a/drivers/pcmcia/pxa2xx_base.c
+++ b/drivers/pcmcia/pxa2xx_base.c
@@ -23,6 +23,7 @@
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/io.h>
diff --git a/drivers/pcmcia/pxa2xx_mainstone.c b/drivers/pcmcia/pxa2xx_mainstone.c
index bbe69b07ce50..5209d8c7764f 100644
--- a/drivers/pcmcia/pxa2xx_mainstone.c
+++ b/drivers/pcmcia/pxa2xx_mainstone.c
@@ -17,7 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <pcmcia/ss.h>
diff --git a/drivers/pcmcia/pxa2xx_sharpsl.c b/drivers/pcmcia/pxa2xx_sharpsl.c
index bd924336a49f..fe5ea36e7de3 100644
--- a/drivers/pcmcia/pxa2xx_sharpsl.c
+++ b/drivers/pcmcia/pxa2xx_sharpsl.c
@@ -16,7 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <asm/mach-types.h>
 #include <asm/hardware.h>
diff --git a/drivers/pcmcia/sa1100_generic.c b/drivers/pcmcia/sa1100_generic.c
index acf60ffc8a12..6d441ec75c6a 100644
--- a/drivers/pcmcia/sa1100_generic.c
+++ b/drivers/pcmcia/sa1100_generic.c
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/config.h>
+#include <linux/platform_device.h>
 #include <pcmcia/cs_types.h>
 #include <pcmcia/cs.h>
diff --git a/drivers/pcmcia/tcic.c b/drivers/pcmcia/tcic.c
index f158b67f6610..e31263864377 100644
--- a/drivers/pcmcia/tcic.c
+++ b/drivers/pcmcia/tcic.c
@@ -44,7 +44,7 @@
 #include <linux/ioport.h>
 #include <linux/delay.h>
 #include <linux/workqueue.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/bitops.h>
 #include <asm/io.h>
diff --git a/drivers/pcmcia/vrc4171_card.c b/drivers/pcmcia/vrc4171_card.c
index 3d2dca675e02..38a028c725d4 100644
--- a/drivers/pcmcia/vrc4171_card.c
+++ b/drivers/pcmcia/vrc4171_card.c
@@ -24,6 +24,7 @@
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 #include <linux/types.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index f24d84538fd5..71dd1ebbe58f 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -30,6 +30,7 @@
 #include <linux/init.h>
 #include <linux/completion.h>
 #include <linux/transport_class.h>
+#include <linux/platform_device.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/scsi/ide-scsi.c b/drivers/scsi/ide-scsi.c
index 00d6a6657ebc..a440ea38efaa 100644
--- a/drivers/scsi/ide-scsi.c
+++ b/drivers/scsi/ide-scsi.c
@@ -180,12 +180,22 @@ static void idescsi_input_buffers (ide_drive_t *drive, idescsi_pc_t *pc, unsigne
                        return;
                }
                count = min(pc->sg->length - pc->b_count, bcount);
-                buf = kmap_atomic(pc->sg->page, KM_IRQ0);
+                if (PageHighMem(pc->sg->page)) {
-                drive->hwif->atapi_input_bytes(drive,
+                        unsigned long flags;
-                                buf + pc->b_count + pc->sg->offset, count);
-                kunmap_atomic(buf, KM_IRQ0);
+                        local_irq_save(flags);
-                bcount -= count;
+                        buf = kmap_atomic(pc->sg->page, KM_IRQ0) +
-                pc->b_count += count;
+                                        pc->sg->offset;
+                        drive->hwif->atapi_input_bytes(drive,
+                                                buf + pc->b_count, count);
+                        kunmap_atomic(buf - pc->sg->offset, KM_IRQ0);
+                        local_irq_restore(flags);
+                } else {
+                        buf = page_address(pc->sg->page) + pc->sg->offset;
+                        drive->hwif->atapi_input_bytes(drive,
+                                                buf + pc->b_count, count);
+                }
+                bcount -= count; pc->b_count += count;
                if (pc->b_count == pc->sg->length) {
                        pc->sg++;
                        pc->b_count = 0;
@@ -205,12 +215,22 @@ static void idescsi_output_buffers (ide_drive_t *drive, idescsi_pc_t *pc, unsign
                        return;
                }
                count = min(pc->sg->length - pc->b_count, bcount);
-                buf = kmap_atomic(pc->sg->page, KM_IRQ0);
+                if (PageHighMem(pc->sg->page)) {
-                drive->hwif->atapi_output_bytes(drive,
+                        unsigned long flags;
-                                buf + pc->b_count + pc->sg->offset, count);
-                kunmap_atomic(buf, KM_IRQ0);
+                        local_irq_save(flags);
-                bcount -= count;
+                        buf = kmap_atomic(pc->sg->page, KM_IRQ0) +
-                pc->b_count += count;
+                                                pc->sg->offset;
+                        drive->hwif->atapi_output_bytes(drive,
+                                                buf + pc->b_count, count);
+                        kunmap_atomic(buf - pc->sg->offset, KM_IRQ0);
+                        local_irq_restore(flags);
+                } else {
+                        buf = page_address(pc->sg->page) + pc->sg->offset;
+                        drive->hwif->atapi_output_bytes(drive,
+                                                buf + pc->b_count, count);
+                }
+                bcount -= count; pc->b_count += count;
                if (pc->b_count == pc->sg->length) {
                        pc->sg++;
                        pc->b_count = 0;
diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c
index 8be7dc0b47b8..ff18fa7044c5 100644
--- a/drivers/scsi/libata-core.c
+++ b/drivers/scsi/libata-core.c
@@ -295,28 +295,6 @@ void ata_exec_command(struct ata_port *ap, const struct ata_taskfile *tf)
 }
 /**
- *      ata_exec - issue ATA command to host controller
- *      @ap: port to which command is being issued
- *      @tf: ATA taskfile register set
- *
- *      Issues PIO/MMIO write to ATA command register, with proper
- *      synchronization with interrupt handler / other threads.
- *
- *      LOCKING:
- *      Obtains host_set lock.
- */
-static inline void ata_exec(struct ata_port *ap, const struct ata_taskfile *tf)
-{
-        unsigned long flags;
-        DPRINTK("ata%u: cmd 0x%X\n", ap->id, tf->command);
-        spin_lock_irqsave(&ap->host_set->lock, flags);
-        ap->ops->exec_command(ap, tf);
-        spin_unlock_irqrestore(&ap->host_set->lock, flags);
-}
-/**
 *      ata_tf_to_host - issue ATA taskfile to host controller
 *      @ap: port to which command is being issued
 *      @tf: ATA taskfile register set
@@ -326,30 +304,11 @@ static inline void ata_exec(struct ata_port *ap, const struct ata_taskfile *tf)
 *      other threads.
 *
 *      LOCKING:
- *      Obtains host_set lock.
- */
-static void ata_tf_to_host(struct ata_port *ap, const struct ata_taskfile *tf)
-{
-        ap->ops->tf_load(ap, tf);
-        ata_exec(ap, tf);
-}
-/**
- *      ata_tf_to_host_nolock - issue ATA taskfile to host controller
- *      @ap: port to which command is being issued
- *      @tf: ATA taskfile register set
- *
- *      Issues ATA taskfile register set to ATA host controller,
- *      with proper synchronization with interrupt handler and
- *      other threads.
- *
- *      LOCKING:
 *      spin_lock_irqsave(host_set lock)
 */
-void ata_tf_to_host_nolock(struct ata_port *ap, const struct ata_taskfile *tf)
+static inline void ata_tf_to_host(struct ata_port *ap,
+                                  const struct ata_taskfile *tf)
 {
        ap->ops->tf_load(ap, tf);
        ap->ops->exec_command(ap, tf);
@@ -1912,12 +1871,14 @@ static void ata_bus_post_reset(struct ata_port *ap, unsigned int devmask)
 *
 *      LOCKING:
 *      PCI/etc. bus probe sem.
+ *      Obtains host_set lock.
 *
 */
 static unsigned int ata_bus_edd(struct ata_port *ap)
 {
        struct ata_taskfile tf;
+        unsigned long flags;
        /* set up execute-device-diag (bus reset) taskfile */
        /* also, take interrupts to a known state (disabled) */
@@ -1928,7 +1889,9 @@ static unsigned int ata_bus_edd(struct ata_port *ap)
        tf.protocol = ATA_PROT_NODATA;
        /* do bus reset */
+        spin_lock_irqsave(&ap->host_set->lock, flags);
        ata_tf_to_host(ap, &tf);
+        spin_unlock_irqrestore(&ap->host_set->lock, flags);
        /* spec says at least 2ms.  but who knows with those
         * crazy ATAPI devices...
@@ -3555,7 +3518,7 @@ int ata_qc_issue_prot(struct ata_queued_cmd *qc)
        switch (qc->tf.protocol) {
        case ATA_PROT_NODATA:
-                ata_tf_to_host_nolock(ap, &qc->tf);
+                ata_tf_to_host(ap, &qc->tf);
                break;
        case ATA_PROT_DMA:
@@ -3566,20 +3529,20 @@ int ata_qc_issue_prot(struct ata_queued_cmd *qc)
        case ATA_PROT_PIO: /* load tf registers, initiate polling pio */
                ata_qc_set_polling(qc);
-                ata_tf_to_host_nolock(ap, &qc->tf);
+                ata_tf_to_host(ap, &qc->tf);
                ap->hsm_task_state = HSM_ST;
                queue_work(ata_wq, &ap->pio_task);
                break;
        case ATA_PROT_ATAPI:
                ata_qc_set_polling(qc);
-                ata_tf_to_host_nolock(ap, &qc->tf);
+                ata_tf_to_host(ap, &qc->tf);
                queue_work(ata_wq, &ap->packet_task);
                break;
        case ATA_PROT_ATAPI_NODATA:
                ap->flags |= ATA_FLAG_NOINTR;
-                ata_tf_to_host_nolock(ap, &qc->tf);
+                ata_tf_to_host(ap, &qc->tf);
                queue_work(ata_wq, &ap->packet_task);
                break;
@@ -4126,8 +4089,6 @@ static void ata_host_init(struct ata_port *ap, struct Scsi_Host *host,
        host->unique_id = ata_unique_id++;
        host->max_cmd_len = 12;
-        scsi_assign_lock(host, &host_set->lock);
        ap->flags = ATA_FLAG_PORT_DISABLED;
        ap->id = host->unique_id;
        ap->host = host;
diff --git a/drivers/scsi/libata-scsi.c b/drivers/scsi/libata-scsi.c
index 1e3792f86fcf..248baae96486 100644
--- a/drivers/scsi/libata-scsi.c
+++ b/drivers/scsi/libata-scsi.c
@@ -39,6 +39,7 @@
 #include <scsi/scsi.h>
 #include "scsi.h"
 #include <scsi/scsi_host.h>
+#include <scsi/scsi_device.h>
 #include <linux/libata.h>
 #include <linux/hdreg.h>
 #include <asm/uaccess.h>
@@ -2405,8 +2406,12 @@ int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
        struct ata_port *ap;
        struct ata_device *dev;
        struct scsi_device *scsidev = cmd->device;
+        struct Scsi_Host *shost = scsidev->host;
-        ap = (struct ata_port *) &scsidev->host->hostdata[0];
+        ap = (struct ata_port *) &shost->hostdata[0];
+        spin_unlock(shost->host_lock);
+        spin_lock(&ap->host_set->lock);
        ata_scsi_dump_cdb(ap, cmd);
@@ -2429,6 +2434,8 @@ int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
                ata_scsi_translate(ap, dev, cmd, done, atapi_xlat);
 out_unlock:
+        spin_unlock(&ap->host_set->lock);
+        spin_lock(shost->host_lock);
        return 0;
 }
diff --git a/drivers/scsi/libata.h b/drivers/scsi/libata.h
index 10ecd9e15e4f..fad051ca4672 100644
--- a/drivers/scsi/libata.h
+++ b/drivers/scsi/libata.h
@@ -48,7 +48,6 @@ extern int ata_qc_issue(struct ata_queued_cmd *qc);
 extern int ata_check_atapi_dma(struct ata_queued_cmd *qc);
 extern void ata_dev_select(struct ata_port *ap, unsigned int device,
                           unsigned int wait, unsigned int can_sleep);
-extern void ata_tf_to_host_nolock(struct ata_port *ap, const struct ata_taskfile *tf);
 extern void swap_buf_le16(u16 *buf, unsigned int buf_words);
 extern int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg);
 extern int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg);
diff --git a/drivers/serial/8250.c b/drivers/serial/8250.c
index afb7ddf200e0..f47d2c454e33 100644
--- a/drivers/serial/8250.c
+++ b/drivers/serial/8250.c
@@ -33,7 +33,7 @@
 #include <linux/sysrq.h>
 #include <linux/mca.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/serial_reg.h>
diff --git a/drivers/serial/imx.c b/drivers/serial/imx.c
index 5b3933b0c997..4a54ff584700 100644
--- a/drivers/serial/imx.c
+++ b/drivers/serial/imx.c
@@ -36,7 +36,7 @@
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/sysrq.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/serial_core.h>
@@ -995,6 +995,7 @@ static int __init imx_serial_init(void)
 static void __exit imx_serial_exit(void)
 {
        uart_unregister_driver(&imx_reg);
+        driver_unregister(&serial_imx_driver);
 }
 module_init(imx_serial_init);
diff --git a/drivers/serial/mpc52xx_uart.c b/drivers/serial/mpc52xx_uart.c
index 8a79968f8ce1..0dd08a09e7e6 100644
--- a/drivers/serial/mpc52xx_uart.c
+++ b/drivers/serial/mpc52xx_uart.c
@@ -45,7 +45,7 @@
 */
 #include <linux/config.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/tty.h>
 #include <linux/serial.h>
diff --git a/drivers/serial/mpsc.c b/drivers/serial/mpsc.c
index aec83f577ce6..ba8838b234da 100644
--- a/drivers/serial/mpsc.c
+++ b/drivers/serial/mpsc.c
@@ -52,6 +52,8 @@
 * 4) AFAICT, hardware flow control isn't supported by the controller --MAG.
 */
+#include <linux/platform_device.h>
 #include "mpsc.h"
 /*
diff --git a/drivers/serial/pxa.c b/drivers/serial/pxa.c
index 8cc4cedadd99..16b2f9417af9 100644
--- a/drivers/serial/pxa.c
+++ b/drivers/serial/pxa.c
@@ -39,7 +39,7 @@
 #include <linux/circ_buf.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/serial_core.h>
diff --git a/drivers/serial/s3c2410.c b/drivers/serial/s3c2410.c
index 06a17dff1a73..036792328d49 100644
--- a/drivers/serial/s3c2410.c
+++ b/drivers/serial/s3c2410.c
@@ -63,7 +63,7 @@
 #include <linux/module.h>
 #include <linux/ioport.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/sysrq.h>
 #include <linux/console.h>
diff --git a/drivers/serial/sa1100.c b/drivers/serial/sa1100.c
index c4a789e6af44..ed618cc7ae96 100644
--- a/drivers/serial/sa1100.c
+++ b/drivers/serial/sa1100.c
@@ -35,7 +35,7 @@
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/sysrq.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/serial_core.h>
diff --git a/drivers/serial/vr41xx_siu.c b/drivers/serial/vr41xx_siu.c
index 2b623ab0e36e..01696b3e3f61 100644
--- a/drivers/serial/vr41xx_siu.c
+++ b/drivers/serial/vr41xx_siu.c
@@ -26,7 +26,7 @@
 #endif
 #include <linux/console.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/err.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
diff --git a/drivers/usb/gadget/dummy_hcd.c b/drivers/usb/gadget/dummy_hcd.c
index 02106bebd5c1..975ace3f5b1e 100644
--- a/drivers/usb/gadget/dummy_hcd.c
+++ b/drivers/usb/gadget/dummy_hcd.c
@@ -50,7 +50,7 @@
 #include <linux/list.h>
 #include <linux/interrupt.h>
 #include <linux/version.h>
+#include <linux/platform_device.h>
 #include <linux/usb.h>
 #include <linux/usb_gadget.h>
diff --git a/drivers/usb/gadget/lh7a40x_udc.c b/drivers/usb/gadget/lh7a40x_udc.c
index 9b3673904daf..bc6269f10cbb 100644
--- a/drivers/usb/gadget/lh7a40x_udc.c
+++ b/drivers/usb/gadget/lh7a40x_udc.c
@@ -21,6 +21,8 @@
 *
 */
+#include <linux/platform_device.h>
 #include "lh7a40x_udc.h"
 //#define DEBUG printk
diff --git a/drivers/usb/gadget/omap_udc.c b/drivers/usb/gadget/omap_udc.c
index 41c96b0afbb3..387692a3611e 100644
--- a/drivers/usb/gadget/omap_udc.c
+++ b/drivers/usb/gadget/omap_udc.c
@@ -38,7 +38,7 @@
 #include <linux/proc_fs.h>
 #include <linux/mm.h>
 #include <linux/moduleparam.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/usb_ch9.h>
 #include <linux/usb_gadget.h>
 #include <linux/usb_otg.h>
diff --git a/drivers/usb/gadget/pxa2xx_udc.c b/drivers/usb/gadget/pxa2xx_udc.c
index f83a9262f953..ee9cd7869d92 100644
--- a/drivers/usb/gadget/pxa2xx_udc.c
+++ b/drivers/usb/gadget/pxa2xx_udc.c
@@ -43,7 +43,7 @@
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
 #include <linux/mm.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <asm/byteorder.h>
diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index ddb8fc591466..f9c3f5b8dd1c 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -70,6 +70,7 @@
 #include <linux/interrupt.h>
 #include <linux/usb.h>
 #include <linux/usb_isp116x.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/drivers/usb/host/ohci-au1xxx.c b/drivers/usb/host/ohci-au1xxx.c
index a277e258eb6c..f0c78cf14b6c 100644
--- a/drivers/usb/host/ohci-au1xxx.c
+++ b/drivers/usb/host/ohci-au1xxx.c
@@ -18,6 +18,8 @@
 * This file is licenced under the GPL.
 */
+#include <linux/platform_device.h>
 #include <asm/mach-au1x00/au1000.h>
 #define USBH_ENABLE_BE (1<<0)
diff --git a/drivers/usb/host/ohci-lh7a404.c b/drivers/usb/host/ohci-lh7a404.c
index 238fa4ade615..336c766c6e29 100644
--- a/drivers/usb/host/ohci-lh7a404.c
+++ b/drivers/usb/host/ohci-lh7a404.c
@@ -16,6 +16,8 @@
 * This file is licenced under the GPL.
 */
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c
index 49815ec4b842..e46cc540cf4d 100644
--- a/drivers/usb/host/ohci-omap.c
+++ b/drivers/usb/host/ohci-omap.c
@@ -16,6 +16,7 @@
 #include <linux/signal.h>       /* SA_INTERRUPT */
 #include <linux/jiffies.h>
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/io.h>
diff --git a/drivers/usb/host/ohci-ppc-soc.c b/drivers/usb/host/ohci-ppc-soc.c
index 4832e57ae579..92cf6f4a1374 100644
--- a/drivers/usb/host/ohci-ppc-soc.c
+++ b/drivers/usb/host/ohci-ppc-soc.c
@@ -14,6 +14,8 @@
 * This file is licenced under the GPL.
 */
+#include <linux/platform_device.h>
 /* configure so an HC device and id are always provided */
 /* always called with process context; sleeping is OK */
diff --git a/drivers/usb/host/ohci-pxa27x.c b/drivers/usb/host/ohci-pxa27x.c
index f4a4aeda40b7..59e20568e8f9 100644
--- a/drivers/usb/host/ohci-pxa27x.c
+++ b/drivers/usb/host/ohci-pxa27x.c
@@ -21,6 +21,8 @@
 #include <linux/device.h>
 #include <linux/signal.h>
+#include <linux/platform_device.h>
 #include <asm/mach-types.h>
 #include <asm/hardware.h>
 #include <asm/arch/pxa-regs.h>
diff --git a/drivers/usb/host/ohci-s3c2410.c b/drivers/usb/host/ohci-s3c2410.c
index fab420a2ce71..ee1fc605b402 100644
--- a/drivers/usb/host/ohci-s3c2410.c
+++ b/drivers/usb/host/ohci-s3c2410.c
@@ -19,6 +19,8 @@
 * This file is licenced under the GPL.
 */
+#include <linux/platform_device.h>
 #include <asm/hardware.h>
 #include <asm/hardware/clock.h>
 #include <asm/arch/usb-control.h>
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index b7fd3f644e1e..b1aa350fd32f 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -138,11 +138,23 @@ reset_needed:
 }
 EXPORT_SYMBOL_GPL(uhci_check_and_reset_hc);
+static inline int io_type_enabled(struct pci_dev *pdev, unsigned int mask)
+{
+        u16 cmd;
+        return !pci_read_config_word(pdev, PCI_COMMAND, &cmd) && (cmd & mask);
+}
+#define pio_enabled(dev) io_type_enabled(dev, PCI_COMMAND_IO)
+#define mmio_enabled(dev) io_type_enabled(dev, PCI_COMMAND_MEMORY)
 static void __devinit quirk_usb_handoff_uhci(struct pci_dev *pdev)
 {
        unsigned long base = 0;
        int i;
+        if (!pio_enabled(pdev))
+                return;
        for (i = 0; i < PCI_ROM_RESOURCE; i++)
                if ((pci_resource_flags(pdev, i) & IORESOURCE_IO)) {
                        base = pci_resource_start(pdev, i);
@@ -153,12 +165,20 @@ static void __devinit quirk_usb_handoff_uhci(struct pci_dev *pdev)
                uhci_check_and_reset_hc(pdev, base);
 }
+static int __devinit mmio_resource_enabled(struct pci_dev *pdev, int idx)
+{
+        return pci_resource_start(pdev, idx) && mmio_enabled(pdev);
+}
 static void __devinit quirk_usb_handoff_ohci(struct pci_dev *pdev)
 {
        void __iomem *base;
        int wait_time;
        u32 control;
+        if (!mmio_resource_enabled(pdev, 0))
+                return;
        base = ioremap_nocache(pci_resource_start(pdev, 0),
                                     pci_resource_len(pdev, 0));
        if (base == NULL) return;
@@ -201,6 +221,9 @@ static void __devinit quirk_usb_disable_ehci(struct pci_dev *pdev)
        u32 hcc_params, val, temp;
        u8 cap_length;
+        if (!mmio_resource_enabled(pdev, 0))
+                return;
        base = ioremap_nocache(pci_resource_start(pdev, 0),
                                pci_resource_len(pdev, 0));
        if (base == NULL) return;
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index 40169d9cf2b1..5607c0ae6835 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -54,6 +54,7 @@
 #include <linux/interrupt.h>
 #include <linux/usb.h>
 #include <linux/usb_sl811.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/drivers/usb/host/sl811_cs.c b/drivers/usb/host/sl811_cs.c
index 38aebe361ca1..e73faf831b24 100644
--- a/drivers/usb/host/sl811_cs.c
+++ b/drivers/usb/host/sl811_cs.c
@@ -19,6 +19,7 @@
 #include <linux/string.h>
 #include <linux/timer.h>
 #include <linux/ioport.h>
+#include <linux/platform_device.h>
 #include <pcmcia/cs_types.h>
 #include <pcmcia/cs.h>
diff --git a/drivers/video/acornfb.c b/drivers/video/acornfb.c
index f02965f39501..9b6a39348f81 100644
--- a/drivers/video/acornfb.c
+++ b/drivers/video/acornfb.c
@@ -26,7 +26,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/fb.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <asm/hardware.h>
diff --git a/drivers/video/arcfb.c b/drivers/video/arcfb.c
index d28457e0c063..126daff1c848 100644
--- a/drivers/video/arcfb.c
+++ b/drivers/video/arcfb.c
@@ -47,6 +47,7 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/arcfb.h>
+#include <linux/platform_device.h>
 #include <asm/uaccess.h>
diff --git a/drivers/video/backlight/corgi_bl.c b/drivers/video/backlight/corgi_bl.c
index 1991fdb32dfb..4867498f68e8 100644
--- a/drivers/video/backlight/corgi_bl.c
+++ b/drivers/video/backlight/corgi_bl.c
@@ -14,7 +14,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/spinlock.h>
 #include <linux/fb.h>
 #include <linux/backlight.h>
diff --git a/drivers/video/dnfb.c b/drivers/video/dnfb.c
index 1dbb82dca40b..1785686a7f11 100644
--- a/drivers/video/dnfb.c
+++ b/drivers/video/dnfb.c
@@ -6,6 +6,8 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/platform_device.h>
 #include <asm/setup.h>
 #include <asm/system.h>
 #include <asm/irq.h>
diff --git a/drivers/video/epson1355fb.c b/drivers/video/epson1355fb.c
index 116e808d71cd..7363d0b25fdf 100644
--- a/drivers/video/epson1355fb.c
+++ b/drivers/video/epson1355fb.c
@@ -54,6 +54,8 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/platform_device.h>
 #include <asm/types.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
diff --git a/drivers/video/gbefb.c b/drivers/video/gbefb.c
index 485604cd4462..316bfe994811 100644
--- a/drivers/video/gbefb.c
+++ b/drivers/video/gbefb.c
@@ -11,7 +11,7 @@
 #include <linux/config.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/errno.h>
 #include <linux/fb.h>
diff --git a/drivers/video/imxfb.c b/drivers/video/imxfb.c
index 0b9301facbd3..64d9bcc38da3 100644
--- a/drivers/video/imxfb.c
+++ b/drivers/video/imxfb.c
@@ -31,7 +31,7 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/cpufreq.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <asm/hardware.h>
diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c
index 6206da9dd5da..efd9333b05c2 100644
--- a/drivers/video/pxafb.c
+++ b/drivers/video/pxafb.c
@@ -36,7 +36,7 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/cpufreq.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <asm/hardware.h>
diff --git a/drivers/video/q40fb.c b/drivers/video/q40fb.c
index 162012bb9264..8416b2e2b501 100644
--- a/drivers/video/q40fb.c
+++ b/drivers/video/q40fb.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/platform_device.h>
 #include <asm/uaccess.h>
 #include <asm/setup.h>
diff --git a/drivers/video/s1d13xxxfb.c b/drivers/video/s1d13xxxfb.c
index cb2f7a1de947..f4437430dc5f 100644
--- a/drivers/video/s1d13xxxfb.c
+++ b/drivers/video/s1d13xxxfb.c
@@ -30,7 +30,7 @@
 #include <linux/config.h>
 #include <linux/module.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/types.h>
diff --git a/drivers/video/s3c2410fb.c b/drivers/video/s3c2410fb.c
index 3862d3cb1fb2..3cef90456a4b 100644
--- a/drivers/video/s3c2410fb.c
+++ b/drivers/video/s3c2410fb.c
@@ -86,6 +86,7 @@
 #include <linux/interrupt.h>
 #include <linux/workqueue.h>
 #include <linux/wait.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
diff --git a/drivers/video/sa1100fb.c b/drivers/video/sa1100fb.c
index 78e5f194b0df..3d35b28aaac7 100644
--- a/drivers/video/sa1100fb.c
+++ b/drivers/video/sa1100fb.c
@@ -173,7 +173,7 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/cpufreq.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <asm/hardware.h>
diff --git a/drivers/video/sgivwfb.c b/drivers/video/sgivwfb.c
index 8413907b379a..cf5106eab2d5 100644
--- a/drivers/video/sgivwfb.c
+++ b/drivers/video/sgivwfb.c
@@ -18,6 +18,8 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/platform_device.h>
 #include <asm/io.h>
 #include <asm/mtrr.h>
diff --git a/drivers/video/vesafb.c b/drivers/video/vesafb.c
index b1243da55fc5..3cc23106641d 100644
--- a/drivers/video/vesafb.c
+++ b/drivers/video/vesafb.c
@@ -19,6 +19,8 @@
 #include <linux/fb.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
+#include <linux/platform_device.h>
 #include <video/vga.h>
 #include <asm/io.h>
 #include <asm/mtrr.h>
diff --git a/drivers/video/vfb.c b/drivers/video/vfb.c
index b137a3fe0752..92d46555dd86 100644
--- a/drivers/video/vfb.c
+++ b/drivers/video/vfb.c
@@ -20,6 +20,8 @@
 #include <linux/vmalloc.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/platform_device.h>
 #include <asm/uaccess.h>
 #include <linux/fb.h>
 #include <linux/init.h>
diff --git a/drivers/video/w100fb.c b/drivers/video/w100fb.c
index 752bf88906a9..cf8cdb108fd9 100644
--- a/drivers/video/w100fb.c
+++ b/drivers/video/w100fb.c
@@ -25,7 +25,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <asm/io.h>
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index ffab4783ac64..c27f8d4098be 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -247,7 +247,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
        wait_queue_head_t *wqh;
        if (!atomic_read(&inode->i_count))
-                WARN_ON(!(inode->i_state & I_WILL_FREE));
+                WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
        else
                WARN_ON(inode->i_state & I_WILL_FREE);
diff --git a/fs/ntfs/ChangeLog b/fs/ntfs/ChangeLog
index de58579a1d0e..50a7749cfca1 100644
--- a/fs/ntfs/ChangeLog
+++ b/fs/ntfs/ChangeLog
@@ -1,18 +1,15 @@
 ToDo/Notes:
        - Find and fix bugs.
-        - In between ntfs_prepare/commit_write, need exclusion between
+        - The only places in the kernel where a file is resized are
-          simultaneous file extensions.  This is given to us by holding i_sem
+          ntfs_file_write*() and ntfs_truncate() for both of which i_sem is
-          on the inode.  The only places in the kernel when a file is resized
+          held.  Just have to be careful in read-/writepage and other helpers
-          are prepare/commit write and truncate for both of which i_sem is
+          not running under i_sem that we play nice...  Also need to be careful
-          held.  Just have to be careful in readpage/writepage and all other
+          with initialized_size extension in ntfs_file_write*() and writepage.
-          helpers not running under i_sem that we play nice...
+          UPDATE: The only things that need to be checked are the compressed
-          Also need to be careful with initialized_size extention in
+          write and the other attribute resize/write cases like index
-          ntfs_prepare_write. Basically, just be _very_ careful in this code...
+          attributes, etc.  For now none of these are implemented so are safe.
-          UPDATE: The only things that need to be checked are read/writepage
+        - Implement filling in of holes in aops.c::ntfs_writepage() and its
-          which do not hold i_sem.  Note writepage cannot change i_size but it
+          helpers.
-          needs to cope with a concurrent i_size change, just like readpage.
-          Also both need to cope with concurrent changes to the other sizes,
-          i.e. initialized/allocated/compressed size, as well.
        - Implement mft.c::sync_mft_mirror_umount().  We currently will just
          leave the volume dirty on umount if the final iput(vol->mft_ino)
          causes a write of any mirrored mft records due to the mft mirror
@@ -22,6 +19,68 @@ ToDo/Notes:
        - Enable the code for setting the NT4 compatibility flag when we start
          making NTFS 1.2 specific modifications.
+2.1.25 - (Almost) fully implement write(2) and truncate(2).
+        - Change ntfs_map_runlist_nolock(), ntfs_attr_find_vcn_nolock() and
+          {__,}ntfs_cluster_free() to also take an optional attribute search
+          context as argument.  This allows calling these functions with the
+          mft record mapped.  Update all callers.
+        - Fix potential deadlock in ntfs_mft_data_extend_allocation_nolock()
+          error handling by passing in the active search context when calling
+          ntfs_cluster_free().
+        - Change ntfs_cluster_alloc() to take an extra boolean parameter
+          specifying whether the cluster are being allocated to extend an
+          attribute or to fill a hole.
+        - Change ntfs_attr_make_non_resident() to call ntfs_cluster_alloc()
+          with @is_extension set to TRUE and remove the runlist terminator
+          fixup code as this is now done by ntfs_cluster_alloc().
+        - Change ntfs_attr_make_non_resident to take the attribute value size
+          as an extra parameter.  This is needed since we need to know the size
+          before we can map the mft record and our callers always know it.  The
+          reason we cannot simply read the size from the vfs inode i_size is
+          that this is not necessarily uptodate.  This happens when
+          ntfs_attr_make_non_resident() is called in the ->truncate call path.
+        - Fix ntfs_attr_make_non_resident() to update the vfs inode i_blocks
+          which is zero for a resident attribute but should no longer be zero
+          once the attribute is non-resident as it then has real clusters
+          allocated.
+        - Add fs/ntfs/attrib.[hc]::ntfs_attr_extend_allocation(), a function to
+          extend the allocation of an attributes.  Optionally, the data size,
+          but not the initialized size can be extended, too.
+        - Implement fs/ntfs/inode.[hc]::ntfs_truncate().  It only supports
+          uncompressed and unencrypted files and it never creates sparse files
+          at least for the moment (making a file sparse requires us to modify
+          its directory entries and we do not support directory operations at
+          the moment).  Also, support for highly fragmented files, i.e. ones
+          whose data attribute is split across multiple extents, is severly
+          limited.  When such a case is encountered, EOPNOTSUPP is returned.
+        - Enable ATTR_SIZE attribute changes in ntfs_setattr().  This completes
+          the initial implementation of file truncation.  Now both open(2)ing
+          a file with the O_TRUNC flag and the {,f}truncate(2) system calls
+          will resize a file appropriately.  The limitations are that only
+          uncompressed and unencrypted files are supported.  Also, there is
+          only very limited support for highly fragmented files (the ones whose
+          $DATA attribute is split into multiple attribute extents).
+        - In attrib.c::ntfs_attr_set() call balance_dirty_pages_ratelimited()
+          and cond_resched() in the main loop as we could be dirtying a lot of
+          pages and this ensures we play nice with the VM and the system as a
+          whole.
+        - Implement file operations ->write, ->aio_write, ->writev for regular
+          files.  This replaces the old use of generic_file_write(), et al and
+          the address space operations ->prepare_write and ->commit_write.
+          This means that both sparse and non-sparse (unencrypted and
+          uncompressed) files can now be extended using the normal write(2)
+          code path.  There are two limitations at present and these are that
+          we never create sparse files and that we only have limited support
+          for highly fragmented files, i.e. ones whose data attribute is split
+          across multiple extents.   When such a case is encountered,
+          EOPNOTSUPP is returned.
+        - $EA attributes can be both resident and non-resident.
+        - Use %z for size_t to fix compilation warnings.  (Andrew Morton)
+        - Fix compilation warnings with gcc-4.0.2 on SUSE 10.0.
+        - Document extended attribute ($EA) NEED_EA flag.  (Based on libntfs
+          patch by Yura Pakhuchiy.)
 2.1.24 - Lots of bug fixes and support more clean journal states.
        - Support journals ($LogFile) which have been modified by chkdsk.  This
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index 894b2b876d35..d0d45d1c853a 100644
--- a/fs/ntfs/Makefile
+++ b/fs/ntfs/Makefile
@@ -6,7 +6,7 @@ ntfs-objs := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
             index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
             unistr.o upcase.o
-EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.24\"
+EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.25\"
 ifeq ($(CONFIG_NTFS_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 5e80c07c6a4d..1c0a4315876a 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1391,8 +1391,7 @@ retry_writepage:
                if (NInoEncrypted(ni)) {
                        unlock_page(page);
                        BUG_ON(ni->type != AT_DATA);
-                        ntfs_debug("Denying write access to encrypted "
+                        ntfs_debug("Denying write access to encrypted file.");
-                                        "file.");
                        return -EACCES;
                }
                /* Compressed data streams are handled in compress.c. */
@@ -1508,8 +1507,8 @@ retry_writepage:
        /* Zero out of bounds area in the page cache page. */
        memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
        kunmap_atomic(kaddr, KM_USER0);
-        flush_dcache_mft_record_page(ctx->ntfs_ino);
        flush_dcache_page(page);
+        flush_dcache_mft_record_page(ctx->ntfs_ino);
        /* We are done with the page. */
        end_page_writeback(page);
        /* Finally, mark the mft record dirty, so it gets written back. */
@@ -1542,830 +1541,6 @@ err_out:
        return err;
 }
-/**
- * ntfs_prepare_nonresident_write -
- *
- */
-static int ntfs_prepare_nonresident_write(struct page *page,
-                unsigned from, unsigned to)
-{
-        VCN vcn;
-        LCN lcn;
-        s64 initialized_size;
-        loff_t i_size;
-        sector_t block, ablock, iblock;
-        struct inode *vi;
-        ntfs_inode *ni;
-        ntfs_volume *vol;
-        runlist_element *rl;
-        struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
-        unsigned long flags;
-        unsigned int vcn_ofs, block_start, block_end, blocksize;
-        int err;
-        BOOL is_retry;
-        unsigned char blocksize_bits;
-        vi = page->mapping->host;
-        ni = NTFS_I(vi);
-        vol = ni->vol;
-        ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
-                        "0x%lx, from = %u, to = %u.", ni->mft_no, ni->type,
-                        page->index, from, to);
-        BUG_ON(!NInoNonResident(ni));
-        blocksize_bits = vi->i_blkbits;
-        blocksize = 1 << blocksize_bits;
-        /*
-         * create_empty_buffers() will create uptodate/dirty buffers if the
-         * page is uptodate/dirty.
-         */
-        if (!page_has_buffers(page))
-                create_empty_buffers(page, blocksize, 0);
-        bh = head = page_buffers(page);
-        if (unlikely(!bh))
-                return -ENOMEM;
-        /* The first block in the page. */
-        block = (s64)page->index << (PAGE_CACHE_SHIFT - blocksize_bits);
-        read_lock_irqsave(&ni->size_lock, flags);
-        /*
-         * The first out of bounds block for the allocated size.  No need to
-         * round up as allocated_size is in multiples of cluster size and the
-         * minimum cluster size is 512 bytes, which is equal to the smallest
-         * blocksize.
-         */
-        ablock = ni->allocated_size >> blocksize_bits;
-        i_size = i_size_read(vi);
-        initialized_size = ni->initialized_size;
-        read_unlock_irqrestore(&ni->size_lock, flags);
-        /* The last (fully or partially) initialized block. */
-        iblock = initialized_size >> blocksize_bits;
-        /* Loop through all the buffers in the page. */
-        block_start = 0;
-        rl = NULL;
-        err = 0;
-        do {
-                block_end = block_start + blocksize;
-                /*
-                 * If buffer @bh is outside the write, just mark it uptodate
-                 * if the page is uptodate and continue with the next buffer.
-                 */
-                if (block_end <= from || block_start >= to) {
-                        if (PageUptodate(page)) {
-                                if (!buffer_uptodate(bh))
-                                        set_buffer_uptodate(bh);
-                        }
-                        continue;
-                }
-                /*
-                 * @bh is at least partially being written to.
-                 * Make sure it is not marked as new.
-                 */
-                //if (buffer_new(bh))
-                //      clear_buffer_new(bh);
-                if (block >= ablock) {
-                        // TODO: block is above allocated_size, need to
-                        // allocate it. Best done in one go to accommodate not
-                        // only block but all above blocks up to and including:
-                        // ((page->index << PAGE_CACHE_SHIFT) + to + blocksize
-                        // - 1) >> blobksize_bits. Obviously will need to round
-                        // up to next cluster boundary, too. This should be
-                        // done with a helper function, so it can be reused.
-                        ntfs_error(vol->sb, "Writing beyond allocated size "
-                                        "is not supported yet. Sorry.");
-                        err = -EOPNOTSUPP;
-                        goto err_out;
-                        // Need to update ablock.
-                        // Need to set_buffer_new() on all block bhs that are
-                        // newly allocated.
-                }
-                /*
-                 * Now we have enough allocated size to fulfill the whole
-                 * request, i.e. block < ablock is true.
-                 */
-                if (unlikely((block >= iblock) &&
-                                (initialized_size < i_size))) {
-                        /*
-                         * If this page is fully outside initialized size, zero
-                         * out all pages between the current initialized size
-                         * and the current page. Just use ntfs_readpage() to do
-                         * the zeroing transparently.
-                         */
-                        if (block > iblock) {
-                                // TODO:
-                                // For each page do:
-                                // - read_cache_page()
-                                // Again for each page do:
-                                // - wait_on_page_locked()
-                                // - Check (PageUptodate(page) &&
-                                //                      !PageError(page))
-                                // Update initialized size in the attribute and
-                                // in the inode.
-                                // Again, for each page do:
-                                //      __set_page_dirty_buffers();
-                                // page_cache_release()
-                                // We don't need to wait on the writes.
-                                // Update iblock.
-                        }
-                        /*
-                         * The current page straddles initialized size. Zero
-                         * all non-uptodate buffers and set them uptodate (and
-                         * dirty?). Note, there aren't any non-uptodate buffers
-                         * if the page is uptodate.
-                         * FIXME: For an uptodate page, the buffers may need to
-                         * be written out because they were not initialized on
-                         * disk before.
-                         */
-                        if (!PageUptodate(page)) {
-                                // TODO:
-                                // Zero any non-uptodate buffers up to i_size.
-                                // Set them uptodate and dirty.
-                        }
-                        // TODO:
-                        // Update initialized size in the attribute and in the
-                        // inode (up to i_size).
-                        // Update iblock.
-                        // FIXME: This is inefficient. Try to batch the two
-                        // size changes to happen in one go.
-                        ntfs_error(vol->sb, "Writing beyond initialized size "
-                                        "is not supported yet. Sorry.");
-                        err = -EOPNOTSUPP;
-                        goto err_out;
-                        // Do NOT set_buffer_new() BUT DO clear buffer range
-                        // outside write request range.
-                        // set_buffer_uptodate() on complete buffers as well as
-                        // set_buffer_dirty().
-                }
-                /* Need to map unmapped buffers. */
-                if (!buffer_mapped(bh)) {
-                        /* Unmapped buffer. Need to map it. */
-                        bh->b_bdev = vol->sb->s_bdev;
-                        /* Convert block into corresponding vcn and offset. */
-                        vcn = (VCN)block << blocksize_bits >>
-                                        vol->cluster_size_bits;
-                        vcn_ofs = ((VCN)block << blocksize_bits) &
-                                        vol->cluster_size_mask;
-                        is_retry = FALSE;
-                        if (!rl) {
-lock_retry_remap:
-                                down_read(&ni->runlist.lock);
-                                rl = ni->runlist.rl;
-                        }
-                        if (likely(rl != NULL)) {
-                                /* Seek to element containing target vcn. */
-                                while (rl->length && rl[1].vcn <= vcn)
-                                        rl++;
-                                lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-                        } else
-                                lcn = LCN_RL_NOT_MAPPED;
-                        if (unlikely(lcn < 0)) {
-                                /*
-                                 * We extended the attribute allocation above.
-                                 * If we hit an ENOENT here it means that the
-                                 * allocation was insufficient which is a bug.
-                                 */
-                                BUG_ON(lcn == LCN_ENOENT);
-                                /* It is a hole, need to instantiate it. */
-                                if (lcn == LCN_HOLE) {
-                                        // TODO: Instantiate the hole.
-                                        // clear_buffer_new(bh);
-                                        // unmap_underlying_metadata(bh->b_bdev,
-                                        //              bh->b_blocknr);
-                                        // For non-uptodate buffers, need to
-                                        // zero out the region outside the
-                                        // request in this bh or all bhs,
-                                        // depending on what we implemented
-                                        // above.
-                                        // Need to flush_dcache_page().
-                                        // Or could use set_buffer_new()
-                                        // instead?
-                                        ntfs_error(vol->sb, "Writing into "
-                                                        "sparse regions is "
-                                                        "not supported yet. "
-                                                        "Sorry.");
-                                        err = -EOPNOTSUPP;
-                                        if (!rl)
-                                                up_read(&ni->runlist.lock);
-                                        goto err_out;
-                                } else if (!is_retry &&
-                                                lcn == LCN_RL_NOT_MAPPED) {
-                                        is_retry = TRUE;
-                                        /*
-                                         * Attempt to map runlist, dropping
-                                         * lock for the duration.
-                                         */
-                                        up_read(&ni->runlist.lock);
-                                        err = ntfs_map_runlist(ni, vcn);
-                                        if (likely(!err))
-                                                goto lock_retry_remap;
-                                        rl = NULL;
-                                } else if (!rl)
-                                        up_read(&ni->runlist.lock);
-                                /*
-                                 * Failed to map the buffer, even after
-                                 * retrying.
-                                 */
-                                if (!err)
-                                        err = -EIO;
-                                bh->b_blocknr = -1;
-                                ntfs_error(vol->sb, "Failed to write to inode "
-                                                "0x%lx, attribute type 0x%x, "
-                                                "vcn 0x%llx, offset 0x%x "
-                                                "because its location on disk "
-                                                "could not be determined%s "
-                                                "(error code %i).",
-                                                ni->mft_no, ni->type,
-                                                (unsigned long long)vcn,
-                                                vcn_ofs, is_retry ? " even "
-                                                "after retrying" : "", err);
-                                goto err_out;
-                        }
-                        /* We now have a successful remap, i.e. lcn >= 0. */
-                        /* Setup buffer head to correct block. */
-                        bh->b_blocknr = ((lcn << vol->cluster_size_bits)
-                                        + vcn_ofs) >> blocksize_bits;
-                        set_buffer_mapped(bh);
-                        // FIXME: Something analogous to this is needed for
-                        // each newly allocated block, i.e. BH_New.
-                        // FIXME: Might need to take this out of the
-                        // if (!buffer_mapped(bh)) {}, depending on how we
-                        // implement things during the allocated_size and
-                        // initialized_size extension code above.
-                        if (buffer_new(bh)) {
-                                clear_buffer_new(bh);
-                                unmap_underlying_metadata(bh->b_bdev,
-                                                bh->b_blocknr);
-                                if (PageUptodate(page)) {
-                                        set_buffer_uptodate(bh);
-                                        continue;
-                                }
-                                /*
-                                 * Page is _not_ uptodate, zero surrounding
-                                 * region. NOTE: This is how we decide if to
-                                 * zero or not!
-                                 */
-                                if (block_end > to || block_start < from) {
-                                        void *kaddr;
-                                        kaddr = kmap_atomic(page, KM_USER0);
-                                        if (block_end > to)
-                                                memset(kaddr + to, 0,
-                                                                block_end - to);
-                                        if (block_start < from)
-                                                memset(kaddr + block_start, 0,
-                                                                from -
-                                                                block_start);
-                                        flush_dcache_page(page);
-                                        kunmap_atomic(kaddr, KM_USER0);
-                                }
-                                continue;
-                        }
-                }
-                /* @bh is mapped, set it uptodate if the page is uptodate. */
-                if (PageUptodate(page)) {
-                        if (!buffer_uptodate(bh))
-                                set_buffer_uptodate(bh);
-                        continue;
-                }
-                /*
-                 * The page is not uptodate. The buffer is mapped. If it is not
-                 * uptodate, and it is only partially being written to, we need
-                 * to read the buffer in before the write, i.e. right now.
-                 */
-                if (!buffer_uptodate(bh) &&
-                                (block_start < from || block_end > to)) {
-                        ll_rw_block(READ, 1, &bh);
-                        *wait_bh++ = bh;
-                }
-        } while (block++, block_start = block_end,
-                        (bh = bh->b_this_page) != head);
-        /* Release the lock if we took it. */
-        if (rl) {
-                up_read(&ni->runlist.lock);
-                rl = NULL;
-        }
-        /* If we issued read requests, let them complete. */
-        while (wait_bh > wait) {
-                wait_on_buffer(*--wait_bh);
-                if (!buffer_uptodate(*wait_bh))
-                        return -EIO;
-        }
-        ntfs_debug("Done.");
-        return 0;
-err_out:
-        /*
-         * Zero out any newly allocated blocks to avoid exposing stale data.
-         * If BH_New is set, we know that the block was newly allocated in the
-         * above loop.
-         * FIXME: What about initialized_size increments? Have we done all the
-         * required zeroing above? If not this error handling is broken, and
-         * in particular the if (block_end <= from) check is completely bogus.
-         */
-        bh = head;
-        block_start = 0;
-        is_retry = FALSE;
-        do {
-                block_end = block_start + blocksize;
-                if (block_end <= from)
-                        continue;
-                if (block_start >= to)
-                        break;
-                if (buffer_new(bh)) {
-                        void *kaddr;
-                        clear_buffer_new(bh);
-                        kaddr = kmap_atomic(page, KM_USER0);
-                        memset(kaddr + block_start, 0, bh->b_size);
-                        kunmap_atomic(kaddr, KM_USER0);
-                        set_buffer_uptodate(bh);
-                        mark_buffer_dirty(bh);
-                        is_retry = TRUE;
-                }
-        } while (block_start = block_end, (bh = bh->b_this_page) != head);
-        if (is_retry)
-                flush_dcache_page(page);
-        if (rl)
-                up_read(&ni->runlist.lock);
-        return err;
-}
-/**
- * ntfs_prepare_write - prepare a page for receiving data
- *
- * This is called from generic_file_write() with i_sem held on the inode
- * (@page->mapping->host).  The @page is locked but not kmap()ped.  The source
- * data has not yet been copied into the @page.
- *
- * Need to extend the attribute/fill in holes if necessary, create blocks and
- * make partially overwritten blocks uptodate,
- *
- * i_size is not to be modified yet.
- *
- * Return 0 on success or -errno on error.
- *
- * Should be using block_prepare_write() [support for sparse files] or
- * cont_prepare_write() [no support for sparse files].  Cannot do that due to
- * ntfs specifics but can look at them for implementation guidance.
- *
- * Note: In the range, @from is inclusive and @to is exclusive, i.e. @from is
- * the first byte in the page that will be written to and @to is the first byte
- * after the last byte that will be written to.
- */
-static int ntfs_prepare_write(struct file *file, struct page *page,
-                unsigned from, unsigned to)
-{
-        s64 new_size;
-        loff_t i_size;
-        struct inode *vi = page->mapping->host;
-        ntfs_inode *base_ni = NULL, *ni = NTFS_I(vi);
-        ntfs_volume *vol = ni->vol;
-        ntfs_attr_search_ctx *ctx = NULL;
-        MFT_RECORD *m = NULL;
-        ATTR_RECORD *a;
-        u8 *kaddr;
-        u32 attr_len;
-        int err;
-        ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
-                        "0x%lx, from = %u, to = %u.", vi->i_ino, ni->type,
-                        page->index, from, to);
-        BUG_ON(!PageLocked(page));
-        BUG_ON(from > PAGE_CACHE_SIZE);
-        BUG_ON(to > PAGE_CACHE_SIZE);
-        BUG_ON(from > to);
-        BUG_ON(NInoMstProtected(ni));
-        /*
-         * If a previous ntfs_truncate() failed, repeat it and abort if it
-         * fails again.
-         */
-        if (unlikely(NInoTruncateFailed(ni))) {
-                down_write(&vi->i_alloc_sem);
-                err = ntfs_truncate(vi);
-                up_write(&vi->i_alloc_sem);
-                if (err || NInoTruncateFailed(ni)) {
-                        if (!err)
-                                err = -EIO;
-                        goto err_out;
-                }
-        }
-        /* If the attribute is not resident, deal with it elsewhere. */
-        if (NInoNonResident(ni)) {
-                /*
-                 * Only unnamed $DATA attributes can be compressed, encrypted,
-                 * and/or sparse.
-                 */
-                if (ni->type == AT_DATA && !ni->name_len) {
-                        /* If file is encrypted, deny access, just like NT4. */
-                        if (NInoEncrypted(ni)) {
-                                ntfs_debug("Denying write access to encrypted "
-                                                "file.");
-                                return -EACCES;
-                        }
-                        /* Compressed data streams are handled in compress.c. */
-                        if (NInoCompressed(ni)) {
-                                // TODO: Implement and replace this check with
-                                // return ntfs_write_compressed_block(page);
-                                ntfs_error(vi->i_sb, "Writing to compressed "
-                                                "files is not supported yet. "
-                                                "Sorry.");
-                                return -EOPNOTSUPP;
-                        }
-                        // TODO: Implement and remove this check.
-                        if (NInoSparse(ni)) {
-                                ntfs_error(vi->i_sb, "Writing to sparse files "
-                                                "is not supported yet. Sorry.");
-                                return -EOPNOTSUPP;
-                        }
-                }
-                /* Normal data stream. */
-                return ntfs_prepare_nonresident_write(page, from, to);
-        }
-        /*
-         * Attribute is resident, implying it is not compressed, encrypted, or
-         * sparse.
-         */
-        BUG_ON(page_has_buffers(page));
-        new_size = ((s64)page->index << PAGE_CACHE_SHIFT) + to;
-        /* If we do not need to resize the attribute allocation we are done. */
-        if (new_size <= i_size_read(vi))
-                goto done;
-        /* Map, pin, and lock the (base) mft record. */
-        if (!NInoAttr(ni))
-                base_ni = ni;
-        else
-                base_ni = ni->ext.base_ntfs_ino;
-        m = map_mft_record(base_ni);
-        if (IS_ERR(m)) {
-                err = PTR_ERR(m);
-                m = NULL;
-                ctx = NULL;
-                goto err_out;
-        }
-        ctx = ntfs_attr_get_search_ctx(base_ni, m);
-        if (unlikely(!ctx)) {
-                err = -ENOMEM;
-                goto err_out;
-        }
-        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-                        CASE_SENSITIVE, 0, NULL, 0, ctx);
-        if (unlikely(err)) {
-                if (err == -ENOENT)
-                        err = -EIO;
-                goto err_out;
-        }
-        m = ctx->mrec;
-        a = ctx->attr;
-        /* The total length of the attribute value. */
-        attr_len = le32_to_cpu(a->data.resident.value_length);
-        /* Fix an eventual previous failure of ntfs_commit_write(). */
-        i_size = i_size_read(vi);
-        if (unlikely(attr_len > i_size)) {
-                attr_len = i_size;
-                a->data.resident.value_length = cpu_to_le32(attr_len);
-        }
-        /* If we do not need to resize the attribute allocation we are done. */
-        if (new_size <= attr_len)
-                goto done_unm;
-        /* Check if new size is allowed in $AttrDef. */
-        err = ntfs_attr_size_bounds_check(vol, ni->type, new_size);
-        if (unlikely(err)) {
-                if (err == -ERANGE) {
-                        ntfs_error(vol->sb, "Write would cause the inode "
-                                        "0x%lx to exceed the maximum size for "
-                                        "its attribute type (0x%x).  Aborting "
-                                        "write.", vi->i_ino,
-                                        le32_to_cpu(ni->type));
-                } else {
-                        ntfs_error(vol->sb, "Inode 0x%lx has unknown "
-                                        "attribute type 0x%x.  Aborting "
-                                        "write.", vi->i_ino,
-                                        le32_to_cpu(ni->type));
-                        err = -EIO;
-                }
-                goto err_out2;
-        }
-        /*
-         * Extend the attribute record to be able to store the new attribute
-         * size.
-         */
-        if (new_size >= vol->mft_record_size || ntfs_attr_record_resize(m, a,
-                        le16_to_cpu(a->data.resident.value_offset) +
-                        new_size)) {
-                /* Not enough space in the mft record. */
-                ntfs_error(vol->sb, "Not enough space in the mft record for "
-                                "the resized attribute value.  This is not "
-                                "supported yet.  Aborting write.");
-                err = -EOPNOTSUPP;
-                goto err_out2;
-        }
-        /*
-         * We have enough space in the mft record to fit the write.  This
-         * implies the attribute is smaller than the mft record and hence the
-         * attribute must be in a single page and hence page->index must be 0.
-         */
-        BUG_ON(page->index);
-        /*
-         * If the beginning of the write is past the old size, enlarge the
-         * attribute value up to the beginning of the write and fill it with
-         * zeroes.
-         */
-        if (from > attr_len) {
-                memset((u8*)a + le16_to_cpu(a->data.resident.value_offset) +
-                                attr_len, 0, from - attr_len);
-                a->data.resident.value_length = cpu_to_le32(from);
-                /* Zero the corresponding area in the page as well. */
-                if (PageUptodate(page)) {
-                        kaddr = kmap_atomic(page, KM_USER0);
-                        memset(kaddr + attr_len, 0, from - attr_len);
-                        kunmap_atomic(kaddr, KM_USER0);
-                        flush_dcache_page(page);
-                }
-        }
-        flush_dcache_mft_record_page(ctx->ntfs_ino);
-        mark_mft_record_dirty(ctx->ntfs_ino);
-done_unm:
-        ntfs_attr_put_search_ctx(ctx);
-        unmap_mft_record(base_ni);
-        /*
-         * Because resident attributes are handled by memcpy() to/from the
-         * corresponding MFT record, and because this form of i/o is byte
-         * aligned rather than block aligned, there is no need to bring the
-         * page uptodate here as in the non-resident case where we need to
-         * bring the buffers straddled by the write uptodate before
-         * generic_file_write() does the copying from userspace.
-         *
-         * We thus defer the uptodate bringing of the page region outside the
-         * region written to to ntfs_commit_write(), which makes the code
-         * simpler and saves one atomic kmap which is good.
-         */
-done:
-        ntfs_debug("Done.");
-        return 0;
-err_out:
-        if (err == -ENOMEM)
-                ntfs_warning(vi->i_sb, "Error allocating memory required to "
-                                "prepare the write.");
-        else {
-                ntfs_error(vi->i_sb, "Resident attribute prepare write failed "
-                                "with error %i.", err);
-                NVolSetErrors(vol);
-                make_bad_inode(vi);
-        }
-err_out2:
-        if (ctx)
-                ntfs_attr_put_search_ctx(ctx);
-        if (m)
-                unmap_mft_record(base_ni);
-        return err;
-}
-/**
- * ntfs_commit_nonresident_write -
- *
- */
-static int ntfs_commit_nonresident_write(struct page *page,
-                unsigned from, unsigned to)
-{
-        s64 pos = ((s64)page->index << PAGE_CACHE_SHIFT) + to;
-        struct inode *vi = page->mapping->host;
-        struct buffer_head *bh, *head;
-        unsigned int block_start, block_end, blocksize;
-        BOOL partial;
-        ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
-                        "0x%lx, from = %u, to = %u.", vi->i_ino,
-                        NTFS_I(vi)->type, page->index, from, to);
-        blocksize = 1 << vi->i_blkbits;
-        // FIXME: We need a whole slew of special cases in here for compressed
-        // files for example...
-        // For now, we know ntfs_prepare_write() would have failed so we can't
-        // get here in any of the cases which we have to special case, so we
-        // are just a ripped off, unrolled generic_commit_write().
-        bh = head = page_buffers(page);
-        block_start = 0;
-        partial = FALSE;
-        do {
-                block_end = block_start + blocksize;
-                if (block_end <= from || block_start >= to) {
-                        if (!buffer_uptodate(bh))
-                                partial = TRUE;
-                } else {
-                        set_buffer_uptodate(bh);
-                        mark_buffer_dirty(bh);
-                }
-        } while (block_start = block_end, (bh = bh->b_this_page) != head);
-        /*
-         * If this is a partial write which happened to make all buffers
-         * uptodate then we can optimize away a bogus ->readpage() for the next
-         * read().  Here we 'discover' whether the page went uptodate as a
-         * result of this (potentially partial) write.
-         */
-        if (!partial)
-                SetPageUptodate(page);
-        /*
-         * Not convinced about this at all.  See disparity comment above.  For
-         * now we know ntfs_prepare_write() would have failed in the write
-         * exceeds i_size case, so this will never trigger which is fine.
-         */
-        if (pos > i_size_read(vi)) {
-                ntfs_error(vi->i_sb, "Writing beyond the existing file size is "
-                                "not supported yet.  Sorry.");
-                return -EOPNOTSUPP;
-                // vi->i_size = pos;
-                // mark_inode_dirty(vi);
-        }
-        ntfs_debug("Done.");
-        return 0;
-}
-/**
- * ntfs_commit_write - commit the received data
- *
- * This is called from generic_file_write() with i_sem held on the inode
- * (@page->mapping->host).  The @page is locked but not kmap()ped.  The source
- * data has already been copied into the @page.  ntfs_prepare_write() has been
- * called before the data copied and it returned success so we can take the
- * results of various BUG checks and some error handling for granted.
- *
- * Need to mark modified blocks dirty so they get written out later when
- * ntfs_writepage() is invoked by the VM.
- *
- * Return 0 on success or -errno on error.
- *
- * Should be using generic_commit_write().  This marks buffers uptodate and
- * dirty, sets the page uptodate if all buffers in the page are uptodate, and
- * updates i_size if the end of io is beyond i_size.  In that case, it also
- * marks the inode dirty.
- *
- * Cannot use generic_commit_write() due to ntfs specialities but can look at
- * it for implementation guidance.
- *
- * If things have gone as outlined in ntfs_prepare_write(), then we do not
- * need to do any page content modifications here at all, except in the write
- * to resident attribute case, where we need to do the uptodate bringing here
- * which we combine with the copying into the mft record which means we save
- * one atomic kmap.
- */
-static int ntfs_commit_write(struct file *file, struct page *page,
-                unsigned from, unsigned to)
-{
-        struct inode *vi = page->mapping->host;
-        ntfs_inode *base_ni, *ni = NTFS_I(vi);
-        char *kaddr, *kattr;
-        ntfs_attr_search_ctx *ctx;
-        MFT_RECORD *m;
-        ATTR_RECORD *a;
-        u32 attr_len;
-        int err;
-        ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
-                        "0x%lx, from = %u, to = %u.", vi->i_ino, ni->type,
-                        page->index, from, to);
-        /* If the attribute is not resident, deal with it elsewhere. */
-        if (NInoNonResident(ni)) {
-                /* Only unnamed $DATA attributes can be compressed/encrypted. */
-                if (ni->type == AT_DATA && !ni->name_len) {
-                        /* Encrypted files need separate handling. */
-                        if (NInoEncrypted(ni)) {
-                                // We never get here at present!
-                                BUG();
-                        }
-                        /* Compressed data streams are handled in compress.c. */
-                        if (NInoCompressed(ni)) {
-                                // TODO: Implement this!
-                                // return ntfs_write_compressed_block(page);
-                                // We never get here at present!
-                                BUG();
-                        }
-                }
-                /* Normal data stream. */
-                return ntfs_commit_nonresident_write(page, from, to);
-        }
-        /*
-         * Attribute is resident, implying it is not compressed, encrypted, or
-         * sparse.
-         */
-        if (!NInoAttr(ni))
-                base_ni = ni;
-        else
-                base_ni = ni->ext.base_ntfs_ino;
-        /* Map, pin, and lock the mft record. */
-        m = map_mft_record(base_ni);
-        if (IS_ERR(m)) {
-                err = PTR_ERR(m);
-                m = NULL;
-                ctx = NULL;
-                goto err_out;
-        }
-        ctx = ntfs_attr_get_search_ctx(base_ni, m);
-        if (unlikely(!ctx)) {
-                err = -ENOMEM;
-                goto err_out;
-        }
-        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-                        CASE_SENSITIVE, 0, NULL, 0, ctx);
-        if (unlikely(err)) {
-                if (err == -ENOENT)
-                        err = -EIO;
-                goto err_out;
-        }
-        a = ctx->attr;
-        /* The total length of the attribute value. */
-        attr_len = le32_to_cpu(a->data.resident.value_length);
-        BUG_ON(from > attr_len);
-        kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
-        kaddr = kmap_atomic(page, KM_USER0);
-        /* Copy the received data from the page to the mft record. */
-        memcpy(kattr + from, kaddr + from, to - from);
-        /* Update the attribute length if necessary. */
-        if (to > attr_len) {
-                attr_len = to;
-                a->data.resident.value_length = cpu_to_le32(attr_len);
-        }
-        /*
-         * If the page is not uptodate, bring the out of bounds area(s)
-         * uptodate by copying data from the mft record to the page.
-         */
-        if (!PageUptodate(page)) {
-                if (from > 0)
-                        memcpy(kaddr, kattr, from);
-                if (to < attr_len)
-                        memcpy(kaddr + to, kattr + to, attr_len - to);
-                /* Zero the region outside the end of the attribute value. */
-                if (attr_len < PAGE_CACHE_SIZE)
-                        memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
-                /*
-                 * The probability of not having done any of the above is
-                 * extremely small, so we just flush unconditionally.
-                 */
-                flush_dcache_page(page);
-                SetPageUptodate(page);
-        }
-        kunmap_atomic(kaddr, KM_USER0);
-        /* Update i_size if necessary. */
-        if (i_size_read(vi) < attr_len) {
-                unsigned long flags;
-                write_lock_irqsave(&ni->size_lock, flags);
-                ni->allocated_size = ni->initialized_size = attr_len;
-                i_size_write(vi, attr_len);
-                write_unlock_irqrestore(&ni->size_lock, flags);
-        }
-        /* Mark the mft record dirty, so it gets written back. */
-        flush_dcache_mft_record_page(ctx->ntfs_ino);
-        mark_mft_record_dirty(ctx->ntfs_ino);
-        ntfs_attr_put_search_ctx(ctx);
-        unmap_mft_record(base_ni);
-        ntfs_debug("Done.");
-        return 0;
-err_out:
-        if (err == -ENOMEM) {
-                ntfs_warning(vi->i_sb, "Error allocating memory required to "
-                                "commit the write.");
-                if (PageUptodate(page)) {
-                        ntfs_warning(vi->i_sb, "Page is uptodate, setting "
-                                        "dirty so the write will be retried "
-                                        "later on by the VM.");
-                        /*
-                         * Put the page on mapping->dirty_pages, but leave its
-                         * buffers' dirty state as-is.
-                         */
-                        __set_page_dirty_nobuffers(page);
-                        err = 0;
-                } else
-                        ntfs_error(vi->i_sb, "Page is not uptodate.  Written "
-                                        "data has been lost.");
-        } else {
-                ntfs_error(vi->i_sb, "Resident attribute commit write failed "
-                                "with error %i.", err);
-                NVolSetErrors(ni->vol);
-                make_bad_inode(vi);
-        }
-        if (ctx)
-                ntfs_attr_put_search_ctx(ctx);
-        if (m)
-                unmap_mft_record(base_ni);
-        return err;
-}
 #endif  /* NTFS_RW */
 /**
@@ -2377,9 +1552,6 @@ struct address_space_operations ntfs_aops = {
                                                   disk request queue. */
 #ifdef NTFS_RW
        .writepage      = ntfs_writepage,       /* Write dirty page to disk. */
-        .prepare_write  = ntfs_prepare_write,   /* Prepare page and buffers
-                                                   ready to receive data. */
-        .commit_write   = ntfs_commit_write,    /* Commit received data. */
 #endif /* NTFS_RW */
 };
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index 3f9a4ff42ee5..eda056bac256 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -21,7 +21,9 @@
 */
 #include <linux/buffer_head.h>
+#include <linux/sched.h>
 #include <linux/swap.h>
+#include <linux/writeback.h>
 #include "attrib.h"
 #include "debug.h"
@@ -36,9 +38,27 @@
 * ntfs_map_runlist_nolock - map (a part of) a runlist of an ntfs inode
 * @ni:         ntfs inode for which to map (part of) a runlist
 * @vcn:        map runlist part containing this vcn
+ * @ctx:        active attribute search context if present or NULL if not
 *
 * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
 *
+ * If @ctx is specified, it is an active search context of @ni and its base mft
+ * record.  This is needed when ntfs_map_runlist_nolock() encounters unmapped
+ * runlist fragments and allows their mapping.  If you do not have the mft
+ * record mapped, you can specify @ctx as NULL and ntfs_map_runlist_nolock()
+ * will perform the necessary mapping and unmapping.
+ *
+ * Note, ntfs_map_runlist_nolock() saves the state of @ctx on entry and
+ * restores it before returning.  Thus, @ctx will be left pointing to the same
+ * attribute on return as on entry.  However, the actual pointers in @ctx may
+ * point to different memory locations on return, so you must remember to reset
+ * any cached pointers from the @ctx, i.e. after the call to
+ * ntfs_map_runlist_nolock(), you will probably want to do:
+ *      m = ctx->mrec;
+ *      a = ctx->attr;
+ * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
+ * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
+ *
 * Return 0 on success and -errno on error.  There is one special error code
 * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
 * of bounds of the runlist.
@@ -46,19 +66,32 @@
 * Note the runlist can be NULL after this function returns if @vcn is zero and
 * the attribute has zero allocated size, i.e. there simply is no runlist.
 *
- * Locking: - The runlist must be locked for writing.
+ * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *          - This function modifies the runlist.
+ *          returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx
+ *          is no longer valid, i.e. you need to either call
+ *          ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
+ *          In that case PTR_ERR(@ctx->mrec) will give you the error code for
+ *          why the mapping of the old inode failed.
+ *
+ * Locking: - The runlist described by @ni must be locked for writing on entry
+ *            and is locked on return.  Note the runlist will be modified.
+ *          - If @ctx is NULL, the base mft record of @ni must not be mapped on
+ *            entry and it will be left unmapped on return.
+ *          - If @ctx is not NULL, the base mft record must be mapped on entry
+ *            and it will be left mapped on return.
 */
-int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn)
+int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx)
 {
        VCN end_vcn;
+        unsigned long flags;
        ntfs_inode *base_ni;
        MFT_RECORD *m;
        ATTR_RECORD *a;
-        ntfs_attr_search_ctx *ctx;
        runlist_element *rl;
-        unsigned long flags;
+        struct page *put_this_page = NULL;
        int err = 0;
+        BOOL ctx_is_temporary, ctx_needs_reset;
+        ntfs_attr_search_ctx old_ctx = { NULL, };
        ntfs_debug("Mapping runlist part containing vcn 0x%llx.",
                        (unsigned long long)vcn);
@@ -66,20 +99,77 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn)
                base_ni = ni;
        else
                base_ni = ni->ext.base_ntfs_ino;
-        m = map_mft_record(base_ni);
+        if (!ctx) {
-        if (IS_ERR(m))
+                ctx_is_temporary = ctx_needs_reset = TRUE;
-                return PTR_ERR(m);
+                m = map_mft_record(base_ni);
-        ctx = ntfs_attr_get_search_ctx(base_ni, m);
+                if (IS_ERR(m))
-        if (unlikely(!ctx)) {
+                        return PTR_ERR(m);
-                err = -ENOMEM;
+                ctx = ntfs_attr_get_search_ctx(base_ni, m);
-                goto err_out;
+                if (unlikely(!ctx)) {
+                        err = -ENOMEM;
+                        goto err_out;
+                }
+        } else {
+                VCN allocated_size_vcn;
+                BUG_ON(IS_ERR(ctx->mrec));
+                a = ctx->attr;
+                BUG_ON(!a->non_resident);
+                ctx_is_temporary = FALSE;
+                end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
+                read_lock_irqsave(&ni->size_lock, flags);
+                allocated_size_vcn = ni->allocated_size >>
+                                ni->vol->cluster_size_bits;
+                read_unlock_irqrestore(&ni->size_lock, flags);
+                if (!a->data.non_resident.lowest_vcn && end_vcn <= 0)
+                        end_vcn = allocated_size_vcn - 1;
+                /*
+                 * If we already have the attribute extent containing @vcn in
+                 * @ctx, no need to look it up again.  We slightly cheat in
+                 * that if vcn exceeds the allocated size, we will refuse to
+                 * map the runlist below, so there is definitely no need to get
+                 * the right attribute extent.
+                 */
+                if (vcn >= allocated_size_vcn || (a->type == ni->type &&
+                                a->name_length == ni->name_len &&
+                                !memcmp((u8*)a + le16_to_cpu(a->name_offset),
+                                ni->name, ni->name_len) &&
+                                sle64_to_cpu(a->data.non_resident.lowest_vcn)
+                                <= vcn && end_vcn >= vcn))
+                        ctx_needs_reset = FALSE;
+                else {
+                        /* Save the old search context. */
+                        old_ctx = *ctx;
+                        /*
+                         * If the currently mapped (extent) inode is not the
+                         * base inode we will unmap it when we reinitialize the
+                         * search context which means we need to get a
+                         * reference to the page containing the mapped mft
+                         * record so we do not accidentally drop changes to the
+                         * mft record when it has not been marked dirty yet.
+                         */
+                        if (old_ctx.base_ntfs_ino && old_ctx.ntfs_ino !=
+                                        old_ctx.base_ntfs_ino) {
+                                put_this_page = old_ctx.ntfs_ino->page;
+                                page_cache_get(put_this_page);
+                        }
+                        /*
+                         * Reinitialize the search context so we can lookup the
+                         * needed attribute extent.
+                         */
+                        ntfs_attr_reinit_search_ctx(ctx);
+                        ctx_needs_reset = TRUE;
+                }
        }
-        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+        if (ctx_needs_reset) {
-                        CASE_SENSITIVE, vcn, NULL, 0, ctx);
+                err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-        if (unlikely(err)) {
+                                CASE_SENSITIVE, vcn, NULL, 0, ctx);
-                if (err == -ENOENT)
+                if (unlikely(err)) {
-                        err = -EIO;
+                        if (err == -ENOENT)
-                goto err_out;
+                                err = -EIO;
+                        goto err_out;
+                }
+                BUG_ON(!ctx->attr->non_resident);
        }
        a = ctx->attr;
        /*
@@ -89,11 +179,9 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn)
         * ntfs_mapping_pairs_decompress() fails.
         */
        end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn) + 1;
-        if (unlikely(!a->data.non_resident.lowest_vcn && end_vcn <= 1)) {
+        if (!a->data.non_resident.lowest_vcn && end_vcn == 1)
-                read_lock_irqsave(&ni->size_lock, flags);
+                end_vcn = sle64_to_cpu(a->data.non_resident.allocated_size) >>
-                end_vcn = ni->allocated_size >> ni->vol->cluster_size_bits;
+                                ni->vol->cluster_size_bits;
-                read_unlock_irqrestore(&ni->size_lock, flags);
-        }
        if (unlikely(vcn >= end_vcn)) {
                err = -ENOENT;
                goto err_out;
@@ -104,9 +192,93 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn)
        else
                ni->runlist.rl = rl;
 err_out:
-        if (likely(ctx))
+        if (ctx_is_temporary) {
-                ntfs_attr_put_search_ctx(ctx);
+                if (likely(ctx))
-        unmap_mft_record(base_ni);
+                        ntfs_attr_put_search_ctx(ctx);
+                unmap_mft_record(base_ni);
+        } else if (ctx_needs_reset) {
+                /*
+                 * If there is no attribute list, restoring the search context
+                 * is acomplished simply by copying the saved context back over
+                 * the caller supplied context.  If there is an attribute list,
+                 * things are more complicated as we need to deal with mapping
+                 * of mft records and resulting potential changes in pointers.
+                 */
+                if (NInoAttrList(base_ni)) {
+                        /*
+                         * If the currently mapped (extent) inode is not the
+                         * one we had before, we need to unmap it and map the
+                         * old one.
+                         */
+                        if (ctx->ntfs_ino != old_ctx.ntfs_ino) {
+                                /*
+                                 * If the currently mapped inode is not the
+                                 * base inode, unmap it.
+                                 */
+                                if (ctx->base_ntfs_ino && ctx->ntfs_ino !=
+                                                ctx->base_ntfs_ino) {
+                                        unmap_extent_mft_record(ctx->ntfs_ino);
+                                        ctx->mrec = ctx->base_mrec;
+                                        BUG_ON(!ctx->mrec);
+                                }
+                                /*
+                                 * If the old mapped inode is not the base
+                                 * inode, map it.
+                                 */
+                                if (old_ctx.base_ntfs_ino &&
+                                                old_ctx.ntfs_ino !=
+                                                old_ctx.base_ntfs_ino) {
+retry_map:
+                                        ctx->mrec = map_mft_record(
+                                                        old_ctx.ntfs_ino);
+                                        /*
+                                         * Something bad has happened.  If out
+                                         * of memory retry till it succeeds.
+                                         * Any other errors are fatal and we
+                                         * return the error code in ctx->mrec.
+                                         * Let the caller deal with it...  We
+                                         * just need to fudge things so the
+                                         * caller can reinit and/or put the
+                                         * search context safely.
+                                         */
+                                        if (IS_ERR(ctx->mrec)) {
+                                                if (PTR_ERR(ctx->mrec) ==
+                                                                -ENOMEM) {
+                                                        schedule();
+                                                        goto retry_map;
+                                                } else
+                                                        old_ctx.ntfs_ino =
+                                                                old_ctx.
+                                                                base_ntfs_ino;
+                                        }
+                                }
+                        }
+                        /* Update the changed pointers in the saved context. */
+                        if (ctx->mrec != old_ctx.mrec) {
+                                if (!IS_ERR(ctx->mrec))
+                                        old_ctx.attr = (ATTR_RECORD*)(
+                                                        (u8*)ctx->mrec +
+                                                        ((u8*)old_ctx.attr -
+                                                        (u8*)old_ctx.mrec));
+                                old_ctx.mrec = ctx->mrec;
+                        }
+                }
+                /* Restore the search context to the saved one. */
+                *ctx = old_ctx;
+                /*
+                 * We drop the reference on the page we took earlier.  In the
+                 * case that IS_ERR(ctx->mrec) is true this means we might lose
+                 * some changes to the mft record that had been made between
+                 * the last time it was marked dirty/written out and now.  This
+                 * at this stage is not a problem as the mapping error is fatal
+                 * enough that the mft record cannot be written out anyway and
+                 * the caller is very likely to shutdown the whole inode
+                 * immediately and mark the volume dirty for chkdsk to pick up
+                 * the pieces anyway.
+                 */
+                if (put_this_page)
+                        page_cache_release(put_this_page);
+        }
        return err;
 }
@@ -122,8 +294,8 @@ err_out:
 * of bounds of the runlist.
 *
 * Locking: - The runlist must be unlocked on entry and is unlocked on return.
- *          - This function takes the runlist lock for writing and modifies the
+ *          - This function takes the runlist lock for writing and may modify
- *            runlist.
+ *            the runlist.
 */
 int ntfs_map_runlist(ntfs_inode *ni, VCN vcn)
 {
@@ -133,7 +305,7 @@ int ntfs_map_runlist(ntfs_inode *ni, VCN vcn)
        /* Make sure someone else didn't do the work while we were sleeping. */
        if (likely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) <=
                        LCN_RL_NOT_MAPPED))
-                err = ntfs_map_runlist_nolock(ni, vcn);
+                err = ntfs_map_runlist_nolock(ni, vcn, NULL);
        up_write(&ni->runlist.lock);
        return err;
 }
@@ -212,7 +384,7 @@ retry_remap:
                                goto retry_remap;
                        }
                }
-                err = ntfs_map_runlist_nolock(ni, vcn);
+                err = ntfs_map_runlist_nolock(ni, vcn, NULL);
                if (!write_locked) {
                        up_write(&ni->runlist.lock);
                        down_read(&ni->runlist.lock);
@@ -236,9 +408,9 @@ retry_remap:
 /**
 * ntfs_attr_find_vcn_nolock - find a vcn in the runlist of an ntfs inode
- * @ni:                 ntfs inode describing the runlist to search
+ * @ni:         ntfs inode describing the runlist to search
- * @vcn:                vcn to find
+ * @vcn:        vcn to find
- * @write_locked:       true if the runlist is locked for writing
+ * @ctx:        active attribute search context if present or NULL if not
 *
 * Find the virtual cluster number @vcn in the runlist described by the ntfs
 * inode @ni and return the address of the runlist element containing the @vcn.
@@ -246,9 +418,22 @@ retry_remap:
 * If the @vcn is not mapped yet, the attempt is made to map the attribute
 * extent containing the @vcn and the vcn to lcn conversion is retried.
 *
- * If @write_locked is true the caller has locked the runlist for writing and
+ * If @ctx is specified, it is an active search context of @ni and its base mft
- * if false for reading.
+ * record.  This is needed when ntfs_attr_find_vcn_nolock() encounters unmapped
- *
+ * runlist fragments and allows their mapping.  If you do not have the mft
+ * record mapped, you can specify @ctx as NULL and ntfs_attr_find_vcn_nolock()
+ * will perform the necessary mapping and unmapping.
+ *
+ * Note, ntfs_attr_find_vcn_nolock() saves the state of @ctx on entry and
+ * restores it before returning.  Thus, @ctx will be left pointing to the same
+ * attribute on return as on entry.  However, the actual pointers in @ctx may
+ * point to different memory locations on return, so you must remember to reset
+ * any cached pointers from the @ctx, i.e. after the call to
+ * ntfs_attr_find_vcn_nolock(), you will probably want to do:
+ *      m = ctx->mrec;
+ *      a = ctx->attr;
+ * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
+ * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
 * Note you need to distinguish between the lcn of the returned runlist element
 * being >= 0 and LCN_HOLE.  In the later case you have to return zeroes on
 * read and allocate clusters on write.
@@ -263,22 +448,31 @@ retry_remap:
 *      -ENOMEM - Not enough memory to map runlist.
 *      -EIO    - Critical error (runlist/file is corrupt, i/o error, etc).
 *
- * Locking: - The runlist must be locked on entry and is left locked on return.
+ * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *          - If @write_locked is FALSE, i.e. the runlist is locked for reading,
+ *          returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx
- *            the lock may be dropped inside the function so you cannot rely on
+ *          is no longer valid, i.e. you need to either call
- *            the runlist still being the same when this function returns.
+ *          ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
+ *          In that case PTR_ERR(@ctx->mrec) will give you the error code for
+ *          why the mapping of the old inode failed.
+ *
+ * Locking: - The runlist described by @ni must be locked for writing on entry
+ *            and is locked on return.  Note the runlist may be modified when
+ *            needed runlist fragments need to be mapped.
+ *          - If @ctx is NULL, the base mft record of @ni must not be mapped on
+ *            entry and it will be left unmapped on return.
+ *          - If @ctx is not NULL, the base mft record must be mapped on entry
+ *            and it will be left mapped on return.
 */
 runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn,
-                const BOOL write_locked)
+                ntfs_attr_search_ctx *ctx)
 {
        unsigned long flags;
        runlist_element *rl;
        int err = 0;
        BOOL is_retry = FALSE;
-        ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
+        ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, with%s ctx.",
-                        ni->mft_no, (unsigned long long)vcn,
+                        ni->mft_no, (unsigned long long)vcn, ctx ? "" : "out");
-                        write_locked ? "write" : "read");
        BUG_ON(!ni);
        BUG_ON(!NInoNonResident(ni));
        BUG_ON(vcn < 0);
@@ -312,33 +506,22 @@ retry_remap:
        }
        if (!err && !is_retry) {
                /*
-                 * The @vcn is in an unmapped region, map the runlist and
+                 * If the search context is invalid we cannot map the unmapped
-                 * retry.
+                 * region.
                 */
-                if (!write_locked) {
+                if (IS_ERR(ctx->mrec))
-                        up_read(&ni->runlist.lock);
+                        err = PTR_ERR(ctx->mrec);
-                        down_write(&ni->runlist.lock);
+                else {
-                        if (unlikely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) !=
+                        /*
-                                        LCN_RL_NOT_MAPPED)) {
+                         * The @vcn is in an unmapped region, map the runlist
-                                up_write(&ni->runlist.lock);
+                         * and retry.
-                                down_read(&ni->runlist.lock);
+                         */
+                        err = ntfs_map_runlist_nolock(ni, vcn, ctx);
+                        if (likely(!err)) {
+                                is_retry = TRUE;
                                goto retry_remap;
                        }
                }
-                err = ntfs_map_runlist_nolock(ni, vcn);
-                if (!write_locked) {
-                        up_write(&ni->runlist.lock);
-                        down_read(&ni->runlist.lock);
-                }
-                if (likely(!err)) {
-                        is_retry = TRUE;
-                        goto retry_remap;
-                }
-                /*
-                 * -EINVAL coming from a failed mapping attempt is equivalent
-                 * to i/o error for us as it should not happen in our code
-                 * paths.
-                 */
                if (err == -EINVAL)
                        err = -EIO;
        } else if (!err)
@@ -1011,6 +1194,7 @@ int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
        ntfs_inode *base_ni;
        ntfs_debug("Entering.");
+        BUG_ON(IS_ERR(ctx->mrec));
        if (ctx->base_ntfs_ino)
                base_ni = ctx->base_ntfs_ino;
        else
@@ -1227,7 +1411,7 @@ int ntfs_attr_can_be_non_resident(const ntfs_volume *vol, const ATTR_TYPE type)
 */
 int ntfs_attr_can_be_resident(const ntfs_volume *vol, const ATTR_TYPE type)
 {
-        if (type == AT_INDEX_ALLOCATION || type == AT_EA)
+        if (type == AT_INDEX_ALLOCATION)
                return -EPERM;
        return 0;
 }
@@ -1319,10 +1503,17 @@ int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
 /**
 * ntfs_attr_make_non_resident - convert a resident to a non-resident attribute
 * @ni:         ntfs inode describing the attribute to convert
+ * @data_size:  size of the resident data to copy to the non-resident attribute
 *
 * Convert the resident ntfs attribute described by the ntfs inode @ni to a
 * non-resident one.
 *
+ * @data_size must be equal to the attribute value size.  This is needed since
+ * we need to know the size before we can map the mft record and our callers
+ * always know it.  The reason we cannot simply read the size from the vfs
+ * inode i_size is that this is not necessarily uptodate.  This happens when
+ * ntfs_attr_make_non_resident() is called in the ->truncate call path(s).
+ *
 * Return 0 on success and -errno on error.  The following error return codes
 * are defined:
 *      -EPERM  - The attribute is not allowed to be non-resident.
@@ -1343,7 +1534,7 @@ int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
 *
 * Locking: - The caller must hold i_sem on the inode.
 */
-int ntfs_attr_make_non_resident(ntfs_inode *ni)
+int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
 {
        s64 new_size;
        struct inode *vi = VFS_I(ni);
@@ -1381,11 +1572,9 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
         * The size needs to be aligned to a cluster boundary for allocation
         * purposes.
         */
-        new_size = (i_size_read(vi) + vol->cluster_size - 1) &
+        new_size = (data_size + vol->cluster_size - 1) &
                        ~(vol->cluster_size - 1);
        if (new_size > 0) {
-                runlist_element *rl2;
                /*
                 * Will need the page later and since the page lock nests
                 * outside all ntfs locks, we need to get the page now.
@@ -1396,7 +1585,7 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
                        return -ENOMEM;
                /* Start by allocating clusters to hold the attribute value. */
                rl = ntfs_cluster_alloc(vol, 0, new_size >>
-                                vol->cluster_size_bits, -1, DATA_ZONE);
+                                vol->cluster_size_bits, -1, DATA_ZONE, TRUE);
                if (IS_ERR(rl)) {
                        err = PTR_ERR(rl);
                        ntfs_debug("Failed to allocate cluster%s, error code "
@@ -1405,12 +1594,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
                                        err);
                        goto page_err_out;
                }
-                /* Change the runlist terminator to LCN_ENOENT. */
-                rl2 = rl;
-                while (rl2->length)
-                        rl2++;
-                BUG_ON(rl2->lcn != LCN_RL_NOT_MAPPED);
-                rl2->lcn = LCN_ENOENT;
        } else {
                rl = NULL;
                page = NULL;
@@ -1473,7 +1656,7 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
         * attribute value.
         */
        attr_size = le32_to_cpu(a->data.resident.value_length);
-        BUG_ON(attr_size != i_size_read(vi));
+        BUG_ON(attr_size != data_size);
        if (page && !PageUptodate(page)) {
                kaddr = kmap_atomic(page, KM_USER0);
                memcpy(kaddr, (u8*)a +
@@ -1538,7 +1721,9 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
                                ffs(ni->itype.compressed.block_size) - 1;
                ni->itype.compressed.block_clusters = 1U <<
                                a->data.non_resident.compression_unit;
-        }
+                vi->i_blocks = ni->itype.compressed.size >> 9;
+        } else
+                vi->i_blocks = ni->allocated_size >> 9;
        write_unlock_irqrestore(&ni->size_lock, flags);
        /*
         * This needs to be last since the address space operations ->readpage
@@ -1652,6 +1837,640 @@ page_err_out:
 }
 /**
+ * ntfs_attr_extend_allocation - extend the allocated space of an attribute
+ * @ni:                 ntfs inode of the attribute whose allocation to extend
+ * @new_alloc_size:     new size in bytes to which to extend the allocation to
+ * @new_data_size:      new size in bytes to which to extend the data to
+ * @data_start:         beginning of region which is required to be non-sparse
+ *
+ * Extend the allocated space of an attribute described by the ntfs inode @ni
+ * to @new_alloc_size bytes.  If @data_start is -1, the whole extension may be
+ * implemented as a hole in the file (as long as both the volume and the ntfs
+ * inode @ni have sparse support enabled).  If @data_start is >= 0, then the
+ * region between the old allocated size and @data_start - 1 may be made sparse
+ * but the regions between @data_start and @new_alloc_size must be backed by
+ * actual clusters.
+ *
+ * If @new_data_size is -1, it is ignored.  If it is >= 0, then the data size
+ * of the attribute is extended to @new_data_size.  Note that the i_size of the
+ * vfs inode is not updated.  Only the data size in the base attribute record
+ * is updated.  The caller has to update i_size separately if this is required.
+ * WARNING: It is a BUG() for @new_data_size to be smaller than the old data
+ * size as well as for @new_data_size to be greater than @new_alloc_size.
+ *
+ * For resident attributes this involves resizing the attribute record and if
+ * necessary moving it and/or other attributes into extent mft records and/or
+ * converting the attribute to a non-resident attribute which in turn involves
+ * extending the allocation of a non-resident attribute as described below.
+ *
+ * For non-resident attributes this involves allocating clusters in the data
+ * zone on the volume (except for regions that are being made sparse) and
+ * extending the run list to describe the allocated clusters as well as
+ * updating the mapping pairs array of the attribute.  This in turn involves
+ * resizing the attribute record and if necessary moving it and/or other
+ * attributes into extent mft records and/or splitting the attribute record
+ * into multiple extent attribute records.
+ *
+ * Also, the attribute list attribute is updated if present and in some of the
+ * above cases (the ones where extent mft records/attributes come into play),
+ * an attribute list attribute is created if not already present.
+ *
+ * Return the new allocated size on success and -errno on error.  In the case
+ * that an error is encountered but a partial extension at least up to
+ * @data_start (if present) is possible, the allocation is partially extended
+ * and this is returned.  This means the caller must check the returned size to
+ * determine if the extension was partial.  If @data_start is -1 then partial
+ * allocations are not performed.
+ *
+ * WARNING: Do not call ntfs_attr_extend_allocation() for $MFT/$DATA.
+ *
+ * Locking: This function takes the runlist lock of @ni for writing as well as
+ * locking the mft record of the base ntfs inode.  These locks are maintained
+ * throughout execution of the function.  These locks are required so that the
+ * attribute can be resized safely and so that it can for example be converted
+ * from resident to non-resident safely.
+ *
+ * TODO: At present attribute list attribute handling is not implemented.
+ *
+ * TODO: At present it is not safe to call this function for anything other
+ * than the $DATA attribute(s) of an uncompressed and unencrypted file.
+ */
+s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
+                const s64 new_data_size, const s64 data_start)
+{
+        VCN vcn;
+        s64 ll, allocated_size, start = data_start;
+        struct inode *vi = VFS_I(ni);
+        ntfs_volume *vol = ni->vol;
+        ntfs_inode *base_ni;
+        MFT_RECORD *m;
+        ATTR_RECORD *a;
+        ntfs_attr_search_ctx *ctx;
+        runlist_element *rl, *rl2;
+        unsigned long flags;
+        int err, mp_size;
+        u32 attr_len = 0; /* Silence stupid gcc warning. */
+        BOOL mp_rebuilt;
+#ifdef NTFS_DEBUG
+        read_lock_irqsave(&ni->size_lock, flags);
+        allocated_size = ni->allocated_size;
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
+                        "old_allocated_size 0x%llx, "
+                        "new_allocated_size 0x%llx, new_data_size 0x%llx, "
+                        "data_start 0x%llx.", vi->i_ino,
+                        (unsigned)le32_to_cpu(ni->type),
+                        (unsigned long long)allocated_size,
+                        (unsigned long long)new_alloc_size,
+                        (unsigned long long)new_data_size,
+                        (unsigned long long)start);
+#endif
+retry_extend:
+        /*
+         * For non-resident attributes, @start and @new_size need to be aligned
+         * to cluster boundaries for allocation purposes.
+         */
+        if (NInoNonResident(ni)) {
+                if (start > 0)
+                        start &= ~(s64)vol->cluster_size_mask;
+                new_alloc_size = (new_alloc_size + vol->cluster_size - 1) &
+                                ~(s64)vol->cluster_size_mask;
+        }
+        BUG_ON(new_data_size >= 0 && new_data_size > new_alloc_size);
+        /* Check if new size is allowed in $AttrDef. */
+        err = ntfs_attr_size_bounds_check(vol, ni->type, new_alloc_size);
+        if (unlikely(err)) {
+                /* Only emit errors when the write will fail completely. */
+                read_lock_irqsave(&ni->size_lock, flags);
+                allocated_size = ni->allocated_size;
+                read_unlock_irqrestore(&ni->size_lock, flags);
+                if (start < 0 || start >= allocated_size) {
+                        if (err == -ERANGE) {
+                                ntfs_error(vol->sb, "Cannot extend allocation "
+                                                "of inode 0x%lx, attribute "
+                                                "type 0x%x, because the new "
+                                                "allocation would exceed the "
+                                                "maximum allowed size for "
+                                                "this attribute type.",
+                                                vi->i_ino, (unsigned)
+                                                le32_to_cpu(ni->type));
+                        } else {
+                                ntfs_error(vol->sb, "Cannot extend allocation "
+                                                "of inode 0x%lx, attribute "
+                                                "type 0x%x, because this "
+                                                "attribute type is not "
+                                                "defined on the NTFS volume.  "
+                                                "Possible corruption!  You "
+                                                "should run chkdsk!",
+                                                vi->i_ino, (unsigned)
+                                                le32_to_cpu(ni->type));
+                        }
+                }
+                /* Translate error code to be POSIX conformant for write(2). */
+                if (err == -ERANGE)
+                        err = -EFBIG;
+                else
+                        err = -EIO;
+                return err;
+        }
+        if (!NInoAttr(ni))
+                base_ni = ni;
+        else
+                base_ni = ni->ext.base_ntfs_ino;
+        /*
+         * We will be modifying both the runlist (if non-resident) and the mft
+         * record so lock them both down.
+         */
+        down_write(&ni->runlist.lock);
+        m = map_mft_record(base_ni);
+        if (IS_ERR(m)) {
+                err = PTR_ERR(m);
+                m = NULL;
+                ctx = NULL;
+                goto err_out;
+        }
+        ctx = ntfs_attr_get_search_ctx(base_ni, m);
+        if (unlikely(!ctx)) {
+                err = -ENOMEM;
+                goto err_out;
+        }
+        read_lock_irqsave(&ni->size_lock, flags);
+        allocated_size = ni->allocated_size;
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        /*
+         * If non-resident, seek to the last extent.  If resident, there is
+         * only one extent, so seek to that.
+         */
+        vcn = NInoNonResident(ni) ? allocated_size >> vol->cluster_size_bits :
+                        0;
+        /*
+         * Abort if someone did the work whilst we waited for the locks.  If we
+         * just converted the attribute from resident to non-resident it is
+         * likely that exactly this has happened already.  We cannot quite
+         * abort if we need to update the data size.
+         */
+        if (unlikely(new_alloc_size <= allocated_size)) {
+                ntfs_debug("Allocated size already exceeds requested size.");
+                new_alloc_size = allocated_size;
+                if (new_data_size < 0)
+                        goto done;
+                /*
+                 * We want the first attribute extent so that we can update the
+                 * data size.
+                 */
+                vcn = 0;
+        }
+        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                        CASE_SENSITIVE, vcn, NULL, 0, ctx);
+        if (unlikely(err)) {
+                if (err == -ENOENT)
+                        err = -EIO;
+                goto err_out;
+        }
+        m = ctx->mrec;
+        a = ctx->attr;
+        /* Use goto to reduce indentation. */
+        if (a->non_resident)
+                goto do_non_resident_extend;
+        BUG_ON(NInoNonResident(ni));
+        /* The total length of the attribute value. */
+        attr_len = le32_to_cpu(a->data.resident.value_length);
+        /*
+         * Extend the attribute record to be able to store the new attribute
+         * size.  ntfs_attr_record_resize() will not do anything if the size is
+         * not changing.
+         */
+        if (new_alloc_size < vol->mft_record_size &&
+                        !ntfs_attr_record_resize(m, a,
+                        le16_to_cpu(a->data.resident.value_offset) +
+                        new_alloc_size)) {
+                /* The resize succeeded! */
+                write_lock_irqsave(&ni->size_lock, flags);
+                ni->allocated_size = le32_to_cpu(a->length) -
+                                le16_to_cpu(a->data.resident.value_offset);
+                write_unlock_irqrestore(&ni->size_lock, flags);
+                if (new_data_size >= 0) {
+                        BUG_ON(new_data_size < attr_len);
+                        a->data.resident.value_length =
+                                        cpu_to_le32((u32)new_data_size);
+                }
+                goto flush_done;
+        }
+        /*
+         * We have to drop all the locks so we can call
+         * ntfs_attr_make_non_resident().  This could be optimised by try-
+         * locking the first page cache page and only if that fails dropping
+         * the locks, locking the page, and redoing all the locking and
+         * lookups.  While this would be a huge optimisation, it is not worth
+         * it as this is definitely a slow code path.
+         */
+        ntfs_attr_put_search_ctx(ctx);
+        unmap_mft_record(base_ni);
+        up_write(&ni->runlist.lock);
+        /*
+         * Not enough space in the mft record, try to make the attribute
+         * non-resident and if successful restart the extension process.
+         */
+        err = ntfs_attr_make_non_resident(ni, attr_len);
+        if (likely(!err))
+                goto retry_extend;
+        /*
+         * Could not make non-resident.  If this is due to this not being
+         * permitted for this attribute type or there not being enough space,
+         * try to make other attributes non-resident.  Otherwise fail.
+         */
+        if (unlikely(err != -EPERM && err != -ENOSPC)) {
+                /* Only emit errors when the write will fail completely. */
+                read_lock_irqsave(&ni->size_lock, flags);
+                allocated_size = ni->allocated_size;
+                read_unlock_irqrestore(&ni->size_lock, flags);
+                if (start < 0 || start >= allocated_size)
+                        ntfs_error(vol->sb, "Cannot extend allocation of "
+                                        "inode 0x%lx, attribute type 0x%x, "
+                                        "because the conversion from resident "
+                                        "to non-resident attribute failed "
+                                        "with error code %i.", vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type), err);
+                if (err != -ENOMEM)
+                        err = -EIO;
+                goto conv_err_out;
+        }
+        /* TODO: Not implemented from here, abort. */
+        read_lock_irqsave(&ni->size_lock, flags);
+        allocated_size = ni->allocated_size;
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        if (start < 0 || start >= allocated_size) {
+                if (err == -ENOSPC)
+                        ntfs_error(vol->sb, "Not enough space in the mft "
+                                        "record/on disk for the non-resident "
+                                        "attribute value.  This case is not "
+                                        "implemented yet.");
+                else /* if (err == -EPERM) */
+                        ntfs_error(vol->sb, "This attribute type may not be "
+                                        "non-resident.  This case is not "
+                                        "implemented yet.");
+        }
+        err = -EOPNOTSUPP;
+        goto conv_err_out;
+#if 0
+        // TODO: Attempt to make other attributes non-resident.
+        if (!err)
+                goto do_resident_extend;
+        /*
+         * Both the attribute list attribute and the standard information
+         * attribute must remain in the base inode.  Thus, if this is one of
+         * these attributes, we have to try to move other attributes out into
+         * extent mft records instead.
+         */
+        if (ni->type == AT_ATTRIBUTE_LIST ||
+                        ni->type == AT_STANDARD_INFORMATION) {
+                // TODO: Attempt to move other attributes into extent mft
+                // records.
+                err = -EOPNOTSUPP;
+                if (!err)
+                        goto do_resident_extend;
+                goto err_out;
+        }
+        // TODO: Attempt to move this attribute to an extent mft record, but
+        // only if it is not already the only attribute in an mft record in
+        // which case there would be nothing to gain.
+        err = -EOPNOTSUPP;
+        if (!err)
+                goto do_resident_extend;
+        /* There is nothing we can do to make enough space. )-: */
+        goto err_out;
+#endif
+do_non_resident_extend:
+        BUG_ON(!NInoNonResident(ni));
+        if (new_alloc_size == allocated_size) {
+                BUG_ON(vcn);
+                goto alloc_done;
+        }
+        /*
+         * If the data starts after the end of the old allocation, this is a
+         * $DATA attribute and sparse attributes are enabled on the volume and
+         * for this inode, then create a sparse region between the old
+         * allocated size and the start of the data.  Otherwise simply proceed
+         * with filling the whole space between the old allocated size and the
+         * new allocated size with clusters.
+         */
+        if ((start >= 0 && start <= allocated_size) || ni->type != AT_DATA ||
+                        !NVolSparseEnabled(vol) || NInoSparseDisabled(ni))
+                goto skip_sparse;
+        // TODO: This is not implemented yet.  We just fill in with real
+        // clusters for now...
+        ntfs_debug("Inserting holes is not-implemented yet.  Falling back to "
+                        "allocating real clusters instead.");
+skip_sparse:
+        rl = ni->runlist.rl;
+        if (likely(rl)) {
+                /* Seek to the end of the runlist. */
+                while (rl->length)
+                        rl++;
+        }
+        /* If this attribute extent is not mapped, map it now. */
+        if (unlikely(!rl || rl->lcn == LCN_RL_NOT_MAPPED ||
+                        (rl->lcn == LCN_ENOENT && rl > ni->runlist.rl &&
+                        (rl-1)->lcn == LCN_RL_NOT_MAPPED))) {
+                if (!rl && !allocated_size)
+                        goto first_alloc;
+                rl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
+                if (IS_ERR(rl)) {
+                        err = PTR_ERR(rl);
+                        if (start < 0 || start >= allocated_size)
+                                ntfs_error(vol->sb, "Cannot extend allocation "
+                                                "of inode 0x%lx, attribute "
+                                                "type 0x%x, because the "
+                                                "mapping of a runlist "
+                                                "fragment failed with error "
+                                                "code %i.", vi->i_ino,
+                                                (unsigned)le32_to_cpu(ni->type),
+                                                err);
+                        if (err != -ENOMEM)
+                                err = -EIO;
+                        goto err_out;
+                }
+                ni->runlist.rl = rl;
+                /* Seek to the end of the runlist. */
+                while (rl->length)
+                        rl++;
+        }
+        /*
+         * We now know the runlist of the last extent is mapped and @rl is at
+         * the end of the runlist.  We want to begin allocating clusters
+         * starting at the last allocated cluster to reduce fragmentation.  If
+         * there are no valid LCNs in the attribute we let the cluster
+         * allocator choose the starting cluster.
+         */
+        /* If the last LCN is a hole or simillar seek back to last real LCN. */
+        while (rl->lcn < 0 && rl > ni->runlist.rl)
+                rl--;
+first_alloc:
+        // FIXME: Need to implement partial allocations so at least part of the
+        // write can be performed when start >= 0.  (Needed for POSIX write(2)
+        // conformance.)
+        rl2 = ntfs_cluster_alloc(vol, allocated_size >> vol->cluster_size_bits,
+                        (new_alloc_size - allocated_size) >>
+                        vol->cluster_size_bits, (rl && (rl->lcn >= 0)) ?
+                        rl->lcn + rl->length : -1, DATA_ZONE, TRUE);
+        if (IS_ERR(rl2)) {
+                err = PTR_ERR(rl2);
+                if (start < 0 || start >= allocated_size)
+                        ntfs_error(vol->sb, "Cannot extend allocation of "
+                                        "inode 0x%lx, attribute type 0x%x, "
+                                        "because the allocation of clusters "
+                                        "failed with error code %i.", vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type), err);
+                if (err != -ENOMEM && err != -ENOSPC)
+                        err = -EIO;
+                goto err_out;
+        }
+        rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
+        if (IS_ERR(rl)) {
+                err = PTR_ERR(rl);
+                if (start < 0 || start >= allocated_size)
+                        ntfs_error(vol->sb, "Cannot extend allocation of "
+                                        "inode 0x%lx, attribute type 0x%x, "
+                                        "because the runlist merge failed "
+                                        "with error code %i.", vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type), err);
+                if (err != -ENOMEM)
+                        err = -EIO;
+                if (ntfs_cluster_free_from_rl(vol, rl2)) {
+                        ntfs_error(vol->sb, "Failed to release allocated "
+                                        "cluster(s) in error code path.  Run "
+                                        "chkdsk to recover the lost "
+                                        "cluster(s).");
+                        NVolSetErrors(vol);
+                }
+                ntfs_free(rl2);
+                goto err_out;
+        }
+        ni->runlist.rl = rl;
+        ntfs_debug("Allocated 0x%llx clusters.", (long long)(new_alloc_size -
+                        allocated_size) >> vol->cluster_size_bits);
+        /* Find the runlist element with which the attribute extent starts. */
+        ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
+        rl2 = ntfs_rl_find_vcn_nolock(rl, ll);
+        BUG_ON(!rl2);
+        BUG_ON(!rl2->length);
+        BUG_ON(rl2->lcn < LCN_HOLE);
+        mp_rebuilt = FALSE;
+        /* Get the size for the new mapping pairs array for this extent. */
+        mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
+        if (unlikely(mp_size <= 0)) {
+                err = mp_size;
+                if (start < 0 || start >= allocated_size)
+                        ntfs_error(vol->sb, "Cannot extend allocation of "
+                                        "inode 0x%lx, attribute type 0x%x, "
+                                        "because determining the size for the "
+                                        "mapping pairs failed with error code "
+                                        "%i.", vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type), err);
+                err = -EIO;
+                goto undo_alloc;
+        }
+        /* Extend the attribute record to fit the bigger mapping pairs array. */
+        attr_len = le32_to_cpu(a->length);
+        err = ntfs_attr_record_resize(m, a, mp_size +
+                        le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
+        if (unlikely(err)) {
+                BUG_ON(err != -ENOSPC);
+                // TODO: Deal with this by moving this extent to a new mft
+                // record or by starting a new extent in a new mft record,
+                // possibly by extending this extent partially and filling it
+                // and creating a new extent for the remainder, or by making
+                // other attributes non-resident and/or by moving other
+                // attributes out of this mft record.
+                if (start < 0 || start >= allocated_size)
+                        ntfs_error(vol->sb, "Not enough space in the mft "
+                                        "record for the extended attribute "
+                                        "record.  This case is not "
+                                        "implemented yet.");
+                err = -EOPNOTSUPP;
+                goto undo_alloc;
+        }
+        mp_rebuilt = TRUE;
+        /* Generate the mapping pairs array directly into the attr record. */
+        err = ntfs_mapping_pairs_build(vol, (u8*)a +
+                        le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
+                        mp_size, rl2, ll, -1, NULL);
+        if (unlikely(err)) {
+                if (start < 0 || start >= allocated_size)
+                        ntfs_error(vol->sb, "Cannot extend allocation of "
+                                        "inode 0x%lx, attribute type 0x%x, "
+                                        "because building the mapping pairs "
+                                        "failed with error code %i.", vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type), err);
+                err = -EIO;
+                goto undo_alloc;
+        }
+        /* Update the highest_vcn. */
+        a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
+                        vol->cluster_size_bits) - 1);
+        /*
+         * We now have extended the allocated size of the attribute.  Reflect
+         * this in the ntfs_inode structure and the attribute record.
+         */
+        if (a->data.non_resident.lowest_vcn) {
+                /*
+                 * We are not in the first attribute extent, switch to it, but
+                 * first ensure the changes will make it to disk later.
+                 */
+                flush_dcache_mft_record_page(ctx->ntfs_ino);
+                mark_mft_record_dirty(ctx->ntfs_ino);
+                ntfs_attr_reinit_search_ctx(ctx);
+                err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                                CASE_SENSITIVE, 0, NULL, 0, ctx);
+                if (unlikely(err))
+                        goto restore_undo_alloc;
+                /* @m is not used any more so no need to set it. */
+                a = ctx->attr;
+        }
+        write_lock_irqsave(&ni->size_lock, flags);
+        ni->allocated_size = new_alloc_size;
+        a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
+        /*
+         * FIXME: This would fail if @ni is a directory, $MFT, or an index,
+         * since those can have sparse/compressed set.  For example can be
+         * set compressed even though it is not compressed itself and in that
+         * case the bit means that files are to be created compressed in the
+         * directory...  At present this is ok as this code is only called for
+         * regular files, and only for their $DATA attribute(s).
+         * FIXME: The calculation is wrong if we created a hole above.  For now
+         * it does not matter as we never create holes.
+         */
+        if (NInoSparse(ni) || NInoCompressed(ni)) {
+                ni->itype.compressed.size += new_alloc_size - allocated_size;
+                a->data.non_resident.compressed_size =
+                                cpu_to_sle64(ni->itype.compressed.size);
+                vi->i_blocks = ni->itype.compressed.size >> 9;
+        } else
+                vi->i_blocks = new_alloc_size >> 9;
+        write_unlock_irqrestore(&ni->size_lock, flags);
+alloc_done:
+        if (new_data_size >= 0) {
+                BUG_ON(new_data_size <
+                                sle64_to_cpu(a->data.non_resident.data_size));
+                a->data.non_resident.data_size = cpu_to_sle64(new_data_size);
+        }
+flush_done:
+        /* Ensure the changes make it to disk. */
+        flush_dcache_mft_record_page(ctx->ntfs_ino);
+        mark_mft_record_dirty(ctx->ntfs_ino);
+done:
+        ntfs_attr_put_search_ctx(ctx);
+        unmap_mft_record(base_ni);
+        up_write(&ni->runlist.lock);
+        ntfs_debug("Done, new_allocated_size 0x%llx.",
+                        (unsigned long long)new_alloc_size);
+        return new_alloc_size;
+restore_undo_alloc:
+        if (start < 0 || start >= allocated_size)
+                ntfs_error(vol->sb, "Cannot complete extension of allocation "
+                                "of inode 0x%lx, attribute type 0x%x, because "
+                                "lookup of first attribute extent failed with "
+                                "error code %i.", vi->i_ino,
+                                (unsigned)le32_to_cpu(ni->type), err);
+        if (err == -ENOENT)
+                err = -EIO;
+        ntfs_attr_reinit_search_ctx(ctx);
+        if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len, CASE_SENSITIVE,
+                        allocated_size >> vol->cluster_size_bits, NULL, 0,
+                        ctx)) {
+                ntfs_error(vol->sb, "Failed to find last attribute extent of "
+                                "attribute in error code path.  Run chkdsk to "
+                                "recover.");
+                write_lock_irqsave(&ni->size_lock, flags);
+                ni->allocated_size = new_alloc_size;
+                /*
+                 * FIXME: This would fail if @ni is a directory...  See above.
+                 * FIXME: The calculation is wrong if we created a hole above.
+                 * For now it does not matter as we never create holes.
+                 */
+                if (NInoSparse(ni) || NInoCompressed(ni)) {
+                        ni->itype.compressed.size += new_alloc_size -
+                                        allocated_size;
+                        vi->i_blocks = ni->itype.compressed.size >> 9;
+                } else
+                        vi->i_blocks = new_alloc_size >> 9;
+                write_unlock_irqrestore(&ni->size_lock, flags);
+                ntfs_attr_put_search_ctx(ctx);
+                unmap_mft_record(base_ni);
+                up_write(&ni->runlist.lock);
+                /*
+                 * The only thing that is now wrong is the allocated size of the
+                 * base attribute extent which chkdsk should be able to fix.
+                 */
+                NVolSetErrors(vol);
+                return err;
+        }
+        ctx->attr->data.non_resident.highest_vcn = cpu_to_sle64(
+                        (allocated_size >> vol->cluster_size_bits) - 1);
+undo_alloc:
+        ll = allocated_size >> vol->cluster_size_bits;
+        if (ntfs_cluster_free(ni, ll, -1, ctx) < 0) {
+                ntfs_error(vol->sb, "Failed to release allocated cluster(s) "
+                                "in error code path.  Run chkdsk to recover "
+                                "the lost cluster(s).");
+                NVolSetErrors(vol);
+        }
+        m = ctx->mrec;
+        a = ctx->attr;
+        /*
+         * If the runlist truncation fails and/or the search context is no
+         * longer valid, we cannot resize the attribute record or build the
+         * mapping pairs array thus we mark the inode bad so that no access to
+         * the freed clusters can happen.
+         */
+        if (ntfs_rl_truncate_nolock(vol, &ni->runlist, ll) || IS_ERR(m)) {
+                ntfs_error(vol->sb, "Failed to %s in error code path.  Run "
+                                "chkdsk to recover.", IS_ERR(m) ?
+                                "restore attribute search context" :
+                                "truncate attribute runlist");
+                make_bad_inode(vi);
+                make_bad_inode(VFS_I(base_ni));
+                NVolSetErrors(vol);
+        } else if (mp_rebuilt) {
+                if (ntfs_attr_record_resize(m, a, attr_len)) {
+                        ntfs_error(vol->sb, "Failed to restore attribute "
+                                        "record in error code path.  Run "
+                                        "chkdsk to recover.");
+                        make_bad_inode(vi);
+                        make_bad_inode(VFS_I(base_ni));
+                        NVolSetErrors(vol);
+                } else /* if (success) */ {
+                        if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
+                                        a->data.non_resident.
+                                        mapping_pairs_offset), attr_len -
+                                        le16_to_cpu(a->data.non_resident.
+                                        mapping_pairs_offset), rl2, ll, -1,
+                                        NULL)) {
+                                ntfs_error(vol->sb, "Failed to restore "
+                                                "mapping pairs array in error "
+                                                "code path.  Run chkdsk to "
+                                                "recover.");
+                                make_bad_inode(vi);
+                                make_bad_inode(VFS_I(base_ni));
+                                NVolSetErrors(vol);
+                        }
+                        flush_dcache_mft_record_page(ctx->ntfs_ino);
+                        mark_mft_record_dirty(ctx->ntfs_ino);
+                }
+        }
+err_out:
+        if (ctx)
+                ntfs_attr_put_search_ctx(ctx);
+        if (m)
+                unmap_mft_record(base_ni);
+        up_write(&ni->runlist.lock);
+conv_err_out:
+        ntfs_debug("Failed.  Returning error code %i.", err);
+        return err;
+}
+/**
 * ntfs_attr_set - fill (a part of) an attribute with a byte
 * @ni:         ntfs inode describing the attribute to fill
 * @ofs:        offset inside the attribute at which to start to fill
@@ -1773,6 +2592,8 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
                /* Finally unlock and release the page. */
                unlock_page(page);
                page_cache_release(page);
+                balance_dirty_pages_ratelimited(mapping);
+                cond_resched();
        }
        /* If there is a last partial page, need to do it the slow way. */
        if (end_ofs) {
diff --git a/fs/ntfs/attrib.h b/fs/ntfs/attrib.h
index 0618ed6fd7b3..9074886b44ba 100644
--- a/fs/ntfs/attrib.h
+++ b/fs/ntfs/attrib.h
@@ -60,14 +60,15 @@ typedef struct {
        ATTR_RECORD *base_attr;
 } ntfs_attr_search_ctx;
-extern int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn);
+extern int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn,
+                ntfs_attr_search_ctx *ctx);
 extern int ntfs_map_runlist(ntfs_inode *ni, VCN vcn);
 extern LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
                const BOOL write_locked);
 extern runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni,
-                const VCN vcn, const BOOL write_locked);
+                const VCN vcn, ntfs_attr_search_ctx *ctx);
 int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
                const u32 name_len, const IGNORE_CASE_BOOL ic,
@@ -102,7 +103,10 @@ extern int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size);
 extern int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
                const u32 new_size);
-extern int ntfs_attr_make_non_resident(ntfs_inode *ni);
+extern int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size);
+extern s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
+                const s64 new_data_size, const s64 data_start);
 extern int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt,
                const u8 val);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index be9fd1dd423d..727533891813 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -19,11 +19,24 @@
 * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
-#include <linux/pagemap.h>
 #include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+#include <linux/sched.h>
+#include <linux/swap.h>
+#include <linux/uio.h>
+#include <linux/writeback.h>
+#include <asm/page.h>
+#include <asm/uaccess.h>
+#include "attrib.h"
+#include "bitmap.h"
 #include "inode.h"
 #include "debug.h"
+#include "lcnalloc.h"
+#include "malloc.h"
+#include "mft.h"
 #include "ntfs.h"
 /**
@@ -56,6 +69,2185 @@ static int ntfs_file_open(struct inode *vi, struct file *filp)
 #ifdef NTFS_RW
 /**
+ * ntfs_attr_extend_initialized - extend the initialized size of an attribute
+ * @ni:                 ntfs inode of the attribute to extend
+ * @new_init_size:      requested new initialized size in bytes
+ * @cached_page:        store any allocated but unused page here
+ * @lru_pvec:           lru-buffering pagevec of the caller
+ *
+ * Extend the initialized size of an attribute described by the ntfs inode @ni
+ * to @new_init_size bytes.  This involves zeroing any non-sparse space between
+ * the old initialized size and @new_init_size both in the page cache and on
+ * disk (if relevant complete pages are already uptodate in the page cache then
+ * these are simply marked dirty).
+ *
+ * As a side-effect, the file size (vfs inode->i_size) may be incremented as,
+ * in the resident attribute case, it is tied to the initialized size and, in
+ * the non-resident attribute case, it may not fall below the initialized size.
+ *
+ * Note that if the attribute is resident, we do not need to touch the page
+ * cache at all.  This is because if the page cache page is not uptodate we
+ * bring it uptodate later, when doing the write to the mft record since we
+ * then already have the page mapped.  And if the page is uptodate, the
+ * non-initialized region will already have been zeroed when the page was
+ * brought uptodate and the region may in fact already have been overwritten
+ * with new data via mmap() based writes, so we cannot just zero it.  And since
+ * POSIX specifies that the behaviour of resizing a file whilst it is mmap()ped
+ * is unspecified, we choose not to do zeroing and thus we do not need to touch
+ * the page at all.  For a more detailed explanation see ntfs_truncate() in
+ * fs/ntfs/inode.c.
+ *
+ * @cached_page and @lru_pvec are just optimizations for dealing with multiple
+ * pages.
+ *
+ * Return 0 on success and -errno on error.  In the case that an error is
+ * encountered it is possible that the initialized size will already have been
+ * incremented some way towards @new_init_size but it is guaranteed that if
+ * this is the case, the necessary zeroing will also have happened and that all
+ * metadata is self-consistent.
+ *
+ * Locking: i_sem on the vfs inode corrseponsind to the ntfs inode @ni must be
+ *          held by the caller.
+ */
+static int ntfs_attr_extend_initialized(ntfs_inode *ni, const s64 new_init_size,
+                struct page **cached_page, struct pagevec *lru_pvec)
+{
+        s64 old_init_size;
+        loff_t old_i_size;
+        pgoff_t index, end_index;
+        unsigned long flags;
+        struct inode *vi = VFS_I(ni);
+        ntfs_inode *base_ni;
+        MFT_RECORD *m = NULL;
+        ATTR_RECORD *a;
+        ntfs_attr_search_ctx *ctx = NULL;
+        struct address_space *mapping;
+        struct page *page = NULL;
+        u8 *kattr;
+        int err;
+        u32 attr_len;
+        read_lock_irqsave(&ni->size_lock, flags);
+        old_init_size = ni->initialized_size;
+        old_i_size = i_size_read(vi);
+        BUG_ON(new_init_size > ni->allocated_size);
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
+                        "old_initialized_size 0x%llx, "
+                        "new_initialized_size 0x%llx, i_size 0x%llx.",
+                        vi->i_ino, (unsigned)le32_to_cpu(ni->type),
+                        (unsigned long long)old_init_size,
+                        (unsigned long long)new_init_size, old_i_size);
+        if (!NInoAttr(ni))
+                base_ni = ni;
+        else
+                base_ni = ni->ext.base_ntfs_ino;
+        /* Use goto to reduce indentation and we need the label below anyway. */
+        if (NInoNonResident(ni))
+                goto do_non_resident_extend;
+        BUG_ON(old_init_size != old_i_size);
+        m = map_mft_record(base_ni);
+        if (IS_ERR(m)) {
+                err = PTR_ERR(m);
+                m = NULL;
+                goto err_out;
+        }
+        ctx = ntfs_attr_get_search_ctx(base_ni, m);
+        if (unlikely(!ctx)) {
+                err = -ENOMEM;
+                goto err_out;
+        }
+        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                        CASE_SENSITIVE, 0, NULL, 0, ctx);
+        if (unlikely(err)) {
+                if (err == -ENOENT)
+                        err = -EIO;
+                goto err_out;
+        }
+        m = ctx->mrec;
+        a = ctx->attr;
+        BUG_ON(a->non_resident);
+        /* The total length of the attribute value. */
+        attr_len = le32_to_cpu(a->data.resident.value_length);
+        BUG_ON(old_i_size != (loff_t)attr_len);
+        /*
+         * Do the zeroing in the mft record and update the attribute size in
+         * the mft record.
+         */
+        kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
+        memset(kattr + attr_len, 0, new_init_size - attr_len);
+        a->data.resident.value_length = cpu_to_le32((u32)new_init_size);
+        /* Finally, update the sizes in the vfs and ntfs inodes. */
+        write_lock_irqsave(&ni->size_lock, flags);
+        i_size_write(vi, new_init_size);
+        ni->initialized_size = new_init_size;
+        write_unlock_irqrestore(&ni->size_lock, flags);
+        goto done;
+do_non_resident_extend:
+        /*
+         * If the new initialized size @new_init_size exceeds the current file
+         * size (vfs inode->i_size), we need to extend the file size to the
+         * new initialized size.
+         */
+        if (new_init_size > old_i_size) {
+                m = map_mft_record(base_ni);
+                if (IS_ERR(m)) {
+                        err = PTR_ERR(m);
+                        m = NULL;
+                        goto err_out;
+                }
+                ctx = ntfs_attr_get_search_ctx(base_ni, m);
+                if (unlikely(!ctx)) {
+                        err = -ENOMEM;
+                        goto err_out;
+                }
+                err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                                CASE_SENSITIVE, 0, NULL, 0, ctx);
+                if (unlikely(err)) {
+                        if (err == -ENOENT)
+                                err = -EIO;
+                        goto err_out;
+                }
+                m = ctx->mrec;
+                a = ctx->attr;
+                BUG_ON(!a->non_resident);
+                BUG_ON(old_i_size != (loff_t)
+                                sle64_to_cpu(a->data.non_resident.data_size));
+                a->data.non_resident.data_size = cpu_to_sle64(new_init_size);
+                flush_dcache_mft_record_page(ctx->ntfs_ino);
+                mark_mft_record_dirty(ctx->ntfs_ino);
+                /* Update the file size in the vfs inode. */
+                i_size_write(vi, new_init_size);
+                ntfs_attr_put_search_ctx(ctx);
+                ctx = NULL;
+                unmap_mft_record(base_ni);
+                m = NULL;
+        }
+        mapping = vi->i_mapping;
+        index = old_init_size >> PAGE_CACHE_SHIFT;
+        end_index = (new_init_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+        do {
+                /*
+                 * Read the page.  If the page is not present, this will zero
+                 * the uninitialized regions for us.
+                 */
+                page = read_cache_page(mapping, index,
+                                (filler_t*)mapping->a_ops->readpage, NULL);
+                if (IS_ERR(page)) {
+                        err = PTR_ERR(page);
+                        goto init_err_out;
+                }
+                wait_on_page_locked(page);
+                if (unlikely(!PageUptodate(page) || PageError(page))) {
+                        page_cache_release(page);
+                        err = -EIO;
+                        goto init_err_out;
+                }
+                /*
+                 * Update the initialized size in the ntfs inode.  This is
+                 * enough to make ntfs_writepage() work.
+                 */
+                write_lock_irqsave(&ni->size_lock, flags);
+                ni->initialized_size = (index + 1) << PAGE_CACHE_SHIFT;
+                if (ni->initialized_size > new_init_size)
+                        ni->initialized_size = new_init_size;
+                write_unlock_irqrestore(&ni->size_lock, flags);
+                /* Set the page dirty so it gets written out. */
+                set_page_dirty(page);
+                page_cache_release(page);
+                /*
+                 * Play nice with the vm and the rest of the system.  This is
+                 * very much needed as we can potentially be modifying the
+                 * initialised size from a very small value to a really huge
+                 * value, e.g.
+                 *      f = open(somefile, O_TRUNC);
+                 *      truncate(f, 10GiB);
+                 *      seek(f, 10GiB);
+                 *      write(f, 1);
+                 * And this would mean we would be marking dirty hundreds of
+                 * thousands of pages or as in the above example more than
+                 * two and a half million pages!
+                 *
+                 * TODO: For sparse pages could optimize this workload by using
+                 * the FsMisc / MiscFs page bit as a "PageIsSparse" bit.  This
+                 * would be set in readpage for sparse pages and here we would
+                 * not need to mark dirty any pages which have this bit set.
+                 * The only caveat is that we have to clear the bit everywhere
+                 * where we allocate any clusters that lie in the page or that
+                 * contain the page.
+                 *
+                 * TODO: An even greater optimization would be for us to only
+                 * call readpage() on pages which are not in sparse regions as
+                 * determined from the runlist.  This would greatly reduce the
+                 * number of pages we read and make dirty in the case of sparse
+                 * files.
+                 */
+                balance_dirty_pages_ratelimited(mapping);
+                cond_resched();
+        } while (++index < end_index);
+        read_lock_irqsave(&ni->size_lock, flags);
+        BUG_ON(ni->initialized_size != new_init_size);
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        /* Now bring in sync the initialized_size in the mft record. */
+        m = map_mft_record(base_ni);
+        if (IS_ERR(m)) {
+                err = PTR_ERR(m);
+                m = NULL;
+                goto init_err_out;
+        }
+        ctx = ntfs_attr_get_search_ctx(base_ni, m);
+        if (unlikely(!ctx)) {
+                err = -ENOMEM;
+                goto init_err_out;
+        }
+        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                        CASE_SENSITIVE, 0, NULL, 0, ctx);
+        if (unlikely(err)) {
+                if (err == -ENOENT)
+                        err = -EIO;
+                goto init_err_out;
+        }
+        m = ctx->mrec;
+        a = ctx->attr;
+        BUG_ON(!a->non_resident);
+        a->data.non_resident.initialized_size = cpu_to_sle64(new_init_size);
+done:
+        flush_dcache_mft_record_page(ctx->ntfs_ino);
+        mark_mft_record_dirty(ctx->ntfs_ino);
+        if (ctx)
+                ntfs_attr_put_search_ctx(ctx);
+        if (m)
+                unmap_mft_record(base_ni);
+        ntfs_debug("Done, initialized_size 0x%llx, i_size 0x%llx.",
+                        (unsigned long long)new_init_size, i_size_read(vi));
+        return 0;
+init_err_out:
+        write_lock_irqsave(&ni->size_lock, flags);
+        ni->initialized_size = old_init_size;
+        write_unlock_irqrestore(&ni->size_lock, flags);
+err_out:
+        if (ctx)
+                ntfs_attr_put_search_ctx(ctx);
+        if (m)
+                unmap_mft_record(base_ni);
+        ntfs_debug("Failed.  Returning error code %i.", err);
+        return err;
+}
+/**
+ * ntfs_fault_in_pages_readable -
+ *
+ * Fault a number of userspace pages into pagetables.
+ *
+ * Unlike include/linux/pagemap.h::fault_in_pages_readable(), this one copes
+ * with more than two userspace pages as well as handling the single page case
+ * elegantly.
+ *
+ * If you find this difficult to understand, then think of the while loop being
+ * the following code, except that we do without the integer variable ret:
+ *
+ *      do {
+ *              ret = __get_user(c, uaddr);
+ *              uaddr += PAGE_SIZE;
+ *      } while (!ret && uaddr < end);
+ *
+ * Note, the final __get_user() may well run out-of-bounds of the user buffer,
+ * but _not_ out-of-bounds of the page the user buffer belongs to, and since
+ * this is only a read and not a write, and since it is still in the same page,
+ * it should not matter and this makes the code much simpler.
+ */
+static inline void ntfs_fault_in_pages_readable(const char __user *uaddr,
+                int bytes)
+{
+        const char __user *end;
+        volatile char c;
+        /* Set @end to the first byte outside the last page we care about. */
+        end = (const char __user*)PAGE_ALIGN((ptrdiff_t __user)uaddr + bytes);
+        while (!__get_user(c, uaddr) && (uaddr += PAGE_SIZE, uaddr < end))
+                ;
+}
+/**
+ * ntfs_fault_in_pages_readable_iovec -
+ *
+ * Same as ntfs_fault_in_pages_readable() but operates on an array of iovecs.
+ */
+static inline void ntfs_fault_in_pages_readable_iovec(const struct iovec *iov,
+                size_t iov_ofs, int bytes)
+{
+        do {
+                const char __user *buf;
+                unsigned len;
+                buf = iov->iov_base + iov_ofs;
+                len = iov->iov_len - iov_ofs;
+                if (len > bytes)
+                        len = bytes;
+                ntfs_fault_in_pages_readable(buf, len);
+                bytes -= len;
+                iov++;
+                iov_ofs = 0;
+        } while (bytes);
+}
+/**
+ * __ntfs_grab_cache_pages - obtain a number of locked pages
+ * @mapping:    address space mapping from which to obtain page cache pages
+ * @index:      starting index in @mapping at which to begin obtaining pages
+ * @nr_pages:   number of page cache pages to obtain
+ * @pages:      array of pages in which to return the obtained page cache pages
+ * @cached_page: allocated but as yet unused page
+ * @lru_pvec:   lru-buffering pagevec of caller
+ *
+ * Obtain @nr_pages locked page cache pages from the mapping @maping and
+ * starting at index @index.
+ *
+ * If a page is newly created, increment its refcount and add it to the
+ * caller's lru-buffering pagevec @lru_pvec.
+ *
+ * This is the same as mm/filemap.c::__grab_cache_page(), except that @nr_pages
+ * are obtained at once instead of just one page and that 0 is returned on
+ * success and -errno on error.
+ *
+ * Note, the page locks are obtained in ascending page index order.
+ */
+static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
+                pgoff_t index, const unsigned nr_pages, struct page **pages,
+                struct page **cached_page, struct pagevec *lru_pvec)
+{
+        int err, nr;
+        BUG_ON(!nr_pages);
+        err = nr = 0;
+        do {
+                pages[nr] = find_lock_page(mapping, index);
+                if (!pages[nr]) {
+                        if (!*cached_page) {
+                                *cached_page = page_cache_alloc(mapping);
+                                if (unlikely(!*cached_page)) {
+                                        err = -ENOMEM;
+                                        goto err_out;
+                                }
+                        }
+                        err = add_to_page_cache(*cached_page, mapping, index,
+                                        GFP_KERNEL);
+                        if (unlikely(err)) {
+                                if (err == -EEXIST)
+                                        continue;
+                                goto err_out;
+                        }
+                        pages[nr] = *cached_page;
+                        page_cache_get(*cached_page);
+                        if (unlikely(!pagevec_add(lru_pvec, *cached_page)))
+                                __pagevec_lru_add(lru_pvec);
+                        *cached_page = NULL;
+                }
+                index++;
+                nr++;
+        } while (nr < nr_pages);
+out:
+        return err;
+err_out:
+        while (nr > 0) {
+                unlock_page(pages[--nr]);
+                page_cache_release(pages[nr]);
+        }
+        goto out;
+}
+static inline int ntfs_submit_bh_for_read(struct buffer_head *bh)
+{
+        lock_buffer(bh);
+        get_bh(bh);
+        bh->b_end_io = end_buffer_read_sync;
+        return submit_bh(READ, bh);
+}
+/**
+ * ntfs_prepare_pages_for_non_resident_write - prepare pages for receiving data
+ * @pages:      array of destination pages
+ * @nr_pages:   number of pages in @pages
+ * @pos:        byte position in file at which the write begins
+ * @bytes:      number of bytes to be written
+ *
+ * This is called for non-resident attributes from ntfs_file_buffered_write()
+ * with i_sem held on the inode (@pages[0]->mapping->host).  There are
+ * @nr_pages pages in @pages which are locked but not kmap()ped.  The source
+ * data has not yet been copied into the @pages.
+ * 
+ * Need to fill any holes with actual clusters, allocate buffers if necessary,
+ * ensure all the buffers are mapped, and bring uptodate any buffers that are
+ * only partially being written to.
+ *
+ * If @nr_pages is greater than one, we are guaranteed that the cluster size is
+ * greater than PAGE_CACHE_SIZE, that all pages in @pages are entirely inside
+ * the same cluster and that they are the entirety of that cluster, and that
+ * the cluster is sparse, i.e. we need to allocate a cluster to fill the hole.
+ *
+ * i_size is not to be modified yet.
+ *
+ * Return 0 on success or -errno on error.
+ */
+static int ntfs_prepare_pages_for_non_resident_write(struct page **pages,
+                unsigned nr_pages, s64 pos, size_t bytes)
+{
+        VCN vcn, highest_vcn = 0, cpos, cend, bh_cpos, bh_cend;
+        LCN lcn;
+        s64 bh_pos, vcn_len, end, initialized_size;
+        sector_t lcn_block;
+        struct page *page;
+        struct inode *vi;
+        ntfs_inode *ni, *base_ni = NULL;
+        ntfs_volume *vol;
+        runlist_element *rl, *rl2;
+        struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
+        ntfs_attr_search_ctx *ctx = NULL;
+        MFT_RECORD *m = NULL;
+        ATTR_RECORD *a = NULL;
+        unsigned long flags;
+        u32 attr_rec_len = 0;
+        unsigned blocksize, u;
+        int err, mp_size;
+        BOOL rl_write_locked, was_hole, is_retry;
+        unsigned char blocksize_bits;
+        struct {
+                u8 runlist_merged:1;
+                u8 mft_attr_mapped:1;
+                u8 mp_rebuilt:1;
+                u8 attr_switched:1;
+        } status = { 0, 0, 0, 0 };
+        BUG_ON(!nr_pages);
+        BUG_ON(!pages);
+        BUG_ON(!*pages);
+        vi = pages[0]->mapping->host;
+        ni = NTFS_I(vi);
+        vol = ni->vol;
+        ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, start page "
+                        "index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
+                        vi->i_ino, ni->type, pages[0]->index, nr_pages,
+                        (long long)pos, bytes);
+        blocksize_bits = vi->i_blkbits;
+        blocksize = 1 << blocksize_bits;
+        u = 0;
+        do {
+                struct page *page = pages[u];
+                /*
+                 * create_empty_buffers() will create uptodate/dirty buffers if
+                 * the page is uptodate/dirty.
+                 */
+                if (!page_has_buffers(page)) {
+                        create_empty_buffers(page, blocksize, 0);
+                        if (unlikely(!page_has_buffers(page)))
+                                return -ENOMEM;
+                }
+        } while (++u < nr_pages);
+        rl_write_locked = FALSE;
+        rl = NULL;
+        err = 0;
+        vcn = lcn = -1;
+        vcn_len = 0;
+        lcn_block = -1;
+        was_hole = FALSE;
+        cpos = pos >> vol->cluster_size_bits;
+        end = pos + bytes;
+        cend = (end + vol->cluster_size - 1) >> vol->cluster_size_bits;
+        /*
+         * Loop over each page and for each page over each buffer.  Use goto to
+         * reduce indentation.
+         */
+        u = 0;
+do_next_page:
+        page = pages[u];
+        bh_pos = (s64)page->index << PAGE_CACHE_SHIFT;
+        bh = head = page_buffers(page);
+        do {
+                VCN cdelta;
+                s64 bh_end;
+                unsigned bh_cofs;
+                /* Clear buffer_new on all buffers to reinitialise state. */
+                if (buffer_new(bh))
+                        clear_buffer_new(bh);
+                bh_end = bh_pos + blocksize;
+                bh_cpos = bh_pos >> vol->cluster_size_bits;
+                bh_cofs = bh_pos & vol->cluster_size_mask;
+                if (buffer_mapped(bh)) {
+                        /*
+                         * The buffer is already mapped.  If it is uptodate,
+                         * ignore it.
+                         */
+                        if (buffer_uptodate(bh))
+                                continue;
+                        /*
+                         * The buffer is not uptodate.  If the page is uptodate
+                         * set the buffer uptodate and otherwise ignore it.
+                         */
+                        if (PageUptodate(page)) {
+                                set_buffer_uptodate(bh);
+                                continue;
+                        }
+                        /*
+                         * Neither the page nor the buffer are uptodate.  If
+                         * the buffer is only partially being written to, we
+                         * need to read it in before the write, i.e. now.
+                         */
+                        if ((bh_pos < pos && bh_end > pos) ||
+                                        (bh_pos < end && bh_end > end)) {
+                                /*
+                                 * If the buffer is fully or partially within
+                                 * the initialized size, do an actual read.
+                                 * Otherwise, simply zero the buffer.
+                                 */
+                                read_lock_irqsave(&ni->size_lock, flags);
+                                initialized_size = ni->initialized_size;
+                                read_unlock_irqrestore(&ni->size_lock, flags);
+                                if (bh_pos < initialized_size) {
+                                        ntfs_submit_bh_for_read(bh);
+                                        *wait_bh++ = bh;
+                                } else {
+                                        u8 *kaddr = kmap_atomic(page, KM_USER0);
+                                        memset(kaddr + bh_offset(bh), 0,
+                                                        blocksize);
+                                        kunmap_atomic(kaddr, KM_USER0);
+                                        flush_dcache_page(page);
+                                        set_buffer_uptodate(bh);
+                                }
+                        }
+                        continue;
+                }
+                /* Unmapped buffer.  Need to map it. */
+                bh->b_bdev = vol->sb->s_bdev;
+                /*
+                 * If the current buffer is in the same clusters as the map
+                 * cache, there is no need to check the runlist again.  The
+                 * map cache is made up of @vcn, which is the first cached file
+                 * cluster, @vcn_len which is the number of cached file
+                 * clusters, @lcn is the device cluster corresponding to @vcn,
+                 * and @lcn_block is the block number corresponding to @lcn.
+                 */
+                cdelta = bh_cpos - vcn;
+                if (likely(!cdelta || (cdelta > 0 && cdelta < vcn_len))) {
+map_buffer_cached:
+                        BUG_ON(lcn < 0);
+                        bh->b_blocknr = lcn_block +
+                                        (cdelta << (vol->cluster_size_bits -
+                                        blocksize_bits)) +
+                                        (bh_cofs >> blocksize_bits);
+                        set_buffer_mapped(bh);
+                        /*
+                         * If the page is uptodate so is the buffer.  If the
+                         * buffer is fully outside the write, we ignore it if
+                         * it was already allocated and we mark it dirty so it
+                         * gets written out if we allocated it.  On the other
+                         * hand, if we allocated the buffer but we are not
+                         * marking it dirty we set buffer_new so we can do
+                         * error recovery.
+                         */
+                        if (PageUptodate(page)) {
+                                if (!buffer_uptodate(bh))
+                                        set_buffer_uptodate(bh);
+                                if (unlikely(was_hole)) {
+                                        /* We allocated the buffer. */
+                                        unmap_underlying_metadata(bh->b_bdev,
+                                                        bh->b_blocknr);
+                                        if (bh_end <= pos || bh_pos >= end)
+                                                mark_buffer_dirty(bh);
+                                        else
+                                                set_buffer_new(bh);
+                                }
+                                continue;
+                        }
+                        /* Page is _not_ uptodate. */
+                        if (likely(!was_hole)) {
+                                /*
+                                 * Buffer was already allocated.  If it is not
+                                 * uptodate and is only partially being written
+                                 * to, we need to read it in before the write,
+                                 * i.e. now.
+                                 */
+                                if (!buffer_uptodate(bh) && bh_pos < end &&
+                                                bh_end > pos &&
+                                                (bh_pos < pos ||
+                                                bh_end > end)) {
+                                        /*
+                                         * If the buffer is fully or partially
+                                         * within the initialized size, do an
+                                         * actual read.  Otherwise, simply zero
+                                         * the buffer.
+                                         */
+                                        read_lock_irqsave(&ni->size_lock,
+                                                        flags);
+                                        initialized_size = ni->initialized_size;
+                                        read_unlock_irqrestore(&ni->size_lock,
+                                                        flags);
+                                        if (bh_pos < initialized_size) {
+                                                ntfs_submit_bh_for_read(bh);
+                                                *wait_bh++ = bh;
+                                        } else {
+                                                u8 *kaddr = kmap_atomic(page,
+                                                                KM_USER0);
+                                                memset(kaddr + bh_offset(bh),
+                                                                0, blocksize);
+                                                kunmap_atomic(kaddr, KM_USER0);
+                                                flush_dcache_page(page);
+                                                set_buffer_uptodate(bh);
+                                        }
+                                }
+                                continue;
+                        }
+                        /* We allocated the buffer. */
+                        unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
+                        /*
+                         * If the buffer is fully outside the write, zero it,
+                         * set it uptodate, and mark it dirty so it gets
+                         * written out.  If it is partially being written to,
+                         * zero region surrounding the write but leave it to
+                         * commit write to do anything else.  Finally, if the
+                         * buffer is fully being overwritten, do nothing.
+                         */
+                        if (bh_end <= pos || bh_pos >= end) {
+                                if (!buffer_uptodate(bh)) {
+                                        u8 *kaddr = kmap_atomic(page, KM_USER0);
+                                        memset(kaddr + bh_offset(bh), 0,
+                                                        blocksize);
+                                        kunmap_atomic(kaddr, KM_USER0);
+                                        flush_dcache_page(page);
+                                        set_buffer_uptodate(bh);
+                                }
+                                mark_buffer_dirty(bh);
+                                continue;
+                        }
+                        set_buffer_new(bh);
+                        if (!buffer_uptodate(bh) &&
+                                        (bh_pos < pos || bh_end > end)) {
+                                u8 *kaddr;
+                                unsigned pofs;
+                                        
+                                kaddr = kmap_atomic(page, KM_USER0);
+                                if (bh_pos < pos) {
+                                        pofs = bh_pos & ~PAGE_CACHE_MASK;
+                                        memset(kaddr + pofs, 0, pos - bh_pos);
+                                }
+                                if (bh_end > end) {
+                                        pofs = end & ~PAGE_CACHE_MASK;
+                                        memset(kaddr + pofs, 0, bh_end - end);
+                                }
+                                kunmap_atomic(kaddr, KM_USER0);
+                                flush_dcache_page(page);
+                        }
+                        continue;
+                }
+                /*
+                 * Slow path: this is the first buffer in the cluster.  If it
+                 * is outside allocated size and is not uptodate, zero it and
+                 * set it uptodate.
+                 */
+                read_lock_irqsave(&ni->size_lock, flags);
+                initialized_size = ni->allocated_size;
+                read_unlock_irqrestore(&ni->size_lock, flags);
+                if (bh_pos > initialized_size) {
+                        if (PageUptodate(page)) {
+                                if (!buffer_uptodate(bh))
+                                        set_buffer_uptodate(bh);
+                        } else if (!buffer_uptodate(bh)) {
+                                u8 *kaddr = kmap_atomic(page, KM_USER0);
+                                memset(kaddr + bh_offset(bh), 0, blocksize);
+                                kunmap_atomic(kaddr, KM_USER0);
+                                flush_dcache_page(page);
+                                set_buffer_uptodate(bh);
+                        }
+                        continue;
+                }
+                is_retry = FALSE;
+                if (!rl) {
+                        down_read(&ni->runlist.lock);
+retry_remap:
+                        rl = ni->runlist.rl;
+                }
+                if (likely(rl != NULL)) {
+                        /* Seek to element containing target cluster. */
+                        while (rl->length && rl[1].vcn <= bh_cpos)
+                                rl++;
+                        lcn = ntfs_rl_vcn_to_lcn(rl, bh_cpos);
+                        if (likely(lcn >= 0)) {
+                                /*
+                                 * Successful remap, setup the map cache and
+                                 * use that to deal with the buffer.
+                                 */
+                                was_hole = FALSE;
+                                vcn = bh_cpos;
+                                vcn_len = rl[1].vcn - vcn;
+                                lcn_block = lcn << (vol->cluster_size_bits -
+                                                blocksize_bits);
+                                cdelta = 0;
+                                /*
+                                 * If the number of remaining clusters touched
+                                 * by the write is smaller or equal to the
+                                 * number of cached clusters, unlock the
+                                 * runlist as the map cache will be used from
+                                 * now on.
+                                 */
+                                if (likely(vcn + vcn_len >= cend)) {
+                                        if (rl_write_locked) {
+                                                up_write(&ni->runlist.lock);
+                                                rl_write_locked = FALSE;
+                                        } else
+                                                up_read(&ni->runlist.lock);
+                                        rl = NULL;
+                                }
+                                goto map_buffer_cached;
+                        }
+                } else
+                        lcn = LCN_RL_NOT_MAPPED;
+                /*
+                 * If it is not a hole and not out of bounds, the runlist is
+                 * probably unmapped so try to map it now.
+                 */
+                if (unlikely(lcn != LCN_HOLE && lcn != LCN_ENOENT)) {
+                        if (likely(!is_retry && lcn == LCN_RL_NOT_MAPPED)) {
+                                /* Attempt to map runlist. */
+                                if (!rl_write_locked) {
+                                        /*
+                                         * We need the runlist locked for
+                                         * writing, so if it is locked for
+                                         * reading relock it now and retry in
+                                         * case it changed whilst we dropped
+                                         * the lock.
+                                         */
+                                        up_read(&ni->runlist.lock);
+                                        down_write(&ni->runlist.lock);
+                                        rl_write_locked = TRUE;
+                                        goto retry_remap;
+                                }
+                                err = ntfs_map_runlist_nolock(ni, bh_cpos,
+                                                NULL);
+                                if (likely(!err)) {
+                                        is_retry = TRUE;
+                                        goto retry_remap;
+                                }
+                                /*
+                                 * If @vcn is out of bounds, pretend @lcn is
+                                 * LCN_ENOENT.  As long as the buffer is out
+                                 * of bounds this will work fine.
+                                 */
+                                if (err == -ENOENT) {
+                                        lcn = LCN_ENOENT;
+                                        err = 0;
+                                        goto rl_not_mapped_enoent;
+                                }
+                        } else
+                                err = -EIO;
+                        /* Failed to map the buffer, even after retrying. */
+                        bh->b_blocknr = -1;
+                        ntfs_error(vol->sb, "Failed to write to inode 0x%lx, "
+                                        "attribute type 0x%x, vcn 0x%llx, "
+                                        "vcn offset 0x%x, because its "
+                                        "location on disk could not be "
+                                        "determined%s (error code %i).",
+                                        ni->mft_no, ni->type,
+                                        (unsigned long long)bh_cpos,
+                                        (unsigned)bh_pos &
+                                        vol->cluster_size_mask,
+                                        is_retry ? " even after retrying" : "",
+                                        err);
+                        break;
+                }
+rl_not_mapped_enoent:
+                /*
+                 * The buffer is in a hole or out of bounds.  We need to fill
+                 * the hole, unless the buffer is in a cluster which is not
+                 * touched by the write, in which case we just leave the buffer
+                 * unmapped.  This can only happen when the cluster size is
+                 * less than the page cache size.
+                 */
+                if (unlikely(vol->cluster_size < PAGE_CACHE_SIZE)) {
+                        bh_cend = (bh_end + vol->cluster_size - 1) >>
+                                        vol->cluster_size_bits;
+                        if ((bh_cend <= cpos || bh_cpos >= cend)) {
+                                bh->b_blocknr = -1;
+                                /*
+                                 * If the buffer is uptodate we skip it.  If it
+                                 * is not but the page is uptodate, we can set
+                                 * the buffer uptodate.  If the page is not
+                                 * uptodate, we can clear the buffer and set it
+                                 * uptodate.  Whether this is worthwhile is
+                                 * debatable and this could be removed.
+                                 */
+                                if (PageUptodate(page)) {
+                                        if (!buffer_uptodate(bh))
+                                                set_buffer_uptodate(bh);
+                                } else if (!buffer_uptodate(bh)) {
+                                        u8 *kaddr = kmap_atomic(page, KM_USER0);
+                                        memset(kaddr + bh_offset(bh), 0,
+                                                        blocksize);
+                                        kunmap_atomic(kaddr, KM_USER0);
+                                        flush_dcache_page(page);
+                                        set_buffer_uptodate(bh);
+                                }
+                                continue;
+                        }
+                }
+                /*
+                 * Out of bounds buffer is invalid if it was not really out of
+                 * bounds.
+                 */
+                BUG_ON(lcn != LCN_HOLE);
+                /*
+                 * We need the runlist locked for writing, so if it is locked
+                 * for reading relock it now and retry in case it changed
+                 * whilst we dropped the lock.
+                 */
+                BUG_ON(!rl);
+                if (!rl_write_locked) {
+                        up_read(&ni->runlist.lock);
+                        down_write(&ni->runlist.lock);
+                        rl_write_locked = TRUE;
+                        goto retry_remap;
+                }
+                /* Find the previous last allocated cluster. */
+                BUG_ON(rl->lcn != LCN_HOLE);
+                lcn = -1;
+                rl2 = rl;
+                while (--rl2 >= ni->runlist.rl) {
+                        if (rl2->lcn >= 0) {
+                                lcn = rl2->lcn + rl2->length;
+                                break;
+                        }
+                }
+                rl2 = ntfs_cluster_alloc(vol, bh_cpos, 1, lcn, DATA_ZONE,
+                                FALSE);
+                if (IS_ERR(rl2)) {
+                        err = PTR_ERR(rl2);
+                        ntfs_debug("Failed to allocate cluster, error code %i.",
+                                        err);
+                        break;
+                }
+                lcn = rl2->lcn;
+                rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
+                if (IS_ERR(rl)) {
+                        err = PTR_ERR(rl);
+                        if (err != -ENOMEM)
+                                err = -EIO;
+                        if (ntfs_cluster_free_from_rl(vol, rl2)) {
+                                ntfs_error(vol->sb, "Failed to release "
+                                                "allocated cluster in error "
+                                                "code path.  Run chkdsk to "
+                                                "recover the lost cluster.");
+                                NVolSetErrors(vol);
+                        }
+                        ntfs_free(rl2);
+                        break;
+                }
+                ni->runlist.rl = rl;
+                status.runlist_merged = 1;
+                ntfs_debug("Allocated cluster, lcn 0x%llx.", lcn);
+                /* Map and lock the mft record and get the attribute record. */
+                if (!NInoAttr(ni))
+                        base_ni = ni;
+                else
+                        base_ni = ni->ext.base_ntfs_ino;
+                m = map_mft_record(base_ni);
+                if (IS_ERR(m)) {
+                        err = PTR_ERR(m);
+                        break;
+                }
+                ctx = ntfs_attr_get_search_ctx(base_ni, m);
+                if (unlikely(!ctx)) {
+                        err = -ENOMEM;
+                        unmap_mft_record(base_ni);
+                        break;
+                }
+                status.mft_attr_mapped = 1;
+                err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                                CASE_SENSITIVE, bh_cpos, NULL, 0, ctx);
+                if (unlikely(err)) {
+                        if (err == -ENOENT)
+                                err = -EIO;
+                        break;
+                }
+                m = ctx->mrec;
+                a = ctx->attr;
+                /*
+                 * Find the runlist element with which the attribute extent
+                 * starts.  Note, we cannot use the _attr_ version because we
+                 * have mapped the mft record.  That is ok because we know the
+                 * runlist fragment must be mapped already to have ever gotten
+                 * here, so we can just use the _rl_ version.
+                 */
+                vcn = sle64_to_cpu(a->data.non_resident.lowest_vcn);
+                rl2 = ntfs_rl_find_vcn_nolock(rl, vcn);
+                BUG_ON(!rl2);
+                BUG_ON(!rl2->length);
+                BUG_ON(rl2->lcn < LCN_HOLE);
+                highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
+                /*
+                 * If @highest_vcn is zero, calculate the real highest_vcn
+                 * (which can really be zero).
+                 */
+                if (!highest_vcn)
+                        highest_vcn = (sle64_to_cpu(
+                                        a->data.non_resident.allocated_size) >>
+                                        vol->cluster_size_bits) - 1;
+                /*
+                 * Determine the size of the mapping pairs array for the new
+                 * extent, i.e. the old extent with the hole filled.
+                 */
+                mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, vcn,
+                                highest_vcn);
+                if (unlikely(mp_size <= 0)) {
+                        if (!(err = mp_size))
+                                err = -EIO;
+                        ntfs_debug("Failed to get size for mapping pairs "
+                                        "array, error code %i.", err);
+                        break;
+                }
+                /*
+                 * Resize the attribute record to fit the new mapping pairs
+                 * array.
+                 */
+                attr_rec_len = le32_to_cpu(a->length);
+                err = ntfs_attr_record_resize(m, a, mp_size + le16_to_cpu(
+                                a->data.non_resident.mapping_pairs_offset));
+                if (unlikely(err)) {
+                        BUG_ON(err != -ENOSPC);
+                        // TODO: Deal with this by using the current attribute
+                        // and fill it with as much of the mapping pairs
+                        // array as possible.  Then loop over each attribute
+                        // extent rewriting the mapping pairs arrays as we go
+                        // along and if when we reach the end we have not
+                        // enough space, try to resize the last attribute
+                        // extent and if even that fails, add a new attribute
+                        // extent.
+                        // We could also try to resize at each step in the hope
+                        // that we will not need to rewrite every single extent.
+                        // Note, we may need to decompress some extents to fill
+                        // the runlist as we are walking the extents...
+                        ntfs_error(vol->sb, "Not enough space in the mft "
+                                        "record for the extended attribute "
+                                        "record.  This case is not "
+                                        "implemented yet.");
+                        err = -EOPNOTSUPP;
+                        break ;
+                }
+                status.mp_rebuilt = 1;
+                /*
+                 * Generate the mapping pairs array directly into the attribute
+                 * record.
+                 */
+                err = ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
+                                a->data.non_resident.mapping_pairs_offset),
+                                mp_size, rl2, vcn, highest_vcn, NULL);
+                if (unlikely(err)) {
+                        ntfs_error(vol->sb, "Cannot fill hole in inode 0x%lx, "
+                                        "attribute type 0x%x, because building "
+                                        "the mapping pairs failed with error "
+                                        "code %i.", vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type), err);
+                        err = -EIO;
+                        break;
+                }
+                /* Update the highest_vcn but only if it was not set. */
+                if (unlikely(!a->data.non_resident.highest_vcn))
+                        a->data.non_resident.highest_vcn =
+                                        cpu_to_sle64(highest_vcn);
+                /*
+                 * If the attribute is sparse/compressed, update the compressed
+                 * size in the ntfs_inode structure and the attribute record.
+                 */
+                if (likely(NInoSparse(ni) || NInoCompressed(ni))) {
+                        /*
+                         * If we are not in the first attribute extent, switch
+                         * to it, but first ensure the changes will make it to
+                         * disk later.
+                         */
+                        if (a->data.non_resident.lowest_vcn) {
+                                flush_dcache_mft_record_page(ctx->ntfs_ino);
+                                mark_mft_record_dirty(ctx->ntfs_ino);
+                                ntfs_attr_reinit_search_ctx(ctx);
+                                err = ntfs_attr_lookup(ni->type, ni->name,
+                                                ni->name_len, CASE_SENSITIVE,
+                                                0, NULL, 0, ctx);
+                                if (unlikely(err)) {
+                                        status.attr_switched = 1;
+                                        break;
+                                }
+                                /* @m is not used any more so do not set it. */
+                                a = ctx->attr;
+                        }
+                        write_lock_irqsave(&ni->size_lock, flags);
+                        ni->itype.compressed.size += vol->cluster_size;
+                        a->data.non_resident.compressed_size =
+                                        cpu_to_sle64(ni->itype.compressed.size);
+                        write_unlock_irqrestore(&ni->size_lock, flags);
+                }
+                /* Ensure the changes make it to disk. */
+                flush_dcache_mft_record_page(ctx->ntfs_ino);
+                mark_mft_record_dirty(ctx->ntfs_ino);
+                ntfs_attr_put_search_ctx(ctx);
+                unmap_mft_record(base_ni);
+                /* Successfully filled the hole. */
+                status.runlist_merged = 0;
+                status.mft_attr_mapped = 0;
+                status.mp_rebuilt = 0;
+                /* Setup the map cache and use that to deal with the buffer. */
+                was_hole = TRUE;
+                vcn = bh_cpos;
+                vcn_len = 1;
+                lcn_block = lcn << (vol->cluster_size_bits - blocksize_bits);
+                cdelta = 0;
+                /*
+                 * If the number of remaining clusters in the @pages is smaller
+                 * or equal to the number of cached clusters, unlock the
+                 * runlist as the map cache will be used from now on.
+                 */
+                if (likely(vcn + vcn_len >= cend)) {
+                        up_write(&ni->runlist.lock);
+                        rl_write_locked = FALSE;
+                        rl = NULL;
+                }
+                goto map_buffer_cached;
+        } while (bh_pos += blocksize, (bh = bh->b_this_page) != head);
+        /* If there are no errors, do the next page. */
+        if (likely(!err && ++u < nr_pages))
+                goto do_next_page;
+        /* If there are no errors, release the runlist lock if we took it. */
+        if (likely(!err)) {
+                if (unlikely(rl_write_locked)) {
+                        up_write(&ni->runlist.lock);
+                        rl_write_locked = FALSE;
+                } else if (unlikely(rl))
+                        up_read(&ni->runlist.lock);
+                rl = NULL;
+        }
+        /* If we issued read requests, let them complete. */
+        read_lock_irqsave(&ni->size_lock, flags);
+        initialized_size = ni->initialized_size;
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        while (wait_bh > wait) {
+                bh = *--wait_bh;
+                wait_on_buffer(bh);
+                if (likely(buffer_uptodate(bh))) {
+                        page = bh->b_page;
+                        bh_pos = ((s64)page->index << PAGE_CACHE_SHIFT) +
+                                        bh_offset(bh);
+                        /*
+                         * If the buffer overflows the initialized size, need
+                         * to zero the overflowing region.
+                         */
+                        if (unlikely(bh_pos + blocksize > initialized_size)) {
+                                u8 *kaddr;
+                                int ofs = 0;
+                                if (likely(bh_pos < initialized_size))
+                                        ofs = initialized_size - bh_pos;
+                                kaddr = kmap_atomic(page, KM_USER0);
+                                memset(kaddr + bh_offset(bh) + ofs, 0,
+                                                blocksize - ofs);
+                                kunmap_atomic(kaddr, KM_USER0);
+                                flush_dcache_page(page);
+                        }
+                } else /* if (unlikely(!buffer_uptodate(bh))) */
+                        err = -EIO;
+        }
+        if (likely(!err)) {
+                /* Clear buffer_new on all buffers. */
+                u = 0;
+                do {
+                        bh = head = page_buffers(pages[u]);
+                        do {
+                                if (buffer_new(bh))
+                                        clear_buffer_new(bh);
+                        } while ((bh = bh->b_this_page) != head);
+                } while (++u < nr_pages);
+                ntfs_debug("Done.");
+                return err;
+        }
+        if (status.attr_switched) {
+                /* Get back to the attribute extent we modified. */
+                ntfs_attr_reinit_search_ctx(ctx);
+                if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                                CASE_SENSITIVE, bh_cpos, NULL, 0, ctx)) {
+                        ntfs_error(vol->sb, "Failed to find required "
+                                        "attribute extent of attribute in "
+                                        "error code path.  Run chkdsk to "
+                                        "recover.");
+                        write_lock_irqsave(&ni->size_lock, flags);
+                        ni->itype.compressed.size += vol->cluster_size;
+                        write_unlock_irqrestore(&ni->size_lock, flags);
+                        flush_dcache_mft_record_page(ctx->ntfs_ino);
+                        mark_mft_record_dirty(ctx->ntfs_ino);
+                        /*
+                         * The only thing that is now wrong is the compressed
+                         * size of the base attribute extent which chkdsk
+                         * should be able to fix.
+                         */
+                        NVolSetErrors(vol);
+                } else {
+                        m = ctx->mrec;
+                        a = ctx->attr;
+                        status.attr_switched = 0;
+                }
+        }
+        /*
+         * If the runlist has been modified, need to restore it by punching a
+         * hole into it and we then need to deallocate the on-disk cluster as
+         * well.  Note, we only modify the runlist if we are able to generate a
+         * new mapping pairs array, i.e. only when the mapped attribute extent
+         * is not switched.
+         */
+        if (status.runlist_merged && !status.attr_switched) {
+                BUG_ON(!rl_write_locked);
+                /* Make the file cluster we allocated sparse in the runlist. */
+                if (ntfs_rl_punch_nolock(vol, &ni->runlist, bh_cpos, 1)) {
+                        ntfs_error(vol->sb, "Failed to punch hole into "
+                                        "attribute runlist in error code "
+                                        "path.  Run chkdsk to recover the "
+                                        "lost cluster.");
+                        make_bad_inode(vi);
+                        make_bad_inode(VFS_I(base_ni));
+                        NVolSetErrors(vol);
+                } else /* if (success) */ {
+                        status.runlist_merged = 0;
+                        /*
+                         * Deallocate the on-disk cluster we allocated but only
+                         * if we succeeded in punching its vcn out of the
+                         * runlist.
+                         */
+                        down_write(&vol->lcnbmp_lock);
+                        if (ntfs_bitmap_clear_bit(vol->lcnbmp_ino, lcn)) {
+                                ntfs_error(vol->sb, "Failed to release "
+                                                "allocated cluster in error "
+                                                "code path.  Run chkdsk to "
+                                                "recover the lost cluster.");
+                                NVolSetErrors(vol);
+                        }
+                        up_write(&vol->lcnbmp_lock);
+                }
+        }
+        /*
+         * Resize the attribute record to its old size and rebuild the mapping
+         * pairs array.  Note, we only can do this if the runlist has been
+         * restored to its old state which also implies that the mapped
+         * attribute extent is not switched.
+         */
+        if (status.mp_rebuilt && !status.runlist_merged) {
+                if (ntfs_attr_record_resize(m, a, attr_rec_len)) {
+                        ntfs_error(vol->sb, "Failed to restore attribute "
+                                        "record in error code path.  Run "
+                                        "chkdsk to recover.");
+                        make_bad_inode(vi);
+                        make_bad_inode(VFS_I(base_ni));
+                        NVolSetErrors(vol);
+                } else /* if (success) */ {
+                        if (ntfs_mapping_pairs_build(vol, (u8*)a +
+                                        le16_to_cpu(a->data.non_resident.
+                                        mapping_pairs_offset), attr_rec_len -
+                                        le16_to_cpu(a->data.non_resident.
+                                        mapping_pairs_offset), ni->runlist.rl,
+                                        vcn, highest_vcn, NULL)) {
+                                ntfs_error(vol->sb, "Failed to restore "
+                                                "mapping pairs array in error "
+                                                "code path.  Run chkdsk to "
+                                                "recover.");
+                                make_bad_inode(vi);
+                                make_bad_inode(VFS_I(base_ni));
+                                NVolSetErrors(vol);
+                        }
+                        flush_dcache_mft_record_page(ctx->ntfs_ino);
+                        mark_mft_record_dirty(ctx->ntfs_ino);
+                }
+        }
+        /* Release the mft record and the attribute. */
+        if (status.mft_attr_mapped) {
+                ntfs_attr_put_search_ctx(ctx);
+                unmap_mft_record(base_ni);
+        }
+        /* Release the runlist lock. */
+        if (rl_write_locked)
+                up_write(&ni->runlist.lock);
+        else if (rl)
+                up_read(&ni->runlist.lock);
+        /*
+         * Zero out any newly allocated blocks to avoid exposing stale data.
+         * If BH_New is set, we know that the block was newly allocated above
+         * and that it has not been fully zeroed and marked dirty yet.
+         */
+        nr_pages = u;
+        u = 0;
+        end = bh_cpos << vol->cluster_size_bits;
+        do {
+                page = pages[u];
+                bh = head = page_buffers(page);
+                do {
+                        if (u == nr_pages &&
+                                        ((s64)page->index << PAGE_CACHE_SHIFT) +
+                                        bh_offset(bh) >= end)
+                                break;
+                        if (!buffer_new(bh))
+                                continue;
+                        clear_buffer_new(bh);
+                        if (!buffer_uptodate(bh)) {
+                                if (PageUptodate(page))
+                                        set_buffer_uptodate(bh);
+                                else {
+                                        u8 *kaddr = kmap_atomic(page, KM_USER0);
+                                        memset(kaddr + bh_offset(bh), 0,
+                                                        blocksize);
+                                        kunmap_atomic(kaddr, KM_USER0);
+                                        flush_dcache_page(page);
+                                        set_buffer_uptodate(bh);
+                                }
+                        }
+                        mark_buffer_dirty(bh);
+                } while ((bh = bh->b_this_page) != head);
+        } while (++u <= nr_pages);
+        ntfs_error(vol->sb, "Failed.  Returning error code %i.", err);
+        return err;
+}
+/*
+ * Copy as much as we can into the pages and return the number of bytes which
+ * were sucessfully copied.  If a fault is encountered then clear the pages
+ * out to (ofs + bytes) and return the number of bytes which were copied.
+ */
+static inline size_t ntfs_copy_from_user(struct page **pages,
+                unsigned nr_pages, unsigned ofs, const char __user *buf,
+                size_t bytes)
+{
+        struct page **last_page = pages + nr_pages;
+        char *kaddr;
+        size_t total = 0;
+        unsigned len;
+        int left;
+        do {
+                len = PAGE_CACHE_SIZE - ofs;
+                if (len > bytes)
+                        len = bytes;
+                kaddr = kmap_atomic(*pages, KM_USER0);
+                left = __copy_from_user_inatomic(kaddr + ofs, buf, len);
+                kunmap_atomic(kaddr, KM_USER0);
+                if (unlikely(left)) {
+                        /* Do it the slow way. */
+                        kaddr = kmap(*pages);
+                        left = __copy_from_user(kaddr + ofs, buf, len);
+                        kunmap(*pages);
+                        if (unlikely(left))
+                                goto err_out;
+                }
+                total += len;
+                bytes -= len;
+                if (!bytes)
+                        break;
+                buf += len;
+                ofs = 0;
+        } while (++pages < last_page);
+out:
+        return total;
+err_out:
+        total += len - left;
+        /* Zero the rest of the target like __copy_from_user(). */
+        while (++pages < last_page) {
+                bytes -= len;
+                if (!bytes)
+                        break;
+                len = PAGE_CACHE_SIZE;
+                if (len > bytes)
+                        len = bytes;
+                kaddr = kmap_atomic(*pages, KM_USER0);
+                memset(kaddr, 0, len);
+                kunmap_atomic(kaddr, KM_USER0);
+        }
+        goto out;
+}
+static size_t __ntfs_copy_from_user_iovec(char *vaddr,
+                const struct iovec *iov, size_t iov_ofs, size_t bytes)
+{
+        size_t total = 0;
+        while (1) {
+                const char __user *buf = iov->iov_base + iov_ofs;
+                unsigned len;
+                size_t left;
+                len = iov->iov_len - iov_ofs;
+                if (len > bytes)
+                        len = bytes;
+                left = __copy_from_user_inatomic(vaddr, buf, len);
+                total += len;
+                bytes -= len;
+                vaddr += len;
+                if (unlikely(left)) {
+                        /*
+                         * Zero the rest of the target like __copy_from_user().
+                         */
+                        memset(vaddr, 0, bytes);
+                        total -= left;
+                        break;
+                }
+                if (!bytes)
+                        break;
+                iov++;
+                iov_ofs = 0;
+        }
+        return total;
+}
+static inline void ntfs_set_next_iovec(const struct iovec **iovp,
+                size_t *iov_ofsp, size_t bytes)
+{
+        const struct iovec *iov = *iovp;
+        size_t iov_ofs = *iov_ofsp;
+        while (bytes) {
+                unsigned len;
+                len = iov->iov_len - iov_ofs;
+                if (len > bytes)
+                        len = bytes;
+                bytes -= len;
+                iov_ofs += len;
+                if (iov->iov_len == iov_ofs) {
+                        iov++;
+                        iov_ofs = 0;
+                }
+        }
+        *iovp = iov;
+        *iov_ofsp = iov_ofs;
+}
+/*
+ * This has the same side-effects and return value as ntfs_copy_from_user().
+ * The difference is that on a fault we need to memset the remainder of the
+ * pages (out to offset + bytes), to emulate ntfs_copy_from_user()'s
+ * single-segment behaviour.
+ *
+ * We call the same helper (__ntfs_copy_from_user_iovec()) both when atomic and
+ * when not atomic.  This is ok because __ntfs_copy_from_user_iovec() calls
+ * __copy_from_user_inatomic() and it is ok to call this when non-atomic.  In
+ * fact, the only difference between __copy_from_user_inatomic() and
+ * __copy_from_user() is that the latter calls might_sleep().  And on many
+ * architectures __copy_from_user_inatomic() is just defined to
+ * __copy_from_user() so it makes no difference at all on those architectures.
+ */
+static inline size_t ntfs_copy_from_user_iovec(struct page **pages,
+                unsigned nr_pages, unsigned ofs, const struct iovec **iov,
+                size_t *iov_ofs, size_t bytes)
+{
+        struct page **last_page = pages + nr_pages;
+        char *kaddr;
+        size_t copied, len, total = 0;
+        do {
+                len = PAGE_CACHE_SIZE - ofs;
+                if (len > bytes)
+                        len = bytes;
+                kaddr = kmap_atomic(*pages, KM_USER0);
+                copied = __ntfs_copy_from_user_iovec(kaddr + ofs,
+                                *iov, *iov_ofs, len);
+                kunmap_atomic(kaddr, KM_USER0);
+                if (unlikely(copied != len)) {
+                        /* Do it the slow way. */
+                        kaddr = kmap(*pages);
+                        copied = __ntfs_copy_from_user_iovec(kaddr + ofs,
+                                        *iov, *iov_ofs, len);
+                        kunmap(*pages);
+                        if (unlikely(copied != len))
+                                goto err_out;
+                }
+                total += len;
+                bytes -= len;
+                if (!bytes)
+                        break;
+                ntfs_set_next_iovec(iov, iov_ofs, len);
+                ofs = 0;
+        } while (++pages < last_page);
+out:
+        return total;
+err_out:
+        total += copied;
+        /* Zero the rest of the target like __copy_from_user(). */
+        while (++pages < last_page) {
+                bytes -= len;
+                if (!bytes)
+                        break;
+                len = PAGE_CACHE_SIZE;
+                if (len > bytes)
+                        len = bytes;
+                kaddr = kmap_atomic(*pages, KM_USER0);
+                memset(kaddr, 0, len);
+                kunmap_atomic(kaddr, KM_USER0);
+        }
+        goto out;
+}
+static inline void ntfs_flush_dcache_pages(struct page **pages,
+                unsigned nr_pages)
+{
+        BUG_ON(!nr_pages);
+        do {
+                /*
+                 * Warning: Do not do the decrement at the same time as the
+                 * call because flush_dcache_page() is a NULL macro on i386
+                 * and hence the decrement never happens.
+                 */
+                flush_dcache_page(pages[nr_pages]);
+        } while (--nr_pages > 0);
+}
+/**
+ * ntfs_commit_pages_after_non_resident_write - commit the received data
+ * @pages:      array of destination pages
+ * @nr_pages:   number of pages in @pages
+ * @pos:        byte position in file at which the write begins
+ * @bytes:      number of bytes to be written
+ *
+ * See description of ntfs_commit_pages_after_write(), below.
+ */
+static inline int ntfs_commit_pages_after_non_resident_write(
+                struct page **pages, const unsigned nr_pages,
+                s64 pos, size_t bytes)
+{
+        s64 end, initialized_size;
+        struct inode *vi;
+        ntfs_inode *ni, *base_ni;
+        struct buffer_head *bh, *head;
+        ntfs_attr_search_ctx *ctx;
+        MFT_RECORD *m;
+        ATTR_RECORD *a;
+        unsigned long flags;
+        unsigned blocksize, u;
+        int err;
+        vi = pages[0]->mapping->host;
+        ni = NTFS_I(vi);
+        blocksize = 1 << vi->i_blkbits;
+        end = pos + bytes;
+        u = 0;
+        do {
+                s64 bh_pos;
+                struct page *page;
+                BOOL partial;
+                page = pages[u];
+                bh_pos = (s64)page->index << PAGE_CACHE_SHIFT;
+                bh = head = page_buffers(page);
+                partial = FALSE;
+                do {
+                        s64 bh_end;
+                        bh_end = bh_pos + blocksize;
+                        if (bh_end <= pos || bh_pos >= end) {
+                                if (!buffer_uptodate(bh))
+                                        partial = TRUE;
+                        } else {
+                                set_buffer_uptodate(bh);
+                                mark_buffer_dirty(bh);
+                        }
+                } while (bh_pos += blocksize, (bh = bh->b_this_page) != head);
+                /*
+                 * If all buffers are now uptodate but the page is not, set the
+                 * page uptodate.
+                 */
+                if (!partial && !PageUptodate(page))
+                        SetPageUptodate(page);
+        } while (++u < nr_pages);
+        /*
+         * Finally, if we do not need to update initialized_size or i_size we
+         * are finished.
+         */
+        read_lock_irqsave(&ni->size_lock, flags);
+        initialized_size = ni->initialized_size;
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        if (end <= initialized_size) {
+                ntfs_debug("Done.");
+                return 0;
+        }
+        /*
+         * Update initialized_size/i_size as appropriate, both in the inode and
+         * the mft record.
+         */
+        if (!NInoAttr(ni))
+                base_ni = ni;
+        else
+                base_ni = ni->ext.base_ntfs_ino;
+        /* Map, pin, and lock the mft record. */
+        m = map_mft_record(base_ni);
+        if (IS_ERR(m)) {
+                err = PTR_ERR(m);
+                m = NULL;
+                ctx = NULL;
+                goto err_out;
+        }
+        BUG_ON(!NInoNonResident(ni));
+        ctx = ntfs_attr_get_search_ctx(base_ni, m);
+        if (unlikely(!ctx)) {
+                err = -ENOMEM;
+                goto err_out;
+        }
+        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                        CASE_SENSITIVE, 0, NULL, 0, ctx);
+        if (unlikely(err)) {
+                if (err == -ENOENT)
+                        err = -EIO;
+                goto err_out;
+        }
+        a = ctx->attr;
+        BUG_ON(!a->non_resident);
+        write_lock_irqsave(&ni->size_lock, flags);
+        BUG_ON(end > ni->allocated_size);
+        ni->initialized_size = end;
+        a->data.non_resident.initialized_size = cpu_to_sle64(end);
+        if (end > i_size_read(vi)) {
+                i_size_write(vi, end);
+                a->data.non_resident.data_size =
+                                a->data.non_resident.initialized_size;
+        }
+        write_unlock_irqrestore(&ni->size_lock, flags);
+        /* Mark the mft record dirty, so it gets written back. */
+        flush_dcache_mft_record_page(ctx->ntfs_ino);
+        mark_mft_record_dirty(ctx->ntfs_ino);
+        ntfs_attr_put_search_ctx(ctx);
+        unmap_mft_record(base_ni);
+        ntfs_debug("Done.");
+        return 0;
+err_out:
+        if (ctx)
+                ntfs_attr_put_search_ctx(ctx);
+        if (m)
+                unmap_mft_record(base_ni);
+        ntfs_error(vi->i_sb, "Failed to update initialized_size/i_size (error "
+                        "code %i).", err);
+        if (err != -ENOMEM) {
+                NVolSetErrors(ni->vol);
+                make_bad_inode(VFS_I(base_ni));
+                make_bad_inode(vi);
+        }
+        return err;
+}
+/**
+ * ntfs_commit_pages_after_write - commit the received data
+ * @pages:      array of destination pages
+ * @nr_pages:   number of pages in @pages
+ * @pos:        byte position in file at which the write begins
+ * @bytes:      number of bytes to be written
+ *
+ * This is called from ntfs_file_buffered_write() with i_sem held on the inode
+ * (@pages[0]->mapping->host).  There are @nr_pages pages in @pages which are
+ * locked but not kmap()ped.  The source data has already been copied into the
+ * @page.  ntfs_prepare_pages_for_non_resident_write() has been called before
+ * the data was copied (for non-resident attributes only) and it returned
+ * success.
+ *
+ * Need to set uptodate and mark dirty all buffers within the boundary of the
+ * write.  If all buffers in a page are uptodate we set the page uptodate, too.
+ *
+ * Setting the buffers dirty ensures that they get written out later when
+ * ntfs_writepage() is invoked by the VM.
+ *
+ * Finally, we need to update i_size and initialized_size as appropriate both
+ * in the inode and the mft record.
+ *
+ * This is modelled after fs/buffer.c::generic_commit_write(), which marks
+ * buffers uptodate and dirty, sets the page uptodate if all buffers in the
+ * page are uptodate, and updates i_size if the end of io is beyond i_size.  In
+ * that case, it also marks the inode dirty.
+ *
+ * If things have gone as outlined in
+ * ntfs_prepare_pages_for_non_resident_write(), we do not need to do any page
+ * content modifications here for non-resident attributes.  For resident
+ * attributes we need to do the uptodate bringing here which we combine with
+ * the copying into the mft record which means we save one atomic kmap.
+ *
+ * Return 0 on success or -errno on error.
+ */
+static int ntfs_commit_pages_after_write(struct page **pages,
+                const unsigned nr_pages, s64 pos, size_t bytes)
+{
+        s64 end, initialized_size;
+        loff_t i_size;
+        struct inode *vi;
+        ntfs_inode *ni, *base_ni;
+        struct page *page;
+        ntfs_attr_search_ctx *ctx;
+        MFT_RECORD *m;
+        ATTR_RECORD *a;
+        char *kattr, *kaddr;
+        unsigned long flags;
+        u32 attr_len;
+        int err;
+        BUG_ON(!nr_pages);
+        BUG_ON(!pages);
+        page = pages[0];
+        BUG_ON(!page);
+        vi = page->mapping->host;
+        ni = NTFS_I(vi);
+        ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, start page "
+                        "index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
+                        vi->i_ino, ni->type, page->index, nr_pages,
+                        (long long)pos, bytes);
+        if (NInoNonResident(ni))
+                return ntfs_commit_pages_after_non_resident_write(pages,
+                                nr_pages, pos, bytes);
+        BUG_ON(nr_pages > 1);
+        /*
+         * Attribute is resident, implying it is not compressed, encrypted, or
+         * sparse.
+         */
+        if (!NInoAttr(ni))
+                base_ni = ni;
+        else
+                base_ni = ni->ext.base_ntfs_ino;
+        BUG_ON(NInoNonResident(ni));
+        /* Map, pin, and lock the mft record. */
+        m = map_mft_record(base_ni);
+        if (IS_ERR(m)) {
+                err = PTR_ERR(m);
+                m = NULL;
+                ctx = NULL;
+                goto err_out;
+        }
+        ctx = ntfs_attr_get_search_ctx(base_ni, m);
+        if (unlikely(!ctx)) {
+                err = -ENOMEM;
+                goto err_out;
+        }
+        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+                        CASE_SENSITIVE, 0, NULL, 0, ctx);
+        if (unlikely(err)) {
+                if (err == -ENOENT)
+                        err = -EIO;
+                goto err_out;
+        }
+        a = ctx->attr;
+        BUG_ON(a->non_resident);
+        /* The total length of the attribute value. */
+        attr_len = le32_to_cpu(a->data.resident.value_length);
+        i_size = i_size_read(vi);
+        BUG_ON(attr_len != i_size);
+        BUG_ON(pos > attr_len);
+        end = pos + bytes;
+        BUG_ON(end > le32_to_cpu(a->length) -
+                        le16_to_cpu(a->data.resident.value_offset));
+        kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
+        kaddr = kmap_atomic(page, KM_USER0);
+        /* Copy the received data from the page to the mft record. */
+        memcpy(kattr + pos, kaddr + pos, bytes);
+        /* Update the attribute length if necessary. */
+        if (end > attr_len) {
+                attr_len = end;
+                a->data.resident.value_length = cpu_to_le32(attr_len);
+        }
+        /*
+         * If the page is not uptodate, bring the out of bounds area(s)
+         * uptodate by copying data from the mft record to the page.
+         */
+        if (!PageUptodate(page)) {
+                if (pos > 0)
+                        memcpy(kaddr, kattr, pos);
+                if (end < attr_len)
+                        memcpy(kaddr + end, kattr + end, attr_len - end);
+                /* Zero the region outside the end of the attribute value. */
+                memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
+                flush_dcache_page(page);
+                SetPageUptodate(page);
+        }
+        kunmap_atomic(kaddr, KM_USER0);
+        /* Update initialized_size/i_size if necessary. */
+        read_lock_irqsave(&ni->size_lock, flags);
+        initialized_size = ni->initialized_size;
+        BUG_ON(end > ni->allocated_size);
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        BUG_ON(initialized_size != i_size);
+        if (end > initialized_size) {
+                unsigned long flags;
+                write_lock_irqsave(&ni->size_lock, flags);
+                ni->initialized_size = end;
+                i_size_write(vi, end);
+                write_unlock_irqrestore(&ni->size_lock, flags);
+        }
+        /* Mark the mft record dirty, so it gets written back. */
+        flush_dcache_mft_record_page(ctx->ntfs_ino);
+        mark_mft_record_dirty(ctx->ntfs_ino);
+        ntfs_attr_put_search_ctx(ctx);
+        unmap_mft_record(base_ni);
+        ntfs_debug("Done.");
+        return 0;
+err_out:
+        if (err == -ENOMEM) {
+                ntfs_warning(vi->i_sb, "Error allocating memory required to "
+                                "commit the write.");
+                if (PageUptodate(page)) {
+                        ntfs_warning(vi->i_sb, "Page is uptodate, setting "
+                                        "dirty so the write will be retried "
+                                        "later on by the VM.");
+                        /*
+                         * Put the page on mapping->dirty_pages, but leave its
+                         * buffers' dirty state as-is.
+                         */
+                        __set_page_dirty_nobuffers(page);
+                        err = 0;
+                } else
+                        ntfs_error(vi->i_sb, "Page is not uptodate.  Written "
+                                        "data has been lost.");
+        } else {
+                ntfs_error(vi->i_sb, "Resident attribute commit write failed "
+                                "with error %i.", err);
+                NVolSetErrors(ni->vol);
+                make_bad_inode(VFS_I(base_ni));
+                make_bad_inode(vi);
+        }
+        if (ctx)
+                ntfs_attr_put_search_ctx(ctx);
+        if (m)
+                unmap_mft_record(base_ni);
+        return err;
+}
+/**
+ * ntfs_file_buffered_write -
+ *
+ * Locking: The vfs is holding ->i_sem on the inode.
+ */
+static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
+                const struct iovec *iov, unsigned long nr_segs,
+                loff_t pos, loff_t *ppos, size_t count)
+{
+        struct file *file = iocb->ki_filp;
+        struct address_space *mapping = file->f_mapping;
+        struct inode *vi = mapping->host;
+        ntfs_inode *ni = NTFS_I(vi);
+        ntfs_volume *vol = ni->vol;
+        struct page *pages[NTFS_MAX_PAGES_PER_CLUSTER];
+        struct page *cached_page = NULL;
+        char __user *buf = NULL;
+        s64 end, ll;
+        VCN last_vcn;
+        LCN lcn;
+        unsigned long flags;
+        size_t bytes, iov_ofs = 0;      /* Offset in the current iovec. */
+        ssize_t status, written;
+        unsigned nr_pages;
+        int err;
+        struct pagevec lru_pvec;
+        ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
+                        "pos 0x%llx, count 0x%lx.",
+                        vi->i_ino, (unsigned)le32_to_cpu(ni->type),
+                        (unsigned long long)pos, (unsigned long)count);
+        if (unlikely(!count))
+                return 0;
+        BUG_ON(NInoMstProtected(ni));
+        /*
+         * If the attribute is not an index root and it is encrypted or
+         * compressed, we cannot write to it yet.  Note we need to check for
+         * AT_INDEX_ALLOCATION since this is the type of both directory and
+         * index inodes.
+         */
+        if (ni->type != AT_INDEX_ALLOCATION) {
+                /* If file is encrypted, deny access, just like NT4. */
+                if (NInoEncrypted(ni)) {
+                        /*
+                         * Reminder for later: Encrypted files are _always_
+                         * non-resident so that the content can always be
+                         * encrypted.
+                         */
+                        ntfs_debug("Denying write access to encrypted file.");
+                        return -EACCES;
+                }
+                if (NInoCompressed(ni)) {
+                        /* Only unnamed $DATA attribute can be compressed. */
+                        BUG_ON(ni->type != AT_DATA);
+                        BUG_ON(ni->name_len);
+                        /*
+                         * Reminder for later: If resident, the data is not
+                         * actually compressed.  Only on the switch to non-
+                         * resident does compression kick in.  This is in
+                         * contrast to encrypted files (see above).
+                         */
+                        ntfs_error(vi->i_sb, "Writing to compressed files is "
+                                        "not implemented yet.  Sorry.");
+                        return -EOPNOTSUPP;
+                }
+        }
+        /*
+         * If a previous ntfs_truncate() failed, repeat it and abort if it
+         * fails again.
+         */
+        if (unlikely(NInoTruncateFailed(ni))) {
+                down_write(&vi->i_alloc_sem);
+                err = ntfs_truncate(vi);
+                up_write(&vi->i_alloc_sem);
+                if (err || NInoTruncateFailed(ni)) {
+                        if (!err)
+                                err = -EIO;
+                        ntfs_error(vol->sb, "Cannot perform write to inode "
+                                        "0x%lx, attribute type 0x%x, because "
+                                        "ntfs_truncate() failed (error code "
+                                        "%i).", vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type), err);
+                        return err;
+                }
+        }
+        /* The first byte after the write. */
+        end = pos + count;
+        /*
+         * If the write goes beyond the allocated size, extend the allocation
+         * to cover the whole of the write, rounded up to the nearest cluster.
+         */
+        read_lock_irqsave(&ni->size_lock, flags);
+        ll = ni->allocated_size;
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        if (end > ll) {
+                /* Extend the allocation without changing the data size. */
+                ll = ntfs_attr_extend_allocation(ni, end, -1, pos);
+                if (likely(ll >= 0)) {
+                        BUG_ON(pos >= ll);
+                        /* If the extension was partial truncate the write. */
+                        if (end > ll) {
+                                ntfs_debug("Truncating write to inode 0x%lx, "
+                                                "attribute type 0x%x, because "
+                                                "the allocation was only "
+                                                "partially extended.",
+                                                vi->i_ino, (unsigned)
+                                                le32_to_cpu(ni->type));
+                                end = ll;
+                                count = ll - pos;
+                        }
+                } else {
+                        err = ll;
+                        read_lock_irqsave(&ni->size_lock, flags);
+                        ll = ni->allocated_size;
+                        read_unlock_irqrestore(&ni->size_lock, flags);
+                        /* Perform a partial write if possible or fail. */
+                        if (pos < ll) {
+                                ntfs_debug("Truncating write to inode 0x%lx, "
+                                                "attribute type 0x%x, because "
+                                                "extending the allocation "
+                                                "failed (error code %i).",
+                                                vi->i_ino, (unsigned)
+                                                le32_to_cpu(ni->type), err);
+                                end = ll;
+                                count = ll - pos;
+                        } else {
+                                ntfs_error(vol->sb, "Cannot perform write to "
+                                                "inode 0x%lx, attribute type "
+                                                "0x%x, because extending the "
+                                                "allocation failed (error "
+                                                "code %i).", vi->i_ino,
+                                                (unsigned)
+                                                le32_to_cpu(ni->type), err);
+                                return err;
+                        }
+                }
+        }
+        pagevec_init(&lru_pvec, 0);
+        written = 0;
+        /*
+         * If the write starts beyond the initialized size, extend it up to the
+         * beginning of the write and initialize all non-sparse space between
+         * the old initialized size and the new one.  This automatically also
+         * increments the vfs inode->i_size to keep it above or equal to the
+         * initialized_size.
+         */
+        read_lock_irqsave(&ni->size_lock, flags);
+        ll = ni->initialized_size;
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        if (pos > ll) {
+                err = ntfs_attr_extend_initialized(ni, pos, &cached_page,
+                                &lru_pvec);
+                if (err < 0) {
+                        ntfs_error(vol->sb, "Cannot perform write to inode "
+                                        "0x%lx, attribute type 0x%x, because "
+                                        "extending the initialized size "
+                                        "failed (error code %i).", vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type), err);
+                        status = err;
+                        goto err_out;
+                }
+        }
+        /*
+         * Determine the number of pages per cluster for non-resident
+         * attributes.
+         */
+        nr_pages = 1;
+        if (vol->cluster_size > PAGE_CACHE_SIZE && NInoNonResident(ni))
+                nr_pages = vol->cluster_size >> PAGE_CACHE_SHIFT;
+        /* Finally, perform the actual write. */
+        last_vcn = -1;
+        if (likely(nr_segs == 1))
+                buf = iov->iov_base;
+        do {
+                VCN vcn;
+                pgoff_t idx, start_idx;
+                unsigned ofs, do_pages, u;
+                size_t copied;
+                start_idx = idx = pos >> PAGE_CACHE_SHIFT;
+                ofs = pos & ~PAGE_CACHE_MASK;
+                bytes = PAGE_CACHE_SIZE - ofs;
+                do_pages = 1;
+                if (nr_pages > 1) {
+                        vcn = pos >> vol->cluster_size_bits;
+                        if (vcn != last_vcn) {
+                                last_vcn = vcn;
+                                /*
+                                 * Get the lcn of the vcn the write is in.  If
+                                 * it is a hole, need to lock down all pages in
+                                 * the cluster.
+                                 */
+                                down_read(&ni->runlist.lock);
+                                lcn = ntfs_attr_vcn_to_lcn_nolock(ni, pos >>
+                                                vol->cluster_size_bits, FALSE);
+                                up_read(&ni->runlist.lock);
+                                if (unlikely(lcn < LCN_HOLE)) {
+                                        status = -EIO;
+                                        if (lcn == LCN_ENOMEM)
+                                                status = -ENOMEM;
+                                        else
+                                                ntfs_error(vol->sb, "Cannot "
+                                                        "perform write to "
+                                                        "inode 0x%lx, "
+                                                        "attribute type 0x%x, "
+                                                        "because the attribute "
+                                                        "is corrupt.",
+                                                        vi->i_ino, (unsigned)
+                                                        le32_to_cpu(ni->type));
+                                        break;
+                                }
+                                if (lcn == LCN_HOLE) {
+                                        start_idx = (pos & ~(s64)
+                                                        vol->cluster_size_mask)
+                                                        >> PAGE_CACHE_SHIFT;
+                                        bytes = vol->cluster_size - (pos &
+                                                        vol->cluster_size_mask);
+                                        do_pages = nr_pages;
+                                }
+                        }
+                }
+                if (bytes > count)
+                        bytes = count;
+                /*
+                 * Bring in the user page(s) that we will copy from _first_.
+                 * Otherwise there is a nasty deadlock on copying from the same
+                 * page(s) as we are writing to, without it/them being marked
+                 * up-to-date.  Note, at present there is nothing to stop the
+                 * pages being swapped out between us bringing them into memory
+                 * and doing the actual copying.
+                 */
+                if (likely(nr_segs == 1))
+                        ntfs_fault_in_pages_readable(buf, bytes);
+                else
+                        ntfs_fault_in_pages_readable_iovec(iov, iov_ofs, bytes);
+                /* Get and lock @do_pages starting at index @start_idx. */
+                status = __ntfs_grab_cache_pages(mapping, start_idx, do_pages,
+                                pages, &cached_page, &lru_pvec);
+                if (unlikely(status))
+                        break;
+                /*
+                 * For non-resident attributes, we need to fill any holes with
+                 * actual clusters and ensure all bufferes are mapped.  We also
+                 * need to bring uptodate any buffers that are only partially
+                 * being written to.
+                 */
+                if (NInoNonResident(ni)) {
+                        status = ntfs_prepare_pages_for_non_resident_write(
+                                        pages, do_pages, pos, bytes);
+                        if (unlikely(status)) {
+                                loff_t i_size;
+                                do {
+                                        unlock_page(pages[--do_pages]);
+                                        page_cache_release(pages[do_pages]);
+                                } while (do_pages);
+                                /*
+                                 * The write preparation may have instantiated
+                                 * allocated space outside i_size.  Trim this
+                                 * off again.  We can ignore any errors in this
+                                 * case as we will just be waisting a bit of
+                                 * allocated space, which is not a disaster.
+                                 */
+                                i_size = i_size_read(vi);
+                                if (pos + bytes > i_size)
+                                        vmtruncate(vi, i_size);
+                                break;
+                        }
+                }
+                u = (pos >> PAGE_CACHE_SHIFT) - pages[0]->index;
+                if (likely(nr_segs == 1)) {
+                        copied = ntfs_copy_from_user(pages + u, do_pages - u,
+                                        ofs, buf, bytes);
+                        buf += copied;
+                } else
+                        copied = ntfs_copy_from_user_iovec(pages + u,
+                                        do_pages - u, ofs, &iov, &iov_ofs,
+                                        bytes);
+                ntfs_flush_dcache_pages(pages + u, do_pages - u);
+                status = ntfs_commit_pages_after_write(pages, do_pages, pos,
+                                bytes);
+                if (likely(!status)) {
+                        written += copied;
+                        count -= copied;
+                        pos += copied;
+                        if (unlikely(copied != bytes))
+                                status = -EFAULT;
+                }
+                do {
+                        unlock_page(pages[--do_pages]);
+                        mark_page_accessed(pages[do_pages]);
+                        page_cache_release(pages[do_pages]);
+                } while (do_pages);
+                if (unlikely(status))
+                        break;
+                balance_dirty_pages_ratelimited(mapping);
+                cond_resched();
+        } while (count);
+err_out:
+        *ppos = pos;
+        if (cached_page)
+                page_cache_release(cached_page);
+        /* For now, when the user asks for O_SYNC, we actually give O_DSYNC. */
+        if (likely(!status)) {
+                if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(vi))) {
+                        if (!mapping->a_ops->writepage || !is_sync_kiocb(iocb))
+                                status = generic_osync_inode(vi, mapping,
+                                                OSYNC_METADATA|OSYNC_DATA);
+                }
+        }
+        pagevec_lru_add(&lru_pvec);
+        ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
+                        written ? "written" : "status", (unsigned long)written,
+                        (long)status);
+        return written ? written : status;
+}
+/**
+ * ntfs_file_aio_write_nolock -
+ */
+static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
+                const struct iovec *iov, unsigned long nr_segs, loff_t *ppos)
+{
+        struct file *file = iocb->ki_filp;
+        struct address_space *mapping = file->f_mapping;
+        struct inode *inode = mapping->host;
+        loff_t pos;
+        unsigned long seg;
+        size_t count;           /* after file limit checks */
+        ssize_t written, err;
+        count = 0;
+        for (seg = 0; seg < nr_segs; seg++) {
+                const struct iovec *iv = &iov[seg];
+                /*
+                 * If any segment has a negative length, or the cumulative
+                 * length ever wraps negative then return -EINVAL.
+                 */
+                count += iv->iov_len;
+                if (unlikely((ssize_t)(count|iv->iov_len) < 0))
+                        return -EINVAL;
+                if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
+                        continue;
+                if (!seg)
+                        return -EFAULT;
+                nr_segs = seg;
+                count -= iv->iov_len;   /* This segment is no good */
+                break;
+        }
+        pos = *ppos;
+        vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+        /* We can write back this queue in page reclaim. */
+        current->backing_dev_info = mapping->backing_dev_info;
+        written = 0;
+        err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
+        if (err)
+                goto out;
+        if (!count)
+                goto out;
+        err = remove_suid(file->f_dentry);
+        if (err)
+                goto out;
+        inode_update_time(inode, 1);
+        written = ntfs_file_buffered_write(iocb, iov, nr_segs, pos, ppos,
+                        count);
+out:
+        current->backing_dev_info = NULL;
+        return written ? written : err;
+}
+/**
+ * ntfs_file_aio_write -
+ */
+static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const char __user *buf,
+                size_t count, loff_t pos)
+{
+        struct file *file = iocb->ki_filp;
+        struct address_space *mapping = file->f_mapping;
+        struct inode *inode = mapping->host;
+        ssize_t ret;
+        struct iovec local_iov = { .iov_base = (void __user *)buf,
+                                   .iov_len = count };
+        BUG_ON(iocb->ki_pos != pos);
+        down(&inode->i_sem);
+        ret = ntfs_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos);
+        up(&inode->i_sem);
+        if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+                int err = sync_page_range(inode, mapping, pos, ret);
+                if (err < 0)
+                        ret = err;
+        }
+        return ret;
+}
+/**
+ * ntfs_file_writev -
+ *
+ * Basically the same as generic_file_writev() except that it ends up calling
+ * ntfs_file_aio_write_nolock() instead of __generic_file_aio_write_nolock().
+ */
+static ssize_t ntfs_file_writev(struct file *file, const struct iovec *iov,
+                unsigned long nr_segs, loff_t *ppos)
+{
+        struct address_space *mapping = file->f_mapping;
+        struct inode *inode = mapping->host;
+        struct kiocb kiocb;
+        ssize_t ret;
+        down(&inode->i_sem);
+        init_sync_kiocb(&kiocb, file);
+        ret = ntfs_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
+        if (ret == -EIOCBQUEUED)
+                ret = wait_on_sync_kiocb(&kiocb);
+        up(&inode->i_sem);
+        if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+                int err = sync_page_range(inode, mapping, *ppos - ret, ret);
+                if (err < 0)
+                        ret = err;
+        }
+        return ret;
+}
+/**
+ * ntfs_file_write - simple wrapper for ntfs_file_writev()
+ */
+static ssize_t ntfs_file_write(struct file *file, const char __user *buf,
+                size_t count, loff_t *ppos)
+{
+        struct iovec local_iov = { .iov_base = (void __user *)buf,
+                                   .iov_len = count };
+        return ntfs_file_writev(file, &local_iov, 1, ppos);
+}
+/**
 * ntfs_file_fsync - sync a file to disk
 * @filp:       file to be synced
 * @dentry:     dentry describing the file to sync
@@ -113,39 +2305,39 @@ static int ntfs_file_fsync(struct file *filp, struct dentry *dentry,
 #endif /* NTFS_RW */
 struct file_operations ntfs_file_ops = {
-        .llseek         = generic_file_llseek,    /* Seek inside file. */
+        .llseek         = generic_file_llseek,   /* Seek inside file. */
-        .read           = generic_file_read,      /* Read from file. */
+        .read           = generic_file_read,     /* Read from file. */
-        .aio_read       = generic_file_aio_read,  /* Async read from file. */
+        .aio_read       = generic_file_aio_read, /* Async read from file. */
-        .readv          = generic_file_readv,     /* Read from file. */
+        .readv          = generic_file_readv,    /* Read from file. */
 #ifdef NTFS_RW
-        .write          = generic_file_write,     /* Write to file. */
+        .write          = ntfs_file_write,       /* Write to file. */
-        .aio_write      = generic_file_aio_write, /* Async write to file. */
+        .aio_write      = ntfs_file_aio_write,   /* Async write to file. */
-        .writev         = generic_file_writev,    /* Write to file. */
+        .writev         = ntfs_file_writev,      /* Write to file. */
-        /*.release      = ,*/                     /* Last file is closed.  See
+        /*.release      = ,*/                    /* Last file is closed.  See
-                                                     fs/ext2/file.c::
+                                                    fs/ext2/file.c::
-                                                     ext2_release_file() for
+                                                    ext2_release_file() for
-                                                     how to use this to discard
+                                                    how to use this to discard
-                                                     preallocated space for
+                                                    preallocated space for
-                                                     write opened files. */
+                                                    write opened files. */
-        .fsync          = ntfs_file_fsync,        /* Sync a file to disk. */
+        .fsync          = ntfs_file_fsync,       /* Sync a file to disk. */
-        /*.aio_fsync    = ,*/                     /* Sync all outstanding async
+        /*.aio_fsync    = ,*/                    /* Sync all outstanding async
-                                                     i/o operations on a
+                                                    i/o operations on a
-                                                     kiocb. */
+                                                    kiocb. */
 #endif /* NTFS_RW */
-        /*.ioctl        = ,*/                     /* Perform function on the
+        /*.ioctl        = ,*/                    /* Perform function on the
-                                                     mounted filesystem. */
+                                                    mounted filesystem. */
-        .mmap           = generic_file_mmap,      /* Mmap file. */
+        .mmap           = generic_file_mmap,     /* Mmap file. */
-        .open           = ntfs_file_open,         /* Open file. */
+        .open           = ntfs_file_open,        /* Open file. */
-        .sendfile       = generic_file_sendfile,  /* Zero-copy data send with
+        .sendfile       = generic_file_sendfile, /* Zero-copy data send with
-                                                     the data source being on
+                                                    the data source being on
-                                                     the ntfs partition.  We
+                                                    the ntfs partition.  We do
-                                                     do not need to care about
+                                                    not need to care about the
-                                                     the data destination. */
+                                                    data destination. */
-        /*.sendpage     = ,*/                     /* Zero-copy data send with
+        /*.sendpage     = ,*/                    /* Zero-copy data send with
-                                                     the data destination being
+                                                    the data destination being
-                                                     on the ntfs partition.  We
+                                                    on the ntfs partition.  We
-                                                     do not need to care about
+                                                    do not need to care about
-                                                     the data source. */
+                                                    the data source. */
 };
 struct inode_operations ntfs_file_inode_ops = {
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 7ec045131808..b24f4c4b2c5c 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -30,6 +30,7 @@
 #include "debug.h"
 #include "inode.h"
 #include "attrib.h"
+#include "lcnalloc.h"
 #include "malloc.h"
 #include "mft.h"
 #include "time.h"
@@ -2291,11 +2292,16 @@ int ntfs_show_options(struct seq_file *sf, struct vfsmount *mnt)
 #ifdef NTFS_RW
+static const char *es = "  Leaving inconsistent metadata.  Unmount and run "
+                "chkdsk.";
 /**
 * ntfs_truncate - called when the i_size of an ntfs inode is changed
 * @vi:         inode for which the i_size was changed
 *
- * We do not support i_size changes yet.
+ * We only support i_size changes for normal files at present, i.e. not
+ * compressed and not encrypted.  This is enforced in ntfs_setattr(), see
+ * below.
 *
 * The kernel guarantees that @vi is a regular file (S_ISREG() is true) and
 * that the change is allowed.
@@ -2306,80 +2312,499 @@ int ntfs_show_options(struct seq_file *sf, struct vfsmount *mnt)
 * Returns 0 on success or -errno on error.
 *
 * Called with ->i_sem held.  In all but one case ->i_alloc_sem is held for
- * writing.  The only case where ->i_alloc_sem is not held is
+ * writing.  The only case in the kernel where ->i_alloc_sem is not held is
 * mm/filemap.c::generic_file_buffered_write() where vmtruncate() is called
- * with the current i_size as the offset which means that it is a noop as far
+ * with the current i_size as the offset.  The analogous place in NTFS is in
- * as ntfs_truncate() is concerned.
+ * fs/ntfs/file.c::ntfs_file_buffered_write() where we call vmtruncate() again
+ * without holding ->i_alloc_sem.
 */
 int ntfs_truncate(struct inode *vi)
 {
-        ntfs_inode *ni = NTFS_I(vi);
+        s64 new_size, old_size, nr_freed, new_alloc_size, old_alloc_size;
+        VCN highest_vcn;
+        unsigned long flags;
+        ntfs_inode *base_ni, *ni = NTFS_I(vi);
        ntfs_volume *vol = ni->vol;
        ntfs_attr_search_ctx *ctx;
        MFT_RECORD *m;
        ATTR_RECORD *a;
        const char *te = "  Leaving file length out of sync with i_size.";
-        int err;
+        int err, mp_size, size_change, alloc_change;
+        u32 attr_len;
        ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
        BUG_ON(NInoAttr(ni));
+        BUG_ON(S_ISDIR(vi->i_mode));
+        BUG_ON(NInoMstProtected(ni));
        BUG_ON(ni->nr_extents < 0);
-        m = map_mft_record(ni);
+retry_truncate:
+        /*
+         * Lock the runlist for writing and map the mft record to ensure it is
+         * safe to mess with the attribute runlist and sizes.
+         */
+        down_write(&ni->runlist.lock);
+        if (!NInoAttr(ni))
+                base_ni = ni;
+        else
+                base_ni = ni->ext.base_ntfs_ino;
+        m = map_mft_record(base_ni);
        if (IS_ERR(m)) {
                err = PTR_ERR(m);
                ntfs_error(vi->i_sb, "Failed to map mft record for inode 0x%lx "
                                "(error code %d).%s", vi->i_ino, err, te);
                ctx = NULL;
                m = NULL;
-                goto err_out;
+                goto old_bad_out;
        }
-        ctx = ntfs_attr_get_search_ctx(ni, m);
+        ctx = ntfs_attr_get_search_ctx(base_ni, m);
        if (unlikely(!ctx)) {
                ntfs_error(vi->i_sb, "Failed to allocate a search context for "
                                "inode 0x%lx (not enough memory).%s",
                                vi->i_ino, te);
                err = -ENOMEM;
-                goto err_out;
+                goto old_bad_out;
        }
        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
                        CASE_SENSITIVE, 0, NULL, 0, ctx);
        if (unlikely(err)) {
-                if (err == -ENOENT)
+                if (err == -ENOENT) {
                        ntfs_error(vi->i_sb, "Open attribute is missing from "
                                        "mft record.  Inode 0x%lx is corrupt.  "
-                                        "Run chkdsk.", vi->i_ino);
+                                        "Run chkdsk.%s", vi->i_ino, te);
-                else
+                        err = -EIO;
+                } else
                        ntfs_error(vi->i_sb, "Failed to lookup attribute in "
-                                        "inode 0x%lx (error code %d).",
+                                        "inode 0x%lx (error code %d).%s",
-                                        vi->i_ino, err);
+                                        vi->i_ino, err, te);
-                goto err_out;
+                goto old_bad_out;
        }
+        m = ctx->mrec;
        a = ctx->attr;
-        /* If the size has not changed there is nothing to do. */
+        /*
-        if (ntfs_attr_size(a) == i_size_read(vi))
+         * The i_size of the vfs inode is the new size for the attribute value.
-                goto done;
+         */
-        // TODO: Implement the truncate...
+        new_size = i_size_read(vi);
-        ntfs_error(vi->i_sb, "Inode size has changed but this is not "
+        /* The current size of the attribute value is the old size. */
-                        "implemented yet.  Resetting inode size to old value. "
+        old_size = ntfs_attr_size(a);
-                        " This is most likely a bug in the ntfs driver!");
+        /* Calculate the new allocated size. */
-        i_size_write(vi, ntfs_attr_size(a)); 
+        if (NInoNonResident(ni))
-done:
+                new_alloc_size = (new_size + vol->cluster_size - 1) &
+                                ~(s64)vol->cluster_size_mask;
+        else
+                new_alloc_size = (new_size + 7) & ~7;
+        /* The current allocated size is the old allocated size. */
+        read_lock_irqsave(&ni->size_lock, flags);
+        old_alloc_size = ni->allocated_size;
+        read_unlock_irqrestore(&ni->size_lock, flags);
+        /*
+         * The change in the file size.  This will be 0 if no change, >0 if the
+         * size is growing, and <0 if the size is shrinking.
+         */
+        size_change = -1;
+        if (new_size - old_size >= 0) {
+                size_change = 1;
+                if (new_size == old_size)
+                        size_change = 0;
+        }
+        /* As above for the allocated size. */
+        alloc_change = -1;
+        if (new_alloc_size - old_alloc_size >= 0) {
+                alloc_change = 1;
+                if (new_alloc_size == old_alloc_size)
+                        alloc_change = 0;
+        }
+        /*
+         * If neither the size nor the allocation are being changed there is
+         * nothing to do.
+         */
+        if (!size_change && !alloc_change)
+                goto unm_done;
+        /* If the size is changing, check if new size is allowed in $AttrDef. */
+        if (size_change) {
+                err = ntfs_attr_size_bounds_check(vol, ni->type, new_size);
+                if (unlikely(err)) {
+                        if (err == -ERANGE) {
+                                ntfs_error(vol->sb, "Truncate would cause the "
+                                                "inode 0x%lx to %simum size "
+                                                "for its attribute type "
+                                                "(0x%x).  Aborting truncate.",
+                                                vi->i_ino,
+                                                new_size > old_size ? "exceed "
+                                                "the max" : "go under the min",
+                                                le32_to_cpu(ni->type));
+                                err = -EFBIG;
+                        } else {
+                                ntfs_error(vol->sb, "Inode 0x%lx has unknown "
+                                                "attribute type 0x%x.  "
+                                                "Aborting truncate.",
+                                                vi->i_ino,
+                                                le32_to_cpu(ni->type));
+                                err = -EIO;
+                        }
+                        /* Reset the vfs inode size to the old size. */
+                        i_size_write(vi, old_size);
+                        goto err_out;
+                }
+        }
+        if (NInoCompressed(ni) || NInoEncrypted(ni)) {
+                ntfs_warning(vi->i_sb, "Changes in inode size are not "
+                                "supported yet for %s files, ignoring.",
+                                NInoCompressed(ni) ? "compressed" :
+                                "encrypted");
+                err = -EOPNOTSUPP;
+                goto bad_out;
+        }
+        if (a->non_resident)
+                goto do_non_resident_truncate;
+        BUG_ON(NInoNonResident(ni));
+        /* Resize the attribute record to best fit the new attribute size. */
+        if (new_size < vol->mft_record_size &&
+                        !ntfs_resident_attr_value_resize(m, a, new_size)) {
+                unsigned long flags;
+                /* The resize succeeded! */
+                flush_dcache_mft_record_page(ctx->ntfs_ino);
+                mark_mft_record_dirty(ctx->ntfs_ino);
+                write_lock_irqsave(&ni->size_lock, flags);
+                /* Update the sizes in the ntfs inode and all is done. */
+                ni->allocated_size = le32_to_cpu(a->length) -
+                                le16_to_cpu(a->data.resident.value_offset);
+                /*
+                 * Note ntfs_resident_attr_value_resize() has already done any
+                 * necessary data clearing in the attribute record.  When the
+                 * file is being shrunk vmtruncate() will already have cleared
+                 * the top part of the last partial page, i.e. since this is
+                 * the resident case this is the page with index 0.  However,
+                 * when the file is being expanded, the page cache page data
+                 * between the old data_size, i.e. old_size, and the new_size
+                 * has not been zeroed.  Fortunately, we do not need to zero it
+                 * either since on one hand it will either already be zero due
+                 * to both readpage and writepage clearing partial page data
+                 * beyond i_size in which case there is nothing to do or in the
+                 * case of the file being mmap()ped at the same time, POSIX
+                 * specifies that the behaviour is unspecified thus we do not
+                 * have to do anything.  This means that in our implementation
+                 * in the rare case that the file is mmap()ped and a write
+                 * occured into the mmap()ped region just beyond the file size
+                 * and writepage has not yet been called to write out the page
+                 * (which would clear the area beyond the file size) and we now
+                 * extend the file size to incorporate this dirty region
+                 * outside the file size, a write of the page would result in
+                 * this data being written to disk instead of being cleared.
+                 * Given both POSIX and the Linux mmap(2) man page specify that
+                 * this corner case is undefined, we choose to leave it like
+                 * that as this is much simpler for us as we cannot lock the
+                 * relevant page now since we are holding too many ntfs locks
+                 * which would result in a lock reversal deadlock.
+                 */
+                ni->initialized_size = new_size;
+                write_unlock_irqrestore(&ni->size_lock, flags);
+                goto unm_done;
+        }
+        /* If the above resize failed, this must be an attribute extension. */
+        BUG_ON(size_change < 0);
+        /*
+         * We have to drop all the locks so we can call
+         * ntfs_attr_make_non_resident().  This could be optimised by try-
+         * locking the first page cache page and only if that fails dropping
+         * the locks, locking the page, and redoing all the locking and
+         * lookups.  While this would be a huge optimisation, it is not worth
+         * it as this is definitely a slow code path as it only ever can happen
+         * once for any given file.
+         */
        ntfs_attr_put_search_ctx(ctx);
-        unmap_mft_record(ni);
+        unmap_mft_record(base_ni);
-        NInoClearTruncateFailed(ni);
+        up_write(&ni->runlist.lock);
-        ntfs_debug("Done.");
+        /*
-        return 0;
+         * Not enough space in the mft record, try to make the attribute
-err_out:
+         * non-resident and if successful restart the truncation process.
-        if (err != -ENOMEM) {
+         */
+        err = ntfs_attr_make_non_resident(ni, old_size);
+        if (likely(!err))
+                goto retry_truncate;
+        /*
+         * Could not make non-resident.  If this is due to this not being
+         * permitted for this attribute type or there not being enough space,
+         * try to make other attributes non-resident.  Otherwise fail.
+         */
+        if (unlikely(err != -EPERM && err != -ENOSPC)) {
+                ntfs_error(vol->sb, "Cannot truncate inode 0x%lx, attribute "
+                                "type 0x%x, because the conversion from "
+                                "resident to non-resident attribute failed "
+                                "with error code %i.", vi->i_ino,
+                                (unsigned)le32_to_cpu(ni->type), err);
+                if (err != -ENOMEM)
+                        err = -EIO;
+                goto conv_err_out;
+        }
+        /* TODO: Not implemented from here, abort. */
+        if (err == -ENOSPC)
+                ntfs_error(vol->sb, "Not enough space in the mft record/on "
+                                "disk for the non-resident attribute value.  "
+                                "This case is not implemented yet.");
+        else /* if (err == -EPERM) */
+                ntfs_error(vol->sb, "This attribute type may not be "
+                                "non-resident.  This case is not implemented "
+                                "yet.");
+        err = -EOPNOTSUPP;
+        goto conv_err_out;
+#if 0
+        // TODO: Attempt to make other attributes non-resident.
+        if (!err)
+                goto do_resident_extend;
+        /*
+         * Both the attribute list attribute and the standard information
+         * attribute must remain in the base inode.  Thus, if this is one of
+         * these attributes, we have to try to move other attributes out into
+         * extent mft records instead.
+         */
+        if (ni->type == AT_ATTRIBUTE_LIST ||
+                        ni->type == AT_STANDARD_INFORMATION) {
+                // TODO: Attempt to move other attributes into extent mft
+                // records.
+                err = -EOPNOTSUPP;
+                if (!err)
+                        goto do_resident_extend;
+                goto err_out;
+        }
+        // TODO: Attempt to move this attribute to an extent mft record, but
+        // only if it is not already the only attribute in an mft record in
+        // which case there would be nothing to gain.
+        err = -EOPNOTSUPP;
+        if (!err)
+                goto do_resident_extend;
+        /* There is nothing we can do to make enough space. )-: */
+        goto err_out;
+#endif
+do_non_resident_truncate:
+        BUG_ON(!NInoNonResident(ni));
+        if (alloc_change < 0) {
+                highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
+                if (highest_vcn > 0 &&
+                                old_alloc_size >> vol->cluster_size_bits >
+                                highest_vcn + 1) {
+                        /*
+                         * This attribute has multiple extents.  Not yet
+                         * supported.
+                         */
+                        ntfs_error(vol->sb, "Cannot truncate inode 0x%lx, "
+                                        "attribute type 0x%x, because the "
+                                        "attribute is highly fragmented (it "
+                                        "consists of multiple extents) and "
+                                        "this case is not implemented yet.",
+                                        vi->i_ino,
+                                        (unsigned)le32_to_cpu(ni->type));
+                        err = -EOPNOTSUPP;
+                        goto bad_out;
+                }
+        }
+        /*
+         * If the size is shrinking, need to reduce the initialized_size and
+         * the data_size before reducing the allocation.
+         */
+        if (size_change < 0) {
+                /*
+                 * Make the valid size smaller (i_size is already up-to-date).
+                 */
+                write_lock_irqsave(&ni->size_lock, flags);
+                if (new_size < ni->initialized_size) {
+                        ni->initialized_size = new_size;
+                        a->data.non_resident.initialized_size =
+                                        cpu_to_sle64(new_size);
+                }
+                a->data.non_resident.data_size = cpu_to_sle64(new_size);
+                write_unlock_irqrestore(&ni->size_lock, flags);
+                flush_dcache_mft_record_page(ctx->ntfs_ino);
+                mark_mft_record_dirty(ctx->ntfs_ino);
+                /* If the allocated size is not changing, we are done. */
+                if (!alloc_change)
+                        goto unm_done;
+                /*
+                 * If the size is shrinking it makes no sense for the
+                 * allocation to be growing.
+                 */
+                BUG_ON(alloc_change > 0);
+        } else /* if (size_change >= 0) */ {
+                /*
+                 * The file size is growing or staying the same but the
+                 * allocation can be shrinking, growing or staying the same.
+                 */
+                if (alloc_change > 0) {
+                        /*
+                         * We need to extend the allocation and possibly update
+                         * the data size.  If we are updating the data size,
+                         * since we are not touching the initialized_size we do
+                         * not need to worry about the actual data on disk.
+                         * And as far as the page cache is concerned, there
+                         * will be no pages beyond the old data size and any
+                         * partial region in the last page between the old and
+                         * new data size (or the end of the page if the new
+                         * data size is outside the page) does not need to be
+                         * modified as explained above for the resident
+                         * attribute truncate case.  To do this, we simply drop
+                         * the locks we hold and leave all the work to our
+                         * friendly helper ntfs_attr_extend_allocation().
+                         */
+                        ntfs_attr_put_search_ctx(ctx);
+                        unmap_mft_record(base_ni);
+                        up_write(&ni->runlist.lock);
+                        err = ntfs_attr_extend_allocation(ni, new_size,
+                                        size_change > 0 ? new_size : -1, -1);
+                        /*
+                         * ntfs_attr_extend_allocation() will have done error
+                         * output already.
+                         */
+                        goto done;
+                }
+                if (!alloc_change)
+                        goto alloc_done;
+        }
+        /* alloc_change < 0 */
+        /* Free the clusters. */
+        nr_freed = ntfs_cluster_free(ni, new_alloc_size >>
+                        vol->cluster_size_bits, -1, ctx);
+        m = ctx->mrec;
+        a = ctx->attr;
+        if (unlikely(nr_freed < 0)) {
+                ntfs_error(vol->sb, "Failed to release cluster(s) (error code "
+                                "%lli).  Unmount and run chkdsk to recover "
+                                "the lost cluster(s).", (long long)nr_freed);
                NVolSetErrors(vol);
+                nr_freed = 0;
+        }
+        /* Truncate the runlist. */
+        err = ntfs_rl_truncate_nolock(vol, &ni->runlist,
+                        new_alloc_size >> vol->cluster_size_bits);
+        /*
+         * If the runlist truncation failed and/or the search context is no
+         * longer valid, we cannot resize the attribute record or build the
+         * mapping pairs array thus we mark the inode bad so that no access to
+         * the freed clusters can happen.
+         */
+        if (unlikely(err || IS_ERR(m))) {
+                ntfs_error(vol->sb, "Failed to %s (error code %li).%s",
+                                IS_ERR(m) ?
+                                "restore attribute search context" :
+                                "truncate attribute runlist",
+                                IS_ERR(m) ? PTR_ERR(m) : err, es);
+                err = -EIO;
+                goto bad_out;
+        }
+        /* Get the size for the shrunk mapping pairs array for the runlist. */
+        mp_size = ntfs_get_size_for_mapping_pairs(vol, ni->runlist.rl, 0, -1);
+        if (unlikely(mp_size <= 0)) {
+                ntfs_error(vol->sb, "Cannot shrink allocation of inode 0x%lx, "
+                                "attribute type 0x%x, because determining the "
+                                "size for the mapping pairs failed with error "
+                                "code %i.%s", vi->i_ino,
+                                (unsigned)le32_to_cpu(ni->type), mp_size, es);
+                err = -EIO;
+                goto bad_out;
+        }
+        /*
+         * Shrink the attribute record for the new mapping pairs array.  Note,
+         * this cannot fail since we are making the attribute smaller thus by
+         * definition there is enough space to do so.
+         */
+        attr_len = le32_to_cpu(a->length);
+        err = ntfs_attr_record_resize(m, a, mp_size +
+                        le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
+        BUG_ON(err);
+        /*
+         * Generate the mapping pairs array directly into the attribute record.
+         */
+        err = ntfs_mapping_pairs_build(vol, (u8*)a +
+                        le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
+                        mp_size, ni->runlist.rl, 0, -1, NULL);
+        if (unlikely(err)) {
+                ntfs_error(vol->sb, "Cannot shrink allocation of inode 0x%lx, "
+                                "attribute type 0x%x, because building the "
+                                "mapping pairs failed with error code %i.%s",
+                                vi->i_ino, (unsigned)le32_to_cpu(ni->type),
+                                err, es);
+                err = -EIO;
+                goto bad_out;
+        }
+        /* Update the allocated/compressed size as well as the highest vcn. */
+        a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
+                        vol->cluster_size_bits) - 1);
+        write_lock_irqsave(&ni->size_lock, flags);
+        ni->allocated_size = new_alloc_size;
+        a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
+        if (NInoSparse(ni) || NInoCompressed(ni)) {
+                if (nr_freed) {
+                        ni->itype.compressed.size -= nr_freed <<
+                                        vol->cluster_size_bits;
+                        BUG_ON(ni->itype.compressed.size < 0);
+                        a->data.non_resident.compressed_size = cpu_to_sle64(
+                                        ni->itype.compressed.size);
+                        vi->i_blocks = ni->itype.compressed.size >> 9;
+                }
+        } else
+                vi->i_blocks = new_alloc_size >> 9;
+        write_unlock_irqrestore(&ni->size_lock, flags);
+        /*
+         * We have shrunk the allocation.  If this is a shrinking truncate we
+         * have already dealt with the initialized_size and the data_size above
+         * and we are done.  If the truncate is only changing the allocation
+         * and not the data_size, we are also done.  If this is an extending
+         * truncate, need to extend the data_size now which is ensured by the
+         * fact that @size_change is positive.
+         */
+alloc_done:
+        /*
+         * If the size is growing, need to update it now.  If it is shrinking,
+         * we have already updated it above (before the allocation change).
+         */
+        if (size_change > 0)
+                a->data.non_resident.data_size = cpu_to_sle64(new_size);
+        /* Ensure the modified mft record is written out. */
+        flush_dcache_mft_record_page(ctx->ntfs_ino);
+        mark_mft_record_dirty(ctx->ntfs_ino);
+unm_done:
+        ntfs_attr_put_search_ctx(ctx);
+        unmap_mft_record(base_ni);
+        up_write(&ni->runlist.lock);
+done:
+        /* Update the mtime and ctime on the base inode. */
+        inode_update_time(VFS_I(base_ni), 1);
+        if (likely(!err)) {
+                NInoClearTruncateFailed(ni);
+                ntfs_debug("Done.");
+        }
+        return err;
+old_bad_out:
+        old_size = -1;
+bad_out:
+        if (err != -ENOMEM && err != -EOPNOTSUPP) {
                make_bad_inode(vi);
+                make_bad_inode(VFS_I(base_ni));
+                NVolSetErrors(vol);
        }
+        if (err != -EOPNOTSUPP)
+                NInoSetTruncateFailed(ni);
+        else if (old_size >= 0)
+                i_size_write(vi, old_size);
+err_out:
        if (ctx)
                ntfs_attr_put_search_ctx(ctx);
        if (m)
-                unmap_mft_record(ni);
+                unmap_mft_record(base_ni);
-        NInoSetTruncateFailed(ni);
+        up_write(&ni->runlist.lock);
+out:
+        ntfs_debug("Failed.  Returning error code %i.", err);
        return err;
+conv_err_out:
+        if (err != -ENOMEM && err != -EOPNOTSUPP) {
+                make_bad_inode(vi);
+                make_bad_inode(VFS_I(base_ni));
+                NVolSetErrors(vol);
+        }
+        if (err != -EOPNOTSUPP)
+                NInoSetTruncateFailed(ni);
+        else
+                i_size_write(vi, old_size);
+        goto out;
 }
 /**
@@ -2420,8 +2845,7 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr)
        err = inode_change_ok(vi, attr);
        if (err)
-                return err;
+                goto out;
        /* We do not support NTFS ACLs yet. */
        if (ia_valid & (ATTR_UID | ATTR_GID | ATTR_MODE)) {
                ntfs_warning(vi->i_sb, "Changes in user/group/mode are not "
@@ -2429,14 +2853,22 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr)
                err = -EOPNOTSUPP;
                goto out;
        }
        if (ia_valid & ATTR_SIZE) {
                if (attr->ia_size != i_size_read(vi)) {
-                        ntfs_warning(vi->i_sb, "Changes in inode size are not "
+                        ntfs_inode *ni = NTFS_I(vi);
-                                        "supported yet, ignoring.");
+                        /*
-                        err = -EOPNOTSUPP;
+                         * FIXME: For now we do not support resizing of
-                        // TODO: Implement...
+                         * compressed or encrypted files yet.
-                        // err = vmtruncate(vi, attr->ia_size);
+                         */
+                        if (NInoCompressed(ni) || NInoEncrypted(ni)) {
+                                ntfs_warning(vi->i_sb, "Changes in inode size "
+                                                "are not supported yet for "
+                                                "%s files, ignoring.",
+                                                NInoCompressed(ni) ?
+                                                "compressed" : "encrypted");
+                                err = -EOPNOTSUPP;
+                        } else
+                                err = vmtruncate(vi, attr->ia_size);
                        if (err || ia_valid == ATTR_SIZE)
                                goto out;
                } else {
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
index 5c248d404f05..f5678d5d7919 100644
--- a/fs/ntfs/layout.h
+++ b/fs/ntfs/layout.h
@@ -1021,10 +1021,17 @@ enum {
        FILE_NAME_POSIX         = 0x00,
        /* This is the largest namespace. It is case sensitive and allows all
           Unicode characters except for: '\0' and '/'.  Beware that in
-           WinNT/2k files which eg have the same name except for their case
+           WinNT/2k/2003 by default files which eg have the same name except
-           will not be distinguished by the standard utilities and thus a "del
+           for their case will not be distinguished by the standard utilities
-           filename" will delete both "filename" and "fileName" without
+           and thus a "del filename" will delete both "filename" and "fileName"
-           warning. */
+           without warning.  However if for example Services For Unix (SFU) are
+           installed and the case sensitive option was enabled at installation
+           time, then you can create/access/delete such files.
+           Note that even SFU places restrictions on the filenames beyond the
+           '\0' and '/' and in particular the following set of characters is
+           not allowed: '"', '/', '<', '>', '\'.  All other characters,
+           including the ones no allowed in WIN32 namespace are allowed.
+           Tested with SFU 3.5 (this is now free) running on Windows XP. */
        FILE_NAME_WIN32         = 0x01,
        /* The standard WinNT/2k NTFS long filenames. Case insensitive.  All
           Unicode chars except: '\0', '"', '*', '/', ':', '<', '>', '?', '\',
@@ -2367,7 +2374,9 @@ typedef struct {
 * Extended attribute flags (8-bit).
 */
 enum {
-        NEED_EA = 0x80
+        NEED_EA = 0x80          /* If set the file to which the EA belongs
+                                   cannot be interpreted without understanding
+                                   the associates extended attributes. */
 } __attribute__ ((__packed__));
 typedef u8 EA_FLAGS;
@@ -2375,20 +2384,20 @@ typedef u8 EA_FLAGS;
 /*
 * Attribute: Extended attribute (EA) (0xe0).
 *
- * NOTE: Always non-resident. (Is this true?)
+ * NOTE: Can be resident or non-resident.
 *
 * Like the attribute list and the index buffer list, the EA attribute value is
 * a sequence of EA_ATTR variable length records.
- *
- * FIXME: It appears weird that the EA name is not unicode. Is it true?
 */
 typedef struct {
        le32 next_entry_offset; /* Offset to the next EA_ATTR. */
        EA_FLAGS flags;         /* Flags describing the EA. */
-        u8 ea_name_length;      /* Length of the name of the EA in bytes. */
+        u8 ea_name_length;      /* Length of the name of the EA in bytes
+                                   excluding the '\0' byte terminator. */
        le16 ea_value_length;   /* Byte size of the EA's value. */
-        u8 ea_name[0];          /* Name of the EA. */
+        u8 ea_name[0];          /* Name of the EA.  Note this is ASCII, not
-        u8 ea_value[0];         /* The value of the EA. Immediately follows
+                                   Unicode and it is zero terminated. */
+        u8 ea_value[0];         /* The value of the EA.  Immediately follows
                                   the name. */
 } __attribute__ ((__packed__)) EA_ATTR;
diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c
index 5af3bf0b7eee..29cabf93d2d2 100644
--- a/fs/ntfs/lcnalloc.c
+++ b/fs/ntfs/lcnalloc.c
@@ -76,6 +76,7 @@ int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
 * @count:      number of clusters to allocate
 * @start_lcn:  starting lcn at which to allocate the clusters (or -1 if none)
 * @zone:       zone from which to allocate the clusters
+ * @is_extension:       if TRUE, this is an attribute extension
 *
 * Allocate @count clusters preferably starting at cluster @start_lcn or at the
 * current allocator position if @start_lcn is -1, on the mounted ntfs volume
@@ -86,6 +87,13 @@ int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
 * @start_vcn specifies the vcn of the first allocated cluster.  This makes
 * merging the resulting runlist with the old runlist easier.
 *
+ * If @is_extension is TRUE, the caller is allocating clusters to extend an
+ * attribute and if it is FALSE, the caller is allocating clusters to fill a
+ * hole in an attribute.  Practically the difference is that if @is_extension
+ * is TRUE the returned runlist will be terminated with LCN_ENOENT and if
+ * @is_extension is FALSE the runlist will be terminated with
+ * LCN_RL_NOT_MAPPED.
+ *
 * You need to check the return value with IS_ERR().  If this is false, the
 * function was successful and the return value is a runlist describing the
 * allocated cluster(s).  If IS_ERR() is true, the function failed and
@@ -137,7 +145,8 @@ int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
 */
 runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn,
                const s64 count, const LCN start_lcn,
-                const NTFS_CLUSTER_ALLOCATION_ZONES zone)
+                const NTFS_CLUSTER_ALLOCATION_ZONES zone,
+                const BOOL is_extension)
 {
        LCN zone_start, zone_end, bmp_pos, bmp_initial_pos, last_read_pos, lcn;
        LCN prev_lcn = 0, prev_run_len = 0, mft_zone_size;
@@ -310,7 +319,7 @@ runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn,
                                continue;
                        }
                        bit = 1 << (lcn & 7);
-                        ntfs_debug("bit %i.", bit);
+                        ntfs_debug("bit 0x%x.", bit);
                        /* If the bit is already set, go onto the next one. */
                        if (*byte & bit) {
                                lcn++;
@@ -729,7 +738,7 @@ out:
        /* Add runlist terminator element. */
        if (likely(rl)) {
                rl[rlpos].vcn = rl[rlpos - 1].vcn + rl[rlpos - 1].length;
-                rl[rlpos].lcn = LCN_RL_NOT_MAPPED;
+                rl[rlpos].lcn = is_extension ? LCN_ENOENT : LCN_RL_NOT_MAPPED;
                rl[rlpos].length = 0;
        }
        if (likely(page && !IS_ERR(page))) {
@@ -782,6 +791,7 @@ out:
 * @ni:         ntfs inode whose runlist describes the clusters to free
 * @start_vcn:  vcn in the runlist of @ni at which to start freeing clusters
 * @count:      number of clusters to free or -1 for all clusters
+ * @ctx:        active attribute search context if present or NULL if not
 * @is_rollback:        true if this is a rollback operation
 *
 * Free @count clusters starting at the cluster @start_vcn in the runlist
@@ -791,15 +801,39 @@ out:
 * deallocated.  Thus, to completely free all clusters in a runlist, use
 * @start_vcn = 0 and @count = -1.
 *
+ * If @ctx is specified, it is an active search context of @ni and its base mft
+ * record.  This is needed when __ntfs_cluster_free() encounters unmapped
+ * runlist fragments and allows their mapping.  If you do not have the mft
+ * record mapped, you can specify @ctx as NULL and __ntfs_cluster_free() will
+ * perform the necessary mapping and unmapping.
+ *
+ * Note, __ntfs_cluster_free() saves the state of @ctx on entry and restores it
+ * before returning.  Thus, @ctx will be left pointing to the same attribute on
+ * return as on entry.  However, the actual pointers in @ctx may point to
+ * different memory locations on return, so you must remember to reset any
+ * cached pointers from the @ctx, i.e. after the call to __ntfs_cluster_free(),
+ * you will probably want to do:
+ *      m = ctx->mrec;
+ *      a = ctx->attr;
+ * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
+ * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
+ *
 * @is_rollback should always be FALSE, it is for internal use to rollback
 * errors.  You probably want to use ntfs_cluster_free() instead.
 *
- * Note, ntfs_cluster_free() does not modify the runlist at all, so the caller
+ * Note, __ntfs_cluster_free() does not modify the runlist, so you have to
- * has to deal with it later.
+ * remove from the runlist or mark sparse the freed runs later.
 *
 * Return the number of deallocated clusters (not counting sparse ones) on
 * success and -errno on error.
 *
+ * WARNING: If @ctx is supplied, regardless of whether success or failure is
+ *          returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx
+ *          is no longer valid, i.e. you need to either call
+ *          ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
+ *          In that case PTR_ERR(@ctx->mrec) will give you the error code for
+ *          why the mapping of the old inode failed.
+ *
 * Locking: - The runlist described by @ni must be locked for writing on entry
 *            and is locked on return.  Note the runlist may be modified when
 *            needed runlist fragments need to be mapped.
@@ -807,9 +841,13 @@ out:
 *            on return.
 *          - This function takes the volume lcn bitmap lock for writing and
 *            modifies the bitmap contents.
+ *          - If @ctx is NULL, the base mft record of @ni must not be mapped on
+ *            entry and it will be left unmapped on return.
+ *          - If @ctx is not NULL, the base mft record must be mapped on entry
+ *            and it will be left mapped on return.
 */
 s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, s64 count,
-                const BOOL is_rollback)
+                ntfs_attr_search_ctx *ctx, const BOOL is_rollback)
 {
        s64 delta, to_free, total_freed, real_freed;
        ntfs_volume *vol;
@@ -839,7 +877,7 @@ s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, s64 count,
        total_freed = real_freed = 0;
-        rl = ntfs_attr_find_vcn_nolock(ni, start_vcn, TRUE);
+        rl = ntfs_attr_find_vcn_nolock(ni, start_vcn, ctx);
        if (IS_ERR(rl)) {
                if (!is_rollback)
                        ntfs_error(vol->sb, "Failed to find first runlist "
@@ -893,7 +931,7 @@ s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, s64 count,
                        /* Attempt to map runlist. */
                        vcn = rl->vcn;
-                        rl = ntfs_attr_find_vcn_nolock(ni, vcn, TRUE);
+                        rl = ntfs_attr_find_vcn_nolock(ni, vcn, ctx);
                        if (IS_ERR(rl)) {
                                err = PTR_ERR(rl);
                                if (!is_rollback)
@@ -961,7 +999,7 @@ err_out:
         * If rollback fails, set the volume errors flag, emit an error
         * message, and return the error code.
         */
-        delta = __ntfs_cluster_free(ni, start_vcn, total_freed, TRUE);
+        delta = __ntfs_cluster_free(ni, start_vcn, total_freed, ctx, TRUE);
        if (delta < 0) {
                ntfs_error(vol->sb, "Failed to rollback (error %i).  Leaving "
                                "inconsistent metadata!  Unmount and run "
diff --git a/fs/ntfs/lcnalloc.h b/fs/ntfs/lcnalloc.h
index a6a8827882e7..72cbca7003b2 100644
--- a/fs/ntfs/lcnalloc.h
+++ b/fs/ntfs/lcnalloc.h
@@ -27,6 +27,7 @@
 #include <linux/fs.h>
+#include "attrib.h"
 #include "types.h"
 #include "inode.h"
 #include "runlist.h"
@@ -41,16 +42,18 @@ typedef enum {
 extern runlist_element *ntfs_cluster_alloc(ntfs_volume *vol,
                const VCN start_vcn, const s64 count, const LCN start_lcn,
-                const NTFS_CLUSTER_ALLOCATION_ZONES zone);
+                const NTFS_CLUSTER_ALLOCATION_ZONES zone,
+                const BOOL is_extension);
 extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
-                s64 count, const BOOL is_rollback);
+                s64 count, ntfs_attr_search_ctx *ctx, const BOOL is_rollback);
 /**
 * ntfs_cluster_free - free clusters on an ntfs volume
 * @ni:         ntfs inode whose runlist describes the clusters to free
 * @start_vcn:  vcn in the runlist of @ni at which to start freeing clusters
 * @count:      number of clusters to free or -1 for all clusters
+ * @ctx:        active attribute search context if present or NULL if not
 *
 * Free @count clusters starting at the cluster @start_vcn in the runlist
 * described by the ntfs inode @ni.
@@ -59,12 +62,36 @@ extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
 * deallocated.  Thus, to completely free all clusters in a runlist, use
 * @start_vcn = 0 and @count = -1.
 *
- * Note, ntfs_cluster_free() does not modify the runlist at all, so the caller
+ * If @ctx is specified, it is an active search context of @ni and its base mft
- * has to deal with it later.
+ * record.  This is needed when ntfs_cluster_free() encounters unmapped runlist
+ * fragments and allows their mapping.  If you do not have the mft record
+ * mapped, you can specify @ctx as NULL and ntfs_cluster_free() will perform
+ * the necessary mapping and unmapping.
+ *
+ * Note, ntfs_cluster_free() saves the state of @ctx on entry and restores it
+ * before returning.  Thus, @ctx will be left pointing to the same attribute on
+ * return as on entry.  However, the actual pointers in @ctx may point to
+ * different memory locations on return, so you must remember to reset any
+ * cached pointers from the @ctx, i.e. after the call to ntfs_cluster_free(),
+ * you will probably want to do:
+ *      m = ctx->mrec;
+ *      a = ctx->attr;
+ * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
+ * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
+ *
+ * Note, ntfs_cluster_free() does not modify the runlist, so you have to remove
+ * from the runlist or mark sparse the freed runs later.
 *
 * Return the number of deallocated clusters (not counting sparse ones) on
 * success and -errno on error.
 *
+ * WARNING: If @ctx is supplied, regardless of whether success or failure is
+ *          returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx
+ *          is no longer valid, i.e. you need to either call
+ *          ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
+ *          In that case PTR_ERR(@ctx->mrec) will give you the error code for
+ *          why the mapping of the old inode failed.
+ *
 * Locking: - The runlist described by @ni must be locked for writing on entry
 *            and is locked on return.  Note the runlist may be modified when
 *            needed runlist fragments need to be mapped.
@@ -72,11 +99,15 @@ extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
 *            on return.
 *          - This function takes the volume lcn bitmap lock for writing and
 *            modifies the bitmap contents.
+ *          - If @ctx is NULL, the base mft record of @ni must not be mapped on
+ *            entry and it will be left unmapped on return.
+ *          - If @ctx is not NULL, the base mft record must be mapped on entry
+ *            and it will be left mapped on return.
 */
 static inline s64 ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
-                s64 count)
+                s64 count, ntfs_attr_search_ctx *ctx)
 {
-        return __ntfs_cluster_free(ni, start_vcn, count, FALSE);
+        return __ntfs_cluster_free(ni, start_vcn, count, ctx, FALSE);
 }
 extern int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h
index 590887b943f5..e38e402e4103 100644
--- a/fs/ntfs/malloc.h
+++ b/fs/ntfs/malloc.h
@@ -39,8 +39,7 @@
 * If there was insufficient memory to complete the request, return NULL.
 * Depending on @gfp_mask the allocation may be guaranteed to succeed.
 */
-static inline void *__ntfs_malloc(unsigned long size,
+static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask)
-                gfp_t gfp_mask)
 {
        if (likely(size <= PAGE_SIZE)) {
                BUG_ON(!size);
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index b011369b5956..0c65cbb8c5cf 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -49,7 +49,8 @@ static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni)
        ntfs_volume *vol = ni->vol;
        struct inode *mft_vi = vol->mft_ino;
        struct page *page;
-        unsigned long index, ofs, end_index;
+        unsigned long index, end_index;
+        unsigned ofs;
        BUG_ON(ni->page);
        /*
@@ -1308,7 +1309,7 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
        ll = mftbmp_ni->allocated_size;
        read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
        rl = ntfs_attr_find_vcn_nolock(mftbmp_ni,
-                        (ll - 1) >> vol->cluster_size_bits, TRUE);
+                        (ll - 1) >> vol->cluster_size_bits, NULL);
        if (unlikely(IS_ERR(rl) || !rl->length || rl->lcn < 0)) {
                up_write(&mftbmp_ni->runlist.lock);
                ntfs_error(vol->sb, "Failed to determine last allocated "
@@ -1354,7 +1355,8 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
                up_write(&vol->lcnbmp_lock);
                ntfs_unmap_page(page);
                /* Allocate a cluster from the DATA_ZONE. */
-                rl2 = ntfs_cluster_alloc(vol, rl[1].vcn, 1, lcn, DATA_ZONE);
+                rl2 = ntfs_cluster_alloc(vol, rl[1].vcn, 1, lcn, DATA_ZONE,
+                                TRUE);
                if (IS_ERR(rl2)) {
                        up_write(&mftbmp_ni->runlist.lock);
                        ntfs_error(vol->sb, "Failed to allocate a cluster for "
@@ -1738,7 +1740,7 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
        ll = mft_ni->allocated_size;
        read_unlock_irqrestore(&mft_ni->size_lock, flags);
        rl = ntfs_attr_find_vcn_nolock(mft_ni,
-                        (ll - 1) >> vol->cluster_size_bits, TRUE);
+                        (ll - 1) >> vol->cluster_size_bits, NULL);
        if (unlikely(IS_ERR(rl) || !rl->length || rl->lcn < 0)) {
                up_write(&mft_ni->runlist.lock);
                ntfs_error(vol->sb, "Failed to determine last allocated "
@@ -1779,7 +1781,8 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
                        nr > min_nr ? "default" : "minimal", (long long)nr);
        old_last_vcn = rl[1].vcn;
        do {
-                rl2 = ntfs_cluster_alloc(vol, old_last_vcn, nr, lcn, MFT_ZONE);
+                rl2 = ntfs_cluster_alloc(vol, old_last_vcn, nr, lcn, MFT_ZONE,
+                                TRUE);
                if (likely(!IS_ERR(rl2)))
                        break;
                if (PTR_ERR(rl2) != -ENOSPC || nr == min_nr) {
@@ -1951,20 +1954,21 @@ restore_undo_alloc:
                NVolSetErrors(vol);
                return ret;
        }
-        a = ctx->attr;
+        ctx->attr->data.non_resident.highest_vcn =
-        a->data.non_resident.highest_vcn = cpu_to_sle64(old_last_vcn - 1);
+                        cpu_to_sle64(old_last_vcn - 1);
 undo_alloc:
-        if (ntfs_cluster_free(mft_ni, old_last_vcn, -1) < 0) {
+        if (ntfs_cluster_free(mft_ni, old_last_vcn, -1, ctx) < 0) {
                ntfs_error(vol->sb, "Failed to free clusters from mft data "
                                "attribute.%s", es);
                NVolSetErrors(vol);
        }
+        a = ctx->attr;
        if (ntfs_rl_truncate_nolock(vol, &mft_ni->runlist, old_last_vcn)) {
                ntfs_error(vol->sb, "Failed to truncate mft data attribute "
                                "runlist.%s", es);
                NVolSetErrors(vol);
        }
-        if (mp_rebuilt) {
+        if (mp_rebuilt && !IS_ERR(ctx->mrec)) {
                if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
                                a->data.non_resident.mapping_pairs_offset),
                                old_alen - le16_to_cpu(
@@ -1981,6 +1985,10 @@ undo_alloc:
                }
                flush_dcache_mft_record_page(ctx->ntfs_ino);
                mark_mft_record_dirty(ctx->ntfs_ino);
+        } else if (IS_ERR(ctx->mrec)) {
+                ntfs_error(vol->sb, "Failed to restore attribute search "
+                                "context.%s", es);
+                NVolSetErrors(vol);
        }
        if (ctx)
                ntfs_attr_put_search_ctx(ctx);
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 453d0d51ea4b..6c16db9e1a8a 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -1447,7 +1447,7 @@ not_enabled:
        if (unlikely(i_size_read(tmp_ino) < sizeof(USN_HEADER))) {
                ntfs_error(vol->sb, "Found corrupt $UsnJrnl/$DATA/$Max "
                                "attribute (size is 0x%llx but should be at "
-                                "least 0x%x bytes).", i_size_read(tmp_ino),
+                                "least 0x%zx bytes).", i_size_read(tmp_ino),
                                sizeof(USN_HEADER));
                return FALSE;
        }
diff --git a/include/asm-i386/apic.h b/include/asm-i386/apic.h
index a515e2aed829..8c454aa58ac6 100644
--- a/include/asm-i386/apic.h
+++ b/include/asm-i386/apic.h
@@ -118,8 +118,7 @@ extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
 extern void nmi_watchdog_tick (struct pt_regs * regs);
-extern int APIC_init(void);
+extern int APIC_init_uniprocessor (void);
-extern void APIC_late_time_init(void);
 extern void disable_APIC_timer(void);
 extern void enable_APIC_timer(void);
diff --git a/include/asm-i386/hw_irq.h b/include/asm-i386/hw_irq.h
index 9139b89497a1..622815bf3243 100644
--- a/include/asm-i386/hw_irq.h
+++ b/include/asm-i386/hw_irq.h
@@ -55,7 +55,6 @@ void init_8259A(int aeoi);
 void FASTCALL(send_IPI_self(int vector));
 void init_VISWS_APIC_irqs(void);
 void setup_IO_APIC(void);
-void IO_APIC_late_time_init(void);
 void disable_IO_APIC(void);
 void print_IO_APIC(void);
 int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
diff --git a/include/asm-i386/mach-default/smpboot_hooks.h b/include/asm-i386/mach-default/smpboot_hooks.h
index d7c70c144f9f..7f45f6311059 100644
--- a/include/asm-i386/mach-default/smpboot_hooks.h
+++ b/include/asm-i386/mach-default/smpboot_hooks.h
@@ -1,6 +1,11 @@
 /* two abstractions specific to kernel/smpboot.c, mainly to cater to visws
 * which needs to alter them. */
+static inline void smpboot_clear_io_apic_irqs(void)
+{
+        io_apic_irqs = 0;
+}
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
        CMOS_WRITE(0xa, 0xf);
@@ -27,3 +32,13 @@ static inline void smpboot_restore_warm_reset_vector(void)
        *((volatile long *) phys_to_virt(0x467)) = 0;
 }
+static inline void smpboot_setup_io_apic(void)
+{
+        /*
+         * Here we can be sure that there is an IO-APIC in the system. Let's
+         * go and set it up:
+         */
+        if (!skip_ioapic_setup && nr_ioapics)
+                setup_IO_APIC();
+}
diff --git a/include/asm-i386/mach-visws/smpboot_hooks.h b/include/asm-i386/mach-visws/smpboot_hooks.h
index 14d8e0375f7a..d926471fa359 100644
--- a/include/asm-i386/mach-visws/smpboot_hooks.h
+++ b/include/asm-i386/mach-visws/smpboot_hooks.h
@@ -11,7 +11,14 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 /* for visws do nothing for any of these */
+static inline void smpboot_clear_io_apic_irqs(void)
+{
+}
 static inline void smpboot_restore_warm_reset_vector(void)
 {
 }
+static inline void smpboot_setup_io_apic(void)
+{
+}
diff --git a/include/asm-ppc/ppc_sys.h b/include/asm-ppc/ppc_sys.h
index 549f44843c5e..bba5305c29ed 100644
--- a/include/asm-ppc/ppc_sys.h
+++ b/include/asm-ppc/ppc_sys.h
@@ -18,7 +18,7 @@
 #define __ASM_PPC_SYS_H
 #include <linux/init.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/types.h>
 #if defined(CONFIG_8260)
diff --git a/include/linux/device.h b/include/linux/device.h
index a9e72ac3fb9f..17cbc6db67b4 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -396,32 +396,6 @@ extern struct device * get_device(struct device * dev);
 extern void put_device(struct device * dev);
-/* drivers/base/platform.c */
-struct platform_device {
-        const char      * name;
-        u32             id;
-        struct device   dev;
-        u32             num_resources;
-        struct resource * resource;
-};
-#define to_platform_device(x) container_of((x), struct platform_device, dev)
-extern int platform_device_register(struct platform_device *);
-extern void platform_device_unregister(struct platform_device *);
-extern struct bus_type platform_bus_type;
-extern struct device platform_bus;
-extern struct resource *platform_get_resource(struct platform_device *, unsigned int, unsigned int);
-extern int platform_get_irq(struct platform_device *, unsigned int);
-extern struct resource *platform_get_resource_byname(struct platform_device *, unsigned int, char *);
-extern int platform_get_irq_byname(struct platform_device *, char *);
-extern int platform_add_devices(struct platform_device **, int);
-extern struct platform_device *platform_device_register_simple(char *, unsigned int, struct resource *, unsigned int);
 /* drivers/base/power.c */
 extern void device_shutdown(void);
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
new file mode 100644
index 000000000000..a726225e0afe
--- /dev/null
+++ b/include/linux/platform_device.h
@@ -0,0 +1,40 @@
+/*
+ * platform_device.h - generic, centralized driver model
+ *
+ * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org>
+ *
+ * This file is released under the GPLv2
+ *
+ * See Documentation/driver-model/ for more information.
+ */
+#ifndef _PLATFORM_DEVICE_H_
+#define _PLATFORM_DEVICE_H_
+#include <linux/device.h>
+struct platform_device {
+        const char      * name;
+        u32             id;
+        struct device   dev;
+        u32             num_resources;
+        struct resource * resource;
+};
+#define to_platform_device(x) container_of((x), struct platform_device, dev)
+extern int platform_device_register(struct platform_device *);
+extern void platform_device_unregister(struct platform_device *);
+extern struct bus_type platform_bus_type;
+extern struct device platform_bus;
+extern struct resource *platform_get_resource(struct platform_device *, unsigned int, unsigned int);
+extern int platform_get_irq(struct platform_device *, unsigned int);
+extern struct resource *platform_get_resource_byname(struct platform_device *, unsigned int, char *);
+extern int platform_get_irq_byname(struct platform_device *, char *);
+extern int platform_add_devices(struct platform_device **, int);
+extern struct platform_device *platform_device_register_simple(char *, unsigned int, struct resource *, unsigned int);
+#endif /* _PLATFORM_DEVICE_H_ */
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 317a979b24de..2b799d40d669 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -12,7 +12,7 @@
 #define _LINUX_SERIAL_8250_H
 #include <linux/serial_core.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 /*
 * This is the platform device platform_data structure
diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index 14cb2718cb77..46e3c0bf3c94 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -1055,6 +1055,7 @@ typedef struct {
        unsigned char emu10k2_chip; /* Audigy 1 or Audigy 2. */
        unsigned char ca0102_chip;  /* Audigy 1 or Audigy 2. Not SB Audigy 2 Value. */
        unsigned char ca0108_chip;  /* Audigy 2 Value */
+        unsigned char ca_cardbus_chip; /* Audigy 2 ZS Notebook */
        unsigned char ca0151_chip;  /* P16V */
        unsigned char spk71;        /* Has 7.1 speakers */
        unsigned char sblive51;     /* SBLive! 5.1 - extout 0x11 -> center, 0x12 -> lfe */
diff --git a/init/main.c b/init/main.c
index 4075d97e94b1..f142d4035341 100644
--- a/init/main.c
+++ b/init/main.c
@@ -64,6 +64,10 @@
 #endif
 #endif
+#ifdef CONFIG_X86_LOCAL_APIC
+#include <asm/smp.h>
+#endif
 /*
 * Versions of gcc older than that listed below may actually compile
 * and link okay, but the end product can have subtle run time bugs.
@@ -310,7 +314,14 @@ extern void setup_arch(char **);
 #ifndef CONFIG_SMP
+#ifdef CONFIG_X86_LOCAL_APIC
+static void __init smp_init(void)
+{
+        APIC_init_uniprocessor();
+}
+#else
 #define smp_init()      do { } while (0)
+#endif
 static inline void setup_per_cpu_areas(void) { }
 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index 877bb00d3295..d1f9da498729 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/wait.h>
 #include <linux/delay.h>
diff --git a/sound/core/init.c b/sound/core/init.c
index 59202de1d2ce..41e224986f35 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -28,6 +28,8 @@
 #include <linux/ctype.h>
 #include <linux/pci.h>
 #include <linux/pm.h>
+#include <linux/platform_device.h>
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/info.h>
diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c
index e9cd8e054f25..53aeff0b783a 100644
--- a/sound/pci/emu10k1/emu10k1_main.c
+++ b/sound/pci/emu10k1/emu10k1_main.c
@@ -579,6 +579,30 @@ static int __devinit snd_emu10k1_ecard_init(emu10k1_t * emu)
        return 0;
 }
+static int __devinit snd_emu10k1_cardbus_init(emu10k1_t * emu)
+{
+        unsigned long special_port;
+        unsigned int value;
+        /* Special initialisation routine
+         * before the rest of the IO-Ports become active.
+         */
+        special_port = emu->port + 0x38;
+        value = inl(special_port);
+        outl(0x00d00000, special_port);
+        value = inl(special_port);
+        outl(0x00d00001, special_port);
+        value = inl(special_port);
+        outl(0x00d0005f, special_port);
+        value = inl(special_port);
+        outl(0x00d0007f, special_port);
+        value = inl(special_port);
+        outl(0x0090007f, special_port);
+        value = inl(special_port);
+        return 0;
+}
 /*
 *  Create the EMU10K1 instance
 */
@@ -624,6 +648,16 @@ static emu_chip_details_t emu_chip_details[] = {
         .ca0108_chip = 1,
         .spk71 = 1,
         .ac97_chip = 1} ,
+        /* Audigy 2 ZS Notebook Cardbus card.*/
+        /* Tested by James@superbug.co.uk 30th October 2005 */
+        /* Not working yet, but progressing. */
+        {.vendor = 0x1102, .device = 0x0008, .subsystem = 0x20011102,
+         .driver = "Audigy2", .name = "Audigy 2 ZS Notebook [SB0530]", 
+         .id = "Audigy2",
+         .emu10k2_chip = 1,
+         .ca0108_chip = 1,
+         .ca_cardbus_chip = 1,
+         .spk71 = 1} ,
        {.vendor = 0x1102, .device = 0x0008, 
         .driver = "Audigy2", .name = "Audigy 2 Value [Unknown]", 
         .id = "Audigy2",
@@ -1011,6 +1045,11 @@ int __devinit snd_emu10k1_create(snd_card_t * card,
                        snd_emu10k1_free(emu);
                        return err;
                }
+        } else if (emu->card_capabilities->ca_cardbus_chip) {
+                if ((err = snd_emu10k1_cardbus_init(emu)) < 0) {
+                        snd_emu10k1_free(emu);
+                        return err;
+                }
        } else {
                /* 5.1: Enable the additional AC97 Slots. If the emu10k1 version
                        does not support this, it shouldn't do any harm */